Lightweight CNN architecture design for rolling bearing fault diagnosis

Abstract Rolling bearing is a key component of rotating machinery, and its fault diagnosis technology is very important to ensure the safety of equipment. With the rapid development of deep learning, the convolutional neural network (CNN) is widely used in bearing fault diagnosis, showing obvious advantages in diagnostic accuracy. However, the deep CNN model generally requires a lot of computing resources and storage space, and it is not easy to apply in practical engineering. Aiming at this problem, a lightweight CNN model for rolling bearing fault diagnosis is designed. This model is combined with a network pruning algorithm and neural architecture search, which not only ensures the accuracy of diagnosis but also reduces computing resources. By constructing the search space of the complete Cell class unit, using the multi-objective reinforcement learning search strategy, and applying the deep learning pruning method to prune and search the network, the lightweight CNN model with higher accuracy is efficiently searched. The rolling bearing fault data set is utilized to validate the use of the lightweight CNN model for diagnosing rolling bearing faults. This model significantly enhances operational efficiency without compromising accuracy, achieving a fault diagnosis accuracy of up to 98.56%.