Component Signal Monitoring Using Probabilistic Reference Deviation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for monitoring the functional behavior of technical components are inaccurate due to arbitrary threshold settings, ignoring external factors like ambient conditions and installation-dependent variables, leading to uncertainty in detecting abnormal behavior.
Innovation Solution
A method that compares the signal of a component with a reference signal describing average functional behavior, determining a comparison variable for deviation and calculating its probability of occurrence using a definable distribution, allowing for dynamic assessment and high sensitivity to small deviations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If fixed threshold values are used for monitoring component behavior, then the monitoring method is simple to implement, but the measurement precision and reliability are poor due to arbitrary threshold selection and inability to account for external factors
Solution Approach 1:
The patent applies preliminary action by collecting and analyzing data from multiple identical components during a learning phase before actual monitoring begins. This pre-processing establishes reference signals that account for external factors and natural variations, enabling accurate anomaly detection without requiring arbitrary threshold settings during operation
Solution Approach 2:
The patent uses copying by creating reference signals from data collected from multiple identical components. These reference signals serve as templates representing normal behavior, allowing the system to compare individual component signals against these copied patterns rather than using fixed thresholds, thereby improving detection accuracy
2Ease of operation
If fixed threshold values are used for monitoring component behavior, then the monitoring system is simple to operate, but the reliability of detecting abnormal behavior is low due to uncertainty in threshold selection
Solution Approach 1:
The patent implements feedback by continuously comparing individual component signals against reference signals derived from multiple identical components. The system calculates deviation values and determines whether these deviations exceed dynamically established thresholds based on the statistical distribution of deviations from the reference, providing reliable anomaly detection while maintaining operational simplicity
Solution Approach 2:
The patent applies parameter changes by transitioning from fixed threshold values to dynamically determined thresholds based on the statistical analysis of deviation values. The threshold is established as a function of the standard deviation of deviations from the reference signal, allowing the system to adapt to varying operating conditions and external factors while maintaining ease of operation
3Device complexity
If arbitrary threshold values are used, then the monitoring method requires minimal data processing, but the functional behavior assessment is inaccurate and subject to great uncertainty
Solution Approach 1:
The patent applies preliminary action by performing comprehensive data collection and statistical analysis during an initial learning phase. This pre-processing establishes reference signals and determines the statistical distribution of deviations, enabling accurate functional behavior assessment without requiring complex real-time calculations during operation
Solution Approach 2:
The patent implements feedback by continuously comparing individual component signals against reference signals and calculating deviation values. The system determines whether deviations exceed dynamically established thresholds based on the statistical distribution of deviations from the reference, providing accurate functional behavior assessment through systematic data processing
Data Source
AI summary
An improved method for investigating a functional behavior of a component of a technical installation includes comparing a signal of the component to be investigated and representing the functional behavior of the component with a reference signal which describes an average functional behavior of identical components. During the comparison, a comparison variable describing the deviation of the signal from the reference signal is determined. In addition, a probability of the occurrence of the comparison variable is determined by using a predefinable distribution of a multiplicity of such comparative variables. A computer program and a computer readable storage medium are also provided.