scholarly journals A Bearing Performance Degradation Modeling Method Based on EMD-SVD and Fuzzy Neural Network

2019 ◽  
Vol 2019 ◽  
pp. 1-10 ◽  
Author(s):  
Jingbo Gai ◽  
Yifan Hu ◽  
Junxian Shen
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Degradation Process ◽  
Test Sample ◽  
Performance Degradation ◽  
Modeling Method ◽  
Intrinsic Mode Functions ◽  
Degradation Modeling ◽  
Fuzzy Neural ◽  
Whole Life Cycle

Bearing performance degradation assessment has great significance to condition-based maintenance (CBM). A novel degradation modeling method based on EMD-SVD and fuzzy neural network (FNN) was proposed to identify and evaluate the degradation process of bearings in the whole life cycle accurately. Firstly, the vibration signals of bearings in known states were decomposed by empirical mode decomposition (EMD) to obtain the intrinsic mode functions (IMFs) containing feature information. Then, the selected key IMFs which contain the main features were decomposed by singular value decomposition (SVD). And the decomposed results were used as the training samples of FNN. At last, the output results of the tested data were normalized to the health index (HI) through learning and training of FNN, and then the performance degradation degree could be described by the distance between the test sample and the normal one. According to the case study, this modeling method could evaluate the performance degradation of bearings effectively and identify the early fault features accurately. This method also provided an important maintenance strategy for the CBM of bearings.

scholarly journals Screw Performance Degradation Assessment Based on Quantum Genetic Algorithm and Dynamic Fuzzy Neural Network

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Xiaochen Zhang ◽  
Hongli Gao ◽  
Haifeng Huang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Fuzzy Neural Network ◽  
Principal Component ◽  
Performance Degradation ◽  
Ball Screw ◽  
Degradation Model ◽  
Quantum Genetic Algorithm ◽  
Feature Vectors ◽  
Fuzzy Neural

To evaluate the performance of ball screw, screw performance degradation assessment technology based on quantum genetic algorithm (QGA) and dynamic fuzzy neural network (DFNN) is studied. The ball screw of the CINCINNATIV5-3000 machining center is treated as the study object. Two Kistler 8704B100M1 accelerometers and a Kistler 8765A250M5 three-way accelerometer are installed to monitor the degradation trend of screw performance. First, screw vibration signal features are extracted both in time domain and frequency domain. Then the feature vectors can be obtained by principal component analysis (PCA). Second, the initialization parameters of the DFNN are optimized by means of QGA. Finally, the feature vectors are inputted to DFNN for training and then get the screw performance degradation model. The experiment results show that the screw performance degradation model could effectively evaluate the performance of NC machine screw.

Modeling of Switched Reluctance Motor Based on Dynamic Fuzzy Neural Network

2012 ◽  
Vol 220-223 ◽  
pp. 665-668 ◽  
Author(s):  
Ai De Xu ◽  
Shan Shan Zhang ◽  
Di Sun
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Switched Reluctance Motor ◽  
Mathematic Model ◽  
Modeling Method ◽  
System Structure ◽  
Actual System ◽  
Switched Reluctance ◽  
Reluctance Motor ◽  
Fuzzy Neural

This paper proposed a novel mathematic model for switched reluctance motor(SRM):dynamic fuzzy neural network(D-FNN) was used to model for SRM based on the inductance characteristics, namely experimentally measured sample data. Compared with other modeling method, the inductance based on D-FNN can be trained on line and has the advantages of compact system structure and strong generalization ability. The SRM system is simulated with the trained inductance model. Compared with the actual system, the current waves are similar. This proves the new modeling method is correct and feasible.

A Compensatory Fuzzy Neural Network Modeling Method Based on Particle Swarm Clustering

2011 ◽  
Vol 48-49 ◽  
pp. 5-8 ◽  
Author(s):  
Chun Tao Man ◽  
Tian Feng Wang ◽  
Xiao Bo Sun ◽  
Xin Xin Yang ◽  
Jia Cui
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Particle Swarm ◽  
Fuzzy Model ◽  
Decomposition Reaction ◽  
Modeling Method ◽  
Neural Network Modeling ◽  
Initial Structure ◽  
Initial Network ◽  
Fuzzy Neural

According to modeling problem for complex systems, a compensatory fuzzy neural network (CFNN) modeling method based on particle swarm clustering is proposed: the particle swarm clustering is used to automatically separate the space of input-output data, obtain the numbers of inference rules of fuzzy model and find fuzzy rules. Based on the rules, we modified fuzzy reasoning process and established initial structure of compensatory fuzzy neural network. Then using adaptive rate algorithm optimized initial network parameters, which can obtain a faster training speed and more precision. Simulation results show that the proposed network has successfully modeled the oxidation decomposition reaction process.

scholarly journals Innovative Modeling Method in Technical Training of High Jumpers

2012 ◽  
Vol 19 (4) ◽  
pp. 253-255
Author(s):  
Ilya Y. Krivetskiy ◽  
Grigoriy I. Popov
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Video Recording ◽  
Individual Performance ◽  
Modeling Method ◽  
Technical Training ◽  
Fine Tuning ◽  
Interactive System ◽  
Kinematic Characteristics ◽  
Fuzzy Neural

AbstractIntroduction. This essay introduces an innovative high jump technique modeling method that uses a cascaded fuzzy neural network. An interactive system for the prediction of the success of a high jump has been designed based on this method and it allows the creation of an individual model for highly skilled athletes to control the jumper's technical training. Material and methods. The research material included a video recording of 92 high jumps and analysis by 48 kinematic characteristics. The result allowed the fine tuning of the cascaded fuzzy neural network model in order to analyse successful and failed jumps. Results and conclusions. We have developed the interactive system based on the analysis of kinematic characteristics of the high jump and this allows individual performance models to be tailored for elite athletes. With the help of this instrument, which takes into account the individual biomechanical features of an athlete's jumping style, we can analyze all stages of a jump in detail, improve the technique through the targeted correction of specific motions and achieve the optimal combination of kinematic values for the best possible result.

Sign in / Sign up

Export Citation Format

Share Document