Quality monitoring of complex manufacturing systems on the basis of model driven approach
Fernando Castaño, Rodolfo E. Haber, Wael M. Mohammed, Mirosław Nejman, Alberto Villalonga, José L. Martínez Lastra
Abstract
Monitoring of complex processes faces several challenges mainly due to the lack of relevant sensory information or \ninsufficient elaborated decision-making strategies. These challenges motivate researchers to adopt complex data processing and \nanalysis in order to improve the process representation. This paper presents the development and implementation of quality \nmonitoring framework based on a model-driven approach using embedded artificial intelligence strategies. In this work, the \nstrategies are applied to the supervision of a microfabrication process aiming at showing the great performance of the framework \nin a very complex system in the manufacturing sector. The procedure involves two methods for modelling a representative quality \nvariable, such as surface roughness. Firstly, the Hybrid Incremental Modelling strategy is applied. Secondly, a Generalized Fuzzy \nClustering C-Means method is developed. Finally, a comparative study of the behavior of the two models for predicting a quality \nindicator, represented by surface roughness of manufactured components, is presented for specific manufacturing process. The \nmanufactured part used in this study is a critical structural aerospace component. In addition, the validation and testing is \nperformed at laboratory and industrial levels, demonstrating proper real-time operation for non-linear processes with relatively \nfast dynamics. The results of this study are very promising in terms of computational efficiency and transfer of knowledge to \nmanufacturing industry