| 马斌,彭志,梁超.基于多源异构数据融合的高坝泄流结构安全智能监测预警方法[J].水利学报,2025,56(9):1132-1142 |
| 基于多源异构数据融合的高坝泄流结构安全智能监测预警方法 |
| Intelligent monitoring and early warning method for high dam discharge structure safety based on multi-source heterogeneous data fusion |
| 投稿时间：2024-12-22 修订日期：2025-08-01 |
| DOI：10.13243/j.cnki.slxb.20240841 |
| 中文关键词: 高坝泄流 监测预警 单分类异常识别 多源异构数据融合 原型监测 |
| 英文关键词: high dam flood discharge monitoring and early warning single classification anomaly recognition multi-source heterogeneous data fusion prototype monitoring |
| 基金项目:国家重点研发计划项目（2022YFB4200704）；天津市应用基础研究项目（22JCYBJC01180）；国家自然科学基金项目（51909185）；天津市科技计划项目全国重点实验室重大专项（24ZXZSSS00450）；华能集团科技项目（HNKJ24-H165）；云南省科技人才与平台计划项目（202405AK340002） |
|
| 摘要点击次数: 61 |
| 全文下载次数: 31 |
| 中文摘要: |
| 高坝泄流结构在漫长的运行期内难避免会发生损伤，亟需实施有效的安全监测预警，以免局部异常扩大为安全事故。鉴于空气声压和流态图像等对局部异常具有良好的敏感性，将对二者的监测与传统的低频振动位移监测同步进行，以丰富监测数据类型、提升有效信息。针对上述多源异构数据，提出了特征级融合方法，将振动、声压的时频图与分割裁剪的流态图像等二维数据拼接为三维矩阵，尽可能地保留和融合各类数据的关键特征。基于自编码器结构，构建深度学习网络，嵌入Inception和GRU模块以提升模型的空间和时序特征学习能力，提出了Autoencoder-Inception-GRU单分类异常识别模型。采用绝对平均误差百分比和欧氏距离作为模型的重构误差函数，并将其最大值的95%设为异常阈值。基于原型监测试验，构建了振动-声压-图像多源异构数据库，详细分析了Autoencoder-Inception-GRU模型的性能，并通过多种情况下的算例研究，检验了所提方法的准确度、鲁棒性和泛化能力。结果表明所提方法性能优异，可为高坝泄流安全监测预警的工程应用提供关键技术支持。 |
| 英文摘要: |
| The discharge structure of high dams will inevitably be damaged during the long operation and maintenance period. It is urgent to implement effective safety monitoring and early warning to avoid local abnormalities from expanding into safety accidents. Since the monitoring items，including air sound pressure and flow pattern images， are very sensitive to abnormal operating states of high dams，they are monitored synchronously with the lowfrequency vibration displacement to enrich the types of monitoring data and improve effective information. A featurelevel fusion is proposed to splice the time-frequency images of vibration and sound pressure with the segmented and cropped flow pattern images in the additional dimension，so as to retain and fuse the key features of the above multisource heterogeneous data as much as possible. Based on the framework of autoencoder，a deep learning network is built，Inception and GRU modules are embedded to improve the spatial and temporal feature learning capabilities of the model，and then the Autoencoder-Inception-GRU single-classification anomaly recognition model is proposed. Absolute mean error percentage and Euclidean distance are used as the reconstruction error function of the model， and 95% of their maximum values are set as the anomaly threshold. Based on the prototype monitoring experiment，a multi-source heterogeneous database of vibration-sound-image was constructed， and the performance of the Autoencoder-Inception-GRU model was analyzed in detail. The accuracy，robustness and generalization ability of the proposed model were tested and investigated by case studies under various conditions. The results show that the proposed approach achieves excellent performance，which provides key technical support for engineering application. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |