US 12,033,059 B2
Method for predicting bearing life based on hidden Markov model and transfer learning
Jun Zhu, Suzhou (CN); Changqing Shen, Suzhou (CN); Nan Chen, Suzhou (CN); Dongmiao Song, Suzhou (CN); Jianqin Zhou, Suzhou (CN); Jun Wang, Suzhou (CN); Juanjuan Shi, Suzhou (CN); Weiguo Huang, Suzhou (CN); and Zhongkui Zhu, Suzhou (CN)
Assigned to SOOCHOW UNIVERSITY, Suzhou (CN)
Appl. No. 17/285,348
Filed by SOOCHOW UNIVERSITY, Suzhou (CN)
PCT Filed Aug. 7, 2020, PCT No. PCT/CN2020/107716
§ 371(c)(1), (2) Date Apr. 14, 2021,
PCT Pub. No. WO2021/042935, PCT Pub. Date Mar. 11, 2021.
Claims priority of application No. 201910838978.8 (CN), filed on Sep. 5, 2019.
Prior Publication US 2021/0374506 A1, Dec. 2, 2021
Int. Cl. G06N 3/04 (2023.01); G06N 3/047 (2023.01); G06N 3/08 (2023.01)
CPC G06N 3/047 (2023.01) [G06N 3/08 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A method for predicting bearing life based on a hidden Markov model and transfer learning, comprising the following steps:
(1) acquiring an original signal of full life of the operation of a rolling bearing;
(2) extracting a time domain feature, a time-frequency domain feature, and a trigonometric function feature from the original signal, to form a feature set;
(3) converting the feature set into an observation sequence to input the observation sequence into the hidden Markov model, and predicting a hidden state in an unsupervised manner, to obtain a failure occurrence time;
(4) using the feature set of the operation of the rolling bearing after the failure occurrence time for life prediction of the rolling bearing: constructing a multilayer perceptron model according to a transfer learning framework, combining feature sets from all source domains and some target domains into a training set to input the training set into the multilayer perceptron model, training a proposed optimized target to obtain a domain invariant feature and an optimal model parameter, and substituting the optimal model parameter into the perceptron model to obtain a neural network life prediction model; and
(5) combining the remaining target domain feature sets into a test set to input the test set into the neural network life prediction model, and predicting the remaining life of the bearing according to an output value.