Research of Glass Fiber Textile Monitor Image Recognition Based on Neural Network

2013 ◽  
Vol 694-697 ◽  
pp. 1978-1982
Author(s):  
Shu Qian Chen ◽  
Yang Lie Fu
Keyword(s):  
Neural Network ◽  
Glass Fiber ◽  
Image Recognition ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Textile Machine ◽  
Weft Fiber ◽  
The Stability ◽  
Monitor Image ◽  
Neural Network Input

Researched on weft fiber cut problems of glass fiber, improved the efficiency of textile production. Glass fiber textile machine is a major producer machine of glass fiber cloth. Textile machines weft detection usually uses the contact type in production, requires that the weft maintains certain pressure to the sensor. Using this method will cause glass fiber weft bristling, and will produce glass fiber floating dust. Damage to the textile machine and has the harm to the human body health. Used video surveillance method to detection the weft, image recognition and speed directly affects the stability of the system. This paper presented a detection methods of glass fiber textiles weft fiber cut based on neural network-based, selected multiple features which were directly related to the image with the weft as neural network input vector, through repeated training samples to remove tiny ripple effects which were caused by weft textile jitter, overcome the traditional method detection accuracy was not high. Experimental results show that this method can effectively avoid the weft jitter, making accurate detection of the weft fiber cut, and achieved satisfactory results.

Research on Flame Combustion Stability Based on Neural Network

2012 ◽  
Vol 516-517 ◽  
pp. 390-394
Author(s):  
Gui Zhi Bai ◽  
Li Hong Zhang ◽  
Shu Qian Chen
Keyword(s):  
Neural Network ◽  
Detection Method ◽  
Combustion Stability ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Multiple Features ◽  
Flame Combustion ◽  
Flame Pulsation ◽  
Neural Network Input ◽  
The Impact

For the use of boiler flame image analysis to detect the boiler flame combustion stability, when the combustion affected by coal, peaking , improper operation or other effects, the flame appeared short pulsation. In general, the traditional detection methods based on gray scale variance can not avoid the impact of flame pulsation on account of the inaccuracy of the boiler combustion stability detection. This paper presents a flame combustion instability detection method based on neural network and selects multiple features which are directly related to the flame stability as neural network input vector. Experiments show that this method can fight off the tiny ripple influence caused by the impurities combustion or peak and simultaneously, greatly improve the detection accuracy and stability.

The Analysis of Faults Detection Software Based on Improved Neural Network Algorithm

2014 ◽  
Vol 602-605 ◽  
pp. 2044-2047
Author(s):  
Miao Yan ◽  
Zhi Bao Liu
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Improved Method ◽  
Software Faults ◽  
Component Software ◽  
The Neural Network ◽  
Neural Network Algorithm ◽  
Detection Software

The large-scale software is consisted of the components which are quite different. The detection accuracy of the traditional faults detection methods for the large-scale component software is not satisfactory. This paper proposes a large-scale software faults detection methods based on improved neural network combining the features of the large-scale software by computing the stable probability and building the neural network faults detection models. The proposed method can analyze the serial faults of the large-scale software to determine the positions of the faults. The experiment and simulation results show that the improved method for large-scale software fault detection can greatly improve the accuracy.

scholarly journals Defect Detection of Industry Wood Veneer Based on NAS and Multi-Channel Mask R-CNN

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4398 ◽  
Author(s):  
Jiahao Shi ◽  
Zhenye Li ◽  
Tingting Zhu ◽  
Dongyi Wang ◽  
Chao Ni
Keyword(s):  
Neural Network ◽  
Defect Detection ◽  
Industrial Applications ◽  
Vital Role ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Wood Veneer ◽  
Multiple Channel ◽  
Execution Speed ◽  
Using Data

Wood veneer defect detection plays a vital role in the wood veneer production industry. Studies on wood veneer defect detection usually focused on detection accuracy for industrial applications but ignored algorithm execution speed; thus, their methods do not meet the required speed of online detection. In this paper, a new detection method is proposed that achieves high accuracy and a suitable speed for online production. Firstly, 2838 wood veneer images were collected using data collection equipment developed in the laboratory and labeled by experienced workers from a wood company. Then, an integrated model, glance multiple channel mask region convolution neural network (R-CNN), was constructed to detect wood veneer defects, which included a glance network and a multiple channel mask R-CNN. Neural network architect search technology was used to automatically construct the glance network with the lowest number of floating-point operations to pick out potential defect images out of numerous original wood veneer images. A genetic algorithm was used to merge the intermediate features extracted by the glance network. Multi-Channel Mask R-CNN was then used to classify and locate the defects. The experimental results show that the proposed method achieves a 98.70% overall classification accuracy and a 95.31% mean average precision, and only 2.5 s was needed to detect a batch of 50 standard images and 50 defective images. Compared with other wood veneer defect detection methods, the proposed method is more accurate and faster.

