当前位置: X-MOL 学术Sci. Tech. Built Environ. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Elimination of multidimensional outliers for a compression chiller using a support vector data description
Science and Technology for the Built Environment ( IF 1.9 ) Pub Date : 2020-12-07 , DOI: 10.1080/23744731.2020.1851544
Jae Min Kim 1 , Cheol Soo Park 2
Affiliation  

Data-driven simulation models can be used for optimal control and decision making in building systems only if they are developed accurately and reliably. An unsolved issue pertains to the data collected from BEMS that generally contain errors owing to sensors, malfunctioning systems, and other unknown reasons. These anomalies generally occur in a multidimensional space and cannot be easily detected. Unfortunately, these anomalies can prevent the simulation model from being accurate, reliable, and scalable. This paper presents an automatic anomaly detection method using a support vector data description (SVDD). The data obtained from a compression chiller in a real office building were classified into raw and filtered datasets based on SVDD. Two artificial neural network (ANN) models were developed (ANNraw and ANNSVDD). Based on the comparison between the two ANNs, the ANNSVDD is found to be better than ANNraw in terms of the model reliability and reproducibility. It is also interesting that the model accuracy differences between the two ANN models are marginal. However, the accuracy of the two ANN models can be improved as long as they are tested against filtered data by SVDD. The improvements in accuracy signify the importance of the elimination of these anomalies.



中文翻译:

使用支持向量数据描述消除压缩冷却器的多维离群值

数据驱动的仿真模型只有在准确,可靠地开发后,才能用于建筑系统中的最佳控制和决策。未解决的问题与从BEMS收集的数据有关,这些数据通常包含由于传感器,系统故障和其他未知原因引起的错误。这些异常通常发生在多维空间中,无法轻易检测到。不幸的是,这些异常会妨碍仿真模型的准确性,可靠性和可扩展性。本文提出了一种使用支持​​向量数据描述(SVDD)的自动异常检测方法。从真实办公楼的压缩式冷却器获得的数据基于SVDD分为原始数据集和过滤后的数据集。开发了两个人工神经网络(ANN)模型(原始ANN和ANN SVDD)。基于两个人工神经网络之间的比较时,ANN SVDD被发现是比ANN更好原料中的模型的可靠性和可重复性方面。有趣的是,两个人工神经网络模型之间的模型精度差异很小。但是,只要通过SVDD对经过过滤的数据进行测试,就可以提高两个ANN模型的准确性。准确性的提高表明消除这些异常的重要性。

更新日期:2020-12-07
down
wechat
bug