Accurate prediction for electro-oxidation regeneration of chromium- containing waste acid based on artificial neural network

doi:10.19965/j.cnki.iwt.2023-1270

Abstract

Abstract:

The waste acid generated in the production of expanded graphite by “chromium method” has the characteristics of high acid concentration and high chromium content. The Cr(Ⅲ) can be oxidized to Cr(Ⅵ) by electro-oxidation in membrane system to realize the regeneration of waste acid containing chromium. Since it was difficult to achieve real-time detection of Cr(Ⅵ) content in this highly acidic system, a study based on artificial neural network was conducted to accurately predict the electro-oxidation regeneration effect of chromium-containing waste acid. Based on the regeneration of chromium-containing waste acid experiments, the key characteristic parameters of hexavalent chromium regeneration including time, sulfuric acid concentration, and electrolyte volume were determined by correlation analysis. Then, through hyperparameter optimization, the relatively optimal topology structure of the artificial neural network was obtained as follows: Neurons=35, Batch size=30, Layers=4. The coefficient of determination(R ²) between predicted value and experimental value was greater than 0.97, and the root-mean-square error(RMSE) was less than 0.04. Finally, the average relative error between predicted value and experimental value was 0.14%, which indicated that the model had good generalization ability. The artificial neural network model overcame the difficulty of predicting electrochemical processes due to multi-parameter, nonlinearity and time variability, and could realize the prediction of Cr(Ⅵ) regeneration under complex mapping conditions, which was of great significance for the optimization and control of electrochemical processes.

Key words: membrane system, electro-oxidation, chromium containing waste acid, artificial neural network, resource regeneration

摘要：

“铬法”膨胀石墨生产过程中产生的废酸具有酸浓度大、铬含量高等特征，可以采用隔膜体系通过电氧化法将Cr（Ⅲ）氧化为Cr（Ⅵ），实现含铬废酸的资源化再生。基于该强酸体系难以实现Cr（Ⅵ）含量的实时检测，开展了基于神经网络精准预测含铬废酸电氧化再生效果的研究。在含铬废酸再生实验基础上，首先采用相关性分析方法确定了电解时间、H₂SO₄浓度和电解液体积为Cr（Ⅵ）再生的关键特征参数，然后通过超参数优化获得人工神经网络的相对最优拓扑结构：神经元数量=35、批训练样本数=30、隐藏层层数=4，构建模型预测值与实验值的决定系数（R ²）大于0.97，均方根误差（RMSE）小于0.04。最后经实验验证，模型预测值与实验值的平均相对误差最大为0.14%，表明模型具有很好的泛化能力。人工神经网络模型克服了由于多参数、非线性与时变性造成的电化学过程预测难的问题，可以实现复杂映射条件下对Cr（Ⅵ）再生的预测，对电化学过程的优化调控具有重要意义。

关键词: 隔膜体系, 电氧化, 含铬废酸, 人工神经网络, 资源化再生

CLC Number:

Yaqi SHI, Guangyuan MENG, Peng CHEN, Xinwan ZHANG, Tao FU, Zhengwu YANG, Liansheng ZHANG, Lehua ZHANG. Accurate prediction for electro-oxidation regeneration of chromium- containing waste acid based on artificial neural network[J]. Industrial Water Treatment, 2025, 45(1): 131-138.

师雅琪, 孟广源, 陈鹏, 张芯婉, 付涛, 杨正武, 张连胜, 张乐华. 基于神经网络精准预测含铬废酸电氧化再生效果[J]. 工业水处理, 2025, 45(1): 131-138.

/ / Recommend / Download Citations

URL: https://www.iwt.cn/EN/10.19965/j.cnki.iwt.2023-1270

https://www.iwt.cn/EN/Y2025/V45/I1/131

Figures/Tables 8

Fig.1 Topology structure diagram of ANN

Fig.2 Effects of different factors on regeneration rate of Cr（Ⅵ）

Fig.3 Heatmap of correlation coefficients

Fig.4 Hyperparameter optimization

Fig.5 Distribution of predicted values and experimental values for train sets and test sets

Fig.6 Error distribution and prediction performance of train set

Fig.7 Error distribution and prediction performance of test set

Fig.8 Error and comparison between predicted values and experimental values of three sets of validation data

