Shear wall external scaffold monitoring method and system based on intelligent algorithm

Abstract

The invention belongs to the technical field of constructional engineering, and particularly discloses a shear wall external scaffold monitoring method and system based on an intelligent algorithm. Comprising the steps that a monitoring system is built, monitoring data of the shear wall external scaffold are collected according to the monitoring system, and a sample data set is built based on the monitoring data; the sample data set is input into an SD-MOP model, and the accident occurrence probability in the scaffold service process is calculated; on the basis of the accident occurrence probability component constraint condition, taking the constraint condition as a target function of a least square support vector machine model, taking key influence parameters of the strength and the stability of the scaffold as input variables, and performing optimization training on the least square support vector machine model to obtain an accident occurrence probability component; and obtaining an optimal prediction model for monitoring the strength and stability of the scaffold. The safety and reliability of the scaffold are remarkably improved, construction accidents are reduced, and the life safety of workers and smooth proceeding of engineering are protected.

Description

Technical Field

[0001] The present invention belongs to the technical field of construction engineering, and more specifically, relates to a shear wall external scaffolding monitoring method and system based on intelligent algorithm. Background Art

[0002] In the field of construction, shear wall external scaffolding is a key temporary structure to ensure construction safety and efficiency. However, due to the complex influence of environmental factors, material aging, construction loads and other factors, the stability and safety of scaffolding face severe challenges. Traditional scaffolding monitoring methods mainly rely on manual inspection and empirical judgment. These methods have problems such as low monitoring efficiency, poor accuracy, and lack of real-time performance, which are difficult to meet the high standards of safety and economy of modern construction projects.

[0003] With the development of intelligent algorithms and sensor technology, monitoring methods based on intelligent algorithms have gradually become a hot topic of research. These methods evaluate and predict the stability and safety of scaffolding by collecting multi-dimensional data of scaffolding and using advanced data processing technology. However, existing intelligent monitoring methods still face some challenges in practical applications:

[0004] Comprehensiveness of data collection: Traditional monitoring systems often only focus on some parameters, such as displacement or load, while ignoring the comprehensive impact of environmental factors on scaffolding stability. Model accuracy and real-time performance: Existing models often lack sufficient accuracy and real-time performance when predicting the probability of scaffolding accidents, and cannot respond to changes in the scaffolding status in a timely manner. Parameter optimization and weight allocation: In multi-objective optimization, how to reasonably allocate the weights of cost, safety and environmental impact is a technical challenge. Identification of key influencing parameters: Among the many influencing factors, how to accurately identify the key parameters that have the greatest impact on scaffolding stability and safety is crucial to improving monitoring efficiency and prediction accuracy.

[0005] In addition, during the construction of the underground box, there will be a situation where the external wall ground-type steel pipe scaffolding cannot be connected to the wall parts through the pre-buried steel pipes. For the construction of such external frame wall parts at the shear wall, pre-buried short steel pipes are generally used to connect the wall parts. However, pre-buried short steel pipes on the external wall will cause leakage of the external wall. Generally, the verticality of the scaffolding is monitored by a total station, which is a waste of labor. Summary of the invention

[0006] In view of the above defects or improvement needs of the prior art, the present invention provides a shear wall external scaffolding monitoring method based on an intelligent algorithm. The method comprehensively considers the scaffolding use environment data, structural data, material data, displacement data and load data, uses the SD-MOP model to calculate the probability of accidents, and combines the least squares support vector machine model and the decision tree model to optimize the training and prediction of the strength and stability of the scaffolding. In addition, the method also innovatively introduces a method for determining the weight coefficient, and scientifically allocates the weights of different targets through the entropy weight method and centrality analysis, thereby improving the intelligence level and prediction accuracy of the monitoring system. Through these technical means, this patent aims to provide a more comprehensive, accurate and real-time scaffolding monitoring solution to meet the safety and economy requirements of modern construction projects.

[0007] To achieve the above object, according to one aspect of the present invention, a shear wall external scaffolding monitoring method based on an intelligent algorithm is proposed, comprising the following steps:

[0008] Step 1: Build a monitoring system, collect monitoring data of the shear wall external scaffolding according to the monitoring system, and construct a sample data set based on the monitoring data;

[0009] Step 2: Input the sample data set into the SD-MOP model to calculate the probability of accidents occurring during the service of the scaffolding;

[0010] Step three, based on the accident probability component constraint condition, and taking the constraint condition as the objective function of the least squares support vector machine model, taking the key influencing parameters of the strength and stability of the scaffolding as input variables, the least squares support vector machine model is optimized and trained to obtain the optimal prediction model for monitoring the strength and stability of the scaffolding.

