Retinal Vessel Extraction Framework Using Modified Adaboost Extreme Learning Machine

An explicit extraction of the retinal vessel is a standout amongst the most significant errands in the field of medical imaging to analyze both the ophthalmological infections, for example, Glaucoma, Diabetic Retinopathy (DR), Retinopathy of Prematurity (ROP), Age-Related Macular Degeneration (AMD) as well as non retinal sickness such as stroke, hypertension and cardiovascular diseases. The state of the retinal vasculature is a significant indicative element in the field of ophthalmology. Retinal vessel extraction in fundus imaging is a difficult task because of varying size vessels, moderately low distinction, and presence of pathologies such as hemorrhages, microaneurysms etc. Manual vessel extraction is a challenging task due to the complicated nature of the retinal vessel structure, which also needs strong skill set and training. In this paper, a supervised technique for blood vessel extraction in retinal images using Modified Adaboost Extreme Learning Machine (MAD-ELM) is proposed. Firstly, the fundus image preprocessing is done for contrast enhancement and in-homogeneity correction. Then, a set of core features is extracted, and the best features are selected using “minimal Redundancy-maximum Relevance (mRmR).” Later, using MAD-ELM method vessels and non vessels are classified. DRIVE and DR-HAGIS datasets are used for the evaluation of the proposed method. The algorithm’s performance is assessed based on accuracy, sensitivity and specificity. The proposed technique attains accuracy of 0.9619 on the DRIVE database and 0.9519 on DR-HAGIS database, which contains pathological images. Our results show that, in addition to healthy retinal images, the proposed method performs well in extracting blood vessels from pathological images and is therefore comparable with state of the art methods.     

Effect of hyperbranched poly(citric polyethylene glycol) with various polyethylene glycol chain lengths on starch plasticization and retrogradation

A series of hyperbranched poly(citric polyethylene glycol) (PCPEG) materials with varied polyethylene glycol (PEG) chain lengths as plasticizers were mixed with maize starch (MS) via cooking and film‐forming. The structure, pasting property, plasticization, aging property, moisture absorption and compatibility of plasticized starches were studied by means of Fourier transform infrared spectroscopy, X‐ray diffraction, rapid viscosity analysis, tension testing, moisture absorption measurements and scanning electron microscopy. Compared with PEG and citric acid, PCPEG was more effective in promoting starch chain movement and inhibiting the retrogradation of starch film. Also, PCPEG/MS had smaller moisture content. The longer the plasticizer chain, the better were the aging resistance and moisture resistance of starch. But with an increase of PEG chain length, mechanical properties of PCPEG/MS deteriorated and the compatibility between PCPEG and MS decreased. The hyperbranched derivative of PEG with longer chain exhibited improved plasticization and compatibility with starch. © 2019 Society of Chemical Industry     

数据驱动的机床等待过程节能方法研究

为了降低机床等待过程中的能耗，提出了一种实时数据驱动的机床等待时间预测与节能控制方法。首先，建立了射频识别驱动的生产进度评估方法，并以生产进度数据作为输入，构建了基于堆栈降噪自编码的机床等待时间预测模型；其次，依据预测的机床等待时间，提出了机床状态切换方法，以降低机床能耗；最后，通过一个电梯零部件制造车间的案例分析，表明该方法的预测误差仅为4.1%，同时将机床等待过程能耗降低了57%，实现了制造车间的节能减排。     

基于SolidWorks和三坐标测量仪的螺杆转子精滚刀建模与检测方法

介绍了基于SolidWorks软件的螺杆转子精加工滚刀的一种精确建模方法和利用该模型对滚刀的关键工序进行模拟验证的方法,同时介绍了在三坐标测量仪上利用螺杆转子精滚刀模型和曲线功能对螺杆转子精滚刀齿形进行检测的方法。     

