Search

Aiming at the problems of complex structure, fault prone and low accuracy of fault identification of asynchronous motor, this paper proposed a fault location recognition model of asynchronous motor based on AB-CNN (AdaBelief-CNN) intelligent algorithm. Taking asynchronous motor as the application background, an experimental platform is built to collect different types of fault data of asynchronous motor. Firstly, the dimension of the data is reduced by principal component analysis, the convolutional neural network (CNN) is used to carry out forward propagation fault recognition training for asynchronous motor fault data, and output the trained data prediction value. Secondly, through the loss function and AdaBelief optimization algorithm, the asynchronous motor fault location recognition model is optimized. Finally, the accuracy of the fault location identification model is tested with the test data. Comparing with the original CNN network identification model and Adam optimized CNN network (AD-CNN), the proposed solution outperforms other schemes by about 10%.

Compared with the static cipher, the dynamic cipher has the characteristic of "one cipher at a time" proposed by Shannon theory. Therefore, it is regarded as the safest among many forms of identity authentication. This paper proposes a five-dimensional chaotic system suitable for the construction of dynamic cipher and analyzes its relevant characteristics, including stability, balance, time-domain waveform, Poincare cross sectional diagram, Lyapunov exponent and bifurcation diagram. The results show that the chaotic system has multiple controllable parameters and a wide range of chaos, which is very suitable for constructing chaotic dynamic ciphers. The complexity of the proposed chaotic system is analyzed to verify the high security of the proposed system. On this basis, a dynamic cipher electronic lock based on chaotic system is designed in this paper. In the designed hardware circuit, the fourth order Runge–Kutta solving algorithm is used to discretize the constructed system, and the chaos is successfully implemented in the single-chip microcomputer. The phase diagram obtained from the circuit simulation data is basically consistent with the numerical simulation. Finally, the circuits of the handheld terminal and the electronic lock terminal are designed and simulated. The simulation results show that the preset function can be basically realized, and the generated chaotic dynamic cipher is random and irregular. The five-dimensional chaotic system proposed in this paper has complex dynamic characteristics, which makes the dynamic cipher electronic lock based on the chaotic system extremely safe.