Method and system for monitoring suspended pouring box girder hanging basket state based on image recognition

Abstract

The invention discloses a suspended pouring box girder hanging basket state monitoring method and system based on image recognition, and relates to the field of suspended pouring box girder hanging basket state monitoring. The method comprises the following steps: dynamically acquiring multi-source data such as an identification image, stress data, environment data and external load of a hanging basket, extracting first deformation data based on the identification image, and mapping the stress data and the environment data into second deformation data and third deformation data respectively; performing fusion processing on the deformation data to obtain fused deformation data; estimating deformation interference of the hanging basket based on the fused deformation data and the environment data, and obtaining interference estimation; constructing a dynamic model between the hanging basket deformation quantity and external load and interference estimation; and fitting the dynamic model by using the collected multi-source data, correcting the deformation quantity by using an observation equation and a Kalman filtering algorithm, and carrying out risk early warning according to the corrected hanging basket deformation quantity and a set deformation quantity threshold value.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of suspended box girder hanging basket state monitoring, particularly to a suspended box girder hanging basket state monitoring method and system based on image recognition. BACKGROUND

[0002] The hanging basket, as an important construction equipment, is widely used in the construction process of suspended box girder in bridge construction. The deformation monitoring of the hanging basket is crucial for ensuring construction safety and engineering quality. Traditional hanging basket deformation monitoring methods mainly rely on single sensors (such as strain sensors, displacement sensors) or simple image recognition technology.

[0003] Although the above methods can provide deformation information to some extent, they have many limitations in complex construction environments. Single sensors, such as strain sensors, can accurately measure local strain, but cannot fully reflect the overall deformation of the hanging basket; displacement sensors can measure the displacement of key points, but cannot provide detailed deformation information and have limited measurement range; traditional methods usually cannot effectively consider the influence of environmental factors (such as wind speed, temperature changes) on the deformation of the hanging basket, resulting in inaccurate monitoring results. With the development of intelligent monitoring technology, image recognition technology can be used to realize real-time monitoring of the deformation of the hanging basket, but it is easily affected by factors such as lighting conditions and background interference, and the fusion of image recognition data and other sensor data in existing technology is not perfect, which cannot fully utilize the advantages of multi-source data. Therefore, we propose a suspended box girder hanging basket state monitoring method and system based on image recognition. SUMMARY

[0004] The main purpose of the present application is to provide a suspended box girder hanging basket state monitoring method and system based on image recognition, which can more comprehensively and accurately monitor the deformation of the hanging basket by fusing multiple sensor data, including image data, strain data and environmental data, and combining deformation interference estimation, thereby realizing precise monitoring of the running state of the hanging basket and effectively solving the problems in the background technology.

[0005] To achieve the above purpose, the technical scheme adopted by the present application is,

[0006] The suspended box girder hanging basket state monitoring method based on image recognition comprises the following steps:

[0007] a) dynamically collecting the recognition image of the hanging basket, stress data μ(t), environmental data ν(t) and external load F ext (t);

[0008] b) extracting first deformation data δ image (t) based on the recognition image, mapping the stress data μ(t) and the environmental data ν(t) into second deformation data δsensor (t) and third deformation data δ env (t);

[0009] c) performing fusion processing on the first deformation data δ image (t), the second deformation data δ sensor (t) and the third deformation data δ env (t) to obtain fused deformation data δ fused (t);

[0010] d) estimating deformation interference of the hanging basket based on the fused deformation data δ fused (t) and the environmental data v(t) to obtain interference estimation

[0011] e) constructing a dynamic model between the deformation variable of the hanging basket and the external load F ext (t) and the interference estimation

[0012] f) fitting the dynamic model using the collected multi-source data, and calculating the deformation variable δ(t) of the hanging basket through the fitted dynamic model.

[0013] g) correcting the deformation variable δ(t) using an observation equation and a Kalman filtering algorithm to obtain a corrected deformation variable δ corrected (t) of the hanging basket.

[0014] h) setting deformation variable thresholds of the hanging basket as δ safe1 , δ safe2 and δ safe3 , and δ safe1 < δ safe2 < δ safe3 , and performing risk warning according to the corrected deformation variable δ corrected (t) of the hanging basket and the set deformation variable thresholds.

[0015] The image recognition-based state monitoring method and system of the cantilever casting basket beam include:

[0016] An image acquisition module is configured to dynamically acquire identification images of the hanging basket.

