30 September 2024 in Measurement Science and Technology
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%.
17 June 2025 in Advances in Mechanical Engineering
The traditional dynamic balance methods require multiple start-stop operations for test weight adjustments, leading to high resource consumption. To improve the efficiency, accuracy, and safety of aero-engine rotor dynamic balancing, a novel dynamic balancing optimization method is proposed. A virtual prototype model of the high-speed aero-engine rotor is constructed to analyze its dynamic characteristics and derive the transfer function under unbalanced excitation. Subsequently, equilibrium equations are established to relate the unbalanced response to rotor amplitude. A multi-strategy improved sparrow search algorithm is then applied. The optimization minimizes the sum of squared residual vibrations and the maximum residual vibration at each measurement point. Experimental verification is conducted on a simulated test bench for a specific type of turbine rotor used in aerospace engines. The results demonstrate that the proposed method improves test weight efficiency and prevents local vibration overruns. It achieves an average vibration reduction of 52.56%, outperforming the 45.23% of traditional on-site dynamic balancing. This approach offers a valuable technical reference for aerospace engine vibration control.