Igor Loboda

Adaptive Vector Directional Filters to Process Multichannel Images

We present a novel algorithm that can suppress impulsive noise in video colour sequences. It uses order statistics, and directional and adaptive processing techniques.

A Mixed Data-Driven and Model Based Fault Classification for Gas Turbine Diagnosis

In modern gas turbine health monitoring systems, the diagnostic algorithms based on gas path analysis may be considered as principal. They analyze gas path measured variables and are capable of identifying different faults and degradation mechanisms of gas turbine components (e.g. compressor, turbine, and combustor) as well as malfunctions of the measurement system itself. Gas path mathematical models are widely used in building fault classification required for diagnostics because faults rarely occur during field operation. In that case, model errors are transmitted to the model-based classification, which poses the problem of rendering the description of some classes more accurate using real data. This paper looks into the possibility of creating a mixed fault classification that incorporates both model-based and data-driven fault classes. Such a classification will combine a profound common diagnosis with a higher diagnostic accuracy for the data-driven classes. A gas turbine power plant for natural gas pumping has been chosen as a test case. Its real data with cycles of compressor fouling were used to form a data-driven class of the fouling. Preliminary qualitative analysis showed that these data allow creating a representative class of the fouling and that this class will be compatible with simulated fault classes. A diagnostic algorithm was created based on the proposed classification (real class of compressor fouling and simulated fault classes for other components) and artificial neural networks. The algorithm was subjected to statistical testing. As a result, probabilities of a correct diagnosis were determined. Different variations of the classification were considered and compared using these probabilities as criteria. The performed analysis has revealed no limitations for realizing a principle of the mixed classification in real monitoring systems.Copyright

Gas Turbine Diagnostics

A gas turbine engine can be considered as a very complex and expensive mechanical system; furthermore, its failure can cause catastrophic consequences. That is why it is desirable to provide the engine by an effective condition monitoring system. Such an automated system based on measured parameters performs monitoring and diagnosis of the engine without the need of its shutdown and disassembly. In order to improve gas turbine reliability and reduce maintenance costs, many advanced monitoring systems have been developed recent decades. Design and use of these systems were spurred by the progress in instrumentation, communication techniques, and computer technology. In fact, development and use of such systems has become today a standard practice for new engines.

Gas Turbine Fault Diagnosis Using Probabilistic Neural Networks

Abstract Efficiency of gas turbine monitoring systems primarily depends on the accuracy of employed algorithms, in particular, pattern classification techniques for diagnosing gas path faults. In recent investigations many techniques have been applied to classify gas path faults, but recommendations for selecting the best technique for real monitoring systems are still insufficient and often contradictory. In our previous work, three classification techniques were compared under different conditions of gas turbine diagnosis. The comparative analysis has shown that all these techniques yield practically the same accuracy for each comparison case. The present contribution considers a new classification technique, Probabilistic Neural Network (PNN), and we compare it with the techniques previously examined. The results for all comparison cases show that the PNN is not inferior to the other techniques. We recommend choosing the PNN for real monitoring systems because it has an important advantage of providing confidence estimation for every diagnostic decision made.

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.

Diagnostic Analysis of Maintenance Data of a Gas Turbine for Driving an Electric Generator

Monitoring algorithms analyzing measured gas path variables provide invaluable insight into gas turbine operating health. Some useful information about a gas turbine and its measurement system can be obtained from a direct analysis of raw measurements. To draw more comprehensive diagnostic information, deviations are usually calculated as discrepancies between the measured and baseline values of monitored variables. The deviations can serve as good indicators of different engine degradation mechanisms. However, there are many negative factors that tend to mask degradation effects. For a long period of time we have analyzed quality of gas path measurement data and a deviation accuracy problem of a gas turbine power plant driving a natural gas pipeline compressor. Possible error sources were examined and some methods were proposed to improve the accuracy of deviation calculations. This paper looks at maintenance data of another object, the General Electric LM2500 gas turbine used as a drive of an electric generator. The data cover prolonged periods of axial compressor fouling with washings between them, and provide valuable information for a deviation examination. In order to reduce deviation errors, the paper considers different cases of the abnormal functioning of the sensors and baseline model inadequacy and proposes measures to avoid them. As a result of these and previous efforts, the deviations have become good fouling indicators. They are capable to quantify the increase of exhaust gas temperature (EGT) and, consequently, to improve planning axial compressor washings.Copyright

