**10. References**

Aretakis, N.; Mathioudakis, K. & Stamatis, A. (2003). Nonlinear engine component fault diagnosis from a limited number of measurements using a combinatorial approach. *Journal of Engineering for Gas Turbines and Power*, Vol.125, Issue 3, (July 2003), pp. 642-650

is verified on maintenance data of the GT1. The comparison of the modified and original identification procedures has shown that the proposed procedure has better properties.

Another way to get more exact estimates is to use the option of the diagnosis at transients and to identify the dynamic model as shown in (Loboda & Hernandez Gonzalez, 2002).

As shown above, the considered system identification-based approach can be realized for the same options as the pattern recognition-based approach. Additionally, the principal problems of the latter (such as inadequacy of the baseline model and inaccurate fault simulation) are also typical for the system identification-based approach. Thus, they are alternative approaches for all steps of a total fault localization process. Furthermore, it can also be demonstrated that with this approaches the stages of fault detection and prognostics can be realized. In this way, we can consider these two approaches as applicable for all gas

The present chapter is devoted to the enhancement of gas path diagnosis reliability. Different approaches are considered and main trends in gas turbine diagnostics are

It was shown that in many cases such convenient ways to enhance the reliability, as choosing the best approximation function and recognition technique as well as tailoring the function and technique, do not yield significant results nowadays. This happens because of

Some new solutions are proposed in the chapter to reduce the gap between simulated diagnostic process and real engine maintenance conditions. Possible error sources are examined in the chapter and some methods are proposed to enhance the deviation accuracy. In addition, new principles are considered to create a more realistic fault classification, for

Among the principal problems to solve in future, insufficient adequacy of the baseline model was detected. The other challenging problem consists in fault simulation inaccuracy. We hope that the observations made in this chapter and the recommendations drawn will help to design and rapidly tailor new gas turbine health monitoring systems. A long list of

The work has been carried out with the support of the National Polytechnic Institute of

Aretakis, N.; Mathioudakis, K. & Stamatis, A. (2003). Nonlinear engine component fault

diagnosis from a limited number of measurements using a combinatorial approach. *Journal of Engineering for Gas Turbines and Power*, Vol.125, Issue 3, (July 2003), pp. 642-650

Such a model can be widely used in monitoring systems as well.

analyzed by the reviewing multiple literature sources.

many investigations already conducted in this area.

example, by generating real error distribution.

references can also be useful for the reader.

Mexico (research project 20113092).

**9. Acknowledgment** 

**10. References** 

path analysis methods.

**8. Conclusion** 


**8** 

*México* 

**Models for Training** 

**on a Gas Turbine Power Plant** 

Edgardo J. Roldán-Villasana and Yadira Mendoza-Alegría

In México, near 15% of the installed electrical energy of CFE, the Mexican Utility Company is based on gas turbine plants. The economical and performance results of a power plant are related to different strategies like modernisation, management, and the training of their

The Advanced Training Systems and Simulation Department (GSACyS) of the Electrical Research Institute (IIE) in México is a group specialised in training simulators that designs and implements tools and methodologies to support the simulators development, exploitation, and maintenance. The GSACyS has developed diverse works related with the training. The main covered areas by the IIE developments are: computer based training

To use real time full scope simulators is one of the most effective and secure way to train power plant operators. According to Hoffman (1995), by using simulators the operators can learn how to operate the power plant more efficiently. In accordance with Fray and Divakaruni (1995), even not full scope simulators are successfully used for operators

Some advantages of using simulators for training are the ability to train on malfunctions, transients and accidents; the reduction of risks of plant equipment and personnel; the ability to train personnel on actual (reproduced) plant events; a broader range of personnel can receive effective training, and eventually, high standard individualised instruction or self-

In the case of simulators, situations "what would have happened if…" arises when a cost benefit analysis is sought. A classical analysis for fuel power plants simulators (Epri, 1993) identified profit of simulators in four classes: availability savings, thermal performance savings, component life savings, and environmental compliance savings. A payback of about three months was estimated. Most often, the justification for acquiring an operators training simulator is based on estimating the reduction in losses (Hosseinpour and Hajihosseini, 2009). It is not difficult to probe the benefits for high-capacity plants where savings means millions of dollars for a few days of un-productivity. Besides, the ability of the simulator to verify the automation system and provide operators with a better

systems, test equipment simulators, and simulators for operators training.

training (with simulation devices planned with these capabilities).

**1. Introduction** 

operators.

training.

*Instituto de Investigaciones Eléctricas, Gerencia de Simulación* 