[0017] A stress data acquisition module is configured to dynamically acquire stress data μ(t) of the hanging basket.

[0018] An environmental data acquisition module is configured to dynamically acquire environmental data v(t) of an environment in which the hanging basket is located.

[0019] A load data acquisition module is configured to dynamically acquire an external load F ext (t) of the hanging basket.

[0020] ​a first deformation data acquisition module configured to extract first deformation data δ image (t) based on the identification image;

[0021] a second deformation data acquisition module configured to map the stress data μ(t) to second deformation data δ sensor (t);

[0022] a third deformation data acquisition module configured to map the environmental data v(t) to third deformation data δ env (t);

[0023] a data fusion module configured to fuse the first deformation data δ image (t), the second deformation data δ sensor (t), and the third deformation data δ env (t) to obtain fused deformation data δ fused (t);

[0024] an interference estimation module configured to estimate deformation interference of the hanging basket based on the fused deformation data δ fused (t) and the environmental data v(t) to obtain interference estimation

[0025] a model construction module configured to construct a dynamic model between deformation variables of the hanging basket and the external load F ext (t) and the interference estimation ;

[0026] a data fitting module configured to fit the dynamic model with the collected multi-source data, and to calculate deformation variables δ(t) of the hanging basket through the fitted dynamic model;

[0027] a data correction module configured to correct the deformation variables δ(t) using an observation equation and a Kalman filtering algorithm to obtain corrected deformation variables δ corrected (t) of the hanging basket;

[0028] a risk warning module configured to set deformation variable thresholds of the hanging basket as δ safe1 , δ safe2 , and δ safe3 , and δ safe1 < δ safe2 < δ safe3 , and to perform risk warning according to the corrected deformation variables δ corrected (t) of the hanging basket and the set deformation variable thresholds.

[0029] Further, in step a), the environmental data includes one or more combinations of wind speed, temperature, and humidity; and the external load includes one or more combinations of construction load, self-weight load, environmental load, and dynamic load.

[0030] Further, in step b), the second deformation data δ

[0031] The second deformation data δ sensor The acquisition method of the third deformation data δ

[0032] The second deformation data δ env The acquisition method of the third deformation data δ env (t) = k · v(t)

[0033] In the formula, L is the structural length of the stress data collection point; E is the elastic modulus of the stress data collection point material; k is a proportional coefficient, representing the sensitivity of the environmental data to the deformation variable.

[0034] Further, in step c), the fused deformation data δ fused The calculation method of the fused deformation data δ

[0035] The calculation method of the fused deformation data δ fused (t) = α · δ image (t) + β · δ sensor (t) + γ · δ env (t)

[0036] In the formula, α, β, and γ are constant coefficients between 0 and 1, and α + β + γ = 1.

[0037] Further, in step d), the expression of the dynamic model is:

[0038]

[0039] In the formula, M is the mass matrix of the hanging basket; N is the damping matrix of the hanging basket; K is the stiffness matrix of the hanging basket; δ''(t) is the second derivative of the deformation variable δ(t); δ'(t) is the first derivative of the deformation variable δ(t).

[0040] The physical meaning of the dynamic model is as follows:

[0041] M · δ''(t): represents the inertial force of the hanging basket system, that is, the inertial effect caused by the mass M of the hanging basket. When the hanging basket deforms, its mass will resist the change of this deformation, generating an inertial force.

[0042] N · δ'(t): represents the damping force, that is, the force generated due to the internal damping characteristics of the hanging basket system (such as the internal damping of the material, air resistance, etc.). The damping force is proportional to the deformation velocity and plays a role in slowing down the deformation change.

[0043] K*delta(t): represents the elastic restoring force, which is the force generated due to the elastic properties of the hanging basket (such as the modulus of elasticity of the material). The elastic restoring force is proportional to the deformation and attempts to restore the hanging basket to its original state.

[0044] F ext (t): represents external forces such as construction loads, wind loads, etc., which will cause the hanging basket to deform.

[0045] represents multi-source interference, including known and unknown interference, which will also affect the deformation of the hanging basket.

[0046] delta(t): is the deformation variable, which describes the deformation state of the hanging basket.

[0047] delta'(t): is the first-order time derivative of the deformation variable, which describes the speed of deformation.

[0048] delta''(t): is the second-order time derivative of the deformation variable, which describes the acceleration of deformation.

