中国仪器仪表
中國儀器儀錶
중국의기의표
CHINA INSTRUMENTATION
2012年
9期
32-36
,共5页
扩散硅压力传感器%误差补偿%BP神经网络%SDE算法
擴散硅壓力傳感器%誤差補償%BP神經網絡%SDE算法
확산규압력전감기%오차보상%BP신경망락%SDE산법
Diffusion silicon pressure sensorError compensation BP neural networkSDE algorithm
采用BP神经网络来建立扩散硅压力传感器的输出输入模型,其网络模型具有三层结构,采用改进型的差分进化算法来优化BP神经网络的权值和阀值,并在MATLAB中进行了仿真。经训练得到补偿后扩散硅压力传感器的输出满量程误差可达到0.035%,结果表明采用基于改进型差分进化算法的BP神经网络建模对提高智能差压传感器的测量准确度具有参考价值。
採用BP神經網絡來建立擴散硅壓力傳感器的輸齣輸入模型,其網絡模型具有三層結構,採用改進型的差分進化算法來優化BP神經網絡的權值和閥值,併在MATLAB中進行瞭倣真。經訓練得到補償後擴散硅壓力傳感器的輸齣滿量程誤差可達到0.035%,結果錶明採用基于改進型差分進化算法的BP神經網絡建模對提高智能差壓傳感器的測量準確度具有參攷價值。
채용BP신경망락래건립확산규압력전감기적수출수입모형,기망락모형구유삼층결구,채용개진형적차분진화산법래우화BP신경망락적권치화벌치,병재MATLAB중진행료방진。경훈련득도보상후확산규압력전감기적수출만량정오차가체도0.035%,결과표명채용기우개진형차분진화산법적BP신경망락건모대제고지능차압전감기적측량준학도구유삼고개치。
A three layers' input-output model of diffused silicon pressure sensor is built using BP neural network, and then using the improved differential evolution algorithm to optimize the weights and thresholds of BP neural network in MATLAB simulation. Through the training, the compensated diffused silicon pressure sensor's output full-scale error can be achieved 0.035%. Theresults show that the BP neural network modeling based on the improved differential evolution algorithm is meaningful to improve the accuracy of the pressure sensor.