基于改进型LS-SVM技术的煤泥浮选智能优化控制方法

Intelligent Optimization Control Method of Slime Flotation Based on Improved LS-SVM Technology

针对现有的煤泥浮选控制算法公式复杂、评估时间长等问题,文章提出了一种基于多重最小二乘支持向量机(LS-SVM)的浮选精煤灰分综合评估模型;首先,建立了基于LS-SVM的单一煤种的单一估计模型,并利用引力搜索算法对其内部参数进行了优化;其次,设计了模型更新策略,解决了单一模型精度下降的问题;此外,为了解决模型失配问题,还研究了由多个单一模型组成的多个LS-SVM模型以及模型切换机制;最后,进行了工业试验和评价,实验结果表明,煤泥浮选的评估值与实际值的平均相对误差为3.32%,综合模型的估计精度和适应性能够满足工业要求。

Aiming at the problems of complex formulas and long evaluation time of the existing slime flotation control algorithms,a comprehensive evaluation model of flotation cleaned coal ash based on multiple least squares support vector machine(LS-SVM)is proposed in this paper.Firstly,a single estimation model of single coal type based on the LS-SVM is established,and a gravity search algorithm is used to optimize the internal parameters.Secondly,the model updating strategy is designed to solve the problem that the accuracy of the single model decreases.In addition,in order to solve the problem of model mismatch,the multiple LS-SVM models composed of multiple single models and the model switching mechanism are also studied.Finally,the industrial test and evaluation are carried out.The experimental results show that the average relative error between the evaluation value and the actual value of slime flotation reaches 3.32%,and the estimation accuracy and adaptability of the comprehensive model can meet the industrial requirements.