基于遗传算法改进的BP神经网络模型的磨损机理智能识别

通过提取磨粒形状特征参数、颜色特征参数和表面纹理等特征参数对磨粒形态进行量化表征,并以此为输入矢量,引入遗传算法(GA)改进BP神经网络对磨粒进行自动分类识别,建立遗传算法改进的BP神经网络模型,并给出具体的算法实现过程。分别应用遗传算法改进的BP神经网络模型和未引入遗传算法改进的BP神经网络模型对磨粒图像进行智能识别。实验结果表明,遗传算法改进的BP神经网络综合了遗传算法的全局优化和BP算法局部搜索速度快的特点,网络识别率较高,具有较好的全局性。     

Surface defect detection in tiling Industries using digital image processing methods: Analysis and evaluation

Ceramic and tile industries should indispensably include a grading stage to quantify the quality of products. Actually, human control systems are often used for grading purposes. An automatic grading system is essential to enhance the quality control and marketing of the products. Since there generally exist six different types of defects originating from various stages of tile manufacturing lines with distinct textures and morphologies, many image processing techniques have been proposed for defect detection. In this paper, a survey has been made on the pattern recognition and image processing algorithms which have been used to detect surface defects. Each method appears to be limited for detecting some subgroup of defects. The detection techniques may be divided into three main groups: statistical pattern recognition, feature vector extraction and texture/image classification. The methods such as wavelet transform, filtering, morphology and contourlet transform are more effective for pre-processing tasks. Others including statistical methods, neural networks and model-based algorithms can be applied to extract the surface defects. Although, statistical methods are often appropriate for identification of large defects such as Spots, but techniques such as wavelet processing provide an acceptable response for detection of small defects such as Pinhole. A thorough survey is made in this paper on the existing algorithms in each subgroup. Also, the evaluation parameters are discussed including supervised and unsupervised parameters. Using various performance parameters, different defect detection algorithms are compared and evaluated.     

基于局部纹理描述算子的手掌静脉身份识别

由于手掌生理结构特性和采集环境因素影响,手掌静脉识别系统中所获取图像容易出现噪声过大、光照不均匀等现象,导致识别性能降低.为了解决这一实际问题,提出一种基于局部纹理描述算子的掌脉识别方法.首先使用Gamma校正、DoG滤波、对比度均衡等手段对掌脉图像进行预处理,降低光照影响.然后将掌脉图像分成互不重叠的区块,使用局部三值模式(LTP)提取每一小块的纹理特征,并加以融合,最后利用卡方距离进行匹配识别.在香港理工大学接触式掌脉图库和自建的非接触式掌脉图库上进行实验测试,结果表明,当图像分块大小为16×16像素时,本方法获得了最高的正确识别率,分别为99.981 6％,99.299 4％,优于其他典型方法,提升了掌脉识别系统的性能,增强了系统的鲁棒性,具有实际应用价值.     

基于模糊C-均值聚类的小波分析人脸识别

提出了一种基于改进的模糊C-均值聚类分类器的不完全小波分析人脸识别方法。实验证明,该文提出的方法能够提高人脸识别率,降低了运行时间。     

Gas recognition algorithm applied in porphyrin array gas detection system北大核心CSCD

The difference map is the basis of identifying gases by the PSA chips. However, there are differences between each difference map of a gas, which is called the“divergent problem”. A pattern recognition algorithm based on backpropagation neural network and rough set was described, which was employed in the porphyrin chemical sensor array integrated system. That algorithm picked up the spots whose color changed obviously using the rough set, and set their values as input of BP network. Comparing with the result of Euclidean distance clustering and BP neural network identification without removing unnecessary data as input, the result of the algorithm proposed in this article has higher identification accuracy to the divergence experimental data. ©, 2014, The Editorial Office of Chinese Journal of Sensors and Actuators. All right reserved.     

