To address the challenge of poor separation performance exhibited by conventional magnetic separation equipment when processing coarse-grained, low-grade magnetite ore, this paper proposes a novel ore recognition method that integrates empirical mode decomposition (EMD) with a convolutional neural network (CNN). First, the original signal undergoes standardization to suppress sensor baseline drift. Then, it is decomposed by using EMD to obtain a series of intrinsic mode functions (IMFs). Subsequently, based on scaling exponents and kurtosis values, IMFs containing significant feature information are selected and fused, resulting in a reconstructed signal with substantially reduced noise. To preserve effective features, the absolute values of the reconstructed signal are taken, followed by normalization and dimensional transformation to convert it into a two-dimensional matrix format, thereby constructing training, validation, and test sets. Finally, a CNN is designed and optimized to automatically extract discriminative features from the preprocessed samples, enabling accurate classification of magnetite ore grades. Experimental results demonstrate that the proposed comprehensive identification method achieves effective and stable classification performance across different ore grades. Specifically, the implementation of standardization and EMD-based denoising has been demonstrated to enhance the accuracy of CNNs in recognizing diverse ores.

To address the challenge of poor separation performance exhibited by conventional magnetic separation equipment when processing coarse-grained, low-grade magnetite ore, this paper proposes a novel ore recognition method that integrates empirical mode decomposition (EMD) with a convolutional neural network (CNN). First, the normalized magnetic induction intensity signals are decomposed using EMD to yield a series of intrinsic mode functions (IMFs). IMFs containing prominent characteristic information are then selected and fused based on their dominant frequency and kurtosis values, resulting in a reconstructed signal with significantly reduced noise. Subsequently, the reconstructed signals undergo inversion, re-normalization, and dimensional transformation into a two-dimensional matrix format to construct the training and testing sample datasets. A convolutional neural network is then designed and optimized to automatically extract discriminative features from these preprocessed samples, enabling accurate classification of magnetite ore grades. Experimental results demonstrate that the proposed EMD-CNN framework achieves effective and stable classification performance across different ore grades. In particular, the application of EMD for noise component removal substantially enhances the CNN’s recognition accuracy for waste rock and medium-grade ore, which are traditionally the most difficult categories to distinguish.