While there is currently an extreme level of ‘hype’ for AI Analytics in the industrial market, the survey results demonstrate organizations understand that applying AI in targeted use cases such as Predictive Maintenance can drive rapid value creation.  Lowering unplanned downtime, optimization of maintenance resources, and running equipment more efficiently to support net zero goals are all proven outcomes when using AI in industrial settings.

The key challenge in capturing this value has been the cost and complexity of building and scaling the analytical models at the core of these use cases.  At Itus Digital, we have solved this challenge by uniquely integrating AI with asset strategies and providing a visual modeling approach that can be easily used by equipment experts.  The asset strategy provides the blueprint for what to analyze and the equipment expert provides the knowledge to identify a failure risk is emerging and how to mitigate when that occurs.

Read the full Verdantix report here.

The post Unlocking Predictive Maintenance Potential appeared first on Itus Digital.

Roanoke, Va. – September 6^th, 2023 – Itus Digital today announced new Artificial Intelligence capabilities designed to enable equipment experts to directly deploy and refine anomaly detection models at scale.  Using a visual modeling approach, practitioners can quickly implement protections to identify emerging failure risks, uncover abnormal operating conditions, and enable predictive maintenance.

Designed to enable advanced analytics on equipment of any criticality profile, the solution monitors equipment, and operating parameters to identify emerging failure risks and prescribe action. A no-code model building and tuning process allows already stretched equipment experts to directly apply their knowledge within asset strategies to detect potential failures and optimize maintenance spend.

“Manufacturers wanting a common-sense approach to asset performance management should look no further than Itus Digital’s APM,” says Joe Perino, an independent industry analyst with PERTEX. “I haven’t seen a simpler, easier-to-use, yet powerful and sophisticated APM solution. In its latest release, Itus APM offers all the vital functions that one needs from risk assessment all the way through predictive and prescriptive maintenance, with actionable recommendations.”

As a new analytical component within Itus’s existing APM work process and Asset Twin library, the machine learning models continuously evaluate failure symptoms and process conditions to ensure asset strategies are effective and optimized.

“Anomaly detection using machine learning has proven to be the most valuable AI industrial use case to date. Unfortunately, the complexity and cost have limited widespread adoption,” said Joe Nichols, President, of Itus Digital. “To solve this problem, we focused on empowering equipment experts, with AI, in the context of an asset strategy. Taking this approach not only streamlines the model building process but provides the analytic with full context on the asset, failure risk, and optimal mitigations.”

Already recognized as one of the most intuitive APM solutions on the market, this addition further expands on Itus’s vision to bring asset management best practices to industrial organizations of all sizes, complexity, and maturity.

Joe Perino further noted, “Reliability, maintenance, and inspection engineers and technicians can DIY without the need for data scientists or product specialists to code AI/ML algorithms and implement complex configurations.”

The solution is immediately available to asset operators, service providers and OEMs looking to improve availability, optimize spend, and reduce operational risk.

Learn more about Itus Pattern Protections here.

About Itus Digital

Itus Digital is a team of industrial software veterans maniacally focused on optimizing the performance of industrial assets by fusing apps, industrial engineering expertise, and analytics within simple-to-use and scalable software solutions.

The post Itus Launches AI Driven Anomaly Detection Solution appeared first on Itus Digital.

A key challenge for AI technology in asset management is the complexity of using it unless you are a data scientist or programmer.  How do organizations take advanced technology, like AI, and make it available and easy to use for those who could drive the most benefit with it?  The front-line team, operating and maintaining the plant, have the knowledge and expertise to make a risk vs. cost tradeoff decision to deliver operational results.  AI is a supporting technology that should be used primarily to enable teams to be more productive and efficient in their daily roles instead of being overwhelmingly complex and hard to use. 

