Predictive Maintenance

FAQ

What is the definition of Condition Monitoring and Predictive Maintenance?

Predictive maintenance is a proactive maintenance strategy that uses data and analysis from Condition Monitoring to evaluate the condition of assets and predict their failure. Predictive Maintenance is subject to the objective of minimizing unplanned downtime by performing maintenance before equipment failure occurs. At the same time, only necessary maintenance is performed, which significantly reduces maintenance costs. Condition Monitoring is usually limited to the use of sensors and other monitoring devices that collect data on the performance and condition of equipment. The collected data is stored in a structured manner and made available to predictive maintenance algorithms via standardized interfaces.

How do Predictive Maintenance and Condition Monitoring work together?

• Data Collection (Condition Monitoring): Sensors and other monitoring devices are installed on assets to collect data about their performance and condition. The sensors collect data on various parameters such as temperature, vibration, pressure or sound. At the same time, information is extracted from the asset controls, such as program sequences or machine faults. Data from different assets are continuously collected at specific time intervals and stored centrally in accessible databases.
• Predictive Modeling (Predictive Maintenance): Based on data analysis, predictive models are created that predict when maintenance is required based on the current condition of the asset. The predictive models use statistical and machine learning algorithms to analyze the data and identify anomalies, patterns, and trends that indicate when equipment failure is likely.
• Maintenance Planning (Predictive Maintenance): The information provided by the predictive models is used to plan maintenance more efficiently. The maintenance team uses the information to schedule maintenance when it is needed, rather than when equipment fails. This way, maintenance can be performed during the scheduled downtime, rather than when an unexpected failure occurs.

What are the benefits of Predictive Maintenance and Condition Monitoring?

• Reduced Downtime: By proactively identifying and correcting equipment problems, Predictive Maintenance helps reduce downtime caused by unplanned equipment failures. This can lead to higher productivity and lower costs for the business.
• Minimized Maintenance Costs: Predictive Maintenance helps minimize maintenance costs because maintenance can be performed during planned downtime rather than as a result of an unexpected failure. In addition, by proactively identifying equipment problems, companies can schedule maintenance more efficiently, reducing the need for emergency repairs. At the same time, unnecessary maintenance calls are avoided, which in turn saves on maintenance costs.
• Longer Equipment Life: By proactively addressing equipment issues, Predictive Maintenance can help extend equipment life. This can lead to reduced costs for the business, as equipment is less likely to need to be replaced more frequently.
• Increased Safety: Predictive Maintenance helps increase safety in industrial and manufacturing operations by reducing the risk of equipment-related accidents. It does this by both avoiding unnecessary maintenance calls and reducing the likelihood of potentially safety-threatening machine failures.

What is an example of a use case for Predictive Maintenance and Condition Monitoring?

An application example for Condition Monitoring and Predictive Maintenance would be the operation of Coordinate Measurement Machines (CMMs) and machine tools in production. For both types of devices, control data such as program sequences or machine errors, as well as additional data from temperature and vibration sensors, would be continuously extracted and stored. The data is made accessible for visualization in a dashboard, so Condition Monitoring allows machine operators to know at a glance the operating states of many machine tools on the shopfloor or CMMs in different measuring rooms, if necessary. As soon as a program finishes running, a machine error occurs or environmental conditions become problematic, this can be detected via the dashboard. In this way, an operator can more reliably take care of more machines or devices without having to be present locally all the time.

At the same time, via the Predictive Maintenance functionalities of the software, the operator receives a message as soon as a critical asset condition is predicted in the short or medium term. This can refer to the wear of a tool for the machine tool, to a machine component such as a bearing, or to the measurement capability of the CMM. In this way, necessary maintenance, calibration or service activities can then already be predicted and planned before unplanned and thus expensive downtime occurs.