Tunnel interval carbon emission calculation system and method based on AI intelligent safety helmet

Abstract

The invention discloses a tunnel interval carbon emission calculation system and method based on AI intelligent safety helmets, and relates to the technical field of shield tunnel interval engineering carbon emission calculation. The intelligent safety helmet collects construction mechanical equipment information through a built-in machine vision module, a built-in equipment identification sensor group and a built-in positioning module, identifies the type and number of shield segments by calling an AI algorithm model, and determines advancing mileage data of the safety helmet in a tunnel. Synchronously identifying operating mechanical equipment in the tunnel, calculating the carbon emission in real time by combining with multi-source sensor data, and calculating the total carbon emission; the carbon emission of the tunnel section is displayed in real time; and comparing the carbon emissions with the carbon emissions of the same type of tunnels in historical periods. According to the method, wearable equipment and a carbon emission calculation technology are creatively fused, carbon emission of the whole period of tunnel construction is accurately metered, and a dynamic carbon footprint management scheme is provided for green tunnel construction through real-time visual feedback and process optimization guidance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of carbon emission calculation of shield tunnel section engineering, and more particularly to a tunnel section carbon emission calculation system and method based on an AI intelligent safety helmet. BACKGROUND

[0002] At present, the green and low-carbon requirements for infrastructure construction are increasingly strict, and the accurate measurement and dynamic management of carbon emissions in the construction process of tunnel engineering have become a problem to be solved. The existing carbon emission calculation methods rely on post-event statistics and static factors, and have problems such as poor timeliness, low precision, and difficulty in covering dynamic changes in the whole construction process. In particular, in the complex tunnel section construction environment, it is particularly difficult to calculate the real-time usage of shield segments, the running state and position of construction machinery and equipment, which leads to the inability to achieve fine carbon emission accounting and real-time optimization guidance.

[0003] Therefore, in view of the defects of the prior art, how to provide a tunnel section carbon emission calculation system and method based on an AI intelligent safety helmet through the safety helmet that must be worn on the construction site is a problem that needs to be solved by those skilled in the art. SUMMARY

[0004] Therefore, the present application provides a tunnel section carbon emission calculation system and method based on an AI intelligent safety helmet, which innovatively integrates wearable smart devices and real-time carbon emission calculation technology, realizes accurate and dynamic measurement of carbon emissions in the whole cycle of tunnel construction, and guides process optimization through visual feedback, thereby constructing a "calculation-warning-control" closed-loop management system and providing a dynamic carbon footprint management scheme for green tunnel construction.

[0005] In order to achieve the above-mentioned purpose, the present application adopts the following technical solution: a tunnel section carbon emission calculation system based on an AI intelligent safety helmet, comprising: a tunnel information system, an intelligent safety helmet, a carbon emission analysis platform, and a multi-dimensional statistical report module; The tunnel information system is used to integrate tunnel engineering parameters, equipment information, and pipeline material data, and to construct a construction cycle carbon emission benchmark database; The intelligent safety helmet is internally provided with a device identification sensor group, a machine vision module, a positioning module, a power module, and an AI algorithm model; The power module is used to provide electric energy; The device identification sensor group, the machine vision module, and the positioning module are used to collect construction machinery and equipment information; The AI algorithm model is used to identify the type and quantity of shield segments according to the construction machinery and equipment data information, determine the travel mileage data of the safety helmet in the tunnel, and calculate the carbon emission based on the construction cycle carbon emission benchmark database; The carbon emission analysis platform is used for displaying the carbon emission of the tunnel section in real time. The multi-dimensional statistical report module realizes longitudinal construction stage comparison and horizontal similar tunnel carbon emission benchmarking based on the historical period carbon emission data of statistics.

[0006] Preferably, the equipment identification sensor group comprises: A millimeter wave radar for detecting the three-dimensional profile of the operating machine; A multi-spectral camera for verifying the type of machine by analyzing the shape of the equipment while observing the shape and number of segments; An RFID reader for identifying the type of construction equipment; A vibration sensor for identifying the operating state of the construction machine.

[0007] Preferably, the AI algorithm model comprises a segment type identification model and a machine carbon emission model. The segment type identification model adopts a multi-scale segment classification network to identify the size and thickness of the segment and determine the type of the segment. The machine carbon emission model adopts a hybrid calculation model integrating a device power database and real-time working condition perception.

[0008] Preferably, the smart safety helmet further comprises an encryption and evidence storage module for encrypting the carbon emission data and uploading it to the carbon emission analysis platform.

