Introducing Artificial Neural Networks as a Specific Enthalpy approximator for a course on introductory Thermodynamics
Document Type
Conference Proceeding
Publication Date
12-4-2020
Department
Department of Mechanical Engineering-Engineering Mechanics
Abstract
In this innovative practice, work-in-progress paper, an example is provided through which mechanical engineering students can be instructed the heuristic creation of feedforward artificial neural networks (ANN), their training, validation and quantification of their accuracy, in the context of a thermodynamics course.As big data and machine learning continue to permeate and affect the viscera of society, new challenges and career opportunities emerge. Organizations such as NSF, McKinsey global institute, Gartner global newsroom, IBM, to name a few, have published projections on the global impact big data and machine learning on the job market and how these technologies are the next frontier in innovation.The example demonstrated here, may be introduced as a module in a traditional thermodynamics course. Using a validated ANN, the thermodynamic property of specific enthalpy of steam is evaluated, when given a thermodynamic state specification of temperature and pressure. The data used to train the neural network is generated using the equations of state provided in the IAPWS IF-97 industrial standard for water and steam. The effect of number and type of layers on the accuracy of the network and the effect of data pre-processing, on the accuracy of the network can be studied.
Publication Title
Proceedings - Frontiers in Education Conference, FIE
ISBN
9781728189611
Recommended Citation
Narendranath, A.
(2020).
Introducing Artificial Neural Networks as a Specific Enthalpy approximator for a course on introductory Thermodynamics.
Proceedings - Frontiers in Education Conference, FIE,
2020-October.
http://doi.org/10.1109/FIE44824.2020.9274222
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/14557
Publisher's Statement
© 2020 IEEE. Publisher’s version of record: https://doi.org/10.1109/FIE44824.2020.9274222