Predictive Maintenance Predictive Maintenance: Efficiency in industry 4.0
The term Predictive Maintenance describes a system initially developed in industry 4.0, which can be looked upon as a core component of industry 4.0. Predictive Maintenance describes a forward-looking approach in which machines and systems are maintained proactively and on the basis of permanently collected data. Predictive Maintenance can thus effectively shorten and reduce downtimes. Essential for this is the comprehensive data acquisition during production.
Predictive Maintenance: A Definition
The term Predictive Maintenance has its origins in industry 4.0 and it is hard to imagine today's smart production without it. Predictive Maintenance basically involves using measurement data from machines and systems in order to be able to determine the maintenance intervals of the individual components and machines based on this data. The aim of Predictive Maintenance is always to maintain the machines and systems proactively and with foresight, so that downtimes can be minimized and maintenance costs can also be reduced to a minimum. Ideally, Predictive Maintenance can accurately predict disruptions and problems so that a company can act before real outages occur, leading to persistent problems. As a result of Predictive Maintenance, production times and the service life of the machines used can be extended, as maintenance is always "on point". In addition, excessive costs can be effectively prevented by unnecessary maintenance intervals. Predictive Maintenance is an industry 4.0 tool that strengthens the productivity and effectiveness of production and provides companies with targeted information about the entire machine and plant park.
Predictive Maintenance vs. conventional maintenance approaches
Traditional maintenance was usually understood in a reactive way. Although reactive maintenance is very easy to implement, it poses a significant risk to companies. Only when errors and malfunctions occur does the system react and the problem is analyzed and the necessary corrective action taken. In contrast to Predictive Maintenance, reactive maintenance can neither prevent nor predict malfunctions, which often leads to considerable downtimes. In the worst case, the urgently needed spare parts for the repair of equipment and machines are not available, which considerably increases downtime. If such a case affects an entire production line or a machine important for the production process, this can in the worst case lead to economic problems for the company. Predictive Maintenance is therefore the safe and, above all, effective variant of maintenance that should now be standard in industry 4.0.
Three important steps for using Predictive Maintenance
If you want to rely on the principle of Predictive Maintenance in your own company, you must bear in mind that three important steps lead to effective and therefore long-term superior Predictive Maintenance:
- The collection, digitization and transmission of all relevant data
- The storage, analysis and evaluation of the collected data sets
- Calculation of probabilities for defined critical events
The first step is to create a database and to install the corresponding sensors on and in the machines. Since many manufacturers are now active in the field of industry 4.0 and its standards, such sensors are already integrated in many machines and systems. In the course of this, however, all relevant data must also be collected by the experts. Who only measures the naked data of the machine, but ignores for example values such as room temperature and humidity, the data often cannot be put into a meaningful context. Predictive Maintenance therefore always involves collecting as much data as possible.
In the second step, the data must be combined in a database and put in relation to each other. Many providers on the market offer practical solutions, which can be operated either in the data center of the provider or directly in the company itself. This is where the quality of the data and its possible applications are decided. Only through targeted and structured storage and fast access to the immense data sets, these can be analyzed by the intelligent algorithms.
The last step is crucial for Predictive Maintenance. In this step, default probabilities are calculated for all relevant components on the basis of the data collected. The better the data, the more accurate the probabilities can be calculated. Predictive Maintenance is based on these probabilities and predictions. Before an event X occurs, component Y can be replaced using Predictive Maintenance to prevent event X.
Overview of the advantages of Predictive Maintenance
Predictive Maintenance offers considerable advantages over other methods of maintenance: On the one hand, unplanned and thus often very expensive machine downtimes can be prevented. Thanks to comprehensive knowledge about the condition of the machines and their individual components, maintenance can be planned exactly as required, which noticeably and significantly increases the productivity of the machines. In addition, the field service assignments of employees can be planned better and thus made more efficient, as maintenance can be carried out specifically and at an intelligent interval. Spare parts management can also be considerably simplified, as the required spare parts are already known in advance and can be kept in stock accordingly. In addition, the continuous analysis of the machines and the read-out data offers the possibility of successively increasing the efficiency of the individual machines and thus optimising capacity utilisation. This allows the machines to amortize their investment costs more quickly and thus contribute to the economic success of the company. Overall, the benefits of Predictive Maintenance are enormous, even if the effort initially seems inconvenient for many users. However, once the system has established itself and the data is not only collected but also evaluated in a targeted manner, Predictive Maintenance can achieve enormous leaps in performance for many machines and systems. Predictive Maintenance is therefore once again a clear advantage for smart production, which is to adapt its performance to current demand and requirements. After all, the companies' flexibility is increasing enormously.
