基于GSA-LSSVM的浓缩机煤泥沉降厚度预测模型研究

Research on Predictive Model of Thickener Slime Sedimentation Thickness Based on GSA-LSSVM

根据选煤厂浓缩机煤泥沉降过程煤泥厚度检测困难,相关检测仪器价格昂贵、检修困难且可靠性较差等情况,提出了利用浓缩过程可测变量,通过对万有引力搜索算法(GSA)优化最小二乘支持向量机(LSSVM)模型中的相关参数,建立了一种基于GSA-LSSVM的浓缩机煤泥沉降厚度预测模型。结果表明,通过煤泥沉降厚度预测值和实测值对比显示相对误差在9%以内,表明模型具有较高的精确性和稳定性。对于实现选煤厂浓缩机运行过程中关键参数在线检测和闭环优化控制具有重要意义。

According to the circumstances of difficult to detect slime thickness,expensive related testing equipment,difficult maintenance and poor reliability during the sedimentation process of the thickener in coal preparation plant.Proposing variables that can be measured to use in the concentration process.Though optimized the relevant parameters in the least squares support vector machine(LSSVM)model by the gravitational search algorithm(GSA),a prediction model of slime sedimentation thickness of thickener based on GSA-LSSVM was established.The results show that the comparison between the predicted value and the measured value of the sedimentation slime thickness shows that the relative error is within 9%,indicating that the model has high accuracy and stability.It is of great significance to realize the on-line detection and closed-loop optimization control of key parameters in the operation process of the thickener of the coal preparation plant.