FACT CHECKING ARTIFICIAL INTELLIGENCE: EFFICIENCY VS. ACCURACY

Artificial intelligence or, more specifically, deep learning entered the digital forensics and incident response (DFIR) space originally to help reduce the amount of time investigators spent analyzing cases. It started out with simple skin tone and body shape detection in graphics; this evolved into the ability to place a percentage value on how much skin appeared in a picture or video.

This technology is especially helpful for investigations into sexual assault, child abuse and other graphically disturbing cases. It saves analysts from manually looking at thousands, or in some cases millions, of graphics and video content, speeding review while at the same time (hopefully) preserving their general well-being in the process.

As deep learning technology has evolved, and more models have been developed, we’re faced with an important equation to solve. Which is more important: efficiency or accuracy? In a perfect world we would want both.

MULTIPLE MODELS

If you take a moment to look around, you’ll notice some big companies are making huge, regular investments into developing artificial intelligence models. These models are often freely available for technology companies like Nuix to incorporate into their own products.

I think it’s important to note here that these models, while freely available, are not the latest and greatest technology available. Still, the fact that so many options are available is impressive in its own right.

By default, Nuix uses Google’s Inception V3 model for image classification. This model balances accuracy (greater than 78.1%) with incredible speed. That’s great for cases where time is a critical factor; other options such as the Yahoo Open NSFW model (now known as Tensorflow by Google) and VGG16 work more slowly, relatively speaking, but operate at over 90% accuracy. The VGG16 model has the ability to learn through data ingestion, thus increasing its accuracy over time.

There are models in development that reach 98% accuracy while maintaining the speed of the Inception V3 model, but they have yet to reach our market.

EXPLORING THE MODELS FURTHER

Graphics analysis is an example of artificial narrow intelligence (ANI), which I explored in the last article. ANI is programmed to perform a specific task, freeing humans from performing repetitive and time-consuming work. For anyone who has performed graphic analysis, we know it certainly qualifies as both.

The models we’re talking about are convolutional neural networks (CNN), which detect patterns in images using techniques that analyze small areas of the image in a layered, procedural approach that can detect image edges, ranges of color and other aspects that help the machine classify the image for the analyst.

Explaining how this works is difficult. Thankfully, there are some great explanations online. One is the brilliant Anh H. Reynaolds’ article on Convolutional Neural Networks, which she was gracious enough to give me permission to share in this blog. AI education site DeepLizard also published an explainer video that’s worth watching to learn more. If you have a need-to-know mindset about how things work, both are worth the time investment.

MAKING THE CHOICE

As I did the research for this article, I came to an important conclusion. I can’t definitively say which model or approach is right for your investigative needs. Analysts should take the time to assess the different models and be comfortable with the mix of accuracy and speed they offer. During testimony, a decent attorney may ask what kind of testing and comparison you conducted to choose your machine learning model. It hasn’t happened often, but I have had attorneys surprise me with the homework they do.

I prefer to use real cases and test different models against them, with a couple caveats. First, you should run tests against models that you’ve already run through your trusted methods and technologies – just be prepared to find things you might not have found the first time around. After all, that’s the benefit of using the technology.

Also, testing is unbillable work – it’s just wrong to bill a client for work done while testing a new machine learning model. That doesn’t make the work any less valuable; the time you spend testing your models and documenting the results will have an incredible impact at every stage of your investigation.

Source: https://www.nuix.com/blog/fact-checking-artificial-intelligence-efficiency-vs-accuracy

A Guide to Building and Measuring a Lean Maintenance Strategy

Professional racing is a masterclass in efficiency. Teams don’t just dislike waste—they hate it.

Every millisecond of a pit stop has a purpose. Every component of a car is analyzed to ensure it’s functioning at its best. Strategies are designed to get from point A to point B as fast as possible.

When you translate this mindset to the shop floor, you achieve a lean maintenance strategy. Lean maintenance is the merciless reduction and elimination of waste at every stage of your maintenance program so you can go further, faster, while spending less.

This guide outlines the basics for building and measuring a lean maintenance strategy, including:

  • What is lean maintenance
  • The types of waste in maintenance
  • A formula for creating a lean maintenance strategy
  • Metrics for tracking lean maintenance success

What is lean maintenance?

Like lean manufacturing, lean maintenance is the continual process of identifying, reducing, and removing waste from maintenance activities. Waste is considered anything that doesn’t increase output, decrease costs, or otherwise boost productivity.

There are a lot of examples of waste in maintenance, including:

  • Money spent on a part that becomes obsolete before it’s used
  • Time spent clarifying the details of a maintenance request
  • Effort spent collecting maintenance data you never use

It’s often difficult to spot waste in your maintenance program. That’s why a lean maintenance strategy can’t work without iteration. Iteration is the practice of making small changes over time to find the best way to set up processes and activities. In other words, lean maintenance is not a one-and-done project. It’s a way of thinking and acting that takes years to build.

What are the benefits of lean maintenance?

Odds are, you’ve uttered the words, “What a waste of time,” or “What a waste of money,” in the last couple of weeks. Lean maintenance eliminates those moments. And while there are a thousand things you could be referring to, most of them can be grouped in these four main benefits:

1. Cost savings

A lean maintenance strategy reduces direct costs (labor and resources) and indirect costs (the money you lose in downtime or lost production). For example, you might discover that you can reduce routine maintenance on an asset from once a week to once a month, cutting labor costs by 75% in the process.

