This paper constructs a spatiotemporal feature fusion network (STNet) to enhance the influence of spatiotemporal features of signals on the diagnostic performance during motor fault diagnosis. The STNet consists of the spatial feature processing capability of convolutional neural networks (CNN) and the temporal feature processing capability of recurrent neural networks (RNN). It is used for fault diagnosis of motor vibration signals. The network uses dual-stream branching to extract the fault features of motor vibration signals by a convolutional neural network and gated recurrent unit (GRU) simultaneously. The features are also enhanced by using the attention mechanism. Then, the temporal and spatial features are fused and input into the softmax function for fault discrimination. After that, the fault diagnosis of motor vibration signals is completed. In addition, several sets of experimental evaluations are conducted. The experimental results show that the vibration signal processing method combined with spatiotemporal features can effectively improve the recognition accuracy of motor faults.
As the key component of a five-axis CNC planer-type milling machine, the integral mechanical property of the A/C swing angle milling head directly affects the machining accuracy and stability of the milling machine. Taking the mechanical A/C swing-angle milling head of a five-axis numerical-control gantry milling machine as the research object, the stress deformation characteristics and natural frequency of the swing-angle milling head under actual working conditions were studied using finite-element analysis. Based on the analytical results, it was determined that the cardan frame, with its large mass proportion and strong rigidity of the whole milling head, is the object to be optimized. The topological optimization of the cardan frame, in which achieving the minimum flexibility was the optimization objective, was carried out to determine the quality reduction area. By comparing the simulation results of the cardan frames of three different rib plate structures, it was shown that the cardan frame performance of the ten-type rib plate structure was optimal. The analytical results showed that, when the cardan frame met the design requirements for stiffness and strength, the mass after optimization was reduced by 13.67% compared with the mass before optimization, the first-order natural frequency was increased by 7.9%, and the maximum response amplitude was reduced in all directions to avoid resonance, which was beneficial to the improvement of the dynamic characteristics of the whole machine. At the same time, the rationality and effectiveness of the lightweight design method of the cardan frame were verified, which has strong engineering practicality. The research results provide an important theoretical basis for the optimization of other machine tool gimbals and have important practical significance and application value.
To plan the work of power generation equipment, it is necessary to ensure that the power supply is sufficient and to achieve the minimum cost to ensure the safety and economy of the microgrid. Based on back propagation neural network–local mean decomposition–long short-term memory (BPNN–LMD–LSTM) load prediction, the design is based on a fixed-time consistency algorithm with random delay to predict the economic dispatch of microgrids. Firstly, the initial power load prediction sequence is obtained by continuous training of the back propagation neural network (BPNN); the residual sequence with other influencing factors is decomposed by local mean decomposition (LMD); and the long short-term memory neural network (LSTM) is used to predict the output prediction residual sequence, and the final short-term power load prediction is obtained. Based on predicting load, the fixed-time consistency algorithm with random delay is used to add supply and demand balance constraints to optimize the power distribution of the power generation units of the distributed microgrid and reduce the power generation cost of the microgrid. The results show that the prediction model has better prediction accuracy, and the scheduling algorithm based on the prediction model has a faster convergence rate to reach the lowest power generation cost.
Compared to traditional power grids, microgrids have a more flexible operating mode. There are various distributed power sources within the microgrid, and different types of distributed power sources have different control methods. Once a short-circuit fault occurs in the microgrid, these characteristics will increase the difficulty of microgrid fault diagnosis and reduce the accuracy of microgrid fault diagnosis. This paper proposes an error-correcting particle swarm optimization back propagation microgrid fault diagnosis method for the diagnosis of short-circuit faults in microgrids that identifies the accuracy of alarm signals, corrects unreasonable signals, and obtains the correct fault set of the microgrid through the temporal logic relationship between each protection. Using the particle swarm optimization back propagation (PSO-BP) neural network algorithm to train fault alarm signals, fast convergence can be achieved, and accurate diagnostic results can be obtained after the sixth generation training is completed. As this fault diagnosis algorithm is applied to line protection equipment, it can be used to diagnose all types of short-circuit faults. This algorithm is easy to implement and has a small data scale, which is conducive to efficient and concise fault diagnoses in microgrids.