Redundant Equipment Anomaly Prediction With Adaptive Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current predictive maintenance methods for industrial equipment are not sensitive enough and have a high false alarm rate, leading to unnecessary equipment replacements and inefficiencies in anticipating failures in parallel-operating rotary machines.
Innovation Solution
A method that records and processes measurements of operating parameters from redundant equipment over time to establish coefficients of determination, noise evaluation, and threshold adjustments, enabling early detection of malfunctions and reducing false failure declarations by comparing the evolution of parameters between identical or similarly operating machines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current predictive maintenance methods are used to monitor equipment parameters, then failure detection is achieved, but false alarm rate is high leading to unnecessary replacements
Solution Approach 1:
The patent creates virtual copies of healthy equipment behavior through digital twins and historical data modeling. By comparing actual equipment parameters against these virtual copies, the system can distinguish between normal variations and true anomalies, significantly reducing false alarms while maintaining high failure detection accuracy.
Solution Approach 2:
The system implements continuous feedback loops where detection results are fed back into the model to refine future predictions. By analyzing false alarm patterns and adjusting thresholds dynamically, the system learns from past errors and improves its discrimination between normal and abnormal conditions over time.
2Loss of time
If early failure detection is implemented to improve maintenance timing, then maintenance planning is optimized, but equipment may be replaced needlessly due to insufficient sensitivity
Solution Approach 1:
The system performs preliminary analysis of equipment parameters using digital twins and predictive models before actual failures occur. By simulating various failure scenarios and comparing against real-time data, the system prepares maintenance plans in advance while maintaining confidence in the predicted failures, avoiding unnecessary replacements.
Solution Approach 2:
The patent monitors multiple parameters simultaneously and analyzes their combined evolution rather than relying on single-parameter thresholds. By tracking parameter trends, correlations, and deviations from predicted behavior, the system can confidently identify true failures and distinguish them from normal operational variations.
3Measurement precision
If monitoring of multiple operating parameters is performed to improve prediction accuracy, then failure anticipation is enhanced, but system complexity increases
Solution Approach 1:
The digital twin platform serves multiple functions simultaneously: it simulates equipment behavior, predicts failures, analyzes parameter correlations, and generates maintenance recommendations. This multi-functional approach consolidates what would otherwise require multiple separate systems into a single unified platform, managing complexity while enhancing prediction accuracy.
Solution Approach 2:
The patent introduces digital twins as intermediaries between physical equipment and analysis systems. These virtual models absorb the complexity of multiple parameter interactions, allowing the actual monitoring system to query simplified representations rather than directly processing all raw sensor data, thereby reducing system complexity while maintaining high prediction accuracy.
Data Source
AI summary
A method for predicting an operating anomaly comprises steps of (i) taking an assembly comprising at least a first and a second equipment item, each equipment item comprising a first operating parameter, (ii) recording and storing measurements over time of the first parameters for the first and the second equipment items, (iii) collecting the measurements during or after the completion of at least one part of an operating cycle, (iv) processing the collected measurements to detect a possible malfunction of the first and second equipment items by establishing a coefficient of determination, (v) emitting a first notification indicating the possible malfunction and/or triggering additional steps if the first coefficient of determination is less than a first threshold, and (vi) emitting a second notification and/or adjusting the first threshold if the first coefficient of determination is greater than or equal to the first threshold.