AIoT intelligent fire-fighting collaborative prevention and control method and system

Abstract

The invention relates to the technical field of intelligent fire fighting and urban public safety, and particularly provides an AIoT intelligent fire fighting collaborative prevention and control method and system, and the method comprises the following steps: S1, deploying a multi-mode sensing terminal array; s2, deploying intelligent edge nodes in each partition of the building; s3, building digital twin bodies of the building; s4, an alliance chain network based on the Hyperledger Fabric is established; and S5, developing an AR panoramic command system, and integrating a UWB positioning module and SLAM live-action modeling. Compared with the prior art, the system can support the visual command of the mobile terminal, achieves the live-action navigation of the fire scene through the fusion of the AR technology, and remarkably improves the fire prevention and control efficiency and the emergency resource scheduling efficiency in a complex building environment.

Description

Technical Field

[0001] The present invention relates to the field of smart firefighting and urban public safety technologies, and specifically provides an AIoT smart firefighting collaborative prevention and control method and system. Background Art

[0002] Current urban fire safety systems are plagued by technical bottlenecks such as insufficient fusion of heterogeneous multi-source data and inefficient emergency response coordination. Traditional fire monitoring relies primarily on standalone smoke detectors (such as those compliant with GB50116) and manual inspections, which can lead to response delays and false alarm rates.

[0003] Although the existing Internet of Things fire protection system (CN112489475A) can realize equipment networking, it lacks the ability to model the topology of building space, and there are errors in the positioning of fire sources. In terms of data fusion, the fire protection big data platform disclosed in CN113421400B still uses the traditional relational database architecture, which is difficult to handle 100,000-level terminal concurrent data streams. In addition, there are data barriers in fire protection, security and other systems, and the cross-platform linkage response time is long. Although similar foreign systems (such as US2021035835A1) have introduced machine learning algorithms, their single-layer cloud architecture causes the transmission delay of key instructions to exceed 800ms, which cannot meet the second-level response requirements of the GB / T26875.3 standard.

[0004] Furthermore, existing emergency response plans are mostly static, lacking the ability to dynamically analyze real-time situations. Furthermore, visual command systems are limited to two-dimensional displays, making it difficult to accurately navigate complex buildings. These technical shortcomings hinder the effectiveness of fire prevention and control in modern urban buildings, especially in super-high-rise complexes (buildings exceeding 250 meters in height). Summary of the Invention

[0005] In response to the above-mentioned deficiencies in the existing technology, the present invention provides a highly practical AIoT smart firefighting collaborative prevention and control method.

[0006] A further technical task of the present invention is to provide an AIoT smart firefighting collaborative prevention and control system that is rationally designed, safe and applicable.

[0007] The technical solution adopted by the present invention to solve its technical problem is:

[0008] The AIoT smart firefighting collaborative prevention and control method has the following steps:

[0009] S1. Deploy a multimodal sensor terminal array;

[0010] S2. Deploy intelligent edge nodes in each zone of the building;

[0011] S3, build building digital twins;

[0012] S4. Establish a consortium chain network based on Hyperledger Fabric;

[0013] S5. Develop an AR panoramic command system that integrates UWB positioning module and SLAM real-scene modeling.

[0014] Furthermore, in step S1, a dual-spectrum thermal imaging camera, a distributed optical fiber temperature sensor, and an air pressure gradient detection device are included to form an ad hoc network using the LoRaWAN protocol.

[0015] Furthermore, in step S2, intelligent edge nodes are deployed in each partition of the building, with built-in FPGA chips to implement the fire feature extraction algorithm, an improved YOLOv5s model is used for flame recognition, and a lightweight risk prediction model is run.

[0016] Furthermore, in step S3, a digital twin of the building is constructed, using the three-dimensional modeling technology of BIM+point cloud fusion, integrating a dynamic plan engine driven by reinforcement learning, and optimizing the emergency strategy in the 10^6-dimensional state space through the Q-learning algorithm.

[0017] Furthermore, in step S4, a consortium chain network based on Hyperledger Fabric is established, and a cross-domain data exchange smart contract is designed to achieve device status synchronization;

[0018] In step S5, the UWB positioning module and SLAM real-scene modeling are integrated, and the Wavelet noise reduction algorithm is used to ensure the voice command recognition rate in a 90dB noise environment. Each layer realizes data communication through the MQTT+HTTP / 3 hybrid protocol.

[0019] The AIoT smart firefighting collaborative prevention and control system first deploys a multimodal sensor terminal array, deploys intelligent edge nodes in each building partition, constructs a digital twin of the building, and establishes a consortium chain network based on Hyperledger Fabric. Finally, it develops an AR panoramic command system that integrates UWB positioning modules and SLAM real-scene modeling.

[0020] Furthermore, a multimodal sensing terminal array is deployed, including dual-spectrum thermal imaging cameras, distributed fiber optic temperature sensors and air pressure gradient detection devices, and an ad hoc network is established using the LoRaWAN protocol.

