Preventive Quality is an approach of the AWS-Institute to design and implement quality assurance in manufacturing industries in a data-based, preventive way. The aim of this approach is to apply the findings of quality assurance back into product development, thus identifying potential product defects at an early stage and avoiding error costs. In detail, methods of machine learning and artificial intelligence are used to perform an automated analysis of data from quality controls and returns to determine correlations between product characteristics and quality. The findings are fed back into the product development process, where an assistance system is used to support the developers.
In contrast to purely predictive analysis approaches, in which only predictions are made about the future occurrence of quality problems, Preventive Quality goes one step further: By analyzing the causes of errors in combination with an assistance system, the development of product errors can be avoided in a holistic approach. The assistance system provides recommendations for the optimization of product development and provides information on alternatives and the economic consequences of a product decision. Thus, an optimal balance between design and quality is achieved immediately during the development process and product defects are avoided before they occur. Preventive Quality optimizes in particular the quality assurance in industries with creative product design and / or a high variety of products.