农业机械学报2018，Vol.49Issue(2)：319-326,8.DOI:10.6041/j.issn.1000-1298.2018.02.041
基于时空信息比较的温室环境传感器故障识别
Sensor Fault Identification in Greenhouse Environment Based on Comparison of Spatial-temporal Information
摘要
Abstract
In order to judge the accuracy of sensor data in greenhouse environment measurement and control system,a sensor fault identification method was proposed based on the comparison of node information.This method based on the principal component analysis (PCA) was to achieve the sensor system fault detection through the monitoring statistics T2 and SPE changes.When the system detected the fault,the different sensor fault identification by using the comparison of node information based on temporal and spatial characteristics were realized,and to compare the effects with different methods,node information was made a comparison based on temporal scale,spatial scale and temporal-spatial scale,for multi-sensor fault identification.Verification results showed that the sensor fault detection method based on PCA can effectively realize the preliminary detection of the sensor system,and the sensor fault identification method based on the comparison of node information took the time and spatial scale into consideration,which can effectively achieve the specific fault sensor positioning.The value of the sensor nodes fault data average CDR was 98.37％,and the average FAR was 1.72％.Compared with the traditional method for sensor fault identification,the CDR increased by 22.067 percentage points and the FAR reduced by 15.762 percentage points,and it was found that the fault recognition method mentioned can effectively guarantee the efficiency of fault diagnosis improve the accuracy of fault diagnosis,and reduce the false alarm rate with reliability and accuracy.关键词
温室环境/传感器/时空特性/节点信息/故障识别Key words
greenhouse environment/sensor/spatial-temporal characteristics/node information/fault identification分类
农业科技引用本文复制引用
王纪章,贺通,周金生,赵丽伟,王建平,李萍萍..基于时空信息比较的温室环境传感器故障识别[J].农业机械学报,2018,49(2):319-326,8.基金项目
江苏省农业自主创新项目(CX(15)1016)、中国博士后基金项目(2015M580400)、江苏省博士后基金项目(1501112B)、江苏省科技支撑计划项目(BE2014406)、江苏省高等学校自然科学研究重大项目(17KJA416002)和江苏省高校优势学科建设工程项目(苏政办发教[2014]37号) （CX(15）
