scholarly journals A Text-Driven Aircraft Fault Diagnosis Model Based on Word2vec and Stacking Ensemble Learning

Aerospace ◽  
2021 ◽  
Vol 8 (12) ◽  
pp. 357
Author(s):  
Shenghan Zhou ◽  
Chaofan Wei ◽  
Pan Li ◽  
Anying Liu ◽  
Wenbing Chang ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Ensemble Learning ◽  
Structured Data ◽  
Unstructured Data ◽  
Aircraft Maintenance ◽  
Text Data ◽  
Text Feature ◽  
Diagnosis Accuracy ◽  
Diagnosis Model ◽  
Support Work

Traditional aircraft maintenance support work is mainly based on structured data. Unstructured data, such as text data, have not been fully used, which means there is a waste of resources. These unstructured data contain a great storehouse of fault knowledge, which could provide decision support for aircraft maintenance support work. Therefore, a text-based fault diagnosis model is proposed in this paper. The proposed method uses Word2vec to map text words into vector space, and the extracted text feature vectors are then input into the classifier based on a stacking ensemble learning scheme. Its performance has been validated using a real aircraft fault text dataset. The results show that the fault diagnosis accuracy of the proposed method is 97.35%, which is about 2% higher than that of the suboptimal method.

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.

Optimal multi-kernel local fisher discriminant analysis for feature dimensionality reduction and fault diagnosis

2021 ◽  
pp. 1748006X2110093
Author(s):  
Qing Zhang ◽  
Heng Li ◽  
Xiaolong Zhang ◽  
Haifeng Wang
Keyword(s):  
Fault Diagnosis ◽  
Discriminant Analysis ◽  
Feature Space ◽  
High Dimensional ◽  
Fisher Discriminant Analysis ◽  
Vibration Signals ◽  
Fisher Discriminant ◽  
Local Fisher Discriminant Analysis ◽  
Diagnosis Accuracy ◽  
Diagnosis Model

To achieve a more desirable fault diagnosis accuracy by applying multi-domain features of vibration signals, it is significative and challenging to refine the most representative and intrinsic feature components from the original high dimensional feature space. A novel dimensionality reduction method for fault diagnosis is proposed based on local Fisher discriminant analysis (LFDA) which takes both label information and local geometric structure of the high dimensional features into consideration. Multi-kernel trick is introduced into the LFDA to improve its performance in dealing with the nonlinearity of mapping high dimensional feature space into a lower one. To obtain an optimal diagnosis accuracy by the reduced features of low dimensionality, binary particle swarm optimization (BPSO) algorithm is utilized to search for the most appropriate parameters of kernels and K-nearest neighbor (kNN) recognition model. Samples with labels are used to train the optimal multi-kernel LFDA and kNN (OMKLFDA-kNN) fault diagnosis model to obtain the optimal transformation matrix. Consequently, the trained fault diagnosis model implements the recognition of machinery health condition with the most representative feature space of vibration signals. A bearing fault diagnosis experiment is conducted to verify the effectiveness of proposed diagnostic approach. Performance comparison with some other methods are investigated, and the improvement for fault diagnosis of the proposed method are confirmed in different aspects.

Ensemble Learning-Based Pulse Signal Classification (Preprint)

2021 ◽  
Author(s):  
Jianjun Yan ◽  
Xianglei Cai ◽  
Songye Chen ◽  
Rui Guo ◽  
Haixia Yan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ensemble Learning ◽  
Time Domain ◽  
Pulse Signal ◽  
Frequency Domain Analysis ◽  
Structured Data ◽  
Unstructured Data ◽  
Classification Model ◽  
Signal Classification ◽  
Time Frequency

BACKGROUND In pulse signal analysis and identification, time domain and time-frequency domain analysis methods can obtain interpretable structured data and build classification models using traditional machine learning methods, while unstructured data like pulse signals contain rich information about the state of the cardiovascular system, and local features of unstructured data can be extracted and classified using deep learning. OBJECTIVE The objective of this paper was to comprehensively use machine learning and deep learning classification methods to fully exploit the information of pulse signals. METHODS The structured data is obtained by using time domain and time frequency domain analysis methods, a classification model is built using SVM, the DCNN network convolution kernel is used to extract local features of the unstructured data, a classification model is built, and the Stacking method is used to fuse the above classification results for decision making. RESULTS The highest accuracy of 0.7914 was obtained using only a single classifier, while the accuracy obtained using the ensemble learning approach was 0.8330. CONCLUSIONS Ensemble learning can effectively utilize information from structured and unstructured data to improve classification accuracy through decision-level fusion. This study provides a new idea and method for pulse signal classification, which is of practical value for pulse diagnosis objectification.

