In the process of industrialization, water pollution accidents occur from time to time, resulting in major economic losses and negative impacts on the water environment. Statistical analysis shows that it is difficult to issue early warning quickly and effectively before the accident, leading to unavoidable water pollution accidents. In order to improve the environment and reduce water pollution accidents, governments and enterprises at all levels need to invest a lot of human resources. In this paper, Bayesian algorithm and artificial neural network are used to study industrial wastewater early warning and effectively prevent water pollution accidents. This paper first introduces the main parts and functions of industrial sewage early warning, then uses Bayesian network to carry out water quality early warning, introduces the calculation process of Bayesian water quality evaluation, and establishes Bayesian network water quality early warning system. Then this paper uses artificial neural network to carry out water quality early warning, builds a comprehensive model of neural network evaluation, and introduces the process of artificial neural network water quality evaluation in detail. In the experimental part, Bayesian algorithm and artificial neural network algorithm are used to evaluate the grade of industrial sewage. The experimental results show that the two algorithms have good accuracy, F1 value and recall rate when evaluating the quality of industrial sewage. The accuracy rate of the industrial sewage quality evaluation results of the two algorithms is more than 95%, which shows that Bayesian algorithm and artificial neural network can be well applied in the industrial sewage early warning field.

Xiangru Hou. Construction of Industrial Sewage Early Warning System Based on Bayesian Algorithm and Artificial Neural Network. Water Pollution Prevention and Control Project (2020), Vol. 1, Issue 4: 51-60. https://doi.org/10.38007/WPPCP.2020.010406.

[1] Guo, Zhiwei. "Graph embedding‐based intelligent industrial decision for complex sewage treatment processes." International Journal of Intelligent Systems 37.12 (2020): 10423-10441.

[2] Yang, Jianqiao. "Novel design concept for a commercial-scale plant for supercritical water oxidation of industrial and sewage sludge." Journal of environmental management 233.3 (2019): 131-140.

[3] Fu, Biao. "Co-combustion of industrial coal slurry and sewage sludge: Thermochemical and emission behavior of heavy metals." Chemosphere 233.10 (2019): 440-451.

[4] Bertocci, I. "Multiple human pressures in coastal habitats: variation of meiofaunal assemblages associated with sewage discharge in a post-industrial area." Science of the Total Environment 655.3 (2019): 1218-1231.

[5] Liu, Xin-Cong. "A path analysis for chemical oxygen demand and ammonia nitrogen discharge from industrial sewage in China." Water Resources 47.1 (2020): 1012-1019.

[6] Sarvari, Hadi. "Barriers to development of private sector investment in water and sewage industry." Built Environment Project and Asset Management 11.1 (2020): 52-70.

[7] Li, Xiang. "Dynamic early warning of rockburst using microseismic multi-parameters based on Bayesian network." Engineering Science and Technology, an International Journal 24.3 (2020): 715-727.

[8] Xie, Xiaoliang. "Bayesian network reasoning and machine learning with multiple data features: air pollution risk monitoring and early warning." Natural Hazards 107,1 (2020): 2555-2572.

[9] Aghaali, Mohammad. "Performance of Bayesian outbreak detection algorithm in the syndromic surveillance of influenza‐like illness in small region." Transboundary and Emerging Diseases 67.5 (2020): 2183-2189.

[10] Geng, Zhiqiang. "Risk early warning of food safety using novel long short-term memory neural network integrating sum product based analytic hierarchy process." British Food Journal 124.3 (2020): 898-914.

[11] Anbarasan, M. "Detection of flood disaster system based on IoT, big data and convolutional deep neural network." Computer Communications 150.1 (2020): 150-157.

[12] Yang, Beibei. "Time series analysis and long short-term memory neural network to predict landslide displacement." Landslides 16.1 (2019): 677-694.

[13] Panchal, Deepak. "SARS-CoV-2: sewage surveillance as an early warning system and challenges in developing countries." Environmental Science and Pollution Research 28 .4(2020): 22221-22240.

[14] Wepener, V., and G. C. O’Brien. "The application of Bayesian networks to evaluate risks from multiple stressors to water quality of freshwater ecosystems." African Journal of Aquatic Science 47.3 (2020): 231-244.

[15] Kadam, A. K. "Prediction of water quality index using artificial neural network and multiple linear regression modelling approach in Shivganga River basin, India." Modeling Earth Systems and Environment 5.3 (2019): 951-962.