A portable knowledge-based system for car breakdown evaluation

- A prototype of KBS for car breakdown evaluation to be accessed remotely using smart devices is presented.
- It uses a flexible algebraic inference engine that can be adapted for many-valued logics.
- The inference engine uses Groebner bases (of polynomial ideals).
- The execution is remote and completely transparent to the user.
- It allows drivers to obtain suggestions immediately when a breakdown occurs just using a smartphone.

Modern cars have many dashboard lights and not all drivers recognize or know the importance of all of them. Red symbols usually indicate a safety issue or a serious problem, meanwhile yellow symbols use to indicate a not so urgent problem. Green and blue symbols usually provide information about the systems connected. But not all the red icons require of the same action, and the user manuals of most modern cars, with their sophisticated electronic systems, have hundreds of pages. Meanwhile, smart devices have become popular and have an outstanding computing power plus Internet connection. Consequently, the conditions for developing a knowledge-based system that helped the unaware driver in case a dashboard light went on, exist. The application should evaluate the situation and recommend the best actions to be carried out by the driver (regarding the possible repair on site or at a workshop, its urgency or even the need to immobilize the vehicle immediately). We have designed such a knowledge-based system and have developed a simplified one as example. A friendly Graphical User Interface has been developed in order to ease the communication with the application and its use in remote using any smart device with Internet connection.