2018 Vol.1 Jun No.3

• Title: Synchronous Optimization Simulation Research on Gear Mechanical Fault Characteristics and Model Parameters
• Name: Langdon Fearghus
• Company: Buckinghamshire New University, England
• Abstract:

  The traditional gear fault detection method does not consider the relationship between gear mechanical fault characteristics and KNN parameters, and optimizes them separately and separately, resulting in low accuracy of gear mechanical fault diagnosis. In this paper, a gear mechanical fault detection model (GA-KNN) with fault characteristics and detection model parameters is proposed. Firstly, the mathematical model of gear mechanical fault detection is constructed by using candidate feature subsets and near-K-parameter parameters, and then the mathematical model is solved by improved genetic algorithm to obtain better accuracy of gear mechanical fault diagnosis. Finally, the performance of the model was tested by simulation experiments. Under the same conditions, compared with the comparison model, the model can obtain the most gear mechanical fault detection model parameters and feature subsets at the same time, which not only improves the mechanical detection accuracy, but also improves the gear mechanical fault detection efficiency.

• Keyword: feature optimization; genetic algorithm; K nearest neighbor algorithm; gear mechanical fault detection
• DOI: 10.12250/jpciams2018030113
• Citation form: Langdon Fearghus.Synchronous Optimization Simulation Research on Gear Mechanical Fault Characteristics and Model Parameters[J]. Computer Informatization and Mechanical System, 2018, vol. 1, pp. 35-41.

[1] Xiong Guoliang, Zhang Long, Chen Hui. Application of TvAR in rotor fault diagnosis under non-stationary conditions[J]. Vibration, Testing & Diagnosis,2007,27(2):108-11.
[2] YUAN Yu, MA Xiaojiang. Application of local wave time-frequency domain multifractal in fault diagnosis[J].Journal of Vibration and Shock,2007,26(5):60-63.
[3] Lu Yong, Li Yourong, Wang Zhigang. Fault diagnosis of rolling mill main drive reducer based on empirical mode decomposition[J]. Vibration, Testing & Diagnostics,2007,27(2):112-116.
[4]Yang Yu, Yu Dejie, Cheng Junsheng. A roller bearing fault diagnosis method based on EMD energy entropy and ANN[J]. Journal of Sound and Vibration, 2006,294(1-2):269-277.
[5]LeiYaguo, He Zhengjia, Zi Yanyang, et al. Fault diagnosisof rotating machinery based on multiple ANFIS combination with GAs[J]. Mechanical Systems and Signal Processing, 2007,21(5):2 280-2 294.
[6] Comet, Lu Junfeng, Zhao Mengna. Rotating machinery fault diagnosis method based on principal component analysis and multivariate support vector machine [J]. Journal of Sichuan Armed Forces, 2010,31(9):83-86.
[7] Sun Yan,Lu Shizhao,Tang Yiyuan. KNN algorithm without prior conditional constraints[J].Mini-microcomputer system, 2008,29(4):682-686.
[8] Wang Xinfeng, Qiu Jing, Liu Champ. Joint optimization of mechanical fault characteristics and classifiers[J]. Journal of National University of Defense Technology, 2005,27(92):92-95.
[9] LI Liangmin, WEN Guangrui. Multi-scale Support Vector Machine Based on Genetic Algorithm and Its Application in Mechanical Fault Diagnosis[J]. Mechanical Science and Technology, 2008,27(8):1101-1106.
[10] Zhang Qiang. PPCA-based Rotating Machinery Fault Identification Algorithm[J]. Computer Simulation, 2011,28(12):335-338.