Improvement of High-Speed Detection Algorithm for Nonwoven Material Defects Based on Machine Vision

Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.

Human intrusion detection for high-speed railway perimeter under all-weather condition

Purpose – The paper aims to solve the problem of personnel intrusion identification within the limits of highspeed railways. It adopts the fusion method of millimeter wave radar and camera to improve the accuracy ofobject recognition in dark and harsh weather conditions.Design/methodology/approach – This paper adopts the fusion strategy of radar and camera linkage toachieve focus amplification of long-distance targets and solves the problem of low illumination by laser lightfilling of the focus point. In order to improve the recognition effect, this paper adopts the YOLOv8 algorithm formulti-scale target recognition. In addition, for the image distortion caused by bad weather, this paper proposesa linkage and tracking fusion strategy to output the correct alarm results.Findings – Simulated intrusion tests show that the proposed method can effectively detect human intrusionwithin 0–200 m during the day and night in sunny weather and can achieve more than 80% recognitionaccuracy for extreme severe weather conditions.Originality/value – (1) The authors propose a personnel intrusion monitoring scheme based on the fusion ofmillimeter wave radar and camera, achieving all-weather intrusion monitoring;(2) The authors propose a newmulti-level fusion algorithm based on linkage and tracking to achieve intrusion target monitoring underadverse weather conditions;(3) The authors have conducted a large number of innovative simulationexperiments to verify the effectiveness of the method proposed in this article.

基于改进Detection Transformer的棉花幼苗与杂草检测模型研究

基于深度学习的目标检测技术在棉花幼苗与杂草检测领域已取得一定进展。论文提出了基于改进Detection Transformer的棉花幼苗与杂草检测模型,以提高杂草目标检测的准确率和效率。首先,引入了可变形注意力模块替代原始模型中的Transformer注意力模块,提高模型对特征图目标形变的处理能力。提出新的降噪训练机制,解决了二分图匹配不稳定问题。提出混合查询选择策略,提高解码器对目标类别和位置信息的利用效率。使用Swin Transformer作为网络主干,提高模型特征提取能力。通过对比原网络,论文提出的模型方法在训练过程中表现出更快的收敛速度,并且在准确率方面提高了6.7%。

Gearbox Deterioration Detection under Steady State,Variable Load, and Variable Speed Conditions

Multiple dominant gear meshing frequencies are present in the vibration signals collected from gearboxes and the conventional spiky features that represent initial gear fault conditions are usually difficult to detect. In order to solve this problem, we propose a new gearbox deterioration detection technique based on autoregressive modeling and hypothesis testing in this paper. A stationary autoregressive model was built by using a normal vibration signal from each shaft. The established autoregressive model was then applied to process fault signals from each shaft of a two-stage gearbox. What this paper investigated is a combined technique which unites a time-varying autoregressive model and a two sample Kolmogorov-Smimov goodness-of-fit test, to detect the deterioration of gearing system with simultaneously variable shaft speed and variable load. The time-varying autoregressive model residuals representing both healthy and faulty gear conditions were compared with the original healthy time-synchronous average signals. Compared with the traditional kurtosis statistic, this technique for gearbox deterioration detection has shown significant advantages in highlighting the presence of incipient gear fault in all different speed shafts involved in the meshing motion under variable conditions.

Cavitation Detection in Variable Speed Pump by Analyzing the Acoustic and Vibration Spectrums

Cavitation in pumps must be detected and prevented. The present work is an attempt to use the simultaneous measurements of vibration and sound for variable speed pump to detect cavitation. It is an attempt to declare the relationship between the vibration and sound for the same discharge of 780 L/h and NPSHA of 0.754 at variable speeds of 1476 rpm, 1644 rpm, 1932 rpm, 2190 rpm, 2466 rpm, and 2682 rpm. Results showed that: the occurrence of cavitation depends on the rotational speed, and the sound signals in both no cavitation and cavitation conditions appear in random manner. While, surveying the vibration and sound spectrums at the second, third, and fourth blade passing frequencies reveals no indications or phenomenon associated with the cavitation at variable speeds. It is recommended to survey the vibration spectra at the rotational and blade passing frequencies simultaneously as a detection unique method of cavitation.

