Predictive Maintenance

Machinery maintenance is vital for many organisations, particularly in aerospace. Airlines spend a substantial share of their total operating costs on maintenance, repair and overhaul (MRO). According to the International Air Transport Association[1] (IATA), global aviation is expected to double over the next twenty years. MRO costs will rise as a result. Airlines face a real challenge in controlling these costs and improving operational efficiency. Predictive maintenance uses sensor technology and artificial intelligence to reduce MRO costs and improve operational efficiency. It makes it possible to get the most out of equipment’s remaining service life by carrying out maintenance and overhauls at the right time and avoiding costly repairs.

Introduction

For years, the prospect of lower MRO costs and greater profitability through intelligent maintenance techniques has appealed to many organisations. The idea behind predictive maintenance is fairly simple: use sensor data and artificial intelligence to maintain machinery at the right time, reducing MRO costs and unplanned downtime. Until recently, the algorithms needed for predictive maintenance had either not been developed, were not sufficiently mature or were too costly to use.

In recent years, however, computing power has increased substantially, advances in artificial intelligence have followed in rapid succession, and sensors have become more accurate and less expensive. This lowers what was initially a high barrier to investment, making predictive maintenance more accessible and attractive to a growing number of organisations.

The energy, transport, manufacturing and information technology sectors are leading the way in predictive maintenance. This is no surprise, particularly in aviation. An annual report by IATA’s Maintenance Cost Technical Group shows that, in 2018, airlines worldwide spent a combined 69 billion[2] dollars on MRO, around 9% of their operating costs. Understandably, airlines are trying to reduce MRO costs with state-of-the-art predictive maintenance algorithms. The Dutch aviation sector is actively working on this: KLM’s most recent annual report[3] states that its largest reduction in MRO costs was achieved through predictive maintenance.

In manufacturing, MRO costs are much higher[4] and, depending on the industry, can account for 15–60% of operating costs. It is therefore crucial for these organisations to optimise MRO.

Maintenance approaches

There are different approaches to inspecting and maintaining equipment. These generally fall into three categories: reactive, preventive and predictive. The main difference lies in how they use the equipment’s service life, a typical progression of which is shown in the figure below.

The earliest maintenance activities were reactive: equipment was repaired only when a fault occurred. The drawback is that this approach brings high costs and risks. You do not know when a machine will fail or how much damage it will cause. If a machine will not be used for the next few days (for example, over the weekend) and can be repaired in time, the financial impact will be limited. But if it is a production machine in a car factory that produces a car every minute, or an aircraft engine on a plane flying at the upper edge of the troposphere, the financial and/or societal consequences can be considerable.Today, much maintenance is carried out preventively, with inspections and maintenance performed at regular intervals. Preventive maintenance helps you avoid unexpected failures that bring high costs and risks. But this approach is not optimal from a cost perspective either: parts or machines are inspected or maintained even when they have not reached the end of their service life. Their remaining useful life is not fully used, resulting in unnecessary costs.By inspecting and maintaining parts and equipment at the right time, you can avoid unnecessary costs and risks. Predictive maintenance makes this possible by aligning maintenance with the actual condition of parts and machines.

What is predictive maintenance?

Predictive maintenance is an approach that aims to detect machine failure mechanisms at the right time and prevent further deterioration through inspections and maintenance.

Failure mechanisms are detected by intelligent algorithms that predict the current condition or remaining useful life of machines based on sensor data. The sensors measure factors including vibration, temperature, sound, lubricant composition, machine performance and many other operational characteristics. The intelligent algorithms are complex mathematical formulas whose parameters continuously adapt to new sensor data and the accuracy of their predictions. As a result, predictions about the actual condition of machines can be highly accurate, provided enough high-quality data is available.

There are two ways to predict maintenance needs. The first is to calculate the probability that components or machines will fail within a given future period. The second is to predict when components will fail. The first option provides information about the current condition of components and machines, and thus indirectly about their remaining useful life, while the second determines their remaining useful life directly.

Applying predictive maintenance requires a large amount of high-quality data, and machines need to be fitted with sensors. Initial investment is therefore relatively high. In most cases, however, organisations already have extensive historical data that they use to operate and manage their processes. This valuable data can be used to explore the potential of predictive maintenance for specific applications. Although initial investment may be relatively high, the benefits are greater still. A study[5] by the US Department of Energy shows that an effective predictive maintenance programme can reduce maintenance costs by 30%, cut downtime by 45% and eliminate as many as 75% of failures.

