Digital instruments recognition based on PCA-BP neural network
Jun Zhang, Lin Zuo, Jiawei Gao, Shaoan Zhao · 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · 2017
Digital instruments are widely used in engineering practices, and the recognition technology of digital instruments has always been extensively studied. Artificial intelligence algorithms, such as neural networks, are widely adopted in the field of target recognition. However, the existing neural network algorithms in the target recognition need to manually adjust the number of hidden layer neurons. They are very time-consuming and difficult to converge to the optimal solution. In this paper, PCA algorithm and traditional BP neural network are used to automatically select the number of neurons in hidden layer. The experimental results show that, compared with traditional algorithm, the PCA-BP neural network algorithm can improve the recognition efficiency, reduce the cost of manual debugging, and ensure the accuracy of the algorithm.