Prof Alessio Benavoli has been awarded funding from the SFI National Challenge Fund – Future Digital Challenge programme in collaboration with Prof Rocco Lupoi from the School of Engineering with their project “HLOOP: Humans-in-the-Loop towards a more effective Artificial Intelligence in manufacturing”. HLOOP will build a single AI-model exploiting the synergy between AI and human-workers to improve process optimisation in manufacturing.
The adoption of Artificial Intelligence (AI) for Process Optimisation (PO) in manufacturing can significantly contribute to make the Irish manufacturing sector more competitive and sustainable. However, its adoption has been slower than expected. Looking at the way AI is being used in PO, the issue is the need of tailoring AI-solutions for every machine tool and context (used material, shape of the manufactured object). With this approach, the industry will need “tens of thousands’’ of unique AI models, which is clearly infeasible.
Human machine operators are more effective at assessing the quality of the manufacturing process while AI is better at dealing with high-dimensional decision problems. With funding support from the SFI Future Digital Challenge programme, Benavoli and Lupoi will focus on building a single AI-model to exploit this synergy between AI and human-workers in their project “HLOOP: Humans-in-the-Loop towards a more effective AI in manufacturing”
Project lead Prof Alessio Benavoli from the School of Computer Science and Statistics elaborates: “Have you ever faced the disappointment of your manufactured product not turning out as desired? The "recipe" you are using may not always produce the desired result, leaving you wondering which parameters to change next in order to maximize the product quality. HLOOP aims to use the feedback of machine operators to train on-the-fly (without any pre-built dataset) and in real-time an AI-model that can predict when the manufacturing process is good/bad and then optimise it, making the manufacturing process more effective, efficient and sustainable.”
How HLOOP works? Let's consider the process of baking a cake (figure-left). Firstly, we carefully select the parameters to optimise, like amount of butter, sugar, and oven temperature. Next, we may experiment with four different recipes, each resulting in a different cake. We then taste each cake and rank the recipes based on our preferences. Using this valuable human feedback, HLOOP can iteratively improve the recipe until we achieve the perfect cake (figure-right). Remarkably, this approach can be applied to any manufacturing process to achieve optimal products/processes, such as the metal injection moulding process (figure-centre).
HLOOP is an interdisciplinary collaboration between the School of Computer Science and Statistics and the School of Engineering, bringing together expertise in Artificial Intelligence/Machine Learning and mechanical and manufacturing engineering. Ultimately, the project aims to advance the Irish manufacturing sector towards a more human-centric, resilient, and green industry.
Project co-lead Prof Rocco Lupoi from the School of Engineering highlights: “The collaboration between the School of Computer Science and Statistics and the School of Engineering can bridge the gap between theoretical knowledge and practical application, ensuring that the proposed solution is not only technically sound but can also address a wide range of process optimization problems in real-world manufacturing settings. This can lead to more effective and efficient manufacturing processes, making the Irish manufacturing sector more competitive and sustainable.”
For more information on the project, please contact Prof Alessio Benavoli - firstname.lastname@example.org