基于BP-SVM的生活污水处理工艺流程设计算法  

Algorithm for designing domestic wastewater treatment process flow based on BP-SVM

作　　者：张建民 陈敏杰 ZHANG Jianmin;CHEN Minjie(School of Urban Planning and Municipal Engineering,Xi’an Polytechnic University,Xi’an 710048,China)

机构地区：[1]西安工程大学城市规划与市政工程学院,陕西西安710048

出　　处：《西安工程大学学报》2024年第3期68-74,共7页Journal of Xi’an Polytechnic University

摘　　要：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 machine 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。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 machine classification algorithm based on boundary points(BP-SVM).Support vector machine classification 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 consumes less compared to other algorithms.The feasibility and effectiveness of the algorithm is proved.

关 键 词：污水处理 工艺流程 支持向量机 遗传算法 边界点 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]