Single-Sensor Engine Multi-Type Fault Detection

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 3; p. 1642
• Main Authors: Tang, Daijie, Bi, Fengrong, Cheng, Jiangang, Yang, Xiao, Shen, Pengfei, Bi, Xiaoyang
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 02.02.2023; MDPI
• Subjects: Artificial intelligence; Classification; Efficiency; Engines; Fault detection; Fault location (Engineering); Fourier transforms; Machine learning; Methods; Neural networks; random forest; Signal processing; single-sensor data; Spectral energy distribution; Spectrum analysis; variational mode decomposition; vibration; China; single-sensor data; variational mode decomposition; random forest; vibration; fault detection
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23031642

Engine fault detection is conducive to improving equipment reliability and reducing maintenance costs. In practical scenarios, high-quality data is difficult to obtain. Usually, only single-sensor data is available. This paper proposes a fault detection method combining Variational Mode Decomposition (VMD) and Random Forest (RF). At first, the spectral energy distribution is obtained by decomposing and statistic the engine data of multiple working conditions. Based on the spectral energy distribution, the overall optimal mode number was identified, and the quadratic penalty term was optimized using SNR. The improved VMD (IVMD) improves mode aliasing and iterative efficiency and unifies feature dimensions. Decomposition of real signals demonstrates the effectiveness. The paper designs a feature vector composed of seven types of attributes, including unit bandwidth energy, center frequency, maximum singular value and so on. The feature vector is then fed to RF for classification. Features are selected in order of importance to classification to improve the training efficiency. By comparing with various algorithms, the proposed method has higher accuracy and faster training efficiency in single-speed, multi-speed and cross-speed single-sensor data diagnosis. The results show that the method has application prospects with little training data and low hardware requirements.