scholarly journals A Novel Deep Learning Model for Mechanical Rotating Parts Fault Diagnosis Based on Optimal Transport and Generative Adversarial Networks

Actuators ◽  
2021 ◽  
Vol 10 (7) ◽  
pp. 146
Author(s):  
Xuanquan Wang ◽  
Xiongjun Liu ◽  
Ping Song ◽  
Yifan Li ◽  
Youtian Qie
Keyword(s):  
Fault Diagnosis ◽  
Real Time ◽  
Network Architecture ◽  
Transport Theory ◽  
Optimal Transport ◽  
Transmission System ◽  
Generative Adversarial Networks ◽  
Time Performance ◽  
Network Algorithm ◽  
Public Data

To solve the poor real-time performance of the existing fault diagnosis algorithms on transmission system rotating components, this paper proposes a novel high-dimensional OT-Caps (Optimal Transport–Capsule Network) model. Based on the traditional capsule network algorithm, an auxiliary loss is introduced during the offline training process to improve the network architecture. Simultaneously, an optimal transport theory and a generative adversarial network are introduced into the auxiliary loss, which accurately depicts the error distribution of the fault characteristic. The proposed model solves the low real-time performance of the capsule network algorithm due to complex architecture, long calculation time, and oversized hardware resource consumption. Meanwhile, it ensures the high precision, early prediction, and transfer aptitude of fault diagnosis. Finally, the model’s effectiveness is verified by the public data sets and the actual faults data of the transmission system, which provide technical support for the application.

Status Monitoring and Fault Diagnosis Network System Based on UPnP

2007 ◽  
Vol 353-358 ◽  
pp. 2632-2635
Author(s):  
Pei Yu Li ◽  
Da Peng Tan ◽  
Tao Qing Zhou ◽  
Bo Yu Lin
Keyword(s):  
Fault Diagnosis ◽  
Embedded System ◽  
Real Time ◽  
Data Storage ◽  
Network Architecture ◽  
Network System ◽  
Time Data ◽  
Status Monitoring ◽  
Self Recognition ◽  
Real Time Data

Aiming at some problems in the fields of industry monitoring technology (IMT) such as bad dynamic ability and poor versatility, this paper brought forward a kind of intelligent Status monitoring and Fault diagnosis Network System (SFNS) based on UPnP-Universal Plug and Play. The model for fault diagnosis network system was established according to characteristics and requirements of IMT network, and system network architecture was designed and realized by UPnP. Using embedded system technology, real-time data collection node, monitoring center node and data storage server were designed, and that supplies powerful real-time data support for SFNS. Industry fields experiments proved that this system can realize self recognition, seamless linkage and other self adapting ability, and can break through the limitation of real IP address to achieve real-time remote monitoring on line.

scholarly journals DC-YOLOv3: A novel efficient object detection algorithm

2021 ◽  
Vol 2082 (1) ◽  
pp. 012012
Author(s):  
Xu Zhang ◽  
Fang Han ◽  
Ping Wang ◽  
Wei Jiang ◽  
Chen Wang
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Real World ◽  
Network Architecture ◽  
Detection Algorithm ◽  
Training Time ◽  
Feature Representations ◽  
Multi Scale ◽  
Time Performance ◽  
Real World Applications

Abstract Feature pyramids have become an essential component in most modern object detectors, such as Mask RCNN, YOLOv3, RetinaNet. In these detectors, the pyramidal feature representations are commonly used which represent an image with multi-scale feature layers. However, the detectors can’t be used in many real world applications which require real time performance under a computationally limited circumstance. In the paper, we study network architecture in YOLOv3 and modify the classical backbone--darknet53 of YOLOv3 by using a group of convolutions and dilated convolutions (DC). Then, a novel one-stage object detection network framework called DC-YOLOv3 is proposed. A lot of experiments on the Pascal 2017 benchmark prove the effectiveness of our framework. The results illustrate that DC-YOLOv3 achieves comparable results with YOLOv3 while being about 1.32× faster in training time and 1.38× faster in inference time.

scholarly journals Bearing Fault Diagnosis Based on the Switchable Normalization SSGAN with 1-D Representation of Vibration Signals as Input

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 2000 ◽  
Author(s):  
Dongdong Zhao ◽  
Feng Liu ◽  
He Meng
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Fault Classification ◽  
Generative Adversarial Networks ◽  
Data Set ◽  
Vibration Signals ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Training Samples ◽  
Public Data

The bearing is a component of the support shaft that guides the rotational movement of the shaft, widely used in the mechanical industry and also called a mechanical joint. In bearing fault diagnosis, the accuracy much depends on the feature extraction, which always needs a lot of training samples and classification in the commonly used methods. Neural networks are good at latent feature extraction and fault classification, however, they have problems with instability and over-fitting, and more labeled samples must be trained. Switchable normalization and semi-supervised learning are introduced to solve the above obstacles in this paper, which proposes a novel bearing fault diagnosis method based on switchable normalization semi-supervised generative adversarial networks (SN-SSGAN) with 1-dimensional representation of vibration signals as input. Experimental results showed that the proposed method has a desirable 99.93% classification accuracy in the case of less labeled data from the public data set of West Reserve University, which is better than the state-of-the-art methods.

