A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
TEMPERATURE COMPENSATION STRATEGY OF PRESSURE SENSOR BASED ON BP NEURAL NETWORK OPTIMIZED BY GLOWWORM SWARM OPTIMIZATION
In order to solve the problem that temperature drift of silicon piezoresistive pressure sensor affects the accuracy of engineering measurement,proposed a temperature compensation strategy for BP neural network based on glowworm swarm optimization. The generalized BP neural network is used to optimize the weights and thresholds by using the firefly algorithm,thus improving the generalization performance and searching speed of the neural network,carried out temperature compensation of pressure sensor by optimized BP neural network. The temperature compensation performance of optimized BP neural network compares to that of conventional neural network and particle swarm optimization neural network. The results showed that compared with the conventional neural network and PSO optimization BP neural network,the optimized GSO optimization BP neural network is effective.The compensation error of GSO-BP neural network is 52% less than that of BP and 23% less than that of PSO-BP.Considering the time of compensation,the comprehensive performance of the BP neural network optimized by GSO is better.The compensated sensor data meet the experimental requirements of the subject.The compensation algorithm is feasible.
TEMPERATURE COMPENSATION STRATEGY OF PRESSURE SENSOR BASED ON BP NEURAL NETWORK OPTIMIZED BY GLOWWORM SWARM OPTIMIZATION
In order to solve the problem that temperature drift of silicon piezoresistive pressure sensor affects the accuracy of engineering measurement,proposed a temperature compensation strategy for BP neural network based on glowworm swarm optimization. The generalized BP neural network is used to optimize the weights and thresholds by using the firefly algorithm,thus improving the generalization performance and searching speed of the neural network,carried out temperature compensation of pressure sensor by optimized BP neural network. The temperature compensation performance of optimized BP neural network compares to that of conventional neural network and particle swarm optimization neural network. The results showed that compared with the conventional neural network and PSO optimization BP neural network,the optimized GSO optimization BP neural network is effective.The compensation error of GSO-BP neural network is 52% less than that of BP and 23% less than that of PSO-BP.Considering the time of compensation,the comprehensive performance of the BP neural network optimized by GSO is better.The compensated sensor data meet the experimental requirements of the subject.The compensation algorithm is feasible.
TEMPERATURE COMPENSATION STRATEGY OF PRESSURE SENSOR BASED ON BP NEURAL NETWORK OPTIMIZED BY GLOWWORM SWARM OPTIMIZATION
WANG Hui (author) / FU Peng (author) / SONG YuNing (author)
2020
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
| British Library Online Contents | 2015