From datasheets to digital intelligence

: transforming material knowledge into rule-based decision support in industrial powder coating

Abstract

Powder coating operations rely increasingly on automation, however day-to-day parameter decisions still depend strongly on operator experience and fragmented manufacturer datasets. This thesis explores how powder coating material data can be digitally transformed, standardized and converted into transparent, rule-based recommendations to support operators, production managers and quality managers in manual, semi-automatic and automatic coating systems, while also enhancing Wagner’s digital service offerings and ecosystem. The study adopts exploratory qualitative design, triangulating three data sources: an analysis of 761 technical datasets from three different powder coating manufacturers, twelve external interviews with coating companies and five internal expert interviews at Wagner. The datasheet analysis identifies a small core of central parameters available across manufactures, but inconsistent terminology, units and layouts limit automatic extraction and comparability. In- and external interviews show that datasheets are rarely used in day-to-day operations, instead knowledge is embedded in recipes located in internal ERP systems and in the heads of experienced experts, resulting in labor-intensive documentation and traceability. Based on these findings, the thesis develops a TID-framework and proposes a conceptual Powder Material Assistant embedded in Wagner’s internal Coatify ecosystem. The concept combines a structured material database including transparent if-then logic, using AI mainly for rule refinement. Anticipated benefits include reduced scrap and rework, shorter set-up and troubleshooting times, lower powder consumption and improved documentation.

Date of Award	6 Feb 2026
Original language	English
Awarding Institution	Universidade Católica Portuguesa
Supervisor	Duarte João Ferreira (Supervisor)