Cargando…
Intelligent Measurement and Analysis of Sewage Treatment Parameters based on Fuzzy Neural Algorithm with ARM9 Core CPU
After entering the new century, the state continues to increase the construction of urban sewage treatment projects in response to the deteriorating water pollution situation. How to collect and analyze the sewage parameter variables in the sewage treatment process to ensure the intelligent measurem...
Autor principal: | |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9313929/ https://www.ncbi.nlm.nih.gov/pubmed/35898788 http://dx.doi.org/10.1155/2022/3498060 |
Sumario: | After entering the new century, the state continues to increase the construction of urban sewage treatment projects in response to the deteriorating water pollution situation. How to collect and analyze the sewage parameter variables in the sewage treatment process to ensure the intelligent measurement and accurate operation of the parameters in the treatment application is an urgent problem to be solved. This paper is mainly based on the computer-aided control system built by the ARM9 core embedded chip, and the feasibility and effectiveness of fuzzy neural network algorithms are discussed to improve the intelligent processing of sewage treatment parameters. After analyzing the principle and implementation flow of fuzzy control and neural network, starting from the characteristics of data collected by ARM9 core chip, the hybrid algorithm model is optimized and improved to further improve the convergence speed and accuracy of the algorithm. The simulation experiment proves that the optimized fuzzy neural control algorithm can effectively identify the dissolved oxygen, nitrate nitrogen, and other parameter data in the sewage treatment, and the recognition accuracy is very close to the true precision. Based on biosensors, the ARM9 core chip control system established by a recursive fuzzy neural network can greatly improve the tracking and control ability of parameters such as dissolved oxygen concentration and nitrate nitrogen concentration in microbial degradation. This has a good development prospect in wastewater treatment control applications. The experimental results show that the recursive fuzzy neural network algorithm proposed in this paper can dynamically track and control the nitrate concentration and dissolved oxygen concentration and ensure that the control is within the accuracy range. The accuracy of recognition is very close to the real accuracy. |
---|