Search

Aiming at the issues of strong noise interference, low fault recognition rate, and weak model generalization in the fault signals of aviation engine hydraulic pipelines, an improved temporal information fusion model for fault diagnosis of the aero-engine hydraulic pipeline was proposed. Firstly, based on the principle of recurrent neural network, the deformation structure of forward and reverse time information fusion was designed, and the time information fusion model of aviation hydraulic pipeline was constructed, and the LeakyReLU function was introduced to improve the model. Then, the measured one-dimensional aviation pipeline time series data set was input into the improved time information fusion model bidirectional recurrent neural network(Bi-RNN) to update the weight parameters. Finally, based on the same measured data set, the proposed improved temporal information fusion model, long short-term memory neural network(LSTM), recurrent neural network(RNN), support vector machine(SVM) and back propagation neural network(BPNN) were respectively input into five fault diagnosis methods for training. The superiority of the proposed method was verified by comparative analysis. The research results indicate that the improved time information fusion method proposed in this article for hydraulic pipeline fault diagnosis has achieved accurate identification of hydraulic pipeline health status and fault status such as cracks and pits, with an accuracy rate of 99.2%. The overall accuracy and comprehensive index F1-sore have been improved by 5.1%. In terms of comprehensive performance, accuracy, and other indicators, it is significantly superior to other fault diagnosis models, providing a new approach for the diagnosis of hydraulic pipeline faults in aviation engines, and has certain engineering application value. [ABSTRACT FROM AUTHOR]

Intelligent diagnosis of faults in an aero-hydraulic pipeline is important for condition monitoring of its systems. However, there are no more qualitative formulas or feature indicators to describe the faults of aero-hydraulic pipelines because of the complexity and diversity of aero-hydraulic pipeline systems, which leads to a very complex pipeline fault mechanism. In addition, although it is well known that the expression of interpretable and representable pipeline intelligent diagnosis models with pipeline fault characteristics are buried in high background noise and strong noise disturbance conditions in practical industrial scenarios, this has yet to be discussed. Inspired by the demand, this paper proposes a novel diagnosis strategy: the 1D-convolutional space-time fusion strategy for aero-engine hydraulic pipelines. Firstly, by optimizing the convolutional neural network and using it to design a one-dimensional convolutional neural network (1DCNN) with a wide input scale to expand the input field of perception, thereby obtaining more comprehensive spatial information of the pipeline data, which can effectively extract richer short sequence features. Secondly, a network of bidirectional gated recurrent Unit (Bi-GRU) is proposed, which integrates a short sequence of high-dimensional features for temporal information fusion, resulting in a certain degree of avoiding memory loss and gradient dispersion caused by the too-large step size. It is demonstrated that, for the noise signal and variable pressure signal, the fault identification accuracy approximated 95.9%, proving the proposed strategy's robustness. By comparing with the other five methods, the proposed strategy has the ability to identify 10 different fault states in the aero-hydraulic pipeline with higher accuracy. [ABSTRACT FROM AUTHOR]

Intelligent diagnosis of faults in an aero-hydraulic pipeline is important for condition monitoring of its systems. However, there are no more qualitative formulas or feature indicators to describe the faults of aero-hydraulic pipelines because of the complexity and diversity of aero-hydraulic pipeline systems, which leads to a very complex pipeline fault mechanism. In addition, although it is well known that the expression of interpretable and representable pipeline intelligent diagnosis models with pipeline fault characteristics are buried in high background noise and strong noise disturbance conditions in practical industrial scenarios, this has yet to be discussed. Inspired by the demand, this paper proposes a novel diagnosis strategy: the 1D-convolutional space-time fusion strategy for aero-engine hydraulic pipelines. Firstly, by optimizing the convolutional neural network and using it to design a one-dimensional convolutional neural network (1DCNN) with a wide input scale to expand the input field of perception, thereby obtaining more comprehensive spatial information of the pipeline data, which can effectively extract richer short sequence features. Secondly, a network of bidirectional gated recurrent Unit (Bi-GRU) is proposed, which integrates a short sequence of high-dimensional features for temporal information fusion, resulting in a certain degree of avoiding memory loss and gradient dispersion caused by the too-large step size. It is demonstrated that, for the noise signal and variable pressure signal, the fault identification accuracy approximated 95.9%, proving the proposed strategy’s robustness. By comparing with the other five methods, the proposed strategy has the ability to identify 10 different fault states in the aero-hydraulic pipeline with higher accuracy.