UAV rotor fault diagnosis based on interval sampling reconstruction of vibration signals and a 1D-CNN deep learning method

2022 ◽  
Author(s):  
Canyi Du ◽  
Xinyu Zhang ◽  
Rui Zhong ◽  
Feng Li ◽  
Feifei Yu ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Speed ◽  
Recognition Rate ◽  
Learning Model ◽  
Identification Accuracy ◽  
Fault Identification ◽  
Complex Data ◽  
Vibration Signals ◽  
Interval Sampling ◽  
Deep Learning Model

Abstract Aiming at the possible mechanical faults of UAV rotor in the working process, this paper proposes a UAV rotor fault identification method based on interval sampling reconstruction of vibration signals and one-dimensional convolutional neural network (1D-CNN) deep learning. Firstly, experiments were designed to collect the vibration acceleration signals of UAV working at high speed under three states (normal, rotor damage by varying degrees, and rotor crack by different degrees). Then considering the powerful feature extraction and complex data analysis abilities of 1D-CNN, an effective deep learning model for fault identification is established utilizing 1D-CNN. During analysis, it is found that the recognition effect of minor faults is not ideal, which causes by all states were identified as normal and then reduces the overall identification accuracy, when using conventional sequential sampling to construct learning. To this end, in order to make the sample data cover the whole process of data collection as much as possible, a learning sample processing method based on interval sampling reconstruction of vibration signal is proposed. And it is also verified that the sample set reconstructed can easily reflect the global information of mechanical operation. Finally, according to the comparison of analysis results, the recognition rate of deep learning model for different degrees of faults is greatly improved, and minor faults could also be accurately identified, through this method. The results show that, the 1D-CNN deep learning model, could diagnose and identify UAV rotor damage faults accurately, by combing the proposed method of interval sampling reconstruction.

scholarly journals Self-Evolution Cascade Deep Learning Model for High-Speed Receiver Adaptation

2020 ◽  
Vol 10 (6) ◽  
pp. 1043-1053
Author(s):  
Bowen Li ◽  
Brandon Jiao ◽  
Chih-Hsun Chou ◽  
Romi Mayder ◽  
Paul Franzon
Keyword(s):  
Deep Learning ◽  
High Speed ◽  
Learning Model ◽  
Deep Learning Model

scholarly journals Utilizing Mobile-based Deep Learning Model for Managing Video in Knowledge Management System

2018 ◽  
Vol 12 (6) ◽  
pp. 62 ◽  
Author(s):  
Harjanto Prabowo ◽  
Tjeng Wawan Cenggoro ◽  
Arif Budiarto ◽  
Anzaludin Samsinga Perbangsa ◽  
Hery Harjono Muljo ◽  
...  
Keyword(s):  
Knowledge Management ◽  
Deep Learning ◽  
Intelligent System ◽  
Learning Model ◽  
Complex Data ◽  
Materials Management ◽  
Video File ◽  
Heavy Burden ◽  
Deep Learning Model ◽  
Video Format

<p>Knowledge Management (KM) system is a core feature in facilitating intellectual growth in organization. However, there are numerous difficulties in maintaining a reliable KM system. One of the challenges is to manage knowledge materials in video format. A video file contains complex data that lead to the difficulties in managing them. Without an intelligent system, managing videos for KM requires a laborious effort. In this paper, an intelligent framework for KM system, embedded with deep learning model, is proposed. The use of the deep learning model alleviates the heavy burden of video materials management in KM system. To enhance the agility of the system, mobile-based deep learning model is utilized in the framework.</p>

scholarly journals Recognition of Vehicle License Plates Based on Image Processing

2021 ◽  
Vol 11 (14) ◽  
pp. 6292
Author(s):  
Tae-Gu Kim ◽  
Byoung-Ju Yun ◽  
Tae-Hun Kim ◽  
Jae-Young Lee ◽  
Kil-Houm Park ◽  
...  
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Recognition Rate ◽  
Super Resolution ◽  
Learning Model ◽  
Distortion Correction ◽  
License Plate ◽  
Generative Adversarial Network ◽  
Perspective Distortion ◽  
Deep Learning Model

