Paper
15 January 2024 Research on neural network temperature compensation for embedded weighing systems
Author Affiliations +
Proceedings Volume 12983, Second International Conference on Electrical, Electronics, and Information Engineering (EEIE 2023); 129831Q (2024) https://doi.org/10.1117/12.3017817
Event: Second International Conference on Electrical, Electronics, and Information Engineering (EEIE 2023), 2023, Wuhan, China
Abstract
The accuracy of weighing systems is easily affected by sensors, conversion circuits, temperature, and other factors. Aiming at the problem of significant temperature impact during the operation of the weighing system, which leads to a decrease in weighing accuracy. This article proposes a BP neural network method for temperature compensation of the weighing system to further improve the weighing accuracy. Firstly, a weighing system is built based on STM32 to collect system temperature and weighing data. Then, a BP neural network is built using MATLAB, and the calibration data is imported to train the optimal model of the BP neural network. Finally, the model parameters are imported into an embedded system to achieve real-time temperature compensation for the STM32 weighing system. The experimental results show that the accuracy and stability of the weighing system have been improved, and it has good application value.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Hui Gan, Meini Lv, Liping Zhan, and Zelin Yan "Research on neural network temperature compensation for embedded weighing systems", Proc. SPIE 12983, Second International Conference on Electrical, Electronics, and Information Engineering (EEIE 2023), 129831Q (15 January 2024); https://doi.org/10.1117/12.3017817
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Neural networks

Data modeling

Education and training

Sensors

Neurons

Embedded systems

Data acquisition

Back to Top