References 27

1	赵正平. 可膨胀石墨及其制品的应用及发展趋势［J］. 中国非金属矿工业导刊，2003（1）：7-9.
	ZHAO Zhengping. The application and prospects of graphite intercalation compounds and its products［J］. China Non-metallic Mining Industry Herald，2003（1）：7-9.
2	PIAO Hongwei， ZHAO Jian， LIU Mingyi，et al. Ultra-low power light driven lycopodium-like nanofiber membrane reinforced by PET braid tube with robust pollutants removal and regeneration capacity based on photo-Fenton catalysis［J］. Chemical Engineering Journal，2022，450：138204.
3	LIAO Minzi， ZHAO Shengxi， WEI Kai，et al. Precise decomplexation of Cr（Ⅲ）-EDTA and in situ Cr（Ⅲ） removal with oxalated zero-valent iron［J］. Applied Catalysis B：Environmental，2023，330：122619. doi:10.1016/j.apcatb.2023.122619
4	RAMÍREZ-ESTRADA A， MENA-CERVANTES V Y， FUENTES-GARCÍA J，et al. Cr（Ⅲ） removal from synthetic and real tanning effluents using an electro-precipitation method［J］. Journal of Environmental Chemical Engineering，2018，6（1）：1219-1225.
5	BONOLA B， SOSA-RODRÍGUEZ F S， GARCÍA-PÉREZ U M，et al. The influence of cathode material，current density and pH on the rapid Cr（Ⅲ） removal from concentrated tanning effluents via electro-precipitation［J］. Journal of Hazardous Materials Advances，2021，2：100008.
6	Weiguang LÜ， RUAN Dingshan， ZHENG Xiaohong，et al. One-step recovery of valuable metals from spent lithium-ion batteries and synthesis of persulfate through paired electrolysis［J］. Chemical Engineering Journal，2021，421：129908.
7	ALLIOUX F M， DAVID O， MERENDA A，et al. Catalytic nickel and nickel-copper alloy hollow-fiber membranes for the remediation of organic pollutants by electrocatalysis［J］. Journal of Materials Chemistry A，2018，6（16）：6904-6915.
8	苏德林，武斌，周定，等. 隔膜电解法净化再生镀锌钝化液的研究［J］. 哈尔滨工业大学学报，1997，29（6）：105-108.
	SU Delin， WU Bin， ZHOU Ding，et al. Purification and regeneration of aged Cr-6 solution by electrolysis method［J］. Journal of Harbin Institute of Technology，1997，29（6）：105-108.
9	CHEN Lei， WU Chun， QIN Wei，et al. Enhanced electrochemical behaviors of carbon felt electrode using redox-active electrolyte for all-solid-state supercapacitors［J］. Journal of Colloid and Interface Science，2020，577：12-18.
10	CHEN Yunfeng， LEI Hao， GAO Zhenqiu，et al. Energy autonomous electronic skin with direct temperature-pressure perception［J］. Nano Energy，2022，98：107273.
11	ARREDONDO D， LAKIN M R. Supervised learning in a multilayer，nonlinear chemical neural network［J］. IEEE Transactions on Neural Networks and Learning Systems，2023，34（10）：7734-7745.
12	SHI Qiao， LIN Yanwen， HAO Yongchao，et al. Unconventional growth of methane hydrates：A molecular dynamics and machine learning study［J］. Energy，2023，282：128337.
13	胡锦文，孟广源，张之杰，等. 人工智能在电化学水处理过程中的应用［J］. 化工进展，2022，41（S1）：497-506.
	HU Jinwen， MENG Guangyuan， ZHANG Zhijie，et al. Application of artificial intelligence model in electrochemical water treatment process［J］. Chemical Industry and Engineering Progress，2022，41（S1）：497-506.
14	OGEDJO M， KAPOOR A， SENTHIL KUMAR P，et al. Modeling of sugarcane bagasse conversion to levulinic acid using response surface methodology（RSM），artificial neural networks（ANN），and fuzzy inference system（FIS）：A comparative evaluation［J］. Fuel，2022，329：125409.
15	LIU Xiaonan， NIE Yong， WU Xiaolei. Predicting microbial community compositions in wastewater treatment plants using artificial neural networks［J］. Microbiome，2023，11（1）：93.
16	SINGH V， MEHRA R， RAMESH K B，et al. Treatment of carpet and textile industry effluents using diplosphaera mucosa VSPA：A multiple input optimisation study using artificial neural network-genetic algorithms［J］. Bioresource Technology，2023，387：129619.
17	张浩良，刘聪，洪乾坤，等. MBR中膜污染的人工神经网络预测研究进展［J］. 工业水处理，2022，42（7）：15-23.
	ZHANG Haoliang， LIU Cong， HONG Qiankun，et al. Research progress of artificial neural network for membrane fouling prediction in MBR［J］. Industrial Water Treatment，2022，42（7）：15-23.
18	严亚萍，王刚，姜盛基，等. 人工神经网络在环境领域中的研究进展［J］. 应用化工，2022，51（1）：170-176.
	YAN Yaping， WANG Gang， JIANG Shengji，et al. Research progress of artificial neural networks in the field of environment［J］. Applied Chemical Industry，2022，51（1）：170-176.
19	DU Shengdong， LI Tianrui， YANG Yan，et al. Deep air quality forecasting using hybrid deep learning framework［J］. IEEE Transactions on Knowledge and Data Engineering，2021，33（6）：2412-2424.
20	MÉNDEZ M， MERAYO M G， NÚÑEZ M. Machine learning algorithms to forecast air quality：A survey［J］. Artificial Intelligence Review，2023：1-36.
21	HAGGERTY R， SUN Jianxin， YU Hongfeng，et al. Application of machine learning in groundwater quality modeling：A comprehensive review［J］. Water Research，2023，233：119745.
22	BILALI A EL， TALEB A， BROUZIYNE Y. Groundwater quality forecasting using machine learning algorithms for irrigation purposes［J］. Agricultural Water Management，2021，245：106625.
23	LIU Xian， LU Dawei， ZHANG Aiqian，et al. Data-driven machine learning in environmental pollution：Gains and problems［J］. Environmental Science & Technology，2022，56（4）：2124-2133.
24	JIANG Yiqi， LI Chaolin， SONG Hongxing，et al. Deep learning model based on urban multi-source data for predicting heavy metals（Cu，Zn，Ni，Cr） in industrial sewer networks［J］. Journal of Hazardous Materials，2022，432：128732.
25	张芯婉，孟广源，方立强，等. 基于BP神经网络的电化学还原硝酸盐过程智能控制［J］. 电化学（中英文），2023，29（12）：34-43.
	ZHANG Xinwan， MENG Guangyuan， FANG Liqiang，et al. Intelligent control based on BP artificial neural network for electrochemical nitrate removal［J］. Journal of Electrochemistry，2023，29（12）：34-43.
26	MAURYA A K， REDDY B S， THEERTHAGIRI J，et al. Modeling and optimization of process parameters of biofilm reactor for wastewater treatment［J］. Science of the Total Environment，2021，787：147624.
27	LU Xuesong， YANG Shoufeng， EVANS J R G. Ultrasound-assisted microfeeding of fine powders［J］. Particuology，2008，6（1）：2-8.

