Integrating model-based diagnosis techniques into current work processes -three case studies from the INDIA project

Although the area of model-based diagnosis has developed a number of protot ypes with impressive features that promised economic impact and, hence, cau ght industrial interest, the number of actual industrial applications is st ill close to zero. One of the reasons is that the successful techniques hav e not yet been turned into tools that reflect and support the current diagn ostic work processes and their existing tools. The INDIA project joined eig ht German partners (research groups, software suppliers, and end users) in an attempt to take a major step in the transfer of model-based diagnosis te chniques into industrial applications. This paper describes part of the wor k carried out in this project. Rather than presenting the theoretical found ations of the techniques in depth, we focus on the aspect of how model-base d diagnostic techniques can be related to established tools and systems in order to provide some leverage for today's work processes and to change the m gradually, as opposed to postulating a radical change in current practice and organizational structures. From this perspective, we discuss the utili zation of model-based techniques for the generation of fault trees for on-l ine testing and diagnosis of fork lifters, generation of test plans for an intelligent authoring system for car diagnosis manuals, and the exploitatio n of existing state-chart process descriptions for post-mortem diagnosis of processes in a dyeing plant.