[0009] Preferably, a tunnel section carbon emission calculation method based on an AI smart safety helmet comprises: Importing carbon emission models of different segments and a tunnel construction carbon emission model, analyzing construction stage division, material list, and mechanical equipment configuration scheme, and generating carbon emission calculation benchmark parameters; Starting the machine vision module of the smart safety helmet, capturing construction scene data through the multi-spectral camera, synchronously triggering the equipment identification sensor group to determine the type of machine and collect operating data of the construction machine, and determining the position of the safety helmet through the positioning module; The AI algorithm model fuses the multi-modal data perceived, matches the segment carbon emission factor library according to the corresponding segment type and number, matches the preset emission factor library according to the type of construction excavation machine, combines the real-time power of the equipment and the fuel consumption rate, and dynamically calculates the instantaneous carbon emission of the current construction surface; The calculation result is double-channel encrypted and transmitted to the time series database and the blockchain node of the carbon emission analysis platform, respectively; The carbon emission analysis platform receives the data stream in real time, generates a three-dimensional carbon emission distribution model through a spatial interpolation algorithm, and simultaneously distinguishes different types of carbon emission; The multi-dimensional statistical report module generates a construction phase carbon emission audit report periodically, compares the deviation rate of the design value and the measured value, and outputs process optimization suggestions to the project management terminal based on the difference.

[0010] Preferably, the different types of carbon emissions include construction carbon emissions, segment carbon emissions, and mechanical equipment operation carbon emissions.

[0011] Preferably, the segment shape and quantity in the interval are captured by a multi-spectrum camera, and a segment type identification model is used to count the segment quantity and corresponding type in the current interval. The single-segment emission coefficient is determined according to the identified segment quantity and corresponding type, and the formula is as follows: Segment carbon emissions = segment quantity * single-segment prefabrication carbon emission equivalent. Wherein, the single-segment prefabrication carbon emission equivalent is calculated by the carbon emission of the material machine list given by the prefabrication field, and different segment types have different carbon emissions.

[0012] Preferably, according to the recognized travel mileage data and the width in the tunnel, the construction carbon emission factor library is matched to determine the unit volume construction carbon emission factor, and the formula is as follows: Construction machinery carbon emissions = tunnel cross-sectional area * positioning position length * unit volume construction carbon emission factor.

[0013] Preferably, when the mechanical equipment and its corresponding type are identified, the mechanical type carbon emission factor library is matched to calculate the mechanical equipment operation carbon emissions as follows: Mechanical carbon emissions = Σ (device power * running time * fuel carbon emission coefficient).

[0014] According to the above technical solution, compared with the prior art, the present application provides a tunnel interval carbon emission calculation system and method based on AI intelligent safety helmet, which constructs a construction cycle carbon emission benchmark database; the intelligent safety helmet collects construction mechanical equipment information through the built-in machine vision module, equipment identification sensor group and positioning module, identifies the shield segment type and quantity by calling the AI algorithm model, determines the travel mileage data of the safety helmet in the tunnel, synchronously identifies the running mechanical equipment in the tunnel combined with multi-source sensor data to calculate the carbon emissions in real time, and calculates the total carbon emissions; the carbon emissions of the tunnel interval are displayed in real time; and the carbon emissions of the same type of tunnel in the historical period are compared. The present application innovatively integrates wearable devices and carbon emission calculation technology to realize accurate measurement of carbon emissions in the whole cycle of tunnel construction, provides real-time visual feedback to guide process optimization, and constructs a closed-loop management system of "real-time calculation-immediate analysis-effective regulation", which provides a dynamic carbon footprint management scheme for green tunnel construction. BRIEF DESCRIPTION OF DRAWINGS

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0016] Figure 1 A schematic diagram of a tunnel section carbon emission calculation system based on an AI smart safety helmet is provided as an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the smart safety helmet of the present invention; Figure 3 This is a schematic diagram illustrating the "end-edge-chain" collaborative architecture used in the smart safety helmet of this invention; Figure 4 This is a functional schematic diagram of the carbon emission analysis platform of the present invention; Figure 5 This is a flowchart illustrating a specific implementation method of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] This invention discloses a carbon emission calculation system for tunnel sections based on an AI-powered smart safety helmet, such as... Figure 1 As shown, it includes: a tunnel information system, a smart safety helmet, a carbon emission analysis platform, and a multi-dimensional statistical report module; The tunnel information system is used to integrate tunnel engineering parameters (such as design drawings, construction plans, and phase divisions), equipment information (such as machinery models and power), and pipeline material data (such as segment types and specifications), as well as a material and machinery carbon emission factor database (segment carbon emission factors and energy carbon emissions), and to build a carbon emission benchmark database for the construction cycle. The segment information captured by the safety helmet spectral camera will have corresponding carbon emission factors, forming a known database. The construction cycle carbon emission benchmark database includes various carbon emission factor libraries for subsequent carbon emission calculations.