Research on Bolt Crack Detection Method Based on Image Processing

2013 ◽  
Vol 433-435 ◽  
pp. 426-429
Author(s):  
Jin Qiu Liu ◽  
Bing Fa Zhang ◽  
Yu Zeng Wang ◽  
Guang Ya Li ◽  
Jing Ru Han
Keyword(s):  
Image Processing ◽  
Edge Detection ◽  
Image Recognition ◽  
Crack Detection ◽  
Detection Method ◽  
Image Acquisition ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Contact Detection ◽  
Fracture Identification

A method of non-contact detection of bolt fracture have serial steps as follows: First of all the required data is obtained through image acquisition, then through the edge detection, image recognition and other image processing on the image to get the bolt fracture identification results, finally the non-contact measurement bolt fracture is realized. Experiments show that bolt crack detection method based on image processing, compared with the traditional detection methods improve the efficiency of detection and improve the detection accuracy. The method for bolt crack detection is feasible.

scholarly journals Straightness Detection Method and Accuracy Analysis of Guide Rail Parts

2021 ◽  
Vol 2133 (1) ◽  
pp. 012020
Author(s):  
Xiaoying Wang
Keyword(s):  
Machine Tools ◽  
Detection Method ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Accuracy Analysis ◽  
Geometric Accuracy ◽  
Guide Rail ◽  
The Common ◽  
The Stability

Abstract Guide rail is widely used in various machine tools. It mainly plays the role of guidance and support. The geometric accuracy of the guide rail, especially the straightness accuracy, directly affects the stability of the machine tool and the accuracy of the workpiece. By analyzing the common detection methods, application scope and detection accuracy of straightness of guide rail parts, the application occasions and detection accuracy of each detection method are clarified. It provides a theoretical basis and guidance for testers to detect straightness and deal with errors.

scholarly journals Metal Surface Defect Detection Using Modified YOLO

Algorithms ◽  
2021 ◽  
Vol 14 (9) ◽  
pp. 257
Author(s):  
Yiming Xu ◽  
Kai Zhang ◽  
Li Wang
Keyword(s):  
Neural Network ◽  
Metal Surface ◽  
Defect Detection ◽  
Surface Defect ◽  
Detection Methods ◽  
Cluster Center ◽  
Detection Accuracy ◽  
Detection Technology ◽  
Speed Advantage ◽  
Surface Defect Detection

Aiming at the problems of inefficient detection caused by traditional manual inspection and unclear features in metal surface defect detection, an improved metal surface defect detection technology based on the You Only Look Once (YOLO) model is presented. The shallow features of the 11th layer in the Darknet-53 are combined with the deep features of the neural network to generate a new scale feature layer using the basis of the network structure of YOLOv3. Its goal is to extract more features of small defects. Furthermore, then, K-Means++ is used to reduce the sensitivity to the initial cluster center when analyzing the size information of the anchor box. The optimal anchor box is selected to make the positioning more accurate. The performance of the modified metal surface defect detection technology is compared with other detection methods on the Tianchi dataset. The results show that the average detection accuracy of the modified YOLO model is 75.1%, which ia higher than that of YOLOv3. Furthermore, it also has a great detection speed advantage, compared with faster region-based convolutional neural network (Faster R-CNN) and other detection algorithms. The improved YOLO model can make the highly accurate location information of the small defect target and has strong real-time performance.

The Research on the Detection Methods of EMU Break Valves Features

2014 ◽  
Vol 687-691 ◽  
pp. 1034-1037
Author(s):  
Chun Ling Guan
Keyword(s):  
Neural Network ◽  
Feature Detection ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Characteristic Parameters ◽  
Spatial Function ◽  
Network Algorithm ◽  
Detection Technology ◽  
Neural Network Algorithm ◽  
Multiple Units

This paper focuses on the detection technology for Electric Multiple Units (EMU) break valves features. Aiming at the issues of EMU break valves features detection, this paper propose a kind of EMU break valves feature detection technology based on neural network algorithm which does not overly dependent on break valve characteristic parameters. The spatial function neural network algorithm is used to predict the EMU break valves features. The experiments illustrate the proposed algorithm can increase the detection accuracy with satisfactory effects in EMU break valves features detection.

