Abstract
In Manufacturing Engineering there is a need to be able to model the behavior of technological variables versus input parameters in order to predict their behavior in advance, so that it is possible to determine the levels of variation that lead to optimal values of the response variables to be obtained. In recent years, it has been a common practice to rely on regression techniques to carry out the above-mentioned task. However, such models are sometimes not accurate enough to predict the behavior of these response variables, especially when they have significant non-linearities. In this present study a comparative analysis between the precision of different techniques based on conventional regression and soft computing is initially carried out. Specifically, regression techniques, based on the response surface model, as well as the use of artificial neural networks and fuzzy inference systems along with adaptive neuro-fuzzy inference systems will be employed to predict the behavior of the aforementioned technological variables. It will be shown that when there are difficulties in predicting the response parameters by using regression models, soft computing models are highly effective, being much more efficient than conventional regression models. In addition, a new method is proposed in this study that consists of using an iterative process to obtain a fuzzy inference system from a design of experiments and then using an adaptive neuro-fuzzy inference system for tuning the constants of the membership functions. As will be shown, with this method it is possible to obtain improved results in the validation metrics. The means of selecting the membership functions to develop this model from the design of experiments is discussed in this present study in order to obtain an initial solution, which will be then tuned by using an adaptive neuro-fuzzy inference system, to predict the behavior of the response variables. Moreover, the obtained results will also be compared.
Highlights
Over the last few years, an increasing number of research studies dealing with modeling of technological response variables as a function of process parameters in order to determine the most appropriate operating conditions has been observed in Manufacturing Engineering
Due to the variability of the data, the wear that the electrode (EW) undergoes in this electrical discharge machining (EDM) process cannot be adequately modeled by using response surface methodology (RSM), and for this reason, in order to adequately model this technological variable, it would be necessary to employ some other technique, for example based on using an Adaptive Neuro-Fuzzy Inference System (ANFIS) or an Artificial Neural Networks (ANN)
As can be seen from the results shown in Ref. [61], in which only RSM-based polynomial regression is used, the R-squared value is greater than 90% in the case of average roughness (Ra), but this coefficient is much lower in the case of electrode wear (EW) and, Ra could be modeled by using RSM, this is not the case for the EW
Summary
Over the last few years, an increasing number of research studies dealing with modeling of technological response variables as a function of process parameters in order to determine the most appropriate operating conditions has been observed in Manufacturing Engineering. Given the importance that these manufacturing processes have for industry, a large number of models have been developed in recent years, based on regression techniques, fuzzy inference systems, and artificial neural networks, generally through the application of supervised learning and feed forward networks In this present research study, different techniques, based both on response surface methodology (RSM) and on soft computing, will be analyzed to determine their capacity to accurately predict the response variables. When regression models are not adequate to predict the behavior of the response variables, it is necessary to use other alternative methodologies and, as shown further on, soft computing has significant advantages over conventional regression methods In this present study, a comparative study is first carried out between the accuracy in regression models, based on RSM, versus that of soft computing techniques such as Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS). Before approaching the present study, several research works that were found in the bibliography will be analyzed in the “State of the Art” section
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