In this study, we have proposed an algorithm that solves the problems which occur during the recognition of a vehicle license plate through closed-circuit television (CCTV) by using a deep learning model trained with a general database. The deep learning model which is commonly used suffers with a disadvantage of low recognition rate in the tilted and low-resolution images, as it is trained with images acquired from the front of the license plate. Furthermore, the vehicle images acquired by using CCTV have issues such as limitation of resolution and perspective distortion. Such factors make it difficult to apply the commonly used deep learning model. To improve the recognition rate, an algorithm which is a combination of the super-resolution generative adversarial network (SRGAN) model, and the perspective distortion correction algorithm is proposed in this paper. The accuracy of the proposed algorithm was verified with a character recognition algorithm YOLO v2, and the recognition rate of the vehicle license plate image was improved 8.8% from the original images.

scholarly journals A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals

Sensors ◽  
2017 ◽  
Vol 17 (2) ◽  
pp. 425 ◽  
Author(s):  
Wei Zhang ◽  
Gaoliang Peng ◽  
Chuanhao Li ◽  
Yuanhang Chen ◽  
Zhujun Zhang
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Domain Adaptation ◽  
Learning Model ◽  
Vibration Signals ◽  
Deep Learning Model ◽  
Adaptation Ability

scholarly journals A compact deep learning model for Khmer handwritten text recognition

2021 ◽  
Vol 10 (3) ◽  
pp. 584
Author(s):  
Bayram Annanurov ◽  
Norliza Noor
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Ad Hoc ◽  
Recognition Rate ◽  
Learning Model ◽  
Text Recognition ◽  
Handwritten Text ◽  
Handwritten Text Recognition ◽  
Fully Connected ◽  
Deep Learning Model

<p>The motivation of this study is to develop a compact offline recognition model for Khmer handwritten text that would be successfully applied under limited access to high-performance computational hardware. Such a task aims to ease the ad-hoc digitization of vast handwritten archives in many spheres. Data collected for previous experiments were used in this work. The oneagainst-all classification was completed with state-of-the-art techniques. A compact deep learning model (2+1CNN), with two convolutional layers and one fully connected layer, was proposed. The recognition rate came out to be within 93-98%. The compact model is performed on par with the state-of-theart models. It was discovered that computational capacity requirements usually associated with deep learning can be alleviated, therefore allowing applications under limited computational power.</p>

scholarly journals Apply VGGNet-Based Deep Learning Model of Vibration Data for Prediction Model of Gravity Acceleration Equipment

2020 ◽  
Author(s):  
SeonWoo Lee ◽  
HyeonTak Yu ◽  
HoJun Yang ◽  
InSeo Song ◽  
JaeHeung Yang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prediction Model ◽  
Learning Model ◽  
Learning Models ◽  
Vibration Signals ◽  
Vibration Data ◽  
Amplitude Data ◽  
Feature Based ◽  
Gravity Acceleration ◽  
Deep Learning Model

Hypergravity accelerators are a type of large machinery used for gravity training or medical research. A failure of such large equipment can be a serious problem in terms of safety or costs. This paper proposes a prediction model that can proactively prevent failures that may occur in a hy-pergravity accelerator. The method proposed in this paper was to convert vibration signals to spectograms and perform classification training using a deep learning model. An experiment was conducted to evaluate the performance of the method proposed in this paper. A 4-channel accel-erometer was attached to the bearing housing, which is a rotor, and time-amplitude data were obtained from the measured values by sampling. The data were converted to a two-dimensional spectrogram, and classification training was performed using a deep learning model for four conditions of the equipment: Unbalance, Misalignment, Shaft Rubbing, and Normal. The ex-perimental results showed that the proposed method had a 99.5% F1-Score, which was up to 23% higher than the 76.25% for existing feature-based learning models.