[0019] The smart safety helmet has a built-in device that includes a sensor group, a machine vision module, a positioning module, a power module, and an AI algorithm model. The power module is used to provide electrical energy; The device identification sensor group, the machine vision module and the positioning module are used to collect construction machinery device information; The AI algorithm model is used to identify the type and quantity of shield segments according to the construction machinery device data information, determine the travel mileage data of the safety helmet in the tunnel, and calculate the carbon emissions based on the construction cycle carbon emission benchmark database; The carbon emission analysis platform is used to display the carbon emissions of the tunnel section in real time; The multi-dimensional statistical report module realizes longitudinal construction stage comparison and horizontal similar tunnel carbon emission benchmarking based on statistical historical period carbon emission data.

[0020] Specifically, the intelligent safety helmet calls the embedded AI algorithm model to identify the type and quantity of shield segments, determines the position (travel mileage data) of the safety helmet in the tunnel in real time through the positioning module, synchronously identifies the operating machinery devices in the tunnel, and combines multi-source sensor data to calculate the segment carbon emissions, construction carbon emissions and machinery device operation carbon emissions in real time. The original environmental data and AI analysis results are transmitted to the cloud platform through the encryption and evidence storage module.

[0021] The carbon emission analysis platform receives and processes encrypted data from the intelligent safety helmet, and displays the tunnel section carbon emission dynamic in real time, generates a carbon emission intensity heat map and trend analysis atlas. A three-dimensional carbon emission distribution model (bound to the BIM model space coordinates) is generated by a spatial interpolation algorithm, which distinguishes different types of carbon emissions (construction carbon emissions, segment carbon emissions, and machinery device operation carbon emissions). Support sliding time window analysis mode, can trace back the carbon emission space distribution characteristics of any construction period.

[0022] The multi-dimensional statistical report module statistically analyzes historical period carbon emission data, realizes longitudinal construction stage comparison and horizontal similar tunnel carbon emission benchmarking. Periodically generate construction stage carbon emission audit report, compare the deviation rate of design value and measured value. Output process optimization suggestions to the project management terminal.

[0023] Specifically, the intelligent safety helmet comprises: a safety helmet shell, which constitutes the main protective structure of the helmet and has an inner cavity; A hat lining is fixedly installed at the top of the inner cavity of the safety helmet shell and used to contact the head when worn; A buffer layer is arranged between the safety helmet shell and the hat lining; A hat band is detachably connected to the lower part of both sides of the safety helmet shell; An AI algorithm model is installed in the form of software in the chip and fixedly installed on the rear outer surface or rear inner cavity of the safety helmet shell; A multi-spectrum camera is embedded and fixed or detachably installed on the front surface of the safety helmet shell (such as the central position above the front brim), and is electrically connected to the AI algorithm model through a data cable / internal wiring / wireless communication module; The Internet of Things sensor group includes an RFID reader embedded in the side or rear surface of the safety helmet shell or fixedly installed on a specific bracket outside the shell, and a vibration sensor fixedly installed in the inner cavity (such as the top or side) or outer surface of the safety helmet shell; The RFID reader and the vibration sensor in the Internet of Things sensor group are electrically connected to the AI algorithm model through a data cable / internal wiring / wireless communication module; A power module is fixedly installed at the rear of the inner cavity (such as below the hat lining) or the rear of the outer surface (such as beside the AI algorithm model) of the safety helmet shell, and supplies power to the AI algorithm model, the multi-spectrum camera, and the Internet of Things sensor group through a power cable; A data interface is provided on the outer surface (such as along the side) of the safety helmet shell and is connected to the AI algorithm model through an internal data cable for data export or charging (which can be integrated with the power module).

[0024] The AI algorithm model calculates the carbon emissions of the construction machinery in real time by fusing machine vision recognition results, equipment operating parameters, and environmental data, and using a dynamic emission factor method.

[0025] Specifically, the equipment identification sensor group includes: A millimeter wave radar for detecting the three-dimensional profile of the construction machinery in a low-visibility environment; A multi-spectrum camera for verifying the type of machinery by analyzing the shape of the equipment while observing the shape and number of segments; An Internet of Things sensor group including an RFID reader and a vibration sensor for identifying the model and operating state (such as empty load / loaded / abnormal) of the construction equipment. The RFID reader determines the type of machinery by reading the equipment tag.

[0026] Specifically, the AI algorithm model includes a segment type identification model and a machinery carbon emission model. The segment type identification model uses a multi-scale segment classification network to identify the size and thickness of the segment and determine the type of segment. The machinery carbon emission model uses a hybrid calculation model integrating a device power database and real-time working condition perception.

[0027] The segment type identification model identifies the type of segment based on a multi-scale segment classification network. The size and thickness of the segment are identified to determine the type of segment, so as to identify the type and number of shield segments. A mechanical carbon emission model for integrating device power data with real-time working condition sensing for hybrid computation.

[0028] Specifically, the intelligent safety helmet further comprises an encryption and storage module, which is used for uploading the carbon emission data after encryption to the carbon emission analysis platform.

