Considering the importance of continually improving the algorithms in aircraft engine diagnostic systems, the present paper proposes and benchmarks a gas-path monitoring and diagnostics framework through the Propulsion Diagnostic Methodology Evaluation Strategy (ProDiMES) software developed by NASA. The algorithm uses fleet-average and individual engine baseline models to compute feature vectors that form a fault classification with healthy and faulty engine classes. Using this classification, a hybrid fault-recognition technique based on regularized extreme learning machines and sparse representation classification was trained and validated to perform both fault detection and fault identification as a common process. The performance of the system was analyzed along with the results of other diagnostic frameworks through four stages of comparison based on different conditions, such as operating regimes, testing data, and metrics (detection, classification, and detection latency). The first three stages were devoted to the independent algorithm development and self-evaluation, while the final stage was related to a blind test case evaluated by NASA. The comparative analysis at all stages shows that the proposed algorithm outperforms all other diagnostic solutions published so far. Considering the advantages and the results obtained, the framework is a promising tool for aircraft engine monitoring and diagnostic systems.

The lack of gas turbine field data, especially faulty engine data, and the complexity of fault embedding into gas turbines on test benches cause difficulties in representing healthy and faulty engines in diagnostic algorithms. Instead, different gas turbine models are often used. The available models fall into two main categories: physics-based and data-driven. Given the models’ importance and necessity, a variety of simulation tools were developed with different levels of complexity, fidelity, accuracy, and computer performance requirements. Physics-based models constitute a diagnostic approach known as Gas Path Analysis (GPA). To compute fault parameters within GPA, this paper proposes to employ a nonlinear data-driven model and the theory of inverse problems. This will drastically simplify gas turbine diagnosis. To choose the best approximation technique of such a novel model, the paper employs polynomials and neural networks. The necessary data were generated in the GasTurb software for turboshaft and turbofan engines. These input data for creating a nonlinear data-driven model of fault parameters cover a total range of operating conditions and of possible performance losses of engine components. Multiple configurations of a multilayer perceptron network and polynomials are evaluated to find the best data-driven model configurations. The best perceptron-based and polynomial models are then compared. The accuracy achieved by the most adequate model variation confirms the viability of simple and accurate models for estimating gas turbine health conditions.

The present paper compares the fault recognition capabilities of two gas turbine diagnostic approaches: data-driven and physics-based (a.k.a. gas path analysis, GPA). The comparison takes into consideration two differences between the approaches, the type of diagnostic space and diagnostic decision rule. To that end, two stages are proposed. In the first one, a data-driven approach with an artificial neural network (ANN) that recognizes faults in the space of measurement deviations is compared with a hybrid GPA approach that employs the same type of ANN to recognize faults in the space of estimated fault parameter. Different case studies for both anomaly detection and fault identification are proposed to evaluate the diagnostic spaces. They are formed by varying the classification, type of diagnostic analysis, and deviation noise scheme. In the second stage, the original GPA is reconstructed replacing the ANN with a tolerance-based rule to make diagnostic decisions. Here, two aspects are under analysis: the comparison of GPA classification rules and whole approaches. The results reveal that for simple classifications both spaces are equally accurate for anomaly detection and fault identification. However, for complex scenarios, the data-driven approach provides on average slightly better results for fault identification. The use of a hybrid GPA with ANN for a full classification instead of an original GPA with tolerance-based rule causes an increase of 12.49% in recognition accuracy for fault identification and up to 54.39% for anomaly detection. As for the whole approach comparison, the application of a data-driven approach instead of the original GPA can lead to an improvement of 12.14% and 53.26% in recognition accuracy for fault identification and anomaly detection, respectively.