为了提高生活污水处理工艺流程设计的效率,建立污水处理工艺数据库,用以保存从现实生活污水处理工艺流程抽象而来的数据样本.使用基于边界点的支持向量机(support vector ma-chine classification algorithm based on boundary points,BP-SVM)的工艺流程设计算法选择工艺,设置多个BP-SVM解决多分类问题,并使用遗传算法(genetic algorithm,GA)对BP-SVM参数进行参数寻优.结果表明:工艺流程设计算法给出了合适的方案,准确率达到94%,并且与其他算法相比消耗更小.证明了算法的可行性与有效性.
Algorithm for designing domestic wastewater treatment process flow based on BP-SVM
In order to improve the efficiency of domestic wastewater treatment process design,a wastewater treatment process database was established to save data samples abstracted from real domestic wastewater treatment processes,and the process was selected by the support vector ma-chine classification algorithm based on boundary points(BP-SVM).Support vector machine clas-sification algorithm based on boundary points(BP-SVM)was used to select the process.Multiple BP-SVMs were set up to solve the multi-classification problem.Parameter optimization of BP-SVM parameters was performed using genetic algorithm(GA).The results of the study show that the process design algorithm gives a suitable solution,verifies an accuracy of 94%,and con-sumes less compared to other algorithms.The feasibility and effectiveness of the algorithm is proved.
sewage treatmentprocesssupport vector machine(SVM)genetic algorithm(GA)boundary point
国家科技期刊平台
NSTL
万方数据
