Billets have oxidized layers and defects on their surface due to the production process, so they must be surface?regulated by grinding. There is no special equipment for surface regrinding of large square steel billets; a square steel regrinding equipment was designed. Kinematic simulation verification was completed using ADAMS software. The results show that the regrinding equipment can simultaneously and smoothly complete the grinding operation on two adjacent surfaces. Using finite element software ANSYS to carry out stress analysis and modal analysis of the regrinding machine under load, and improve the structure; according to the simplified kinematic model, static analysis was carried out to get the required input driving torque, and the selection of the critical components of the spring was completed. Theoretical calculations and simulation results show that this regrinding machine can efficiently grind the surface of large square billets.

The vibration signal during the operation of high voltage circuit breaker can reflect the mechanical state of circuit breaker. Aiming at the shortcomings of feature extraction and fault diagnosis accuracy of shallow vibration signal analysis model, a fault diagnosis method of high voltage circuit breaker based on convolutional neural network optimized by genetic algorithm was proposed. Using the global optimization ability of genetic algorithm, the optimal initial network structure parameters and the number of neurons in the whole connection layer were obtained through the selection, crossover and mutation of genetic algorithm to optimize the convolutional neural network, and the optimized convolutional neural network is applied to the fault diagnosis of high voltage circuit breaker. The results show that the diagnosis performance of the proposed network model is better than that of convolution neural network, dynamic support vector machine and multilayer perceptron.