Quote from Charles Rogers

2. Efficiency gains

Efficiency is another word for getting more done in less time. Lean maintenance strategies help you find activities and processes that take too much time so you can modify or eliminate them. Voltalia’s maintenance team is a great example of this benefit in practice. The company noticed that one of its service teams spent 40 hours a week driving from the office to an off-site facility. The solution was to build a satellite office near the off-site facility to save time.

3. Maximized potential

When machines and people are not bogged down by unnecessary duties, they can operate at full capacity and perform to the best of their abilities. Tom Dufton’s maintenance team is a perfect example. Tom, a maintenance manager, noticed his skilled maintenance technicians were spending a lot of time assisting production. He used this data to advocate for extra operators so his team could get back to maintaining equipment.

4. Employee engagement

Removing unnecessary work and administrative tasks helps employees feel more engaged with their work. It also gives them time to up-skill and do high-value work. One way this translates into real life is with new maintenance software. If technicians don’t have time to learn the system, your big investment in technology could be for nothing. Eliminating extra tasks elsewhere will give your team time to learn, ask questions, and get used to new technology.

Quote from Bryan Sapot

The three types of waste in maintenance

The first step in eliminating waste is to find it. There are three main areas in a maintenance operation where waste shows up: Environmental, financial, and human potential.

Environmental waste

Environmental waste occurs when raw materials are used inefficiently or disposed of because of inefficient maintenance activities.

Examples of environmental waste in maintenance include:

  • An increase in scrap or rework after equipment maintenance
  • Overuse of fuel by improperly maintained vehicles or unnecessary transportation to and from a worksite
  • Overstocking parts for maintenance due to an outdated inventory purchasing schedule

The impact of environmental waste from maintenance includes:

  • More pollution and trash
  • Higher carbon emissions
  • Low-quality products
  • Increased safety hazards

Some strategies for reducing environmental waste in maintenance include:

  • Frequent inventory cycle counts and just-in-time purchasing to ensure your storeroom isn’t flooded with unused inventory
  • Grouping scheduled maintenance together in one time period to cut down on travel
  • A mandatory check from a second technician after repairs or replacements prior to production to ensure start-ups don’t result in scrap or rework

Financial waste

Financial waste refers to the extra costs from inefficient maintenance. It also includes lost production from unnecessary downtime.

Examples of financial waste in maintenance include:

  • High labor and parts costs from preventive maintenance tasks that are done too frequently
  • Defective products from an asset that was assembled or rebuilt incorrectly
  • Delayed maintenance because technicians had to wait for a part to complete repairs

The impact of financial waste includes:

  • Higher labor and parts costs
  • More capital expenditures
  • Lost revenue
  • Missed opportunities to grow the business

Strategies for becoming leaner include:

  • Identifying tasks in your preventive maintenance schedule that can be eliminated or done less frequently
  • Reducing downtime by finding maintenance work that can be completed while an asset is running
  • Building a FRACAS to address and prevent failure on critical equipment
  • Creating parts kits for critical equipment to speed up repairs and avoid stockouts
  • Setting a regular meeting with production staff to align maintenance with operations and get updates equipment changes

Wasted human potential

Administrative work and unnecessary tasks wear on staff and take them away from specialized tasks only they can do. Burnout, poor morale, and turnover increase, leading to even more waste.

Examples of wasted human potential in maintenance include:

  • Spending hours every day writing, reviewing, and sorting work orders
  • Fixing the same component over and over again
  • Inspecting non-critical equipment with low or nonexistent failure rates
  • Supporting production more than once in a while
  • Searching for parts and supplies in your storeroom

The impact of wasted human potential includes:

  • High employee turnover and loss of organizational knowledge
  • Low wrench time and big backlogs
  • Decreased employee engagement and low adoption of new systems
  • More pencil whipping and less accurate data

Strategies for becoming leaner include:

  • Conduct frequent maintenance team meetings to discuss challenges and brainstorm solutions
  • Automate activities you do frequently, like creating work orders or reports
  • Eliminate or reduce scheduled maintenance that has low rates of follow-up work
  • Train machine operators to do routine maintenance tasks

Creating a lean maintenance mindset

The first step in creating a lean maintenance strategy is to ask the right questions, challenge the way you do things, and be willing to change. This is a lean maintenance mindset and it’s essential to make lean maintenance strategies work long term.

There are four changes that’ll help you shift to a lean maintenance mindset:

1. From small details ? Big picture

There will always be days when your team is reacting to everything—putting out fires, getting last-minute requests, and racing to catch up on backlog.

But a lean maintenance mindset prevents this from becoming the norm. It allows you to build maintenance activities around business and production goals, and deprioritize or eliminate work that doesn’t connect to these goals.

For example, you might spend an hour every week creating a report. But if that report doesn’t help you eliminate waste, that time becomes waste itself. You can either spend time building more useful reports or do other waste-eliminating work.

2. From getting it done ? Collecting data as you go

A lot of maintenance teams operate in survival mode. Complete the task and move on to the next one. No time for any extra steps.

But a lean maintenance strategy hinges on data and taking the time to collect it. Those five extra minutes it takes to complete extra fields on a work order adds up. Having a lean maintenance mindset means building a buffer in your schedule to account for this. It also means everyone knows the importance of these extra steps and isn’t pressured to fudge the numbers to make up for lost time.

3. From big changes ? iterative improvements

Everyone wants to see big wins as quickly as possible. Our brains crave a finish line and tangible results.