[0011] As further preferred, in step 1, the monitoring data includes:

[0012] Scaffolding use environment data, scaffolding structure data, scaffolding material data, scaffolding displacement data and scaffolding load data;

[0013] Wherein, the environmental data includes: wind speed, temperature, humidity;

[0014] The material data include: mechanical property parameters of scaffolding materials;

[0015] The scaffolding displacement data includes: inclination data, horizontal displacement and vertical displacement data, and settlement data;

[0016] The scaffolding load data includes: pressure data and axial force data.

[0017] As further preferred, in step 2, the SD-MOP model includes:

[0018] P acc =f(T, W, H, L, E, σ y ,θ,Δx,Δy,S,P,F)

[0019] F 目 =min(w1·C+w2·P acc +w3·E)

[0020] g(E,σ y , P, F)≤0

[0021] Where T is temperature, W is wind speed, H is humidity, L is scaffold length, E is elastic modulus, σy is yield strength, θ is inclination angle, Δx is horizontal displacement, Δy is vertical displacement, S is settlement, P is pressure, F is axial force, C is cost, Pacc is accident probability, E is environmental impact, and w1, w2, and w3 are weight coefficients.

[0022] As a further preferred method, the weight coefficient is determined by the following method:

[0023] (201) constructing an influencing factor set C = {Cj, j = 1, 2, ..., n} according to the monitoring data, where each Cj represents an influencing factor;

[0024] (202) Through expert scoring or data analysis, the judgment matrix R = (rij)m×n between the influencing factors is obtained, where rij represents the degree of influence of factor i on factor j;

[0025] (203) The judgment matrix R is normalized to obtain the normalized matrix B = (b ij ) m×n ,in,

[0026] (204) The entropy value Hj is calculated according to the normalized matrix B, and the formula is:

[0027]

[0028] in, When fij=0, ln f ij →0;

[0029] (205) Calculate the entropy weight kj of each influencing factor, the formula is:

[0030]

[0031] (206) Construct the direct impact average relationship matrix:

[0032] A=(a ij ) n×n

[0033] Among them, aij represents the influence of factor i on factor j;

[0034] (207) The direct impact average relationship matrix A is standardized to obtain the standardized direct impact matrix N = (n ij ) n×n And the comprehensive influence matrix T = (t ij ) n×n :

[0035] N=lim k→∞ (N 1 +N 2 +...+N k )=N(IN) -1

[0036] Where I is the identity matrix;

[0037] (208) Calculate influence, influence and centrality:

[0038] According to the comprehensive influence matrix T, the influence degree fi, the influence degree ei, the centrality degree ri and the cause degree zi of each influencing factor are calculated. The formula is:

[0039]

[0040] r i =f i +e i

[0041] z i =f i -e i

[0042] (209) Calculate the weight coefficient:

[0043] The weight coefficients w1, w2, w3 are calculated based on the centrality ri. The formula is:

[0044]

[0045] As a further preferred embodiment, in step 3, a decision tree model is used to analyze key influencing parameters of the strength and stability of the scaffold, specifically including:

[0046] (301) normalizing the monitoring data;

[0047] (302) Construct a decision tree model:

[0048]

[0049] Where D is the data set, A is the attribute, Dv is the data subset when the value of attribute A is v, |y| is the number of categories, and pk is the probability of the kth category;

[0050] (303) In the process of building a decision tree, if a node meets the pre-pruning condition, the splitting is stopped and the key influencing parameters are obtained.

[0051] As a further preferred embodiment, step three further includes: using the key influencing parameters identified by the decision tree as input variables of the LSSVM model and the accident probability Pacc as a constraint condition to construct an LSSVM model training model:

[0052]

[0053] Where: w is the weight vector, b is the bias term, ε i is the error term of the ith sample, C is the regularization parameter, φ(·) is the kernel function mapping, i = 1, …, N, N is the number of samples, yi is the actual output of the ith sample, and λ is the weight parameter of the accident probability, which is used to balance the impact of the accident probability in the optimization objective.

[0054] As a further preferred embodiment, in step 3, the Gaussian kernel function expression of the LSSVM model is as follows:

[0055]

[0056] Among them, x is the input variable, x i is the i-th sample, x j is the jth sample, σ 2 is the kernel width parameter.

