Fault Diagnosis of AUV’s Thrusters Based on SVM

2015 ◽  
Vol 738-739 ◽  
pp. 858-862
Author(s):  
Lei Wan ◽  
Ying Hao Zhang ◽  
Yu Shan Sun ◽  
Yue Ming Li
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Marine Environment ◽  
Autonomous Underwater Vehicle ◽  
Underwater Vehicle ◽  
Small Sample ◽  
High Dimensional ◽  
Support Vector ◽  
Simulation Results

An autonomous underwater vehicle (AUV) should have the ability of adapting the complexity and unpredictability of the marine environment, which means that the technology of AUV’s fault diagnosis is very significant, especially the part of thrusters. In order to make it possible, one fault diagnosis strategy of AUV’s thrusters is proposed, which is based on the support vector machine (SVM). SVM has many unique advantages in solving small-sample, nonlinear and high dimensional problems. In this paper, different character signal is inputted SVM to train and test it. The simulation results show that the fault diagnosis of AUV’s thrusters based on offline SVM can classify the fault styles successfully, which proves its feasibility and effectiveness. This method offers a new way to solve the fault diagnosis of AUVs.

scholarly journals Sparse Representation and SVM Diagnosis Method Inter-Turn Short-Circuit Fault in PMSM

2019 ◽  
Vol 9 (2) ◽  
pp. 224 ◽  
Author(s):  
Siyuan Liang ◽  
Yong Chen ◽  
Hong Liang ◽  
Xu Li
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Sparse Representation ◽  
Permanent Magnet ◽  
Short Circuit ◽  
Small Sample ◽  
Support Vector ◽  
Feature Vectors ◽  
Diagnosis Method ◽  
Short Circuit Fault

Permanent magnet synchronous motors (PMSM) has the advantages of simple structure, small size, high efficiency, and high power factor, and a key dynamic source and is widely used in industry, equipment and electric vehicle. Aiming at its inter-turn short-circuit fault, this paper proposes a fault diagnosis method based on sparse representation and support vector machine (SVM). Firstly, the sparse representation is used to extract the first and second largest sparse coefficients of both current signal and vibration signals, and then they are composed into four-dimensional feature vectors. Secondly, the feature vectors are input into the support vector machine for fault diagnosis, which is suitable for small sample. Experiments on a permanent magnet synchronous motor with artificially set inter-turn short-circuit fault and a normal one showed that the method is feasible and accurate.

FAULT DIAGNOSIS BASED ON LMD-SVD AND INFORMATION-GEOMETRIC SUPPORT VECTOR MACHINE FOR HYDRAULIC PUMPS

2015 ◽  
Vol 39 (3) ◽  
pp. 569-580 ◽  
Author(s):  
Ye Tian ◽  
Chen Lu ◽  
Zhipeng Wang ◽  
Zili Wang
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Small Sample ◽  
Support Vector ◽  
Svm Classifier ◽  
Health States ◽  
Diagnosis Method ◽  
Stationary Vibration ◽  
Local Mean ◽  
Value Decomposition

This study proposes a fault diagnosis method for hydraulic pumps based on local mean decomposition (LMD), singular value decomposition (SVD), and information-geometric support vector machine (IG-SVM). First, the nonlinear and non-stationary vibration signals are decomposed using LMD into several product functions (PFs). Then, the PFs are processed by SVD to obtain more stable and compact feature vectors. Finally, the health states are identified by an IG-SVM classifier, which is less-dependent on the selected kernel function and parameters than SVM. In addition, the comparisons between LMD, EMD, and WPD demonstrate the superiority of LMD in feature extraction. Compared with SVM and BP neural network, IG-SVM shows higher classification accuracy and computational efficiency in dealing with small-sample fault diagnosis. From the experimental results, it was concluded that the proposed method can effectively realize fault diagnosis for hydraulic pumps under small-sample conditions.

Fault Diagnosis for Grounding Grids Based on Genetic Algorithm and Support Vector Machine

2013 ◽  
Vol 787 ◽  
pp. 909-913
Author(s):  
Ling Jian Li ◽  
Min Fang Peng ◽  
Ke Xin Zhao
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Support Vector ◽  
Grounding Grid ◽  
Grounding Grids ◽  
Diagnosis Method ◽  
Simulation Results ◽  
Type Of Failure ◽  
Corrosion Simulation

This paper presents a genetic algorithm to optimize support vector machine parameters for grounding grid fault diagnosis method. Grounding grid is equivalent to a pure resistance model, extract characteristics of different kinds of corrision states, Using genetic algorithm optimize support vector machine kernel function parameters, achieve the identification of the type of failure mode, Grounding grid of 6 × 6 test can quickly detect the grounding grid corrosion, simulation results show that the method has higher accuracy than support vector machine.

