Open AccessRemote Maintenance System of Industrial Ultra-Pure Water Based on Deep Learning
Author(s) -
Sheng Xu,
Lei Wang,
Xiang He
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/632/3/032025
Subject(s) - artificial neural network , electronics , computer science , convergence (economics) , electricity , energy consumption , process engineering , water quality , radial basis function , production (economics) , energy (signal processing) , automotive engineering , real time computing , engineering , artificial intelligence , electrical engineering , ecology , statistics , mathematics , macroeconomics , economics , biology , economic growth
In order to meet the requirements of controlling the water quality of electric power, electronics and other manufacturing industries and reducing energy consumption through remote operation and maintenance system, an intelligent remote operation and maintenance system of ultra-pure water is constructed for ultra-pure water manufacturing in electronic industry. radial basis function neural network and generalized regression neural network are used to fit and predict the effluent quality of ultra-pure water. Through data analysis, the above algorithm is used to realize the accurate prediction of ultra-pure water system and intelligent adaptive control, which improves the accuracy and convergence speed of the algorithm. The results show that on the basis of the simulation of the model, the purpose of improving water production quality, saving energy and reducing consumption can be achieved through backwater utilization and frequency conversion speed regulation.