[0021] Furthermore, intelligent edge nodes are deployed in various partitions of the building, with built-in FPGA chips to implement fire feature extraction algorithms, adopt an improved YOLOv5s model for flame recognition, and run a lightweight risk prediction model.

[0022] Furthermore, a digital twin of the building is constructed, using three-dimensional modeling technology that integrates BIM+point cloud fusion, integrating a dynamic plan engine driven by reinforcement learning, and optimizing emergency strategies in a 10^6-dimensional state space through the Q-learning algorithm.

[0023] Furthermore, a consortium chain network based on Hyperledger Fabric was established, and cross-domain data exchange smart contracts were designed to achieve device status synchronization;

[0024] It integrates UWB positioning module and SLAM real-scene modeling, uses Wavelet noise reduction algorithm to ensure voice command recognition rate in 90dB noise environment, and realizes data communication between each layer through MQTT+HTTP / 3 hybrid protocol.

[0025] Compared with the existing technology, the AIoT smart fire protection collaborative prevention and control method and system of the present invention has the following outstanding beneficial effects:

[0026] (1) In terms of response time, through edge computing nodes and hybrid communication protocols, the fire identification speed is increased to 150ms / frame, and the overall system response delay is reduced by 78% compared with the traditional architecture, achieving a real-time response of 180ms;

[0027] (2) In terms of spatial positioning accuracy, the three-dimensional digital twin model integrates UWB positioning technology, reducing the fire source positioning error from the industry average of 5 meters to 0.5 meters, improving the spatial resolution by 10 times;

[0028] (3) In terms of intelligent decision-making, the dynamic emergency plan engine driven by reinforcement learning has increased the efficiency of emergency plan generation by 40 times with millions of training data, and the successful prediction rate has increased to 92%;

[0029] (4) In terms of system collaboration, blockchain smart contracts achieve a state synchronization error of less than 1ms for 8 types of heterogeneous system equipment, and the multi-system linkage response time is compressed from 5 minutes to 28 seconds;

[0030] (5) In terms of anti-interference capability, the wavelet transform-based speech enhancement algorithm maintains a 95% command recognition rate in a 90dB noise environment, which is 35% higher than traditional noise reduction technology;

[0031] (6) In terms of scalability, the new protocol stack supports concurrent access to over 3,000 terminals, increasing system capacity fivefold compared to conventional IoT platforms. This reduces the false alarm rate to below 3% and increases emergency resource dispatch efficiency by 60%, making it particularly suitable for minute-level closed-loop fire response in complex scenarios such as super-high-rise buildings (>300 meters). BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 It is a flowchart of the AIoT smart fire protection collaborative prevention and control method. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solutions of the present invention, the present invention will be further described in detail below in conjunction with specific embodiments. Obviously, the embodiments described are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0035] A best embodiment is given below:

[0036] like Figure 1 As shown, an AIoT smart fire protection collaborative prevention and control method in this embodiment has the following steps:

[0037] S1. Deploy a multimodal sensor terminal array;

[0038] Deploy a multimodal sensor terminal array, including a dual-spectrum thermal imaging camera (working wavelengths 3-5μm and 8-12μm), a distributed fiber optic temperature sensor (temperature measurement accuracy ±0.5℃), and an air pressure gradient detection device (range 0-100Pa), and form an ad hoc network through the LoRaWAN protocol.

[0039] S2. Deploy intelligent edge nodes in each zone of the building;

[0040] The built-in FPGA chip implements the fire feature extraction algorithm, uses the improved YOLOv5s model for flame recognition (mAP value reaches 92.7%), and runs a lightweight risk prediction model (inference time <50ms).

[0041] S3, build building digital twins;

[0042] It adopts BIM+point cloud fusion 3D modeling technology (accuracy ±2cm), integrates a reinforcement learning-driven dynamic plan engine, and optimizes emergency strategies in a 10^6-dimensional state space through the Q-learning algorithm.

[0043] S4. Establish a consortium chain network based on Hyperledger Fabric;

[0044] Design cross-domain data exchange smart contracts to achieve device status synchronization for eight types of systems, including fire protection, electricity, and elevators (timestamp error <1ms);

[0045] S5. Develop an AR panoramic command system that integrates UWB positioning module and SLAM real-scene modeling;

[0046] We developed an AR panoramic command system that integrates a UWB positioning module (accuracy ±10cm) with SLAM real-world modeling. Using a Wavelet noise reduction algorithm, we ensure voice command recognition in 90dB noise environments. Data is communicated across all layers using a hybrid MQTT+HTTP / 3 protocol. The system's overall response latency is controlled at 180±20ms, supporting concurrent access from over 3,000 terminals.

[0047] Based on the above method, the AIoT smart fire collaborative prevention and control system in this embodiment first deploys a multimodal sensor terminal array, deploys intelligent edge nodes in each partition of the building, builds a digital twin of the building, establishes a consortium chain network based on Hyperledger Fabric, and finally develops an AR panoramic command system that integrates the UWB positioning module and SLAM real-scene modeling.

