Bridge fabrication machine construction full-period informatization management system based on AI technology

Abstract

The invention discloses a bridge fabrication machine construction full-period informatization management system based on an AI technology, and the system comprises a bridge fabrication machine global sensing subsystem which is used for collecting construction parameters in the construction operation process of a bridge fabrication machine; the edge processing subsystem is used for performing edge processing on the construction parameters acquired by the bridge fabrication machine global sensing subsystem; the digital twinning subsystem is used for establishing a digital twinning model for simulating the whole construction period of the bridge fabrication machine and synchronously mapping the construction parameters subjected to edge processing to the digital twinning model; and the safety monitoring subsystem is used for monitoring the working safety of the bridge fabrication machine based on the digital twin model. The method is used for solving the problems that in the prior art, the monitoring and analysis capacity of the construction process of the cantilever bridge fabrication machine is poor, and operation safety is not facilitated, and the purposes of informatization management of the construction process of the bridge fabrication machine and improvement of the safety and scientificity of the construction process of a continuous beam are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of bridge construction machine construction management, and particularly relates to a bridge construction machine construction whole cycle information management system based on AI technology. BACKGROUND

[0002] With the increasing importance of expressways / railways and the like in the field of transportation, the requirements for expressway construction are also continuously increasing. Bridge engineering, as one of the core projects of expressway projects, has an important influence on the overall project duration and quality, especially in the construction process of mountainous expressways.

[0003] Traditional processes usually use hanging basket cast-in-place method to realize continuous beam construction of expressways and high-speed railways. However, the hanging basket construction needs more hanging basket installation and debugging work on site, and with the advancement of construction sections, the hanging basket needs to be moved and re-anchored each time, which is complicated and time-consuming. The formwork of the hanging basket may be deformed during multiple uses and movements, which makes it difficult to control the size accuracy and surface quality of the beam body. Moreover, the formwork is hung on the main structure, and the formwork adjustment cannot be supported, which needs electric hoists for auxiliary adjustment, and the operation is difficult and the construction efficiency is low.

[0004] In recent years, the cantilever bridge construction machine has been widely concerned as a new type of bridge construction equipment. Compared with the traditional hanging basket construction, the cantilever bridge construction machine has the following advantages: modular design, prefabrication of each module in the factory, then transported to the construction site for rapid assembly, fast overall positioning speed; the main truss is installed with wheels, which cooperates with the track laid on the pier or beam body, relies on electric drive to realize rolling on the track, and the walking speed and position are accurately controlled by the electric system; better guarantee of the shape size accuracy and surface flatness of the beam body, effective control of the appearance quality of the beam body.

[0005] The existing cantilever bridge construction machine includes a truss system, a walking system, a suspension system, a formwork system, an anchoring system, a worker safety protection system and a hydraulic system; although it can realize rapid and efficient construction of continuous beams through the cooperation of various systems, its active monitoring capability in the construction process is still weak, and it cannot effectively analyze and monitor the construction process of the cantilever bridge construction machine, and the operation safety and intelligent degree need to be improved. SUMMARY

[0006] The present application provides a bridge construction machine construction whole cycle information management system based on AI technology to solve the problem of weak monitoring and analysis capability of the construction process of the cantilever bridge construction machine in the prior art, which is not conducive to operation safety, realizes information management of the construction process of the bridge construction machine, and improves the safety and scientificity of the continuous beam construction process.

[0007] The application is realized by the following technical solutions:

[0008] An AI technology-based bridge-building machine construction whole-cycle informatization management system, comprising:

[0009] A bridge-building machine whole-domain perception subsystem, configured to collect construction parameters in a bridge-building machine construction operation process;

[0010] An edge processing subsystem, configured to perform edge processing on the construction parameters collected by the bridge-building machine whole-domain perception subsystem;

[0011] A digital twin subsystem, configured to establish a digital twin model simulating a bridge-building machine construction whole cycle, and to synchronously map the edge-processed construction parameters to the digital twin model;

[0012] A safety monitoring subsystem, configured to monitor the safety of the bridge-building machine operation based on the digital twin model.

