Zero-Sequence Current Fault Diagnosis for Transmission Chains
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fault diagnosis methods for rotating machinery, particularly in industrial transmission systems, face challenges such as high costs due to sensor requirements, interference, and sensitivity to initial conditions, and lack robustness and universality in feature extraction, especially when using single-phase current signals.
Innovation Solution
A fault diagnosis method based on joint entropy enhanced sparse learning using zero sequence current, which involves data preprocessing, establishment of a rotating machinery fault diagnosis model, and utilization of a sparse autoencoder with improved loss functions to extract representative features from zero sequence current signals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If vibration-based fault diagnosis methods are used, then fault information can be obtained, but sensor mounting costs increase and system interference occurs
Solution Approach 1:
The patent replaces the mechanical vibration-based diagnosis system with an electrical current-based system. Instead of using vibration sensors that require mechanical mounting on rotating machinery, the invention utilizes current sensors that measure electrical current in the power transmission system, thereby eliminating the need for mechanical sensor installation while still achieving fault detection through signal analysis
Solution Approach 2:
The patent introduces current signals as an intermediary medium for fault diagnosis. Rather than directly measuring mechanical vibration, the system uses electrical current as a mediator that reflects the mechanical state of the transmission system, allowing indirect but effective fault detection without mechanical sensor contact
2Device complexity
If single-phase current signals are used for diagnosis, then the method is simple, but diagnosis accuracy decreases due to limited information
Solution Approach 1:
The patent merges three-phase current signals into a unified zero-sequence current signal for fault diagnosis. By combining the information from all three phases and extracting the zero-sequence component, the system achieves comprehensive fault detection capability while maintaining algorithmic simplicity, effectively resolving the trade-off between method complexity and diagnostic accuracy
Data Source
AI summary
A fault diagnosis method for a transmission chain based on joint entropy enhanced sparse learning using a zero sequence current includes the following steps: data acquisition and preprocessing; establishment of a rotating machinery fault diagnosis model for sparse feature learning of a zero sequence current; and obtaining of a diagnosis result by inputting the preprocessed zero sequence current data to the trained rotating machinery fault diagnosis model. The fault diagnosis method for a transmission chain based on joint entropy enhanced sparse learning using a zero sequence current can extract a weak fault feature in a current signal automatically and efficiently without relying on traditional signal processing techniques and diagnosis experience, and has good robustness for signals containing noise.