国内外板带材表面质量检测方法研究进展

随着板带材越来越广泛的应用于工业生产,板带材的表面质量问题也越来越受到用户的关注.本文介绍了传统检测法、自动检测法以及机器视觉检测法三种常用的表面质量检测法,对其中的优缺点进行分析表明,采用面阵CCD技术和线阵CCD技术,结合自学习神经网络分类的机器视觉检测,在生产中应用效果较好.最后总结了板带材检测方法的发展方向:研究更有效的分类识别算法分类识别板带材的表面缺陷;优化图像采集和处理的算法,缩短计算时间.     

模具行业信息

<正>新兴战略性产业将牵引中国模具产业增长在当前"后危机时代",世界各主要发达国家和经济体均选择了不同的新兴产业作为突破口。奥巴马政府将新兴产业重点放在新能源和环保产业上,欧盟重在将"绿色技术"和其他高端技术提升至全球领先水平,日本把重点产业放在新型汽车、低碳产业、新能源(太阳能)等新兴产业,韩国将绿色技术、尖端产业融合、高附加值服务等三大领域共17项新兴产业确定为重点产业。尽管各国的政治经济体制不同,但无论是以市场经济为主导的欧美国家,还是以政府主导型经济为主的东亚国家和地区,政府大多对未来需要重点发展的新兴产业给予必要的培育和扶持。如今,中国政府已     

Short communication: Changes in gait symmetry in healthy and lame dairy cows based on 3-dimensional ground reaction force curves following claw trimming

Lameness is a frequent health problem in dairy cows. This preliminary study aimed to detect gait differences between healthy and lame walking cows using 3-dimensional force plates. We examined left–right leg symmetry changes of healthy and lame Holstein dairy cows following claw trimming. Gait scoring (GS) was performed on d −5, 0, 1, and 7 relative to claw trimming. Before the experiment, 5 cows walked normally (initial GS = 1) and 4 cows limped moderately on a hind leg (initial GS = 3). Gait was measured on d −2, −1, 0, 1, and 7 relative to trimming by obtaining ground reaction forces as cows walked repeatedly across 2 parallel 3-dimensional force plates. From the ground reaction forces, stance phase data were derived using computerized procedures. Left–right leg symmetries of entire curves in the 3 force directions were calculated. Effects of lameness and trimming were analyzed in a mixed model, using a low lameness threshold (GS > 1). One week after claw trimming, only one cow was mildly lame. In addition, the symmetries of all 3 dimensions were significantly improved shortly after trimming. Importantly, lameness significantly worsened vertical symmetry. Lame cows walked significantly more slowly than healthy cows. In conclusion, all force symmetries seemed capable of detecting gait responses to claw trimming. Although our results are based on a small number of animals, vertical leg symmetry was affected by lameness.     

切削颤振信号的混沌时间序列识别方法研究

对切削颤振的在线监测识别是提高加工质量的关键技术之一。基于离散动力系统非线性混沌控制理论,以加工过程振动信号为非线性系统输入量,采用嵌入时间序列和关联积分的C-C算法,确定最佳嵌入维数m与时间延迟τ,进而对在线监测获得的离散振动信号进行相空间重构。实施铣削颤振试验,采用上述时间序列分析方法获得颤振产生前后的相图,分析表明相图表现出混沌特性,实现了切削颤振的识别。     

一种基于加速度信息的上肢动作识别研究方法

提出一种基于GM阈值的二叉判决分析法,应用于人体上肢动作的分类识别研究。选用MEMS三轴加速度传感器ADXL345,设计一套人体动作的加速度采集系统。自定义上肢动作进行实验,采集人体执行上肢动作时的三维加速度信号后,进行小波阈值去噪的预处理过程,提取上肢动作的几何均值GM(Geometric Mean)作为特征值进行阈值的选取。实验结果表明:结合小波分析理论方法,基于GM阈值的方法实现了人体上肢动作的分类识别,并验证了系统设计及理论算法的简便性、高效性,对基于加速度传感器的动作识别研究具有一定的参考价值。