基于IPSO-LSSVM的污水BOD预测应用研究

生化需氧量（BOD）的快速准确测量对于污水处理过程的调控至关重要。针对污水处理过程中BOD浓度测量时效性较低等问题，选择最小二乘支持向量机（LSSVM）作为BOD浓度预测模型，并选用粒子群优化算法（PSO）优化回归性能参数，同时使用自适应惯性权重计算方法对PSO进行改进，建立了IPSO-LSSVM预测模型。运用预测模型对某污水厂数据进行仿真研究以及3种误差分析，结果表明该模型具有较好的预测精度。

Research on Application of Predicting Wastewater BOD Based on IPSO-LSSVM

The COD parameters in the sewage treatment process have strong nonlinearity and are difficult to measure directly. In order to improve the accuracy and timeliness of COD concentration measurement in the process of sewage treatment, a COD prediction model based on particle swarm optimization optimization least squares support vector machine was established. Firstly, the auxiliary variables in the model are selected according to the on-site process of sewage treatment, and the least squares support vector machine model is established. Secondly, the parameters in the model are optimized by particle swarm algorithm to obtain the best performance. Finally, the parameters after training optimization are brought into the model for prediction. The prediction results show that the model has good prediction accuracy and can provide reliable reference information for sewage treatment sites.