离心逆流式超细粉干式分级机的研制

介绍了离心逆流式超细粉分级机的基本工作原理及特性，采用Ａｌ＿２＿３物料进行了超细粉分级试验。结果表明这种分级机适于超细粉分级并具有较高的分级精度，可与国外同类分级机相比，具有较大的应用前景。     

卧轮式分级机转子临界转速的计算

为避免卧轮式分级机在运转过程中产生共振,以卧轮式分级机实验机和工业样机转子为研究对象,采用传递矩阵法和基于ANSYS Workbench 16.0的有限元法对其临界转速进行计算,将计算结果与试验测试结果进行比较。结果表明,对于实验机,传递矩阵法与试验测试结果偏差为11.9%,有限元法与试验测试结果偏差为4.1%;对于工业样机,传递矩阵法与试验测试结果偏差为10.5%,有限元法与试验测试结果偏差为3.5%,说明有限元法计算结果准确性更高,认为对于卧轮式分级机转子临界转速的计算,更适合采用有限元法。     

超细粉体射流分级机的正交试验研究

采用正交试验设计和直观分析的方法,对影响超细粉体射流分级机工作的各因素进行研究,从而找出该分级机的最佳工作参数。     

离心式气流分级机的现状与进展

从分级流场构建的角度对离心式气流分级机进行梳理分类,按照分级区旋涡转轴的不同分为竖直旋涡分级机和水平旋涡分级机,并对几种代表机型的流场特征及研究进展进行了剖析,指出竖直旋涡分级机的研究较多,而水平旋涡分级机的研究相对较少,强调了合理构建与组合分级流场和淘洗流场的重要性,展望了离心式气流分级机的研究前景。     

超细粉射流分级机工业样机的研制

论述了超细粉射流分级机工业样机的研制及结构与工作原理 ,通过大量的试验与理论研究 ,证明了利用射流的附壁效应进行微米级粉体干式分级的可行性与可靠性。     

径向气流对旋风分级器的影响

为了改善分级器性能,试验引入径向气流对旋风分级器中的颗粒进行再次分离;试验物料选用催化裂化(FCC)和S-Zorb催化剂,对分级机进行了5组不同径向气速的试验。结果表明:该分级机对2种物料的最小切割粒径分别为6.5、3.3μm;试验中分级粒径为2μm时,FCC和S-Zorb催化剂的牛顿分级效率分别为91.9%和54.1%;径向风的引入破坏了康达效应的形成条件,有利于提高分级效果;进出口压降随着径向气流量的增大而降低;分级机对FCC催化剂的去"细"能力较好,对S-Zorb催化剂的去"粗"能力较好。     

超细粉射流分级机的放大及流场分布探析

在对实验室小型超细粉射流分级机流场分析的基础上,对上述机型进行了改进与放大,并通过试验研究证明改进后的机型分级性能有了很大提高,流场分布更加合理。     

控制性气流粉碎技术制备等积球形墨粉

采用自制的控制性气流粉碎机制备等积球形墨粉,通过改变粉碎强度、第一级分级机转速和第一级分级机二次风量来控制墨粉的颗粒形貌,通过改变第二级分级机转速和第二级分级机二次风量来控制墨粉粒度分布的集中性。结果表明,在流化床粉碎强度为0.6 MPa,流化床底部二次风量为86 m3/h,第一级分级机电机变频器频率为17 Hz,第二级分级机电机变频器频率为36 Hz,第二级分级机二次风量为287 m3/h时,制得墨粉的粒度分布最集中,形貌最均匀,球形度最高,此时第二级分级机产量为72.5 kg/h,成品率为79.2%。     

密友深耕超细研磨领域 开发新品卧式行星球磨机

正伴随着深冷超细气流粉碎生产线、安全防爆型气流粉碎系统和大型超细粉体分级机的成功开发和安装试车成功,日前密友粉体装备制造开始研发卧式行星超细球磨机。密友行星磨分级机在线检测生产线已经申请专利,卧式行星超细球磨机与行星磨分级机在线检测生产线有效结合将会给广大粉     

