Research Article
Thermal Zero Drift Compensation of Pressure Sensor Based on Data Mining and BP Neural Network
@INPROCEEDINGS{10.1007/978-3-030-94551-0_8, author={Ya-ping Li and Dan Zhao}, title={Thermal Zero Drift Compensation of Pressure Sensor Based on Data Mining and BP Neural Network}, proceedings={Advanced Hybrid Information Processing. 5th EAI International Conference, ADHIP 2021, Virtual Event, October 22-24, 2021, Proceedings, Part I}, proceedings_a={ADHIP}, year={2022}, month={1}, keywords={Data mining BP neural network Pressure sensor drift compensation Artificial fish swarm algorithm}, doi={10.1007/978-3-030-94551-0_8} }- Ya-ping Li
Dan Zhao
Year: 2022
Thermal Zero Drift Compensation of Pressure Sensor Based on Data Mining and BP Neural Network
ADHIP
Springer
DOI: 10.1007/978-3-030-94551-0_8
Abstract
Due to the poor compensation accuracy, the traditional compensation algorithm for thermal zero shift of pressure sensor results in large error of pressure measurement. Therefore, this paper proposes a pressure sensor thermal zero drift compensation algorithm based on data mining and BP neural network. Combined with the data mining process, the characteristics of the thermal zero drift of the pressure sensor are analyzed, and the hysteresis and nonlinear characteristic curve of the pressure sensor is obtained to prepare for the compensation of the thermal zero drift. Then BP neural network is introduced to determine the parameter update mode, which is effectively combined with artificial fish swarm algorithm, and the compensation of pressure sensor thermal zero shift is realized by implementing the thermal zero shift compensation algorithm of pressure sensor. The experimental results show that the pressure measurement error range of the algorithm in this paper is 0.30 N–1.45 N. Compared with the three existing algorithms, the pressure measurement error of the algorithm in this paper is smaller, which indirectly shows that the algorithm in this paper has a higher thermal zero drift compensation accuracy, which fully shows that the algorithm in this paper compensates better performance.
