This paper proposes an improved steel surface defect detection algorithm based on ESI-YOLOv8 to enhance detection accuracy and reduce false positives and false negatives. The algorithm introduces a novel EP module and integrates the large separation convolutional attention module and the spatial pyramid pooling module to propose the SPPF-LSKA module. Additionally, the original CIOU loss function is replaced with the INNER-CIOU loss function. The EP module minimizes redundant computations and model parameters to optimize efficiency and increases the multiscale fusion mechanism to expand the sensory field. The SPPF-LSKA module reduces computational complexity, accelerates model operation speed, and improves detection accuracy. The INNER-CIOU loss function improves detection speed and model accuracy by controlling the scale size of the auxiliary border. Experimental results show that the algorithm's detection accuracy increased to 78%, which is 3.7% higher than the original YOLOv8. The model parameters were reduced, and the verification was conducted using the CoCo dataset, resulting in an average accuracy of 77.8%. The algorithm demonstrates its ability to perform steel plate surface defect detection with efficiency and accuracy. The YOLOv8 model has some shortcomings in detecting defects on steel surfaces, including low detection accuracy, large model size, and weak generalisation ability of the loss function. To enhance the effectiveness of steel surface defect detection, further improvements and optimizations are required for the YOLOv8 model. The paper introduces the EP module, SPPF-LSKA module, and INNER-CIOU loss function to improve the model's performance. The experimental results show that the improved model has higher accuracy, lower parameter count, and better performance compared to the original YOLOv8 model. The model is tested on the CoCo dataset and achieves an average accuracy of 77.8%. The improved model has a lower leakage rate and performs better in detecting various types of defects. The model is more precise in its detection and has a higher average accuracy compared to the original model. The ablation experiments show that the EP module, SPPF-LSKA module, and INNER-CIOU loss function each contribute to the model's performance. The combination of these modules results in the highest accuracy. The model outperforms other mainstream models in terms of accuracy, parameter count, and computational efficiency. The study concludes that the ESI-YOLOv8 model has good stability and meets the requirements of small volume and high accuracy detection, which can better meet the requirements of steel surface defect detection.This paper proposes an improved steel surface defect detection algorithm based on ESI-YOLOv8 to enhance detection accuracy and reduce false positives and false negatives. The algorithm introduces a novel EP module and integrates the large separation convolutional attention module and the spatial pyramid pooling module to propose the SPPF-LSKA module. Additionally, the original CIOU loss function is replaced with the INNER-CIOU loss function. The EP module minimizes redundant computations and model parameters to optimize efficiency and increases the multiscale fusion mechanism to expand the sensory field. The SPPF-LSKA module reduces computational complexity, accelerates model operation speed, and improves detection accuracy. The INNER-CIOU loss function improves detection speed and model accuracy by controlling the scale size of the auxiliary border. Experimental results show that the algorithm's detection accuracy increased to 78%, which is 3.7% higher than the original YOLOv8. The model parameters were reduced, and the verification was conducted using the CoCo dataset, resulting in an average accuracy of 77.8%. The algorithm demonstrates its ability to perform steel plate surface defect detection with efficiency and accuracy. The YOLOv8 model has some shortcomings in detecting defects on steel surfaces, including low detection accuracy, large model size, and weak generalisation ability of the loss function. To enhance the effectiveness of steel surface defect detection, further improvements and optimizations are required for the YOLOv8 model. The paper introduces the EP module, SPPF-LSKA module, and INNER-CIOU loss function to improve the model's performance. The experimental results show that the improved model has higher accuracy, lower parameter count, and better performance compared to the original YOLOv8 model. The model is tested on the CoCo dataset and achieves an average accuracy of 77.8%. The improved model has a lower leakage rate and performs better in detecting various types of defects. The model is more precise in its detection and has a higher average accuracy compared to the original model. The ablation experiments show that the EP module, SPPF-LSKA module, and INNER-CIOU loss function each contribute to the model's performance. The combination of these modules results in the highest accuracy. The model outperforms other mainstream models in terms of accuracy, parameter count, and computational efficiency. The study concludes that the ESI-YOLOv8 model has good stability and meets the requirements of small volume and high accuracy detection, which can better meet the requirements of steel surface defect detection.