But that’s not how lean maintenance works. Instead, it depends on making small, consistent improvements. If done right, it’s a process that’s never truly finished. The best way to tackle this shift is to give yourself and your team small goals and milestones, track progress, and celebrate success.

For example, you might want to cut out unnecessary steps in your scheduled maintenance. In lean maintenance, you’ll examine your work orders once a month to reduce delays and increase wrench time by 10% to 15% across the entire year. It’s crucial to track progress, celebrate it with your team, and get suggestions from technicians on how to keep winning. Technicians will feel a sense of ownership over this metric and will be invested in making progress.

4. From “that’s the way it is” ? “Is this necessary?”

It’s easy to accept the status quo. It’s uncomfortable to change. And it takes a lot of work.

But lean maintenance is all about challenging business as usual. You need to look at everything your team does with a critical eye and make changes if something no longer makes sense. This requires you to adopt a win-or-learn mentality instead of a win-or-fail mindset. Your team will be able to question things without blame or punishment.

For example, you might have done a PM at the same interval for a decade. But everything has changed in that time, from the equipment to the technician doing the work. You need to question how the PM is done as well. Should it be done more or less? Is it even necessary anymore?

Building a lean maintenance strategy

Building a lean maintenance strategy follows a three-step formula:

  1. Understand what you’re currently doing and how you’re doing it
  2. Find areas of waste and eliminate them
  3. Create processes that allow you to do steps one and two over and over again

Step 1: Mapping your maintenance process

This step is about knowing how your team currently operates so you can find the work you’re doing too much of and work you’re not doing enough. This stage involves documenting your maintenance processes, including:

  • Key information about equipment, like criticality and failure modes (this FMEA template can help you collect this data)
  • What inspections and repairs are done, and how often
  • What an emergency looks like and how your team reacts
  • How follow-up or corrective maintenance is created, assigned, and tracked
  • Team meetings and what happens in each one
  • Goal-setting, metrics creation, reporting, and data collection
  • Health, safety, and compliance activities
  • Parts purchasing and storeroom management

Then think about business needs:

Step 2: Identify opportunities for improvement you can act on now

The next step is to find out where you’re spending too much time, money, or energy. Here are a few ways you can spot waste hiding in your processes:

  1. Look at specific processes with members of your maintenance team. Ask them what part of the process takes the most time or where they face challenges when completing work. Use this insight to make activities easier and remove roadblocks.For example, something as small as misidentifying lubrication can lead to wasted time, breakdowns, lost production, and buying too many supplies. Colour-coding lubrication and bearings can eliminate this waste altogether.
  2. Identify tasks that consistently take more time or money than planned and conduct a root cause analysis to find out why. This is more helpful than slashing costs, which can do more harm than good and doesn’t address the real reason for the waste.For example, labor costs for a weekly work order are twice as high as you’ve budgeted. An RCA might find repair times are longer than expected because different technicians are doing the work. You might tweak the schedule to put the same technician on the job so they can familiarize themselves with the work and do it faster.
  3. Audit your planned maintenance work to make it more efficient. We outlined the steps for auditing your PMs in a separate article, but the main takeaway is to question the need for all regular maintenance and the frequency, timing, and resource for each task.For example, a PM might be triggered every 10 days, regardless of how much the asset is used. That can be a waste of time and money. In this situation, try triggering maintenance based on usage, like after every 100 hours of production.
  4. Develop KPIs and metrics around the growth and success of your team. This data will allow you to find wasted potential on your maintenance team.For example, you might track turnover rates or knowledge-sharing opportunities on your team. These stats can uncover complex processes or areas of low productivity that you can correct. The end result is better morale and a higher-performing maintenance team.

Step 3: Build a long-term vision

The core vision of your lean maintenance strategy will always be to improve maintenance bit by bit so it supports business goals. But those goals may change, as will the things you need to improve.

This step is about documenting what you’ve iterated on, the impact of change, and what might come next.

If your iterations produced a negative result, don’t immediately jump back to the way things were. Instead, think about what caused the negative result and see if there’s another iterative improvement. It can take a few tries to get it right.

Choosing metrics for a lean maintenance strategy and tracking success

While every project will have different KPIs and metrics based on your desired outcomes, here are some best-practice metrics to start with:

Environmental wasteFinancial wasteHuman potential waste
Idle timesMaintenance costs (by asset, type, task, etc.)Wrench time
Raw material usageEquipment downtime (planned and unplanned)Employee turnover
Carbon emissions/energy useRate of corrective maintenance after inspectionsTime spent on production support
Travel times to/from sitesResponse rates to breakdowns/emergenciesTime spent on administrative tasks
Raw materials disposal (ie. oil)Clean start-ups after maintenanceNumber of steps in a maintenance process

While this isn’t a comprehensive look at lean maintenance metrics, it does give you a good foundation. And you don’t need to track, measure, and improve every metric. Choose metrics you can realistically collect and ones that connect to production and business goals.

There are two ways to create success plans around each metric and push your lean maintenance strategy forward. The first is to go small. Pick a few metrics and focus on improving specific areas of your maintenance operation. For example, if you want to reduce maintenance costs, choose your top 10 most expensive tasks. Focus on reducing waste in these activities.

The other method is to go broad. Aim for a goal that includes improving several metrics. For example, the ultimate target might be increasing efficiency through better standardization across sites. As part of this project, you can standardize the processes for work requests, reporting, and parts purchasing. There are several metrics you can use to build your project and track its success. This includes the number of steps in a maintenance process, time spent on admin tasks, response rates to breakdowns, and raw materials usage.

