Faculty Publications

Now showing 1 - 3 of 3

Modelling of squeeze casting process using design of experiments and response surface methodology
(Maney Publishing maney@maney.co.uk, 2015) Gowdru Chandrashekarappa, M.; Krishna, P.; Parappagoudar, M.B.
The present work makes an attempt to model and analyse squeeze casting process by utilising design of experiments and response surface methodology. The input–output data for developing regression models and test cases is obtained by conducting the experiments. Surface roughness, ultimate tensile strength and yield strength have been measured for different combinations of process variables, namely, squeeze pressure, pressure duration, pouring temperature and die temperature. Two non-linear regression models based on central composite design (CCD) and Box-Behnken design (BBD) of experiments have been developed to establish the input–output relationships. The effects of process variables on the measured responses have been studied using surface plots. The performances of the two non-linear models have been tested for their prediction accuracy with the help of 15 test cases. It is observed that, both CCD and BBD, the non-linear regression models are statistically adequate and capable of making accurate predictions. © 2015 W. S. Maney & Son Ltd.
Squeeze casting process modeling by a conventional statistical regression analysis approach
(Elsevier Inc. usjcs@elsevier.com, 2016) Gowdru Chandrashekarappa, G.C.; Krishna, P.; Parappagoudar, M.B.
During the casting process, the alloy composition, melt treatment modification, processing method, and process variables change the microstructure, thereby affecting the mechanical properties. The hybrid squeeze casting method has been used to limit casting defects, refine the micro-structure, and enhance the mechanical properties. The process variables influence the mechanical and micro-structure properties during squeeze casting. In the present study, we established nonlinear input–output relationships and explored the physical behavior of this process based on the statistical design of experiments and using the response surface methodology. Experiments were conducted to measure the responses in terms of the density, hardness, and secondary dendrite arm spacing. Two nonlinear regression models, i.e., Box–Behnken design and central composite design, were used to conduct experiments, collect experimental data, identify significant process variables, analyze the collected data, and establish the complex input–output relationships. Surface plots were used to explore the effects of the squeeze pressure, pressure duration, pouring, and die temperature on the measured responses. Analysis of variance tests were conducted to evaluate the statistical suitability of the models developed. Furthermore, the accuracies of the predictions made by the models were investigated based on test cases. We found that both of the nonlinear models were statistically adequate and they provided complete insights into the complex nonlinear input–output relationships. Central composite design performed better for the secondary dendrite arm spacing and hardness responses, whereas its performance was the same as that of Box–Behnken design for the density response. The relationships between the responses (i.e., outputs) were established by generating large volumes of input–output data using the nonlinear regression models. We found that the density, hardness, and secondary dendrite arm spacing responses could be obtained by utilizing the nonlinear regression equations and the same set of process variables. Furthermore, the secondary dendrite arm spacing response could be expressed as third order nonlinear functions of density or hardness (structure to property relationship). The results showed that the secondary dendrite arm spacing had inverse relationships with density and hardness, whereas density and hardness had direct relationships. © 2016 Elsevier Ltd
Artificial bee colony, genetic, back propagation and recurrent neural networks for developing intelligent system of turning process
(Springer Nature, 2020) Shettigar, A.K.; Gowdru Chandrashekarappa, G.C.M.; Ganesh, G.R.; Vundavilli, P.R.; Parappagoudar, M.B.
Intelligent manufacturing requires significant technological interventions to interface manufacturing processes with computational tools in order to dynamically mold the systems. In this era of the 4th industrial revolution, Artificial neural network (ANNs) is a modern tool equipped with a better learning capability (based on the past experience or history data) and assists in intelligent manufacturing. This research paper reports on ANNs based intelligent modelling of a turning process. The central composite design is used as a data-driven modelling tool and huge input–output is generated to train the neural networks. ANNs are trained with the data collected from the physics-based models by using back-propagation algorithm (BP), genetic algorithm (GA), artificial bee colony (ABC), and BP algorithm trained with self-feedback loop. The ANNs are trained and developed as both forward and reverse mapping models. Forward modelling aims at predicting a set of machining quality characteristics (i.e. surface roughness, cylindricity error, circularity error, and material removal rate) for the known combinations of cutting parameters (i.e. cutting speed, feed rate, depth of cut, and nose radius). Reverse modelling aims at predicting the cutting parameters for the desired machining quality characteristics. The parametric study has been conducted for all the developed neural networks (BPNN, GA-NN, RNN, ABC-NN) to optimize neural network parameters. The performance of neural network models has been tested with the help of ten test cases. The network predicted results are found in-line with the experimental values for both forward and reverse models. The neural network models namely, RNN and ABC-NN have shown better performance in forward and reverse modelling. The forward modelling results could help any novice user for off-line monitoring, that could predict the output without conducting the actual experiments. Reverse modelling prediction would help to dynamically adjust the cutting parameters in CNC machine to obtain the desired machining quality characteristics. © 2020, Springer Nature Switzerland AG.

Faculty Publications

Browse

Filters

Settings

Sort By

Results per page

Search Results