A comparison of performance of artificial intelligence methods in prediction of dry sliding wear behavior

Developing a computational model for studying tribological performance is essential for computing accurate life cycle of various materials. Caused by the existence of complicated and nonlinear interactions between material surfaces, exact modeling of wear behavior is very difficult. Artificial intelligence (AI) can be used in distinguishing similar patterns in experimental data and predictive modeling of a certain material's wear behavior. In this paper, artificial neural networks (ANNs) approach, adaptive neural-based fuzzy inference system (ANFIS) technique, and fuzzy clustering method (FCM) are used to develop a simple, accurate, and applicable model for predicting the wear behavior of sinter-hardened steel parts. Three different cooling rates (0.5, 2, and 3 A degrees C/s) were applied on six specimens made out of pre-alloyed Astaloy 85 Mo and Distaloy AB powders by powder metallurgy (PM) method. Reciprocating dry sliding wear tests were carried out on these specimens with three different loads. The empirical results were assorted in two different batches. One was used along with the mentioned artificial intelligence approaches to develop three wear behavior models. In order to verify and compare these models, predicted results gained from these models were compared to the second batch of the results. Outcome of the models were promising. Using magnitude of two statistical functions, root-mean squared error and coefficient of multiple determinations, we showed that our predictions are in great correlation with experimental data and the best performance can be obtained using ANN method.