It’s essential to share your wins, regardless of your approach. The whole point of lean maintenance is to make small gains that add up to big ones over time. Showing off your success keeps momentum high, increases buy-in, and helps you advocate for more resources to expand your lean maintenance program.

Quote from Jason Afara

Lean maintenance is ongoing

At its core, lean maintenance is about tying maintenance practices to business needs. This will likely ruffle feathers, but it’s a critical step to move maintenance from a cost center to a value driver. And when you do that, the world begins to open up for the maintenance team to be seen as a true business partner.

Source: https://www.fiixsoftware.com/blog/guide-to-creating-a-lean-maintenance-strategy/

Sustainability with Intelligent Information Management

Fighting climate change has undoubtedly become, and rightly so, one of the major drivers of people’s behavior in recent years. At the same time, the importance of sustainability to business has grown too. Whilst companies have to a large extent realized their responsibility on sustainability, the ability to find ways to become ever more environmentally healthy remains a challenge.

Many companies have or are initiating their environmental policies, aligned with an increasing amount of similar requirements from their trading partners, which places demands upon their own internal processes. Thus, sustainability has become a clear factor on B2B sales, not only B2C, As people are placing more and more importance on these topics in their personal lives, green values have become an important factor.  Employee demands for sustainability change are becoming selection criteria when applying for a new job. This places far more emphasis on a prospective employer to show a progressive approach to these demands if they are to persuade new talent to join. 

Challenges for sustainability in Information Management

The role of Information Management is often not the most obvious when it comes to a sustainable way of working. The most notable effect of modern IT systems is clearly their ability to support collaboration over vast distances, i.e., as an enabler of remote work and avoiding unnecessary travel to business meetings. The COVID-19 epidemic has quite naturally sped up the transformation towards remote work, so communications over remote meetings with Teams, Zoom, etc., have pretty much become the norm.

Even though modern remote meeting systems enable communications over remote connections, they are not very good for non-formal communications that we tend to do while in the office or meeting clients or partners on site. The lack of such non-formal communication places even more importance in information management processes, including tools for employees to easily carry out their responsibilities.

Traditionally, managing the company’s business critical documents has been especially reliant on the non-formal communications taking place in the workplace and physical meetings. Finding the correct documents or previous work has been done by asking around in the office. A lot of documentation is simply replicated, with approval processes largely completed by signing paper copies in the office. Thus, better means for document & content management are certainly one challenge that companies need to address, allowing operations with reduced overheads.

Besides providing means for remote work, there are other factors in Information Management systems that affect the total CO2 footprint of a company. As these systems consume substantial amounts of energy, optimizing their usage of computing resources and digital storage would result in a more sustainable workplace. Unfortunately, such issues were largely overlooked when companies initially set up their information management systems and, therefore, offer considerable room for sustainability enhancement.

Sustainability challenges have gained more attention lately. For example, Capgemini has recently produced a report and an article about “Sustainable IT” that outlines very similar conclusions as mentioned here: Sustainable IT Leads to Significant Benefits But Is Still Not a Focus for Most Organizations.

How to make content management an asset for sustainability

State-of-the-art information management usually relies upon Enterprise Content Management (ECM), i.e., managing a company’s documents and the information related to them. The question is: How can a company become more sustainable by improving the way they are using and managing their documentation?

Reflecting the challenges outlined above, the benefits of an ECM system for a company from the sustainability viewpoint can be summarized by the following three points:

  1. A common system for accessing documents and supporting digitized processes.  This approach enables effective collaboration on the documents, typically involving review & approval processes, even when working remotely. Thus, an ECM system can act as an important enabler for remote work, avoiding travel to meet clients and partners whilst enhancing customer service.
  2. Avoiding document copies.  Document version management in ECM systems and the ability to use document links instead of email attachments, reduce storage requirements, thus saving energy required for maintaining multiple document repositories. In practice, this means that the companies can reduce the amount of network drives & other repositories by utilizing modern ECM systems.
  3. Cloud environments enable computing resources to be securely shared. A cloud-based solution is a collaborative resource distributed among many users / clients, thus using processing power much more efficiently than systems relying on the processors in each users’ PCs or company servers. In this manner, using cloud-based ECM solutions can drastically reduce the overall computing power needed for document management.

Improving a company’s sustainability can be seen as a ripple effect: changes that by themselves seem small but combined together make a real difference. Applying modern ECM technology to enable intelligent information management is an important part of striving towards more environmentally healthy way of working.

Source: https://resources.m-files.com/blog/sustainability-with-intelligent-information-management

5 Ways Your Maintenance Team Can Increase Production Efficiency

Every day, meat processing plants need to make sure the metal detectors in their machines are working. It’s a simple check to ensure there’s metal where there should be and no metal where there shouldn’t be.

This process involves running test balls through the machine. It takes about 45 minutes to complete (25 minutes of manual labour and 20 minutes of admin time). It’s routine maintenance— the type most people don’t give a second thought to.

It’s also an example of how tweaking maintenance processes can boost production efficiency. Instead of a manual check, the inspection can be done with an automated test-ball shooter. A button is pressed, the balls roll out on their own, and the task is wrapped up in five minutes. The result is more than 160 hours of extra equipment availability per year.

