Application of New Type Pre-classification Hydrocyclone with Centrifugal Volute in Grinding Process

Hydrocyclone is widely used in closed-circuit grinding process. However, in the first classification operation of coarse particles with high pulp density, the shortcomings of traditional cyclone are that the grinding cycle load is much high, the apex of cyclone is easily to be blocked and classification efficiency is less. Specifically, the problems of traditional cyclone used in grinding process are as follows： （1） Mill utilization factor is low and its handling capacity is small; （2） Coarse particles mixing in cyclone overflow affects the following separation process and fine particles mixing in underflow causes over-grinding, which affects the total recovery rate of valuable minerals; （3） High grinding cycle load leads to large amount of high-density slurry pumping, which causes high energy consumption and severe wear of cyclones, pipelines and pumps. The applications of new type pre-classification hydrocyclone with centrifugal volute in the first classification process of iron mine mill are introduced in the paper. Pulp particles fed in the centrifugal volute are arranged in advance, so that coarse particles can be far away from the overflow pipe, which can reduce the short circuit current to avoid coarse particles entering overflow and improve classification efficiency and accuracy of cyclone. The strong points of the new cyclone in the coarse classification operation are as follows： （1） Finer overflow and less fine particles mixing in underflow improves classification efficiency more than 10%; （2） Lower ball mill load cycle improves ball capacity more than 10%; （3） Grinding energy consumption reduces by more than 20% and cyclone feed pump reduces energy consumption by more than 12%. In short, new type pre-classification cyclone with centrifugal volute solves the problems of fine particles mixing in underflow, high grinding cycle load and less classification efficiency in the coarse classification operation. Therefore, it has broad application prospects in ferrous metal and non-ferrous metal ore dressing plant.

Image Steganalysis Based on Deep Content Features Clustering

The training images with obviously different contents to the detected images will make the steganalysis model perform poorly in deep steganalysis.The existing methods try to reduce this effect by discarding some features related to image contents.Inevitably,this should lose much helpful information and cause low detection accuracy.This paper proposes an image steganalysis method based on deep content features clustering to solve this problem.Firstly,the wavelet transform is used to remove the high-frequency noise of the image,and the deep convolutional neural network is used to extract the content features of the low-frequency information of the image.Then,the extracted features are clustered to obtain the corresponding class labels to achieve sample pre-classification.Finally,the steganalysis network is trained separately using samples in each subclass to achieve more reliable steganalysis.We experimented on publicly available combined datasets of Bossbase1.01,Bows2,and ALASKA#2 with a quality factor of 75.The accuracy of our proposed pre-classification scheme can improve the detection accuracy by 4.84%for Joint Photographic Experts Group UNIversal WAvelet Relative Distortion(J-UNIWARD)at the payload of 0.4 bits per non-zero alternating current discrete cosine transform coefficient(bpnzAC).Furthermore,at the payload of 0.2 bpnzAC,the improvement effect is minimal but also reaches 1.39%.Compared with the previous steganalysis based on deep learning,this method considers the differences between the training contents.It selects the proper detector for the image to be detected.Experimental results show that the pre-classification scheme can effectively obtain image subclasses with certain similarities and better ensure the consistency of training and testing images.The above measures reduce the impact of sample content inconsistency on the steganalysis network and improve the accuracy of steganalysis.