[0049] Further, the expression of the observation equation is: delta fused (t) = delta(t) + epsilon(t); where epsilon(t) is the observation noise, representing the difference between the fused deformation data delta fused (t) and the true deformation variable.

[0050] Further, the specific steps for correcting the deformation variable delta(t) using the observation equation and Kalman filtering algorithm are:

[0051] delta corrected (t) = delta(t) + K(t) * [delta fused (t) - delta(t)]

[0052] where K(t) is the Kalman gain.

[0053] Further, the risk warning principle is:

[0054] When delta corrected (t) < delta safe1 , it is determined that the hanging basket is safe and no warning is given.

[0055] When delta safe1 <= delta corrected (t) < delta safe2 , it is determined that the hanging basket has a low risk and a first-level warning is given.

[0056] When delta safe2 <= delta corrected (t) < delta safe3 , it is determined that the hanging basket has a medium risk and a second-level warning is given.

[0057] When delta corrected (t) >= delta safe3 When delta

[0058] The present application has the following advantages,

[0059] Compared with the prior art, the present application fully utilizes the advantages of different data sources by fusing multiple sensor data, effectively reduces the error and limitation of single sensor data, and significantly improves the precision of the hanging basket deformation variable monitoring.

[0060] Compared with the prior art, the present application can effectively improve the anti-interference ability of the monitoring system in complex construction environment by estimating multi-source interference, and ensure the accuracy and reliability of the monitoring results.

[0061] Compared with the prior art, the present application can realize real-time dynamic monitoring of the hanging basket deformation variable based on dynamic model and numerical solution method, and timely reflect the deformation state of the hanging basket, which provides a strong guarantee for construction safety.

[0062] Compared with the prior art, the present application considers the influence of environmental factors on the deformation of the hanging basket and incorporates it into the monitoring model, so that the monitoring system can maintain good performance under different environmental conditions and enhance the environmental adaptability of the system.

[0063] Compared with the prior art, the present application can effectively reduce the safety risk in the construction process by monitoring the deformation variable of the hanging basket in real time and issuing early warning signals in time, and providing enough time for the construction personnel to take measures, thereby protecting the life safety of the construction personnel and the engineering quality.

[0064] Compared with the prior art, the present application provides real-time and accurate deformation information of the hanging basket for construction management personnel, which helps to better master the construction progress and quality, optimize the construction scheme and resource allocation, and improve the construction efficiency and management level. BRIEF DESCRIPTION OF DRAWINGS

[0065] Figure 1 The present application is based on image recognition and the overall structure of the hanging basket state monitoring method and system of the suspended pouring box girder is shown in the figure.

[0066] Figure 2 The structure of the present application based on image recognition and the structure of the suspended pouring box girder hanging basket state monitoring system is shown in the figure. DETAILED DESCRIPTION

[0067] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0068] The specific implementation process of the technical solution of the present application includes the following steps:

[0069] a) dynamically collecting the identification image of the hanging basket, stress data μ(t), environmental data v(t) and external load F ext (t);

[0070] The environmental data includes one or a combination of more of wind speed, temperature and humidity;

[0071] The external load includes:

[0072] Construction load: including concrete pouring load, weight of construction personnel and equipment, etc.

[0073] Dead load: the weight of the hanging basket itself and other structural components on the hanging basket.

[0074] Environmental load: such as wind load, thermal expansion and contraction caused by temperature change, etc.

[0075] Dynamic load: such as vibration and impact during construction process, etc.

[0076] External load determination method:

[0077] Construction load: including concrete pouring load F concrete and weight load of construction personnel and equipment F personnel ;

[0078] Calculation method: calculate the load according to the pouring volume and density of concrete. For example, the density of concrete is about 2400 kg / m 3 , and the pouring volume V can be obtained from the construction design drawings.

[0079] Formula: F concrete = ρ concrete · V· g; wherein, ρ concrete is the density of concrete, V is the pouring volume, and g is the acceleration of gravity.

[0080] Measurement method: during the concrete pouring process, the weight of concrete can be measured in real time by a weighing sensor.

[0081] Weight load of construction personnel and equipment F personnel :

[0082] Calculation method: estimate according to the weight of construction personnel and equipment.

[0083] Formula: Where N is the number of workers and equipment, m i is the weight of the ith worker or equipment.

