Prognosis of gas turbine remaining useful life using particle filter approach

Abstract

Gas turbines are commonly used in distributed power generation. Because of high speed nature, they require good maintenance for increased reliability and availability. Remaining useful life prediction is therefore an essential part of condition‐based maintenance to better foresee future state hence guaranteeing design efficiency, reduced maintenance cost, and improved safety. Gas turbines also contain a lot of sensors data that need to be processed for better prediction. In this paper, a probabilistic approach called particle filter is used for prediction. The proposed approach is tested using Turbofan degradation data provided by NASA as a benchmark problem. Meanwhile, through time the gas turbines experiences a change from normal state to degraded state attributed to aging, corrosion and erosion etc. Hence, in the context of abundant data, it is helpful to know the transition between states. For the same reason, the present paper suggests a statistical approach called Z‐test. The test results show that the proposed technique provides score and MAPE values of 559.9 and 21.6 respectively, comparable to past reported performance.

Remaining useful life prediction of crude oil pipeline by means of deterioration curves

“…The ERF threshold values provided by the crude oil industry for maintenance were used to calculate the RUL of the pipeline. The RUL is the time at which the health indicator (in this research ERF) value will intersect the threshold for failure (ie, ERF = 1.0) and the formula is given by Equation where t p is predicted failure time and t c is current time.…”

“…The value will intersect the threshold for failure (ie, ERF = 1.0) and the formula is given by Equation (3). 16,17…”

Transient Behavior in Variable Geometry Industrial Gas Turbines: A Comprehensive Overview of Pertinent Modeling Techniques

“…Gas turbines have certain design conditions, however, they are being operated off design due to power fluctuations, which results in performance degradation [ 7 , 8 ]. Apart from this, some critical factors such as startup, load change, shutdown, variations in ambient conditions, equipment failure and other abnormal behavior exist, which can trigger transient behavior by shifting the engine’s equilibrium from one steady state to another steady state [ 9 ].…”

Reliability analysis of gas turbine engine by means of bathtub‐shaped failure rate distribution

“…4 These risks also escalate with time and are characterized by reliability, maintainability, and availability. [5][6][7][8][9] To ensure safe operation and minimize avoidable risks during the operation of gas turbines, techniques such as diagnosis, [10][11][12][13][14] prognosis, 3,[15][16][17][18] and reliability monitoring [19][20][21][22][23][24] have widely been employed.…”

“…The study introduced the analysis of extending the aircraft life beyond expected operating time. Zhou et al 21 Garmabaki et al 31 studied a fleet of AJ 37 strike aircraft and presented a procedure for identifying suitable reliability model for F I G U R E 1 Gas turbine schematic diagram 3 F I G U R E 2 Bathtub curve for electronics and mechanical systems repairable units. The study focused on the statistical techniques; however, details for maintenance strategy selection were not discussed.…”