In order to improve the mechanical structure of the type of fault resolution precision high voltage circuit breaker spring mechanism, the paper analyzes the characteristics of the circuit breaker and the combination of mechanical vibration signal PSO algorithm (PSO) SVM parameter optimization method proposed collaborative dynamic acceleration constant inertia weight particle swarm optimization (WCPSO) optimization support vector machine (SVM) analysis breaker fault classification parameters and kernel function parameters. The vibration signal circuit breaker empirical mode decomposition, the total intrinsic mode components through energy analysis to obtain the required fault feature vectors and support vector machine as input, the use of dynamic acceleration constant synergy inertia weight PSO support vector machines penalty factor C and radial basis kernel function parameters optimize the fault feature vector signal input test samples after SVM training sample trained optimized for fault classification, fault status classification. Introduction With the maturity distribution automation systems, circuit breakers and distribution system as an important device has important significance for its fault diagnosis. Mechanical vibration signals generated breakers in sub-closing action contains a lot of state information, has important practical implications for the analysis of vibration signals of these [1] . These frontier of contemporary theories and methods will inevitably penetrate into the diagnostic techniques in the past, making the diagnosis can almost simultaneous development of these frontier [2-3] . Swarm intelligence optimization technology as a new technology, is a new hot field of artificial intelligence research, which will be used in PSO breaker fault diagnosis, a new hotspot [4-7] . social insects swarm intelligence is inspired by a series of new solutions to complex problems through traditional simulation generated by their actions, it is the simple dumb many groups of individuals by a simple mutual cooperation between the intelligent behavior exhibited. Among them, the PSO [8] (Particle Swarm Optimization, PSO) is a J.Kennedy and RCEberhart proposed in 1995 based on the principle of swarm intelligence optimization algorithms, It converges fast, easy to implement and only a few parameters need to be adjusted, and thus was put forth to become intelligent optimization and evolutionary computing a new hotspot [9-11] . How to use effective mathematical tool for runtime behavior of PSO, convergence, convergence speed, parameter selection, parameter robustness and computational complexity of the analysis should be the current research focus [5] . Feature Vectors Extracted Based on the Total Weight of Energy by IMF According to the test signal and the theoretical knowledge known techniques, regardless of the actual dimensions in the case of the oscillating signals ( ) x t time integral of the square of 2 ( ) x t is called the energy of the signal: 2 ( ) | ( ) | Q i x t dt (1)
[1]
Jun Cai,et al.
Multi-fault classification based on support vector machine trained by chaos particle swarm optimization
,
2010,
Knowl. Based Syst..
[2]
Chengliang Liu,et al.
Application of Particle Swarm Optimization-Based Support Vector Machine in Fault Diagnosis of Turbo-Generator
,
2008,
2008 Second International Symposium on Intelligent Information Technology Application.
[3]
Riccardo Poli,et al.
Particle swarm optimization
,
1995,
Swarm Intelligence.
[4]
Tsair-Fwu Lee,et al.
Particle Swarm Optimization-Based SVM Application: Power Transformers Incipient Fault Syndrome Diagnosis
,
2006,
2006 International Conference on Hybrid Information Technology.
[5]
Zhi Biao Shi,et al.
Diagnosis for Vibration Fault of Steam Turbine Based on Modified Particle Swarm Optimization Support Vector Machine
,
2011
.
[6]
Sid Ahmed Bessedik,et al.
Prediction of flashover voltage of insulators using least squares support vector machine with particle swarm optimisation
,
2013
.
[7]
Qi Wu.
Fault diagnosis model based on Gaussian support vector classifier machine
,
2010,
Expert Syst. Appl..
[8]
Songlin Sun,et al.
Fault diagnosis of sensor by chaos particle swarm optimization algorithm and support vector machine
,
2011,
Expert systems with applications.
[9]
Xin Ma.
Power Transformer Fault Diagnosis Based on Least Squares Support Vector Machine and Particle Swarm Optimization
,
2011
.