A deep learning approach towards the detection and recognition of opening of windows for effective management of building ventilation heat losses and reducing space heating demand

Tien, Paige Wenbin; Wei, Shuangyu; Liu, Tianshu; Calautit, John Kaiser; Darkwa, Jo; Wood, Christopher J.

doi:10.1016/j.renene.2021.05.155

Cited by 49 publications

(29 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although this testing in real-time would demonstrate clear areas where training improvement would need to be made to ensure minimal false detection and false alarms. Finally, it is envisioned that an all in one (AIO) system will be developed in the future that could have multiple functions such as control of heating and ventilation31, air conditioning systems (HVAC)32 and fire safety.…”

Section: Discussionmentioning

confidence: 99%

Development and evaluation of a vision-based transfer learning approach for indoor fire and smoke detection

Pincott

Tien

Wei

et al. 2022

Building Services Engineering Research and Technology

Self Cite

View full text Add to dashboard Cite

Fire poses a significant risk across industrial and domestic settings, especially to firefighters who must tackle the blaze. Current technology for detection in indoor environments are smoke detectors and flame detectors. However, these detectors have several limitations during the ignition phase of a fire and propagation. These systems cannot detect an exact position of the fire nor how the fire is spreading or its size, all of which is necessary information for fire services when dealing with these incidents. A potential solution is to use artificial intelligence techniques such as computer vision, which has shown the potential to detect and recognise objects and activities in indoor spaces. This study aims to develop a vision-based fire and smoke detection system. A deep learning technique that incorporates convolutional neural networks (CNN) was utilised to develop the real-time detection approach that can potentially provide necessary information for fire services, including identifying the position and size of the fire and how the fire spreads. A transfer learning approach using a pre-trained model was used to train the detector. Based on the detection and recognition tests using indoor fire and smoke videos, results indicated that the fire detection achieved up to 92.37% correct detections while the smoke detection did not perform as well. Hence, further improvement and evaluation of the detection approach will be conducted in future work, focusing on the impact of different parameters such as the detection model, building type, indoor space size and positioning of the detection camera. The present study provides an insight into the capabilities and potential applications of the concept.

show abstract

Section: Discussionmentioning

confidence: 99%

Development and evaluation of a vision-based transfer learning approach for indoor fire and smoke detection

Pincott

Tien

Wei

et al. 2022

Building Services Engineering Research and Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, the average daily peak and peak-to-average ratio could be reduced by 10 and 6%, respectively, showing the great benefits of a coordinated approach. Tien et al [61] also introduced DRL control strategies that can provide real-time monitoring of the amount of time that windows are left open and, subsequently, adjust the air-conditioning system to minimize energy wastage and maintain indoor environment quality, as well as thermal comfort. The strategy was capable of identifying windows' status with an average accuracy of 97.29%, indicating its potential to help building managers to prevent unnecessary heating or cooling demand.…”

Section: Energy Saving and Emission Reductionmentioning

confidence: 99%

Recent Advances in Low-Carbon and Sustainable, Efficient Technology: Strategies and Applications

et al. 2022

View full text Add to dashboard Cite

The COVID-19 pandemic has had a significant impact on the supply chains of traditional fossil fuels. According to a report by the International Energy Agency (IEA) from 2020, oil-refining activity fell by more than the IEA had anticipated. It was also assumed that the demand in 2021 would likely be 2.6 million bpd below the 2019 levels. However, renewable markets have shown strong resilience during the crisis. It was determined that renewables are on track to meet 80% of the growth in electricity demand over the next 10 years and that sustainable energy will act as the primary source of electricity production instead of coal. On the other hand, the report also emphasized that measures for reducing environmental pollution and CO2 emissions are still insufficient and that significant current investments should be further expanded. The Sustainable Development of Energy, Water and Environment Systems (SDEWES) conference series is dedicated to the advancement and dissemination of knowledge on methods, policies and technologies for improving the sustainability of development by decoupling growth from the use of natural resources. The 15th SDEWES conference was held online from 1–5 September 2020; more than 300 reports with 7 special sections were organized on the virtual conference platform. This paper presents the major achievements of the recommended papers in the Special Issue of Energies. Additionally, related studies connected to the above papers published in the SDEWES series are also introduced, including the four main research fields of energy saving and emission reduction, renewable energy applications, the development of district heating systems, and the economic assessment of sustainable energy.

show abstract

“…Generally, people spent a significant amount of time indoors [9,10] and migration of the work environment to homes due to the lockdown has further accentuated the trend. The shift to working remotely emphasises the necessity of more studies on indoor air quality [11][12][13][14][15]. Therefore, the mechanism of indoor pollution and its effect on building occupants' health and well-being should be well understood and adequately assessed when designing new buildings and spaces.…”

Section: Introduction and Literature Reviewmentioning

confidence: 99%

Impact of Ventilation Strategy on the Transmission of Outdoor Pollutants into Indoor Environment Using CFD

Mohammadi

Calautit

2021

Sustainability

Self Cite

View full text Add to dashboard Cite

The transition to remote working due to the pandemic has accentuated the importance of clean indoor air, as people spend a significant portion of their time indoors. Amongst the various determinants of indoor air quality, outdoor pollution is a significant source. While conventional studies have certainly helped to quantify the long-term personal exposure to pollutants and assess their health impact, they have not paid special attention to the mechanism of transmission of pollutants between the two environments. Nevertheless, the quantification of infiltration is essential to determine the contribution of ambient pollutants in indoor air quality and its determinants. This study evaluates the transmission of outdoor pollutants into the indoor environment using 3D computational fluid dynamics modelling with a pollution dispersion model. Naturally ventilated buildings next to an urban canyon were modelled and simulated using Ansys Fluent and validated against wind tunnel results from the Concentration Data of Street Canyons database. The model consisted of two buildings of three storeys each, located on either side of a road. Two line-source pollutants were placed in the street, representing traffic emissions. Three internal rooms were selected and modelled on each floor and implemented with various ventilation strategies. Results indicate that for a canyon with an aspect ratio of 1, indoor spaces in upstream buildings are usually less polluted than downstream ones. Although within the canyon, pollution is 2–3 times higher near the upstream building. Cross ventilation can minimise or prevent infiltration of road-side pollutants into indoor spaces, while also assisting in the dispersion of ambient pollutants. The critical configuration, in terms of air quality, is single-sided ventilation from the canyon. This significantly increases indoor pollutant concentration regardless of the building location. The study reveals that multiple factors determine the indoor–outdoor links, and thorough indexing and understanding of the processes can help designers and urban planners in regulating urban configuration and geometries for improved indoor air quality. Future works should look at investigating the influence of indoor emissions and the effects of different seasons.

show abstract

A deep learning approach towards the detection and recognition of opening of windows for effective management of building ventilation heat losses and reducing space heating demand

Cited by 49 publications

References 58 publications

Development and evaluation of a vision-based transfer learning approach for indoor fire and smoke detection

Development and evaluation of a vision-based transfer learning approach for indoor fire and smoke detection

Recent Advances in Low-Carbon and Sustainable, Efficient Technology: Strategies and Applications

Impact of Ventilation Strategy on the Transmission of Outdoor Pollutants into Indoor Environment Using CFD

Contact Info

Product

Resources

About