Principle of Neural Network in Automobile Fault Detection Under the Background of Big Data

Abstract

With the development of automobile industry, people have higher and higher requirements for the safety, handling stability, economy, environmental protection and other performance of the automobile, and the function and structure of automobile products are becoming more and more complex. Many mechanical systems have been replaced by electronic control systems. The automobile is a typical mechatronics product. The large use of these components greatly increases the difficulty of fault diagnosis. Some faults are difficult to be judged by traditional methods. In order to improve the maintenance efficiency, better and more efficient diagnosis methods must be adopted. With the continuous advancement and development of artificial intelligence, the problem of automobile fault detection is becoming more and more important in the field of big data. Therefore, this paper proposes a fault diagnosis method based on big data. The neural network method combined with the existing vehicle detection technology can achieve a large number of vehicle fault detection, and effectively improve the efficiency and level of vehicle fault detection. The research shows that the neural network has the advantages of good self-learning and adaptive characteristics, and can overcome the difficulties in the detection process. Therefore, it can be used for the fault diagnosis and fault detection of the complex control system of the automobile. The trained network has a good effect on the fault diagnosis and diagnosis of the automobile, which can make up for the deficiency of the artificial experience method.