To reduce defects, we firstly need to identify why problems occur. Next, to what degree those factors affect the defect rate. Additionally, if I am to vary a parameter, what impact would it have on the overall defect rate?
In order to understand the factors that affect defect rate, we needed an understanding of certain machine, environment and human factors and their effect on the defect rate. Additionally, how much impact these factors have on the defect rate, was quantified through a sensitivity analysis and a correlation analysis.
There were multiple AI solutions including,
State-of-the-art transformer based defect and production volume forecasting time series module
Defect prediction with employee, machine and environmental data
Defect classification
Additionally, Six-sigma graphs to understand the range at which certain parameters have to be kept and what needs to be improved were provided. The implementation of the system has increased the effectiveness of the investments made by company on their QA efforts.
If you have a factory that needs a QA system that contains predictive AI models and defect classification systems, reach out to me!