Research on Rotating Machinery Vibration Fault Based on Support Vector Machine

2010 ◽  
Vol 139-141 ◽  
pp. 2603-2607
Author(s):  
Chao Zhang ◽  
De Qing Liu
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
System Modeling ◽  
Model Identification ◽  
Rotating Machinery ◽  
Small Sample ◽  
Support Vector ◽  
Initial Symptom ◽  
Fault Diagnose ◽  
New Ideas

The research on support vector machine in fault diagnose has already obtained a lot of breakthroughs, such as the mode identify problems in small sample, nonlinearity, high dimension and so on. However, there are some limitations in the traditional support vector machine. In this paper, in allusion to the current rotating machinery fault diagnosis problem, the basic principles of support vector machine are studied. According to the complex characteristics of rotating machinery vibration fault, a fault extraction method is proposed based on the K-L transform. Multi-classification algorithm of support vector machine is improved, and the algorithm is used to analyze the rotating machinery vibration. By using its capabilities of model identification and system modeling, the initial symptom, occurrence, development of the typical faults are dynamically analyzed. These provide new ideas and methods for fault diagnosis of rotating machinery.

Research Status of Fault Diagnosis Based on Support Vector Machine

2013 ◽  
Vol 475-476 ◽  
pp. 787-791
Author(s):  
Li Mei Liu ◽  
Jian Wen Wang ◽  
Ying Guo ◽  
Hong Sheng Lin
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Small Sample ◽  
Learning Ability ◽  
Practical Significance ◽  
Support Vector ◽  
Limited Information ◽  
Risk Minimization ◽  
Minimization Principle ◽  
Good Learning

Support vector machine has good learning ability and it is good to perform the structural risk minimization principle of statistical learning theory and its application in fault diagnosis of the biggest advantages is that it is suitable for small sample decision. Its nature of learning method is under the condition of limited information to maximize the implicit knowledge of classification in data mining and it is of great practical significance for fault diagnosis. This paper analyzed and summarized the present situation of application of support vector machine in fault diagnosis and made a meaningful exploration on development direction of the future.

Fault Diagnosis of Power Transformer Based on Adaptive Differential Evolution and Least Square Support Vector Machine

2013 ◽  
Vol 791-793 ◽  
pp. 912-916 ◽  
Author(s):  
Zi Pin Li ◽  
Hui Peng
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Differential Evolution ◽  
Power Transformer ◽  
Differential Evolution Algorithm ◽  
Classification Problem ◽  
Small Sample ◽  
Least Square ◽  
Support Vector ◽  
Adaptive Differential Evolution

Least square support vector machine (LS-SVM) can solve small sample, high-dimensional and non-linear multi-classification problem well, so it is applicable to the power transformer fault diagnosis. However, the parameters of LS-SVM have significant effect on the classification results.In this paper, the adaptive differential evolution algorithm (ADE) is applied to optimize the parameters of LS-SVM. The scaling factor and crossover rate are adjusted dynamically in the whole evolution process, so the robustness of the algorithm is improved greatly. The optimized LS-SVM is applied to fault diagnosis of power transformer, the results obtained demonstrate superiority of the proposed approach.

Fault Diagnosis for Temperature Signal of Turbine Blade Based on LS-SVM

2013 ◽  
Vol 385-386 ◽  
pp. 580-584 ◽  
Author(s):  
Li Wei Chen ◽  
Chen Dong Wang
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Least Squares ◽  
Turbine Blade ◽  
Small Sample ◽  
Support Vector ◽  
Support Vector Machine Algorithm ◽  
Operation Speed ◽  
Svm Algorithm ◽  
Temperature Signal

This document discusses the support vector machine (SVM) algorithm, then discusses least squares support vector machine (LS-SVM) algorithm, at the same time, the applications of SVM in the fault diagnosis of temperature signal of turbine blade being discussed, the least squares support vector machine algorithm being used in the research of fault diagnosis, being compared with LVQ neural network, experiments result show the operation speed of the least squares support vector machine algorithm is fast, its generalization ability is stronger, SVM can solve small sample learning problems as well as no-linear, high dimension and local minimization problems in the fault diagnosis of temperature signal of turbine blade.

Fault Diagnosis Method of Mine Motor Based on Support Vector Machine

2019 ◽  
Vol 13 ◽  
Author(s):  
Yan Zhang ◽  
Ren Sheng
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Optimization Method ◽  
Support Vector ◽  
Optimal Parameters ◽  
Instantaneous Power ◽  
Practical Usefulness ◽  
Sample Data ◽  
Diagnosis Method ◽  
Fault Characteristic

Background: In order to improve the efficiency of fault treatment of mining motor, the method of model construction is used to construct the type of kernel function based on the principle of vector machine classification and the optimization method of parameters. Methodology: One-to-many algorithm is used to establish two kinds of support vector machine models for fault diagnosis of motor rotor of crusher. One of them is to obtain the optimal parameters C and g based on the input samples of the instantaneous power fault characteristic data of some motor rotors which have not been processed by rough sets. Patents on machine learning have also shows their practical usefulness in the selction of the feature for fault detection. Results: The results show that the instantaneous power fault feature extracted from the rotor of the crusher motor is obtained by the cross validation method of grid search k-weights (where k is 3) and the final data of the applied Gauss radial basis penalty parameter C and the nuclear parameter g are obtained. Conclusion: The model established by the optimal parameters is used to classify and diagnose the sample of instantaneous power fault characteristic measurement of motor rotor. Therefore, the classification accuracy of the sample data processed by rough set is higher.

Sign in / Sign up

Export Citation Format

Share Document