[0084] Dead load F self

[0085] Calculation method: According to the structural design drawings of the hanging basket, calculate the weight of the hanging basket and its attached structures.

[0086] Formula: F self = m self ·g; Where m self is the total weight of the hanging basket and its attached structures.

[0087] Environmental load (take wind load F wind as an example)

[0088] Wind load F wind :

[0089] Calculation method: Calculate the wind load according to the wind speed and the windward area of the hanging basket.

[0090] The wind load formula is: F wind = 0.5ρ air ·A·v 2 ·C d ; Where ρ air is the air density (about 1.225 kg / m 3 ), A is the windward area of the hanging basket, v is the wind speed, C d is the drag coefficient (usually take about 1.2).

[0091] Measurement method: Real-time measurement of wind speed by wind speed sensor.

[0092] Thermal expansion and contraction caused by temperature change F thermal :

[0093] Calculation method: Calculate the force caused by deformation according to the thermal expansion coefficient of the material and temperature change.

[0094] The formula is: F thermal = E·A·a·ΔT

[0095] Where E is the elastic modulus of the material, A is the cross-sectional area, α is the thermal expansion coefficient, and ΔT is the temperature change.

[0096] Measurement method: Real-time measurement of temperature change by temperature sensor.

[0097] Dynamic load F dynamic

[0098] Calculation method: Dynamic load is usually difficult to calculate accurately, which can be estimated by vibration analysis or empirical formula.

[0099] Measurement method: Dynamic load is measured in real time by acceleration sensor or vibration sensor.

[0100] By adding the above various loads, the external load F ext (t) is obtained.

[0101] F ext (t) = F concrete + F personnel + F self + F wind + F thermal + F dynamic .

[0102] b) Based on the identified image, the first deformation data δ image (t) is extracted, and the stress data μ(t) and the environmental data ν(t) are mapped into the second deformation data δ sensor (t) and the third deformation data δ env (t), respectively.

[0103] Through image recognition technology, the geometric features of the hanging basket are extracted from the image, such as the bending degree of the main truss, the displacement of the node, etc., and these geometric features are converted into deformation data. For example, by calculating the bending angle of the main truss or the displacement of the node, the first deformation data δ image (t) is obtained.

[0104] There is a physical relationship between strain and deformation. For example, through the elastic modulus of the material and the cross-sectional geometric parameters, the strain can be converted into displacement or deformation amount, so the second deformation data δ sensor (t) can be obtained by:

[0105] Environmental data (such as wind speed, temperature) may indirectly affect the deformation of the hanging basket. For example, wind speed may cause the hanging basket to vibrate, and temperature change may cause the material to expand and contract with heat. By establishing a relationship model between environmental factors and deformation, the third deformation data δ env (t) can be obtained, specifically: δ env (t) = k·ν(t);

[0106] In the formula, L is the structural length of the stress data collection point; E is the elastic modulus of the material of the stress data collection point; k is the proportional coefficient, which represents the sensitivity of the environmental data to the deformation.

[0107] c) The first deformation data δ image (t), the second deformation data δ sensor (t) and the third deformation data δenv (t) is obtained by fusing the deformation data δ fused (t);

[0108] The fusion deformation data δ fused (t) is calculated by:

[0109] δ fused (t) = α·δ image (t) + β·δ sensor (t) + γ·δ env (t)

[0110] wherein α, β and γ are constant coefficients between 0 and 1, and α + β + γ = 1.

[0111] d) estimating the deformation interference of the hanging basket based on the fusion deformation data δ fused (t) and the environmental data v(t), to obtain an interference estimate

[0112] Specifically, the interference estimate can be divided into known interference and unknown interference wherein

[0113] The known interference such as environmental temperature changes, wind loads, etc., which can be measured by sensors.

[0114] Specifically, in the present embodiment, several calculation methods of the known interference under different environmental factors are given:

[0115] When only wind speed interference exists, the known interference wherein ρ is air density, C d is the drag coefficient (wind tunnel experiment calibration) ;

[0116] When only temperature interference exists, the known interference wherein E is the elastic modulus, r is the linear expansion coefficient (material manual), and ΔT(t) is the temperature change;

[0117] When only solar radiation interference exists, the known interference wherein I is the sectional moment of inertia, and h is the elevation;

[0118] When wind speed interference and temperature interference exist simultaneously, the known interference

[0119] When wind speed interference and solar radiation interference exist simultaneously, the known interference

[0120] When temperature disturbance and solar radiation disturbance exist simultaneously, the known disturbance is

[0121] When wind speed disturbance, temperature disturbance and solar radiation disturbance exist simultaneously, the known disturbance is

[0122] Unknown disturbance For example, random vibration during construction process, equipment operation noise, etc. These disturbances are usually difficult to measure accurately, but can be assumed to be bounded, i.e. satisfying where D is the disturbance upper bound, which can be determined empirically in the specific implementation process.

