基于ANFIS的软测量模型在浮选中的应用

以浮选过程为研究对象,提出一种基于自适应神经-模糊推理系统的经济技术指标软测量模型。该模型采用主元分析进行输入数据集降维,运用最小二乘法和粒子群优化算法相结合的混合学习算法对自适应神经-模糊推理系统结构参数进行优化设计。该混合学习算法提高了网络参数辨识的收敛速度,仿真结果表明,提出的模型能很好地实现浮选过程经济技术指标的全局预测,满足优化浮选药剂添加的计算要求。

Application of the soft sensing model based on the adaptive network-based fuzzy inference system(ANFIS) to the flotation process

A soft sensing model for predicting economic and technologic indexes based on the adaptive network-based fuzzy inference system(ANFIS) is proposed for the flotation process.The model adopts principal component analysis(PCA) to reduce dimensions of the input data.The structure parameters of the ANFIS are tuned by the hybrid algorithm which combines particle swarm optimization(PSO) with the least-square method.The new algorithm greatly raises the speed of parameters identification and computation convergence.Simulation results show that the proposed modeling is effective in the prediction of indexes and meets the requirement of optimization computation for the flotation process.