Sparse transfer learning for identifying rotor and gear defects in the mechanical machinery

It is incredibly difficult to build a data-driven machine learning model for the automatic detection of defects in rotating machinery. The existing techniques, based on machine learning models, work satisfactory for one machinery but unsatisfactorily for others. The problem of identifying defects becomes sever when the enough training data is not available. Here, a sparse deep learning model is put forward that can efficiently learn from the limited training data. The existing cost function of CNN has been improved by adding sparsity cost for the purpose of improving the performance of deep learning. To assimilate the sparsity, unnecessary activation of neurons is averted in the feature extraction layer of CNN. A trigonometric sparsity cross entropy (TSCE) function is built to obtain the sparsity cost. The updated CNN is trained with enough samples from the source domain. Thereafter, fine-tuning of the model is carried out from small data samples of the target domain for detecting defects. The testing of proposed deep learning model is carried out on two types of data set, one is gear and another is rotor. The concluding results obtained from the proposed work has been compared with current stateof-the-artwork. The comparison analysis shows the usefulness of the proposed methodology over the existing methods.

Automated summary

This study proposes a sparse deep learning model that improves the performance of machine learning models by introducing sparsity cost into CNN, effectively learning in the absence of training data. Through extensive training with samples from the source domain and fine-tuning with small data samples from the target domain, the model shows excellent performance in detecting defects in rotating machinery.