Artificial intelligence techniques applied to vehicle management system diagnostics

A vehicle management system (VMS) research and development project is underway at McDonnel Aircraft to integrate control of systems on combat aircraft and enhance diagnostics. A VMS demonstrator has been constructed to test VMS methodologies and architectures. Two real-time expert systems are under development to diagnose electrical and fuel system failures on the VMS demonstrator: an electrical expert system, located on a Sun Microsystems SPARCstation 1 that acquires data from a centralized computer; and a fuel expert system, located in the control computers using a shared memory allocation with the control software. Both expert systems used the CLIPS inference engine developed by NASA. Future enhancements to the two expert systems will include more use of probability in determining failures and testing other versions of the CLIPS inference engine.<
>