Polynomials and Neural Networks for Gas Turbine Monitoring: a Comparative Study

Abstract

Gas turbine health monitoring includes the common stages of problem detection, fault identification, and prognostics. To extract useful diagnostic information from raw recorded data, these stages require a preliminary operation of computing differences between measurements and an engine baseline, which is a function of engine operating conditions. These deviations of measured values from the baseline data can be good indicators of engine health. However, their quality and the success of all diagnostic stages strongly depend on the adequacy of the baseline model employed and, in particular, on the mathematical techniques applied to create it.To create a baseline model, we have applied polynomials and the least squares method for computing the coefficients over a long period of time. Methods were proposed to enhance such a polynomial-based model. The resulting accuracy was sufficient for reliable monitoring of gas turbine deterioration effects. The polynomials previously investigated thus far are used in the present study as a standard for evaluating artificial neural networks, a very popular technique in gas turbine diagnostics. The focus of this comparative study is to verify whether the use of networks results in a better description of the engine baseline. Extensive field data for two different industrial gas turbines were used to compare these two techniques under various conditions. The deviations were computed for all available data, and the quality of the resulting deviation plots was compared visually. The mean error of the baseline model was used as an additional criterion for comparing the techniques. To find the best network configurations, many network variations were realised and compared with the polynomials. Although the neural networks studied were found to be close to the polynomials in accuracy, they did not exceed the polynomials in any variation. In this way, it seems that polynomials can be successfully used for engine monitoring, at least for the gas turbines analysed herein.

Estimation and monitoring of unmeasured gas turbine variables

“…For the "No noise" scheme, the input data is ideally accurate, and 0 Z ε is an approximation error. It varies for different variables, but its level is comparable to the errors of the baseline for measured variables (Loboda and Feldshteyn 2011). The error 04 Z ε is very small (corresponds to a computer error) because the variable 4 Z (high pressure turbine efficiency) is constant at baseline conditions.…”

Gas Turbine Diagnostic Algorithm Testing Using the Software ProDiMES

“…Three variations are proposed using simulated data with no-fault scenarios through ProDiMES and the model with the lowest total error is selected for the fault recognition stage. A baseline model can be developed based on a thermodynamic model or artificial neural networks (Loboda and Feldshteyn, 2010). The first option needs complex algorithms while the second one requires considerable execution time for training.…”

Research on Method for Monitoring Service Life of Hot-End Components in Gas Turbine based on Condition Analysis

“…The two standard methods use directly engine data for condition monitoring, however these methods can be sensitive to the quality and quantity of example data. Some advanced methods for turbine engine condition monitoring were brought out, such as CASE-based reasoning, the expert systems with fuzzy logic rules and neural network methods [4][5][6][7]. However, the CASE-based reasoning approach was limited by the variation in operational behavior between classes of engine, and the expert systems were attempted to improve the generality by the combination of databases from multiple engines.…”