This is just one example of how companies can leverage maintenance to increase production efficiency. This article outlines several other strategies for bolstering production efficiency using maintenance, including:

  • How maintenance impacts production efficiency
  • Five ways the maintenance team can boost production capacity
  • How to measure the impact of maintenance on production

What is production efficiency?

Production efficiency is a measurement used mostly by manufacturers to determine how well (and how long) a company can keep up with demand. It compares current production rates to expected or standard production rates.

A higher rate of production efficiency delivers three critical outcomes for manufacturers:

  1. Reduced resource usage: Efficient production systems produce the same number of goods with fewer resources
  2. Higher financial margins: Efficient production means higher margins throughout the supply chain
  3.  A better customer experience: Efficient production allows products and services to be regularly and dependably delivered to customers

How to calculate production efficiency

The calculation for production efficiency compares the actual output rate to the standard output rate. The formula can be applied to either manual or automated work.

When it comes to industrial processes, the calculation takes quality into account. Let’s say you produce 50 units in an hour, but only 30 are useable. Your rate of production for that hour is 30 units.

The following formula is used to calculate production efficiency:

Production Efficiency = (Actual Output Rate / Standard Output Rate) x 100

For example, a manufacturing company receives a new order of 100 units. The standard rate of completion for 100 units is 10 hours, or 10 units per hour. However, the company took 12 hours to complete 100 quality units. In this case, the production efficiency formula would look like this:

Actual Output Rate = 100 units / 12 hours (8.3 units/hour)

Standard Output Rate = 100 units / 10 hours (10 units/hour)

Production Efficiency = (8.3 / 10) x 100 (83%)

In this instance, output and productivity levels are below capacity.

Production Efficiency Formula

How maintenance can increase production efficiency

Proper equipment maintenance is essential for increasing production efficiency. It ensures your total effective equipment performance (TEEP) is as high as it can be. Using preventive maintenance to keep assets operating at their best helps to:

  • Limit equipment downtime: If equipment is checked regularly, you can find and fix failures before they cause big breakdowns that disrupt production. Having a solid preventive maintenance schedule also allows you to coordinate with production so planned downtime is done quickly.
  • Establish a corrective action system for failures: Having a strategy to find, analyze, and fix failure (aka a FRACAS) allows you to target recurring issues at their root. You can spot and eliminate problems that impact equipment availability and product quality the most.
  • Coordinate better shift changeovers: Better changeovers between maintenance shifts means communicating the right information to technicians quickly and accurately. This includes a run-down of what work needs to be done, when, and any obstacles that might get in the way of that work.
  • Ensuring standard operating procedures are clear and maintained: SOPs train operators to do routine maintenance so machines can be operated with fewer breakdowns and accidents.
Stewart Fergusson quote

Five things your maintenance team can start doing tomorrow to increase production efficiency

There are a lot of projects that take months or years to complete. But getting quick wins is also crucial for building momentum and proving the value of your maintenance team. So, here are five things your maintenance team can start doing tomorrow to increase production efficiency.

1. Optimize the frequency of your PMs

A preventive maintenance schedule can be a good example of having too much of a good thing. Going overboard on preventive maintenance can affect production efficiency in two ways. You can either waste valuable time preventing non-existent failure. Or you can increase the risk of failure by meddling with a perfectly fine component.

These guidelines can help you find the right balance between too many PMs and too few:

  • Use equipment maintenance logs to track the found failure rate on preventive maintenance tasks. Start with PMs that take the longest to do or cost the most.
  • If a PM leads to regular corrective maintenance, keep it at the same frequency.
  • If a PM rarely identifies failure, try increasing the time between inspections. If the found failure rate exceeds the frequency of the PM, tweak your schedule so it’s better aligned. For example, an inspection might happen every two weeks. But a failure is usually found every six weeks. In this case, plan for the PM to happen every 4-6 weeks instead.
  • If a machine experiences frequent breakdowns between inspections, try shortening maintenance intervals. You can also modify the trigger for maintenance, changing it from a time-based trigger to usage or performance-based trigger.
PDCA model

2. Identify machines that can be maintained while running

Some routine maintenance can be done while a machine is still operating. Find out if there are any assets that can be safely worked on while being used for production. The key word there is ‘safely’. This might mean that some work can’t be done because certain areas of a machine aren’t safely accessible while it’s operating. In this scenario, determine if partial maintenance is possible and if it’ll have a positive impact on the performance of the equipment.

It’s also a good idea to track rotating or spare assets and swap them for production equipment when possible. That allows you to do regular maintenance on these machines without sacrificing productivity.

3. Make equipment capabilities transparent and clear

Create an iron-clad list of instructions for operating equipment and common issues to be aware of. You can use a failure modes and effects analysis (FMEA) to create a list of common failures experienced by each asset. This can also include warning signs for breakdowns.

Having this information clearly outlined and easily accessible gives operators a chance to notice the early signs of failure and notify maintenance before it gets worse. Employees will be empowered to observe and identify any potential problems, and report them accordingly.

