This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Designing of Automotive Vacuum Pumps - Development of Mathematical Model for Critical Parameters and Optimization using Artificial Neural Networks
Technical Paper
2012-01-0779
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
In this ever-changing field of automotive industry where there is high competition to seek a place in market, it is necessary to design and develop products with a minimum lead time meeting the target specifications. This is normally achieved through product variants specific to customer requirements from the repository of design base created. Design bases are created based on the previous products and by bench marking. Vacuum Pump is an engine driven part identified for this study. The main aim of this study is to create a mathematical model, and use Artificial Neural Networking (ANN) to arrive at a design base. In the process of building the mathematical model, two key design parameters namely profile and performance were identified and model was constructed. Using this mathematical model, proto samples were prepared for a range of vacuum pump capacities and were tested. These test results were used for training the ANN to create the design base for any future design. The NN predicted values had a good correlation with the actual values of tested proto samples. Thus, the design was optimized for greater accuracy, which will serve as a design base for future applications.
Recommended Content
Authors
Topic
Citation
S R, N., Subramanian, A., Suresh kumar, J., and Sivanantham, R., "Designing of Automotive Vacuum Pumps - Development of Mathematical Model for Critical Parameters and Optimization using Artificial Neural Networks," SAE Technical Paper 2012-01-0779, 2012, https://doi.org/10.4271/2012-01-0779.Also In
References
- Hornik, K. “Approximation capabilities of multilayer feedforward networks,” Neural Networks 4 2 251 257 1991
- MacKay, D. J. C. “A practical Bayesian framework for backpropagation networks,” Neural Computation 4 3 448 472 1992
- Chambers, A. Fitch, R. K. Halliday, B. S. “Basic Vacuum Technology,” 0-75-030495-2 1998
- Nagendiran, S. Sivanantham, R. Kumar, J. “Improvement of the Performance of Cam-Operated Vacuum Pump for Multi Jet Diesel Engine,” SAE Technical Paper 2009-01-1462 2009 10.4271/2009-01-1462
- Bishop, Ch. M. “Neural Networks for Pattern Recognition.” Clarendon Press Oxford 1995
- Abraham, A. 2004 Meta-Learning Evolutionary Artificial Neural Networks Neuro computing Journal 56c Elsevier Science Netherlands 1-38
- Patterson, D.W. 1995 Artificial Neural Networks - Theory and Applications Prentice Hall
- Nagendiran, S. Sureshkumar, J. Sivanantham, R. Pandarinath, H., "Performance Optimization of Vacuum Pump for a Diesel Engine for Euro V Application by Experiments," SAE Technical Paper 2011-01-0071 2011 10.4271/2011-01-0071