基于改进YOLOv5算法的管道漏磁信号识别方法

Pipeline Magnetic Flux Leakage Signal Recognition Method Based on Improved YOLOv5 Algorithm

摘要:

长输油气管道作为能源运输的主要方式,安全问题至关重要。管道漏磁内检测技术作为管道缺陷检测的重要方法之一,在管道安全保障中发挥着重要作用。人工智能技术可实现管道内检测数据的自动识别,对于减少人力工作量,减少人为误差,提升数据判读准确性具有重要意义。通过引入损失函数Distance-IoU对目标检测算法YOLOv5进行改进,利用改进YOLOv5算法对管道漏磁数据进行训练,使之具有对漏磁缺陷信号自动识别的能力。通过实验,对实际漏磁内检测数据进行识别。结果表明,改进的YOLOv5算法实现了管道缺陷漏磁信号的自动检测识别。并且在相同的训练条件下,改进的YOLOv5算法相较于原始算法准确率有明显的提升,在识别缺陷数量上其精度达到92.8％,比原算法提升了3.22％,改进后的模型损失函数平均损失率为3.6％,比原始YOLOv5模型降低了2.2％,表明该方法在管道缺陷漏磁数据自动识别检测方面具有较好的可行性。

Abstract:

As the main way of energy transportation, long-distance oil and gas pipeline safety is very important. As one of the important methods of pipeline defect detection, pipeline magnetic flux leakage internal detection technology plays an important role in pipeline safety. Artificial intelligence technology can realize the automatic identification of pipeline inspection data, which is of great significance to reduce human workload, reduce human error and improve the accuracy of data interpretation. The distance IOU loss function is introduced to improve the yolov5 algorithm, and the improved yolov5 algorithm is used to train the pipeline magnetic flux leakage data, so that it can automatically identify the magnetic flux leakage signal. Through experiments, the actual MFL internal detection data are identified. The results show that the improved yolov5 algorithm can realize the automatic identification and detection of pipeline defects. Under the same training conditions, the accuracy of the improved model is significantly higher than that of the original model. The accuracy of defect identification is 92.8%, which is 3.22% higher than that of the original model. The average loss rate of the improved model is 3.6%, which is 2.2% lower than that of the original model, The results show that the method is feasible in automatic identification and detection of pipeline defect magnetic flux leakage data.