Prognostics of gas turbine: A condition-based maintenance approach based on multi-environmental time similarity

The maintenance cost of a gas turbine is significantly higher than its original purchase cost. This study presents a novel prognostic condition-based maintenance (CBM) approach based on the theory of multi-environmental time similarity (METS). In this approach, gas turbine of the same type is regarded as the reference system, and two influential factors - the running hours and number of start-ups are selected as the main degradation indicators. The similarities are calculated based on the values of the degradation indicators under service environment and benchmark environment. Equivalent life (EL) of the object system under the benchmark environment is calculated on the basis of the similarities and historical data of the object system under the service environment. Remaining life (RL) of the object system is obtained by comparing EL and theoretical life. Real-time RL, historical RL and their calculating algorithms are proposed for acquiring more accurate historical degradation data that can be employed for decision making. Factored service factor is proposed as a key indicator in decision making of CBM, and four optional CBM scenarios are constructed based on different values of the factored service factor. This approach is applied in a thermal power plant in Hangzhou, China, and its effectiveness is proved as an extra power generation of 302,640 MW·h can be achieved due to re-scheduled maintenance.