flotation machine 2019

unistar

unistar

Qingdao Unistar Environmental Technology Co., Ltd is a high-tech industrial enterprise dedicated to environmental protection, ecological restoration and comprehensive prevention and control of environmental pollution. The company specializes in various environmental protection technology research and popularization, environmental protection equipment production, environmental protection engineering design and construction, environmental protection project operation and management.

At the beginning of its establishment, The B.I.G adhered to the "Four High" development concept of high starting point, high technology, high professional, high efficiency and high quality service. Through cooperation with colleagues, scientific research institutes, enterprises and company such as Ocean University of China, Environmental College of Qingdao University of technology, Hong Kong Locke Environmental Protection Construction (International) Co., Ltd. and South Korea Shiyu Environmental Corporation.

We continue to develop new technologies and products, use highly specialized technology and equipment to create high-quality products, high-quality projects, and strive to become the leading comprehensive environmental service provider in China.

Unistar Environmental Technology Co., Ltd. is mainly engaged in industrial waste gas treatment equipment, industrial waste water treatment equipment, domestic sewage treatment equipment and various specifications of environmental protection supporting equipment. we can provide comprehensive services in scheme design, process design, product processing and engineering installation.

We always put our customers first and pay attention to their needs so as to truly understand their business and help them solve environmental problems. The company has successfully completed a series of high-quality environmental protection construction projects. We are qualified to undertake large-scale projects international.

coarse chalcopyrite recovery in a universal froth flotation machine - sciencedirect

coarse chalcopyrite recovery in a universal froth flotation machine - sciencedirect

A new hybrid froth flotation machine recovers particles with a wide size range.Coarse particles are recovered in a fluidized bed.Fines and ultra-fines are recovered in a high-shear in-line contactor.Results are given for flotation of a copper ore crushed to a top size of 600m.Coarse particle recovery limited by encapsulation of valuable particles.Modelling shows significant savings in energy, easy dewatering of tails.

A new froth flotation machine has been developed, known as the NovaCell, which can recover mineral particles over a wide particle size range, from the lower limit of flotation, to an upper limit which depends on the liberation characteristics of the ore. In a single device, the collection of the fines and the coarse particles takes place in separate environments. The finest particles are contacted with bubbles in a high-shear aerator, while the coarse particles are captured by bubbles in the gentle environment in a fluidised bed.

In this paper, the flotation of a porphyry copper ore in the NovaCell is described. The head grade was 1.0% Cu, and the copper mineral was freed from encapsulation at a relatively coarse size. The initial grind size was 600m. Tests were conducted in a laboratory unit, in both batch and continuous modes, using a conventional reagent suite. The data were analysed, and rate constants were established on a size-by-size basis. The rate constants for the batch and continuous modes were consistent. They were used to predict the performance of a bank of similar cells in series. It was found that with four rougher NovaCells in series, and a cleaner circuit, it would be possible to obtain copper recoveries above 99%. Approximately 80% of the feed is rejected as coarse gangue particles from the roughers, thereby reducing the load on the secondary mills preparatory to the cleaner circuit. The savings in operating costs of grinding energy and media, are estimated to be 40% approximately.

The NovaCell delivers two tailings streams, one of which has been de-slimed in the fluidised bed. It can be drawn from the Cell at a high percent solids, and is suitable for dry stacking without further dewatering. The test program uncovered a number of interesting features relating to the distribution of copper in the feed on a size-by-size basis, and to the maximum recovery at infinite residence time as a function of particle size, which will be described.

flotation froth image classification using convolutional neural networks - sciencedirect

flotation froth image classification using convolutional neural networks - sciencedirect

A machine vision system was installed on an industrial coal flotation column.A convolutional neural network (CNN) was developed to extract the froth features.A CNN-based classifier was applied to classify the froth images.Proposed classifier yielded much better performance than artificial neural networks.The proposed classifier can be used in on-line machine vision based control systems.

In recent years, the use of machine vision systems for monitoring and control of the flotation plants has significantly increased. The classification of froth images is a critical step in development of an on-line machine vision based control system. Deep learning is a recent advance in machine learning that uses programmable neural networks to extract high-level features from image data. In this research study a convolutional neural network (CNN) is developed to classify the froth images collected from an industrial coal flotation column operated under various process conditions (air flow rate, frother dosage, slurry solids%, froth depth and collector dosage). In the first step, the froth images captured at different air flow rates are classified by the CNN algorithm and its classification accuracy is compared with a conventional artificial neural network (ANN). The results show that the froth classification system based on CNN significantly outperforms the ANN classifier in terms of classification accuracy and computation time. In the second step, the whole images taken under different operating conditions are classified using the CNN algorithm. The experimental results indicate that the CNN model is able to classify the froth images with an overall accuracy of 93.1%. The promising results of this study demonstrate the significant potential of deep learning neural networks in froth image analysis, which is of great importance for development of machine vision systems.