[0013] In view of the weak monitoring and analysis capability of the construction process of a cantilever bridge-building machine in the prior art, which is not conducive to the safety of the operation, the application provides an AI technology-based bridge-building machine construction whole-cycle informatization management system, which comprises a bridge-building machine whole-domain perception subsystem, an edge processing subsystem, and a digital twin subsystem; the bridge-building machine whole-domain perception subsystem collects a large amount of construction parameters in the bridge-building machine construction operation process, and the edge processing subsystem performs in-situ processing on the collected massive data, thereby providing high-quality input for the digital twin subsystem while ensuring low-latency safe response and facilitating efficient execution of optimization instructions. The digital twin subsystem in the application establishes a digital twin model simulating the bridge-building machine construction whole cycle based on digital twin technology, and synchronously maps the edge-processed construction parameters to the digital twin model, so that the entire construction process can be monitored and accurately predicted in real time on the digital twin model, and the safety of the bridge-building machine operation process can be effectively monitored and warned by the safety monitoring subsystem.

[0014] The application overcomes the defects of the cantilever bridge-building machine construction process, such as strict control precision requirement, high operation risk, and weak monitoring and analysis capability of the construction process in the prior art, and truly realizes the transparency and predictability of the bridge-building machine construction process. The digital twin model realizes precise control and active intervention of the construction process through virtual-real interaction, significantly improves the informatization level of bridge engineering, significantly improves the safety of the continuous beam construction process, and is conducive to providing scientific guidance for the continuous beam construction based on the bridge-building machine.

[0015] Further, the bridge-building machine whole-domain perception subsystem comprises:

[0016] Distributed fiber-optic stress sensors are arranged in the poured segment, the cantilever end, the cantilever root and the cantilever segment joint of the bridge girder erection machine, and are used for monitoring the stress changes of the poured segment of the bridge and the main stress positions of the bridge girder erection machine.

[0017] Inclination meters and displacement meters are arranged at the cantilever end of the bridge girder erection machine, and are used for monitoring the deflection deformation; the displacement, inclination and bending deformation of the bridge girder erection machine can be monitored through the inclination meters and displacement meters.

[0018] Acceleration sensors are arranged at the top end of the truss of the bridge girder erection machine, and are used for monitoring the acceleration of the truss; the bridge girder erection machine can be assisted to be controlled during active movement, and the safety of the bridge girder erection machine can be judged under extreme harsh working conditions such as earthquakes and gales.

[0019] Fiber-optic grating sensors are arranged on the anchorage devices at both ends of each suspender of the bridge girder erection machine, and are used for monitoring the internal force of the suspender; the internal force of the suspender of the bridge girder erection machine can be monitored in real time through the strain-sensitive characteristics of the fiber-optic grating sensors, so as to ensure the construction safety, control the bridge alignment and ensure the quality of the completed bridge. The fiber-optic grating sensors have the advantages of strong anti-electromagnetic interference ability, electrical safety, convenient distributed or multi-point measurement (one fiber stringing multiple gratings), fast response speed, long transmission distance, good corrosion resistance and the like.

[0020] Wind condition sensors, temperature sensors and humidity sensors are arranged on the top of the bridge girder erection machine, and are respectively used for monitoring the wind speed and direction, the environmental temperature and the air humidity of the working environment.

[0021] Vibration sensors are arranged on the walking system, the anchoring system, the truss system, the suspension system and the formwork system of the bridge girder erection machine, and are used for monitoring the vibration data of the bridge girder erection machine; the vibration data in the scheme include but are not limited to vibration acceleration, amplitude and the like.

[0022] The first image acquisition unit includes a plurality of first cameras, and the shooting direction is towards the poured segment and the formwork system of the bridge girder erection machine; the first image acquisition unit is used as a physical monitoring unit of the whole system, and is used for manually monitoring the maintenance of the poured segment and the opening and closing of the formwork system in the background.

[0023] Further, the edge processing subsystem includes:

[0024] The data preprocessing module is used for preprocessing the collected construction parameters, and the preprocessing includes denoising and removing abnormal values;

[0025] The feature extraction module extracts the characteristic values of the preprocessed construction parameters by using the principal component analysis method;

[0026] The edge gateway module is used for transmitting the characteristic values of the preprocessed construction parameters to the digital twin subsystem;

[0027] An edge computing module is deployed to deploy a lightweight AI model for stress overrun local early warning; the lightweight AI model can adopt an LSTM model, and when the stress calculated by the model exceeds the set threshold, a warning information is sent out.

[0028] Further, the method for establishing the digital twin model comprises:

[0029] A finite element model of the bridge building machine is established;

[0030] The material constitutive relation is determined; the load condition and the boundary condition are set; and the grid is divided;

[0031] Parameterized variables are embedded, and the parameterized variables include the elastic modulus of the concrete;

[0032] The coordinates of each collection device in the global perception subsystem of the bridge building machine are mapped into the corresponding grid nodes, and the mapping method can be realized by shape function interpolation technology.

