Driving Unit Predictive Maintenance Using Peak Interval Baselines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current predictive maintenance methods for driving units are inadequate in detecting abnormal conditions in a timely and reliable manner, leading to significant losses due to unexpected downtime and malfunction.
Innovation Solution
A precise predictive maintenance method that measures and collects peak intervals, mean values, and median values between the highest and lowest points of a driving period, setting alarm limits and gradient values based on collected data, and issues alarms when real-time measurements exceed these limits, indicating potential abnormalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional predictive maintenance methods are used, then the system can detect some abnormal conditions, but the detection reliability and timeliness are insufficient leading to unexpected downtime
Solution Approach 1:
The patent segments the driving period into multiple sub-periods and calculates statistical parameters (mean, median, peak interval) for each segment. This segmentation allows for more granular analysis of driving patterns and improves the reliability of abnormal condition detection by comparing actual parameters against historically established baselines for each specific segment.
Solution Approach 2:
The system performs preliminary actions by collecting and analyzing driving information during normal operating conditions to establish baseline statistical parameters before malfunctions occur. These pre-established baselines enable timely detection of deviations from normal operation, allowing maintenance to be scheduled before actual failures happen.
2Measurement precision
If multiple statistical parameters are measured and compared against alarm limits, then the precision of abnormal condition detection is improved, but the complexity of the maintenance system increases
Solution Approach 1:
The patent applies a universal maintenance system that handles multiple types of driving units (motors, pumps, conveyors, compressors) through a common architecture. The system universally collects driving information, calculates the same set of statistical parameters (mean, median, peak interval) for all devices, and uses consistent alarm limit comparison methods, thereby improving detection precision without proportionally increasing complexity.
Solution Approach 2:
The system transforms raw driving information into multiple derived statistical parameters (mean value, median value, peak interval, gradient values) and compares these transformed parameters against alarm limits. This parameter transformation approach improves detection precision by capturing different aspects of abnormal conditions while maintaining manageable system complexity through standardized processing.
Data Source
AI summary
The present invention relates to a precise predictive maintenance method for a driving unit and a configuration thereof includes a first base information collecting step S10 of dividing change information of an energy size, a second base information collecting step S20 of connecting a peak interval between a highest point and a lowest point of a driving period in a driving state of the driving unit; a setting step S30 of setting an alarm gradient value, and a detecting step S40 of detecting the driving unit as an abnormal state.