基于多模型建模的木材含水率测量方法研究

针对单一模型无法全面描述木材含水率的复杂非线性特性问题,本文提出一种多模型建模的方法测量木材含水率,该方法先用模糊C均值聚类算法将含水率等效电阻、进风口、出风口温度等数据分成具有不同聚类中心的子集,每一子集依据样本数分别采用径向基网络、支持向量积训练得出子模型,再用模糊聚类后产生的隶属度将各子模型的输出加权求和得到木材含水率测量的模型。通过实例验证了本方法与RBFNN建模对于木材含水率的检测,具有更好的泛化结果和测量精度。

The Study on Wood Moisture Measurement Based Multi-modeling Method

To solve the problem that a single model can not fully describe precisely the non-linear characteristic of the wood moisture content in the full scale., wood moisture measurement based multi-modeling method is presented in this paper, the method firstly used FCM to classify equivalent resistance value, the inlet tuyere temperature and the outlet tuyere temperature data into subsets which have different cluster centers. Each subset makes a model according to RBFNN and LS-SVM according to the sample numbers of each subset, and then makes out the model. An example simulation proves that this method has a better generalization results and measurement accuracy.