Measurement and analysis of fluorescent whitening agent content in soybean milk based on image techniques

This paper presents a method for measuring and quantitatively analyzing the fluorescent whitening agent in soybean milk based on image techniques. After collecting the fluorescent images of the soybean milk samples, the top seven wavelet moment invariants are selected according to the sample training and experimental comparison. Then calculate the standard templates of the 49 classes of calibration samples with different fluorescent whitening agent content ranging from 0.02 mg/ml to 0.5 mg/ml. The minimum distance method is carried out to match the testing sample with the calibration template, which realizes the quantitative analysis. To verify the effectiveness of the presented method, the prediction experiment is carried out. Results show that the absolute errors are within 0.005 mg/ml and the relative errors are within 5%, which means this method can measure the fluorescent whitening agent in soybean milk. This research presents a new approach for detecting the illegal fluorescence additive in food production.     

Frequency domain image analysis for the characterization of porous products

Many pharmaceutical products are obtained via freeze-drying of liquid solutions to obtain stable long lasting preparations. The freeze-dry process produces porous cakes whose structure strongly depends on the freezing phase, so that monitoring and optimizing this phase can help both reducing the product cost and insuring its constant quality. Nowadays the optimization is usually performed by determining the cake mass transfer coefficient via a costly process in pilot plants, while the quality is assured only by controlling the process conditions. This paper describes an alternative way of approximately estimating the mass transfer coefficient, which is based on the observation of the product structure by a simple electron microscope followed by a frequency domain imaging process. While the process has been designed and characterized specifically for pharmaceutical products, the proposed approach can be used in several other fields where the characteristics of porous material have to be monitored.     

Charge coupled device based on optical tomography system in detecting air bubbles in crystal clear water

Optical tomography is one of the tomography methods which are non-invasive and non-intrusive system, consisting of emitter with detectors. Most of the available detectors systems are intrusive where sensors or probes need to be placed within the analyzed processes and this will create disturbances in the current processes. This research are conducted in order to analyze and proved the capability of laser with Charge Coupled Device in an optical tomography system for detecting air bubbles exist in crystal clear water. Experiments in detecting moving air bubbles are conducted. The images of captured data are reconstructed based on filtered image of Linear Back Projection with Hybrid algorithms. As a conclusion, this research have successfully developed an optical tomography system that capable to capture the image and measure the diameter and velocity of rising air bubbles in a non-flowing crystal clear water.     

装载机八杆机构工作装置优化设计

为了提高装载机八杆机构工作装置的铲斗平移性,介绍了一种基于ADAMS的可行且快速的优化设计方法。首先用Solidworks建立工作装置的三维模型,通过数据交换接口将该模型导入ADAMS中建立工作装置的虚拟样机模型。接着以工作装置各个铰接点的坐标为设计变量,其它设计要求为约束函数,铲斗平移性为目标函数,以此建立工作装置优化设计的数学模型。最后利用ADAMS强大的计算功能进行优化计算找出目标函数的最优解,从而使铲斗的平移性得到显著提高,为接下来工作装置的多体动力学分析奠定了模型基础。     

自行车制动蓄能装置优化设计

采用圆柱螺旋弹簧作为蓄能主元件,以自行车为实验载体设计了一种弹簧式制动蓄能装置,通过搭建实验平台验证了该技术路线可行。在满足蓄能要求和强度条件下,以蓄能装置的质量最小为优化目标,建立了其质量优化数学模型并设计了优化算法流程,对主要零部件直筒形外壳、圆柱弹簧、滚珠丝杠和锥齿轮副质量优化的约束条件和目标函数进行了分析与推导。通过Matlab软件对优化模型进行了计算,并利用ANSYS软件对优化结果进行仿真验证,结论可行。优化得到的蓄能装置主要零部件总质量最小值是5.446kg,实现了制动蓄能装置整体质量优化的目的,降低了蓄能装置附加于车体上引起车辆行驶过程中的额外耗能。     

基于机器视觉及深度学习的静脉药物调配机器人药瓶识别北大核心

静脉药物调配机器人需要对数百种不同类型的药物进行调配,不同药物药瓶类型的识别、测量是精准调配的关键。对静脉药物调配机器人在药瓶类型分类、药瓶关键尺寸测量等不同任务要求情况下,运用基于机器视觉方法和深度学习框架YOLOv5s,实现了一种高效稳定的识别测量方法。结合机器视觉方法的测量准确性,深度学习方法对背景、光源的不敏感性,实现配药过程中不同环节药瓶的准确识别、测量。并通过实验定量地检测背景、环境光源对于识别结果的影响。     

基于改进GA-KSW熵法的无人机拍摄绝缘子故障识别

针对输电线路中绝缘子的故障问题,设计并实现一套绝缘子自爆故障识别算法。设计无人机整体构架,包括导航能力、避障能力以及高压线旁工作的抗干扰能力;对传统遗传算法进行改进,结合最佳熵阈值确定法对绝缘子图像进行分割;利用形态学得到纯净的绝缘子串;采用所设计的拟合算法推测绝缘子应有位置,分别从正视图和斜视图对绝缘子自爆故障进行识别。结果表明：所提算法在分割绝缘子图像时精确度高,速度比传统遗传算法提高了约75%;该算法适用于多角度拍摄的绝缘子故障识别,为无人机拍摄的绝缘子故障识别提供了保障。     

基于改进SIFT算法的机械臂识别抓取研究北大核心

为解决水下机器人进行水下目标物识别时,存在的计算速度慢、抗噪声能力差等问题,提出一种基于SIFT和FLANN的图像识别算法,并在自主研发的机械臂平台上进行验证。使用改进算法提高目标识别的准确率;基于D-H法建立机械臂模型进行运动学分析,实现系统优化控制。利用机械臂进行多组抓取实验。结果表明:所提方法不仅可以准确地识别海参,同时可以自动调节识别框的位置,提高机械臂抓取的成功率,验证了该算法的有效性。     

New approach in tool wear measuring technique using CCD vision system

This paper suggests a reliable direct measuring procedure for measuring different tool wear parameters. Modern image processing techniques and machine vision systems today enable direct tool wear measurement to be accomplished in-cycle. The presented system is characterized by its measurement flexibility, high spatial resolution and good accuracy. The system consists of a light source to illuminate the tool, CCD camera, laser diod (used in conjunction with profile deepness assessment) with linear projector, grabber for capturing the picture, and a PC. The technique is specially characterized by its determination of profile deepness with the help of projected laser raster lines on a tool surface. So it has advantage comparing with other techniques, which can measure only 2D profiles. With the technique presented in this paper a 3D image of relief surface can be obtained without having need to employ a very complicated measuring system. All indirect methods like acoustic emission, force measurement, spindle current measurement, vibration sensors, etc. are very time consuming and demand very expensive subsidiary measurement equipment, compared with the method presented here.     

铸造铅合金曲面工件X射线检测工艺研究

针对铸造铅合金曲面工件的内部质量检测问题，通过研究射线检测工艺，优化射线检测参数和研制孔型像质计，实现了铅铸件的射线检测和检测过程质量控制。结果表明可检出工件内部小至Ф3mm的缺陷，且缺陷主要为疏松和渣孔。