[0048] Among them, a multimodal sensing terminal array is deployed, including dual-spectrum thermal imaging cameras, distributed fiber optic temperature sensors and air pressure gradient detection devices, and a self-organizing network is formed using the LoRaWAN protocol.

[0049] Intelligent edge nodes are deployed in various areas of the building, with built-in FPGA chips to implement fire feature extraction algorithms, use an improved YOLOv5s model for flame recognition, and run a lightweight risk prediction model.

[0050] Build a digital twin of the building, adopt 3D modeling technology that integrates BIM+point cloud, integrate a dynamic plan engine driven by reinforcement learning, and optimize emergency strategies in a 10^6-dimensional state space through the Q-learning algorithm.

[0051] Establish a consortium chain network based on Hyperledger Fabric, design cross-domain data exchange smart contracts, and achieve device status synchronization;

[0052] It integrates UWB positioning module and SLAM real-scene modeling, uses Wavelet noise reduction algorithm to ensure voice command recognition rate in 90dB noise environment, and realizes data communication between each layer through MQTT+HTTP / 3 hybrid protocol.

[0053] The above-mentioned specific implementation methods are only specific cases of the present invention. The patent protection scope of the present invention includes but is not limited to the above-mentioned specific implementation methods. Any technical solutions that conform to the above-mentioned specific implementation methods of the present invention and any appropriate changes or substitutions made thereto by ordinary technicians in the relevant technical field shall fall within the patent protection scope of the present invention.

[0054] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. AIoT smart fire protection collaborative prevention and control method, characterized by: The steps are as follows: S1. Deploy a multimodal sensor terminal array; S2. Deploy intelligent edge nodes in each zone of the building; S3, build building digital twins; S4. Establish a consortium chain network based on Hyperledger Fabric; S5. Develop an AR panoramic command system that integrates UWB positioning module and SLAM real-scene modeling.

2. The AIoT smart fire protection collaborative prevention and control method according to claim 1 is characterized in that: In step S1, a dual-spectrum thermal imaging camera, a distributed optical fiber temperature sensor, and an air pressure gradient detection device are used to form an ad hoc network using the LoRaWAN protocol.

3. The AIoT smart fire protection collaborative prevention and control method according to claim 2 is characterized in that: In step S2, intelligent edge nodes are deployed in each partition of the building, with built-in FPGA chips to implement the fire feature extraction algorithm, use the improved YOLOv5s model for flame recognition, and run a lightweight risk prediction model.

4. The AIoT smart fire protection collaborative prevention and control method according to claim 3 is characterized in that: In step S3, a digital twin of the building is constructed, using the 3D modeling technology of BIM+point cloud fusion, integrating a dynamic plan engine driven by reinforcement learning, and optimizing the emergency strategy in the 10^6-dimensional state space through the Q-learning algorithm.

5. The AIoT smart fire protection collaborative prevention and control method according to claim 3 is characterized in that: In step S4, a consortium chain network based on Hyperledger Fabric is established, and a cross-domain data exchange smart contract is designed to achieve device status synchronization; In step S5, the UWB positioning module and SLAM real-scene modeling are integrated, and the Wavelet noise reduction algorithm is used to ensure the voice command recognition rate in a 90dB noise environment. Each layer realizes data communication through the MQTT+HTTP / 3 hybrid protocol.

6. AIoT smart fire protection collaborative prevention and control system, characterized by: First, deploy a multimodal sensor terminal array, deploy intelligent edge nodes in each partition of the building, build a digital twin of the building, and establish a consortium chain network based on Hyperledger Fabric. Finally, develop an AR panoramic command system that integrates UWB positioning modules and SLAM real-scene modeling.

7. The AIoT smart fire protection collaborative prevention and control system according to claim 6 is characterized in that: Deploy a multimodal sensor terminal array, including dual-spectrum thermal imaging cameras, distributed fiber optic temperature sensors, and air pressure gradient detection devices, and use the LoRaWAN protocol to form an ad hoc network.

8. The AIoT smart fire protection collaborative prevention and control system according to claim 7 is characterized in that: Intelligent edge nodes are deployed in various areas of the building, with built-in FPGA chips to implement fire feature extraction algorithms, use an improved YOLOv5s model for flame recognition, and run a lightweight risk prediction model.

9. The AIoT smart fire protection collaborative prevention and control system according to claim 8 is characterized in that: Build a digital twin of the building, adopt 3D modeling technology that integrates BIM+point cloud, integrate a dynamic plan engine driven by reinforcement learning, and optimize emergency strategies in a 10^6-dimensional state space through the Q-learning algorithm.

10. The AIoT smart fire protection collaborative prevention and control system according to claim 9 is characterized in that: Establish a consortium chain network based on Hyperledger Fabric, design cross-domain data exchange smart contracts, and achieve device status synchronization; It integrates UWB positioning module and SLAM real-scene modeling, uses Wavelet noise reduction algorithm to ensure voice command recognition rate in 90dB noise environment, and realizes data communication between each layer through MQTT+HTTP / 3 hybrid protocol.

Images