fault detection in flotation processes based on deep learning and support vector machine | springerlink

fault detection in flotation processes based on deep learning and support vector machine | springerlink

Effective fault detection techniques can help flotation plant reduce reagents consumption, increase mineral recovery, and reduce labor intensity. Traditional, online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation, like color, shape, size and texture, always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case. In this work, a new integrated method based on convolution neural network (CNN) combined with transfer learning approach and support vector machine (SVM) is proposed to automatically recognize the flotation condition. To be more specific, CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection. As compared with the existed recognition methods, it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy. Hence, a CNN-SVM based, real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.

, (, , , ), , (CNN) , (SVM) , CNN-SVM ,

YANG Chun-hua, ZHOU Kai-jun, MOU Xue-min, GUI Wei-hua. Froth color and size measurement method for flotation based on computer vision [J]. Chinese Journal of Scientific Instrument, 2009, 30(4): 717721. (in Chinese)

ZHAO Lu, PENG Tao, HAN Hua, CAO Wei, LOU Yang-ge, XIE Xiao-tian. Fault condition recognition based on multi-scale co-occurrence matrix for copper flotation process [C]// Proceedings of the 19th World Congress International Federation of Automatic Control. Cape Town, South Africa. 2014: 70917097.

ALDRICH C, MARAIS C, SHEAN B J, CILLIERS J J. Online monitoring and control of froth flotation systems with machine vision: A review [J]. International Journal of Mineral Processing, 2010, 96(1): 113.

YANG Chun-hua, XU Can-hui, GUI Wei-hua, DU Jian-jiang. Nonparametric density estimation of bubble size distribution for monitoring mineral flotation process [C]// Proceedings of the 28th Chinese Control Conference. Shanghai, China. 2009: 29412945.

LIU Jin-ping, GUI Wei-hua, TANG Zhao-hui, YANG Chun-hua, ZHU Jian-yong, LI Jian-qi. Recognition of the operational statuses of reagent addition using dynamic bubble size distribution in copper flotation process [J]. Minerals Engineering, 2013, 45: 128141.

YANG Chun-hua, REN Hui-feng, GUI Wei-hua, YAN Feng, TANG Zhao-hui. Performance recognition using texture credit distributed SVM for froth flotation process [J]. Chinese Journal of Scientific Instrument, 2011, 32(10): 22052209. (in Chinese)

HE Ming-fang, YANG Chun-hua, WANG Xiao-li, GUI Wei-hua, WEI Li-jun. Nonparametric density estimation of froth colour texture distribution for monitoring sulphur flotation process [J]. Minerals Engineering, 2013, 53: 203212.

LING Yi-qiu, YANG Chun-hua, HE Ming-fang, GUI Wei-hua. Fault condition detection for sulfur flotation process based on texture unit distribution [J]. Computing Technology and Automation, 2013, 32(1): 2831. (in Chinese)

LECUN Y, HUANG F J, BOTTOU L. Learning methods for generic object recognition with invariance to pose and lighting [C]// Proceedings of the 2004 IEEE Computer Society Conference. Washington DC, USA. 2004: 97104.

SZEGEDY C, LIU W J, SERMANET P, REED S, ANGURLOV D, RABINOVICH A. Going deeper with convolutions [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA, 2015: 19.

NG H W, NGUYEN V D, VONIKAKIS V, WINKLER S. Deep learning for emotion recognition on small datasets using transfer learning [C]// Proceedings of the 2015 ACM on International Conference on Multimodal Interaction. Seattle, USA. 2015: 443449.

SZEGEDY C, VANHOUCKE V, IOFFE S, SHLENS J, WOJNA Z. Rethinking the inception architecture for computer vision [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA. 2016: 28182826.

MA Ai-lian, XU De-gang, XIE Yong-fang, YANG Chun-hua, GUI Wei-hua. Analysis of dynamic texture features of flotation froth images based on space-time characteristics of complex networks [J]. Journal of Chemical Industry and Engineering, 2016, 68(3): 10231031. (in Chinese)

Projects(61621062, 61563015) supported by the National Natural Science Foundation of China; Project(2016zzts056) supported by the Central South University Graduate Independent Exploration Innovation Program, China

Li, Zm., Gui, Wh. & Zhu, Jy. Fault detection in flotation processes based on deep learning and support vector machine. J. Cent. South Univ. 26, 25042515 (2019). https://doi.org/10.1007/s11771-019-4190-8

Related Equipments