Event Modelling in the Manufacturing process: IQONIC Initiatives

In the last few months, IQONIC partners have been working on the data acquisition and collection of the production process, both fabrication and assembly (Defect life-cycle management, disassembly and remanufacturing_WP5). The accomplishment of the data analysis will then pave the way for the forthcoming establishment of a defect prediction model aiming notably at building an autonomous adaptive engine for real-time inspection, control and decision support of opto-electronic production at the engineering level. This is the main purpose of WP6, Process and Artificial Intelligence Implementation, which will simultaneously deal with the development of models for predicting defect due to deterioration of machinery condition and of multi-parametric models of product instances, while interfacing with MES and other higher level management systems.

In this frame, Brunel University London organised on August 2nd the Robotics, Autonomous and Manufacturing Systems Symposium, which further deepened IQONIC research on defect prediction modelling. On this occasion, the Brunel University gave a presentation on “Event Modeler Method in Manufacturing Process”, which concerns real time sensitivity analysis in large scale and complex manufacturing systems. The method, which borrows principles from the event tracking of interrelated causal events and deploys clustering methods to automatically measure the relevance and contribution made by each input event data (ED) on system outputs, will be applied in IQONIC WP6 research activities aiming at straightening  the theoretical and the practical foundation for the engineering of knowledge and data in modern and complex systems.

For further information on this topic:

Wang, J., Ma, Y., Zhang, L., Gao, R. and Wu, D. (2018). Deep learning for smart manufacturing: Methods and applications. Journal of Manufacturing Systems, 48, pp.144-156.

Wang, T., Chen, Y., Qiao, M. and Snoussi, H. (2017). A fast and robust convolutional neural network-based defect detection model in product quality control. The International Journal of Advanced Manufacturing Technology, 94(9-12), pp.3465-3471.