A Hybrid Data Analytic Approach to Evaluate the Performance of Stirling Engine using Machine Learning Techniques

The revolution of Industry 4.0 involves the smart way of incorporating manufacturing with digitized technology and machine learning in a holistic approach. Assessing and evaluating industrial applications needs analytic methods and machine learning techniques to have a good way of predicting. This research involves the evaluation of the performance of the Stirling engine using a hybrid approach upon statistical evaluation. The methodology incorporates swarm intelligence along with a generalized linear model upon analytic evaluation. Experimental results show that the evaluation of the hybrid machine learning model provides improved accuracy of about 89.67% with a P-value <0.001 respectively. With the proposed method the most significant feature corresponds to the ambient temperature, if this is maintained efficiently then the performance analysis of the stir-ling engine can be varied in accordance to the usage of the industrial applications. Thus it provides an efficient platform for data analysis and modeling for measuring the effect caused by the Stirling engine. This provides the ecosystem with an efficient temperature handling mechanism for variants among Stirling engines.