Predicting the evolution of sheet metal surface scratching by the technique of artificial intelligence
- PDF / 1,882,428 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 98 Downloads / 199 Views
ORIGINAL ARTICLE
Predicting the evolution of sheet metal surface scratching by the technique of artificial intelligence Wei Li 1 & Liangchi Zhang 2 & Xinping Chen 3 & Chuhan Wu 1 & Zhenxiang Cui 3 & Chao Niu 3 Received: 22 July 2020 / Accepted: 11 November 2020 # Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract This paper presents an artificial intelligence (AI) method for the evolution prediction of surface scratching in sheet metals subjected to contact sliding. Ball-on-disk sliding was employed, and ball diameter, normal load, surface roughness, sliding cycles and the maximum scratching depth in the metal sheet were taken as the fuzzy variables to assess the contributions of individual variables to the surface damage. To improve the prediction accuracy, the quantum-behaved particle swarm optimisation (QPSO) algorithm was further developed and utilised to refine the fuzzy model by optimising the membership functions of the fuzzy variables. It was found that this AI technique, which integrates the fuzzy set theory with the improved QPSO algorithm, can accurately, reliably and efficiently predict the surface scratching evolution, which is otherwise impossible to be implemented. Keywords Surface scratching evolution . Artificial intelligence . Fuzzy modelling . Sliding contact . Sheet metal forming
1 Introduction Sheet metals, such as those of high-strength steels, have been widely used in the automobile industry to make carbody panels with the aid of various manufacturing processes such as deep drawing and stamping. In these processes, sliding between metal sheet and die/mould surfaces under high contact stresses is a common characteristic. Such contact sliding inevitably causes surface wear of the counterparts. Due to the complexity in deformation and morphology, including the randomly distributed asperities in the counterpart surfaces, their intricate interactive deformation and the influence of lubrication, it has been impossible to predict the extent and evolution of the wear-induced surface scratching. As a result, engineers can only make vague judgements based on their experience and skills [1], which is inaccurate and inefficient. * Liangchi Zhang [email protected] 1
School of Mechanical and Manufacturing Engineering, The University of New South Wales, Sydney, NSW 2052, Australia
2
Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen 518055, Guangdong, China
3
Baoshan Iron & Steel Co., Ltd., Shanghai 200941, China
It is therefore essential and necessary to develop a feasible method capable of the evolution prediction of surface scratching depth in the process of sheet metal forming, such that a smart process control can become possible. To characterise the rough surface contact, some statistical models of microscale asperities have been developed, e.g., the purely elastic model [2] and the elasto-plastic model [3]. In these studies, however, surface wear was unable to be taken into account. Some empirical investigations on
Data Loading...