[0123] e) Constructing the dynamic model between the hanging basket deformation variable δ(t) and the external load F ext (t) and disturbance estimation ;

[0124] The expression of the dynamic model is:

[0125]

[0126] where M is the mass matrix of the hanging basket; N is the damping matrix of the hanging basket; K is the stiffness matrix of the hanging basket; δ”(t) is the second derivative of the deformation variable δ(t); δ'(t) is the first derivative of the deformation variable δ(t).

[0127] It should be noted that the physical meaning of the dynamic model is as follows:

[0128] M·δ”(t): represents the inertial force of the hanging basket system, i.e. the inertial effect due to the mass M of the hanging basket. When the hanging basket deforms, its mass will resist the change of this deformation, producing an inertial force.

[0129] N·δ'(t): represents the damping force, i.e. the force due to the internal damping characteristics of the hanging basket system (such as material internal damping, air resistance, etc.). The damping force is proportional to the deformation velocity, and plays a role in slowing down the deformation change.

[0130] K·δ(t): represents the elastic restoring force, i.e. the force due to the elastic properties of the hanging basket (such as the modulus of elasticity of the material). The elastic restoring force is proportional to the deformation variable, trying to restore the hanging basket to its original state.

[0131] F ext (t): represents external forces such as construction loads, wind loads, etc. These forces will cause the hanging basket to deform.

[0132] represents multi-source disturbance, including known and unknown disturbances, which will also affect the deformation of the hanging basket.

[0133] δ(t): is the shape variable, describing the deformation state of the form traveler.

[0134] δ'(t): is the first order time derivative of the shape variable, describing the velocity of the deformation.

[0135] δ''(t): is the second order time derivative of the shape variable, describing the acceleration of the deformation.

[0136] These variables collectively describe the dynamic behavior of the form traveler under external forces and disturbances.

[0137] The procedure for determining the mass matrix M, damping matrix N, and stiffness matrix K of the form traveler system can be obtained by the following steps:

[0138] Finite element modeling → parameter acquisition → matrix assembly → experimental calibration

[0139] The specific method is as follows:

[0140] Determination of the mass matrix M: first calculate the "element mass matrix", and then assemble it into the "overall mass matrix".

[0141] Element mass matrix

[0142] Use the consistent mass formula to discretize the main truss, base mold, side mold, and sling of the form traveler into beam, plate, and rod elements;

[0143] Assemble the overall mass matrix

[0144] According to the correspondence of node degrees of freedom, superimpose all the element mass matrices to obtain the mass matrix M.

[0145] The determination method of the stiffness matrix K is the same as above.

[0146] Determination of the damping matrix N: damping is difficult to "directly assemble" like mass and stiffness, and three engineering approximations are commonly used, specifically Rayleigh damping, complex modal damping, and experimental identification method (use impact or environmental vibration test to measure frequency response function, and use optimization algorithm to invert);

[0147] Boundary conditions and load correction

[0148] Support constraints: delete or modify the corresponding degrees of freedom in K;

[0149] Additional mass: the wet weight of concrete, construction tools, etc. are added to M as concentrated mass;

[0150] Additional stiffness: the contact surface between the formwork and the concrete, the elastic effect of the sling is converted into an equivalent spring in parallel to K.

[0151] Calibration and verification

[0152] After the finite element model is completed, the first 3-5 order natural frequencies and damping ratios are measured through field modal test (hammering or environmental excitation), and compared with the calculation results, the parameters are fine-tuned in reverse, so that the error is less than 5%, and finally the mass matrix M, the damping matrix N and the stiffness matrix K are determined.

[0153] f) fitting the dynamic model using the collected multi-source data, and calculating the deformation amount δ(t) of the hanging basket through the fitted dynamic model.

[0154] g) correcting the deformation amount δ(t) using the observation equation and Kalman filtering algorithm to obtain the corrected hanging basket deformation amount δ corrected (t).

