Long Short-Term Memory Network-Based Normal Pattern Group for Fault Detection of Three-Shaft Marine Gas Turbine

Fault detection and diagnosis can improve safety and reliability of gas turbines. Current studies on gas turbine fault detection and diagnosis mainly focus on the case of abundant fault samples. However, fault data are rare or even unavailable for gas turbines, especially newly-run gas turbines. Aiming to realize fault detection with only normal data, this paper proposes the concept of normal pattern group. A group of long-short term memory (LSTM) networks are first used for characterizing the mapping relationships among measurable parameters of healthy three-shaft gas turbines. Experiments show that the proposed method can detect all 13 common gas path faults of three-shaft gas turbines sensitively while remaining low false alarm rate. Comparison experiment with single normal pattern model verifies the necessaries and superiorities of using normal pattern group. Meanwhile, comparison between LSTM network and other methods including support vector regression, single-layer feedforward neural network, extreme learning machine and Elman recurrent neural network verifies the superiorities of LSTM network in fault detection. Furthermore, comparison experiment with four common one-class classifiers further verifies the superiorities of the proposed method. This also indicates the superiorities of data-driven methods and gas turbine principle fusion to some extent.

Automated summary

The study introduces the concept of normal pattern group for gas turbine fault detection using only normal data. By characterizing the mapping relationships among measurable parameters with long-short term memory networks, all 13 common faults of three-shaft gas turbines were detected sensitively, demonstrating the superiority of the proposed method. The comparison with other methods and classifiers further validates the superior performance of the data-driven approach and gas turbine principle fusion.