| Theme | Automation, Automated guided vehicles |
|---|---|
| Project title | Case-based expert system for automated reaction in freely navigating automated guided vehicle systems (FTS-Expert) |
| Project duration | 01.02.2017 – 31.12.2019 |
| Results |
The research project's goal is the development of a case-based expert system, which is capable of an automated reaction to disturbances in free navigating Automated Guided Vehicle Systems (AGVs). In order to do that the system examines the current occurrence with disturbance scenarios in its database. Based on similarities the expert system takes the proper action. A promising method from the area of knowledge-based approaches is case-based reasoning, which is to be applied in the context of this research program.
The system to be developed supports companies in their efforts to increase the efficiency of installed AGVs. This can be achieved by reducing the system downtimes that are caused by manual disturbance management. Since currently, the involvement of experts for resolving disturbances is mandatory companies could accomplish a reduction of overall cost with the usage of the described expert system. The innovative approach of the planned expert system is among other things, the fact that it assesses the urge of action given by the disturbances and their interactions within the overall system.
Publications about the project
Automated guided vehicle systems (AGVS) are an essential part of modern intralogistics. So far, the major part of the design cycle (implementation and operation) of an AGVS demands human expertise. Especially, the manually executed management of occurring disturbances leads to high maintenance costs since it often requires the consultation of experts. Therefore, the following paper discusses the development of a Case-Based Reasoning (CBR) expert system for assisting the disturbance management in AGVS. The development is sectioned into three major parts: (1) generation of the case-base, (2) development of the algorithms for case retrieval, case adaptation and retaining new cases and (3) the validation of the expert system. The generation of the case-base and the training data for the expert system is done by simulating the real production layout of a German white good manufacturer using the simulation environment Visual Components. The solutions for the simulated disturbances as well as the adaptation algorithms are based on knowledge extracted from system experts.
automated guided vehicles AGV, case-based reasoning, disturbance management, expert systems
