THE OVERALL OBJECTIVE OF THIS PROJECT IS TO REDUCE THE NUMBER OF LONG- AND SHORT-DURATION BEAM TRIPS IN ACCELERATOR DRIVEN SYSTEMS FOR NUCLEAR ENERGY WASTE TRANSMUTATION APPLICATIONS BY AN ORDER OF MAGNITUDE WHEN COMPARED TO THE CURRENT STATE-OF-THE-ART. A SECONDARY OBJECTIVE IS TO INTEGRATE PHYSICS INFORMATION WITH DATA-DRIVEN MACHINE LEARNING (ML) METHODS TO IDENTIFY ACCELERATOR EQUIPMENT ISSUES TO ASSIST IN SMART MAINTENANCE PRACTICES THAT FURTHER ENHANCE THE RELIABILITY AND EFFICIENCY OF THE BEAM LINE.