Engineers at Diodes Incorporated in Greenock are improving how production data is used on the factory floor through a collaboration with the National Manufacturing Institute Scotland (NMIS), helping accelerate decision-making, reduce manual analysis, and improve operational efficiency across semiconductor manufacturing.
The initiative forms part of NMIS’s Data-Driven Design and Manufacturing Colab (D3M-Colab) programme, which supports manufacturers in developing in-house data science capability and applying it directly to real-world production challenges.
At Diodes’ 24-hour wafer fabrication facility, engineers previously relied heavily on spreadsheets and manual extraction of production information to analyse manufacturing performance. While effective, the approach limited scalability and slowed the speed at which insights could be generated and acted upon.
Working alongside NMIS, operated by the University of Strathclyde, the engineering team has introduced more advanced data science techniques, including Python-based workflows and specialist semiconductor software tools. The changes are helping automate data handling processes, improve consistency, and make analysis more accessible across the manufacturing operation.
The programme also included a structured 12-week training initiative designed to help engineers independently develop and deploy data-led manufacturing projects, supported by NMIS data scientists. New dashboard tools created through the collaboration are enabling production data to be visualised more clearly, supporting faster and more informed operational decisions.
Andrew Burns, engineering manager at Diodes Incorporated, said the project had allowed the company to move beyond manual data analysis and adopt more advanced manufacturing intelligence capabilities.
“We’re now able to present our data in a much more accessible way, which means decisions can be made more quickly and with greater confidence,” he said. “It’s helped us identify where we can improve efficiency, quality and cost, and it’s opened the door to how we can use data even more effectively in the future.”
Diodes engineers are now exploring additional applications, including AI-driven analysis of manufacturing outputs and predictive maintenance systems capable of identifying early signs of equipment failure. The company believes these approaches could help reduce downtime, lower maintenance costs, and extend equipment life.
Andrew Sherlock, director of data-driven manufacturing at NMIS, said the collaboration demonstrated how manufacturers could move beyond simply collecting data to using it strategically within production environments.
“By bringing together engineering expertise and data science, we’re supporting teams to identify where improvements can be made and giving them the skills to turn that insight into action,” he said.
The project also sits within a wider effort to strengthen Scotland’s semiconductor manufacturing ecosystem, including the upcoming National Advanced Semiconductor Packaging and Integration Centre (NASPIC) in Renfrewshire, which will support development and commercialisation of next-generation semiconductor technologies.
The broader programme is backed through the UK Innovation Accelerator initiative, led by Innovate UK on behalf of UK Research and Innovation, which is investing £100 million into regional R&D projects across the UK.
