With the advent of Industry 4.0,marked by a surge in intelligent manufacturing,advanced sensors embedded in smart factories now enable extensive data collection on equipment operation.The analysis of such data is pivo...With the advent of Industry 4.0,marked by a surge in intelligent manufacturing,advanced sensors embedded in smart factories now enable extensive data collection on equipment operation.The analysis of such data is pivotal for ensuring production safety,a critical factor in monitoring the health status of manufacturing apparatus.Conventional defect detection techniques,typically limited to specific scenarios,often require manual feature extraction,leading to inefficiencies and limited versatility in the overall process.Our research presents an intelligent defect detection methodology that leverages deep learning techniques to automate feature extraction and defect localization processes.Our proposed approach encompasses a suite of components:the high-level feature learning block(HLFLB),the multi-scale feature learning block(MSFLB),and a dynamic adaptive fusion block(DAFB),working in tandem to extract meticulously and synergistically aggregate defect-related characteristics across various scales and hierarchical levels.We have conducted validation of the proposed method using datasets derived from gearbox and bearing assessments.The empirical outcomes underscore the superior defect detection capability of our approach.It demonstrates consistently high performance across diverse datasets and possesses the accuracy required to categorize defects,taking into account their specific locations and the extent of damage,proving the method’s effectiveness and reliability in identifying defects in industrial components.展开更多
木材缺陷智能检测技术可以有效降低人工误检带来的经济损失,对提高木材加工智能化水平具有重要意义。提出了一种木材缺陷智能检测算法,通过双循环生成对抗网络(double least generative adversarial networks,DLGAN)及密集卷积网络(Dens...木材缺陷智能检测技术可以有效降低人工误检带来的经济损失,对提高木材加工智能化水平具有重要意义。提出了一种木材缺陷智能检测算法,通过双循环生成对抗网络(double least generative adversarial networks,DLGAN)及密集卷积网络(Dense-Net)来检测色差、虫眼、裂纹、节子和伤疤等5种木材常见缺陷。首先,使用DLGAN技术扩充数据集,提高数据集的多样性和数量,缓解了因训练数据不足而导致的过拟合问题;其次,基于Dense-Net的特点,采用密集的卷积块序列提高对微弱特征的提取和学习能力,以便更好地检测木材缺陷。试验结果表明,相比VGG16、Inception-v2、ResNet 3种经典卷积神经网络,基于DLGAN增广数据集训练的Dense-Net模型有效提高了木材缺陷检测模型的性能,平均准确率达到92.7%,在只使用少量训练数据的情况下模型依然具有良好的图像生成能力和训练鲁棒性。展开更多
基金supported by the Natural Science Foundation of Heilongjiang Province(Grant Number:LH2021F002).
文摘With the advent of Industry 4.0,marked by a surge in intelligent manufacturing,advanced sensors embedded in smart factories now enable extensive data collection on equipment operation.The analysis of such data is pivotal for ensuring production safety,a critical factor in monitoring the health status of manufacturing apparatus.Conventional defect detection techniques,typically limited to specific scenarios,often require manual feature extraction,leading to inefficiencies and limited versatility in the overall process.Our research presents an intelligent defect detection methodology that leverages deep learning techniques to automate feature extraction and defect localization processes.Our proposed approach encompasses a suite of components:the high-level feature learning block(HLFLB),the multi-scale feature learning block(MSFLB),and a dynamic adaptive fusion block(DAFB),working in tandem to extract meticulously and synergistically aggregate defect-related characteristics across various scales and hierarchical levels.We have conducted validation of the proposed method using datasets derived from gearbox and bearing assessments.The empirical outcomes underscore the superior defect detection capability of our approach.It demonstrates consistently high performance across diverse datasets and possesses the accuracy required to categorize defects,taking into account their specific locations and the extent of damage,proving the method’s effectiveness and reliability in identifying defects in industrial components.
文摘针对基于显性知识的智能制造缺陷检测机制在工程实践中日益凸显的若干缺陷,提出了一种基于机器视觉和深度残差收缩网络(deep residual shrinkage networks,D-RSN)的智能制造缺陷检测方法,并进行了先验环境下的仿真验证。首先利用互补金属氧化物半导体(complementary metal oxide semiconductor,CMOS)相机集群搭建快速机器视觉图像获取装置,形成融合前置训练集和后置测试集的图像特征数据池;然后利用D-RSN对数据池前置训练集进行图像缺陷特征隐性知识学习辨识,构建时间正序下的图像缺陷特征全息感知机制;最后利用深度长短期记忆(deep long short-term memory,D-LSTM)神经网络对数据池后置测试集进行图像缺陷自主检测,借助图像缺陷定位及分类函数输出检测结果。选取某医用外科口罩智能制造生产线为工程实践验证载体,对模型进行了工程应用实践验证,结果表明:所提方法较好地改善了基于显性知识的智能制造缺陷检测机制在工程实践中日益凸显的若干缺陷,可以自主学习辨识图像缺陷特征隐性知识,大幅度提高了智能制造缺陷检测有效率,图像缺陷检测均值有效率达98.37%,符合医用外科口罩智能制造生产线国检要求。