[0029] The encryption and storage module is fixedly installed in the inner cavity of the safety helmet shell, and the core thereof comprises a special encryption chip, which is electrically connected with the core processor of the AI algorithm model through an internal data bus and performs data interaction. The encryption chip adopts the national encryption SM4 algorithm, uniformly encrypts the to-be-transmitted data output by the AI algorithm model, and generates an encrypted data stream. The encrypted data stream is then packaged into a data packet conforming to a specific transmission protocol (such as MQTT or HTTPS) by a data packaging functional unit. The encrypted data packet after packaging is connected to the AI algorithm model or the encryption chip through an internal data cable through a communication interface module fixedly installed on the safety helmet shell, and is finally transmitted to the cloud platform by using a wireless communication mode. At the same time, the blockchain storage function runs in the AI algorithm model or the cloud platform, is responsible for receiving the to-be-stored data, combining the to-be-stored data with a timestamp and a device ID into a storage transaction, and sending the storage transaction to a preset blockchain network through a communication interface or a cloud network. The blockchain network adopts a consortium chain architecture, and the nodes thereof are deployed to include a cloud server node and at least one local regulatory agency or enterprise server node, so as to realize the traceability and tamper-proof storage of the carbon emission data.

[0030] In the embodiment, the intelligent safety helmet adopts a “end-edge-chain” collaborative architecture. Multi-modal sensing layer: The multi-spectral camera supports fusion of visible light and near-infrared waveband, enhances the ability of texture feature extraction of the surface of the pipe piece; the millimeter wave radar constructs a three-dimensional space scanning system, and identifies the contour and moving track of the construction machinery through a dynamic point cloud matching technology; the vibration sensor inverses the mechanical operation state through frequency spectrum feature analysis, and dynamically correlates with the device energy consumption model.

[0031] Edge intelligent computing layer: The embedded computing unit realizes real-time alignment and feature fusion of multi-source data, supports fast carbon emission inference calculation; integrates a dynamic emission factor library (basic layer: prefabricated component full life cycle carbon emission factor; working condition layer: device operation state-energy consumption dynamic correlation parameter).

[0032] In one specific embodiment of the present application, an AI intelligent safety helmet-based tunnel section carbon emission calculation method comprises: S100, import different segment carbon emission model factors and tunnel construction carbon emission model factors through the tunnel information system, analyze the construction phase division, material list and mechanical equipment configuration scheme, and generate carbon emission calculation benchmark parameters (segment emission factor library, construction emission factor library, mechanical emission factor library, etc.); S200, real-time sensing of construction scene and data acquisition: starting the intelligent safety helmet to sense the multi-modal data of the construction scene, fusing the multi-modal data, and dynamically calculating the instantaneous carbon emission intensity of the current construction surface; Specifically, the machine vision module of the intelligent safety helmet is started, the data of the construction scene is captured through the multispectral camera, the type of the equipment is determined and the operation data of the construction machinery are collected through the synchronous triggering of the equipment identification sensor group, and the position of the safety helmet is determined through the positioning module; the number of segments is calculated, the work of the equipment is calculated, and the carbon emission of the corresponding position is calculated; The AI algorithm model fuses the multi-modal data perceived, matches the segment carbon emission factor library according to the type and number of the corresponding segments, matches the preset emission factor library according to the type of the construction excavation machinery, combines the real-time power and fuel consumption rate of the equipment, and dynamically calculates the instantaneous carbon emission of the current construction surface.

[0033] Specifically, the worker wears an intelligent safety helmet, starts the intelligent safety helmet, captures the shape and number of segments in the tunnel interval through the multispectral camera, and uses the segment type identification model to count the type and number of segments in the current interval. Synchronous triggering of the Internet of Things sensor group (RFID, millimeter wave radar) determines the type of the equipment and collects the operation data (power, state) of the construction machinery. The position (mileage) of the safety helmet is determined through the positioning module, so as to determine the carbon emission flow of the corresponding position.

[0034] S300, the multi-modal data perceived and the calculation results are double-channel encrypted and transmitted to the time series database and the blockchain node of the carbon emission analysis platform respectively; Specifically, the AI algorithm model performs multi-modal data fusion, matches the segment carbon emission factor library and the construction excavation carbon emission quota according to the type and number of the corresponding segments, determines the carbon emission of the segments and excavation, matches the preset emission factor library by the type of the machinery, combines the real-time power and fuel consumption rate of the equipment, and finally dynamically calculates the instantaneous carbon emission of the current construction surface.

[0035] Specifically, the encryption module double-channel encrypts the perceived data and the calculation results, and transmits the encrypted data to the time series database and the blockchain node of the cloud platform for storage.

[0036] S400, the carbon emission analysis platform receives the data stream in real time, generates a three-dimensional carbon emission distribution model (bound with the BIM model space coordinates) through a spatial interpolation algorithm, and distinguishes different types of carbon emission at the same time; S500, periodically generate a construction phase carbon emission audit report, compare the deviation rate of the design value and the measured value, and output process optimization suggestions to the project management terminal based on the benchmark parameters.