Research on Fault Diagnosis of Drive Train in Wind Turbine Based on EMD and LSSVM

2012 ◽  
Vol 512-515 ◽  
pp. 763-770 ◽  
Author(s):  
Hui Liu ◽  
Chao Wang ◽  
Wen Jun Yan
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Wind Turbines ◽  
Extraction Method ◽  
Drive Train ◽  
Support Vector ◽  
Feature Extraction Method ◽  
Mode Decomposition ◽  
Diagnosis Accuracy ◽  
Diagnosis Model

Fault feature extraction method based on Empirical Mode Decomposition (EMD) and fault diagnosis model based on Least Squares Support Vector Machines (LSSVM) were proposed after typical faults in drive train for wind turbines being analyzed. An experiment was designed to verify the validity of feature extraction method and the intelligent diagnosis model. The results showed that EMD can effectively extract fault characteristics of the drive train in wind turbines, the classification speed and diagnosis accuracy of LSSVM classifier based on radial basis function are better than the SVM, BPNN and other classifiers which are commonly used in practice.

scholarly journals Diagnosing post-traumatic stress disorder using electronic medical record data

2021 ◽  
Vol 27 (4) ◽  
pp. 146045822110532
Author(s):  
Hasan Zafari ◽  
Leanne Kosowan ◽  
Farhana Zulkernine ◽  
Alexander Signer
Keyword(s):  
Primary Care ◽  
Post Traumatic Stress Disorder ◽  
Traumatic Stress ◽  
Stress Disorder ◽  
Structured Data ◽  
Unstructured Data ◽  
Post Traumatic Stress ◽  
Data Types ◽  
Text Data ◽  
Post Traumatic

This study proposes a predictive model that uses structured data and unstructured narrative notes from Electronic Medical Records to accurately identify patients diagnosed with Post-Traumatic Stress Disorder (PTSD). We utilize data from primary care clinicians participating in the Manitoba Primary Care Research Network (MaPCReN) representing 154,118 patients. A reference sample of 195 patients that had their PTSD diagnosis confirmed using a manual chart review of structured data and narrative notes, and PTSD negative patients is used as the gold standard data for model training, validation and testing. We assess structured and unstructured data from eight tables in the MaPCReN namely, patient demographics, disease case, examinations, medication, billing records, health condition, risk factors, and encounter notes. Feature engineering is applied to convert data into proper representation for predictive modeling. We explore serial and parallel mixed data models that are trained on both structured and unstructured data to identify PTSD. Model performances were calculated based on a highly skewed hold-out test dataset. The serial model that uses both structured and text data as input, yielded the highest values in sensitivity (0.77), F-measure (0.76), and AUC (0.88) and the parallel model that uses both structured and text data as the input obtained the highest positive predicted value (PPV) (0.75). Diseases such as PTSD are difficult to diagnose. Information recorded in the chart note over multiple visits of the patients with the primary care physicians has higher predictive power than structured data and combining these two data types can increase the predictive capabilities of machine learning models in diagnosing PTSD. While the deep-learning model outperformed the traditional ensemble model in processing text data, the ensemble classifier obtained better results in ingesting a combination of features obtained from both data types in the serial mixed model. The study demonstrated that unstructured encounter notes enhance a model’s ability to identify patients diagnosed with PTSD. These findings can enhance quality improvement, research, and disease surveillance related to PTSD in primary care populations.

scholarly journals An Adaptive Industrial Control Equipment Safety Fault Diagnosis Method in Industrial Internet of Things

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Hanrui Zhang ◽  
Qianmu Li ◽  
Shunmei Meng ◽  
Zhuoran Xu ◽  
Chaoxian Lv
Keyword(s):  
Dynamic Programming ◽  
Fault Diagnosis ◽  
Internet Of Things ◽  
Ensemble Learning ◽  
Industrial Internet Of Things ◽  
Industrial Control ◽  
Adjustment Method ◽  
Control Equipment ◽  
Industrial Internet ◽  
Diagnosis Model

