土壤湿度采集节点电压补偿方法——基于最小二乘支持向量机

Voltage Compensation Method of Soil Moisture Acquisition Nodes——Based on Least Squares Support Vector Machine

针对适用于WSN土壤湿度采集节点的EC-5传感器对电源电压敏感的问题,从传感器工作原理入手,分析电源电压引起检测误差的来源,且发现当传感器各项参数确定后,这种误差是随被测土壤湿度增大而增大的。采用CC 2 4 3 0芯片作为WSN信息传输节点,建立具有多节点的上下位机WSN土壤湿度采集系统,以节点电压和被测土壤实际湿度为对象,运用最小二乘支持向量机对采集节点中非线性土壤湿度传感器系统进行逆向建模,在上位机上实现由电源电压引起EC-5传感器检测误差的补偿。实验和仿真结果表明,该方法能有效地减少节点电池电压变化对WSN土壤湿度采集精度的影响。

Aimed at the voltage-sensitive problem of EC-5 sensor which is suitable for WSN soil moisture acquisition nodes,the thesis analyzes the sources of detection error according to the sensor working principle,and finds that this error will increase with the soil moisture when sensor parameters are determined.Using CC2430 platform as WSN information transmission node,WSN soil moisture acquisition system with multiple nodes based on controller and host computer is established.Taking node voltage u and the real soil moisture θ as parameters,the inverse modeling of nonlinear soil moisture sensor system is performed by least squares support vector machine（LS-SVM）,and the compensation of EC-5 sensor detection error caused by supply voltage is implemented in host computer.Experiments and simulation results show that this method can sharply reduce the influence caused by node voltage variation and improve the detection precision.