THIS INVESTIGATION WILL ASSESS AND DEMONSTRATE THE FEASIBILITY OF USING ARTIFICIAL INTELLIGENCE (AI) TECHNIQUES TO DEVELOP AN EXPERT SYSTEM SERVING AS AN ACCIDENT DIAGNOSIS AND PROGNOSIS (AD&P) AIDE.

Period of Performance: 01/01/1986 - 12/31/1986

$49.6K

Phase 1 SBIR

Recipient Firm

Technology Applications, Inc.
6621 SOUTHPOINT DR N - STE 310
Jacksonville, FL 32216
Principal Investigator

Abstract

THIS INVESTIGATION WILL ASSESS AND DEMONSTRATE THE FEASIBILITY OF USING ARTIFICIAL INTELLIGENCE (AI) TECHNIQUES TO DEVELOP AN EXPERT SYSTEM SERVING AS AN ACCIDENT DIAGNOSIS AND PROGNOSIS (AD&P) AIDE. THE NEED FOR SUCH A SYSTEM IS BASED UPON INDUSTRY AND REGULATORY COMMITMENT TO IMPROVED NUCLEAR PLANT PERFORMANCE AND SAFETY.AI TECHNOLOGY IS JUST NOW MAKING ITS WAY OUT OF THE LABORATORY AND INTO THE REAL WORLD; AS SUCH, THE TIME IS RIPE FOR INVESTIGATING PRACTICAL, VALUE-ADDED AI APPLICATIONS. THE CONTRACTOR WILL INVESTIGATE AND DEMONSTRATE THE FEASIBILITY OF (1) USING CRITICAL SAFETY FUNCTION STATUS TREE TECHNOLOGY TO DIAGNOSE NUCLEAR PLANT ACCIDENT SITUATIONS, (2) USING PROBABILISTIC RISK ASSESSMENTEVENT SEQUENCE ANALYSIS TECHNOLOGY TO PREDICT THE VARIOUS DIRECTIONS AN ACCIDENT-IN-PROGRESS MIGHT TAKE, AND (3) USING FUNCTIONAL RESTORATION GUIDELINE TECHNOLOGY TO GENERATE CORRECTIVE ACTION RECOMMENDATION FOR STABILIZING THE REACTOR PLANT. DURING THE COURSE OF THE PROJECT, A WORKING SCALE MODEL, REFERRED TO AS THE AD&P AIDE DEMONSTRATION PROTOTYPE, WILL BE DEVELOPED. ITS PURPOSE WILL BE TO PROVIDE AN EXPERIMENTATION ENVIRONMENT FOR PROVIDING RAPID FEEDBACK ONT HE CONCEPTS UNDER INVESTIGATION, INCLUDING TECHNICAL FEASIBILITY, PRACTICALITY, AND USEFULNESS. THE FINAL REPORT WILL DUCUMENT THE RESULTS OF THE FEASIBILITY STUDIES, A DESCRIPTION AND EVALUATION OF THE DEMONSTRATION PROTOTYPE AND CONCLUSIONS AND RECOMMENDATIONS.