一种融合专家知识和监测数据的水质预测模型  

A water quality prediction model integrating expert knowledge and monitoring data

作　　者：韩晓霞 陈媛 胡冠宇 唐帅文 HAN Xiaoxia;CHEN Yuan;HU Guanyu;TANG Shuaiwen(Combat Support Institute,Rocket Force University of Engineering,Xi an 710025,China;Missile Engineering Institute,Rocket Force University of Engineering,Xi an 710025,China;School of Computer Science and Information Security,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]火箭军工程大学作战保障学院,陕西西安710025 [2]火箭军工程大学导弹工程学院,陕西西安710025 [3]桂林电子科技大学计算机科学与信息安全学院,广西桂林541004

出　　处：《浙江工业大学学报》2021年第5期569-576,共8页Journal of Zhejiang University of Technology

基　　金：国家自然科学基金资助项目(61773388,61751304)。

摘　　要：为了解决目前水质预测中未考虑局部无知性这一问题,提出一种基于幂集置信规则库(Belief rule base with power set,PBRB)的水质预测模型。该模型能够有效融合专家知识与定量数据,并能在描述多种不确定性的同时,将传统的辨识框架扩展到幂集,使其能够很好地表达无知性从而提高水质预测精度。此外,利用协方差矩阵自适应进化策略(Covariance matrix adaptive evolution strategy,CMA-ES)算法对PBRB模型进行优化。仿真结果表明:PBRB模型能准确预测一段时间内水质变化趋势,预测精度高于其他传统方法。To solve the problem of local ignorance that is not considered in the current water quality prediction,a water quality prediction model using BRB model under power set(PBRB)is proposed.This model can effectively fuse expert knowledge and quantitative data,and while describing a variety of uncertainties,it can extend the traditional identification framework to power sets.It can express ignorance well and improve the accuracy of water quality prediction.In addition,the covariance matrix adaptive evolution strategy(CMA-ES)algorithm is utilized to optimize PBRB model.The simulational result show that the PBRB model can accurately predict the trend of water quality over a period of time,the prediction accuracy is higher than other traditional methods.

关 键 词：水质预测 置信规则库 CMA-ES算法 幂集 

分 类 号：X824[环境科学与工程—环境工程]