ACCURATE DETECTION OF HIGH-SPEED MULTI-TARGET VIDEO SEQUENCES MOTION REGIONS BASED ON RECONSTRUCTED BACKGROUND DIFFERENCE

The paper first discusses shortcomings of classical adjacent-frame difference. Sec ondly, based on the image energy and high order statistic(HOS) theory, background reconstruction constraints are setup. Under the help of block-processing technology, background is reconstructed quickly. Finally, background difference is used to detect motion regions instead of adjacent frame difference. The DSP based platform tests indicate the background can be recovered losslessly in about one second, and moving regions are not influenced by moving target speeds. The algorithm has important usage both in theory and applications.

Improved High Speed Flame Detection Method Based on YOLOv7

In order to solve the problems of the traditional flame detection method, such as low detection accuracy, slow detection speed and lack of real-time detection ability. An improved high speed flame detection method based on YOLOv7 is proposed. Based on YOLOv7 and combined with ConvNeXtBlock, CN-B network module was constructed, and YOLOv7-CN-B flame detection method was proposed. Compared with the YOLOv7 method, this flame detection method is lighter and has stronger flame feature extraction ability. 2059 open flame data sets labeled with single flame categories were used to avoid the enhancement effect brought by high-quality data sets, so that the comparative experimental effect completely depended on the performance of the flame detection method itself. The results show that the accuracy of YOLOv7-CN-B method is improved by 5% and mAP is improved by 2.1% compared with YOLOv7 method. The detection speed reached 149.25 FPS, and the single detection speed reached 11.9 ms. The experimental results show that the YOLOv7-CN-B method has better performance than the mainstream algorithm.

Speed and Accuracy Tradeoff for LiDAR Data Based Road Boundary Detection

Road boundary detection is essential for autonomous vehicle localization and decision-making,especially under GPS signal loss and lane discontinuities.For road boundary detection in structural environments,obstacle occlusions and large road curvature are two significant challenges.However,an effective and fast solution for these problems has remained elusive.To solve these problems,a speed and accuracy tradeoff method for LiDAR-based road boundary detection in structured environments is proposed.The proposed method consists of three main stages:1)a multi-feature based method is applied to extract feature points;2)a road-segmentation-line-based method is proposed for classifying left and right feature points;3)an iterative Gaussian Process Regression(GPR)is employed for filtering out false points and extracting boundary points.To demonstrate the effectiveness of the proposed method,KITTI datasets is used for comprehensive experiments,and the performance of our approach is tested under different road conditions.Comprehensive experiments show the roadsegmentation-line-based method can classify left,and right feature points on structured curved roads,and the proposed iterative Gaussian Process Regression can extract road boundary points on varied road shapes and traffic conditions.Meanwhile,the proposed road boundary detection method can achieve real-time performance with an average of 70.5 ms per frame.

Intelligent GPS-Less Speed Detection and Clustering in VANET

Vehicular Ad Hoc Network （VANET） has emerged as a new wireless network for vehicular communications. To provide a flexible and high reliable communication service in VANET, vehicles are clustered to construct many small networks （clusters） so that channel interferences and flooding messages can be limited. This research presents a novel Multi-Resolution Relative Speed Detection （MRSD） model to improve the clustering algorithm in VANET without using Global Positioning System （GPS）. MRSD uses the Moving Average Convergence Divergence （MACD）, the Momentum of Received Signal Strength （MRSS）, and Artificial Neural Networks （ANNs） to estimate the motion state and the relative speed of a vehicle based purely on Received Signal Strength. The proposed MRSD model is accurate with the assistance of the intelligent classification, and incurs less overhead in the cluster head election than that of other algorithms.

Electromagnetic Tomography System for Defect Detection of High-Speed Rail Wheel

A novel electromagnetic tomography(EMT)system for defect detection of high-speed rail wheel is proposed,which differs from traditional electromagnetic tomography systems in its spatial arrangements of coils.A U-shaped sensor array was designed,and then a simulation model was built with the low frequency electromagnetic simulation software.Three different algorithms were applied to perform image reconstruction,therefore the defects can be detected from the reconstructed images.Based on the simulation results,an experimental system was built and image reconstruction were performed with the measured data.The reconstructed images obtained both from numerical simulation and experimental system indicated the locations of the defects of the wheel,which verified the feasibility of the EMT system and revealed its good application prospect in the future.