[0037] Specifically, the multi-dimensional statistical report module periodically generates (such as daily / weekly / construction phase) a construction phase carbon emission audit report, and outputs process optimization suggestions to the project management terminal based on historical data and comparative analysis.

[0038] Specifically, the intelligent safety helmet adopts an "end-edge-chain" collaborative architecture to achieve accurate carbon emission perception and calculation in construction scenarios through the following technologies: Multi-modal perception layer: multi-spectral cameras support visible light and near-infrared band fusion to enhance pipe surface texture feature extraction capability, combined with deep learning models to achieve high-precision pipe type recognition; millimeter wave radar constructs a three-dimensional space scanning system to identify the operating machinery contour through dynamic point cloud matching technology; the vibration sensor signal processing module collects raw vibration signals, pre-processes (such as filtering, amplification) and fast Fourier transform (FFT) processes the raw vibration signals, generates corresponding vibration spectrum data, and based on pre-set spectrum feature thresholds or pattern recognition rules, extracts and analyzes the received spectrum data, and then determines the operating state of the corresponding construction machinery equipment belongs to one of idle, load or abnormal; and dynamically associates with the equipment energy consumption model to obtain the mechanical energy consumption per unit time through the mechanical energy consumption database.

[0039] Edge intelligent computing layer: embedded computing unit realizes real-time alignment and feature fusion of multi-source data, and through mechanical energy consumption data and pipe carbon emission factors, it is unified for carbon emission calculation, supporting millisecond-level carbon emission inference calculation; Dynamic emission factor library integrates a multi-level parameter system: basic layer: prefabricated component full life cycle carbon emission factor; working condition layer: equipment operating state-energy consumption dynamic correlation parameter; Trusted transmission layer: dual-channel encryption mechanism implements differentiated security policies for raw perception data and calculation results; blockchain storage module realizes fast on-chain of data fingerprints, ensuring traceability and anti-repudiation of carbon emission data; The safety helmet shell passes industrial-level protection certification, and the built-in emergency power supply can maintain core function operation in emergency situations. The system supports remote model updating and knowledge migration to achieve intelligent adaptation across construction scenarios.

[0040] Specifically, the different types of carbon emissions include construction carbon emissions, pipe carbon emissions, and mechanical equipment operation carbon emissions.

[0041] Specifically, edge intelligent computing (real-time carbon emission calculation)

[0042] AI algorithm model performs multi-modal data fusion: The number of pipe pieces in the interval is counted by using a pipe piece type identification model, and a single pipe piece emission coefficient is determined according to the type of the pipe piece, and the formula is as follows: The carbon emission of the pipe piece = the number of pipe pieces x the carbon emission equivalent of a single pipe piece in prefabrication; The carbon emission equivalent of a single pipe piece in prefabrication is calculated from the carbon emission of the material list given by the prefabrication yard, and different pipe piece types have different carbon emissions.

[0043] Specifically, the construction (excavation) carbon emission calculation: according to the identified mileage data (mileage) and tunnel section information (width / area), the construction carbon emission factor library is matched to determine the unit volume construction carbon emission factor: The carbon emission of the construction machinery = the tunnel section area x the positioning position length x the unit volume construction carbon emission factor.

[0044] Specifically, when the mechanical equipment and its corresponding type are identified, the mechanical type carbon emission factor library is matched to calculate the mechanical carbon emission as follows: The carbon emission of the machinery = Σ (device power x operation time x fuel carbon emission coefficient).

[0045] Therefore, the total carbon emission = the carbon emission of the pipe piece + the carbon emission of the construction + the carbon emission of the machinery; The fuel carbon emission coefficient is dynamically adjusted according to the real-time oil product detection result.

[0046] Specifically, the three-dimensional carbon emission distribution model is bound with the BIM model space coordinates, supports the sliding time window analysis mode, and can trace back the carbon emission space distribution characteristics of any construction period.

[0047] In terms of real-time visual display of tunnel interval carbon emission dynamics, the system constructs a carbon emission monitoring interface through three-dimensional space-time mapping technology, and distinguishes and real-time visualizes different types of carbon emissions (construction, pipe piece, machinery) on the platform. The platform realizes dynamic visualization by using the following core technologies: The tunnel three-dimensional carbon emission intensity heat map (dynamic color spectrum mapping: green-yellow-red) is generated by using a space thermal rendering engine, which can reflect the carbon emission equivalent of each interval and the difference between different types of carbon emissions in real time. It supports hierarchical display according to carbon emission types and supports clicking on the pipe piece to view the hidden carbon data in the prefabrication stage.

[0048] The space-time cube analysis module (sliding time window to build X / Y / Z+time four-dimensional data cube) supports the cross-section comparison mode and the time spectrum analysis mode.

