4.7 Article

Detection and quantification of temperature sensor drift using probabilistic neural networks

期刊

EXPERT SYSTEMS WITH APPLICATIONS
卷 213, 期 -, 页码 -

出版社

PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2022.118884

关键词

Long-term structural health monitoring; Data validation; Temperature sensor drift; Fiber optics; Machine learning; Probabilistic neural networks; Data-driven prediction; Temperature prediction; Anomaly detection

向作者/读者索取更多资源

Temperature effects play a crucial role in the strain and deformations of civil infrastructure. Accurate methods for detecting and quantifying anomalies in temperature data are necessary. This study proposes a probabilistic neural network as a temperature prediction model and introduces a sensible threshold to mitigate seasonal biases. Additionally, a novel drift detection and quantification method based on the evolution of probability distributions is presented.
Temperature effects are a major driver of strain and deformations in weather-exposed civil infrastructure, such as bridges and buildings. For such structures, long-term temperature data holds the potential for data-driven prediction of expected structural behavior, which in turn enables the detection of anomalous structural behavior. For this reason, structural health monitoring (SHM) strategies typically employ temperature sensors. However, the success of SHM is contingent on the quantity and quality of the available temperature data. Hence, accurate automatic methods for the detection and quantification of anomalies in temperature data are needed. In particular, gradual temperature sensor drifts are difficult to detect and can introduce errors into the thermal compensation of strain sensors, which can be erroneously confounded with time-dependent structural behavior. Current data-driven methods use air temperature as predictor because it exhibits good correlation with temperatures in the structure. Sensor drift is typically quantified by analysis of the prediction residuals; however, these methods are not robust to outliers and can be affected by seasonal biases. In this work, a probabilistic neural network is used as the nonlinear data-driven temperature prediction model which enables the introduction of a sensible threshold to mitigate seasonal model bias. Furthermore, a novel drift detection method based on the evolution of parameters of a trinomial probability distribution is introduced, together with a robust drift quantification method. The performance of this method is assessed using real temperature data from a pedestrian bridge, spanning over seven years of the structure's life.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据