[0033] Further, the digital twin subsystem comprises:

[0034] A motion simulation module is configured to simulate the movement process of the walking system of the bridge building machine in the digital twin model under any working condition; that is, during the movement of the bridge building machine, the real-time collected motion working condition of the bridge building machine is synchronized into the digital twin model, so that the relative motion of the bridge building machine and the formed area in the digital twin model is realized.

[0035] A data assimilation module is configured to project the construction parameters processed by the edge into the digital twin model, and then dynamically correct the state and parameters of the digital twin model according to the actual working condition.

[0036] A parameterized variable inversion module is configured to invert the parameterized variable based on the construction parameters processed by the edge; the uncertain parameters embedded in the establishment process of the digital twin model are defined as parameterized variables, and the parameterized variables are inverted in real time by the received construction parameters, so that the online accurate calibration of the uncertain parameters of the digital twin model is realized.

[0037] A visualization module is configured to render and display the BIM model of the bridge building machine and the formed area of the bridge; wherein the BIM model of the bridge building machine is established in advance and imported; the BIM model of the formed area of the bridge is generated by the pre-imported bridge design drawing and the walking path of the bridge building machine. In the BIM model, different colors can be used to map and distinguish different stress areas, so as to facilitate the background personnel to quickly grasp the real-time stress condition of the construction process.

[0038] Further, the digital twin subsystem further comprises a creep prediction module for predicting the creep of the concrete in the formed region of the bridge, the creep prediction module comprising a prediction model as follows:

[0039] ;

[0040] wherein t0 is the age of the concrete when it begins to bear stress; t is the target time at which the creep needs to be predicted; ε(t, t0) is the total creep deformation in the time t-t0; σ is the sustained stress; E is the elastic modulus; K is a material constant related to the type of aggregate; ψ is the creep rate index; C u is the ultimate creep coefficient.

[0041] The essence of concrete creep prediction is the modeling of time-dependent material behavior. Traditional physical models have explicit creep equations, but have the problem of difficult parameter calibration. Algorithms such as LSTM can capture the nonlinear characteristics of concrete creep, but lack physical constraints, making it difficult to accurately model. The creep prediction model proposed in this scheme can overcome the above problems, combining material constants and field data to achieve millimeter-level creep prediction. The sustained stress σ refers to the constant compressive stress that the concrete bears for a long time (such as stress due to prestress, self-weight); the material constant K can be obtained by regression of creep test data; the creep rate index ψ is a rate that characterizes the rate at which the creep reaches a steady value, and can be obtained by Kalman gain matrix inversion.

[0042] Further, the safety monitoring subsystem comprises:

[0043] an overload warning unit for obtaining stress data in the digital twin model, identifying stress overload regions and warning;

[0044] a crack prediction unit for obtaining crack data in the digital twin model in the cast segment and the bridge deck system, and predicting the crack propagation path based on mechanical simulation;

[0045] a loosening warning unit for obtaining vibration data of the bridge deck machine in the digital twin model, and predicting the pre-tightening force of each bolt based on the vibration spectrum, identifying loose bolts and warning;

[0046] a limit condition unit for applying extreme construction loads to the digital twin model, and judging the operation safety based on the response results under the extreme construction loads;

[0047] a weather risk unit for obtaining local weather forecast data, and predicting the anti-overturning ability of the digital twin model based on the local weather forecast data;

[0048] a life management unit for predicting the remaining life of the key components of the bridge deck machine based on a fatigue cumulative damage model.

[0049] The scheme provides at least six risk early warning and management units related to the safety monitoring of the bridge builder, can realize effective monitoring and early warning of the bridge builder construction process from aspects of stress overload, crack direction, bolt loosening, extreme load (such as complete eccentricity of concrete pouring), extreme weather (such as strong wind disturbance) and fatigue cumulative damage, and significantly improves the safety and scientific nature of the continuous beam construction process.

[0050] Further, the weather risk unit calculates the overturning resistance capacity by the following formula:

[0051] ;

[0052] In the formula, G is the overturning resistance coefficient; W i is the self weight of the i th stable component; d i is the horizontal distance from the i th stable component to the overturning axis; F is the total horizontal wind load acting on the bridge builder; h is the height difference between the centroid height of the wind receiving surface and the overturning axis; wherein:

[0053] ;

[0054] In the formula, v is the wind speed; A is the projection area of the wind load on the bridge builder in the most unfavorable direction; C is the wind load body shape coefficient.

