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

  • The indoor climate of a modern building, i.e., the air temperature, relative humidity, poisonous gas concentrations, volatile organic compounds level, is closely related to human health, comfort, and work productivity

  • We investigate a series of most representative prediction and pattern recognition based anomaly detection methods, aiming at proposing a model that is most suitable for realizing indoor climate control with a vertical plant wall system

  • With temporal features appended to the sensory data, the performance of the artificial neural network (ANN) model improves to some degree, as expected

Read more

Summary

Introduction

The indoor climate of a modern building, i.e., the air temperature, relative humidity, poisonous gas concentrations, volatile organic compounds level, is closely related to human health, comfort, and work productivity. Many commercial products and solutions are available in the market to improve indoor air quality, among which the vertical plant wall system (VPS) has proved to be a promising solution [3]. A statically placed vertical plant wall system can contribute to the indoor climate by passively purifying the air while the procedure can be accelerated and enhanced by integrating lighting, ventilation and irrigation systems to the plant wall [3]. Our previous study has proposed an IoT and public cloud-based remote monitoring and management system for the vertical plant wall industry, aiming at tackling the maintenance challenges encountered by plant wall suppliers [6]. Through a web-based human–machine interface (HMI), administrators are capable of performing remote control over the actuators, i.e., the lighting, ventilation and watering systems, in order to maintain a purified indoor climate

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call