Acoustic Resonance Fast Detection Method of Harmonic Reducer Based on Support Vector Machine Algorithm

Abstract

Assembly error abnormal quality testing of harmonic reducers is an important part of the pre-delivery process of manufacturers and focuses on abnormality assessment, which can reduce financial losses due to product recalls and further protect the interests of users and the reputation of manufacturers. Sound signals offer the benefit of simple and non-contact measurements for acoustic resonance testing and can facilitate pre-delivery fast factory testing of harmonic reducers. This paper presents an experimental method for sound data acquisition, feature extraction and analysis. Hammered excitation of a harmonic reducer is used to obtain acoustic datasets for both abnormal and normal harmonic reducers. Time and frequency domain features of the sound signals are extracted, and the classification algorithms of support vector machine(SVM), random forest(RF) and K-means are compared. The results show that the accuracy of SVM on the test set is 98. 0%, that of RF is 95. 0%, and that of K-means is only 53. 0%. The SVM classifier's accuracy, recall, and F1 scores are high. Based on the SVM harmonic reducer quality detection model, the national instrument(NI) data acquisition card and Labview are used to design the harmonic reducer fast detection software for the harmonic reducer pre-delivery inspection of manufacturers.

Keywords

harmonic reducer / acoustic resonance testing / feature extraction / classification analysis / support vector machine(SVM) algorithm

References

[1] MUSSER C W. The harmonic drive[J]. Machine Design, 1960,14:160-173.

[2] MASOUMI M, ALIMOHAMMADI H. An investigation into the vibration of harmonic drive systems[J]. Frontiers of Mechanical Engineering, 2013, 8(4):409-419.

[3] ZHAO Y Q. Damage detection and performance evaluation of harmonic reducer based on sound signal and acoustic emission[D]. Shanghai: Donghua University, 2023. (in Chinese)

[4] SHIROISHI J, LI Y, LIANG S, et al. Bearing condition diagnostics via vibration and acoustic emission measurements[J]. Mechanical Systems and Signal Processing, 1997, 11(5):693-705.

[5] WANG H C. Research on crack identification of parts based on resonance acoustic nondestructive testing technology[D]. Taiyuan: North University of China, 2019. (in Chinese)

[6] JATZLAU P, MÜLLER M, GROSSE C U. Identification of flawed CFPR samples using local acoustic resonance spectroscopy (LARS) [C]//19th World Conference on Non-Destructive Testing. Munich: DGZfP, 2016.

[7] JU Y C, KRALJEVSKI I, NEUNÜBEL H, et al. Acoustic resonance testing of small data on sintered cogwheels[J]. Sensors, 2022, 22(15):5814.

[8] ZHANG S N, WANG F L, YOU F Q, et al. Robust least squares support vector machine based on robust learning algorithm and its application[J]. Control and Decision, 2010, 25(8):1169-1172,1177. (in Chinese)

[9] CERVANTES J, GARCIA-LAMONT F, RODRÍGUEZ-MAZAHUA L, et al. A comprehensive survey on support vector machine classification:applications,challenges and trends[J]. Neurocomputing, 2020,408:189-215.

[10] HEINRICH M, VALESKE B, RABE U. Efficient detection of defective parts with acoustic resonance testing using synthetic training data[J]. Applied Sciences, 2022, 12(15):7648.

[11] YIN Y, XIE L F, HUANG T B. A deep learning method for magnetic tile internal defect inspection based on acoustic vibration[J]. China Measurement & Test, 2020, 46(3):32-38. (in Chinese)

[12] TANDON N, CHOUDHURY A. A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings[J]. Tribology International, 1999, 32(8):469-480.

[13] XU Y, XIE G S, SHENG X W, et al.The invention relates to a method and device for a quick inspection of harmonic speed reducer:CN, 202211211977.9[P].2022-09-30. (in Chinese)

[14] LI M, YANG J H, WANG X J. The cyclic spectrum density method based on entropy and its application to the fault diagnosis of rolling bearings[J]. Journal of Vibration Engineering, 2015, 28(1):164-174. (in Chinese)

[15] YU Y, LI Y, YANG P, et al. Improved wavelet threshold function and ACEWT method for feature extraction of acoustic emission signals from rolling bearing faults[J]. Journal of Vibration and Shock, 2023, 42(17):194-202. (in Chinese)

[16] SCHNABEL S, GOLLING S, MARKLUND P, et al. The influence of contact time and event frequency on acoustic emission signals[J]. Proceedings of the Institution of Mechanical Engineers,Part J:Journal of Engineering Tribology, 2017, 231(10):1341-1349.

[17] LIU M H, LU J G, ZHANG J K, et al. Fault diagnosis of gearbox rolling bearing based on VMD energy entropy[J]. Coal Mine Machinery, 2023, 44(10):173-175. (in Chinese)

Funding

National Natural Science Foundation of China(52375528)