Dynamic unbalance detection of cardan shaft in high-speed train based on EMD-SVD-NHT

Contrary to the aliasing defect between the adjacent intrinsic model functions(IMFs) existing in empirical model decomposition(EMD), a new method of detecting dynamic unbalance with cardan shaft in high-speed train was proposed by applying the combination between EMD, Hankel matrix, singular value decomposition(SVD) and normalized Hilbert transform(NHT). The vibration signals of gimbal installed base were decomposed through EMD to get different IMFs. The Hankel matrix constructed through the single IMF was orthogonally executed through SVD. The critical singular values were selected to reconstruct vibration signs on the basis of the key stack of singular values. Instantaneous frequencys(IFs) of reconstructed vibration signs were applied to detect dynamic unbalance with shaft and eliminated clutter spectrum caused by the aliasing defect between the adjacent IMFs, which highlighted the failure characteristics. The method was verified by test data in the unbalance condition of dynamic cardan shaft. The results show that the method effectively detects the fault vibration characteristics caused by cardan shaft dynamic unbalance and extracts the nature vibration features. With comparison to the traditional EMD-NHT, clarity and failure characterization force are significantly improved.

A Study on the Sensor Applications for Position Detection and Guideway Monitoring in High Speed Maglev

The high speed maglev is mainly characterized by propulsion using linear synchronous motor (LSM) and vehicle levitation from the guideway surface. In LSM propulsion control, the position detection sensor is used to detect running vehicle position for synchronized current generation. To maintain the stable levitating condition during vehicle running, the irregularity of guideway surface should be monitored by sensors measuring the displacement and acceleration between vehicle and guideway. In this study, the application methods of these sensors in the high speed maglev are investigated and through the experiments by using the small-scale test bed, the validity of examined methods is confirmed.

Fast-speed self-powered PEDOT:PSS/α-Ga_(2)O_(3)nanorod array/FTO photodetector with solar-blind UV/visible dual-band photodetection

Theα-Ga2 O_(3)nanorod array is grown on FTO by hydrothermal and annealing processes.And a self-powered PEDOT:PSS/α-Ga_(2)O_(3)nanorod array/FTO(PGF)photodetector has been demonstrated by spin coating PEDOT:PSS on theα-Ga_(2)O_(3)nanorod array.Successfully,the PGF photodetector shows solar-blind UV/visible dual-band photodetection.Our device possesses comparable solar-blind UV responsivity(0.18 mA/W at 235 nm)and much faster response speed(0.102 s)than most of the reported self-poweredα-Ga_(2)O_(3)nanorod array solar-blind UV photodetectors.And it presents the featured and distinguished visible band photoresponse with a response speed of 0.136 s at 540 nm.The response time is also much faster than the other non-self-poweredβ-Ga_(2)O_(3)DUV/visible dual-band photodetectors due to the fast-speed separation of photogenerated carries by the built-in electric field in the depletion regions of PEDOT:PSS/α-Ga_(2)O_(3)heterojunction.The results herein may prove a promising way to realize fast-speed self-poweredα-Ga_(2)O_(3)photodetectors with solar-blind UV/visible dual-band photodetection by simple processes for the applications of multiple-target tracking,imaging,machine vision and communication.

Real Time Speed Bump Detection Using Gaussian Filtering and Connected Component Approach

An Intelligent Transportation System (ITS) is a new system developed for the betterment of user in traffic and transport management domain area for smart and safe driving. ITS subsystems are Emergency vehicle notification systems, Automatic road enforcement, Collision avoidance systems, Automatic parking, Map database management, etc. Advance Driver Assists System (ADAS) belongs to ITS which provides alert or warning or information to the user during driving. The proposed method uses Gaussian filtering and Median filtering to remove noise in the image. Subsequently image subtraction is achieved by subtracting Median filtered image from Gaussian filtered image. The resultant image is converted to binary image and the regions are analyzed using connected component approach. The prior work on speed bump detection is achieved using sensors which are failed to detect speed bumps that are constructed with small height and the detection rate is affected due to erroneous identification. And the smartphone and accelerometer methodologies are not perfectly suitable for real time scenario due to GPS error, network overload, real-time delay, accuracy and battery running out. The proposed system goes very well for the roads which are constructed with proper painting irrespective of their dimension.

