A transfer learning based geometric position-driven machining error prediction method for different working conditions*

2021 ◽  
Author(s):  
Teng Zhang ◽  
Hao Sun ◽  
Lin Zhou ◽  
Shengqiang Zhao ◽  
Fangyu Peng ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Working Conditions ◽  
Prediction Method ◽  
Error Prediction ◽  
Machining Error

scholarly journals A New Error Prediction Method for Machining Process Based on a Combined Model

2018 ◽  
Vol 2018 ◽  
pp. 1-8 ◽  
Author(s):  
Wei Zhou ◽  
Xiao Zhu ◽  
Jun Wang ◽  
Yan Ran
Keyword(s):  
Neural Network ◽  
Prediction Method ◽  
Machining Process ◽  
Error Prediction ◽  
Combined Model ◽  
Machining Error ◽  
Advantages And Disadvantages ◽  
Model Combining ◽  
Machining Errors ◽  
The Individual

Machining process is characterized by randomness, nonlinearity, and uncertainty, leading to the dynamic changes of machine tool machining errors. In this paper, a novel model combining the data processing merits of metabolic grey model (MGM) with that of nonlinear autoregressive (NAR) neural network is proposed for machining error prediction. The advantages and disadvantages of MGM and NAR neural network are introduced in detail, respectively. The combined model first utilizes MGM to predict the original error data and then uses NAR neural network to forecast the residual series of MGM. An experiment on the spindle machining is carried out, and a series of experimental data is used to validate the prediction performance of the combined model. The comparison of the experiment results indicates that combined model performs better than the individual model. The two-stage prediction of the combined model is characterized by high accuracy, fast speed, and robustness and can be applied to other complex machining error predictions.

scholarly journals Rolling Bearing Fault Prediction Method Based on QPSO-BP Neural Network and Dempster–Shafer Evidence Theory

Energies ◽  
2020 ◽  
Vol 13 (5) ◽  
pp. 1094 ◽  
Author(s):  
Lanjun Wan ◽  
Hongyang Li ◽  
Yiwei Chen ◽  
Changyun Li
Keyword(s):  
Neural Network ◽  
Working Conditions ◽  
Bp Neural Network ◽  
Evidence Theory ◽  
Prediction Method ◽  
Rolling Bearing ◽  
Fault Prediction ◽  
Fault Classification ◽  
Bearing Fault ◽  
Hidden Layer

To effectively predict the rolling bearing fault under different working conditions, a rolling bearing fault prediction method based on quantum particle swarm optimization (QPSO) backpropagation (BP) neural network and Dempster–Shafer evidence theory is proposed. First, the original vibration signals of rolling bearing are decomposed by three-layer wavelet packet, and the eigenvectors of different states of rolling bearing are constructed as input data of BP neural network. Second, the optimal number of hidden-layer nodes of BP neural network is automatically found by the dichotomy method to improve the efficiency of selecting the number of hidden-layer nodes. Third, the initial weights and thresholds of BP neural network are optimized by QPSO algorithm, which can improve the convergence speed and classification accuracy of BP neural network. Finally, the fault classification results of multiple QPSO-BP neural networks are fused by Dempster–Shafer evidence theory, and the final rolling bearing fault prediction model is obtained. The experiments demonstrate that different types of rolling bearing fault can be effectively and efficiently predicted under various working conditions.

scholarly journals A phase-error prediction method for coherent beam combining via convolutional neural network

Optik ◽  
2021 ◽  
pp. 167827
Author(s):  
Haolong Jia ◽  
Jing Zuo ◽  
Qiliang Bao ◽  
Chao Geng ◽  
Xinyang Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Phase Error ◽  
Prediction Method ◽  
Coherent Beam ◽  
Error Prediction ◽  
Coherent Beam Combining ◽  
Beam Combining

scholarly journals Deep Transfer Learning-Based Fault Diagnosis for Gearbox under Complex Working Conditions

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Zitong Wan ◽  
Rui Yang ◽  
Mengjie Huang
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
Working Conditions ◽  
Evaluation Method ◽  
Working Condition ◽  
Negative Effects ◽  
Gear Fault ◽  
Diagnosis Method ◽  
Fault Feature Extraction ◽  
Better Than

In the large amount of available data, information insensitive to faults in historical data interferes in gear fault feature extraction. Furthermore, as most of the fault diagnosis models are learned from offline data collected under single/fixed working condition only, this may cause unsatisfactory performance for complex working conditions (including multiple and unknown working conditions) if not properly dealt with. This paper proposes a transfer learning-based fault diagnosis method of gear faults to reduce the negative effects of the abovementioned problems. In the proposed method, a cohesion evaluation method is applied to select sensitive features to the task with a transfer learning-based sparse autoencoder to transfer the knowledge learnt under single working condition to complex working conditions. The experimental results on wind turbine drivetrain diagnostics simulator show that the proposed method is effective in complex working conditions and the achieved results are better than those of traditional algorithms.

Novel Error Prediction Method of Dynamic Measurement Lacking Information

2012 ◽  
Vol 40 (1) ◽  
pp. 104165 ◽  
Author(s):  
M. R. Mitchell ◽  
R. E. Link ◽  
Ge Leyi ◽  
Zhao Wei ◽  
Huang Songling ◽  
...  
Keyword(s):  
Prediction Method ◽  
Dynamic Measurement ◽  
Error Prediction
Sign in / Sign up

Export Citation Format

Share Document