scholarly journals GlaucoNet: A Highly Robust Stacked Auto-Encoder assisted Deep Learning Model for Glaucoma Detection System

2019 ◽  
Vol 9 (1) ◽  
pp. 5293-5303
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Detection System ◽  
Imaging Techniques ◽  
Initial Period ◽  
Learning Model ◽  
Classification Model ◽  
Complex Data ◽  
Glaucoma Detection ◽  
Deep Learning Model

High pace rise in Glaucoma, an irreversible eye disease that deteriorates vision capacity of human has alarmed academia-industries to develop a novel and robust Computer Aided Diagnosis (CAD) system for early Glaucomatic eye detection. The main root cause for glaucoma growth depends on its structural alterations in the retina and is very much essential for ophthalmologists to identify it at an initial period to stop its progression. Fundoscopy is among one of the biomedical imaging techniques to analyze the internal structure of retina. Recently, numerous efforts have been made to exploit SpatialTemporal features including morphological values of Optical Disk (OD), Optical Cup (OC), Neuro-Retinal Rim (NRR) etc to perform Glaucoma detection in fundus images. Here, some issues like: suitable pre-processing, precise Region of Interest segmentation, post-segmentation and lack of generalized threshold limits efficacy of the major existing approaches. Furthermore, the optimal segmentation of OD and OC, nerves removal from OD or OC is often tedious and demands more efficient solution. However, these approaches cumulatively turn out to be computationally complex and time-consuming. As potential alternative, deep learning techniques have gained widespread attention, especially for image analysis or vision technologies. With this motive, in this paper, the authors proposed a novel Convolutional Stacked Auto-Encoder (CSAE) assisted Deep Learning Model for Glaucoma Detection and Classification model named GlaucoNet. Unlike classical methods, GlaucoNet applies Stacked Auto-Encoder by using hierarchical CNN structure to perform deep feature extraction and learning. By adapting complex data nature, and large features, GlaucoNet was designed with three layers: convolutional layer (CONV), Max-pool layer (MP) and two Fully Connected (FC) layers where the first performs feature extraction and learning, while second exhibits feature selection followed by the reduction of spatial resolution of the individual feature map to avoid large number of parameters and computational complexities. To avoid saturation problem in this work, by marking an applied dropout as 0.5. MATLAB based simulation-results with DRISHTI-GS and DRION-DB datasets affirmed that the proposed GlaucoNet model outperforms as compared to other state-of-art techniques: neural network based approaches in terms of accuracy, recall, precision, F-Measure and balanced accuracy. The overall parametric measured values shown better performance for GlaucoNet model.

A hybrid deep-learning model for fault diagnosis of rolling bearings under strong noise environment

2022 ◽  
Author(s):  
Ke Zhang ◽  
Caizi Fan ◽  
Xiaochen Zhang ◽  
Huaitao Shi ◽  
Songhua Li
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Recognition Rate ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Learning Model ◽  
Detection Accuracy ◽  
Practical Applications ◽  
Reconstructed Signal ◽  
Deep Learning Model

Abstract Aiming at the problem that the signal of rolling bearing is interfered by strong noise in practical engineering environment, which leads to the decline of the diagnosis accuracy of intelligent diagnosis model. This paper proposes a novel hybrid model (CDAE-BLCNN). First, the rolling bearing vibration signal containing noise was input into the Convolutional Denoising Auto-Encoder (CDAE), which denoises the signal through unsupervised learning, and then outputs the reconstructed data. Secondly, a hybrid neural network (BLCNN) composed of multi-scale wide convolution kernel block (MWCNN) and bidirectional long-short-term memory network (BiLSTM) was used to extract intrinsic fault features from the reconstructed signal and diagnose fault types. The analysis results demonstrate that the proposed hybrid deep learning model achieves higher detection accuracy even under different noise and various rotating speed. Compared with other models, there is a high fault recognition rate, robustness, and generalization ability, which may be favorable to practical applications.

Sign in / Sign up

Export Citation Format

Share Document