[0057] As a further preferred embodiment, in step 3, a particle swarm optimization algorithm is used to optimize the parameters of the LSSVM model, wherein the update formula of the particle swarm optimization algorithm includes:

[0058]

[0059] In the formula, is the velocity of particle i at time t, is the position of particle i at time t, z is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers between [0,1], is the individual optimal position of particle i, is the optimal position of the group.

[0060] According to another aspect of the present invention, there is also provided a shear wall external scaffolding monitoring system based on an intelligent algorithm, comprising:

[0061] The first main control module is used to build a monitoring system, collect monitoring data of the shear wall external scaffolding according to the monitoring system, and construct a sample data set based on the monitoring data;

[0062] The second main control module is used to input the sample data set into the SD-MOP model to calculate the probability of accidents occurring during the service of the scaffolding;

[0063] The third main control module is used to optimize the least squares support vector machine model based on the accident probability component constraint condition, and use the constraint condition as the objective function of the least squares support vector machine model, and use the key influencing parameters of the strength and stability of the scaffolding as input variables to obtain the optimal prediction model for monitoring the strength and stability of the scaffolding.

[0064] As further preferred, the monitoring system includes:

[0065] Shear walls;

[0066] A round steel bar, which is an L-shaped structure, one end of which is buried in the shear wall and the other end of which is horizontally extended out of the shear wall;

[0067] A retractable connecting member, one end of which is connected to a round steel extending horizontally out of the shear wall, and the other end of which is connected to a scaffold;

[0068] A plurality of steel bar meters, provided on the columns of the scaffold, for measuring the axial force of the scaffold;

[0069] A plurality of settlement meters, arranged at the bottom of the scaffold, for measuring the settlement of the scaffold;

[0070] The tilt angle measuring module is arranged between the retractable connecting member and the scaffolding, and is used to measure the tilt angle of the scaffolding. The tilt angle measuring module includes a cylindrical shell, a conical container is arranged inside the cylindrical shell, a conductive liquid is arranged inside the container, an indicator light is arranged on the cylindrical shell, the negative pole of the power supply is connected to the connection terminal at the bottom of the cylinder, and the positive pole of the power supply is connected to the connection terminal on the side wall of the cylinder. Three connection terminals of different heights are arranged on the side wall, and different electronic components are arranged on each connection terminal. When the scaffolding pole tilts, the container will pour out the conductive liquid, and a closed loop is formed through the connection terminals at both ends, thereby triggering the indicator light.

[0071] In general, the above technical solution conceived by the present invention has the following technical advantages compared with the prior art:

[0072] 1. The present invention can monitor the key parameters of the scaffold in real time, such as environmental data, structural data, material data, displacement data and load data. Combined with the SD-MOP model and the LSSVM model, this method can accurately calculate the probability of accidents during the service of the scaffold and predict the strength and stability of the scaffold. This prediction capability significantly improves the safety and reliability of the scaffold, reduces the occurrence of construction accidents, protects the lives of workers and the smooth progress of the project.

[0073] 2. The present invention balances the three goals of cost, accident probability and environmental impact through weight coefficients, so that construction costs can be effectively controlled and environmental impact can be reduced under the premise of ensuring safety. By identifying the key influencing parameters through the decision tree model, the design and material selection of scaffolding can be carried out more targeted, resource allocation can be optimized, waste can be reduced, and cost-effectiveness can be maximized.

[0074] 3. The present invention not only includes traditional sensors and measuring equipment, but also combines advanced intelligent algorithms, such as particle swarm optimization algorithm and least squares support vector machine model, so that the monitoring system has the ability of self-learning and self-optimization. This intelligent monitoring system can quickly respond to changes in the scaffolding state, adjust the monitoring strategy in time, and improve the monitoring efficiency and accuracy. In addition, the intelligence of the system also makes remote monitoring and automatic control possible, laying the foundation for the development of the field of intelligent building construction in the future.

[0075] 4. The present invention solves the problem of water leakage in shear walls caused by traditional pre-buried short steel pipes by connecting pre-buried round steel with perforated steel plates, thereby improving the appearance and overall quality of the shear walls. At the same time, the angle of the rod can be freely adjusted and the length of the rod can be adjusted telescopically through the supports on the perforated steel plates, thereby solving the problem of being applicable to external frames and shear walls at different distances and improving the installation efficiency of wall connecting parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 It is a flow chart of a shear wall external scaffolding monitoring method based on intelligent algorithm according to an embodiment of the present invention;

[0077] Figure 2 is a schematic diagram of the structure of a monitoring system involved in an embodiment of the present invention;

[0078] Figure 3 yes Figure 2 The structural diagram of the tilt angle measurement module;

[0079] Figure 4 yes Figure 2 Schematic diagram of the structure of medium round steel.

