Adaptive prognostic approaches combining regime identification with equipment operating history

Health management is becoming increasingly important in expensive and complex machinery such as aircraft, shipboard equipments, and ground vehicles. The diagnosis of failures in such vehicles (or in their subsystems) based on asset condition has been analyzed in-depth in the last few decades, and is relatively well understood. However, prognostic evaluation of faults in machinery, also known as prognostic health management (PHM), is a much harder task that involves predicting impending faults in the system and determining remaining useful life of the machinery. A good adaptive prognostics system can also serve to speed the diagnosis of problems by providing indication of what sections of the asset are most likely to be the cause of problems, or are soon to need maintenance. A number of methods for prognostics have been researched with varying degrees of success. A number of possible algorithms, as well as a detailed description of a hybrid Condition Based Maintenance (CBM) - Prognostic technique being investigated for use will be presented, especially those techniques that can be refined through the use of test results. The system described incorporates a number of Artificial Intelligence techniques to process and analyze the current condition of a vehicle, with respect to the operating regimes encountered, and to generate a prognosis for each monitored component. The discussion will describe a means of testing, verifying and iteratively improving prognostic capabilities throughout the lifecycle of the asset. A focal point of the discussion will be the use of an open, extensible CBM+ system that incorporates distributed, spatial data collection and centralized processing and algorithm development to provide a continuously improving system.