{"id":8235,"date":"2026-06-19T17:25:50","date_gmt":"2026-06-19T15:25:50","guid":{"rendered":"https:\/\/es.ai-matters.eu\/ai-testing-laser-welding-defect-detection-manufacturing\/"},"modified":"2026-07-22T11:46:52","modified_gmt":"2026-07-22T09:46:52","slug":"ai-testing-laser-welding-defect-detection-manufacturing","status":"publish","type":"post","link":"https:\/\/es.ai-matters.eu\/en\/ai-testing-laser-welding-defect-detection-manufacturing\/","title":{"rendered":"How NIT used AI to improve laser welding defect detection through high-quality data synthetic generation"},"content":{"rendered":"
\n
\n
\n
NIT’s Experience:<\/div>\n
<\/path><\/svg><\/path><\/svg><\/path><\/svg><\/path><\/svg><\/path><\/svg><\/div>\n<\/div>\n<\/div>\n<\/div>\n
<\/div>\n

How can AI-based inspection systems be improved and validated before industrial deployment without disrupting production lines or investing in costly new experiments?<\/strong><\/strong><\/strong><\/h2>\n

In this user story, we show how New Infrared Technologies (NIT) used AI-MATTERS to test and validate the performance of an AI-based infrared inspection solution, improving automatic defect detection accuracy and increasing industrial deployment readiness with reduced upfront risk or any production disruption at its clients facilities. AI-MATTERS provided access to both technology and domain expertise, data enrichment and benchmarking services to validate the solution under realistic industrial conditions.<\/p>\n

New Infrared Technologies (NIT) is a technology provider developing AI-enabled infrared autonomous inspection systems for manufacturing. As a tech provider, NIT needed to technically validate and mature its AI-based defect detection solution, moving from a promising prototype towards deployable performance levels while minimizing development cost, risk and dependency on end-user production facilities.<\/p>\n

The Challenge<\/strong><\/strong><\/h2>\n

The AI\u2011based infrared inspection solution for laser welding quality control suffered from limited and unbalanced datasets, particularly for defective cases. As a result, detection accuracy remained insufficient to support industrial deployment decisions.<\/p>\n

NIT lacked access to large volumes of representative defect data and could not easily perform new experimental campaigns, which would have required repeated access to end\u2011user production facilities and could impact ongoing manufacturing processes. This uncertainty prevented objective performance validation and hindered further development and market uptake of the solution.<\/p>\n

The Approach<\/strong><\/strong><\/h2>\n

Through AI\u2011MATTERS, NIT gained access to a Testing and Experimentation Facility (TEF) providing:<\/p>\n