Machine Condition Monitoring With Adaptive Maintenance Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining maintenance requirements of machine parts are often inaccurate, leading to unnecessary downtimes and increased costs due to premature replacement of parts.
Innovation Solution
A diagnostic system that uses sensors to monitor machine parts and determine condition monitoring parameters, which are then compared to predetermined maintenance thresholds set based on inspection results of previously inspected parts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If machine parts are exchanged on a regular time base to prevent unexpected failures, then reliability is improved, but productivity deteriorates due to unnecessary downtimes and increased costs
Solution Approach 1:
The diagnostic device continuously monitors machine parts using sensors and compares actual condition parameters against dynamically updated maintenance thresholds. This feedback mechanism enables maintenance decisions based on real-time condition data rather than fixed schedules, preventing unnecessary replacements while ensuring timely intervention when parts actually need maintenance.
Solution Approach 2:
The system uses inspection results from previously inspected parts to automatically update maintenance thresholds, enabling the diagnostic system to self-optimize over time. This self-learning capability allows the system to adapt to specific machine behavior patterns and wear characteristics, improving accuracy without requiring external recalibration.
2Reliability
If machine parts are exchanged on a regular time base, then reliability is improved, but loss of substance increases due to unnecessary part replacements
Solution Approach 1:
The system continuously compares actual part condition parameters against maintenance thresholds to determine when replacement is truly necessary. This feedback-based decision-making prevents premature replacement of parts that have not yet reached their end of useful life, reducing waste and associated costs while maintaining operational safety.
Solution Approach 2:
The patent replaces time-based mechanical scheduling with condition-based monitoring using sensors and data processing. This substitution enables precise determination of maintenance needs based on actual part condition rather than arbitrary time intervals, eliminating unnecessary replacements and reducing material waste.
3Measurement precision
If simulation of failure through specific processing of machine parts is used to determine thresholds, then measurement precision is improved, but reliability deteriorates because it does not exactly represent actual wear
Solution Approach 1:
The diagnostic device automatically updates maintenance thresholds using inspection results from previously inspected parts of the same type. This self-learning mechanism enables the system to derive thresholds from actual operational data and real wear patterns observed in the specific machine environment, rather than relying on generic simulations that may not represent actual conditions.
Solution Approach 2:
The system performs preliminary inspections on machine parts before they fail, collecting data on their actual condition and wear patterns. These preliminary inspection results are then used to update maintenance thresholds, creating a proactive approach that captures real wear characteristics before failure occurs, thereby improving both precision and representativeness.
4Measurement precision
If maintenance thresholds are set based on inspection results of previously inspected parts, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The diagnostic device automatically updates its own maintenance thresholds using inspection results from previously inspected parts. This self-service capability eliminates the need for manual threshold setting and reduces dependency on external expert intervention, improving measurement precision while managing complexity through automation rather than human expertise.
Solution Approach 2:
The diagnostic device is designed to handle multiple functions including data acquisition, threshold determination, condition monitoring, and maintenance decision support within a single integrated system. This multi-functionality approach manages complexity by consolidating diverse operations into one unified platform rather than requiring separate systems for each function.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The subject matter described here relates to a method and a diagnostic system for reliably determining the maintenance requirement of a machine including a plurality of machine parts 1a, 1b, 1c. The method comprises the steps of receiving measuring signals from a plurality of sensors attached to the plurality of machine parts 1a, 1b, 1c; determining a condition monitoring parameter for each machine part 1a, 1b, 1c from the measuring signals; and requesting for maintenance of a machine part 1a, 1b, 1c if a condition monitoring parameter of said machine part 1a, 1b, 1c exceeds a predetermined maintenance threshold. In order to improve the accuracy of the predetermined maintenance threshold, the latter is determined based on inspection results of previously inspected machine parts 1a, 1b, 1c.