Feasibility of applying neural network in the mechanical designing

Jialin Wang

doi:10.1117/12.2621173

29 November 2021 Feasibility of applying neural network in the mechanical designing

Jialin Wang

Proceedings Volume 12080, 4th International Symposium on Power Electronics and Control Engineering (ISPECE 2021); 1208048 (2021) https://doi.org/10.1117/12.2621173
Event: 4th International Symposium on Power Electronics and Control Engineering (ISPECE 2021), 2021, Nanchang, China

Abstract

Parameter-calculation is an important part of the machine design process and this stage usually takes a lot of time. The workload of parameter-calculation is always proportional to the complexity and fineness of the design. As the demand for variety machines keeps increasing these years, a better method is necessary to increase the efficiency and quality of calculations during design a new machine. In this paper, neural network is thought of the solution. By learning from the researches in neural network and finite element analysis which is broadly used in the area of engineering presently. The neural network is found to have a better performance in efficiency, accuracy and cost performance and the results indicate neural network could be a better alternative of the finite element analysis.

Citation Download Citation

Jialin Wang "Feasibility of applying neural network in the mechanical designing", Proc. SPIE 12080, 4th International Symposium on Power Electronics and Control Engineering (ISPECE 2021), 1208048 (29 November 2021); https://doi.org/10.1117/12.2621173

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available