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

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

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 fa...

Full description

Bibliographic Details
Main Authors: Zhenzhong Xu, Bang Chen, Shenghan Zhou, Wenbing Chang, Xinpeng Ji, Chaofan Wei, Wenkui Hou
Format: Article
Language:English
Published: MDPI AG 2021-04-01
Series:Aerospace
Subjects:
text-driven
aircraft fault diagnosis
text feature extraction
convolutional neural network
priori knowledge
Online Access:https://www.mdpi.com/2226-4310/8/4/112
id doaj-404d923725f14c19a0cd516273a63238
record_format Article
spelling doaj-404d923725f14c19a0cd516273a632382021-04-14T23:05:04ZengMDPI AGAerospace2226-43102021-04-01811211210.3390/aerospace8040112A Text-Driven Aircraft Fault Diagnosis Model Based on a Word2vec and Priori-Knowledge Convolutional Neural NetworkZhenzhong Xu0Bang Chen1Shenghan Zhou2Wenbing Chang3Xinpeng Ji4Chaofan Wei5Wenkui Hou6Technology Development Department, Avicas Generic Technology Co., LTD, Yangzhou 225000, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaSchool of Reliability and Systems Engineering, Beihang University, Beijing 100191, ChinaIn 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.https://www.mdpi.com/2226-4310/8/4/112text-drivenaircraft fault diagnosistext feature extractionconvolutional neural networkpriori knowledge
collection DOAJ
language English
format Article
sources DOAJ
author Zhenzhong Xu
Bang Chen
Shenghan Zhou
Wenbing Chang
Xinpeng Ji
Chaofan Wei
Wenkui Hou
spellingShingle Zhenzhong Xu
Bang Chen
Shenghan Zhou
Wenbing Chang
Xinpeng Ji
Chaofan Wei
Wenkui Hou
A Text-Driven Aircraft Fault Diagnosis Model Based on a Word2vec and Priori-Knowledge Convolutional Neural Network
Aerospace
text-driven
aircraft fault diagnosis
text feature extraction
convolutional neural network
priori knowledge
author_facet Zhenzhong Xu
Bang Chen
Shenghan Zhou
Wenbing Chang
Xinpeng Ji
Chaofan Wei
Wenkui Hou
author_sort Zhenzhong Xu
title A Text-Driven Aircraft Fault Diagnosis Model Based on a Word2vec and Priori-Knowledge Convolutional Neural Network
title_short A Text-Driven Aircraft Fault Diagnosis Model Based on a Word2vec and Priori-Knowledge Convolutional Neural Network
title_full A Text-Driven Aircraft Fault Diagnosis Model Based on a Word2vec and Priori-Knowledge Convolutional Neural Network
title_fullStr A Text-Driven Aircraft Fault Diagnosis Model Based on a Word2vec and Priori-Knowledge Convolutional Neural Network
title_full_unstemmed A Text-Driven Aircraft Fault Diagnosis Model Based on a Word2vec and Priori-Knowledge Convolutional Neural Network
title_sort text-driven aircraft fault diagnosis model based on a word2vec and priori-knowledge convolutional neural network
publisher MDPI AG
series Aerospace
issn 2226-4310
publishDate 2021-04-01
description 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.
topic text-driven
aircraft fault diagnosis
text feature extraction
convolutional neural network
priori knowledge
url https://www.mdpi.com/2226-4310/8/4/112
work_keys_str_mv AT zhenzhongxu atextdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT bangchen atextdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT shenghanzhou atextdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT wenbingchang atextdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT xinpengji atextdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT chaofanwei atextdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT wenkuihou atextdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT zhenzhongxu textdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT bangchen textdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT shenghanzhou textdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT wenbingchang textdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT xinpengji textdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT chaofanwei textdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
AT wenkuihou textdrivenaircraftfaultdiagnosismodelbasedonaword2vecandprioriknowledgeconvolutionalneuralnetwork
_version_ 1721526780748103680

Similar Items