Would you really trust the Pit Crew to control the steering wheel of a Formula One Car?  Of course not.  Their role is to support and enable the drivers to be as efficient and productive as possible. The Itus Digital solution provides a way to visually model patterns or anomalies in machine data.  The key word is visually.   This approach allows an engineer, who “knows” the asset operating conditions and failure risks to build models based on the variances that occur from those conditions. 

Using the comparison to Formula One, the F1 driver, from their cockpit, sees a condition they want to use as a data point.  The driver can “mark” the track by pressing a button on their steering wheel.  For example, the driver might want to associate this data point (or section of the racetrack) with performance data involving braking power, or cornering.  The F1 team uses the data that’s collected to adjust their race strategy to achieve incremental performance improvements. 

Our visual approach uses the engineer’s expertise and enables them to observe, and “mark” data variances which indicate emerging risk of failure, deviations which could affect quality or even expected operating conditions. 

The process starts with the engineer evaluating the historical data for the machine to supply context for modeling the asset.  Information such as work performed, identified failures, process and machine condition are brought together in a timeline view.  With one complete view of the machine’s behaviors and activities, engineers can identify “markers on the track” so that specific areas of improvement can be found and encapsulated in a machine learning model.   

But what if you only know what ‘good’ conditions look like for a machine and aren’t entirely sure how to pinpoint ‘bad’ anomalies or conditions?  Many AI techniques focus on historical behaviors which are precursors to ‘bad’ conditions where the machine is likely to fail. These ‘bad’ conditions can be highly erratic and may not look the same every time.  So how do you help the reliability engineer that only knows what good operational conditions look like and simply wants to be notified if there are deviations from that?

The Itus Digital approach allows its users to visually model ‘good’ conditions where equipment is running as expected and send notifications when deviations from those conditions are detected.  This solution is a great starting point for organizations which may not have exact tracking of historical failures but look to know when key operating parameters show potential machine issues. 

There are still many mysteries surrounding AI, but we are simplifying the on-track experience for our drivers, the engineers, so they can spend their time solving problems, improve the quality of their decisions and accelerate their asset management maturity.

The post Accelerating Artificial Intelligence in Asset Management – Part II appeared first on Itus Digital.

This Netflix series showcases the amazing engineering effort behind the top performing racecars in the world.  But why are we discussing F1 racecars in a blog about AI (Artificial Intelligence)?  This Netflix series tells a story about decisions, how they affect outcomes for every race, and how the use of data and information affects the quality of those decisions.

The current state of AI is like Formula One racecars. These machines depend on advanced technology and specialized skills.  They require a highly technical engineering team coordinating their efforts to ensure the racecar goes around each lap of the track, in the least amount of time possible.  This is a process of continually compounding the team’s collective understanding of their cars, the tracks they race on, their competitors, and the conditions they need to adjust for before and during the event.

Harnessing the power of AI is similar to harnessing the power of an F1 race car.  The team of engineers, subject matter experts, and data scientists precisely coordinate their efforts to use information they have (historical data) to produce information they don’t have (predictions).  The quality of these predictions directly enables the quality of decisions made by heads of the team.  At this elite level, the aggregation of marginal improvements is what makes the difference between a podium finish or not scoring any points at all.  This elite and prestigious level of performance can attract and retain the top available talent to be part of this team.

Similarly, to harness the power of AI, a team of data scientists, subject matter experts, and specialized software engineers are required.  This means that only those organizations that can attract and dedicate such a team are going to reap the rewards promised by AI. At least for now.

When you consider the application of AI within industrial facilities, building a team to drive successful AI projects can be even more challenging.  A skills gap due to an aging and retiring workforce, the need to collaborate across many organizational functions such as operations, maintenance and IT can create significant burden on already stretched resources.  One of the keys to being able to successfully leverage AI at scale, is to put the power directly into the hands of equipment and process experts.  Yes, AI as an enabling technology provides great productivity gains by rapidly assessing large volumes of data on a continuous basis, but the true value drivers are not algorithms.  It’s the people and their knowledge of how the production process operates, how equipment can fail, the symptoms that indicate potential failure and most importantly what action to take when anomalies are detected.

