Case-based reasoning applied to geometric measurements for decision support in manufacturing

  • Ella Olsson
  • Peter Funk
  • Alf Andersson
Original Article


Measurements from products are continuously collected to allow adjustments in the production line to certify a feasible product quality. Case-based reasoning is a promising methodology for this type of quality assurance. It allows product measurements and its related adjustments to the production line to be stored as cases in a case-based reasoning system. The idea is to describe an event of adjustments based on deviations in geometric measurement points on a product and connect these measurements to their correlated adjustments done to the production line. Experience will implicitly be stored in each case in the form of uniquely weighted measurement points according to their positive influence on adjustments. Methods have been developed in order to find these positive correlations between measurements and adjustments by analysing a set of historical product measurement and their following adjustments. Each case saved in the case base will be “quality assured” according to this methods and only cases containing strong positive correlations will be used by the system. The correlations will be used to supply each case with its own set individual weights.


Decision support systems Experience reuse Case-based reasoning Quality improvement 



The authors gratefully acknowledge the funding from the Swedish Foundation for Strategic Research (SSF) ProViking grant (project no V08.04) and the ITEA 2 grant (project no 10020) making this research possible and to Volvo Car Corporation for their contribution of time and giving access to the manufacturing line.


  1. Aamodt A, Plaza E (1994) Case-based reasoning: foundational issues, methodological variations, and system approaches. AI Commun 7(1):39–59Google Scholar
  2. Dahlgren E, Castillo PC (2010) Development of web interface, server and database for intelligent process surveillance with focus on Geometry variations. Mälardalen University, VästeråsGoogle Scholar
  3. Gao C (2010) Connect measurements of car body parts to adjustments in production line. Uppsala and Mälardalen University, VästeråsGoogle Scholar
  4. Kolodner J (1993) Case-based reasoning. Morgan Kaufmann, San FranciscoGoogle Scholar
  5. Mark B. (1989). Case-based reasoning for autoclave management. Proceedings of the case-based reasoning workshopGoogle Scholar
  6. Mitchell T (1997) Machine learning. McGraw Hill, USAzbMATHGoogle Scholar
  7. Xiong N, Funk P (2010) Combined feature selection and similarity modelling in case-based reasoning using hierarchical memetic algorithm. In: IEEE Congress on Evolutionary Computation (CEC), pp 1537–1542Google Scholar
  8. Olsson E, Funk P (2009) Agent-based monitoring using case-based reasoning for experience reuse and improved quality. J Qual Maint Eng 15(2):14CrossRefGoogle Scholar
  9. Rodgers JL, Nicewander WA (1988) Thirteen ways to look at the correlation coefficient. Am Stat 42(1):59–66CrossRefGoogle Scholar
  10. Watson I (1997) Applying case-based reasoning: techniques for enterprise systems. Morgan Kaufmann, San FranciscozbMATHGoogle Scholar

Copyright information

© The Society for Reliability Engineering, Quality and Operations Management (SREQOM), India and The Division of Operation and Maintenance, Lulea University of Technology, Sweden 2013

Authors and Affiliations

  1. 1.Saab AB AerosystemsArbogaSweden
  2. 2.School of Innovation, Design, and EngineeringMälardalen UniversityVästeråsSweden
  3. 3.Volvo Car Corporation, Manufacturing EngineeringOlofströmSweden
  4. 4.Product Development Chalmers UniversityGöteborgSweden

Personalised recommendations