What is preven­tive mainten­ance?

Share post:

The term “preven­tive mainten­ance” is often used in connec­tion with the optimiza­tion of mainten­ance plans. This article explains what is behind this and how to imple­ment preven­tive mainten­ance based on histo­rical failure data.

A very well-known and old example of preven­tive mainten­ance is the V-belt in a car, which trans­mits the rotation of the engine cranks­haft to various auxiliary units. It is parti­cu­larly important to supply the alter­nator, which provides power to many of the car’s electrical compon­ents, as well as the hydraulic pump, water pump, power steering, venti­la­tion and air condi­tio­ning.

Back to preven­tive mainten­ance: Experi­ence has shown that a V-belt lasts an average of around 100,000 kilome­ters. However, the running time depends on various factors, such as the power of the engine, the age of the V-belt and the number of start/stop opera­tions. Without knowing these influences precisely, a safety factor is applied to the average service life of the V-belt. The safety factor must also take into account that a broken V-belt can lead to signi­fi­cant engine damage. For example, we set the safety factor to γ=0.8 and replace the V-belt appro­xi­m­ately every γ⋅100,000=80,000 kilome­ters, using the inspec­tion dates recom­mended by the manufac­turer. Of course, indivi­dual V-belts can also last 120,000 or 150,000 kilome­ters, but proac­tive repla­ce­ment or preven­tive mainten­ance minimizes the risk of engine damage without comple­tely elimi­na­ting it. When deter­mi­ning the safety factor, the poten­tial engine damage must be taken into account on the one hand; on the other hand, the effort or workshop costs for repla­cing the V-belt.

This example can be applied to all mecha­nical (and electronic) devices. Typically, the expected load cycles of ball bearings, the average burning time of light bulbs or the service life of sealing rings are known. These compon­ents are used in trains, airplanes, genera­tors, robots, eleva­tors, power plants, bicycles, etc. in every country in the world. These many millions of compon­ents make effec­tive preven­tive mainten­ance important in order to avoid damage and system failures.

So how does preven­tive mainten­ance work? The example of the V-belt has already shown this quite well: you need histo­rical failure data for the system type under conside­ra­tion or, as in the example of the V-belt, histo­rical failure data for the compo­nent under conside­ra­tion. If you want to carry out the calcu­la­tion for a new type of system, you can aggre­gate findings from the installed compon­ents or test the system in various practical tests in the labora­tory.

As with V-belts, in practice there are several time dimen­sions that describe the failure inter­vals of the system. Let’s take the example of a car that is rarely driven. In this case, the V-belt will eventually become porous and may only last 50,000 kilome­ters or less. In another example, the car is moved several times a day (e.g. in a postal delivery vehicle), which can also cause the V-belt to break after 50,000 kilome­ters. A distinc­tion is made between the Mean Time Between Removal (MTBR), the Mean Duration Between Removal (MDBR) and the Mean Cycles Between Removal (MCBR). Depen­ding on the appli­ca­tion, further time dimen­sions are conceivable. A specific failure interval results as a linear combi­na­tion of the indivi­dual time dimen­sions, the coeffi­ci­ents of which are derived from an optimiza­tion algorithm. Typically, we use a meta-heuristic such as Simulated Annealing for this task, which converges to a good (local) optimum in finite time.

The next step is to deter­mine which situa­tions can have an influence on the failure of the system/component. To this end, it is advisable to consult experts from develo­p­ment and produc­tion and, if neces­sary, users. If there are too many influences, these can be reduced using statis­tical methods for feature selec­tion. Alter­na­tively, the infor­ma­tion content of the influences can be condensed using a principal compo­nent or factor analysis. In the case of V-belts, these are typically the average speed of the belt, the quality of the material, the ambient tempe­ra­tures (perhaps a V-belt lasts longer in Norway than in Saudi Arabia? or shorter?) and others.

A set of rules must now be derived from the influen­cing varia­bles in order to be able to predict specific failure behavior. Statis­tical decision trees or the Random Forest machine learning method are usually used for this purpose. Both methods arrange the influences in descen­ding order depen­ding on their infor­ma­tion content and separate the charac­te­ristics in each tree level as shown schema­ti­cally in the follo­wing figure. In order to achieve maximum flexi­bi­lity in the conside­ra­tion and combi­na­tion of all influences and time dimen­sions, we have also imple­mented indivi­dual algorithms for clamping the trees for our custo­mers.

Was ist eigentlich Preventive Maintenance?

Figure 2: Schematic repre­sen­ta­tion of a decision tree for the imple­men­ta­tion of preven­tive mainten­ance for V-belts

Each node of the tree contains average times (for three time dimen­sions) from all histo­rical failures that fulfill the criteria of the branch under conside­ra­tion. The tree shown was not fully formed (this is known as prunning) because, for example, only a small amount of data was available from manufac­turer 5. The diffe­rence between the actual distances between two changes and the calcu­lated times in the corre­spon­ding node of the tree deter­mine the quality of the tree.

A typical service life can now be read from the tree for a specific appli­ca­tion situa­tion of the part or compo­nent. As described above, it is advisable to apply a safety factor to the times, which should take into account the costs of failure and the costs of repla­ce­ment. The forecast model should also be presented with current outage and repla­ce­ment infor­ma­tion in order to be able to take changed environ­mental condi­tions into account in the forecast.

To increase the forecast quality, either further statis­tical charac­te­ristics can be taken into account or data from the specific V-belt (the specific serial) can be recorded with the aid of sensors. For example, an acoustic sensor could be used to measure the smooth running of the V-belt. If sensors are used to measure the current condi­tion of the compo­nent, this is referred to as “predic­tive mainten­ance”. How predic­tive mainten­ance works will be explained in one of our next blog posts.

Picture of Björn Piepenburg

Björn Piepen­burg

Projektanfrage

Vielen Dank für Ihr Interesse an den Leistungen von m²hycon. Wir freuen uns sehr, von Ihrem Projekt zu erfahren und legen großen Wert darauf, Sie ausführlich zu beraten.

Von Ihnen im Formular eingegebene Daten speichern und verwenden wir ausschließlich zur Bearbeitung Ihrer Anfrage. Ihre Daten werden verschlüsselt übermittelt. Wir verarbeiten Ihre personenbezogenen Daten im Einklang mit unserer Datenschutzerklärung.

Project request

Thank you for your interest in m²hycon’s services. We look forward to hearing about your project and attach great importance to providing you with detailed advice.

We store and use the data you enter in the form exclusively for processing your request. Your data is transmitted in encrypted form. We process your personal data in accordance with our privacy policy.