With the rapid development of intelligent manufacturing and Industrial Internet of Things, many industrial control systems have high requirements for the security of the system itself. Failures of industrial control equipment will cause abnormal operation of industrial control equipment and waste of resources. It is very meaningful to detect and identify potential equipment abnormalities and failures in time and implement effective fault tolerance strategies. In the Industrial Internet of Things environment, the instructions and parameters of industrial control equipment often change due to changes in actual requirements. However, it is impractical to customize the learning method for each parameter value. Aiming at the problem, this paper proposes a fault diagnosis model based on ensemble learning and proposes a method of updating voting weights based on dynamic programming to assist decision-making. This method is based on Bagging strategy and combined with dynamic programming voting weight adjustment method to complete fault type prediction. Finally, this paper uses different loads as dynamic conditions; the diagnostic capability of the Bagging-based fault diagnosis integrated model in a dynamically changing industrial control system environment is verified by experiments. The fault diagnosis model of industrial control equipment based on ensemble learning effectively improves the adaptive ability of the model and makes the fault diagnosis framework truly intelligent. The voting weight adjustment method based on dynamic programming further improves the reliability of voting.

scholarly journals Application of Deep Learning in Fault Diagnosis of Rotating Machinery

Processes ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 919
Author(s):  
Wanlu Jiang ◽  
Chenyang Wang ◽  
Jiayun Zou ◽  
Shuqing Zhang
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Fault Diagnosis ◽  
Rotating Machinery ◽  
Generative Adversarial Networks ◽  
Extraction Ability ◽  
One Dimensional ◽  
Adversarial Networks ◽  
Diagnosis Model ◽  
The One

The field of mechanical fault diagnosis has entered the era of “big data”. However, existing diagnostic algorithms, relying on artificial feature extraction and expert knowledge are of poor extraction ability and lack self-adaptability in the mass data. In the fault diagnosis of rotating machinery, due to the accidental occurrence of equipment faults, the proportion of fault samples is small, the samples are imbalanced, and available data are scarce, which leads to the low accuracy rate of the intelligent diagnosis model trained to identify the equipment state. To solve the above problems, an end-to-end diagnosis model is first proposed, which is an intelligent fault diagnosis method based on one-dimensional convolutional neural network (1D-CNN). That is to say, the original vibration signal is directly input into the model for identification. After that, through combining the convolutional neural network with the generative adversarial networks, a data expansion method based on the one-dimensional deep convolutional generative adversarial networks (1D-DCGAN) is constructed to generate small sample size fault samples and construct the balanced data set. Meanwhile, in order to solve the problem that the network is difficult to optimize, gradient penalty and Wasserstein distance are introduced. Through the test of bearing database and hydraulic pump, it shows that the one-dimensional convolution operation has strong feature extraction ability for vibration signals. The proposed method is very accurate for fault diagnosis of the two kinds of equipment, and high-quality expansion of the original data can be achieved.

Study on Remote Control and Fault Diagnosis for Ultrahigh Speed Grinding

2007 ◽  
Vol 359-360 ◽  
pp. 518-522
Author(s):  
Wan Shan Wang ◽  
Tian Biao Yu ◽  
Xing Yu Jiang ◽  
Jian Yu Yang
Keyword(s):  
Remote Control ◽  
Fault Diagnosis ◽  
Knowledge Acquisition ◽  
Rough Set ◽  
Theoretical Research ◽  
Reduction Rule ◽  
Diagnosis System ◽  
Linear Speed ◽  
Fault Diagnosis System ◽  
Diagnosis Model

Remote control and fault diagnosis of ultrahigh speeding grinding is studied, which is based on the theory of rough set. Knowledge acquisition and reduction rule of fault diagnosis, realization method of remote control for ultrahigh speed grinding are studied, diagnosis model is established. Based on the theoretical research and ultrahigh speed grinder with a linear speed of 250 m/s, the remote control and fault diagnosis system of ultrahigh speed grinding is developed. Results of the system running show that the environment is improved, the mental pressure of workers is relieved and the efficiency is improved. At the same time, it proves that the ability to diagnosis and the accuracy of diagnosis for the ultrahigh speed grinding are improved and the time for diagnosis is shortened by applying rough set.

Sign in / Sign up

Export Citation Format

Share Document