Coal Characterization and Classification through IDNN Innovations Contrasted with LeNet-5 and CNN Techniques

Coal remains the predominant energy source worldwide, yet the presence of gangue, an unwanted byproduct from coal power plants, poses challenges. Effective removal of gangue during coal's pre-processing phase is imperative. The advent of advanced computing opens avenues for refining gangue separation techniques. Our study introduces a novel deep neural network approach for precise gangue identification. This method builds upon discernible differences in grayscale and surface texture between coal and gangue to design a coal-gangue filtration system. Leveraging this technique, machines can autonomously detect and segregate gangue, minimizing human intervention. Should the coal sector adopt this innovative technology, it would catalyze a transformative shift towards automated coal gangue extraction. This not only elevates raw coal processing efficiency but also enhances the overall coal quality. Empirical tests underscore the efficacy of our method, recording a remarkable accuracy improvement of up to 98.87% in distinguishing coal and gangue materials compared to existing practices.