English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

As for image-based recognition of coal and gangue, the image features are susceptible to the environment, which makes coal and gangue difficult to recognize and locate. We build a simulation experiment platform and construct an image dataset covering the scenarios of different illuminance, moisture, and belt speed. Moreover, in a combination of the YOLOv4 target detection algorithm and a mixed domain attention mechanism, we develop a detection model trained using our dataset. The recognition accuracy of coal, gangue, and coal and gangue combined are 98.2%, 99.0%, and 97.3%, respectively, and the recognition time was 32 ms. We then design an orthogonal experiment of coal and gangue recognition under the influence of three factors (illuminance, moisture content, and belt speed) and four levels and a range analysis. As a result, we obtain the weight sequence and the optimal combination of three factors. The experimental results show that moisture content has the highest influence on weight on recognition accuracy, followed by illuminance and belt speed. We further build the practical working condition simulation experiment platform and choose the illuminance to 4000lux, moisture content to 0.6%, and belt speed to 0.4 m/s to evaluate the recognition and location of coal and gangue on a moving belt. The recognition accuracy of coal, gangue, and the combination are 96%, 98% and 95%, respectively. The average location error of the X and Y coordinate is 5.6 mm and 7.3 mm, respectively.

Multiple factors influence coal and gangue image recognition method and experimental research based on deep learning