CM-YOLOv8 is a lightweight object detection algorithm designed for coal mine fully mechanized mining faces. It improves detection performance by using adaptive predefined anchor boxes tailored to the coal mining dataset and employs L1 norm-based pruning to reduce model computation and parameter volume without sacrificing accuracy. The algorithm achieves a 40% reduction in model size with less than 1% accuracy drop. It is validated on the DsLMF+ dataset, demonstrating efficiency and practicality in coal mining scenarios. CM-YOLOv8 significantly reduces computational requirements and maintains high accuracy, making it suitable for resource-constrained environments. The algorithm uses a genetic algorithm-based K-means clustering method to generate adaptive anchor boxes and applies L1 norm-based pruning to optimize the network structure. The results show that CM-YOLOv8 outperforms other algorithms in terms of computational efficiency and accuracy, making it a promising solution for real-time object detection in coal mines.CM-YOLOv8 is a lightweight object detection algorithm designed for coal mine fully mechanized mining faces. It improves detection performance by using adaptive predefined anchor boxes tailored to the coal mining dataset and employs L1 norm-based pruning to reduce model computation and parameter volume without sacrificing accuracy. The algorithm achieves a 40% reduction in model size with less than 1% accuracy drop. It is validated on the DsLMF+ dataset, demonstrating efficiency and practicality in coal mining scenarios. CM-YOLOv8 significantly reduces computational requirements and maintains high accuracy, making it suitable for resource-constrained environments. The algorithm uses a genetic algorithm-based K-means clustering method to generate adaptive anchor boxes and applies L1 norm-based pruning to optimize the network structure. The results show that CM-YOLOv8 outperforms other algorithms in terms of computational efficiency and accuracy, making it a promising solution for real-time object detection in coal mines.