The Research on Fault Diagnosis for Gas Recovery of Single Coal Bed Methane well Based on Improved Particle Swarm Optimizing Support Vector Machine

Abstract

As a new type of energy, coal-bed gas plays an important role in the national resource structure. This paper introduce the principle and process of gas recovery of single coal-bed methane well, according to the analysis of faults occurred in the system of gas recovery of single coal-bed methane well, by analyzing the characteristics parameters of gas recovery of single coal bed methane well system, combining with the advantages of support vector machine theory can solve the problems of nonlinear and high dimension. Because of the parameters selection of support vector machine has great influence on fault diagnosis, this article use particle swarm algorithm to optimize the parameters of support vector machine. In order to improve the shortcoming of Particle Swarm Optimization (PSO) algorithm which is easy to fall into local optimal, this article proposed that utilize improved particle swarm optimization support vector machine model for gas recovery of single coal-bed methane well system. The simulation results show that the new diagnosis model has a good fault diagnosis practicality and can be applied to fault diagnosis of single well.