An Ensemble Learning-Based Remaining Useful Life Prediction Method for Aircraft Turbine Engine

Zeng, Jiyan; Cheng, Yujie

doi:10.1016/j.ifacol.2020.11.009

Cited by 16 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic structure of SAE is an AE, which is trained to copy its input to its output. 20 The AE includes the encoder and the decoder. In the encoder network, the condition monitoring signal x = [ x 1 , x 2 , …, x m ] is transformed into the low-dimensional hidden feature h = [ h 1 , h 2 , …, h n ] as follow:…”

Section: Basic Theorymentioning

confidence: 99%

Section: Basic Theorymentioning

confidence: 99%

“…In the field of reliability, ensemble learning is also widely used. Zeng and Cheng 20 proposed an ensemble learning method to predict RUL. SAE, LSTM, and convolutional neural network (CNN) are combined to predict the RUL of aircraft engines in this method, and the weight required for each algorithm is allocated according to the Euclidean distance.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An ensemble deep autoencoders based on asymmetric structure for operational reliability assessment of bearings

Jin

Yang

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

At present, with the rapid growth of manufacturing and big data, reliability technology has gradually become a topical issue in the industrial field. Aiming at the operation reliability assessment of rolling bearings, this paper proposes a bearings operational reliability assessment using an ensemble deep autoencoder based on asymmetric structure. In this method, an ensemble deep autoencoder is used to adaptively learn degradation features from condition monitoring data, where the ensemble deep autoencoder adopts an asymmetric structure with different activation functions in the encoder and decoder. Then, the learned features are classified by correlation analysis, and the typical features in each category are selected. Finally, the operation reliability of rolling bearings is evaluated through the definition of reliability based on Mahalanobis distance. Through the example evaluation of rolling bearing operation reliability and comparison with other feature extraction methods, it can be concluded that this method has stronger feature extraction ability and can effectively show the trend of bearing degradation.

show abstract

Section: Basic Theorymentioning

confidence: 99%

Section: Basic Theorymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An ensemble deep autoencoders based on asymmetric structure for operational reliability assessment of bearings

Jin

Yang

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…However, this method lacks accuracy due to limited consideration of external factors and real operating conditions. Polynomial approximation of bench test results is another approach [18,19], requiring extensive data and resulting in a cumbersome model when different operating modes are approximated separately. Due to how costly, limited, and noisy experimental data are, fuzzy inference systems [20,21] and neural networks [22,23] are effective.…”

Section: Introductionmentioning

confidence: 99%

Neural Network Approximation of Helicopter Turboshaft Engine Parameters for Improved Efficiency

Vladov,

Yakovliev,

Bulakh

et al. 2024

Energies

View full text Add to dashboard Cite

The work is devoted to the development of a method for neural network approximation of helicopter turboshaft engine parameters, which is the basis for researching engine energy characteristics to improve efficiency, reliability, and flight safety. It is proposed to use a three-layer direct propagation neural network with linear neurons in the output layer for training in which the scale conjugate gradient algorithm is modified by introducing a moment coefficient into the analytical expression. This modification helps in calculating new model parameters to avoid falling into a local minimum. The dependence of the energy released during helicopter turboshaft engine compressor rotation on the gas-generator rotor r.p.m. was obtained. This enables the determination of the optimal gas-generator rotor r.p.m. region for a specific type of helicopter turboshaft engine. The optimal ratio of energy consumption and compressor operating efficiency is achieved, thereby ensuring helicopter turboshaft engines’ optimal performance and reliability. Experimental data support the high efficiency of using a three-layer feed-forward neural network with linear neurons in the output layer, trained using a modified scale conjugate gradient algorithm, for approximating parameters of helicopter turboshaft engines compared to the analogues. Specifically, this method better predicts the relations between the energy release during compressor rotation and gas-generator rotor r.p.m. The efficiency coefficient of the proposed method was 0.994, which exceeded that of the closest analogue (0.914) by 1.09 times.

show abstract

“…Zhao et al used the extreme learning machine (ELM) to diagnose mechanical cross-domain faults [13]. Zeng et al proposed a method based on the ensemble learning [14]. Wang et al presented a memory-enhanced hybrid deep learning network (MEHDLN) combining CNN and RNN [15].…”

Section: Introductionmentioning

confidence: 99%

Attention-based Dual-channel Deep Neural Network For Aero-engine RUL Prediction Under Time-varying Operating Conditions

Zhao¹,

Zou²

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

For complex systems such as aerospace, remaining useful life (RUL) prediction is a general technique that provides information for decision-making in predictive maintenance. In the industrial field, RUL prediction under time-varying operating conditions is a challenging task. In this paper, an attention-based dual-channel deep neural network is proposed to fuse the time-varying operating conditions, with both prediction channels using long short-term memory (LSTM) neural networks. First, the features are extracted by a one-dimensional convolutional neural network (CNN). The operating conditions and sensor data are put into the dual-channel LSTM neural networks separately for prediction. The obtained results are combined with the attention mechanism to assign weights and finally put into the fully connected network for linear mapping to get the final RUL prediction results. This study is based on the N-CMAPSS dataset published by NASA. Compared with traditional methods, this method demonstrates its superiority and effectiveness.

show abstract

An Ensemble Learning-Based Remaining Useful Life Prediction Method for Aircraft Turbine Engine

Cited by 16 publications

References 8 publications

An ensemble deep autoencoders based on asymmetric structure for operational reliability assessment of bearings

An ensemble deep autoencoders based on asymmetric structure for operational reliability assessment of bearings

Neural Network Approximation of Helicopter Turboshaft Engine Parameters for Improved Efficiency

Attention-based Dual-channel Deep Neural Network For Aero-engine RUL Prediction Under Time-varying Operating Conditions

Contact Info

Product

Resources

About