Component Health Monitoring with Adaptive Peak Count Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional health monitoring systems face challenges in accurately determining the health state of components due to noisy signals and variable degradation trends, leading to issues with setting proper thresholds for detection, resulting in either premature or missed notifications.
Innovation Solution
A health monitoring system that uses a sensor, such as an accelerometer, to generate status indicators, which are analyzed to determine if they exceed a dynamic threshold calculated as the mean value plus a configurable factor times the standard deviation, and counts peak occurrences to trigger maintenance notifications, rather than relying on overall trend analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional threshold-based monitoring is used, then the system is simple to operate, but it produces either premature or missed detections due to noisy signals and variable degradation trends
Solution Approach 1:
The system dynamically adapts the threshold based on the historical behavior and variability of each component's status indicators. Instead of using fixed thresholds, the system learns the component-specific patterns and adjusts thresholds accordingly, allowing accurate detection across diverse component types with varying degradation trends
Solution Approach 2:
The system performs preliminary learning during an initial period to establish baseline patterns and thresholds for each component before actual health monitoring begins. This preliminary action enables the system to adapt to component-specific characteristics and reduce false detections from the start of monitoring
2Measurement precision
If filtering or smoothing is applied to reduce noise, then the signal quality improves, but the response time to detect actual degradation increases
Solution Approach 1:
The system applies different processing strategies to different aspects of the signal. Noise reduction is applied selectively to distinguish genuine degradation peaks from random noise, while preserving the temporal characteristics of actual degradation events. The system identifies and counts peak occurrences that exceed adaptive thresholds, maintaining responsiveness to real changes
3Adaptability or versatility
If a single threshold is used for all component types, then the system is easy to implement, but it cannot accommodate different degradation trends of various components
Solution Approach 1:
The system implements a universal adaptive thresholding mechanism that automatically adapts to different component types and degradation patterns. The same core algorithm learns and adjusts thresholds based on the specific characteristics of each component, providing both universality across component types and adaptability to individual patterns without requiring manual configuration
Data Source
AI summary
A health monitoring system includes at least one sensor. A health monitoring unit (HMU) is operatively connected to the at least one sensor to receive data therefrom and to generate at least one status indicator (SI) based on the data from the at least one sensor. A computing device is operatively connected to the HMU to receive data therefrom and is configured to generate a health notification when a quantity of the SI that are greater than or equal to a pre-determined SI threshold exceed a pre-determined peak count threshold. A method for monitoring and determining the health of a component includes collecting data during a sample cycle from at least one sensor to generate a numerical SI for a given component with a computing device. The method includes identifying if the numerical SI qualifies as a peak SI, which is greater or equal to a pre-determined SI threshold.