An AI based control system and method for treating sewage/waste water by means of a neural network and a back-propagation algorithm

摘要

An AI (artificial intelligence) control system for controlling automatically variable factors, such as DO (dissolved oxygen), SRT (solids retention time) and the like depending upon properties of the inflow water, the internal condition of the reaction tank and the target treated water quality, particularly the AI control system wherein a retention time is applied in consideration of each volume of the reaction tank and the sedimentation tank, and thereby, each SP (set point), such as each DO and SRT of the 1st story and the 2nd story of the exhalation tank, is obtained from the data collected by measuring automatically BOD (biological oxygen demand), an incoming stream flow and a water temperature, control automatically a control valve for controlling the supply air and a pump for drawing sludge by means of each PV (present value), and then a learning method, an algorithm for controlling the surplus sludge and the like are used by letting AI (corresponding to the neural network controller) learn through the use of the knowledge-base, setting a concentration of DO in response to any change in a temperature and a concentration and calculating an appropriate SRT.