[0049] Specifically, the spatial thermal rendering engine: through the binding of environmental data stored by the blockchain and the BIM model coordinates, a three-dimensional carbon emission intensity thermal map of the tunnel is generated. The thermal gradient adopts dynamic color spectrum mapping (green-yellow-red), which reflects the carbon emission equivalent difference of each meter interval in real time. The system supports displaying the carbon emission contribution degree by layer according to the carbon emission types (pipe piece / construction / mechanical), and clicking any pipe piece can penetrate to view the implied carbon emission data in the prefabrication stage.

[0050] Specifically, the space-time cube analysis module: a four-dimensional carbon emission data cube (X / Y / Z axis space coordinates + time axis) is constructed by using a sliding time window technology, supporting: cross-section comparison mode: synchronously display the carbon emission intensity difference of the same mileage of different tunnel cross-section groups; time spectrum analysis mode: the carbon emission period characteristics of the tunnel are presented through a 3D graph.

[0051] In one specific embodiment of the present application, as shown in Figure 1 , a tunnel interval carbon emission calculation system based on an AI intelligent safety helmet includes a tunnel information system, an intelligent safety helmet, a carbon emission analysis platform and a multi-dimensional statistical report module: The tunnel information system integrates tunnel engineering parameters (design drawings / construction stage division), equipment information (mechanical model / power) and pipe material data (pipe piece type / specification) to construct a carbon emission benchmark database. The intelligent safety helmet is internally provided with a multi-spectrum camera (installed in the front), an Internet of Things sensor group (RFID reader / vibration sensor), a positioning module, an AI algorithm model and an encryption and storage module, please refer to Figure 2 ; The carbon emission analysis platform receives data to generate a three-dimensional carbon emission distribution model and a thermal map. The multi-dimensional statistical report module statistically processes historical data and outputs an audit report.

[0052] Specifically, as shown in Figure 3 , the intelligent safety helmet adopts an "end-edge-chain" collaborative architecture: 1. Multi-modal perception layer: The multi-spectrum camera fuses visible light and near-infrared bands to enhance the pipe piece surface texture feature extraction capability; The millimeter wave radar constructs a three-dimensional space scanning system, and identifies the construction mechanical contour through dynamic point cloud matching; The vibration sensor inversely calculates the mechanical operation state (empty load / loaded / abnormal) through frequency spectrum analysis; 2. Edge intelligent computing layer: The AI algorithm model carries a pipe piece type identification model (multi-scale classification network) and a mechanical carbon emission model; Integrated dynamic emission factor library: basic layer (whole life cycle factor of prefabricated component), working condition layer (device state- energy consumption associated parameter); The carbon emission analysis platform generates a three-dimensional carbon emission distribution model bound to the BIM model coordinates through a spatial interpolation algorithm, as shown in Figure 4 As shown, support: (1) Three-dimensional model construction: dynamically bind discrete carbon emission data points with the tunnel BIM design graph coordinate system to ensure accurate data mapping to the corresponding pipe piece position, and establish a real-time correlation between the pipe piece space position and the carbon emission amount through the mileage coordinates (X / Y / Z) of the positioning module.

[0053] (2) Spatial thermal rendering engine: use dynamic color spectrum (green-yellow-red) to display the carbon emission intensity per meter; classify according to the construction carbon emission layer (earthwork excavation), the pipe piece carbon emission layer (prefabricated embodied carbon), and the mechanical equipment layer (shield machine operation carbon).

[0054] (3) Spatiotemporal cube analysis module: construct a four-dimensional data cube (X / Y / Z+time axis) to realize cross-section comparison and time spectrum analysis.

[0055] Based on the above system, the embodiment of the present application also proposes a tunnel section carbon emission calculation method based on AI intelligent safety helmet, as shown in Figure 5 The method comprises the following steps: Step 1: initialization of reference parameters Import the pipe piece carbon emission factor library, the construction emission factor library, and the mechanical emission factor library through the tunnel information system, analyze the construction phase division scheme to generate calculation reference parameters.

[0056] Step 2: real-time sensing of construction scene

[0057] Workers wear intelligent safety helmets to enter the tunnel section; a multi-spectrum camera captures the shape and number of pipe pieces, a pipe piece type recognition model counts the current pipe piece type and number; a millimeter wave radar scans the three-dimensional profile of construction machinery, an RFID reader verifies the mechanical model; a positioning module determines the mileage position of the safety helmet; a vibration sensor collects device operation state data (power / load rate).

[0058] Step 3: edge intelligent calculation (core calculation logic)

[0059] After collecting the data, the AI chip can be used to calculate the pipe piece carbon emission amount, the construction carbon emission amount, and the mechanical equipment operation carbon emission amount, respectively.