[0155] The expression of the observation equation is: δ fused (t) = δ(t) + ε(t); wherein ε(t) is the observation noise.

[0156] The specific steps for correcting the deformation amount δ(t) using the Kalman filtering algorithm are as follows:

[0157] δ corrected (t) = δ(t) + K(t) × [δ fused (t) - δ(t)]

[0158] In the formula, K(t) is the Kalman gain.

[0159] It should be noted that the observation noise ε(t) represents the difference between the fused deformation data δ fused (t) and the true deformation amount, which can be determined by the following method:

[0160] Method 1:

[0161] Statistical analysis: statistical analysis is performed on the measurement data to calculate the mean and variance. It is assumed that the observation noise is zero-mean Gaussian noise, i.e.: ∈(t) ~ N(0, σ 2 ); wherein σ 2 is the variance of the observation noise, which can be estimated by experimental data or historical data.

[0162] Method 2:

[0163] Model error analysis: analyze the errors of the data conversion model and the environmental influence model, which will directly affect the size of the observation noise. For example, if the image recognition algorithm has low accuracy, or the environmental influence model is not accurate enough, the observation noise will increase accordingly.

[0164] h) set the deformation threshold of the hanging basket as δ safe1 , δ safe2 and δ safe3 , and δ safe1 < δ safe2< delta safe3 , according to the corrected hanging basket deformation variable delta corrected (t) and the set deformation variable threshold value, the risk early warning principle is:

[0165] When delta corrected (t) < delta safe1 , it is determined that the hanging basket state is safe, and no early warning is performed.

[0166] When delta safe1 <= delta corrected (t) < delta safe2 , it is determined that the hanging basket state has low risk, and first-level early warning is performed.

[0167] When delta safe2 <= delta corrected (t) < delta safe3 , it is determined that the hanging basket state has medium risk, and second-level early warning is performed.

[0168] When delta corrected (t) >= delta safe3 , it is determined that the hanging basket state has high risk, and third-level early warning is performed.

[0169] The above shows and describes the basic principles and main features of the present application and the advantages of the present application. Those skilled in the art should understand that the present application is not limited by the above examples, and the above examples and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring the state of a hanging basket for a cast-in-place box girder based on image recognition, characterized in that, The method comprises the following steps: a) dynamically collecting the identification image of the hanging basket, stress data μ(t), environmental data v(t) and external load F ext (t); b) extracting first morphing data δ based on the identification image image (t), mapping the stress data μ(t) and the environmental data v(t) into second morphing data δ sensor (t) and third morphing data δ env (t), respectively; c) fusing the first deformation data δ image (t), the second deformation data δ sensor (t) and the third deformation data δ env (t) to obtain fused deformation data δ fused (t). d) based on said fusion deformation data δ fused (t) and said environmental data v(t) estimate the deformation disturbance of the hanging basket, obtaining a disturbance estimate e) constructing a dynamic model of the hanging basket shape variable and the external load F ext (t) and the disturbance estimate between the (t) and the disturbance estimate f) fitting the dynamic model with the collected multi-source data, and calculating the deformation δ(t) of the hanging basket through the fitted dynamic model.

2. The image recognition-based state monitoring method and system for the hanging basket of the cast-in-place box girder, according to claim 1, characterized in that, In step a), the environmental data comprises one or more combinations of wind speed, temperature and humidity; and the external load comprises one or more combinations of construction load, dead load, environmental load and dynamic load. 3.The image recognition based state monitoring method of the hanging basket of the cast-in-place box girder according to claim 1, characterized in that, In step b), The second deformation data δ sensor The acquisition method of (t) is: The third deformation data δ env The acquisition method of (t) is: δ env (t) = k · v(t) wherein L is the structural length of the stress data collection point; E is the elastic modulus of the material of the stress data collection point; and k is a proportional coefficient representing the sensitivity of the environmental data to the deformation.

4. The image recognition-based state monitoring method of the hanging basket of a cast-in-place box girder according to claim 1 or 3, characterized in that, In step c) the fusion deformation data δ fused The calculation method of (t) is: δ fused (t) = a - δ image (t) + β - δ sensor (t) + γ - δ env (t) wherein α, β and γ are constant coefficients between 0 and 1, and α+β+γ=1.