[0055] Those skilled in the art should understand that:

[0056] The stable component in the scheme refers to all devices that generate overturning resisting moment through their own gravity during the construction process of the bridge builder, such as truss systems, anchoring systems, outriggers, counterweights, formwork systems, poured beam segments, construction tools, etc.

[0057] The overturning axis in the scheme is the axis of the bridge builder, which can be considered as the connecting line of the front and rear outriggers.

[0058] Further, it also includes a spraying control subsystem; the spraying control subsystem includes:

[0059] The spraying unit includes a plurality of spray heads arranged on the truss of the bridge builder, the spray heads are directed towards the poured segment of the bridge, and the emission direction is horizontal;

[0060] The second image acquisition unit includes a plurality of second cameras arranged on the truss of the bridge builder, the shooting direction of the second cameras is directed towards the poured segment of the bridge;

[0061] The first image recognition unit is used to identify the non-spraying area in the image acquired by the second image acquisition unit;

[0062] A first control unit is configured to control the initial velocity of the one or more nozzles closest to the non-sprayed area, so that the water jet is sprayed to the non-sprayed area.

[0063] In the field of bridge pouring, although the automatic spraying system has been widely used, the existing automatic spraying system can only start spraying at a fixed time and quantity, and it is difficult to meet the automatic development needs of intelligent bridge building machines. Based on this, the spraying control subsystem is integrated into the whole cycle information management system, the image of the sprayed section is collected by the second image acquisition unit, and the non-sprayed area is defined as the non-sprayed area by identifying the non-sprayed area in the image by the first image recognition unit. Then, the first control unit locates the non-sprayed area, locates the one or more nozzles closest to each non-sprayed area, calculates the horizontal distance between the corresponding one or more nozzles and the non-sprayed area, calculates the initial velocity required for horizontal spraying to the non-sprayed area by the parabolic formula, and finally controls the initial velocity of the corresponding one or more nozzles by the calculation result. Of course, the initial velocity can be realized by controlling the existing ways such as pumping pressure, water head height or nozzle size, which is not limited here. In addition, the first image recognition unit in the present scheme uses existing image recognition technology to identify the non-sprayed area, such as color difference based on feature recognition technology.

[0064] The spraying control subsystem of the present scheme can quickly and automatically complete the re-spraying operation for the missed spraying area based on the actual spraying effect on site, overcoming the defects of uneven spraying and easy existence of blind area in the automatic spraying process of the prior art.

[0065] Further, it further comprises a vibrating control subsystem; the vibrating control subsystem comprises:

[0066] A vibrating unit comprising a plurality of attached vibrators arranged on the outer wall of the bridge building machine formwork system;

[0067] A height recognition unit for recognizing the height of the poured concrete;

[0068] A second control unit for controlling each attached vibrator; when the height of the poured concrete is higher than the height of a certain attached vibrator, the attached vibrator is started;

[0069] A third image acquisition unit comprising a plurality of third cameras arranged above the pouring area;

[0070] A second image recognition unit for recognizing the pits on the surface of the concrete in the image obtained by the third image acquisition unit.

[0071] In the scheme, the attached vibrators are distributed on the outer wall of the formwork system; when the second control unit determines that the height of the internally poured concrete exceeds a certain attached vibrator, the corresponding attached vibrator is controlled to start.

[0072] In addition, the control of the vibration time in the prior art is dependent on the operation experience and is subjective, and misjudgment is prone to occur, which delays the construction period. In the scheme, the third image acquisition unit photographs the top image of the poured concrete from top to bottom above the concrete pouring area, and the second image recognition unit recognizes the pits in the image; if there are pits, it means that there are still bubbles to be broken, so the vibration needs to continue; if there are no new pits in a period of time, it can be considered that the concrete has been vibrated and compacted, and the vibration operation can be stopped in time. The scheme provides an objective control method for the vibration time based on image recognition technology, which can reduce the dependence on the experience of on-site operators and ensure the stability of the vibration effect. Of course, the third cameras in the third image acquisition unit can be adaptively arranged and installed according to the specific working conditions on site, such as on the bracket above the formwork. In addition, the identification of pits by the second image recognition unit can also be realized based on existing image recognition technology.

[0073] Compared with the prior art, the present application has at least the following advantages and beneficial effects:

[0074] 1. The bridge building machine construction full-cycle information management system based on AI technology overcomes the defects of the cantilever bridge building machine construction process, such as strict control precision requirement, high operation risk, weak monitoring and analysis ability of the existing technology, and truly realizes the transparency and predictability of the bridge building machine construction process. The precise control and active intervention of the construction process are realized through the virtual-real interactive digital twin model, which significantly improves the informatization degree of bridge engineering and the safety of continuous beam construction process, and is beneficial to providing scientific guidance for continuous beam construction based on the bridge building machine.

