Skip to Main content Skip to Navigation
Journal articles

Connectionist intelligent model estimates output power and torque of stirling engine

Abstract : Stirling engine is an Environmental friendly heat engine which can reduce \CO2\ emission through combustion process. Various criteria should be considered for designing and optimizing stirling heat engines such as power, torque, and pressure loss in heat exchangers of stirling engine, efficiency and so forth. In the aforementioned criteria, output power and shaft torque are the most important criteria which represent the performance and efficiency of the stirling engines. So, determination of output power and shaft torque with low uncertainty and high precision are required. In this paper, a new generation of intelligent models named “least square support vector machine (LSSVM)” is employed to predict output power and shaft torque of stirling engines. To build, train and test the \LSSVM\ model, various accurate experimental data from open literature are employed. The outputs of the \LSSVM\ model are compared to experimental ones and statistical parameters of the \LSSVM\ model including correlation coefficient, average absolute relative deviation (AARD) and root mean square error (RMSE) are calculated. According to the results obtained via \LSSVM\ model, the \LSSVM\ model can predict output power and shaft torque of Stirling heat engine with reasonable and acceptable accuracy. Finally, the \LSSVM\ model can help us in designing of Stirling engine with low degree of uncertainty and high precision.
Keywords : Modeling
Document type :
Journal articles
Complete list of metadata

https://hal.univ-lorraine.fr/hal-01417581
Contributor : Lemta Ul <>
Submitted on : Thursday, December 15, 2016 - 5:06:52 PM
Last modification on : Monday, March 29, 2021 - 4:02:54 PM

Identifiers

Collections

Citation

Mohammad H. Ahmadi, Mohammad Ali Ahmadi, Seyed Abbas Sadatsakkak, Michel Feidt. Connectionist intelligent model estimates output power and torque of stirling engine. Renewable and Sustainable Energy Reviews, Elsevier, 2015, 50, pp.871 - 883. ⟨10.1016/j.rser.2015.04.185⟩. ⟨hal-01417581⟩

Share

Metrics

Record views

162