In the APM space, we have seen AI applied to the most critical and complex assets, yet these represent a very small percentage of the total assets in an industrial facility.  If we could turbo charge the process by enabling equipment experts to directly build anomaly detection models at a faster rate, we can unlock much more value across a broader set of challenges related to the risk, cost, and performance of assets.

It wasn’t the sophisticated engineering that went into the car that brought about the era of motorized transportation. It was Henry Ford’s assembly line production which brought the car to the masses.  AI is going to continue to advance and will do so at an increasing rate.  But until we solve the challenges of practicality and availability, we will be dependent on precision-coordinated teams of highly skilled experts.

Look out for our next post where we will offer some insights into approaches to fully harness the power of AI.

The post Accelerating Artificial Intelligence in Asset Management – Part I appeared first on Itus Digital.

Back in the mid-1990’s members of the Itus Digital team were involved in a project to consolidate service intervals of a heavy haul fleet in an open pit coal mine.  Rather than spend ten or twelve million dollars to increase the size of the haul truck fleet, we wanted to see if we could achieve an increase in production capacity from the existing fleet. One of the requirements of the project was to double the engine oil drain interval.  This would allow the service intervals to be consolidated sufficiently to keep the existing haul trucks working for longer and unlock un-utilized production capacity.  However, we needed to have confidence that we could increase these oil drain intervals without increasing the risk of engine failure.  The things we needed twenty-five years ago are the same things we need today:

• Understanding of failure modes
• The protections that needed to be in place to sufficiently reduce the risk of failure
  • Doing the right things
  • Monitoring the right things
• Historical data about:
  • How the lubricant breaks down
  • How the engine can fail due to lubrication-related problems
• Analysis of used oil and filters to justify a PM extension

If we’d been able to apply deep neural networks back then, to watch one or multiple conditions, and detect anomalies that indicated potential failure risk, we might have reduced the duration of the project by several months and achieved a lower-cost way to monitor certain failure modes with higher confidence.

Unfortunately, we experienced two engine failures during the project.  These failures were directly attributed to maintenance activities that were not done when they needed to be done.  One of the failures occurred because the lubricant hadn’t been topped up.  The second failure occurred because the engine lubricant filter hadn’t been properly serviced.  In this scenario, anomaly detection would not have detected these failures and highlights the need to treat Artificial Intelligence (AI) and Machine Learning (ML) as a specialized technique to complement foundational asset management practices such as preventative maintenance compliance.

With ChatGPT, AI/ML has reached a new level of hype, promise, and even a dose of fear.  Have we reached a point, like a Star Trek episode, when we can simply ask the ship’s computer to answer questions, provide options, or execute certain tasks?  While ChatGPT is a powerful tool that can quickly generate an answer to your question, it has no mechanism for telling you when the right time is to apply the solution.  An effective asset strategy requires more than just a simple answer to a question.  It must be operationalized, dynamic, and the enabling capability of your work process.

The anomaly detection concept involves picking up an incipient failure signal, further leftward on the IPF curve.  This simple concept implies that the earlier we detect the deviation of the expected signal, the more time we’ll have to do something about it thus, minimizing potential impact to operation.

This isn’t a new technique in the industrial space.  Mathematics and models of failure have been around for decades.  There is a vast amount of data available to feed these models and produce the decision support we need.  The role of AI/ML is to bring down the cost of and increase the accuracy of prediction by efficiently analyzing large volumes of data and advising equipment experts when failure risks emerge.  It should also bring about a more optimal division of labor between humans and machines.

Industrial equipment can have significant variation in risk. Failure modes exist which are not optimally detected with AI/ML, and every organization must work within budget and cost constraints.  Furthermore, when assessed appropriately a run-to-failure strategy could be the optimal answer.  Consideration of all these factors, the classic constructs of asset management, is more important than ever given the level of hype given to AI, as the singular answer to optimizing asset performance.