[0075] 2. The bridge building machine construction full-cycle information management system based on AI technology overcomes the problems of parameter calibration difficulty and lack of physical constraints in the existing technology, and realizes millimeter-level creep prediction by combining material constants and field data.

[0076] 3. The bridge building machine construction full-cycle information management system based on AI technology provides at least six risk warning and management units related to the safety monitoring of the bridge building machine, which can realize effective monitoring and warning of the bridge building machine construction process from multiple aspects such as stress overload, crack direction, bolt loosening, extreme load, extreme weather and fatigue cumulative damage, significantly improving the safety and scientific nature of the continuous beam construction process.

[0077] 4. The present invention is an information management system for the entire construction cycle of a bridge-building machine based on AI technology. The proposed spray control subsystem can quickly and automatically complete the respraying operation for missed areas based on the actual spraying effect on site, overcoming the defects of uneven spraying and easy existence of spray blind spots in the existing automatic spraying process.

[0078] 5. The present invention provides an information management system for the entire construction cycle of bridge-building machines based on AI technology. Based on image recognition technology, it provides an objective control method for vibration time, which can reduce the dependence on the experience of on-site operators and ensure stable vibration effect. Attached Figure Description

[0079] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0080] Figure 1 This is a system schematic diagram of a specific embodiment of the present invention. Detailed Implementation

[0081] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments and accompanying drawings. The illustrative embodiments and descriptions of this invention are for explaining the invention only and are not intended to limit the invention. In the description of this application, it should be understood that terms such as "front," "rear," "left," "right," "upper," "lower," "vertical," "horizontal," "high," "low," "inner," and "outer," indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description. They do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the scope of protection of this application.

[0082] Example 1:

[0083] like Figure 1 The diagram shows an AI-based information management system for the entire construction lifecycle of a bridge-building machine, comprising a bridge-building machine full-domain perception subsystem, an edge processing subsystem, a digital twin subsystem, and a safety monitoring subsystem.

[0084] The bridge-building machine's all-domain perception subsystem is used to collect construction parameters during the bridge-building machine's construction operation; specifically, it includes:

[0085] Distributed fiber optic stress sensors are deployed inside the cast-in-place segments, as well as at the cantilever ends, cantilever roots, and joints of the cantilever segments of the bridge-building machine, to monitor stress changes.

[0086] An inclinometer and a displacement meter are arranged at the cantilever end of the bridge builder, for monitoring deflection deformation, i.e. monitoring the inclination and displacement;

[0087] An acceleration sensor is arranged at the top end of the truss of the bridge builder, for monitoring the acceleration of the truss;

[0088] Fiber Bragg grating sensors are arranged on the anchorage devices at both ends of each boom of the bridge builder, for monitoring the internal force of the boom;

[0089] A wind condition sensor, a temperature sensor, and a humidity sensor are arranged at the top of the bridge builder, for monitoring the wind speed and direction, the environmental temperature, and the air humidity of the working environment, respectively;

[0090] Vibration sensors are arranged on the running system, the anchoring system, the truss system, the suspension system, and the formwork system of the bridge builder, for monitoring the vibration data of the bridge builder;

[0091] The first image acquisition unit includes a plurality of first cameras, and the shooting direction is towards the poured segment and the formwork system of the bridge builder.

[0092] The edge processing subsystem is used for edge processing of the construction parameters collected by the bridge builder global perception subsystem; specifically including:

[0093] The data preprocessing module is used for preprocessing the collected construction parameters, and the preprocessing includes denoising and removing abnormal values;

[0094] The feature extraction module extracts the characteristic values of the preprocessed construction parameters using principal component analysis;

[0095] The edge gateway module is used for transmitting the characteristic values of the preprocessed construction parameters to the digital twin subsystem;

[0096] The edge computing module deploys a lightweight AI model, and is used for local early warning of stress overrun.

[0097] The digital twin subsystem is used for establishing a digital twin model simulating the whole construction cycle of the bridge builder, and synchronously mapping the edge-processed construction parameters to the digital twin model; specifically including:

[0098] The motion simulation module is used for simulating the movement process of the running system of the bridge builder under any working condition in the digital twin model;

[0099] The data assimilation module is used for projecting the edge-processed construction parameters into the digital twin model;

[0100] The parameterized variable inversion module is used for inverting the parameterized variable based on the edge-processed construction parameters;

[0101] a visualization module, configured to render and display a BIM model of the bridge-erecting machine and the formed region of the bridge;

[0102] a creep prediction module, configured to predict the creep of the concrete in the formed region of the bridge.

