Intelligent tribological forecasting model and system for disc brake

Abstract

This paper aims at improving the braking ability and reliability of disc brakes. Based on some braking tests of the disc brake, an intelligent forecasting model for its tribological properties was established firstly by the artificial neural network (ANN) technology. Its input layer contains three braking cells: braking pressure, sliding velocity and surface temperature. And its output layer contains three tribological cells: friction coefficient and its stability coefficient, and wear rate. Secondly, an intelligent forecasting system was developed based on the model. It is mainly composed of three parts: sensing system, data collecting system, and data computing system. Finally, the disc brake used in mine hoists was tested on the system as an example. It is shown that the experimental data which contain nonlinear relationships between the braking conditions and tribological properties of disc brake are theoretical foundations of the tribological forecasting. The ANN is especially suitable for establishing the tribological forecasting model. And the optimized BP network is proved as a simple and effective computing model. The intelligent model and system established in this paper has quite favorable forecasting ability and practicability. By the contrast, it has higher precision for forecasting of the friction coefficient and its stability coefficient than the wear rate. The difference was attributed to man-made testing errors of data samples during tribological experiments.

Review on the friction and wear of brake materials

“…For examples, the classical adhesive friction and wear theories should be modified, the forming and evolving mechanisms of friction films should be investigated, 48 the friction surface topography may be characterized by fractal theories 49 or cellular automata, and so on. On the other hand, instead of being deduced from friction and wear mechanisms, the relationship between tribological behaviors and influential factors may be presented more simply and intuitively based on artificial intelligence technologies such as artificial neural network, [50][51][52][53] fuzzy algorithm, expert system and gray theory, 54 and so on.…”

Comparative Analysis of Abrasive Wear Using Response Surface Method and Artificial Neural Network

“…Accurate prediction of wear behaviour by ANN provides an alternative to the current time-consuming testing methods. Since then, the technique has been successfully used in the tribology field, which includes wear of polymer composites [18][19][20][21][22], tool wear [23], online wear rating [24], brake performance [25,26], corrosion of polymers [27], wheel and rail wear [28], copper-aluminium nano-composite wear rate [29], wear of heattreated aluminium-clay composites [30] and wire electrical discharge process [31][32][33]. Bhaumik et al [34] implemented the technique for predicting the coefficient of friction for various friction modifiers.…”

Artificial Neural Networks (ANNs) as a Novel Modeling Technique in Tribology

“…In recent years, an increasing number of tribological studies turned to the use of artificial intelligence (AI) techniques (Bucholz et al, 2012;Ali et al, 2014), including data mining (Liao et al, 2012) and artificial neural networks (Gandomi and Roke, 2015). In the last two decades, starting from the work of Jones et al (1997), the areas of successful incorporation of AI generally and neural networks (NNs) specially have been constantly expanding in tribology research and cover such diverse applications as wear of polymer composites (Kadi, 2006;Jiang et al, 2007), tool wear (Quiza et al, 2013), brake performance (Aleksendrić and Barton, 2009;Bao et al, 2012), erosion of polymers (Zhang et al, 2003), wheel and rail wear (Shebani and Iwnicki, 2018). Nevertheless, it is important to emphasize that, while AI is widely applied for diagnostics (identification), classification, and prediction (process control) (Meireles et al, 2003), much remains to be scrutinized to extend its modeling (in a narrow sense of this term) capabilities.…”