4. Use work order data to identify where your team can be more efficient

Work order data can tell you what jobs can get done quicker and how to minimize the risk of asset failure so you can boost production efficiency. Look for these telltale signs of broken processes in your work orders:

  • Unavailable parts and supplies: If this issue is delaying maintenance, review the purchasing process for parts and supplies. That includes making sure your cycle counts are accurate and the threshold for purchase approvals is low enough that inventory can get replenished quickly. You can also create parts kits for frequent repairs or emergency repairs on production equipment so your team can locate and retrieve parts quickly.
  • Misidentified/misdiagnosed problems or missing instructions: Make sure task lists, failure codes, and descriptions are clear. Attach photos, manuals, and other documentation to the work order.
  • Diverted resources resulting from emergency work orders: Emergencies can always be avoided. Analyze your work order data, find tasks that are too big, and break it down into smaller jobs to reduce the risk of major disruptions.
  • Scheduling conflicts with production: See if maintenance can be scheduled while production is happening or if work can be done at an alternate time, like evenings or weekends. You can also consider giving operators minor maintenance responsibilities associated with the work order.
  • Lack of adequate worker skillset: Work order data can show you if the person/people assigned to the work may not have the right skills. Make it very clear on the work request what kind of skills or certifications are necessary for certain maintenance types.

5. Find the biggest obstacles for your team and eliminate them

You can learn a lot from the data that comes from your equipment and work orders. But sometimes, you just have to ask the people who are doing the actual work. They will be able to tell you what barriers they face when completing work. Acting on this information is crucial to continually improve your maintenance processes. All those improvements can add up to a huge boost in production efficiency.

For example, your technicians may spend a lot of time going back and forth from the office to retrieve manuals, asset histories, or other materials that help them on a job. You probably won’t know that just by looking at work order records or wrench time reports. Armed with this information, you can figure out a solution. Maybe that’s creating areas throughout your facility where files can be accessed for nearby assets. Or it could be digitizing those files so they can be accessed through a mobile device.

Here are a few questions to ask your technicians to find any roadblocks:

  • What tasks commonly take you away from a machine?
  • Are information and parts easily accessible? If not, why?
  • What information would help you complete work more efficiently?
  • Are there processes or systems that are hard to use or you think could be improved?
  • Is there anything that frequently keeps you from starting a task on time?

Four ways to measure the impact of maintenance on production efficiency

There are many ways to measure how your maintenance efforts are affecting production efficiency. The most common metrics are the following:

Found failure rate on preventive maintenance

This metric will help you measure how efficient your preventive maintenance schedule is. If your found failure rate is high, it means you’re cutting down on unnecessary maintenance while preventing major disruptions to production.

Unplanned asset downtime (last 90 days)

This number tracks the amount of unplanned equipment downtime and compares it to the previous 90-day period. Because each minute of downtime lowers your production efficiency, this number highlights how maintenance is contributing to healthier, higher-performing assets.

Average time to respond to and repair breakdowns

This stat quantifies all the work you’ve done to prepare for emergencies. Breakdowns will happen. Having a plan to quickly and safely fix these failures will help you reduce the amount of time production is stalled.

Clean start-ups

Compare the amount of useable products coming from the equipment prior to and after maintenance is completed. If the machine is running better after maintenance, it’s proof that your team is increasing production capacity in a meaningful way.

Maintenance has the opportunity to drive production efficiency

Maintenance often gets talked about as an expense. A necessary evil. A cost-center. But the reality is, good maintenance can drive your business forward. When you keep the machines running, you can do more, faster, with less. That means happier customers, a better bottom line, and more profit for everyone in the supply chain. It’s a true win-win-win.

In order to turn maintenance from a cost centre to a business driver, you need to reorient maintenance as a business function and start asking how maintenance can drive production efficiency. From there, a world of opportunity opens up.

Source: https://www.fiixsoftware.com/blog/increase-production-efficiency-with-maintenance/

The perfect formula for aligning operations and maintenance

When operations and maintenance don’t work well together, it can be costly. And messy. Take this story of a food manufacturer as an example.

The facility uses a sheeter, which rolls huge balls of dough. The sheeter needs to be cleaned every day. The production team regularly cleans the machine with water. There’s just one problem with this—water makes the dough clump up and break the machine. As a result, emergency maintenance is the norm.

If this situation feels familiar to you, you’re not alone. It happens thousands of times a day. Operations and maintenance have different goals, motivations, and processes. The result is confusion, frustration, and finger-pointing. This isn’t good for business or employee health.

This article is all about learning how to break that cycle and improve alignment between operations and maintenance, including:

  • Metrics to share
  • How to increase collaboration
  • Tips for building joint processes

Why aligning operations and maintenance should be your top priority

Any manufacturer working to reduce waste is either leading the pack or about to break away from the field. For proof of that, look no further than the fact that manufacturers waste 20% of every dollar they spend.

Waste often appears during production as highlighted by these scary stats (courtesy of automation.com):

  • Large industrial facilities lose over 323 production hours a year to unplanned downtime
  • The average annual cost of downtime is $532,000 per hour or $172 million per plant
  • The cost of downtime for Fortune 500 manufacturers is equal to 8% of annual revenues
Cost of DowntimeAutomotiveFMCG/CPGHeavy IndustryOil & Gas
Unplanned downtime hours per facility each month29252332
Cost per hour of downtime$1,343,400$23,600$187,500$220,000

Huge costs are one thing. But work delays, reactive maintenance, and emergency purchases have a mental and physical toll as well.

Improving the relationship between operations and maintenance is critical to cutting downtime at its source.

“When maintenance and operations are aligned, it allows the business to find issues within the operations,” says Jason Afara, Senior Solutions Engineer at Fiix.

“And then business leaders can make informed decisions on how to correct these issues with the appropriate resources. It turns guessing games and blame games into a unified effort.”

