Design of transformer substation monitoring device based on acoustic seismic integration
-
摘要: 在役变电站一次、二次设备出现问题的频率较高，当设备发生故障或者所处环境发生改变时，其所发出的声音和震动信号也会随之改变，因此对设备声音和震动参量的快速辨识可以协助开展站内设备安全管理。为此设计了一种用于电力物联网的声震一体状态监测装置，该装置能够实时采集变电站内环境和设备运行过程中的声音和震动数据，并对数据进行融合处理，实现对环境和设备运行状态的长期监控，为克服传统单一参量监测诊断易造成漏判与误判的问题提供了解决思路，有助于提高无人值守变电站的安全工作水平。Abstract: The frequency of problems with the primary and secondary equipment of the in-service substation is relatively high. When the equipment fails or the external environment changes, the sound and vibration signals it emits will also change accordingly. Quick identification can assist in the safety management of equipment in the station.To this end, an integrated acoustic and vibration state monitoring device for the power Internet of Things is designed. The device can collect real-time sound and vibration data in the substation environment and during equipment operation, and fuse the data to realize the environment and the environment. The long-term monitoring of equipment operating status provides a solution for overcoming missed judgments and misjudgments easily caused by traditional single-parameter monitoring and diagnosis, and helps to improve the safe working level of unattended substations.
-
Keywords:
- multisensor /
- acoustic shock node /
- fusion processing /
- condition monitoring
-
-
[1] 李刚, 张博, 赵文清, 等.电力设备状态评估中的数据科学问题:挑战与展望[J].电力系统自动化, 2018, 42(21):10-20, 177. [2] 侯增起.基于声音特征的变电设备故障分类与定位方法研究[D].北京:华北电力大学, 2018. [3] 邵向潮, 刘贯科, 廖肇毅, 等.变电设备运行背景噪声差异性研究[J].湖北电力, 2019, 43(2):1-6. [4] 李伟, 李硕.理解数字声音——基于一般音频/环境声的计算机听觉综述[J].复旦学报(自然科学版), 2019, 58(3):269-313. [5] 李鹏, 毕建刚, 于浩, 等.变电设备智能传感与状态感知技术及应用[J].高电压技术, 2020, 46(09):3097-3113. [6] 邢怀飞, 李芳, 刘育梁. 无线传感器网络声震节点目标分类综述[J]. 计算机科学, 2008, 8(7):1748-1756. [7] ELGORT K, KOMAROMY S, MADDEN J, et al.US army employment of unattended ground sensors[C]//2005 IEEE Design Symposium, Systems and Information Engineering.Charlottesville, VA, USA:IEEE, 2005.
[8] 蒋晓永, 杨涛.基于变步长LMS和SVM的电能表内异物声音识别[J].传感器与微系统, 2019, 38(2):143-146. [9] 姚琨, 杨吉斌, 张雄伟, 等.基于多分辨率时频特征融合的声学场景分类[J].声学技术, 2020, 39(4):494-500. [10] 张进, 吴健, 欧习洋, 等.基于特征降维和神经网络的电能表内异物声音自动识别[J].机械设计与制造, 2021(3):234-237. [11] 廖瑞金, 袁磊, 汪可, 等. 基于S变换和双向二维主成分分析的局部放电模式识别[J]. 重庆大学学报, 2013, 36(5):56-63. [12] 黄海涛.机械设备噪声诊断中声源识别方法的研究[D].武汉:武汉理工大学, 2017. [13] 宁培培.基于麦克风阵列的机械故障诊断研究[D].成都:电子科技大学, 2019. [14] 张瑶, 罗林根, 王辉, 等.基于MPSO-MLE的变电站设备异常声源定位方法[J].高电压技术, 2020, 46(9):3145-3153. [15] 刘志颖, 缪希仁, 陈静, 等.电力架空线路巡检可见光图像智能处理研究综述[J].电网技术, 2020, 44(3):1057-1069. [16] 刘梓权, 王慧芳, 曹靖, 等.基于卷积神经网络的电力设备缺陷文本分类模型研究[J].电网技术, 2018, 42(2):644-651.
计量
- 文章访问数: 2
- HTML全文浏览量: 0
- PDF下载量: 4
下载:
