Operational knowledge acquisition for water supply support system using PLS regression

This paper aims to replicate the operation of an experienced operator for a water supply system. The steering groups of water supply systems face problems due to the decreasing number of experienced operators. Without the skill of experienced operators, it is difficult to carry out safe and stable operation. For this purpose, regression analysis was adapted to replicate the operation of an experienced operator. To resolve the regression problem of knowledge acquisition and decreasing number of experienced operators, partial least squares was used. By using the proposed method, operation in accordance with the state of the water distributions is possible. From the evaluation by using objective functions, it turned out that the operation of the proposed method reflects the policy of the target operation. In addition, experimental results show that the root mean square (RMS) of water level and water conveyances of the proposed method was smaller than RMS of the conventional method. From these results, the proposed method can acquire and regenerate the operation knowledge of an experienced operator.