[1]	Jun YANG, Jie ZHOU, Nan ZHANG, Haibo XU. Effect of Re-flocculation of coagulant on ultrafiltration and reverse osmosis membrane system [J]. Industrial Water Treatment, 2022, 42(9): 155-159.
[2]	Haoliang ZHANG, Cong LIU, Qiankun HONG, Kanming WANG, Hongyu WANG. Research progress of artificial neural network for membrane fouling prediction in MBR [J]. Industrial Water Treatment, 2022, 42(7): 15-23.
[3]	Bowen Gao,Qianyi Ge,Pengkang Jin,Rui Wang,Ziyuan Wang,Zijun Yang. Printing and dyeing wastewater source separation treatment process and its application in reconstruction project [J]. Industrial Water Treatment, 2020, 40(9): 119-123.
[4]	Zhuo Qiongfang, Luo Meiqing, Li Yongming, Yang Bo, Yi Hao, Wang Li, Cui Kai, Guo Qingwei, Xie Shuibo, Lin Jiancong, He Tao. Preparation of novel titanium-based lead dioxide electrode and its degradation capacity for perfluorooctanoic acid(PFOA) [J]. INDUSTRIAL WATER TREATMENT, 2019, 39(3): 30-34.
[5]	Shen Mingjin. Application of Kohonen and RBF neural networks to simultaneous determination of cobalt, nickel and vanadium in wastewater [J]. INDUSTRIAL WATER TREATMENT, 2016, 36(8): 97-100.
[6]	Zhao Zhongqiang, Lu Xiaoshan, Zuo Weixiong. Researcch on the electro-oxidation treatment of water-based printing ink wastewater [J]. INDUSTRIAL WATER TREATMENT, 2015, 35(7): 72-75.
[7]	Jiang Yeli, Wang Bojun, Zhu Zhaolian, Li Aimin. Study on the treatment of toluene nitrification wastewater by electro-catalytic reduction-electro-oxidation [J]. INDUSTRIAL WATER TREATMENT, 2014, 34(9): 36-39.
[8]	Wang Shudong, Tan Yuehai, Jin Ludong, Guo Linlin, Huang Dongdong. Analysis of the key running points of double-membrane process and typical fault treatment [J]. INDUSTRIAL WATER TREATMENT, 2013, 33(4): 85-87.
[9]	Xu Bo, Jia Mingchun, Men Jinfeng. Study on the prediction of the deoxidization efficiency of modified sponge iron with artificial neural network [J]. INDUSTRIAL WATER TREATMENT, 2012, 32(9): 29-31.
[10]	Shi Baoqiang, Zhang Hanmin, Yang Fenglin, Meng Fangang, Zhang Xingwen. Prospect of artificial neural network in the study of membrane fouling in membrane bioreactor [J]. INDUSTRIAL WATER TREATMENT, 2006, 26(12): 14-17.
[11]	Tan Lei, Wang Baoshan, Li Desheng, Xu Donghui. Study on the treatment of paper mill was tewater by flocculation and electro-oxidation reactor [J]. INDUSTRIAL WATER TREATMENT, 2006, 26(11): 19-22.
[12]	Qing Xiaoxia, Yu Jianping. Soft sensors and it's use in wastewater treatment systems [J]. INDUSTRIAL WATER TREATMENT, 2005, 25(3): 13-16.
[13]	Liu Jianyong, Xue Gang, Liu Zhongping, Zhou Xuefei, Gu Guowei. Fuzzy neural network control used in the process of sewage water treatment [J]. INDUSTRIAL WATER TREATMENT, 2003, 23(5): 9-12.

Please choose a citation manager

Content to export