In summary, Asset Performance Management requires more than just anomaly detection or understanding of when maintenance activities occur.  Asset Performance Management helps organizations balance the risk, cost, and performance of assets.  As such, anomaly detection may be an important part of an operationalized strategy, if it is in service to that outcome.

The post AI, Anomaly Detection & Asset Management – Keeping it Real appeared first on Itus Digital.

Principle No. 1 – Believability

Asset health is a very important subject, and it’s encouraging to see how much new attention is being paid to it. So, let’s suppose a machine has been trained to detect certain cancers, as reliably or more so, than a human radiologist.  If the algorithm training is successful, the believability of the machine increases over time.  It may even get to a point where the believability of the machine exceeds that of the human.  The outcome should be, cancers detected earlier, treatment applied sooner, higher probability of survival.

In a similar way, vibration analysis can help predict incipient signals of certain failure modes of certain types of assets.  Vibration analysis is one of the predictive maintenance technologies that has earned high believability over time. This growth in believability is based on the impact of the trained and experienced human technologist, whose analysis and recommendations result in failures detected earlier, intervention is applied sooner, lower probability of loss.

Today, there are claims that artificial intelligence (AI) and machine learning (ML) have improved the utilization and results of vibration analysis.  Just like the machine that detects certain cancers, the compelling use case for AI and ML for vibration analysis is one that impacts the believability of the analysis results.  That is, we need to know that it improves on what humans have done so well for the last several decades.

Ajay Agrawal wrote a book titled “Prediction Machines – The Simple Economics of Artificial Intelligence“. This book is helpful for developing a mental model for evaluating AI/ML technology.  In it, he explains the fundamentals involving the use of data. “First, is input data, which is fed to the algorithm and used to produce a prediction.  Second is training data, which is used to generate the algorithm in the first place. Finally, there is feedback data, which is used to improve the algorithm’s performance with experience.” There is no doubt that in the last twenty-five to thirty years, plenty of vibration analysis and failure data has been accumulated.  As such, we should want to understand how the use of AI/ML has “become good enough to predict in the wild”, and at least has the same believability as the human engineer.

Principle No. 2 – Decision Support

What could advances in prediction and improved believability mean to the organization that has already included vibration analysis in its asset strategies?  It could enable a more optimal division of labor between the human experts and the prediction machine’s capabilities.  Ray Dalio, in his book, Principles: Life and Work, describes how using the power of prediction machines, “allowed me and the people I worked with to compound our understanding over time and improve the quality of our collective decision making”.  The thing that should attract us to these technologies is how they can help us to do more of what we are good at.

Principle No. 3 – Asset health is not about predicting failures

Just because a machine can predict the evidence of tumors or other maladies, it doesn’t mean the patient is healthy or unhealthy.  The application of AI/ML to successfully predict machine failures is part of a strategy to preserve the function of an asset along the duration of its mission time.  Asset health is measured according to the number of exceptions that come from monitoring the asset strategy.  The lower the number, the better asset health, the more effective the strategy.

The machine that detects cancer won’t comment on the patient’s lifestyle and risk factors.  It doesn’t see those things.  The human physician doesn’t step aside and allow the machine to make decisions, but rather uses the machine’s capabilities to enhance the quality of her own diagnosis and decisions.  The asset management professional, like the oncologist, makes use of prediction as an enabling part of the operationalized asset strategy that balances risk, cost, and performance of assets.

At the end of the Yellow Brick Road is a man who is not a wizard after all but someone who helps Dorothy, and her friends make practical conclusions about their own circumstances.  It turns out they never needed a wizard at all but had the knowledge and capability already to achieve what they desired. Hopefully these principles help to reduce the wizardry of AI/ML and put more emphasis on results and outcomes and how AI/ML can help us to do more of what we’re already good at.

The post We’re Off to See the Wizard, What’s Behind the Curtain? appeared first on Itus Digital.