A Novel Gas Path Fault Diagnostic Model for Gas Turbine Based on Explainable Convolutional Neural Network With LIME Method

2021 ◽  
Author(s):  
Chen Yao ◽  
Xi Yueyun ◽  
Chen Jinwei ◽  
Zhang Huisheng
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Gas Turbine ◽  
Data Driven ◽  
Diagnostic Model ◽  
Input Matrix ◽  
Diagnosis Model ◽  
Fault Diagnostic ◽  
Gas Path Fault

Abstract Gas turbine is widely used in aviation and energy industries. Gas path fault diagnosis is an important task for gas turbine operation and maintenance. With the development of information technology, especially deep learning methods, data-driven approaches for gas path diagnosis are developing rapidly in recent years. However, the mechanism of most data-driven models are difficult to explain, resulting in lacking of the credibility of the data-driven methods. In this paper, a novel explainable data-driven model for gas path fault diagnosis based on Convolutional Neural Network (CNN) using Local Interpretable Model-agnostic Explanations (LIME) method is proposed. The input matrix of CNN model is established by considering the mechanism information of gas turbine fault modes and their effects. The relationship between the measurement parameters and fault modes are considered to arrange the relative position in the input matrix. The key parameters which contributes to fault recognition can be achieved by LIME method, and the mechanism information is used to verify the fault diagnostic proceeding and improve the measurement sensor matrix arrangement. A double shaft gas turbine model is used to generate healthy and fault data including 12 typical faults to test the model. The accuracy and interpretability between the CNN diagnosis model built with prior mechanism knowledge and built by parameter correlation matrix are compared, whose accuracy are 96.34% and 89.46% respectively. The result indicates that CNN diagnosis model built with prior mechanism knowledge shows better accuracy and interpretability. This method can express the relevance of the failure mode and its high-correlation measurement parameters in the model, which can greatly improve the interpretability and application value.

scholarly journals Fault Diagnosis of Rotary Machines Using Deep Convolutional Neural Network with Wide Three Axis Vibration Signal Input

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 4017 ◽  
Author(s):  
Davor Kolar ◽  
Dragutin Lisjak ◽  
Michał Pająk ◽  
Danijel Pavković
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Input Matrix ◽  
Accelerometer Signal ◽  
Rotary Machinery ◽  
Signal Input

Fault diagnosis is considered as an essential task in rotary machinery as possibility of an early detection and diagnosis of the faulty condition can save both time and money. This work presents developed and novel technique for deep-learning-based data-driven fault diagnosis for rotary machinery. The proposed technique input raw three axes accelerometer signal as high definition 1D image into deep learning layers which automatically extract signal features, enabling high classification accuracy. Unlike the researches carried out by other researchers, accelerometer data matrix with dimensions 6400 × 1 × 3 is used as input for convolutional neural network training. Since convolutional neural networks can recognize patterns across input matrix, it is expected that wide input matrix containing vibration data should yield good classification performance. Using convolutional neural networks (CNN) trained model, classification in one of the four classes can be performed. Additionally, number of kernels of CNN is optimized using grid search, as preliminary studies show that alternating number of kernels impacts classification results. This study accomplished the effective classification of different rotary machinery states using convolutional artificial neural network for classification of raw three axis accelerometer signal input.

scholarly journals Design and Analysis for Early Warning of Rotor UAV Based on Data-Driven DBN

Electronics ◽  
2019 ◽  
Vol 8 (11) ◽  
pp. 1350 ◽  
Author(s):  
Chen ◽  
Wu ◽  
Wu ◽  
Xiong ◽  
Han ◽  
...  
Keyword(s):  
Neural Network ◽  
Control System ◽  
Fault Diagnosis ◽  
Early Warning ◽  
Flight Control ◽  
Data Driven ◽  
Diagnostic Model ◽  
Flight Control System ◽  
Model Based ◽  
On Line

The unmanned aerial vehicle (UAV), which is a typical multi-sensor closed-loop flight control system, has the properties of multivariable, time-varying, strong coupling, and nonlinearity. Therefore, it is very difficult to obtain an accurate mathematical diagnostic model based on the traditional model-based method; this paper proposes a UAV sensor diagnostic method based on data-driven methods, which greatly improves the reliability of the rotor UAV nonlinear flight control system and achieves early warning. In order to realize the rapid on-line fault detection of the rotor UAV flight system and solve the problems of over-fitting, limited generalization, and long training time in the traditional shallow neural network for sensor fault diagnosis, a comprehensive fault diagnosis method based on deep belief network (DBN) is proposed. Using the DBN to replace the shallow neural network, a large amount of off-line historical sample data obtained from the rotor UAV are trained to obtain the optimal DBN network parameters and complete the on-line intelligent diagnosis to achieve the goal of early warning as possible as quickly. In the end, the two common faults of the UAV sensor, namely the stuck fault and the constant deviation fault, are simulated and compared with the back propagation (BP) neural network model represented by the shallow neural network to verify the effectiveness of the proposed method in the paper.