[0060] The pipe piece carbon emission amount calculation: according to the identified pipe piece type and quantity, match the pipe piece carbon emission factor library, determine the single pipe piece emission coefficient, and the pipe piece carbon emission amount is as follows: Pipe piece carbon emission amount = pipe piece quantity × single pipe piece prefabricated carbon emission equivalent; Construction (excavation) carbon emission calculation: According to the identified travel mileage data (mileage) and tunnel section information (width / area), match the construction carbon emission factor library to determine the unit volume construction carbon emission factor: Construction carbon emission = tunnel section area x positioning position length x unit volume construction carbon emission factor; Mechanical equipment operation carbon emission calculation: According to the identified mechanical equipment and its type, match the mechanical type carbon emission factor library: Mechanical carbon emission = Σ (equipment power x operation time x fuel carbon emission coefficient); Among them, the fuel carbon emission coefficient is adjusted dynamically according to the real-time energy carbon emission factor result or working condition.

[0061] Calculate the instantaneous total carbon emission intensity of the current construction surface: Total carbon emission = segment carbon emission + construction carbon emission + mechanical carbon emission.

[0062] Step 4: Encryption and transmission of trusted data

[0063] Integrate the carbon emissions of different parts obtained and the segment, construction, and mechanical data, and through the encryption and storage module, the perceived data and calculation results are double-channel encrypted and transmitted to the cloud time series database and blockchain node storage at the same time.

[0064] Step 5: Three-dimensional visualization and dynamic analysis

[0065] After obtaining the encrypted data on the carbon emission analysis platform, the three-dimensional model is constructed by combining the segment carbon emission calculation, construction carbon emission, and mechanical carbon emission data through machine vision data, positioning module data, and built-in tunnel information library. The main content is to dynamically bind discrete carbon emission data points with the tunnel BIM design graph coordinate system to ensure accurate mapping of data to the corresponding segment location, and to establish a real-time correlation between segment space location and carbon emission through the mileage coordinates (X / Y / Z) of the positioning module. Then, according to the segment carbon emission calculation, construction carbon emission, and mechanical carbon emission data, spatial thermal rendering is realized, and dynamic color spectrum (green-yellow-red) is used to display carbon emission intensity per meter. Different colors represent different types of carbon emissions; according to the construction carbon emission layer (earth excavation), segment carbon emission layer (precast implicit carbon), and mechanical equipment layer (shield machine operation carbon), classification is carried out. Finally, according to the tunnel construction database, the space-time cube analysis module is constructed, including the construction of four-dimensional data cube (X / Y / Z+time axis), which realizes cross-section comparison and time spectrum analysis.

[0066] Step 6: Optimization feedback

[0067] Finally, the data analyzed by the carbon emission platform is uploaded to the multi-dimensional statistical report module to generate an audit report, which mainly includes: - the deviation rate of the design value and the measured value; - comparing the measured data with the past measured tunnel data to optimize the tunnel carbon emission benchmark value; - outputting process optimization suggestions to the project management terminal (such as: "the mechanical carbon emission of XX section is over standard, it is suggested to adjust the equipment load rate").

[0068] The embodiments of the present application have the following beneficial effects: Precise and real-time: By integrating multi-modal sensors and edge AI computing in the intelligent safety helmet, the carbon emission is directly calculated in real time and accurately in the construction line, solving the problems of lag and low precision in traditional methods.

[0069] Full-cycle coverage: The system covers the whole cycle of tunnel construction carbon footprint from the implicit carbon of pipe precast to the dynamic carbon of construction process.

[0070] Dynamic visualization: Real-time, intuitive and multi-dimensional visualization of carbon emission is achieved through three-dimensional heat maps, space-time cubes and other methods, which facilitates managers to quickly grasp the distribution and trend of carbon emission.

[0071] Reliable and credible: By using double-channel encryption and blockchain storage technology, the carbon emission data is ensured to be tamper-proof and traceable, meeting the requirements of carbon verification.

[0072] Closed-loop optimization: By providing historical comparison, horizontal benchmarking, deviation analysis and optimization suggestions, a closed-loop carbon management mechanism of "calculation-early warning-control" is constructed, which effectively guides the optimization of green construction technology.

[0073] Wearable and convenient: The safety helmet worn by workers is used as the carrier, without the need for additional complex deployment, and it is easy to promote and use in the construction site.

[0074] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts of each embodiment can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the related parts can be referred to the method part.

