柱塞卡滞原因分析

某柱塞泵工作中发生柱塞卡滞,经显微形貌观察、光谱分析、电子探针面扫描分析和显微硬度分析等,确定柱塞卡滞的根本原因为原材料组织中存在严重的网状共晶碳化物,降低了强度和韧性,增大了柱塞球面表层的脆性,进而导致了球面部位的接触疲劳抗力下降。严重的疲劳磨损与接触疲劳造成了柱塞球面脱层破坏,由此产生的金属碎屑进入柱塞与衬套的配合间隙处,进而限制了柱塞的自由运动。     

Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems

We present a data-driven method for monitoring machine status in manufacturing processes. Audio and vibration data from precision machining are used for inference in two operating scenarios: (a) variable machine health states (anomaly detection); and (b) settings of machine operation (state estimation). Audio and vibration signals are first processed through Fast Fourier Transform and Principal Component Analysis to extract transformed and informative features. These features are then used in the training of classification and regression models for machine state monitoring. Specifically, three classifiers (K-nearest neighbors, convolutional neural networks and support vector machines) and two regressors (support vector regression and neural network regression) were explored, in terms of their accuracy in machine state prediction. It is shown that the audio and vibration signals are sufficiently rich in information about the machine that 100% state classification accuracy could be accomplished. Data fusion was also explored, showing overall superior accuracy of data-driven regression models.     

基于深度学习的人体姿态估计方法综述

基于深度学习的人体姿态估计方法旨在通过构建合适的神经网络，直接从二维的图像特征中回归出人体姿态信息。主要按照2D人体姿态估计到3D人体姿态估计的顺序，并从单人检测与多人检测、稀疏的关节点检测与密集的模型构建等方面，对近年来基于深度学习的人体姿态估计方法进行系统介绍，从而初步了解如何通过深度学习的方法得到人体姿态的各个要素，包括肢体部件的相对朝向和比例尺度、骨骼关节点的位置坐标和连接关系，甚至更为复杂的人体蒙皮模型信息。最后,对当前研究面临的挑战以及未来的热点动向进行概述，清晰地呈现出该领域的发展脉络。     

深度学习识别光网络单元故障的设计与应用

为解决依赖装维上门鉴别光网络单元故障带来的不便,可以从机器视觉入手实现自动化故障识别。近年,ImageNet挑战赛的成功推动了物体识别技术的跨越式发展,特别是基于卷积的深度学习技术在视觉识别方面已经达到人类水平,为光网络单元故障的自动识别提供了技术基础。文章对识别光网络单元的工作状态进行了研究,将设备工作状态分为7个场景,提出了利用手机APP采集图片识别故障的解决方案并投入了实际生产;重点阐述了深度学习模块的设计与实现,提出一种通过算法整合的方式综合运用物体检测和图像分类算法,分3阶段逐步求精,解决了图片过滤,光网络单元型号和状态识别等问题,实现了基于计算机视觉自动识别光网络单元故障。从数据上看产品的端到端准确率超过84%,识别速度达到10 FPS,月均提供服务超过1万人次,在减少用户等待的同时节约了人力资源。     

Moderate lameness leads to marked behavioral changes in dairy cows

Lameness is one of the most prevalent diseases affecting the welfare of cows in modern dairy production. Lameness leads to behavioral changes in severely lame cows, which have been investigated in much detail. For early detection of lameness, knowledge of the effects of moderate lameness on cow behavior is crucial. Therefore, the behavior of nonlame and moderately lame cows was compared on 17 Swiss dairy farms. On each farm, 5 to 11 nonlame (locomotion score 1 of 5) and 2 to 7 moderately lame (locomotion score 3 of 5) cows were selected for data collection in two 48-h periods (A, B) separated by an interval of 6 to 10 wk. Based on visual locomotion scoring, 142 nonlame and 66 moderately lame cows were examined in period A and 128 nonlame and 53 moderately lame cows in period B. Between these 2 periods, the cows underwent corrective hoof trimming. Lying behavior, locomotor activity, and neck activity were recorded by accelerometers (MSR145 data logger, MSR Electronics GmbH, Seuzach, Switzerland), and feeding and rumination behaviors by noseband sensors (RumiWatch halter, ITIN + HOCH GmbH, Liestal, Switzerland). Furthermore, visits to the brush and the concentrate feeder, and the milking order position were recorded. In comparison with nonlame cows, moderately lame cows had a longer lying duration, a longer average lying bout duration, and a greater lateral asymmetry in lying duration. Average locomotor activity, locomotor activity during 1 h after feed delivery or push-ups, and average neck activity were lower in moderately lame cows. Eating time and the number of eating chews (jaw movements) were reduced in moderately lame compared with nonlame cows, whereas no effect of moderate lameness was evident for ruminating time, number of ruminating chews and boluses, and average number of ruminating chews per bolus. Moderately lame cows visited the concentrate feeder and the brush less frequently, and they were further back in the milking order compared with nonlame cows. In conclusion, nonlame and moderately lame cows differed in a biologically relevant way in many of the behavioral variables investigated in this study. Therefore, the use of these behavioral changes seems to be promising to develop a tool for early lameness detection.     

Graph-based video fingerprinting using double optimal projection

A double optimal projection method that involves projections for intra-cluster and inter-cluster dimensionality reduction are proposed for video fingerprinting. The video is initially set as a graph with frames as its vertices in a high-dimensional space. A similarity measure that can compute the weights of the edges is then proposed. Subsequently, the video frames are partitioned into different clusters based on the graph model. Double optimal projection is used to explore the optimal mapping points in a low-dimensional space to reduce the video dimensions. The statistics and geometrical fingerprints are generated to determine whether a query video is copied from one of the videos in the database. During matching, the video can be roughly matched by utilizing the statistics fingerprint. Further matching is thereafter performed in the corresponding group using geometrical fingerprints. Experimental results show the good performance of the proposed video fingerprinting method in robustness and discrimination.     

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

上榆泉煤矿煤泥水多参数在线检测系统应用研究

针对上榆泉煤矿煤泥水性质参数人工检测周期长、误差大、滞后性严重的问题,采用多参数传感器和PLC,开发了煤泥水多参数在线检测系统。经过8 h稳定运行,平均结果显示该厂煤泥水参数为pH值为7.71、浓度9.45%、中值直径(D50)39.56μm、流量2 440 m3/h、水质硬度428.94 mg/L,与人工检测结果相一致。应用结果表明,该检测系统能够实现煤泥水多参数在线监测和数据分析功能,使煤泥水的处理更高效。     

视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。