Fault Diagnosis of Steam Turbine-Generator Sets Using an EPSO-Based Support Vector Classifier

Liu

Lecture Notes in Electrical Engineering

2014

Self Cite

To enhance diagnosis accuracy of vibration faults for steam turbinegenerator sets (STGS), this paper presents evolutionary programming-based radial basis function (EP-RBF) networks. The proposed EP automatically determine the optimal parameters for the RBF network, which includes the number of neurons in the hidden layer, the centers of hidden neurons, the spread parameters, and the weights in the output layer of the RBF network. The test results demonstrate that the proposed EP-RBF network has a higher diagnostic accuracy than the RBF network and multilayer perceptron (MLP) network trained by error back-propagation algorithm. Moreover, this paper reveals that the proposed EP-RBF network can apply to effectively diagnose vibration fault of STGS.

Section: Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Approaches for Vibration Fault Diagnosis of Steam Turbine-Generator Sets

Liu

Lecture Notes in Electrical Engineering

2014

Self Cite

“…Azadeh et al [18] proposed a unique flexible algorithm for classifying the condition of centrifugal pump based on support vector machine hyper-parameters optimization and artificial neural networks (ANNs). Sun et al [19] proposed an enhanced particle swarm optimization (EPSO)-based support vector classifier (SVC) to extract the support vector from databases, in order to diagnose vibration faults in steam turbine-generator sets (STGS). Dong et al [20] proposed a modified multi-sensor information fusion method for hydraulic fault diagnosing system based multi-parallel particle swarm optimization (PSO)-Hopfield neural network and modified Dempster-Shafer (D-S).…”

Section: Introductionmentioning

confidence: 99%

Study on a New Fault Diagnosis Method Based on Combining Intelligent Technologies

Li¹,

Zhou²

2016

IJMUE

In allusion to more indeterminate information and higher speed request characteristic in fault diagnosis system, according to the intelligence complementary strategy, a new fault diagnosis(SWPSO-BPN) model based on combining improved particle swarm optimization (PSO) algorithm and Back-propagation(BP) neural network is proposed in this paper. In the SWPSO-BPN method, an improved PSO (SWPSO) algorithm is proposed to optimize the parameters of BP neural network in order to overcome the shortcomings of slow learning speed and being easy to fall into local minimum, and obtain the optimal values of parameter combination in the BP neural network(SWPSO-BPN) model. Then proposed SWPSO-BPN model is applied to diagnose the fault in order to obtain a new fault diagnosis (SWPSO-BPN-FD) method. Finally, the proposed SWPSO-BPN-FD method is used to test the data from bearing data center of CWRU. The experimental results show that the proposed SWPSO-BPN-FD method can accurately and effectively realize high precision fault diagnosis of rolling bearing. And this method takes on strong robustness and generalization ability.

The 26th Chinese Control and Decision Conference (2014 CCDC)

“…For example, neural network [1][2][3][4], support vector machine [5,6], decision tree [7,8], Bayesian network [9,10], hidden Markov model [11][12][13], etc. Though these above intelligent methods can quickly detect and diagnose some faults to some extent; however, their main limitation is the statistic assumption.…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis method for complex equipment using cased-based reasoning

Zhang

Wang

et al. 2014

Rapid and accurate fault detection and diagnosis (FDD) is gaining importance for complex equipments because of the need to increase reliability and to decrease possible loss. In this paper, an intelligent fault diagnosis method is presented by using case-based reasoning (CBR) methodology to infer and classify various failures. Firstly, the case representation and the case base are established according to the characteristics of diagnosis process, and a novel case retrieval approach base on the improved grey relational analysis is presented to solve the matching problems under uncertain cases. Secondly, a new CBR-based Engine fault diagnosis (Engine-FD) system is designed and developed to diagnose four faults of 4135 diesel engine according to eighteen fault features. Finally, the application results show that the proposed fault diagnosis method has a good reliability and engineering practicability, and it can be used to solve other fault diagnosis problems.