Development of a hybrid PCA-ANFIS measurement system for monitoring product quality in the coating industry

In industry today many products are sold for their efficacy rather than their chemical composition. There are several key attributes within the coating industry such as, anchorage, seal strength etc., which characterize the quality of the final product and are features used by the company to promote the sale of the product. Such quality variables (dependent variables) however may involve measurement difficulties. The difficulties can be due to a variety of reasons, including: (1) reliability of on-line sensors, (2) lack of appropriate on-line instrumentation. In the coating process off-line laboratory tests determine product quality measurements. However, such laboratory analyses introduce delays in the measurement of key performance indicators. This can result in a significant economic loss if the analysed product fails the quality control test. An improved monitoring system is required therefore to determine product quality online and minimise commercial wastage. To facilitate this, advanced monitoring and control or optimization techniques require inferred measurements, generated with correlations from readily available process variables (independent variables). Although inferential models are widely used in industry, only a few techniques for inferential model development are discussed in the open literature. This paper therefore presents an improved systematic approach for the development of inferential models using soft computing systems and demonstrate the methodology by inferring the ´anchorage´ of polymeric-coated substrates (i.e. Tyvek or paper) in the coating industry.