IWOA-CNN-transformer-based fault diagnosis method for marine engine

Abstract

Disclosed is an IWOA-CNN-Transformer-based fault diagnosis method for a marine engine, including: collecting operating data of the marine engine under normal and fault conditions and performing preprocessing on the operating data, and constructing a data set and dividing the data set into a training set and a validation set; improving a whale optimization algorithm by introducing an optimal neighbourhood perturbation, an adaptive weight, and a variable spiral position update strategy to construct an improved whale optimization algorithm; constructing a CNN-Transformer model, optimizing a hyperparameter of the model by using the improved whale optimization algorithm to obtain an optimal hyperparameter combination; and improving the CNN-Transformer model based on the optimal hyperparameter combination, and training the model by using the training set and evaluating the model by using the validation set, so as to achieve a predictive diagnosis of engine fault classification by an improved CNN-Transformer model.