The Remote Intelligent Monitoring and Fault Diagnosis & Processing System

2012 ◽  
Vol 479-481 ◽  
pp. 2625-2629
Author(s):  
Chang Yi Wang ◽  
Peng Bao ◽  
Zhuo Zhang
Keyword(s):  
Fault Diagnosis ◽  
Real Time ◽  
Network Architecture ◽  
Technical Problem ◽  
Processing System ◽  
Automatic Monitoring ◽  
Structure Design ◽  
Real Time Monitoring ◽  
The Real ◽  
Automated Support

This subject is proposed based on the conflict between the heavy workload for maintenance personnel and few personnel at the geological survey automated master station at present, and the purpose is to solve the problem that the SCADA real-time monitoring system, UPS power supply system, automated support system as well as the automated computer room environment and equipment cannot achieve the real-time monitoring, fault diagnosis and accident processing of the remote unified platform. It proposes the remote online automatic monitoring and intelligent diagnosis and processing system on the basis of the OPEN3000 system platform. It uses the distributed network architecture in the network design to protect the security of database and the video records in the video system; it adopts the modular structure design, and combined with the expert system and the rule database design of database knowledge, thereby solving the technical problem that the real-time monitoring and fault diagnosis of SCADA, UPS, video and many other systems and equipment are being integrated into a unified platform.

scholarly journals GAN-Holo: Generative Adversarial Networks-Based Generated Holography Using Deep Learning

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Aamir Khan ◽  
Zhang Zhijiang ◽  
Yingjie Yu ◽  
Muhammad Amir Khan ◽  
Ketao Yan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Computation Time ◽  
Input Image ◽  
Generative Adversarial Networks ◽  
Second Phase ◽  
Generative Adversarial Network ◽  
Recovery Method ◽  
Holographic Image ◽  
Time Performance

Current development in a deep neural network (DNN) has given an opportunity to a novel framework for the reconstruction of a holographic image and a phase recovery method with real-time performance. There are many deep learning-based techniques that have been proposed for the holographic image reconstruction, but these deep learning-based methods can still lack in performance, time complexity, accuracy, and real-time performance. Due to iterative calculation, the generation of a CGH requires a long computation time. A novel deep generative adversarial network holography (GAN-Holo) framework is proposed for hologram reconstruction. This novel framework consists of two phases. In phase one, we used the Fresnel-based method to make the dataset. In the second phase, we trained the raw input image and holographic label image data from phase one acquired images. Our method has the capability of the noniterative process of computer-generated holograms (CGHs). The experimental results have demonstrated that the proposed method outperforms the existing methods.

The Non-Constant Speed Bearing Fault Diagnosis Based on Speed Measuring Method

2013 ◽  
Vol 760-762 ◽  
pp. 901-905
Author(s):  
Bin Wu ◽  
Shi Jun Wang ◽  
Ying Tang ◽  
Yue Gang Luo
Keyword(s):  
Fault Diagnosis ◽  
Real Time ◽  
Measuring Method ◽  
Measurement Methods ◽  
Constant Speed ◽  
Measuring Range ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Time Performance ◽  
Speed Measurement

This paper compares the existing speed measurement methods, discusses a speed measurement based on microcontroller used in non-constant speed bearing fault diagnosis that has the wide measuring range, high precision, good real-time performance.

scholarly journals Real-Time Smile Detection using Deep Learning

2019 ◽  
Vol 35 (2) ◽  
pp. 135-145
Author(s):  
Chi Cuong Nguyen ◽  
Giang Son Tran ◽  
Thi Phuong Nghiem ◽  
Jean-Christophe Burie ◽  
Chi Mai Luong
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Network Architecture ◽  
State Of The Art ◽  
Neural Network Architecture ◽  
Time Performance ◽  
Art Object ◽  
Real World Applications ◽  
Facial Images ◽  
Smile Detection

Real-time smile detection from facial images is useful in many real world applications such as automatic photo capturing in mobile phone cameras or interactive distance learning. In this paper, we study different architectures of object detection deep networks for solving real-time smile detection problem. We then propose a combination of a lightweight convolutional neural network architecture (BKNet) with an efficient object detection framework (RetinaNet). The evaluation on the two datasets (GENKI-4K, UCF Selfie) with a mid-range hardware device (GTX TITAN Black) show that our proposed method helps in improving both accuracy and inference time of the original RetinaNet to reach real-time performance. In comparison with the state-of-the-art object detection framework (YOLO), our method has higher inference time, but still reaches real-time performance and obtains higher accuracy of smile detection on both experimented datasets.

Design of shifting strategy for capacity adjustment device of power reflux hydraulic transmission systems based on working condition identification

2020 ◽  
pp. 095440702096686
Author(s):  
Yingzhe Kan ◽  
Dongye Sun ◽  
Datong Qin ◽  
Yong Luo ◽  
Minghui Hu ◽  
...  
Keyword(s):  
Real Time ◽  
Working Condition ◽  
Transmission System ◽  
Identification Algorithm ◽  
Hardware In The Loop ◽  
Wheel Loader ◽  
Time Performance ◽  
Shifting Strategy ◽  
Working Principle ◽  
Simulation Results

The performance of a wheel loader (WL) can be improved with the application of a power reflux hydraulic transmission system (PRHTS) with a capacity adjustment device (CA-device). However, due to CA-device’s unique working principle, the traditional shifting strategy is not suitable for CA-device. Apply traditional shifting strategy to CA-device will result in frequent or incorrect shifting. In order to solve this problem, this paper proposes applying the working condition identification to the CA-device shifting strategy. Combining the working principle of PRHTS with CA-device and the analysis of WL V-condition, the requirement for the working condition identification algorithm of the CA-device shifting strategy is obtained, and a working condition identification algorithm for WL V-condition is designed. Simulation results show that applying the working condition identification algorithm to the CA-device shifting strategy can avoid frequent shifts and incorrect shifts. A hardware-in-the-loop platform is built to verify the real-time performance of the shifting strategy. Results show that the proposed shifting strategy exhibits a satisfactory level of real-time performance.

Sign in / Sign up

Export Citation Format

Share Document