Applications of Artificial Intelligence in the Process Control of Electro Chemical Discharge Machining (ECDM)
T. K.K.R. Mediliyegedara (Glasgow Caledonian University, UK), A. K.M. De Silva (Glasgow Caledonian University, UK), D. K. Harrison (Glasgow Caledonian University, UK) and J. A. McGeough (The University of Edinburgh, UK)
Copyright: © 2007
This chapter presents the applications of Artificial Intelligence (AI) in the process control of Electro Chemical Discharge Machining (ECDM). The performance of the ECDM process depends on the pulse shape of the voltage and current waveforms. However, the type of the pulse and shape of the voltage and current waveforms are highly non linear and complex in nature. Therefore, the intelligent pulse classification systems are required for the achievement of better performance of the ECDM process. The aim of the study is to investigate the most suitable pulse classification architecture which provides the better classification accuracy with the minimum calculation time. A Neural Network Pulse Classification System (NNPCS), a Fuzzy Logic Pulse Classification System (FLPCS) and a Neuro Fuzzy Pulse Classification System (NFPCS) were developed for the pulse classification of the ECDM process. However, the NNPCS was selected as the most suitable pulse classification system for the ECDM process control system as it provides the smallest calculation time and reasonable classification accuracy.