Sensor-based Monitoring of Machining Processes using Incremental Learning for Inspection by Exception

The UK manufacturing industry faces many challenges to remain competitive and increase revenue with reduced energy demand and material waste in production. Customers are seeking not only ever more precise products at lower cost, but also shorter lead times and greater product variability. Furthermore, the reliance of manufacturing enterprises on skilled and experienced operators is a huge obstacle to meeting the current trends of Industry 4.0 for the digital transformation of manufacturing processes. The aim of this project is to produce a step-change in the capability of monitoring machining processes, with the focus being in the product health. The novelty of the proposed research lies in the development of state-of-the-art metrology informatics systems based on incremental learning algorithms and multi-sensor data for machining process monitoring and control. Novel Artificial Intelligence (AI)-based monitoring methods using in-process metrology data will be designed and developed for machining processes to reduce the need for non-value adding processes, such as dimensional inspection. The key to this is in determining the most suitable combination of sensors that complement each other and in identifying monitoring variables which are linked to process dynamics directly. To carry out the proposed research, specialised equipment, such as sensors, data acquisition systems, etc., is needed which is not available from the university of Portsmouth, hence the reason for this grant application.