[0103] The creep prediction module comprises a prediction model as follows:

[0104] ;

[0105] wherein: t0 is the age of the concrete when it starts to bear stress; t is the target time at which the creep is to be predicted; ε(t, t0) is the total creep deformation in the time t-t0; σ is the sustained stress; E is the elastic modulus; K is a material constant related to the type of aggregate; ψ is a creep rate index, which is set to 0.6 by default for general construction concrete; C u is a limit creep coefficient.

[0106] Preferably, the limit creep coefficient C u is a humidity-related coefficient, and the calculation formula in the embodiment is as follows:

[0107] wherein: H is the air humidity; and VSR is the volume-to-surface area ratio of the poured segment.

[0108] Preferably, the material constant K has a value as follows:

[0109] for lightweight aggregate, K = 4-6;

[0110] for granite aggregate, K = 7-9;

[0111] for quartzite aggregate, K = 10-13;

[0112] for limestone aggregate, K = 8-10.

[0113] The method for establishing the digital twin model comprises the following steps:

[0114] establishing a finite element model of the bridge-erecting machine; preferably, the finite element model is obtained by converting the BIM model;

[0115] determining the material constitutive relation; setting the load condition and the boundary condition; and dividing the mesh;

[0116] embedding parameterized variables, the parameterized variables including the elastic modulus of the concrete;

[0117] mapping the coordinates of each collection device in the global perception subsystem of the bridge-erecting machine to the corresponding mesh nodes.

[0118] The safety monitoring subsystem is configured to monitor the work safety of the bridge-erecting machine based on the digital twin model; specifically, the safety monitoring subsystem comprises:

[0119] an overload early warning unit configured to obtain stress data in the digital twin model, identify stress overload areas, and provide early warnings;

[0120] a crack prediction unit configured to obtain crack data in the digital twin model on the cast segment and the bridge-erecting machine template system, and predict crack propagation paths based on mechanical simulation;

[0121] a loosening early warning unit configured to obtain vibration data of the bridge-erecting machine in the digital twin model, predict the pre-tightening force of each bolt based on the vibration spectrum, identify loosening bolts, and provide early warnings;

[0122] a limit condition unit configured to apply extreme construction loads to the digital twin model, and determine the safety of the operation based on the response results under the extreme construction loads;

[0123] a weather risk unit configured to obtain local weather forecast data, and predict the overturning resistance of the digital twin model based on the local weather forecast data;

[0124] a life management unit configured to predict the remaining life of the key components of the bridge-erecting machine based on a fatigue cumulative damage model.

[0125] The weather risk unit calculates the overturning resistance by the following formula:

[0126] ;

[0127] In the formula, G is the overturning resistance coefficient; W i is the weight of the i-th stable component; d i is the horizontal distance from the i-th stable component to the overturning axis; F is the total horizontal wind load acting on the bridge-erecting machine; h is the height difference between the centroid height of the wind-affected surface and the overturning axis; wherein:

[0128] ;

[0129] In the formula, v is the wind speed; A is the projected area of the wind load on the bridge-erecting machine in the most unfavorable direction; C is the wind load shape coefficient, and in this embodiment, the bridge-erecting machine is equivalent to a truss structure, and C = 1.3.

[0130] In a more preferred embodiment, the weather risk unit provides overturning resistance warnings by the following standards:

[0131] If G≥1.5: normal operation is allowed;

[0132] If 1.2≤G<1.5: the travel speed of the bridge-erecting machine is limited;

[0133] If G<1.2: the bridge-erecting machine is locked and is not allowed to travel.

[0134] Example 2:

[0135] An AI technology-based bridge construction machine construction whole-cycle information management system, further comprising a spraying control subsystem and a vibrating control subsystem based on the embodiment 1.

[0136] The spraying control subsystem comprises:

[0137] a spraying unit comprising a plurality of nozzles arranged on a truss of the bridge construction machine, the nozzles being directed towards a bridge-cast segment and having a horizontal ejection direction;

[0138] a second image acquisition unit comprising a plurality of second cameras arranged on the truss of the bridge construction machine, the second cameras having a shooting direction towards the bridge-cast segment;

[0139] a first image recognition unit configured to recognize an unsprayed area in an image acquired by the second image acquisition unit;

[0140] a first control unit configured to control an initial ejection velocity of one or more nozzles closest to the unsprayed area, so that the water flow ejected by the nozzles sprays the unsprayed area.

