Editorial Feature

IoT Technologies in Smoke Detectors

This article highlights recent developments in Internet of Thing (IoT) technology applied to smoke and fire detection.

Image Credit: nikkytok/Shutterstock.com

The Internet of Things (IoT) refers to technologies that apply computer processing and (typically) wireless connectivity technologies to physical and electronic devices to realize the network-enabling and digitization benefits of the internet in the physical world.

IoT technology is a key feature of the current wave of digitization. It is an underpinning technology for the Industry 4.0 model, in which industrial processes are monitored and controlled through a network using all of the discrete areas and movements in the process as input/output nodes.

IoT is also entering our homes, offices, places of learning, and public spaces. The same application of sensors, microprocessors, wireless data transfer, and efficient algorithms driving data-led decision making and performance improvement in industry enables data-led smart home and facilities management for the public.

Smoke detection can be a crucial feature of smart homes and buildings. Embedding smoke alarms with digital sensors, microprocessors, wireless connectivity, and the appropriate energy source to power these additions can improve the fire response of occupants, emergency departments, and automated or semi-automated systems – and ultimately save lives.

NB-IoT for Smoke Detection Systems

Recently, scientists from Qiqihar University College of Communication and Electronic Engineering, China, set out the benefits of narrowband (NB) IoT for smoke detection.

NB systems are designed to work with limited bandwidth. This makes them more reliable, as wireless connectivity can be more rugged and still have much more built-in redundancy to operate reliably. NB-IoT technology can greatly reduce the power consumption and cost of the equipment and increase its service life compared to traditional wireless networking technology.

In an example system provided by the Qiqihar team, the equipment for an NB-IoT smoke-detecting system was charged using polycrystalline silicon photovoltaic cells and energy was stored with supercapacitors. The photovoltaic charging circuit used the variable step length conductance increment method to track the maximum power point to improve the efficient use of solar energy in the system as a whole.

Low-Cost, Ultra-Low Power Consumption IoT

Smoke alarm systems are crucial for reducing indoor fires and protecting property. However, existing systems have drawbacks, including high upfront costs, difficulties monitoring working states, low data accuracy, and complex management requirements.

To address these issues, an independent smoke, temperature, and humidity sensing alarm system based on NB-IoT technology was recently proposed at a conference by scientists from China’s Xi’an University of Science & Technology.

The scientists said their system was low cost; had ultra-low power consumption; featured equipment damage and electric quantity alarms, multi-party alarms; and employed unified deployment management.

The temperature, humidity, and smoke data would be cross-referenced to give staff a clearer understanding of the fire scene, leading to better decision-making by the human frontline.

After testing, the system was able to work on standby for around five years, making it suitable for remote, hard-to-access locations. The team said this long life also made the system good value for money compared to smoke detection on the market currently.

Integrating Water Sprinklers and Emergency Departments

Scientists from Asia Pacific University of Technology and Innovation, Malaysia and  Prince Sultan University, Saudi Arabia, integrated water sprinklers and emergency department alerts in an IoT-based smoke detection system to improve fire response.

They proposed a system that would integrate different sensors, including heat, smoke, and flame. These signals go through an algorithm to check the fire's potential before broadcasting the predicted result to various parties using a GSM modem.

To obtain real-life data without endangering human lives, IoT technology was used to provide the fire department with necessary data on the fire’s exact location, make-up, and intensity.

The proposed system's main feature was to minimize false alarms using artificial intelligence (AI), which the researchers said made it more reliable. The experimental results showed the superiority of the proposed system in terms of affordability, effectiveness, and responsiveness. This was achieved partly by using the Ubidots platform, which facilitates faster and more reliable data exchange.

Sensing Smoke in Fog

IoT technologies typically face challenges in detecting smoke in a foggy outside environment.

To address this issue, an international interdisciplinary team from Sejong University in Seoul, South Korea, Instituto de Telecomunicações in Aveiro, Portugal, and Universidade de Fortaleza in Fortaleza, Brazil, recently proposed an energy-efficient system based on deep convolutional neural networks for early smoke detection in both normal and foggy physical environments.

The proposed method utilized the VGG-16 architecture, a convolutional neural network, due to its accuracy and time efficiency compared to other more computationally demanding networks, such as GoogleNet and AlexNet.