袋装水泥装车机及拨板机构的设计与研究

针对袋装水泥装车半自动化问题，设计一款全自动装车机。首先，根据袋装水泥车间生产状况，确定水泥装车方案，即采用抽屉式逐层装车原理，利用ＳｏｌｉｄＷｏｒｋｓ创建装车机三维模型；其次，为使水泥包快速准确地到达指定位置，针对拨板机构中的分拨板及导柱进行受力分析，建立其力学模型，推导出应力公式；最后，通过 ＡＮＳＹＳ有限元软件进行分拨板的力学仿真，为后续的优化设计提供依据。     

Heat transfer inside a horizontal channel with an open trapezoidal enclosure subjected to a heat source of different lengths

The heat transfer phenomena inside a horizontal channel with an open trapezoidal enclosure subjected to a heat source of different lengths was investigated numerically in the present work. The heat source is considered as a local heating element of varying length, which is embedded at the bottom wall of the enclosure and maintained at a constant temperature. The air flow enters the channel horizontally at a constant cold temperature and a fixed velocity. The other walls of the enclosure and the channel are kept thermally insulated. The flow is assumed laminar, incompressible, and two‐dimensional, whereas the fluid is considered Newtonian. The results are presented in the form of the contours of velocity, isotherms, and Nusselt numbers profiles for various values of the dimensionless heat source lengths (0.16 ≤ ε ≤ 1). while, both Prandtl and Reynolds numbers are kept constant at (Pr = 0.71) and (Re = 100), respectively. The results indicated that the distribution of the isotherms depends significantly on the length of the heat source. Also, it was noted that both the local and the average Nusselt numbers increase as the local heat source length increases. Moreover, the maximum temperature is located near the heat source location.     

基于SARIMA-GRNN-SVM的短期商业电力负荷组合预测方法

针对短期商业电力负荷预测准确性与周期难以满足现有电力现货市场的问题,提出了一种基于SARIMAGRNN-SVM(seasonal autoregressive integrated moving average-generalized regression neural network-support vector machine)的商业电力负荷组合预测模型。首先,对商业电力负荷变化的周期规律与随机因素的复杂影响进行了分析;然后,结合以上分析,选用SARIMA和GRNN为单一预测模型对商业电力负荷进行预测,并利用SVM进行组合,实现日前商业电力负荷预测;最后,通过某商业综合体的电力负荷数据进行验证。所提组合预测模型较单一预测模型拥有更优的预测精度与鲁棒性,可以为短期商业电力负荷预测提供借鉴。     

Investigation of fracture behavior of cement-bonded corundum castables using wedge splitting test and digital image correlation method

To investigate the fracture behavior of cement-bonded corundum castables, various cement contents and pre-treating temperatures have been comparatively studied using the wedge splitting method and the digital image correlation technique. The results show that the microstructure enhances the mechanical properties, so the fracture energy and the maximum load as well as the fracture modes are affected correspondingly. The castables demonstrate the highest fracture energy and maximum load at 1600 °C with cement content of 10 wt% due to an appropriate amount of CA6. At the temperatures of 110 and 1100 °C, the crack propagation within the matrix and along the interface are dominated whereas within the aggregates significantly increased at 1600 °C, leading to the brittleness of materials. However, increasing the cement content can reduce their brittleness, caused by the maximum strain in thex-direction, largest length of the main crack, and high ratio of crack propagation in the matrix.     

680m~3浮选机工业化应用过程中的动力学性能测试与分析

680m~3浮选机投入生产试运行已一年有余,表现出卓越的设备稳定性和分选性。本文从浮选流体动力学角度出发,对680m~3浮选机在带矿运行过程中的充气性能、矿浆循环悬浮性能和气泡大小及其负载性能进行了测试分析。结果表明,680m~3浮选机充气量可以达到1.1m~3/(m~2·min)以上,能够满足一般硫化矿大气量的生产需求,空气分散度在7以上,平均气含率约7%;不同深度浮选槽内矿浆浓度和粒级分布较为均匀,无明显分层现象。气泡表面积通量可达39.20s-1,随着气泡的上浮,气泡负载呈现上升趋势,最高可达3.37g/L。优越的浮选流体动力学特性充分地保障了680m3浮选机良好的分选效果。