基于SVM多元非线性回归的微波谐振腔谷物含水率测量法

使用微波谐振腔对物料含水率测量过程中，减少谐振参量与含水率多元非线性回归过程的误差是影响测量精度的主要因素。针对这一问题，建立了一种基于支持向量机多元非线性回归模型，并确定了其中谐振频率、品质因数和环境温度的特征值、贡献率。应用SVM—KM对该模型进行实验研究，利用50组数据对模型进行训练并验证其学习性能，利用另外15组数据验证其泛化能力。实验表明，该方法能够实现微波谐振腔物料含水率的软测量，且小样本条件下比神经元网络具有优势。对SVM多元非线性回归泛化性能进行测试，其均方根相对误差为1．06％，平均绝对相对误差为0．96％，最大绝对相对误差为1．16％。

Grain moisture content measurement based on SVM multiple non-linear regression using microwave resonancet

This paper provides a method of regression for multiple non-linear relations between resonance parameters and moisture content in order to reduce the measurement errors. A multiple non-linear regression model based on support vector machine (SVM) has been developed. The eigenvalue and contribution degree of resonance frequency, quality factor and environment temperature are calculated. Experiments have been conducted using SVM-KM toolbox with 50 group data for training model and 15 group data for verifying the model performance. The results show that this algorithm not only has the ability to realize the moisture soft-sensor using microwave coaxial but also has the advantage over Neural Network Algorithm under small sample conditions. The root mean square relative error, mean absolute relative error and maximize absolute relative error of SVM model generalization performance are 1.06%, 0.96% and 1.16%, respectively.