Where to align operations and maintenance processes

Planning scheduled downtime

The definition of efficient maintenance is keeping equipment up and running with as little downtime as possible. Of course, this is easier said than done. The production team has quotas to fill. Anything that gets in the way of hitting that target is a threat. That includes maintenance.

“We would fight operations just to get a little bit of maintenance on a machine,” says Jason, remembering his time as a maintenance manager.

This is all too common and unproductive. Luckily, there are two ways maintenance and operations can create a plan for preventive maintenance that benefits both groups:

  1. Use data to compare the impact of maintenance to the impact of failure
  2. Develop shared processes that reduce the amount of scheduled downtime

The first step is for both teams to understand how their activities affect the performance of equipment. Once again, it’s often more complicated than it sounds.

“This is where maintenance departments usually fail,” says Charles Rogers, a Senior Implementation Consultant at Fiix with over 33 years of experience in maintenance.

“They don’t have data to back up their asks. You have to be able to prove your case and show evidence that if you don’t do maintenance on schedule, there will be much worse consequences at some point—probably sooner than later.”

The best way to align your efforts is to determine the acceptable risk and the consequences of failure as one team. Share information on common failure modes, how often they’re expected to happen, as well as repair times and costs for each one. Compare this to the frequency of scheduled maintenance, the time it takes to do these tasks, and the costs involved.

Quantifying the difference makes it clear that scheduling frequent breaks in production for maintenance is a better way for both teams to hit their goals and avoid big, time-consuming breakdowns.

Creating shared processes between operations and maintenance allows the teams to share and action data. For example, it allows operators to detect small failures and maintenance technicians to respond to them faster. Examples of these processes include:

  • Regular meetings between operations and maintenance leaders to discuss production and preventive maintenance schedules, spec changes on machines, or other updates
  • Quarterly meetings between the two teams to discuss successes, challenges, solutions, and root cause analysis
  • A work request process that enables machine operators to quickly and confidently identify problems and empowers technicians to prioritize and respond to issues with minimal disruption

Creating shared work and clear responsibilities

Any mention of operations and maintenance working together will inevitably lead to talk of total productive maintenance (TPM). You can read a short primer on TPM here, but the idea is that everyone at a company (from technicians to accountants) is responsible and involved in maintenance.

Making operations part of the maintenance process is one of the easiest and most effective ways to begin building a TPM program. Here’s an example of how that might be done:

How operations can be involved chart

The key to making these shared processes successful is to create clear job responsibilities. When people know exactly what they need to do, it helps you:

  • Provide the right training and materials to the right people
  • Create accurate timelines and budgets
  • Test new processes, optimize them, and expand them
  • Pick out bad data and figure out the root cause of it

Start defining clear responsibilities by creating a maintenance type for operators. This allows you to track how much work you’re giving to operations. It also helps you design work order templates for operators so they know what to do and where to go if the scope of work changes.

Building realistic work timelines

When operations and maintenance know how long it takes to get things done, it’s easier to set schedules, budgets, and targets accordingly. It also prevents unseen delays, reduces frustration, and fosters respect between the two teams. But it’s not useful to share maintenance timelines if they aren’t accurate. There are a few strategies to make sure expectations match reality:

  1. Look at equipment maintenance logs. Identify work that frequently takes longer than is expected, and adjust timelines accordingly.
  2. Analyze your work order data to find PMs with a high rate of required follow-up maintenance. Factor that into your brief to the operations team.
  3. Account for parts of a work order that fall outside of actual wrench time. That includes retrieving parts, completing safety procedures, and running tests on machines.

Providing realistic timelines doesn’t always mean your schedules will match up. But it does help operations and maintenance have a conversation about what can be done in the time you have. When determining what maintenance can be sacrificed for production, here are a few questions to ask:

Five questions to help operations and maintenance solve scheduling conflicts

Five ways to build a strong relationship between operations and maintenance

Your operations and maintenance teams might be best friends. Or maybe there’s some tension between them. Whatever the relationship is like, there’s always an opportunity to make it better with a few, simple strategies.

Create multiple ways for the two teams to communicate

Communicating with other teams is often one of the first activities to be abandoned when work gets busy. That’s why there needs to be formal processes in place to maintain the flow of information. Creating dedicated channels for communication might include:

  • Team meetings: Regular meetings create space for everyone’s voice to be heard and to keep challenges, plans, and updates visible
  • Channels to post and see updates: This can be anything from a whiteboard to a WhatsApp group, or a digital work request portal for tracking the status of requests
  • Peer reviews: This is a process where operations and maintenance team members review each other anonymously to identify how they can work better together

There are a few key pieces of information to discuss when you’re working in these channels:

  • Machines updates: Bring up spec changes, potential problems, safety risks, or updates to standard operating procedures
  • Schedules: Talk about upcoming work, risks or conflicts, what’s needed to be successful, and any changes from what was previously discussed
  • Reporting: Review targets, progress, troubling trends, or major successes in your reporting
  • Roadblocks and solutions: Discuss major challenges or questions your team has and collaborate on ways to remove those obstacles
  • Long-term planning: Figure out how both teams can continually improve, including how to better manage budgets, hit long-term goals, and develop new skills

Having a framework for communication between operations and maintenance allows you to turn talk into action. Here are a few ground rules:

  • Focus on solutions, not blame: Finding a solution should be the goal of all your conversations
  • Focus on the collective: Find solutions that work for everyone, instead of trying to win an argument or battle for your team
  • Develop a feedback loop: Create trust by actioning feedback and keeping everyone aware of progress
  • Value consistency, but stay flexible: Commit to communicating, but understand that meetings might need to move around once in a while if an emergency occurs
  • Create an agenda for all meetings: Have a plan for what you’re going to talk about so you can make the most of everyone’s time

Set the same goals

There will be less friction between operations and maintenance when the two teams define success the same way. There might be different ideas on how to get to your goal, but both departments will be moving in the same direction.

