Evaluation of ANN and ANFIS modeling ability in the prediction of AISI 1050 steel machining performance

Abstract

In the development of an accurate modeling technique for the design of an efficient machining process, manufacturers must be able to identify the most suitable technique capable of producing a fast and accurate performance. This study evaluates the performance of the Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) models in predicting the machining responses (metal removal rate and tool wear) in an AIS steel turning operation. With data generated from carefully designed machining experimentation, the adequacies of the ANN and ANFIS techniques in modeling and predicting the responses were carefully analyzed and compared. Both techniques displayed excellent abilities in predicting the responses of the machining process. However, a comparison of both techniques indicates that ANN is relatively superior to the ANFIS techniques, considering the accuracy of its results in terms of the prediction errors obtained for the ANN and ANFIS of 6.1% and 11.5% for the MRR and 4.1% and 7.2% for the Tool wear respectively. The coefficient of correlation (R 2 ) obtained from the analysis further confirms the preference of the ANN with a maximum value of 92.1% recorded using the ANN compared to that of the ANFIS of 73%. The experiment further reveals that the performance of the ANN technique can yield the most ideal results when the right parameters are employed.

Optimization of Distribution Control System in Oil Refinery by Applying Hybrid Machine Learning Techniques

“…Further, an adaptive neuro-fuzzy inference system (ANFIS) modelling based soft sensor was used in the prediction of steel machine responses (metal removal rate and tool wear) and the performance was compared with ANN. The result shows that the prediction accuracy is higher for ANFIS compared to ANN technique [17]. In food drying processes industry, the ANN and ANFIS model were used to predict the moisture ratio (MR), energy utilization (EU), energy utilization ratio (EUR), exergy loss and exergy efficiency of onion slices drying process by Multi-Stage Semi-Industrial Continuous Belt.…”

Predicting the Ultimate Axial Capacity of Uniaxially Loaded CFST Columns Using Multiphysics Artificial Intelligence

“…Artificial Neural Networks (ANNs) are computer algorithms that anticipate and classify the issues concerned with the effective processing of data [ 42 ]. As its name indicates, ANNs are based on mathematical models based on the human brain’s neuron system [ 43 ]. ANN’s have various layers of processing elements or nodes.…”

“…ANFIS has a better prediction potential and is a better alternative for computing nonlinear complex problems with greater precision [ 58 ]. With similar learning capability as ANN, ANFIS learns from training data containing a multiplex model and then gives the solutions in a fuzzy interface system (FIS) [ 43 ]. In MATLAB R2020b there is a tool called ANFIS that can train the input and output entities for the best connection between both the parameters.…”

Dynamic Optimal ANFIS Parameters Tuning with Particle Swarm Optimization

“…Fuzzy logic is a powerful and easy to design method that is created by applying expert knowledge about inference rules without requiring model knowledge (Guillaume 2001). The fuzzy inference system mainly consists of three conceptual components: the rule base, which consists of the sum of fuzzy rules, the database, which is used to define the degrees of membership, and the inference mechanism, which is used to collect rules from the inputs and outputs of the system and produce corresponding results (Hodzic 2016) (Sada and Ikpeseni 2021). The superiority of artificial neural networks over demand forecasting methods was first demonstrated in (Zhang, Eddy Patuwo, and Y. Hu 1998).…”

“…The approach of classification by assigning degrees of membership to objects that do not belong was first proposed by Zadeh (Zadeh 1994). Adaptive Network-based Fuzzy Inference System (ANFIS) classification is an artificial neural network based method, which is particularly used to solve pattern recognition problems that require rule-based process control (Sada and Ikpeseni 2021). These approaches are obtained after training fuzzy inference rules with artificial neural networks, which even experts in the field have difficulty in drawing conclusions (Kundapura and Hegde 2021;Yaseen et al 2019).…”