An image segmentation method of pulverized coal for particle size analysis

An important index to evaluate the process efficiency of coal preparation is the mineral liberation degree of pulverized coal,which is greatly influenced by the particle size and shape distribution acquired by image segmentation.However,the agglomeration effect of fine powders and the edge effect of granular images caused by scanning electron microscopy greatly affect the precision of particle image segmentation.In this study,we propose a novel image segmentation method derived from mask regional convolutional neural network based on deep learning for recognizing fine coal powders.Firstly,an atrous convolution is introduced into our network to learn the image feature of multi-sized powders,which can reduce the missing segmentation of small-sized agglomerated particles.Then,a new mask loss function combing focal loss and dice coefficient is used to overcome the false segmentation caused by the edge effect.The final comparative experimental results show that our method achieves the best results of 94.43%and 91.44%on AP50 and AP75 respectively among the comparison algorithms.In addition,in order to provide an effective method for particle size analysis of coal particles,we study the particle size distribution of coal powders based on the proposed image segmentation method and obtain a good curve relationship between cumulative mass fraction and particle size.

Effects of Sn residue on the high temperature stability of the H_2-permeable palladium membranes prepared by electroless plating on Al_2O_3 substrate after SnCl_2–PdCl_2 process: A case study

The stability of composite palladium membranes is of key importance for their application in hydrogen energy systems. Most of these membranes are prepared by electroless plating, and beforehand the substrate surface is activated by a SnCl_2–PdCl_2 process, but this process leads to a residue of Sn, which has been reported to be harmful to the membrane stability. In this work, the Pd/Al_2O_3 membranes were prepared by electroless plating after the SnCl_2–PdCl_2 process. The amount of Sn residue was adjusted by the SnCl_2 concentration, activation times and additional Sn(OH)_2coating. The surface morphology, cross-sectional structure and elemental composition were analyzed by scanning electron microscopy(SEM), metallography and energy dispersive spectroscopy(EDS), respectively. Hydrogen permeation stability of the prepared palladium membranes were tested at450–600 °C for 400 h. It was found that the higher SnCl_2 concentration and activation times enlarged the Sn residue amount and led to a lower initial selectivity but a better membrane stability. Moreover, the additional Sn(OH)_2coating on the Al_2O_3 substrate surface also greatly improved the membrane selectivity and stability.Therefore, it can be concluded that the Sn residue from the SnCl_2–PdCl_2 process cannot be a main factor for the stability of the composite palladium membranes at high temperatures.

Marketing of Transnational Maize Seed Enterprises from the Perspective of Customer Equity

Customer is important equity of an enterprise. Customer equity is the total combined customer lifetime values of all of the company's customers. In the context of invasion of transnational seed companies,how to cope with huge crisis and challenge is a problem to be solved by national companies and government. From the perspective of customer equity driving factors and sub-driving factors,this paper made an empirical study on transnational and national maize seed enterprises using principal component analysis( PCA). Results indicated that the driving factors for customer equity of national and transnational maize seed enterprises are basically similar,while there are large differences in ranking of importance of principal components. Besides,there are great differences in sub-driving factors of customer equity.

Evolution of precipitate and precipitate/matrix interface in Al-Zn-Mg-Cu(-Ag)alloys

Evolution of precipitate and precipitate/matrix interface in artificially aged Al-Zn-Mg-Cu(-Ag)alloys has been systematically studied.In the early stage of ageing,Ag,as a fast diffuser,can promote the formation of solute pairs and small clusters.Solute clusters are further demonstrated to be able to act as precursors forη’precipitates by in-situ STEM heating.With prolonged ageing time,the precipitate/matrix interface evolves from the Zn-dominated interface between early-stageη’and Al matrix to the Zn and Mg co-segregatedη’/Al andη_(2)/Al interfaces.Theη’/Al interfacial layers are shown to precede the formation ofη’,while theη_(2)/Al interfaces are found to be closely related to the thickening process ofη_(2)and the involved particular atomic movements are specified.Experimental observations and DFT calculations re-veal that forη’andη_(2),Ag can dissolve into the precipitate as well as locate at the precipitate/matrix interface without showing preference.For Cu,its dissolution in the precipitate and segregation on the interface mainly occur forη_(2)rather thanη’.The incorporation of Ag and Cu does not change the defined precipitate structure.