In June 2005 1,2 , Naval Surface Warfare Center (NSWC) Gas Turbine Emerging Technologies conducted testing on a General Electric LM2500 gas turbine engine. This engine is the main propulsor for DDG-51 and CG-47 class United States Navy surface ships. The purpose of this testing was to induce compressor stall in order to evaluate existing algorithms for stall prediction and gather data for further algorithm development. In addition to existing sensor data, dynamic pressure sensors, with data rates ranging from 20-1000 KHz, were installed in various compressor stages for additional capability. Utilizing the data collected, in conjunction with a MATLAB-based neural network approach, NSWC has developed algorithms to detect and trend stall margin and related quantities that can eventually be used in an early stall warning system onboard ship. Algorithms can be incorporated into the recently installed Full Authority Digital Control, allowing real-time stall detection and prevention. This paper discusses the feasibility of employing a neural network approach to detect and output a compressor stall margin value and associated risk of compressor stall for U.S. Navy LM2500 gas turbine engines TABLE OF CONTENTS 1. INTRODUCTION.

The benefits of utilizing Condition Based Maintenance (CBM) over a time based preventative approach to reduce life cycle costs has been well documented over the years. The U.S. Navy has been working through several separate programs, such as Smartship, Integrated Condition Assessment System (ICAS), Accelerated Capabilities Initiative (ACI), to develop this technology for use in the fleet. Recently, an effort was initiated to coordinate these programs in an application on marine gas turbines. This paper describes the phased process of CBM implementation on marine gas turbines and the resulting benefits of reduced life cycle costs and condition based engineering plant alignment.

This paper details the on-going effort of NAVSEA Philadelphia to provide a command and control technology upgrade to the Model 139 Gas Turbine Generator Set, while deploying a novel approach to this process using Open System Architecture Condition Based Maintenance (OSA-CBM) archetype. The long-term goal of the process being implemented is to serve as the foundation for a communication and interfacing standardization for the marine gas turbine (GT) community. The topics to be discussed in this essay span from investigation to a proposed design, which includes physical measurement of parameters, sensor-Full Authority Digital Controller (FADC) interfacing, and overall system architecture.

As part of the Naval gas turbine CBM effort, diagnostic and prognostic algorithms that utilize state-of-the-art probabilistic modeling and analysis technologies are being developed and implemented onboard Navy ships. The algorithms under development and testing will enhance gas turbine preventative maintenance in such areas as compressor on-line/crank wash and fuel nozzle replacement. In one application, the prognostic module assesses and predicts compressor performance degradation due to salt ingestion. From this information, the optimum time for on-line water washing or crank washing can be determined from a cost/benefit standpoint. A second application diagnoses the severity of fuel nozzle fouling in real-time during startup. This paper discusses the diagnostic and prognostic modeling approaches to these maintenance issues and their implementation for an Allison 501-K34 gas turbine engine onboard a DDG 51 class guided missile destroyer.

The Naval Surface Warfare Center Gas Turbine Emerging Technologies section conducted land-based testing on a gas turbine generator set in December 2003. The purpose of this testing, which was conducted on a Rolls Royce/Allison 501-K17 gas turbine, was to collect data that could be used to improve a previously developed computer program for predicting optimal compressor wash time intervals. For the purpose of Phase I of this testing, fouling was accomplished by injecting salt into the gas turbine inlet air stream. Phase II of this testing will consist of fouling the middle and back regions of the compressor. Influence coefficients can then be developed for each of these regions indicating how a given region affects overall performance. Typically, in a marine environment, fouling of the front stages occurs due to ingested salt while fouling in middle and rear regions occurs from a combination of ingested salt and oil seal leakage. A number of sensors, including compressor inlet and discharge condition probes, bleed air flow and fuel flow meters, were added in order to monitor engine performance during the testing. In addition, hardware was added to both ingest and monitor the concentration of salt in gas turbine inlet air. For Phase II testing, middle and rear stages of the 14-stage compressor shall be accessed through existing 5th and 10th stage bleed ports. A salt solution will be physically applied to the blades while the compressor is rotated by hand. Results from Phase I indicate that front stage compressor fouling causes a clear increase in inlet static pressure. This is due to the mass flow restriction through the compressor. Additional results are currently being summarized, and data is being utilized to improve the 501-K17 compressor wash prognostics algorithm previously noted.