Bearing fault diagnosis employing Gabor and augmented architecture of convolutional neural network

2019 ◽  
Vol 13 (3) ◽  
pp. 5689-5702
Author(s):  
N. Fathiah Waziralilah ◽  
Aminudin Abu ◽  
M. H. Lim ◽  
Lee Kee Quen ◽  
Ahmed Elfakarany
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Image Representation ◽  
Gabor Transform ◽  
Spatial Awareness ◽  
Bearing Fault ◽  
Vibration Data ◽  
Bearing Fault Diagnosis ◽  
Diagnosis Model

The vast impact on machinery that is rooted by bearing degradation thus pinpointing bearing fault diagnosis as indubitably very crucial. The research is innovated to diagnose the fault in bearing by implementing deep learning approach which is Convolutional Neural Network (CNN) that has superiority over image processing and pattern recognition. A novel model comprises of Gabor Transform and CNN is proposed whereby Gabor Transform is utilized in representing the raw vibration signals into its image representation. The CNN architecture is augmented for a better accuracy of the bearing fault diagnosis model. To date, the method combination has never been deployed in establishing fault diagnosis model. Plus, the usage of Gabor Transform in mechanical area especially in bearing fault diagnosis is meagrely reported. Scant researches in mechanical diagnosis are dedicated to work on the image representation of the vibration data whereas the CNN works better when fed by images input due to its unique strength of CNN in images processing and spatial awareness. At the end of the research, it is perceived that the proposed model comprises of Gabor Transform and CNN can diagnose the bearing faults with 100% accuracy and perform better than when CNN is fed with raw signals.

scholarly journals Research on Gas-Path Fault-Diagnosis Method of Marine Gas Turbine Based on Exergy Loss and Probabilistic Neural Network

Energies ◽  
2019 ◽  
Vol 12 (24) ◽  
pp. 4701 ◽  
Author(s):  
Yunpeng Cao ◽  
Xinran Lv ◽  
Guodong Han ◽  
Junqi Luan ◽  
Shuying Li
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Gas Turbine ◽  
Probabilistic Neural Network ◽  
Second Law Of Thermodynamics ◽  
Fault Detection And Isolation ◽  
Exergy Loss ◽  
Diagnosis Method ◽  
Gas Path Fault ◽  
Faulty Component

In order to improve the accuracy of gas-path fault detection and isolation for a marine three-shaft gas turbine, a gas-path fault diagnosis method based on exergy loss and a probabilistic neural network (PNN) is proposed. On the basis of the second law of thermodynamics, the exergy flow among the subsystems and the external environment is analyzed, and the exergy model of a marine gas turbine is established. The exergy loss of a marine gas turbine under the healthy condition and typical gas-path faulty condition is analyzed, and the relative change of exergy loss is used as the input of the PNN to detect the gas-path malfunction and locate the faulty component. The simulation case study was conducted based on a three-shaft marine gas turbine with typical gas-path faults. Several results show that the proposed diagnosis method can accurately detect the fault and locate the malfunction component.

scholarly journals A Text-Driven Aircraft Fault Diagnosis Model Based on a Word2vec and Priori-Knowledge Convolutional Neural Network

Aerospace ◽  
2021 ◽  
Vol 8 (4) ◽  
pp. 112
Author(s):  
Zhenzhong Xu ◽  
Bang Chen ◽  
Shenghan Zhou ◽  
Wenbing Chang ◽  
Xinpeng Ji ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Prior Knowledge ◽  
Text Data ◽  
Proposed Model ◽  
Text Feature ◽  
Civil Aircraft ◽  
Diagnosis Model ◽  
Validation Experiments

In the process of aircraft maintenance and support, a large amount of fault description text data is recorded. However, most of the existing fault diagnosis models are based on structured data, which means they are not suitable for unstructured data such as text. Therefore, a text-driven aircraft fault diagnosis model is proposed in this paper based on Word to Vector (Word2vec) and prior-knowledge Convolutional Neural Network (CNN). The fault text first enters Word2vec to perform text feature extraction, and the extracted text feature vectors are then input into the proposed prior-knowledge CNN to train the fault classifier. The prior-knowledge CNN introduces expert fault knowledge through Cloud Similarity Measurement (CSM) to improve the performance of the fault classifier. Validation experiments on five-year maintenance log data of a civil aircraft were carried out to successfully verify the effectiveness of the proposed model.

Sign in / Sign up

Export Citation Format

Share Document