earticle

영어

In this paper, the Self-Organizing Feature Maps (SOFM) neural network is applied to analyse the multi dimensional process data, and to diagnose the inter-relationship of the process variables in a real municipal sewage treatment plant. The data set had been collected from a sewer system in the Gwangyang city, Korea. The data had been measured in the period of 1st January, 2004 and 31th December, 2006. The data set contains daily averaged values for each of the twenty
three variables. Through the component planes visualization, it is evident that the effluent is related to rainfall, flow rate, temperature, MLSS, SRT, RAS and DO. Especially, rainfall, flow rate and temperature are the most important driving force to increase in effluent levels in the Gwangyang municipal sewage treatment plant. It is concluded that the SOFM technique provides an effective analyzing and diagnosing tool to understand the system behavior and to extract knowledge contained in multi-dimensional data of a large-scale sewage treatment plant.