[0075] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A carbon emission calculation system for tunnel sections based on an AI-powered smart safety helmet, characterized in that, include: Tunnel information system, smart safety helmet, carbon emission analysis platform, and multi-dimensional statistical reporting module; The tunnel information system is used to integrate tunnel engineering parameters, equipment information and pipeline material data to build a carbon emission benchmark database for the construction cycle; The smart safety helmet has a built-in device that identifies a sensor group, a machine vision module, a positioning module, a power module, and an AI algorithm model. The power module is used to provide electrical energy; The device identification sensor group, machine vision module, and positioning module are used to collect information about construction machinery and equipment. The AI ​​algorithm model is used to identify the type and quantity of shield tunnel segments based on the data information of the construction machinery and equipment, determine the travel distance of the safety helmet in the tunnel, and calculate the carbon emissions based on the carbon emission benchmark database of the construction cycle. The carbon emission analysis platform is used to display the carbon emissions in the tunnel section in real time; The multi-dimensional statistical reporting module uses historical carbon emission data to compare carbon emissions during the construction phases and benchmark carbon emissions of similar tunnels in the horizontal direction.

2. The tunnel section carbon emission calculation system based on an AI smart safety helmet according to claim 1, characterized in that, The device identification sensor group includes: Millimeter-wave radar is used to detect the three-dimensional profile of operating machinery; Multispectral cameras are used to verify the type of machinery by analyzing the shape of the equipment, while simultaneously observing the shape and quantity of the tube segments. RFID readers are used to identify the type of construction machinery and equipment. Vibration sensors are used to identify the operating status of construction machinery.

3. The tunnel section carbon emission calculation system based on an AI smart safety helmet according to claim 1, characterized in that, The AI ​​algorithm model includes: a segment identification model and a mechanical carbon emission model; The segment type identification model employs a multi-scale segment classification network. The mechanical carbon emission model adopts a hybrid calculation model that integrates an equipment power database and real-time operating condition perception.

4. The tunnel section carbon emission calculation system based on an AI smart safety helmet according to claim 1, characterized in that, The smart safety helmet also includes an encryption and evidence storage module, which is used to encrypt carbon emission data and then upload it to the carbon emission analysis platform.

5. A method for calculating carbon emissions in tunnel sections based on an AI-powered smart helmet, applied to the tunnel section carbon emission calculation system based on an AI-powered smart helmet as described in any one of claims 1-4, characterized in that, include: Import carbon emission models of different tunnel segments and tunnel construction carbon emission models, analyze the construction stage division, material list and mechanical equipment configuration scheme, and generate carbon emission calculation benchmark parameters; The machine vision module of the smart safety helmet is activated, and data of the construction scene is captured by the multispectral camera. The device identification sensor group is triggered simultaneously to determine the type of machinery and collect the operating data of the construction machinery. The position of the safety helmet is determined by the positioning module. The AI ​​algorithm model fuses the perceived multimodal data, matches the segment carbon emission factor library according to the corresponding segment type and quantity, matches the preset emission factor library according to the construction excavation machinery type, and dynamically calculates the instantaneous carbon emissions of the current construction face by combining the real-time power of the equipment and the fuel consumption rate. The calculation results are encrypted in two channels and transmitted to the time-series database and blockchain node of the carbon emission analysis platform, respectively. The carbon emission analysis platform receives data streams in real time and generates a three-dimensional carbon emission distribution model through spatial interpolation algorithms, while also distinguishing different types of carbon emissions. The multi-dimensional statistical reporting module regularly generates carbon emission audit reports during the construction phase, compares the deviation rate between design values ​​and measured values, and outputs process optimization suggestions to the project management terminal based on the differences.

6. The method for calculating carbon emissions in tunnel sections based on an AI-powered smart safety helmet according to claim 5, characterized in that, The different types of carbon emissions include construction carbon emissions, segment carbon emissions, and mechanical equipment operation carbon emissions.

7. The method for calculating carbon emissions in tunnel sections based on an AI-powered smart safety helmet according to claim 5, characterized in that, The shape and number of tunnel segments within the interval are captured by a multispectral camera, and the number and corresponding types of tunnel segments in the current interval are counted using a tunnel segment type recognition model. The emission factor for a single tunnel segment is determined based on the number and type of the identified segments, using the following formula: Carbon emissions per segment = Number of segments × Carbon emission equivalent per prefabricated segment; The carbon emission equivalent of a single precast segment is calculated from the list of materials, labor and equipment provided by the precast yard. Different types of segments have different carbon emission amounts.

8. The method for calculating carbon emissions in tunnel sections based on an AI-powered smart safety helmet according to claim 5, characterized in that, Based on the identified travel mileage data and tunnel width, a construction carbon emission factor database is matched to determine the construction carbon emission factor per unit volume, as shown in the following formula: Carbon emissions from construction machinery = tunnel cross-sectional area × location length × carbon emission factor per unit volume.

9. The method for calculating carbon emissions in tunnel sections based on an AI-powered smart safety helmet according to claim 5, characterized in that, Once the mechanical equipment and its corresponding type are identified, the carbon emission factor library for the mechanical type is matched, and the carbon emissions from the operation of the mechanical equipment are calculated as follows: Mechanical carbon emissions = Σ (equipment power × operating time × fuel carbon emission coefficient).

Images