Multi-parameter online optimization algorithm of BP neural network algorithm in Internet of Things service

• Published in: Neural computing & applications Vol. 33; no. 2; pp. 505 - 515
• Main Authors: Wang, Pingquan, Liu, Xun, Han, Zheng
• Format: Journal Article
• Language: English
• Published: London Springer London 01.01.2021; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computer simulation; Data collection; Data Mining and Knowledge Discovery; Feedback; Image Processing and Computer Vision; Internet of Things; Moisture content; Neural networks; Optimization; Parameters; Probability and Statistics in Computer Science; S.I.: DPTA Conference 2019; Time measurement; NNA; MP online measurement; BP neural network; IOT system
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-020-04913-8

With the development of science and technology, the application of the Internet of Things (IOT) is becoming more and more widespread. Applying BP neural network algorithms (NNA) to the IOT system will help improve the performance of the IOT system. The research purpose of this paper is to solve the problems of long-parameter measurement cycle and untimely feedback of the existing IOT online measurement system. In this paper, a multi-parameter (MP) IOT online measurement system based on BP NNA is designed, and a simulation test experiment is performed. The MP online measurement IOT system based on the BP NNA completes the parameter collection, analysis, and display through the perception layer, network transmission layer, and application layer. The core is that the system application layer adds the BP NNA to optimize real-time acquisition parameters, processing to reduce parameter measurement time. It can be known from algorithm simulation experiments that the online measurement system based on the BP NNA proposed in this paper uses the BP NNA to predict the absolute error value of the final moisture content and the measured moisture content within 0.3, and the absolute error of the moisture content value in actual production. It is acceptable in the range of 0.5, which speeds up data collection time. This system has a very good effect on improving the feedback adjustment speed of the manufacturing process system.