涡轮分级机分级轮流场的数值模拟与分析

为进一步研究涡轮分级机流场中的分级轮径向速度和分级区流场分布情况,更好地指导涡轮气流分级机的设计、优化和运行,通过用FLUENT6.2中的分离-隐式求解器对涡轮分级机的流场进行了模拟与分析。主要针对分级机径向速度的均匀性分析,并与实验进行比较。结果表明:进入分级轮的气流径向速度不均匀,分级轮的高度越高,径向速度越不均匀,较高的分级轮会有部分气流外溢,外溢位置、大小与分级轮的高度相关,从而引起进入分级轮的径向气流速度反而增大,高径比最好为0.3～0.5。     

Performance analysis of EM,SVD, and SVM classifiers in classification of carcinogenic regions of medical images

In this article, the performance analysis of Expectation Maximization (EM), Singular Value Decomposition (SVD), and Support Vector Machines (SVM) classifiers for classification of carcinogenic regions from various medical images is carried out. Cancer detection is one of the critical issues where excessive care needs to be taken for better diagnosis. Any classifier needs to detect the cancer with respect to the efficiency in time of detection and performance. Due to these, three classifiers are selected: Expectation Maximization (EM), Singular Value Decomposition (SVD), and Support Vector Machines (SVM). EM classifier performs as the optimizer and SVD classifier performs as the dual class classifier. SVM classifier is used as both optimizer and classifier for multiclass classification procedure and for wide stage cancer detection procedures. The performance analysis of all the three classifiers are analyzed for a group of 100 cancer patients based on the benchmark parameter such as Performance Measures and Quality Metrics. From the experimental results it is evident, that the SVM classifier significantly outperforms other classifiers in the classification of carcinogenic regions of medical images.     

Classifier performance during dynamic fine grinding in fluidized bed opposed jet mills

Dry grinding of particles to sizes below 10 µm can be realized in fluidized bed opposed jet mills. In these mills the energy for comminution is supplied by pressurized gas, which is introduced through focused nozzles. The gas transports the material towards an internal classifier, which separates the fines from the coarse material. The fines are discharged whereas the coarse material is recycled. Within this study special attention is paid to separation at the classifying wheel. Limestone batch grinding experiments were performed in a fluidized bed opposed jet mill equipped with on-line and in-line probes: The particle size distributions (PSDs) of the product flow and the solid concentration below the classifier were determined on-line. The flow field around the classifier was recorded by a high-speed camera and off-line measurements of the mill inventory and its PSD were performed. Our measurements reveal that the solid transport from the milling zone to the classifier and the classifier performance strongly depend on solid concentration. Increasing the solid feed concentration or the classifier wheel speed leads to unwanted accumulation of product-sized particles inside the mill. In particular, we find high solid loadings of up to 1.05 g?g^?1 and strong cluster formation (local zones of high solid concentration) in the vicinity of the classifier blades. Estimated separation efficiency curves of the classifier show a strong “fish-hook effect” which increases with the solid concentration. Our findings are relevant for future process optimization by careful tuning of grinding performance, holdup and classifier speed.     

Centre-based restricted nearest feature plane with angle classifier for face recognition

An improved classifier based on the nearest feature plane (NFP), called the centre-based restricted nearest feature plane with the angle (RNFPA) classifier, is proposed for the face recognition problems here. The famous NFP uses the geometrical information of samples to increase the number of training samples, but it increases the computation complexity and it also has an inaccuracy problem coursed by the extended feature plane. To solve the above problems, RNFPA exploits a centre-based feature plane and utilizes a threshold of angle to restrict extended feature space. By choosing the appropriate angle threshold, RNFPA can improve the performance and decrease computation complexity. Experiments in the AT&T face database, AR face database and FERET face database are used to evaluate the proposed classifier. Compared with the original NFP classifier, the nearest feature line (NFL) classifier, the nearest neighbour (NN) classifier and some other improved NFP classifiers, the proposed one achieves competitive performance.     

