Hostname: page-component-586b7cd67f-rcrh6 Total loading time: 0 Render date: 2024-11-25T12:38:41.993Z Has data issue: false hasContentIssue false

A neuro-fuzzy approach to the weight estimation of aircraft structural components

Published online by Cambridge University Press:  27 January 2016

C. Hannon*
Affiliation:
School of Mechanical Engineering, University of Leeds, Leeds, UK
V. V. Toropov*
Affiliation:
School of Civil Engineering, University of Leeds, Leeds, UK

Abstract

This paper explores the issues related to the application of fuzzy logic techniques to aid the process of weight estimation for aircraft structures at preliminary design stages. The focus lays on the design of a neuro-fuzzy system for the weight analysis, through the use of the Neuro-Fuzzy Function Approximator (NEFPROX) algorithm. The paper introduces a three-level process designed around Mamdani fuzzy systems derived through NEFPROX and analyses its application to the sizing and weight estimation of spoiler attachment ribs. Problems such as structure parameterisation, variable selection and model optimisation are explored as part of the process validation phase on the selected structural case study. The model performance is evaluated with respect to modelling accuracy, generalisation capabilities and the interdependencies between the variables the model is able to derive from the analysis of the given structural examples. The results are then compared to the performance obtained from the application of Takagi-Sugeno-Kang (TSK) fuzzy models derived using Adaptive Network-based Fuzzy Inference System (ANFIS) on the same sample of spoiler attachment ribs. Results highlight the benefits of adopting NEFPROX for the derivation of fuzzy systems to be applied in structural weight estimation problems, from the point of view of both accuracy of the approximation provided and the quality and interpretability of the final rulebase derived by the system.

Type
Research Article
Copyright
Copyright © Royal Aeronautical Society 2011 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

