Article Details

Abstract

In recent years, with the gradual expansion of the scope of AI applications, various industries are connected with Artificial Intelligence more or less. Traditional water quality monitoring methods include manual sampling and laboratory analysis, on-site testing, and remote sensing technology, which exist poor timeliness, limited coverage, discontinuous data, and high costs and other problems. The advent of neural networks has significantly enhanced the effect of traditional technologies in prediction and data processing. Based on this, the BP neural network is optimized using Particle Swarm Optimization. The results show that the optimized model achieves higher accuracy and smaller error. This not only further improves the accuracy and timeliness of water quality monitoring but also significantly reduces monitoring costs, saving manpower, material resources, and financial resources. It provides a new technical means for water quality monitoring.

Keywords

Artificial Intelligence; water quality monitoring; Particle Swarm Optimization; BP neural network

References

1. [1] Ren Haijing, Ma Yiyi The Development Status and Prospects of Smart Water Management in China [J]. Construction Technology, 2021 (6): 60-63+67
2. [2] Liu Dongjun, Zou Zhihong Application of Optimal Weighted Combination Prediction Method in Water Quality Prediction [J]. Journal of Environmental Science, 2012, 32 (12): 3128-3132
3. [3] Wang Lixue, Ma Hui, Yang Xu, et al. Non flood season water quality prediction of Dahuofang Reservoir using BP neural network based on MATLAB [J]. Journal of Shenyang Agricultural University, 2014, 45 (3): 363-367
4. [4] Sun Yibing A Brief Discussion on the Advantages, Disadvantages and Improvements of BP Network [J]. Science and Technology Innovation Guide, 2009 (24): 18
5. [5] Ju Zhenchuang, Wang Xiao, Gong Yanxia Research on Yellow River Water Quality Prediction Based on BP Neural Network [J]. Journal of Qinghai University, 2017, 35 (3): 88-92+102
6. [6] Gu Jie, Wang Jia, Deng Junhui, etc Water quality prediction based on ARIMA model and BP neural network algorithm [J]. Water Purification Technology, 2020, 39 (6): 73-82
7. [7] Chen Jian, Huang Lihua, Qu Jiting Prediction of Bond Strength between FRP Reinforcement and Concrete Interface Based on BP Neural Network [J]. Journal of Dalian University of Technology, 2021, 61 (3): 272-279
8. [8] Zhang Pingliang, Wang Bi Particle Swarm Optimization Algorithm for Dynamic Search Space [J]. Computer Application Research, 2016, 33 (7): 2047-2050+2067
9. [9] Tie Jincheng, Zhao Zhanying Application research on model hyperparameter optimization method based on particle swarm optimization algorithm [J]. Computer Applications and Software, 2023, 40 (10): 150-155
10. [10] GOODFELLOW I，BENGIO Y，COURVILLE A. Deep Learning [M].[S.I.].MIT press，2016.
11. [11] XU L，SONG B Y，CAO M Y. An Improved Particle Swarm Optimization Algorithm with Adaptive Weighted Delay Velocity [J].Systems Science & Control Engineering，2021，9（1）：188-197.
12. [12] Zhao Zhenjiang Network Traffic Prediction and Research Based on PSO-BP Neural Network [J]. Computer Applications and Software, 2009, 26 (1): 218-221

About the authors

Yan Jia (July 2000-), female, Han ethnicity, from Xi'an, Shaanxi Province, is currently pursuing a master's degree in deep learning.