Application of Axis Orbit Image Optimization in Fault Diagnosis for Rotor System

Abstract

The shape characteristic of the axis orbit plays an important role in the fault diagnosis of rotating machinery. However, the original signal is typically messy, and this affects the identification accuracy and identification speed. In order to improve the identification effect, an effective fault identification method for a rotor system based on the axis orbit is proposed. The method is a combination of ensemble empirical mode decomposition (EEMD), morphological image processing, Hu invariant moment feature vector, and back propagation (BP) neural network. Experiments of four fault forms are performed in single-span rotor and double-span rotor test rigs. Vibration displacement signals in the X and Y directions of the rotor are processed via EEMD filtering to eliminate the high-frequency noise. The mathematical morphology is used to optimize the axis orbit including the dilation and skeleton operation. After image processing, Hu invariant moments of the skeleton axis orbits are calculated as the feature vector. Finally, the BP neural network is trained to identify the faults of the rotor system. The experimental results indicate that the time of identification of the tested axis orbits via morphological processing corresponds to 13.05 s, and the identification accuracy rate ranges to 95%. Both exceed that without mathematical morphology. The proposed method is reliable and effective for the identification of the axis orbit and aids in online monitoring and automatic identification of rotor system faults.

Axis Orbit Recognition of the Hydropower Unit Based on Feature Combination and Feature Selection

“…Xue et al [ 26 ] applied the fuzzy closeness feature of time series to extract the characteristic parameters of the axis orbit and optimized the SVM model for fault classification to improve the accuracy of hydraulic turbine diagnosis. Pang et al [ 28 ] proposed a rotor system fault-identification method based on the axis orbit, integrating empirical mode decomposition (EEMD), morphological image processing, Hu invariant moment eigenvector, and the back-propagation (BP) neural network. The existing axis-orbit recognition methods have low recognition accuracy and poor robustness, while scholars primarily focus on the pattern recognition of axis orbits with single dimensions of feature set.…”

A Technique for Centrifugal Pump Fault Detection and Identification Based on a Novel Fault-Specific Mann–Whitney Test

“…Non-destructive testing methods, including orbit analysis [8], deflection shape analysis [9], acoustic emission (AE) analysis [10], and vibration signal (VS)-based monitoring, are used for the intelligent fault diagnosis of CPs [11]. A fault in the mechanical specimen will change the stiffness of the material, which will result in a shock in the VS that appears at a specific frequency, providing an overall picture of the status of the machine.…”

An intelligent fault diagnosis scheme for hydropower units based on the pattern recognition of axis orbits

“…However, the fault information of a single vibration measuring point is not sufficient for a comprehensive evaluation of the unit status. As an important indicator for fault diagnosis of hydropower units, the axis orbit is synthesized by multiple vibration signals of measuring points in the X and Y directions, which contains more information on vibration and operating conditions of the unit, and can display the rotor's running condition of the hydropower unit more intuitively [20]. The axis orbit shows different characteristics when failures occur, and changes in shape and size.…”