Fault Detection in Rotary Machines via Subspace Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current fault detection methods for rotary machines rely heavily on expert knowledge and are not effective in accurately identifying nonlinear faults such as sliding friction and loose connections, especially in noisy environments.
Innovation Solution
A model-based fault detection method that uses Singular Value Decomposition (SVD) to analyze the dynamic behavior of rotary machines, forming an over-determined set of linear equations and extracting the number of states needed to accurately model the process, which helps in detecting nonlinear faults by indicating the order of the state space system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If expert knowledge-based fault detection methods are used, then the detection process is simple to implement, but the accuracy in identifying nonlinear faults is insufficient
Solution Approach 1:
The patent replaces expert knowledge-based mechanical judgment with a mathematical model-based detection system. By using subspace identification and singular value decomposition to analyze the relationship between input and output data, the system automatically identifies nonlinear faults without relying on expert experience, thereby improving detection accuracy while maintaining implementation feasibility
Solution Approach 2:
The patent changes the detection parameters from qualitative expert judgment to quantitative analysis of the number of states in the system model. By monitoring changes in the estimated number of states through singular value decomposition, the system can detect nonlinear faults such as sliding friction and loose connections, achieving high accuracy in fault identification
2Reliability
If traditional vibration analysis methods are used, then the measurement process is simple, but the ability to detect nonlinear faults in noisy environments is poor
Solution Approach 1:
The patent introduces an intermediary mathematical model (subspace identification model) that mediates between the raw vibration signals and the fault detection process. This model separates the linear system behavior from nonlinear fault characteristics, enabling reliable detection of nonlinear faults even in noisy environments by analyzing the residual differences between model predictions and actual measurements
Solution Approach 2:
The patent creates a mathematical copy of the system's dynamic behavior through state-space modeling. By comparing the modeled behavior with actual measurements, the system can identify deviations caused by nonlinear faults, achieving reliable detection independent of noise levels in the original signals
Data Source
AI summary
Modem rotary machine production requires built-in fault detection and diagnoses. The occurrence of faults, e.g. increased friction or loose bonds has to be detected as early as possible. Theses faults generate a nonlinear behavior. Therefore, a method for fault detection and diagnosis of a rotary machine is presented. Based on a rotor system model for the faulty and un-faulty case, subspace-based identification methods are used to compute singular values that are used as features for fault detection. The method is tested on an industrial rotor balancing machine.