DeepReturn: A deep neural network can learn how to detect previously-unseen ROP payloads without using any heuristics

2020 ◽  
Vol 28 (5) ◽  
pp. 499-523
Author(s):  
Xusheng Li ◽  
Zhisheng Hu ◽  
Haizhou Wang ◽  
Yiwei Fu ◽  
Ping Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
False Positive Rate ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Address Space ◽  
High Detection Rate ◽  
Positive Rate ◽  
In The Wild ◽  
Space Layout

Return-oriented programming (ROP) is a code reuse attack that chains short snippets of existing code to perform arbitrary operations on target machines. Existing detection methods against ROP exhibit unsatisfactory detection accuracy and/or have high runtime overhead. In this paper, we present DeepReturn, which innovatively combines address space layout guided disassembly and deep neural networks to detect ROP payloads. The disassembler treats application input data as code pointers and aims to find any potential gadget chains, which are then classified by a deep neural network as benign or malicious. Our experiments show that DeepReturn has high detection rate (99.3%) and a very low false positive rate (0.01%). DeepReturn successfully detects all of the 100 real-world ROP exploits that are collected in-the-wild, created manually or created by ROP exploit generation tools. DeepReturn is non-intrusive and does not incur any runtime overhead to the protected program.

scholarly journals A Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7279
Author(s):  
Yao Wang ◽  
Peizhi Yu
Keyword(s):  
Neural Network ◽  
Intrusion Detection ◽  
High Speed ◽  
Large Scale ◽  
Feature Fusion ◽  
Low Cost ◽  
Obstacle Detection ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Real Time Processing

The efficiency and the effectiveness of railway intrusion detection are crucial to the safety of railway transportation. Most current methods of railway intrusion detection or obstacle detection are inappropriate for large-scale applications due to their high cost or limited coverage. In this study, we present a fast and low-cost solution to intrusion detection of high-speed railways. As the solution to heavy computational burdens in the current convolutional-neural-network-based detection methods, the proposed method is mainly a novel neural network based on the SSD framework, which includes a feature extractor using an improved MobileNet and a lightweight and efficient feature fusion module. In addition, aiming to improve the detection accuracy of small objects, the feature map weights are introduced through convolution operation to fuse features at different scales. TensorRT is employed to optimize and deploy the proposed network in the low-cost embedded GPU platform, NVIDIA Jetson TX2, to enhance the efficiency. The experimental results show that the proposed methods achieved 89% mAP on the railway intrusion detection dataset, and the average processing time for a single frame was 38.6 ms on the Jetson TX2 module, which satisfies the need of real-time processing.

scholarly journals Improving Performance of Seismic Fault Detection by Fine-Tuning the Convolutional Neural Network Pre-Trained with Synthetic Samples

Energies ◽  
2021 ◽  
Vol 14 (12) ◽  
pp. 3650
Author(s):  
Zhe Yan ◽  
Zheng Zhang ◽  
Shaoyong Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Fault Detection ◽  
Seismic Data ◽  
Learning Strategy ◽  
Real Data ◽  
Fine Tuning ◽  
Detection Methods ◽  
Training Dataset ◽  
Detection Accuracy

Fault interpretation is an important part of seismic structural interpretation and reservoir characterization. In the conventional approach, faults are detected as reflection discontinuity or abruption and are manually tracked in post-stack seismic data, which is time-consuming. In order to improve efficiency, a variety of automatic fault detection methods have been proposed, among which widespread attention has been given to deep learning-based methods. However, deep learning techniques require a large amount of marked seismic samples as a training dataset. Although the amount of synthetic seismic data can be guaranteed and the labels are accurate, the difference between synthetic data and real data still exists. To overcome this drawback, we apply a transfer learning strategy to improve the performance of automatic fault detection by deep learning methods. We first pre-train a deep neural network with synthetic seismic data. Then we retrain the network with real seismic samples. We use a random sample consensus (RANSAC) method to obtain real seismic samples and generate corresponding labels automatically. Three real 3D examples are included to demonstrate that the fault detection accuracy of the pre-trained network models can be greatly improved by retraining the network with a few amount of real seismic samples.

Sign in / Sign up

Export Citation Format

Share Document