Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item Application of fractional factorial design for evaluating the separation performance of the screening machine(Taylor and Francis Ltd., 2022) Shanmugam, B.K.; Vardhan, H.; Raj, M.G.; Kaza, M.; Sah, R.; Hanumanthappa, H.Implementing the planned execution of experiments will optimize the resources and time of a newly developed process or equipment. In the present work, the screening machine is newly developed equipment designed for the separation of coal. The present work was carried out to evaluate the performance of separation efficiency of the screening machine using generalized and forward selection fractional factorial experimental design. Further, the present work will also determine the significance of each operational variable, such as moisture content, angle, and frequency, for increasing separation efficiency. A cube plot was developed from the experimental design, which shows the highest and lowest condition of separation efficiency for each level of the operational variables. Further, a Pareto chart was developed to evaluate the significant operational variable for the screening machine. The results of the generalized method and forward selection method of fractional design show that the moisture content was the most significant operational variable, followed by angle and frequency. The results also show that the screen blinding of a screening machine plays an important role in reducing the separation efficiency of a screening machine. © 2021 Taylor & Francis Group, LLC.Item Comparison of the predictive model performance of Taguchi’s L27 and Box Behnken design optimization method for separating coal in vibrating screen(Taylor and Francis Ltd., 2023) Shanmugam, B.K.; Vardhan, H.; Raj, M.G.; Kaza, M.; Sah, R.; Hanumanthappa, H.The present research work evaluates the influential process parameters such as moisture content, angle, and frequency for separating coal in the vibrating screen. The design of the experiment for three factors with three levels was obtained using Taguchi’s and Response surface methodology’s (RSM) method. Taguchi’s L27 and RSM Box–Behnken design (BBD) method was used to conduct the separation experiment on a vibrating screen. The main effect plot of Taguchi’s L27 and BBD method was used to evaluate the optimized condition for obtaining the highest separation efficiency of the vibrating screen. The optimized condition obtained was lower moisture content (4%), lower angle (1 degree in upward slope), and medium frequency (9 Hz). The interaction plot of Taguchi’s L27 and BBD method was used to evaluate the interaction between the process parameters. From the interaction plot and ANOVA results, it was clear that the moisture content is the most significant parameter compared with the angle and frequency parameter for separating coal in a vibrating screen. From the prediction results, it was also clear the regression coefficient of Taguchi’s L27 was higher when compared with the RSM BBD method. This shows that Taguchi’s L27 is the most suitable optimization method compared with RSM. © 2022 Taylor & Francis Group, LLC.Item Comparison of the prediction performance of separating coal in separation equipment using machine learning based cubic regression modelling and cascade neural network modelling(Taylor and Francis Ltd., 2023) Shanmugam, B.K.; Vardhan, H.; Raj, M.G.; Kaza, M.; Sah, R.; Hanumanthappa, H.The availability of low-grade coal with a high amount of ash has urged the improvisation of separation equipment with minimal or no water utilization. The present work addresses the study on the separation equipment performance with different moisture coal. The experimental results were obtained in terms of separation efficiency. After obtaining the experimental results, the mathematical modeling results were obtained using different techniques. The cubic regression and cascade neural network models were considered to study the mathematical correlation with experimental results. The R-squared value of each mathematical modeling technique was correlated with the model fitting to check the model’s validity. The results clearly showed that the cubic model fitting for the experimental condition had provided an excellent R-squared value varying from 92% to 99%. The cascade model fitting for the experimental condition has provided a higher R-squared value, i.e., more than 99%. Results show that for all experimental conditions, the cascade model fitting of the neural network technique provides the significant mathematical modeling technique suitable for predicting the separation equipment’s performance compared to the cubic model of the regression technique. © 2022 Taylor & Francis Group, LLC.