Predictive maintenance applies data and models to predict when a piece of equipment or an asset will fail. This approach helps companies to proactively address situations that would otherwise result in costly downtime or discontinuity, either by predicting failure or by suggesting recommended actions to take following that failure.
The alternative is a break-fix approach, which is costly to the company in many ways. Once a machine fails, significantly more resources are required to get it back online than would be the case if the problem was known—and avoided—in advance.
Types of Maintenance
There are three ways to approach maintenance:
The reactive, break-fix approach means that we only replace components when they fail. This method can lead to crippling and expensive consequences, and depending on what type of machine we’re talking about, it could even be dangerous. For example, if the machine in question is a jet engine, failure could put hundreds of lives at risk and potentially ruin a company’s reputation indelibly.
Pre-scheduled maintenance is a slightly better approach in that issues are sorted and addressed on a regular basis. However, if no maintenance is required, it is wasteful of a company’s resources. You don’t know when failure is likely to occur, so a conservative approach is required to avoid unnecessary costs. For example, when you service a machine early, you are essentially wasting viable machine life, applying maintenance resources inefficiently, and generally compounding your cost of doing business.
Being able to predict when a machine will fail is the ideal situation, but it is difficult to forecast with any great accuracy. In a best-case scenario, you will know when a machine is due to fail. You will also know what parts are going to fail so you can reduce the time spent diagnosing the issue and reduce waste and risk in the process. When machine failure is signaled by the predictive system, maintenance is scheduled as close to the event as possible to make the most of its remaining useful life.
Problems that Can Be Addressed With Predictive Maintenance
Leveraging data collected from IIoT devices, we can begin to address a wide range of maintenance issues with the ultimate goal of achieving a preemptive posture using machine learning (ML).
Problems that can be addressed include:
- Detecting the Point of Failure. This concept involves predicting when a component has failed and will help to better predict at what point in its lifecycle a part or machine will fail.
- Incipient Failure Detection. In this instance, we can detect failures before they happen by applying sensor data to the ML algorithm.
- Maximize Remaining Useful Life. With the ability to predict the interval before which a component fails, we can apply maintenance or replace components at exactly the right times. Conversely, we would be replacing these same parts at regular intervals and wasting valuable resources as the parts are still operating as they should.
The more accurately we can predict when a part or a machine will fail, the easier it is to achieve maximum productivity and efficiency throughout the organization.
Areas where you will see improvement include:
- More efficient use of labor force
- Fewer resources are needed to monitor machine function
- Predictable productivity levels
- Maximize machine and part life
- Production proceeds at peak levels
- Eliminate non-essential maintenance tasks
- Risk reduction
- Workplace safety improvement
Approaches to Predictive Maintenance
For predictive maintenance to succeed, there are three main aspects that must be present.
First, and probably foremost, you need quality data. Ideally, you want historical data that takes into account events that have, in the past, ended in failure. Failure data needs to be juxtaposed against static features of the machine itself, including its average use, general properties, and the conditions under which it operates.
You will no doubt end up with a lot of data, so it is critical to focus on the right data. Getting hung up on extraneous information does little more than muddy the waters, deflecting attention away from what’s most important. You should ask yourself, what failures are likely to occur? Which ones do you want to predict? What happens when a process fails? Does it happen fast, or is it a slow burn over time?
Finally, take a close look at any other related systems and parts. Are there other components that are related to the failure? Can their performance be measured? And finally, how often do these measurements need to happen?
Data collection needs to take place over an extended period for best results. Quality data results in a more accurate predictive model. Anything less will only narrow the field of possibilities rather than give you hard truths. Analyze the available data and ask yourself if it is possible to build a predictive model based on these insights.
It is important to have the proper context when looking at a problem, as only then do we have the ability to evaluate the predictions with some accuracy.
In general, we use one of two predictive modeling approaches:
Regression Models predict the remaining useful lifetime of a component. It tells us how much time we have left before the machine fails. For a regression model to work, historical data is necessary. Every event is tracked and, ideally, various types of failure are represented.
The assumption offered by the regression model is that, based on the inherent (static) aspects of the system and its performance in the present, its remaining lifecycle is predictable. However, if there are several ways in which a system can fail, a separate model must be created for each possibility.
Classification models predict machine failure within a certain window of time. In this scenario, we don’t need to know too far in advance when or if a machine is going to fail, only that failure is imminent.
Classification and regression models are similar in many ways, but they do differ on a few points. First, the classification looks at a window of time rather than an exact time. This means that the gradation of the degradation process is a little more relaxed, requiring less exacting data.
Additionally, the classification model supports multiple types of failure, allowing incidents to be grouped together under the same classification. The success of a classification model depends on there being enough data available, and enough instances of certain types of failures to inform the ML model.
How It Works
Once modeled, predictive maintenance proceeds in this way:
The ML model collects sensor data and, based on historical failure data, identifies the events that precede a failure.
We pre-set the desired parameters to trigger an alert to a potential failure. When the sensor data breaches these parameters, an alert is initiated.
Where machine learning comes in is in detecting unusual patterns that are outside normal system operation. With better awareness of these anomalies based on quality data, our ability to predict failure improves dramatically.
In conclusion, machine learning supports the analysis of vast amounts of data with minimal human intervention. Applied using best practices, it is the ideal approach to cost reduction and risk mitigation.
By applying machine learning, combined with data collected from IIoT devices, it is possible to improve processes, reduce costs, optimize employee efficiency, and reduce machine downtime significantly – all critical aspects of a successful organization.
If you would like to learn more about machine learning and how it can support a predictive maintenance posture, reach out today.