Anomaly detection based on machine learning in IoT-based vertical plant wall for indoor climate control. (October 2020)

• Record Type: Journal Article
• Authors: Liu, Yu; Pang, Zhibo; Karlsson, Magnus; Gong, Shaofang
• Is Part Of: Building and environment. Volume 183(2020)
• Publication Date: 2020-10
• Subjects: Vertical plant wall -- Indoor climate control -- Anomaly detection -- Internet of Things -- Machine learning -- Neural networks; Buildings -- Environmental engineering -- Periodicals; Building -- Research -- Periodicals; Constructions -- Technique de l'environnement -- Périodiques; Electronic journals; 696
• DOI: 10.1016/j.buildenv.2020.107212
• Languages: English
• ISSNs: 0360-1323

Abstract

Abstract: Indoor climate is closely related to human health, comfort and productivity. Vertical plant wall systems, embedded with sensors and actuators, have become a promising application for indoor climate control. In this study, we explore the possibility of applying machine learning based anomaly detection methods to vertical plant wall systems so as to enhance the automation and improve the intelligence to realize predictive maintenance of the indoor climate. Two categories of anomalies, namely point anomalies and contextual anomalies are researched. Prediction-based and pattern recognition-based methods are investigated and applied to indoor climate anomaly detection. The results show that neural network-based models, specifically the autoencoder (AE) and the long short-term memory encoder decoder (LSTM-ED) model surpass the others in terms of detecting point anomalies and contextual anomalies, respectively, therefore can be deployed into vertical plant walls systems in industrial practice. Based on the results, a new data cleaning method is proposed and a prediction-based method is deployed to the cloud in practice as a proof-of-concept. This study showcases the advancements in machine learning and Internet of things can be fully utilized by researches on building environment to accelerate the solution development. Highlights: Benchmarked anomaly detection in real indoor CO2 and temperature datasets. Proposed neural network-based methods to detect point and contextual anomalies. Proposed a data-preprocessing method and provided practical proof-of-concept. Showcased a solution development example utilizing machine learning and IoT.