Preventive vs. Predictive: Differences are noticeable
Even if the terms preventive maintenance and Predictive Maintenance initially sound similar and are also used in a similar way, they still differ enormously. Similar to Predictive Maintenance, preventive maintenance also tries to avoid downtimes or to keep them as short as possible. However, no data is collected during preventive maintenance, but the maintenance intervals are determined according to a fixed pattern or according to past experience. In the worst case scenario, wear parts are replaced which still function smoothly. In the long run, this causes considerable costs, as the material costs for the company increase without a specific cause. On the other hand, excessive wear cannot be detected either. If a component wears out particularly quickly and, above all, faster than the maintenance schedule requires, an unforeseen breakdown occurs, which means additional costs for the company. In the end, preventive maintenance is all about guessing as well as possible or estimating, based on experience, when replacement and maintenance would make sense. It is of decisive importance for the cost-benefit factor to arrange maintenance and repairs as early as necessary and as late as possible. These points become obsolete with Predictive Maintenance. The condition of all relevant components can be checked on the basis of the data collected. This means that unworn components are neither replaced nor signs of wear are overlooked. Although the initial effort for this form of maintenance may seem higher, the data and data sets collected can be used specifically to improve the performance of the systems. This means that the data is not only available for Predictive Maintenance, but can also be used in a variety of ways within the company. In summary, this can be broken down into the following points:
- Fixed maintenance patterns
- Replacement of components independent of their wear
- High costs due to high demand for spare parts
- Can neither predict nor prevent breakdowns
- Maintenance depending on the condition of the machine or system
- Systematic replacement of worn parts
- Low costs due to fewer services and spare parts
- Failures are avoided and maintenance intervals are demand-oriented
Predictive Maintenance in relation to big data
The great difficulty for Predictive Maintenance is located in the processing and storage of the collected data records. For effective Predictive Maintenance, various data sets not only have to be collected, but also have to be stored, put in relation to each other and processed by intelligent algorithms. This combination is the only way to make reliable predictions about the condition of machines and thus enjoy the advantages of Predictive Maintenance. In addition, the data collected can all have completely different data formats and value variables. After all, not only the data of the machines and systems themselves play an important role, but also the associated environment variables. Temperature, humidity and air pressure can also play a role in many systems and in their wear. As part of Predictive Maintenance, enormous data streams are collected, which must be updated and processed at regular intervals. Only in this way trends and developments can be recorded on the basis of the various measurement data and made available for analysis.
However, this means that in the context of the smart industry and smart production enormously large databases with huge capacities must be used, which can process the collected data at the required speed. In general, you should always bear in mind that the size of the data basis and the performance of the algorithms used have a lasting influence on the quality and reliability of the findings obtained. Considering the economic side, on the one hand there are the investment costs for Predictive Maintenance, which can very quickly take on very large dimensions in many companies. On the other hand, however, there are decreasing costs for maintenance, service staff and spare parts and at the same time an increase in productivity. If these two cost centers are compared, the one-off investment costs and the running costs for Predictive Maintenance appear to be significantly lower than they initially appeared. The larger the machine park and the better the workload, the more the pendulum swings towards Predictive Maintenance.
Application examples of Predictive Maintenance
A very good example of the use of Predictive Maintenance can be found in many vehicles. Thanks to the extensive data collection by many different sensors it is possible to reduce expensive breakdowns and repairs of a vehicle to a minimum. For this purpose, the sensors record a wide variety of data in the engine and the chassis and compare them both with the optimum and with the data history. This means that any damage that may occur can be detected at an early stage and reported to the driver by the software. Even further are vehicles with networked telemetry, which are able to report this data directly to the workshop or the manufacturer of the vehicle. In such a case, not only the vehicle owner can be directly informed via such a system, but also the responsible authorised workshop. This means that it can stock up on the required spare parts at an early stage and thus reduce the repair time to a minimum.
Predictive Maintenance is also becoming increasingly popular in the industry. Thanks to the sensors also installed here, vibrations, temperatures and noise of a machine, for example, can be permanently monitored. Even the smallest deviations are thus registered and can, for example, indicate the failure of a bearing at an early stage. In such a case, the bearing can be replaced in time without further delays. Thanks to Predictive Maintenance, it is already known which component is to be replaced in which area of the machine, which also minimizes maintenance time. The downtimes of the entire machine and also the working time of the service technicians can thus be reduced to a minimum.
Some of the systems maintained by Predictive Maintenance in the industry include wind turbines. In this way, turbine downtimes can be reduced to a minimum through Predictive Maintenance. Thanks to intelligent mathematical algorithms, the vibration analysis of the various components can be optimally adjusted so that reliable predictions about failure probabilities of individual components are possible. If these forecasts are combined with the prevailing wind conditions and the planned downtimes of such a turbine, the replacement of the endangered components can be carried out early and thus without considerable effort. This saves time and costs and also prevents a longer and unplanned downtime of the entire system.