SVM State Classification for Apparatus Fault Cause Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fault monitoring systems for apparatuses face challenges in accurately capturing and understanding the complex relationships between operating parameters, making it difficult to determine the state and cause of faults, especially with numerous parameters involved.
Innovation Solution
The implementation of a support vector machine (SVM) that captures and processes operating parameters such as electrical voltage, current, acceleration, and temperature to classify the state of an apparatus into normal and fault states, predicting potential future faults by generating a temporal trajectory and identifying decisive parameters for fault occurrence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a large number of operating parameters are captured to improve fault monitoring accuracy, then measurement completeness is improved, but the complex relationships between parameters cause relevant values to be hidden and resolution deteriorates
Solution Approach 1:
The patent extracts and isolates the most relevant operating parameters from a large set of captured parameters using support vector machine analysis. By identifying and focusing on decisive parameters that have the greatest impact on fault states, the system extracts critical information while filtering out redundant data that would otherwise hide relevant values and complicate the analysis.
2Measurement precision
If manual analysis by experts is used to establish fault causes, then diagnostic accuracy can be achieved, but the process requires tedious manual work and is time-consuming
Solution Approach 1:
The patent implements a self-service diagnostic system where the support vector machine automatically analyzes operating parameters, identifies fault states, and determines causal relationships without requiring expert intervention. The system serves itself by autonomously processing data, generating trajectories, and providing diagnostic results, thereby eliminating tedious manual work while maintaining high diagnostic accuracy through machine learning algorithms.
3Measurement precision
If support vector machine is used to classify operating parameters, then state determination accuracy is improved, but the system complexity increases
Solution Approach 1:
The patent transforms the complex classification problem by changing parameters through the support vector machine approach. The SVM converts high-dimensional operating parameter data into a transformed feature space where classification boundaries become more manageable. By applying kernel functions and parameter transformations, the system achieves accurate state determination while the mathematical transformation simplifies the underlying complexity rather than increasing it.
Data Source
AI summary
The invention relates to a system and to a method for determining a state of a device by means of a trained support-vector machine. According to the invention, an operating parameter space is divided into classification volumes, at least one of which indicates a normal state and at least one other of which indicates a fault state of the device. A current state of the device can therefore be determined by determining where a current operating parameter point is to be arranged in the operating parameter space. The invention further relates to methods and to variants of the system in order to facilitate a cause evaluation and to determine particularly relevant operating parameters for the fault determination.