Fault Diagnosis of Drill Pipe for High Coalbed Methane Extraction Based on CNN and VMD
In order to further improve the fault diagnosis accuracy of the motor drive system,a method using VMD and CNN for the fault diagnosis of the motor drive system was designed.The orthogonal experiment method is used to optimize the CNN parameters,and the decomposed natural modal components are input into the CNN model for training.The results show that a stable fitness function is obtained when the number of iterations increases to 85.It shows that the optimization algorithm has obvious advantages and can promote the improvement of diagnostic accuracy.The diagnosis success rate of the training sample is 98.6％,which is higher than that of the test sample 95.6％,indicating that the CNN model has better fault identification and diagnosis performance.This research is helpful to improve the working stability of power generation equipment,and can also be extended to other mechanical transmission fields.
motor drive systemfault diagnosislearning algorithmfitness
NETL
NSTL
万方数据