1. Bechdolt, R.W., et al, Aircraft Weight Engineering, ed. SAWE, 1996, Los Angeles, California, USA.Google Scholar
2. Mack, R.J. A Rapid Empirical Method for Estimating the Gross Takeoff Weight of a High Speed Civil Transport, 1999, NASA, TM-1999-209535.Google Scholar
3. Scott, P.W. and Nguyen, D. The Initial Weight Estimate, in 55th International Conference – Society of Allied Weight Engineers. 1996: Atlanta, Georgia, USA.Google Scholar
4. Rocha, H., Li, W. and Hahn, A. Principal component regression for fitting wing weight data of subsonic transport, J Aircr, 2006, 43, (6), pp 19251936.Google Scholar
5. Ardema, M.D., et al, Fuselage and wing weight of transport aircraft, SAE transactions, 1996. 105, (1), pp 15361552.Google Scholar
6. Udin, S.V. and Anderson, W.J. Wing mass formula for twin fuselage aircraft, J Aircr, 1992, 29, (5): pp 907914.Google Scholar
7. Scott, P.W. Developing Highly Accurate Empirical Weight Estimating Relationships: Obstacle and Tactics. in 51st International Conference of the Society of Weight Engineers. 1992. Hartford, Connecticut, USA: SAWE.Google Scholar
8. Shanley, F.R. Weight-Strength Analysis of Aircraft Structures. 2nd ed, Dover Publications. 1960, New York, USA, Dover Publications.Google Scholar
9. Hammitt, R.L. Structural Weight Estimation by the Weight Penalty Concept for Preliminary Design, in 15th Annual Conference – Society of Allied Weight Engineers. 1956, San Diego, California, USA.Google Scholar
10. Macci, S.H. Semi-Analytical Method for Predicting Wing Structural Mass, in 54th Annual Conference – Society of Allied Weight Engineers. 1995, Huntsville, Alabama, USA.Google Scholar
11. Caldell, W.E. On the Use of Aicraft Density in Preliminary Design, in 28th Annual Conference - Society of Allied Weight Engineers. 1969, Society of Allied Weight Engineers: San Francisco, California, USA.Google Scholar
12. St. John, R.S. The Derivation and Application of Analytical-Statistical Weight Prediction Techniques, in 28th Annual Conference – Society of Allied Weight Engineers. 1969, San Francisco, California, USA.Google Scholar
13. Droegkamp, K. Finite Element Model Weight Estimation, in 51st Annual Conference – Society of Allied Weight Engineers, 1992: Hartford, Connecticut, USA.Google Scholar
14. Hwang, H.Y., et al. Multidisciplinary aircraft design and evaluation software integrating CAD, Analysis, Database and Optimisation. Advances in Engineering Software, 2005, 37, pp 312326.Google Scholar
15. Flamand, J.M. IMPACT: Innovative Mass Properties Analysis CATIA Tool, in 60th International Annual Conference – Society of Allied Weight Engineers, 2001, Society of Allied Weight Engineers: Arlington, Texas, USA.Google Scholar
16. Nauck, D. and Kruse, R. Neuro-fuzzy systems for function approximation, Fuzzy Set Syst, 1999. 101, (2), pp 261271.Google Scholar
17. Mamdani, E.H. and Assilian, S. An experiment in linguistic synthesis with a fuzzy logic controller, Int J Man-Machine Studies, 1975. 7, (1), pp 113.Google Scholar
18. Jang, J. ANFIS: adaptive-network-based fuzzy inference system. Systems, Man and Cybernetics, IEEE Transactions on, 1993. 23, (3), pp 665685.Google Scholar
19. Hannon, C., et al, An Alternative View on Weight Estimation for the Aircraft Industry: Problems and MDO Solutions. 12th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, 2008.Google Scholar
20. Chawdry, P.K., Roy, R. and Pant, R.K. Soft Computing Engineering Design and Manufacturing, Springer, 1998, London, UK.Google Scholar
21. Fonseca, E.T., et al. A Neural Network System for Patch Load Prediction, J Intell Robotics Syst, 2001, 31, (1-3), pp 185200.Google Scholar
22. Zadeh, L. Fuzzy sets* information and control, 1965, 8, (3), pp 338353.Google Scholar
23. Kosko, B., Fuzzy systems as universal approximators, IEEE Trans. Comput, 1994, 43, (11), pp 13291333.Google Scholar
24. Jang, J.-S.R. and Sun, C.-T. Neuro-Fuzzy and Soft Computing: a Computational Approach to Learning and Machine Intelligence, 1997, Prentice-Hall, p 614.Google Scholar
25. Jassbi, J.J., et al. A Comparison of Mandani and Sugeno Inference Systems for a Space Fault Detection Application. in Automation Congress, 2006. WAC ’06. World. 2006.Google Scholar
26. Abraham, A. Neuro Fuzzy Systems: State-of-the-art Modeling Techniques, 2001.Google Scholar
27. Lotfi, A. The Importance of Learning in Fuzzy Systems. 2nd International Conference in Fuzzy Logic and Technology (EUSFLAT 2001), 2001, pp 439442.Google Scholar
28. Guney, K. and Sarikaya, N. Adaptive neuro-fuzzy inference system for computing the physical dimensions of electrically thin and thick rectangular microstrip antennas, Int J Infrared and Millimeter Waves, 2006, 27, (2), pp 219233.Google Scholar
29. Nauck, D. Neuro-fuzzy systems: review and prospects. 5. European Congress on Intelligent Techniques and Soft Computing (EUFIT’97).Google Scholar
30. Dawson, C. and Wilby, R. Hydrological modelling using artificial neural network, Prog Phys Geog, 2001, 25, (1), pp 80108.Google Scholar
31. Chiu, S. Selecting input variables for fuzzy models, J Intelligent and Fuzzy Systems, 1996, 4, (4), pp 243256.Google Scholar
32. Tung, W.L. and Quek, C. A mamdani-takagi-sugeno based linguistic neural-fuzzy inference system for improved interpretability-accuracy representation. in Fuzzy Systems, 2009. FUZZ-IEEE 2009. IEEE International Conference on. 2009.Google Scholar
33. Alonso, J.M., Magdalena, L. and González-Rodríguez, G. Looking for a good fuzzy system interpretability index: An experimental approach, Int J Approximate Reasoning, 2009, 51, (1), pp 115134.Google Scholar
34. Castellano, G., Fanelli, A.M. and Mencar, C. Design of transparent mamdani fuzzy inference systems, in Design and application of hybrid intelligent systems. 2003, IOS Press, pp 468476.Google Scholar