基于 BPNN 的焦化废水生化处理的智慧预测和调控

Intelligent Prediction and Control Technology of Coking Wastewater Bio-Treatment Based on BPNN Model

摘要

焦化厂污水生化处理过程复杂，难以精准调控药剂投加量达到稳定出水的效果。本研究采用基于反向传播神经网络（BPNN）的智慧调控方法，实现对焦化废水生化出水水质和药剂投加量的精准预测。结果表明，水质预测模型的决定系数（R²）达到 0.891，药剂投加量预测模型的R² 分别为 0.605、0.798 和 0.809。数据清洗和特征选择显著提升了模型的预测性能，双输出模型的预测效果优于单输出模型。本研究可为焦化行业生化处理过程及其加药装置的智慧调控提供理论参考。

Abstract

The biochemical treatment of coking wastewater is a complex process, so accurate regulation of chemical dosing to ensure stable effluent quality poses a great challenge. In this study, an intelligent control model based on a back propagation neural network (BPNN) was proposed to achieve precise prediction of effluent quality and chemical dosage in the biochemical treatment process of coking wastewater. The results demonstrated that the coefficient of determination (R²) of the effluent quality prediction model reached 0.891. TheR² values of the chemical dosage prediction models were 0.605, 0.798, and 0.809, respectively. Data preprocessing techniques, including data cleaning and feature selection, significantly enhanced the predictive performance of the models. Moreover, the dual-output model exhibited superior predictive accuracy than the single-output models. This study provides a theoretical reference for the intelligent regulation of biochemical treatment processes and chemical dosing systems in the coking industry

关键词

神经网络 / 水质预测 / 智慧调控 / 数据预处理 / 焦化废水

Key words

neural network / water quality prediction / intelligent control / data cleaning / coking wastewater

参考文献

[1] 孙贤波, 钱飞跃, 庞丽娜, 等. 焦化废水生化出水总氰构成及去除特性 [J].华东理工大学学报 (自然科学版), 2011, 37(3):335-339.

[2] 张万辉, 韦朝海. 焦化废水的污染物特征及处理技术的分析 [J].化工环保, 2015, 35(3):272-278.

[3] 郭忠良, 李培, 李森. 焦化废水处理技术研究进展 [J].中国资源综合利用, 2023, 41(12):155-158.

[4] SIGMUND G, GHARASOO M, HÜFFER T, et al. Deep learning neural network approach for predicting the sorption of ionizable and polar organic pollutants to a wide range of carbonaceous materials[J].Environmental Science & Technology, 2020, 54(7):4583-4591.

[5] 陈春霞. 浅析机器学习的发展与应用 [J].信息系统工程, 2017(8):99-100.

[6] LOWE M, QIN R W, MAO X W. A review on machine learning, artificial Intelligence, and smart technology in water treatment and monitoring[J].Water, 2022, 14(9):1384.

[7] 成睿, 孟广源, 殷瑶, 等. 神经网络 BPNN 模型机器学习方法应用于电化学去除氨氮过程的预测与优化 [J].华东理工大学学报 (自然科学版), 2023, 49(2):202-210.

[8] 李思敏, 产青青, 金鑫, 等. 机器学习在水务行业中的应用现状与发展前景 [J].水电能源科学, 2024(3):43-48.

[9] LIU M, LU J. Support vector machine: An alternative to artificial neuron network for water quality forecasting in an agricultural nonpoint source polluted river?[J].Environmental Science and Pollution Research, 2014, 21(18):11036-11053.

[10] HAGHIABI A H, NASROLAHI A H, PARSAIE A. Water quality prediction using machine learning methods[J].Water Quality Research Journal, 2018, 53(1):3-13.

[11] CASTRASTRILLO M, GARCÍA Á L. Estimation of high frequency nutrient concentrations from water quality surrogates using machine learning methods[J].Water research, 2020, 172:115490.

[12] WU Y, ZHANG X, XIAO Y, et al. Attention neural network for water image classification under IoT environment[J].Applied Sciences, 2020, 10(3):909.

[13] ŠILJIĆ TOMIĆ A, ANTANASIJEVIĆ D, RISTIĆ M, et al. A linear and non—linear polynomial neural network modeling of dissolved oxygen content in surface water: Inter— and extrapolation performance with inputs’ significance analysis[J].Science of the Total Environment, 2018, 610—611:1038-1046.

[14] MA J, DING Y X, CHENG J C P, et al. Soft detection of 5—day BOD with sparse matrix in city harbor water using deep learning techniques[J].Water Research, 2020, 170:115350.

[15] CHEN K Y, CHEN H X, ZHOU C L, et al. Comparative analysis of surface water quality prediction performance and identification of key water parameters using different machine learning models based on big data[J].Water research, 2020, 171:115454.

[16] 阳艳芳. 单片机在水处理自动加药系统中的应用 [J].电子技术应用, 1995(4):6-7, 21.

[17] 曹龙. 给水处理厂加药系统的控制研究 [D].沈阳: 东北大学, 2014.

[18] 孙奎. 污水处理自动加药系统设计与应用 [J].科技创新与应用, 2017(4):27-28.

[19] MAN Y, HU Y S, REN J Z. Forecasting COD load in municipal sewage based on ARMA and VAR algorithms[J].Resources, Conservation and Recycling, 2019, 144:56-64.

[20] WANG Z F, MAN Y, HU Y S, et al. A deep learning based dynamic COD prediction model for urban sewage[J].Environmental Science: Water Research & Technology, 2019, 5(12):2210-2218.

[21] BAGHERZADEH F, MEHRANI M J, BASIRIFARD M, et al. Comparative study on total nitrogen prediction in wastewater treatment plant and effect of various feature selection methods on machine learning algorithms performance[J].Journal of Water Process Engineering, 2021, 41:102033.

[22] HEO S, NAM K, TARIQ S, et al. A hybrid machine learning—based multi—objective supervisory control strategy of a full—scale wastewater treatment for cost—effective and sustainable operation under varying influent conditions[J].Journal of Cleaner Production, 2021, 291:125853.

[23] HUANG R X, MA C X, MA J, et al. Machine learning in natural and engineered water systems[J].Water Research, 2021, 205:117666.

[24] 安昱宁. 基于深度学习的污水处理厂出水水质预测建模研究 [D].山东青岛: 青岛理工大学, 2024.

基金资助

2023 年鸡西市石墨产业揭榜挂帅项目(JKJB2023H03)

新疆天山英才项目