“In the worst scenario, these departments are siblings who are constantly fighting,” says Jason.

“But in the best-case scenario, you’re working together to achieve the same goals, celebrating together when you hit those targets, and joining forces to get back on track when you don’t.

There are a few metrics that both operations and maintenance can share responsibility for:

  1. Clean start-ups after maintenance and first-pass yield/first-pass good: Both numbers aim to measure efficiency and waste
  2. Total cost per unit of production: Both operations and maintenance can be accountable for reducing costs while improving quality
  3. Time spent supporting production/maintenance: Tracking the time each team spends supporting the other will help you allocate resources and create effective hiring plans
  4. Unplanned downtime( last 90 days): See the impact of preventive maintenance and the shared processes that make this work efficient
  5. Mean time to detect and repair: Everyone has a part in finding and fixing failure before it leads to breakdowns and doing so with as little disruption to the business as possible

Integrate production and maintenance systems

It’s easy for operations to have a negative view of maintenance when their only exposure to it is a breakdown or service interruption. Integrating the systems used for production and maintenance provides visibility into each team’s work. This allows you to see the positive impact of each department and help each other accomplish even more.

Ryan Robinson’s maintenance team is a great example of how integrating maintenance software with equipment and production systems can deliver incredible results. Ryan, the shop manager at a wholesale tree grower, connected sensors on several machines with a CMMS. This gave him the data he needed to optimize maintenance intervals and increase production efficiency.

“Because we know how equipment is used on a daily basis, we have some idea of what is going to be expected of maintenance tomorrow, and the next day, and the next day,” says Ryan.

Ryan was also able to use this data to spot vehicles with high idle times. He brought this information to the farm manager, who figured out the reason why and found a solution.

Read Ryan’s story

World-class maintenance teams are aligned with operations

Operations and maintenance are the heartbeat of any company with lots of assets and big production targets. That’s why it’s essential that they develop a healthy relationship and formal processes for working together. The two teams must share everything from the metrics they aim for to the systems they use, and the schedule that guides their work. Joining forces gives them better visibility into the challenges that face the business and the power to overcome them. It’s a win-win for everyone involved.

Source: https://www.fiixsoftware.com/blog/guide-to-aligning-operations-and-maintenance/

Natural Language Processing Acquisition Opens Doors For Nuix Product Roadmap

Nuix announced its decision to buy Topos Labs, Inc. (Topos), a developer of natural language processing (NLP) software that helps computer systems better understand text and spoken words at speed and scale.

Headquartered in Boston, MA, Topos designed its artificial intelligence (AI) driven NLP platform to reduce the workload on data reviewers and analysts by surfacing relevant or risky content faster. Its mission is to provide customers with risk-oriented content intelligence for proactive risk management and regulatory compliance.

The addition to Topos to our already extensive software platform will, as you’ll see, play a noticeable role in making the lives of our users easier. Whether you’re tasked with conducting internal corporate investigations, handling legal discovery review or ensuring your organization is meeting its risk and regulatory obligations, Topos’ NLP capabilities and integration with Nuix in the coming months will be something to pay attention to.

POWERFUL ANALYSIS AND CLASSIFICATION
The platform, which is still in the early stages of its development, can already automate accurate analysis and classification of complex content in documents, electronic communications and social media. Business users can directly define NLP models through the software’s no-code user interface, reducing the time required to identify risk in the organization’s data. From there, it can present the risk assessment of confidential, sensitive and regulated content in user-friendly dashboards.

“The acquisition of Topos is an exciting evolution in Nuix’s journey,” said David Sitsky, Nuix Engineering Founder and Chief Scientist. “Integrating the Nuix Engine’s ability to process vast quantities of unstructured data with the next generation NLP capabilities of Topos will be game-changing for Nuix’s product portfolio.”

“Topos will strengthen Nuix’s product offering by helping customers get to relevant data even faster,” added Rod Vawdrey, Nuix Global Group CEO. “The potential for user-friendly dashboards and for users to easily customize the software to their specific needs also reflects Nuix’s focus on empowering our customers to search through unstructured data at speed and scale. We look forward to Christopher Stephenson [Topos CEO] and his talented team joining Nuix.”

WELCOMING THE TOPOS TEAM
As part of the deal the Topos team, including members of senior management, joined Nuix. By welcoming the Topos team and integrating the NLP capability at this stage of its development, Nuix can optimize the technology to benefit its investigations, eDiscovery and governance, risk and compliance (GRC) customers, further enhancing the unstructured data processing power of the Nuix Engine.

“We are delighted to join Nuix and are excited about combining our innovative NLP platform with the Nuix platform,” said Christopher Stephenson, CEO, Topos Labs. “Along with my talented engineering and product team, I look forward to deploying Topos to further enhance Nuix’s powerful processing capabilities and to being part of a global leader in investigative analytics and intelligence software.”

Source: https://www.nuix.com/blog/natural-language-processing-acquisition-opens-doors-nuix-product-roadmap