A Generalized Fault Classification for Gas Turbine Diagnostics at Steady States and Transients

Gas turbine diagnostic techniques are often based on the recognition methods using the deviations between actual and expected thermodynamic performances. The problem is that the deviations generally depend on current operational conditions. However, our studies show that such a dependency can be low. In this paper, we propose a generalized fault classification that is independent of the operational conditions. To prove this idea, the probabilities of true diagnosis were computed and compared for two cases: the proposed classification and the conventional one based on a fixed operating point. The probabilities were calculated through a stochastic modeling of the diagnostic process. In this process, a thermodynamic model generates deviations that are induced by the faults, and an artificial neural network recognizes these faults. The proposed classification principle has been implemented for both steady state and transient operation of the analyzed gas turbine. The results show that the adoption of the generalized classification hardly affects diagnosis trustworthiness and the classification can be proposed for practical realization.

An Integrated Approach to Gas Turbine Monitoring and Diagnostics

This paper presents an investigation of a conventional gas turbine diagnostic process and its generalization. A usual sequence of diagnostic actions consists of two stages: monitoring (fault detection) and subsequent proper diagnosis (fault identification). Such an approach neither implies fault identification nor uses the information about incipient faults unless the engine is recognized as faulty. In previous investigations for engine steady state operation conditions we addressed diagnostics problems without their relation with the monitoring process. Fault classes were given by samples of patterns generated by a static gas turbine performance model. This fault simulation took into account faults of varying severity including incipient ones. A diagnostic algorithm employed artificial neural networks to identify an actual fault. In the present paper we consider the monitoring and diagnosis as joint processes extending our previous approach over both of them. It is proposed to form two classes for the monitoring using the above-mentioned classes constructed for the diagnosis. A two-shaft industrial gas turbine has been chosen to test the proposed integrated approach to monitoring and diagnosis. A general recommendation following from the presented investigation is to identify faults simultaneously with fault detection. This permits accumulating preliminary diagnoses before the engine faulty condition is detected and a rapid final diagnosis after the fault detection.Copyright

3D vector directional filters to process video sequences

We present novel algorithms to suppress impulsive noise in video color sequences. They use order statistics, directional and adaptive processing techniques. Extensive simulation results in known reference video color sequences have demonstrated that the proposed filters consistently outperform other filters by balancing the tradeoff between noise suppression, detail preservation, and chromaticity characteristics. The criteria used to compare the performance or various filters were the PSNR, MAE, and NCD.

Gas Turbine Fault Classification Using Probability Density Estimation

Diagnostics is an important aspect of a condition based maintenance program. To develop an effective gas turbine monitoring system in short time, the recommendations on how to optimally design every system algorithm are required. This paper deals with choosing a proper fault classification technique for gas turbine monitoring systems.To classify gas path faults, different artificial neural networks are typically employed. Among them the Multilayer Perceptron (MLP) is the mostly used. Some comparative studies referred to in the introduction show that the MLP and some other techniques yield practically the same classification accuracy on average for all faults. That is why in addition to the average accuracy, more criteria to choose the best technique are required. Since techniques like Probabilistic Neural Network (PNN), Parzen Window (PW) and k-Nearest Neighbor (K-NN) provide a confidence probability for every diagnostic decision, the presence of this important property can be such a criterion. The confidence probability in these techniques is computed through estimating a probability density for patterns of each concerned fault class.The present study compares all mentioned techniques and their variations using as criteria both the average accuracy and availability of the confidence probability. To compute them for each technique, a special testing procedure simulates numerous diagnosis cycles corresponding to different fault classes and fault severities. In addition to the criteria themselves, criteria imprecision due to a finite number of the diagnosis cycles is computed and involved into selecting the best technique.Copyright