Abstract
Recognizing and distinguishing coal and gangue are essential in engineering, such as in coal-fired power plants. This paper employed a convolutional neural network (CNN) to recognize coal and gangue images and help segregate coal and gangue. A typical workflow for CNN image recognition is presented as well as a strategy for updating the model parameters. Based on a powerful trained image recognition model, VGG16, the idea of transfer learning was introduced to build a custom CNN model to solve the problems of massive trainable parameters and limited computing power linked to the building of a brand-new model from scratch. Two hundred and forty coal and gangue images were collected in a database, including 100 training images and 20 validation images for each material. A recognition accuracy of 82.5% was obtained for the validation images, which demonstrated a decent performance of our model. According to the analysis of parameter updating in the training process, a principal constraint for obtaining a higher recognition accuracy mainly resided in a shortage of training samples. This model was also used to identify photos from a washing plant stockpiles, which verified its capability of dealing with field pictures. CNN combined with the transfer learning method we used can provide fast and robust coal/gangue distinction that does not require harsh data support and equipment support. This method will exhibit brighter prospects in engineering if the target image database (as with the coal and gangue images in this study) can be further enlarged.
Highlights
In many countries, coal-fired power plants provide most of the electrical energy used because of their simple construction, ease of control, and abundant source of feed [1]
Most current papers devoted to coal/gangue image recognition share the common idea that certain features extracted from coal/gangue images manually or by algorithms feed into a pre-set mathematic or statistical model to determine image category
A recognition accuracy of 82.5% was realized for validation pictures after the model was trained on a relatively small database
Summary
Coal-fired power plants provide most of the electrical energy used because of their simple construction, ease of control, and abundant source of feed [1]. A similar strategy was implemented by Gao [5] He obtained the greyscale distributions of coal and gangue by analyzing a large number of images and he employed the Bayesian Discriminant algorithm to differentiate coal and gangue images on the basis of existing greyscale distributions. Most current papers devoted to coal/gangue image recognition share the common idea that certain features extracted from coal/gangue images manually or by algorithms feed into a pre-set mathematic or statistical model to determine image category. A trained CNN was employed to recognize coal/gangue images collected from project fields and online. This CNN was combined with a transfer learning strategy to solve the shortage of training data.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