[0141] In a more preferred embodiment, when the first control unit needs to adjust the initial ejection velocity of the nozzles, the horizontal distance between the nozzles and the center point of the unsprayed area is first calculated, and then based on the parabolic formula, the theoretical initial velocity of the water flow ejected by the nozzles to reach the center point of the unsprayed area is calculated as the required initial ejection velocity of the nozzles.

[0142] In a more preferred embodiment, the first image recognition unit calculates the center point of the unsprayed area by the following method: outlining the contour line of the unsprayed area, finding the two points farthest away on the contour line, and taking the midpoint of the line connecting the two points farthest away as the center point of the unsprayed area.

[0143] The vibrating control subsystem comprises:

[0144] a vibrating unit comprising a plurality of attached vibrators arranged on the outer wall of the formwork system of the bridge construction machine;

[0145] a height recognition unit configured to recognize the height of the cast concrete;

[0146] a second control unit configured to control the attached vibrators, and when the height of the cast concrete is higher than the height of a certain attached vibrator, the attached vibrator is started;

[0147] a third image acquisition unit comprising a plurality of third cameras arranged above the casting area;

[0148] a second image recognition unit configured to recognize a pit on the surface of the concrete in an image acquired by the third image acquisition unit.

[0149] The third image acquisition unit takes a top image of the poured concrete from top to bottom above the concrete pouring area, and the second image recognition unit recognizes the pits in the image. If there are pits, it means that there are still bubbles to be broken, so the vibrating needs to continue. If there are no new pits within 5 minutes, it is considered that the concrete has been vibrated and compacted, and the vibrating work can be stopped in time.

[0150] More preferably, the artificial sets the minimum vibrating time for the vibrating unit. If there are no new pits within 5 minutes, but the total vibrating time is less than the minimum vibrating time, continue vibrating until the minimum vibrating time is met.

[0151] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application should be included in the protection scope of the present application.

[0152] It should be noted that in this document, relational terms such as first and second and the like can only be used to distinguish one entity or action from another entity or action, and do not necessarily require or imply that there is any such actual relationship or order between these entities or actions. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus including a series of elements includes not only those elements, but also other elements not explicitly listed or inherent to such a process, method, article or apparatus.