High Speed and Low Power Architecture for Network Intrusion Detection System

The tremendous growth in the field of modern communication and network systems places demands on the security. As the network complexity grows, the need for the automated detection and timely alert is required to detect the abnormal activities in the network. To diagnose the system against the malicious signatures, a high speed Network Intrusion Detection System is required against the attacks. In the network security applications, Bloom Filters are the key building block. The packets from the high speed link can be easily processed by Bloom Filter using state- of-art hardware based systems. As Bloom Filter and its variant Counting Bloom Filter suffer from False Positive Rate, Multi Hash Counting Bloom Filter architecture is proposed. The proposed work, constitute parallel signature detection improves the False Positive Rate, but the throughput and hardware complexity suffer. To resolve this, a Multi-Level Ranking Scheme is introduced which deduces the 13% - 16% of the power and increases the throughput to 23% - 30%. This work is best suited for signature detection in high speed network.

A Hybrid Intrusion Detection Method Based on Convolutional Neural Network and AdaBoost

To solve the problem of poor detection and limited application range of current intrusion detection methods,this paper attempts to use deep learning neural network technology to study a new type of intrusion detection method.Hence,we proposed an intrusion detection algorithm based on convolutional neural network(CNN)and AdaBoost algorithm.This algorithm uses CNN to extract the characteristics of network traffic data,which is particularly suitable for the analysis of continuous and classified attack data.The AdaBoost algorithm is used to classify network attack data that improved the detection effect of unbalanced data classification.We adopt the UNSW-NB15 dataset to test of this algorithm in the PyCharm environment.The results show that the detection rate of algorithm is99.27%and the false positive rate is lower than 0.98%.Comparative analysis shows that this algorithm has advantages over existing methods in terms of detection rate and false positive rate for small proportion of attack data.

Comparative Study on Perimeter Intrusion Detection System of High-speed Railway

The perimeter intrusion detection system is critical to China’s railway safety.An efficient intrusion detection system can effectively avoid human casualties and property damage.This article makes a comprehensive comparison of popular detection systems in recent years.It first outlines the characteristics and classification of intrusion detection systems,and then introducestherelevantliteratureofcontactandnon-contactsystemsaccordingtodifferenttypes,andalsointroducesthe principles and architecture of the models they use in detail.Finally,the detection performance and suitable environment under different system models are analyzed by comparison.

Study on Detection and Recognition of Speed Signs

Speed sign detection and recognition are the important part of the driving assistant systems.Combining gradient-based random Hough transform with BP network,a method is proposed to detect and recognize speed signs.Firstly,the gradient-based random Hough transform is used to detect and locate the speed signs.Then four contour features of the 'digit' inside the speed signs are extracted and recognized using the method of BP network.The results show that this method can detect and recognize the speed signs accurately and efficiently.

A New Sensorless Technique for the Speed Detection of an Induction Motor

This paper presents a new sensorless method, the so-called harmonic impedance / admittance, for detecting speed of induction motors, which is based on the impedance measurement, harmonic analysis and digital signal processing. The method improves theperformance of conventional voltage-based and current-based techniques, because the impedance or admittance harmonics is independent of input or output of motor system due to the system-inherent nature of impedance. It has been used successfully in detecting the rotor speed of three-phase induction motors. A comparison between the proposed method and the conventionalcurrent-based method is also demonstrated.

IDS-INT:Intrusion detection system using transformer-based transfer learning for imbalanced network traffic

A network intrusion detection system is critical for cyber security against llegitimate attacks.In terms of feature perspectives,network traffic may include a variety of elements such as attack reference,attack type,a subcategory of attack,host information,malicious scripts,etc.In terms of network perspectives,network traffic may contain an imbalanced number of harmful attacks when compared to normal traffic.It is challenging to identify a specific attack due to complex features and data imbalance issues.To address these issues,this paper proposes an Intrusion Detection System using transformer-based transfer learning for Imbalanced Network Traffic(IDS-INT).IDS-INT uses transformer-based transfer learning to learn feature interactions in both network feature representation and imbalanced data.First,detailed information about each type of attack is gathered from network interaction descriptions,which include network nodes,attack type,reference,host information,etc.Second,the transformer-based transfer learning approach is developed to learn detailed feature representation using their semantic anchors.Third,the Synthetic Minority Oversampling Technique(SMOTE)is implemented to balance abnormal traffic and detect minority attacks.Fourth,the Convolution Neural Network(CNN)model is designed to extract deep features from the balanced network traffic.Finally,the hybrid approach of the CNN-Long Short-Term Memory(CNN-LSTM)model is developed to detect different types of attacks from the deep features.Detailed experiments are conducted to test the proposed approach using three standard datasets,i.e.,UNsWNB15,CIC-IDS2017,and NSL-KDD.An explainable AI approach is implemented to interpret the proposed method and develop a trustable model.