Abstract
This study aims to replicate the operations performed by an experienced operator of a water supply system. Steering groups of water supply systems face problems because of the decreasing number of experienced operators. Without the skill of experienced operators, it is difficult to carry out safe and stable operations. Regression analysis was adapted in this study to replicate the operations performed by an experienced operator. To resolve the nonlinear regression problems of knowledge acquisition and decreasing number of experienced operators, a support vector machine (SVM) was used. For knowledge acquisition from sensor data, data mining and principal component analysis (PCA) were used. Experimental results showed that when the proposed method was used, the average of the root mean square values of the water level improved by 29.8% as compared to that obtained by the conventional method. Thus, we confirmed that the proposed method can acquire operation knowledge from experienced operators and use it to prepare an operation plan. This method is expected to compensate for the decrease in the number of experienced operators.