Claims

1. An AI technology-based bridge-building machine construction full-cycle information management system, characterized in that, The method comprises the following steps: A bridge-building machine global perception subsystem is used to collect construction parameters during the construction operation of the bridge-building machine; An edge processing subsystem is used to perform edge processing on the construction parameters collected by the bridge-building machine global perception subsystem; A digital twin subsystem is used to establish a digital twin model simulating the entire construction cycle of the bridge-building machine, and to synchronize the edge-processed construction parameters to the digital twin model; A safety monitoring subsystem is used to monitor the safety of the bridge-building machine based on the digital twin model. 2.The AI technology-based bridge construction full-cycle information management system of claim 1, wherein, The bridge-building machine global perception subsystem comprises: Distributed optical fiber stress sensors are arranged inside the poured segment, at the cantilever end, the cantilever root and the cantilever segment joint of the bridge-building machine, and are used to monitor stress changes; Inclinometers and displacement meters are arranged at the cantilever end of the bridge-building machine, and are used to monitor deflection deformation; Acceleration sensors are arranged at the top of the truss of the bridge-building machine, and are used to monitor the acceleration of the truss; Fiber Bragg grating sensors are arranged on the anchorage devices at both ends of each boom of the bridge-building machine, and are used to monitor the internal force of the boom; Wind condition sensors, temperature sensors and humidity sensors are arranged on the top of the bridge-building machine, and are used to monitor the wind speed and direction, the environmental temperature and the air humidity of the working environment, respectively; Vibration sensors are arranged on the walking system, the anchoring system, the truss system, the suspension system and the formwork system of the bridge-building machine, and are used to monitor the vibration data of the bridge-building machine; A first image acquisition unit comprises a plurality of first cameras, and the shooting direction is towards the poured segment and the formwork system of the bridge-building machine. 3.The AI technology-based bridge construction full-cycle information management system of claim 1, wherein, The edge processing subsystem comprises: A data preprocessing module is used to preprocess the collected construction parameters, and the preprocessing includes denoising and removing abnormal values; A feature extraction module is used to extract the characteristic values of the preprocessed construction parameters by using principal component analysis; An edge gateway module is used to transmit the characteristic values of the preprocessed construction parameters to the digital twin subsystem; An edge computing module is used to deploy a lightweight AI model for local early warning in case of stress overrun. 4.The AI technology-based bridge construction machine construction whole-cycle information management system according to claim 1, characterized in that, The method for establishing the digital twin model comprises the following steps: A finite element model of the bridge-building machine is established; Material constitutive relations are determined, load conditions and boundary conditions are set, and grids are divided; Parameterized variables are embedded, and the parameterized variables include the elastic modulus of concrete; The coordinates of each acquisition device in the bridge-building machine global perception subsystem are mapped into corresponding grid nodes. 5.The AI technology-based bridge construction machine construction whole-cycle information management system according to claim 4, characterized in that, The digital twin subsystem comprises: A motion simulation module is used to simulate the movement process of the walking system of the bridge-building machine under any working condition in the digital twin model; A data assimilation module is used to project the edge-processed construction parameters into the digital twin model; A parameterized variable inversion module is used to invert the parameterized variables based on the edge-processed construction parameters; A visualization module is used to render and display the BIM model of the bridge-building machine and the formed region of the bridge. 6.The AI technology-based bridge construction full-cycle information management system of claim 1, wherein, The digital twin subsystem further comprises a creep prediction module for predicting the creep of the concrete in the formed region of the bridge, and the creep prediction module comprises the following prediction model: ； wherein: t0 is the age at which the concrete begins to experience stress; t is the target time for which creep is desired to be predicted; ε(t, t0) is the total creep deformation over the time t - t0; σ is the sustained stress; E is the modulus of elasticity; K is a material constant related to the aggregate type; ψ is the creep rate exponent; C u is the ultimate creep coefficient. 7.The AI technology-based bridge construction machine construction whole-cycle information management system according to claim 1, characterized in that, The safety monitoring subsystem comprises: An overload early warning unit is used to obtain stress data in the digital twin model, identify stress overload areas and give early warnings. A crack prediction unit configured to obtain crack data of the cast segment and the bridge-erecting machine template system in the digital twin model, and predict a crack propagation path based on mechanical simulation; A loosening early warning unit configured to obtain vibration data of the bridge-erecting machine in the digital twin model, and predict the pre-tightening force of each bolt based on the vibration spectrum, identify a loosening bolt, and issue an early warning; An extreme working condition unit configured to apply an extreme construction load to the digital twin model, and determine the operation safety based on the response result under the extreme construction load; A meteorological risk unit configured to obtain local weather forecast data, and predict the overturning resistance of the digital twin model based on the local weather forecast data; A life management unit configured to predict the remaining life of a key component of the bridge-erecting machine based on a fatigue cumulative damage model. 8.The AI technology-based bridge construction machine construction whole-cycle information management system according to claim 7, characterized in that, The meteorological risk unit calculates the overturning resistance by the following formula: ； where: G is the anti-overturning coefficient; W i Wi is the self-weight of the ith stabilizing component; di i Fi is the horizontal distance from the ith stabilizing component to the overturning axis; F is the total horizontal wind load acting on the bridge-erecting machine; h is the height difference between the centroid height of the wind-affected surface and the overturning axis; wherein: ； In the formula, v is the wind speed, A is the projection area of the wind load on the bridge-erecting machine in the most unfavorable direction, and C is the wind load shape coefficient. 9.The AI technology-based bridge construction machine construction whole-cycle information management system according to claim 1, characterized in that, The spraying control subsystem further includes: A spraying unit including a plurality of spray heads arranged on the truss of the bridge-erecting machine, the spray heads facing the cast segment of the bridge and having a horizontal emission direction; A second image acquisition unit including a plurality of second cameras arranged on the truss of the bridge-erecting machine, the second cameras having a shooting direction facing the cast segment of the bridge; A first image recognition unit configured to identify an unsprayed area in the image acquired by the second image acquisition unit; A first control unit configured to control the initial velocity of the emission of one or more spray heads closest to the unsprayed area, so that the water flow is sprayed to the unsprayed area. 10.The AI technology-based bridge construction machine construction whole-cycle information management system of claim 1, wherein, The vibrating control subsystem further includes: A vibrating unit including a plurality of attached vibrators arranged on the outer wall of the template system of the bridge-erecting machine; A height recognition unit configured to recognize the height of the cast concrete; A second control unit configured to control each attached vibrator; when the height of the cast concrete is higher than the height of a certain attached vibrator, the attached vibrator is started; A third image acquisition unit including a plurality of third cameras arranged above the casting area; A second image recognition unit configured to recognize the pits on the surface of the concrete in the image acquired by the third image acquisition unit.

Images