欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为补偿压力传感器的温度漂移，将BP（后向传播）神经网络应用于压力传感器的温度补偿中，同时应用变尺度法对BP神经网络学习算法的缺陷进行改进，采用L-M学习算法的下降方向进行搜索，有效解决了算法失效问题；采用乘以放大倍数和加上扰动项的策略，从而放大权值更新向量和权值导数更新向量，有效解决了溢出问题。仿真结果表明，该方法有效地抑制了温度对压力传感器输出的影响，提高了传感器的稳定性和准确性。
英文摘要：
In this paper, the Back Propagation （BP） neural network is applied for the purpose of compensating the temperature drift of the pressure sensor and the Davidon Fletcher Powell （DFP） method is adopted to overcome the drawbacks of this net- work learning algorithm. Algorithm unavailability is effectively solved by search in the descent direction of the L-M learning al- gorithm and the overflow problem is solved by multiplying a magnification factor added by a disturbance term and thus magnifying the weight updated vector and the weight derivative updated vector. The simulation results show that this method can ef- fectively suppress the effects of temperature on the pressure sensor output and improve the stability and accuracy of the sensor.
同期刊论文项目
同项目期刊论文
Synthesis and thermoelectric characterization of nickel/silicon nanowire arrays by electroplating te
Nonenzymatic Alkaline Direct Glucose Fuel Cell With a Silicon Microchannel Plate Supported Electroca
Enhancement of the efficiency of dye-sensitized solar cells with highly ordered Pt-decorated nanostr
Fabrication of highly ordered porous nickel oxide anode materialsand their electrochemical character
Fabrication of nanocomposite electrode based on Bi4xNdxTi3O12 perovskite supported by silicon microc
Glucose oxidase immobilization platform based on ZnO nanowiressupported by silicon nanowires for glu
Ordered-standing nickel hydroxide microchannel arrays: Synthesis and application for highly sensitiv
期刊信息
位置：