Experiments conducted on benchmark smoke detection datasets showed how the technique performed better than state-of-the-art methods in terms of accuracy, false alarm rate, and efficiency. The researchers said their system demonstrated a viable AI-based means of IoT-enabled smoke detection in challenging conditions.

Connecting IoT with Alarms and Lighting for Smart Evacuation

Evacuating a building from a fire in under twenty minutes improves survival rates dramatically. A recent paper proposed an IoT-based intelligent fire emergency response system with decentralized control to speed up evacuation and make it safer.

Sensors like smoke detectors, flame detectors, and heat detectors detect information on the progression of the fire and poisonous gas, and the building's vibrational state.

The system designs the path to evacuation points based on these conditions and guides evacuees to the best, safest way out with lights.

The system environment is composed of an Ember EM250 chipset, sensor modules, CDD controller, a communication module, a power module, a CSD controller, LED displays on walls and doors, and alarms.

Bidirectional data integration can occur as soon as fire or smoke is detected, with cooperation between the building owner or facility manager of the relevant building and the emergency services.

Continue reading: An Overview of Smoke Detectors

References and Further Reading

Alqourabah, H., et al (2021). A smart fire detection system using IoT technology with automatic water sprinkler. International Journal of Electrical and Computer Engineering. doi.org/10.11591/ijece.v11i4.pp2994-3002

Horowitz, B.T. (2020). IoT Makes Fire Detection Systems Smarter. [Online] IEEE Spectrum. Available at: https://spectrum.ieee.org/how-iot-makes-fire-detection-systems-smarter 

Khan, S., et al (2019). Energy-Efficient Deep CNN for Smoke Detection in Foggy IoT Environment. IEEE Internet of Things Journal. doi.org/10.1109/JIOT.2019.2896120.

Liu, Y., et al (2021). Design of NB-IoT smoke sensing terminal based on photovoltaic and supercapacitor power supply. Journal of Physics: Conference Series. doi.org/10.1088/1742-6596/1885/5/052008.

Ryu, C-S. (2015). IoT-based Intelligent for Fire Emergency Response Systems. International Journal of Smart Home. doi.org/10.14257/ijsh.2015.9.3.15.

Wang, J., et al (2019). Design of a Smart Independent Smoke Sense System Based on NB-IoT Technology. 2019 International Conference on Intelligent Transportation, Big Data & Smart City. doi.org/10.1109/ICITBS.2019.00104.

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Ben Pilkington

Written by

Ben Pilkington

Ben Pilkington is a freelance writer who is interested in society and technology. He enjoys learning how the latest scientific developments can affect us and imagining what will be possible in the future. Since completing graduate studies at Oxford University in 2016, Ben has reported on developments in computer software, the UK technology industry, digital rights and privacy, industrial automation, IoT, AI, additive manufacturing, sustainability, and clean technology.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Pilkington, Ben. (2023, February 22). IoT Technologies in Smoke Detectors. AZoSensors. Retrieved on February 24, 2024 from https://www.azosensors.com/article.aspx?ArticleID=2753.

  • MLA

    Pilkington, Ben. "IoT Technologies in Smoke Detectors". AZoSensors. 24 February 2024. <https://www.azosensors.com/article.aspx?ArticleID=2753>.

  • Chicago

    Pilkington, Ben. "IoT Technologies in Smoke Detectors". AZoSensors. https://www.azosensors.com/article.aspx?ArticleID=2753. (accessed February 24, 2024).

  • Harvard

    Pilkington, Ben. 2023. IoT Technologies in Smoke Detectors. AZoSensors, viewed 24 February 2024, https://www.azosensors.com/article.aspx?ArticleID=2753.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this article?

Leave your feedback
Your comment type
Submit
Azthena logo

AZoM.com powered by Azthena AI

Your AI Assistant finding answers from trusted AZoM content

Azthena logo with the word Azthena

Your AI Powered Scientific Assistant

Hi, I'm Azthena, you can trust me to find commercial scientific answers from AZoNetwork.com.

A few things you need to know before we start. Please read and accept to continue.

  • Use of “Azthena” is subject to the terms and conditions of use as set out by OpenAI.
  • Content provided on any AZoNetwork sites are subject to the site Terms & Conditions and Privacy Policy.
  • Large Language Models can make mistakes. Consider checking important information.

Great. Ask your question.

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.