The advantages and disadvantages.

It is now clear that predictive maintenance offers numerous benefits, particularly in cost savings and risk management. The benefits of using intelligent algorithms to predict maintenance needs can be summarised as follows:

• Longer operational life for components and machines
• Lower costs for energy, labour, maintenance and parts
• Less unexpected (catastrophic) downtime for components and machines
• Better service and product quality
• Greater safety for employees and the environment
• Less maintenance equipment needed

Predictive maintenance therefore improves operational efficiency through lower costs, higher quality, reduced risks and more sustainable practices. There are also drawbacks, however:

• Management is often unaware of the potential savings
• High initial investment
• Higher training costs for operating staff

Example of a predictive model.

This section uses a scientific paper[6] published at the International Conference on Circuits and Systems to demonstrate the accuracy of predictive maintenance models.

In the paper, predictive maintenance algorithms use sensor data to predict the number of flights aircraft engines have left, known as their Remaining-Useful-Lifetime (RUL). The researchers use NASA’s Turbofan Degradation Simulation dataset. This four-part dataset consists of time series covering three operational settings and 21 sensor measurements from a fleet of aircraft engines over a given period. The engines are of the same type but vary in how they were manufactured and how much wear they have sustained. These differences are not recorded in the dataset.

At the start of the time series, the aircraft engines function as expected, but faults begin to develop over time due to wear. These failure mechanisms progress until the engines eventually fail. The time series used to train the algorithms end some time before the engines fail. The algorithms are then trained to predict as accurately as possible how much time remains before failure.

The article compares several algorithms, and Random Forest performs best. Figure 1 shows its predictions for the different aircraft engines in the first part of the dataset. Accurate predictions lie close to the diagonal, where the predicted remaining useful life (RUL) equals the actual RUL.

Figure 1: Random Forest algorithm for predicting remaining useful life.

The Random Forest algorithm’s mean squared error on the first part of the dataset is approximately 25. This means its predictions of how many flights an aircraft engine has left before it fails differ from the actual number by an average of 5 flights. Figure 1 also shows that the algorithm is more accurate when failure is imminent. This is as expected: predicting the near future is easier than predicting the distant future. With predictions this accurate, you can intervene in time and extend the operational life of your machines. The predicted number of remaining flights can also be higher than the actual number. In this undesirable scenario, an aircraft engine fails unexpectedly, bringing significant risks and costs. That is why human MRO expertise and AI must complement each other, not replace each other. For equipment whose operation directly affects the wellbeing of people and the environment, preventive and predictive maintenance need to go hand in hand.

Data Science Lab and predictive maintenance.

Does your organisation make intensive use of machinery? Are you looking for a more sustainable approach to maintenance? Do you want to reduce MRO costs and increase operational efficiency? We invite you to our Lab to explore together which techniques your organisation needs and which are right for it.

References

For more information about the possibilities of predictive maintenance, see the sources below.

• Mobley, R. Keith. An introduction to predictive maintenance. Elsevier, 2002.
• Selcuk, Sule. "Predictive maintenance, its implementation and latest trends." Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture9 (2017): 1670-1679.

1. https://www.iata.org/en/pressroom/pr/2018-10-24-02/
2. Airline Maintenance Cost Executive Commentary Edition 2019 - https://www.iata.org/contentassets/bf8ca67c8bcd4358b3d004b0d6d0916f/mctg-fy2018-report-public.pdf
3. KLM Annual Report 2019 - https://www.klm.com/travel/nl_nl/images/KLM-Jaarverslag-2019_tcm541-1063986.pdf
4. Mobley, R. Keith. An introduction to predictive maintenance. Elsevier, 2002.
5. “Operations & Maintenance Best Practices: A Guide to Achieving Operational Effi‐ciency,” US Department of Energy Federal Energy Management Program, August 2010
6. Mathew, Vimala, et al. "Prediction of Remaining Useful Lifetime (RUL) of turbofan engine using machine learning." 2017 IEEE International Conference on Circuits and Systems (ICCS). IEEE, 2017.

020-3031414