Image Recognition of Coal and Coal Gangue Using a Convolutional Neural Network and Transfer Learning
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".