The Study Of Coal Quality And Gangue Based On Infrared Image System

Owing to the enormous demand and growingly large-scale use of coal in the USA,China,and developing countries,speculation has been put forward about other possible hazards to environmental quality and human health.The composition of fly ash(Aad)and volatile matter(Vad)of coal has not been examined carefully until relatively recently.As a result,there is still much to be explored in known hazards and harms to the natural environment of the earth.From the responsibility toward our planet and encourage to save our nature,this dissertation is providing solution for discharged materials that is resulted of the wet separation process and giving solution for pollutants and toxic substances that is resulted of coal combustion,the solutions provided in this work categories into three creative methods based on two main principles include infrared radiation principle and wind turbine technology.These solutions main contents are as following:Chapter 3 is to distinguish between coal and gangue in the production lines of mining factories based on the thermal energy and infrared radiation emission of an object.Before the manipulators select an unwanted object to remove it,all objects should pass through a wind heater that the surface of each object acquires the same thermal energy between 30? and 50?,depending on the background temperature.the manipulators make a decision based on data that are extracted from the infrared image by using support vector machine(SVM).We exploit only one feature of the infrared image,namely,Cb,which is extracted from the YCb Cr color space,and then compute the mean value of Cb after heating and capturing the photos for the coal and gangue samples.The proposed method achieves a high classification accuracy 97.83 % by using Gaussian-SVM.Chapter 4 is to distinguish coal quality and efficiently separate gangue and rock from the production lines of coal preparation plant(CPP)by exploiting infrared machine vision and deep learning convolutional neural networks(CNN).In this method,the common models of CNN are trained and tested in this work to identify coal quality in addition to distinguishing gangue and rock.Also,we study the effect of replacing the classifier such as(CNN)rather than(SVM)Successfully,we obtained unique classification accuracy attained(95.09%)validation accuracy,in the prediction phase(160)new images of coal and gangue(80 for both)have been tested to measure the efficiency of the work,the prediction result comes with(100%)for coal recognition accuracy and(97.5%)gangue recognition accuracy giving an overall prediction accuracy(98.75%).Chapter 5,we propose a new method to distinguish coal quality and efficiently separate gangue and rock from the production lines of coal preparation plant(CPP)by exploiting infrared machine vision and deep learning convolutional neural networks(CNN).In this paper,we explore and learn how may be removed,modified,avoided,and exploited sustainable energy together with artificial intelligence to make coal use less harmful to humans and nature and/or more useful for the general welfare.The common models of CNN(e.g.,Alex Net,Dark Net-58,Googl?e Net,Nas Net?Mobileb,Res Net-18,Mobile Net-v2,Inception-v3 and Dense Net-201)are trained and tested in this work to identify coal quality(e.g.,Lignite,Bituminous,Sub-bituminous and Anthracite)in addition to distinguishing gangue and rock.Successfully,we obtained unique classification accuracy attained 100% for training and testing processes by employing Res Net-18 and Dense Net-201 models.Overall,the fundamental aim of three methods that we mentioned above is to find solution to decrease emissions of pollutants and toxic substances that released to air and the natural envenoms by using both infrared radiation principle for select high quality coal.Successfully,based on the result of the three method,we have published three papers in SCI journal.