生物氧化预处理过程中溶氧量的预测研究

溶氧量作为影响生物氧化速率的重要因素之一，精准地预测溶氧量对生物氧化冶金工艺有着十分重要的意义，为提高模型预测的精度，本文提出一种基于鲸鱼算法-最小二乘支持向量机（WOA-LSSVM）的矿浆溶氧量预测建模方法，用鲸鱼算法对最小二乘支持向量机的核函数宽度和惩罚因子进行寻优，然后建立WOA-LSSVM溶氧量预测模型，最后输出预测结果，并与LSSVM和(粒子群算法)PSO-LSSVM模型对比。研究表明，WOA-LSSVM模型的预测结果更接近于实际值，其相对误差也比另外两种模型低，该模型可以很好地预测溶解氧，具有预测精度高的优势，可应用于之后对于溶氧量的预测研究。

Study on The Prediction of Dissolved Oxygen during The Biological Oxidation Pretreatment Process

As one of the important factors influencing the rate of biological oxidation, dissolved oxygen content is very important for the biological oxidation metallurgy process. To improve the accuracy of model prediction, this paper proposes a whale algorithm-based least square support Vector machine (WOA-LSSVM) predictive modeling method for dissolved oxygen content of pulp, the whale algorithm is used to optimize the kernel function width and penalty coefficients of the least-squares-supported vector machine, the WOA-LSSVM dissolved oxygen prediction model is established and finally the prediction results are output and compared with LSSVM and (particle swarm optimization) PSO-LSSVM model. According to the study results, the predicted results of the WOA-LSSVM model are closer to the actual values and the relative error is lower than the other two models, this model can predict dissolved oxygen well, and has the advantage of high prediction accuracy, which can be applied to the future research on the prediction of dissolved oxygen.