Computational & Technology Resources
an online resource for computational,
engineering & technology publications
Civil-Comp Proceedings
ISSN 1759-3433
CCP: 84
Edited by: B.H.V. Topping, G. Montero and R. Montenegro
Paper 48

Failure Modelling in Pin-Loaded Joints Using an Adaptive Neuro-Fuzzy Approach

S. Shirazi Kia, S. Noroozi, B. Carse, J. Vinney and M. Rabbani

Faculty of Computing, Engineering and Mathematical Science, University of the West of England, Bristol, United Kingdom

Full Bibliographic Reference for this paper
S. Shirazi Kia, S. Noroozi, B. Carse, J. Vinney, M. Rabbani, "Failure Modelling in Pin-Loaded Joints Using an Adaptive Neuro-Fuzzy Approach", in B.H.V. Topping, G. Montero, R. Montenegro, (Editors), "Proceedings of the Fifth International Conference on Engineering Computational Technology", Civil-Comp Press, Stirlingshire, UK, Paper 48, 2006. doi:10.4203/ccp.84.48
Keywords: pin joint, ANFIS, C4.5, composite, classification, non-linear behaviour, tensile load.

Accurate prediction of failure in pin-loaded joints is crucial to optimising the design of a structure. The aim of this study is to investigate the performance of an adaptive network-based fuzzy inference system (ANFIS) [1] for failure prediction in composite and aluminium joints. The presented ANFIS models combine the neural network adaptive capabilities and the fuzzy logic qualitative approach. In addition, we compare the performance of ANFIS with C4.5, a well-known classification algorithm [2].

To construct the models, the study used data sets obtained from experimental tests on pin-loaded composite as well as aluminium joints. A laminate composite (carbon fibre reinforced plastic) plate of length L, thickness t and width W with a hole of diameter D with a pin is used. In the tensile test, different edge distance/diameter (E/D) ratios were considered. The object is to find to find: (a) the load-displacement tensile response for each specimen (b) the ultimate failure load.

The system is a four input-one output system. The input variables are material type, edge distance, load step and load value and the joint behaviour at that specific step is taken as the output variables. In order to take the material properties into account, two models have been generated, one for each material type. In both cases, four different E/D ratios have been applied for training the systems while they were tested with a new E/D ratio. For each edge distance/diameter ratio, three sets of data have been applied. The total classification error showed that the proposed ANFIS model could be used in predicting failure load by taking into consideration the misclassification rates.

Our analysis indicates that ANFIS can be trained to model tensile failure regarding the composite joints. However, it could only outperform the classical methods for aluminium joints. The reason is due to the fact that there are three possible behaviours for aluminium joints (elastic, plastic and failure behaviour) while for composite there are only non-failure and failure levels.

Based on the analysis of membership functions, it should be mentioned that both E/D ratio and load values have considerable impact on the prediction of behaviour of pin-loaded joints. The procedures developed in this work could be used in design with little further modification.

J.S.R. Jang, "ANFIS: adaptive-network-based fuzzy inference system", IEEE Trans Syst, Man, Cybernet 23 (3); pp 665-85, 1993. doi:10.1109/21.256541
J.R. Quinlan, C4.5: Programs for Machine Learning. Morgan Kaufman Publishers, San Mateo, California, 1993.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description