This paper presents the statistical characterization of the oxidation degradation mechanism affecting the nozzles of turbines operated in Oil and Gas utilities. The degradation mechanism is modeled as a four-state, continuous-time semi-Markov process with Weibull distributed transition times. Maximum likelihood estimation is used to infer the parameters of the model from an available set of field data, whereas a numerical approach to estimate the Fisher information matrix is used to characterize the uncertainty in the estimates. The estimates obtained are, then, utilized to compute the probabilities of occupying the four degradation states over time and the corresponding uncertainties. A case study is shown, dealing with real field data

We consider the maintenance process of gas turbines used in the Oil and Gas industry: the capital parts are first removed from the gas turbines and replaced by parts of the same type taken from the warehouse; then, they are repaired at the workshop and returned to the warehouse for use in future maintenance events. Experience-based rules are used to manage the flow of the parts for a profitable gas turbine operation. In this article, we formalize the part flow management as a sequential decision problem and propose reinforcement learning for its solution. An application to a scaled-down case study derived from real industrial practice shows that reinforcement learning can find policies outperforming those based on experience-based rules.

Several operating parameters for the control and protection of the units are acquired by the control and protection systems used in industrial applications. The use of these parameters in conjunction of physical models, empirical models and transfer functions (that represent digital replicas of the engine) allows for a broader scope of condition monitoring, taking into account the wing to wing process which spans from data acquisition to end user actionable insight. This paper describes 3 specific cases: 1) an algorithm based on the performance model of the overall GT used to monitor the axial compressor degradation and optimize the planned axial compressor water wash of an aero-derivative GT; 2) an analytic based on the flow function physic model used to monitor the clogging of the fuel nozzles in a heavy duty GT and to plan their maintenance; 3) an analytic based on a hybrid model used to monitor the axial thrust acting on a roller bearing of an aero-derivative GT and used to verify the status of the bearing and to plan its maintenance. Moreover, the paper provides details about the evaluation of the measurements, describes the model accuracy and explains how the results obtained are affected by these uncertainties and the methods used to mitigate these uncertainties. In addition, this paper shows a method to aggregate and weigh the monitoring of each single component and its own status into an overall health view.

This paper describes a Monte Carlo (MC) based approach for reconstructing missing information in a dataset

In general, two approaches have been followed so far in gas turbine maintenance procedures to determine correct inspection intervals: “no interdependency” or “interdependency” between number of starts and number of running hours. The first approach is based on the assumption that starts and running hours induce different deterioration processes not correlated to each other. Accordingly, the number of starts defines the life limit for cyclic duty operation where low-cycle fatigue phenomena dominate, while the number of running hours define the continuous operation life limit for which erosion, corrosion and creep are controlling factors. The “interdependency” approach instead assumes that failure is produced by combination of low-cycle fatigue and continuous degradation mechanisms: in this scheme the frequency of starts becomes a fundamental parameter in order to determine the optimal maintenance interval. A statistical and reliability engineering methodology to validate the first or rather the second line of action is described in the paper. The population on which the study was conducted is made up by GE Oil & Gas PGT10 gas turbines that are in operation worldwide with fleet operation totaling 1,5 million hours. Most of the cases examined consist of mechanical drive applications for natural gas production, storage and transportation, with significant combination of both intermittent and continuous operation. Hot gas path components have been chosen for examination in consideration of their sensitivity to effects of both cyclic fatigue stress and wear mechanisms. The analysis concentrates on transition piece and combustion liner, both having scored a number of failures statistically significant for the purposes of this study. This analysis is considered the key to optimize inspection intervals and therefore achieve extended machine life. The methodology, based on Weibull data analysis, has been applied to a restricted sample of machines that operate in “standard” conditions, corresponding to gas fuel utilization, mechanical drive service with homogeneous load factor and very low number of trips. The study shows that interdependency between starts and running hours does exist and, given the number of starts, the corresponding running hours can be evaluated, and the inspection intervals appropriately predicted. Further developments of this study will be aimed at evaluating maintenance factors for “non standard” conditions such as dual fuel combustion systems, generator drive and operation with higher number of trips etc.