基于遗传算法的神经网络被动声呐目标分类研究

被动声呐目标识别系统中目标分类器的设计和训练是一项重要内容，本文设计了目标分类器的神经网络结构，提出了一种用改进的遗传算法训练神经网络分类器的新方法，最后，对海上实录的Ａ，Ｂ，Ｃ三类目标噪声进行了分类识别，实验结果表明基于遗传算法的神经网络分类器比传统的基于ＢＰ算法的神经网络分类源泛化性能有明显提高。     

模糊融合分类器在水雷识别中的应用

当目标的类别多时会使分类器的精度和稳健性大受影响,用神经网络分类器去完成复杂的目标分类任务是难以保证其可靠性的。引入信息融合条件下一种新型的分类器,即模糊融合分类器,该分类器可以自动“过滤”无效和冗余特征的负面影响,实现有效的特征层融合识别。采用4种特征提取方法,利用三个模糊融合神经网络作为分类器进行特征层的融合,再将分类器的输出作为决策层的融合,提高系统的分类性能。通过处理水雷实体回波数据得出的识别率表明,所选取的特征提取和分类器算法是有效的。     

分级式冲击磨及其分级机阻力损失的研究

为了研究分级式冲击磨以及分级机的阻力特性,对LNI-610-30型分级式冲击磨进行了阻力损失的现场测试与研究。结果表明:在相同流量下,单独开启冲击磨或分级机,其各自的工作阻力损失随各自传动转速的增大而增大;同时开启时(两者转向相反),由于各自形成的涡流场的相互影响,其总体阻力损失小于二者在同转速下分别开启时的阻力损失之和,其差值随着两者转速的增大而增大。     

Gas particle industrial flow simulation using RANSTAD

A turbulent gas particle finite-volume flow simulation of a representative coal classifier is presented. Typical values of the loading ratio permit a one-way coupling analysis. As a case study, the computational fluid dynamics code,ranstad, and the modelling aspects are discussed in some detail. The simulation indicates that small (≈ 30 μm) coal particles pass through the classifier to the furnace but that large (≈ 300 μm) particles are captured and remilled. The computational simulation indicates that the classifier performance can be improved by internal geometric modification. The commitment of the Electricity Commission of New South Wales (Pacific Power) to the exploitation of Computational Engineering for the improvement of all aspects of electricity generation is acknowledged.     

Real-time signal classification with an acousto-optic triple-product processor cascaded into a volume holographic classifier

An all-optical generalized linear machine applied to a high-bandwidth temporal signal-classification problem is demonstrated. The classifier consists of a dimensional increasing acousto-optic triple-product processor feature extractor cascaded through an optically addressed spatial light modulator into a volume holographic implementation of a linear classifier. Multiple-expo sure implementations of learning are used to train the classifier interconnection weights in a photorefractive crystal for a training set of wide-bandwidth temporal signals input to the acousto-optic triple-product processor. Experimental implementation of high-speed, time-shift and Doppler invariant, wide-bandwidth signal identification is demonstrated.     

Sentiment Analysis Method Based on Kmeans and Online Transfer Learning

Sentiment analysis is a research hot spot in the field of natural language processing and content security. Traditional methods are often difficult to handle the problems of large difference in sample distribution and the data in the target domain is transmitted in a streaming fashion. This paper proposes a sentiment analysis method based on Kmeans and online transfer learning in the view of fact that most existing sentiment analysis methods are based on transfer learning and offline transfer learning. We first use the Kmeans clustering algorithm to process data from one or multiple source domains and select the data similar to target domain data to establish the classifier, so that the processed data does not negatively transfer the data in the target domain. And then create a new classifier based on the new target domain. The source domain classifier and target domain classifier are combined with certain weights by using the homogeneous online transfer learning method to achieve sentiment analysis. The experimental results show that this method has achieved better performance in terms of error rate and classification accuracy.