基于改进YOLOv7的火电厂管道及阀门泄漏分割与检测  

Leakage segmentation and detection of pipelines and valves in thermalpower plants based on improved YOLOv7

作　　者：彭道刚 陈晨 王丹豪 潘俊臻 PENG Dao-gang;CHEN Chen;WANG Dan-hao;PAN Jun-zhen(College of Automation Engineering,Shanghai University of Electric Power,Shanghai 200090,China;College of Electrical Power Engineering,Shanghai University of Electric Power,Shanghai 200090,China)

机构地区：[1]上海电力大学自动化工程学院,上海200090 [2]上海电力大学电气工程学院,上海200090

出　　处：《控制与决策》2024年第9期2977-2986,共10页Control and Decision

基　　金：上海市“科技创新行动计划”高新技术领域项目(21511101800)。

摘　　要：火电厂关键区域的管道、阀门等设备时常发生油液、蒸汽等物质的泄漏故障.为了提高火电厂管道及阀门泄漏故障的分割与检测精度,加快模型推理速度,提出一种基于改进YOLOv7的火电厂管道及阀门泄漏分割与检测算法,通过在YOLOv7网络中加入相关实例分割模块,实现实例分割与目标检测任务的并行;通过融入极化自注意力机制和可分离的视觉深度自注意力模块(separable vision transformer),弱化复杂背景的干扰,强化对泄漏区域的边缘提取;在后处理阶段运用置信度传播簇机制(confidence propagation cluster, CP-cluster),提高模型定位的准确性;在颈部网络使用幽灵卷积降低特征冗余,并通过通道剪枝技术压缩模型,实现模型轻量化.实验结果表明,在加入各项改进后,算法分割任务与检测任务的mAP@0.5:0.95指标分别达到75.7%、82.2%,相较于基础模型,指标分别提高了11.9%、7.1%,且模型参数量减少了30.3%,可有效地应用于电厂的实际生产环境中.Equipment such as pipelines and valves in key areas of thermal power plants often experience leakage faults of substances such as oil and steam.In order to improve the segmentation and detection accuracy of pipelines and valves leakage faults in thermal power plants and accelerate model inference speed,a pipeline and valve leakage segmentation and detection algorithm in thermal power plants based on the improved YOLOv7 is proposed.By adding relevant instance segmentation modules to the YOLOv7 network,the parallelization of instance segmentation and target detection tasks are achieved.By integrating polarized self-attention mechanism and separated vision transformer modules,the interference of complex backgrounds is weakened,the edge extraction of the leakage area is strengthened.Then,in the post-processing stage,the CP-cluster(confidence propagation cluster)mechanism is applied to improve the accuracy of model localization;Finally,Ghostconv is used in the neck network to reduce feature redundancy,and the model is compressed by channel pruning technology to achieve lightweight model.The experimental results show that after adding various improvements,the mAP@0.5:0.95 of the algorithm’s segmentation task and detection task reach 75.7%and 82.2%,respectively,which increase by 11.9%and 7.1%compared to the basic model,and the model parameter decreases by 30.3%.The model can be effectively applied in the actual production environment of power plants.

关 键 词：泄漏检测 实例分割 目标检测 自注意力机制 置信度传播簇机制 通道剪枝 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]