Within the context of smart manufacturing or Industry 4.0, a strong technologic shift has become apparent within industry to move towards both more intelligence and more sustainability towards net-zero or zero waste targets. The importance of quality control in smart manufacturing process has always been recognized. However, now more than ever before, it is a key requirement in order for manufacturing companies to remain competitive and sustainable in the digital age. Because of the complexities and globalization of the manufacturing supply chain, real-time product quality control has become an important issue in the global manufacturing industry. Therefore, the fundamental understanding of the strategic application of how net-zero or zero waste ambition into practical smart robotic manufacturing is essential, especially for online quality control through in-process nondestructive inspection. To achieve the UK’s ambitious net-zero carbon objectives, research and innovation are required to solve a wide range of technological and operational challenges. In particular we are committed to address the Engineering Net Zero and Manufacturing and the Circular Economy challenges.

Though nondestructive techniques have been widely applied in manufacturing for many tasks including inspections, they are currently facing many emerging challenges arising from human-robot collaborative manufacturing processes, which have presented a fundamental knowledge gap on how to intelligently control product quality in-process by dealing with process uncertainties, variations caused by the highly customised production, dynamic interactions of humans/other machines including other robots and the need for greater flexibility and intelligence in smart manufacturing systems. Cobot-enabled nondestructive quality control in production lines with advanced vision and machine learning inspections provides a feasible solution to solving these challenges.  

The ambition of this project is to fundamentally investigate novel human-robot collaborative nondestructive strategies for in-process quality control in smart manufacturing to fill the knowledge gap and research need identified above.  The key novelty is the development of explainable machine learning algorithms, fast-response sensing (in particular machine vision and Nondestructive Testing (NDT)) and novel quality control strategy that implicitly consider human knowledge, process uncertainty, dynamic interaction and variation through intelligent fusion of multiple sensors and sources of information when making collaborative decisions for in-process quality inspection and control.