Predictive Maintenance: Efficiency in industry 4.0
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.