5. The image recognition-based state monitoring method of the hanging pouring box girder basket according to claim 1, characterized in that, In step d), the expression of the dynamic model is: wherein M is the mass matrix of the hanging basket; N is the damping matrix of the hanging basket; K is the stiffness matrix of the hanging basket; δ''(t) is the second derivative of the deformation δ(t); and δ'(t) is the first derivative of the deformation δ(t).

6. The image recognition-based state monitoring method of the hanging box girder basket according to claim 5, characterized in that, Further comprising: g) using an observation equation and a Kalman filter algorithm to correct the deformation variable δ(t) to obtain a corrected hanging basket deformation variable δ corrected (t).

7. The image recognition-based state monitoring method of the hanging box girder basket according to claim 6, characterized in that, The expression of the observation equation is: δ fused (t) = δ(t) + ε(t); where ε(t) is the observation noise, representing the difference between the fused deformation data δ fused (t) and the true deformation variable. 8.The image recognition based state monitoring method of the hanging basket of the cast-in-place box girder according to claim 7, characterized in that, The specific steps of correcting the deformation δ(t) by using the observation equation and the Kalman filtering algorithm are: delta corrected (t) = delta(t) + K(t) x [delta fused (t) - delta(t)] wherein K(t) is the Kalman gain. 9.The image recognition based state monitoring method of the hanging basket of the cast-in-place box girder according to claim 8, characterized in that, Further comprising: h) setting the deformation threshold of the hanging basket as δ safe1 , δ safe2 , and δ safe3 , and δ safe1 < δ safe2 < δ safe3 , according to the corrected hanging basket deformation δ corrected (t) and the set deformation threshold, a risk warning is carried out, and the risk warning principle is: When δ corrected (t) < δ safe1 , the hanging basket state is determined to be safe, and no pre-warning is performed. When δ safe1 ≤ δ corrected (t) < δ safe2 , it is determined that the hanging basket state has low risk, and a first-level early warning is performed. When δ safe2 ≤ δ corrected (t) < δ safe3 , it is determined that the hanging basket state has a medium risk, and a secondary warning is given. When δ corrected (t)≥δ safe3 , it is determined that the hanging basket state has high risk, and a three-level warning is performed.

10. A system for full image recognition based state monitoring of a form traveler of a cast-in-place box girder according to any one of claims 1 to 9, characterized in that comprising: an image collection module for dynamically collecting the identification image of the hanging basket; a stress data collection module for dynamically collecting the stress data μ(t) of the hanging basket; an environmental data collection module for dynamically collecting the environmental data v(t) of the environment where the hanging basket is located; The load data acquisition module is used for dynamically collecting the external load F of the hanging basket ext (t); a first deformation data acquisition module configured to extract first deformation data δ based on the identification image image (t); a second deformation data acquisition module, configured to map the stress data μ(t) into second deformation data δ sensor (t); a third deformation data acquisition module, configured to map the environmental data v(t) into third deformation data δ env (t); a data fusion module configured to fuse the first deformation data δ image (t), the second deformation data δ sensor (t) and the third deformation data δ env (t) to obtain fused deformation data δ fused (t). an interference estimation module configured to estimate the deformation interference of the hanging basket based on the fused deformation data δ fused (t) and the environmental data v(t) to obtain an interference estimate a model construction module, configured to construct a dynamic model between a hanging basket deformation variable and the external load F ext (t) and the interference estimate (t) and the interference estimate a data fitting module for fitting the dynamic model with the collected multi-source data, and calculating the deformation δ(t) of the hanging basket through the fitted dynamic model; and an image collection module for dynamically collecting the identification image of the hanging basket; a stress data collection module for dynamically collecting the stress data μ(t) of the hanging basket; an environmental data collection module for dynamically collecting the environmental data v(t) of the environment where the hanging basket is located; a data fitting module for fitting the dynamic model with the collected multi-source data, and calculating the deformation δ(t) of the hanging basket through the fitted dynamic model; and A data correction module is configured to correct the deformation variable δ(t) by using an observation equation and a Kalman filtering algorithm, and obtain a corrected hanging basket deformation variable δ corrected (t). The risk warning module is configured to set the deformation threshold of the hanging basket as δ safe1 , δ safe2 , and δ safe3 , and δ safe1 < δ safe2 < δ safe3 , and perform risk warning according to the corrected hanging basket deformation δ corrected (t) and the set deformation threshold.

Images