[0080] In all the drawings, the same reference numerals represent the same technical features, specifically: 1-shear wall; 2-round steel; 3-perforated steel plate; 4-retractable rod; 5-fastener; 6-tilt angle measurement module; 7-indicator light; 8-power supply; 9-conductive liquid; 10-side terminal; 11-bottom terminal. DETAILED DESCRIPTION

[0081] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0082] like Figure 1 As shown, a shear wall external scaffolding monitoring method based on an intelligent algorithm provided by an embodiment of the present invention comprises the following steps:

[0083] Step 1: Build a monitoring system, collect monitoring data of the shear wall external scaffolding according to the monitoring system, and construct a sample data set based on the monitoring data.

[0084] In this step, the monitoring data includes:

[0085] Scaffolding use environment data, scaffolding structure data, scaffolding material data, scaffolding displacement data and scaffolding load data;

[0086] Wherein, the environmental data includes: wind speed, temperature, humidity;

[0087] The material data include: mechanical property parameters of scaffolding materials;

[0088] The scaffolding displacement data includes: inclination data, horizontal displacement and vertical displacement data, and settlement data;

[0089] The scaffolding load data includes: pressure data and axial force data.

[0090] In this step, the monitoring data of the scaffolding mainly includes the following aspects:

[0091] Tilt monitoring: Monitor the tilt of external wall scaffolding to assess its stability.

[0092] Displacement monitoring: Monitor the horizontal and vertical displacement of the scaffolding to measure the deformation of the formwork.

[0093] Load monitoring: monitors the pressure on scaffolding poles to assess the load-bearing capacity of the scaffolding.

[0094] Environmental monitoring: including monitoring of environmental factors such as wind speed, temperature and humidity, which may affect the stability of the scaffolding.

[0095] Pole axial force monitoring: Monitor the axial force of the pole to prevent structural instability caused by excessive axial force.

[0096] Pole tilt monitoring: monitor the tilt angle of the pole to ensure the verticality and stability of the scaffolding.

[0097] Pole horizontal displacement monitoring: Monitor the horizontal displacement of the poles to evaluate the horizontal stability of the scaffolding.

[0098] Formwork settlement monitoring: For high formwork, monitor the settlement of the formwork to assess the stability of the structure.

[0099] Monitoring camera equipment: Use camera equipment to monitor the situation at the construction site in real time so as to detect potential safety hazards in time.

[0100] The collection and analysis of these monitoring data are crucial to ensure the safety and stability of scaffolding construction. Through real-time monitoring and data analysis, problems in construction can be discovered and solved in a timely manner, improving construction efficiency and quality.

[0101] More specifically, monitoring data collection:

[0102] Scaffolding environment data: including wind speed, temperature, humidity and other environmental factors. Scaffolding structure data: including scaffolding size, structural layout, etc. Scaffolding material data: including material mechanical performance parameters, such as yield strength, elastic modulus, etc. Scaffolding displacement data: including inclination data, horizontal displacement and vertical displacement data, settlement data. Scaffolding load data: including pressure data, axial force data.

[0103] Step 2: Input the sample data set into the SD-MOP model to calculate the probability of accidents during the service of the scaffold. The SD-MOP model is used to calculate the probability of accidents, which combines system dynamics and multi-objective optimization.

[0104] In this step, the SD-MOP model includes:

[0105] P acc =f(T, W, H, L, E, σ y ,θ,Δx,Δy,S,P,F)

[0106] F 目 =min(w1·C+w2·P acc +w3·E)

[0107] g(E,σ y , P, F)≤0

[0108] Where T is temperature, W is wind speed, H is humidity, L is scaffold length, E is elastic modulus, σy is yield strength, θ is inclination angle, Δx is horizontal displacement, Δy is vertical displacement, S is settlement, P is pressure, F is axial force, C is cost, Pacc is accident probability, E is environmental impact, and w1, w2, and w3 are weight coefficients.

[0109] Preferably, the weight coefficient is determined by the following method:

[0110] (201) constructing an influencing factor set C = {Cj, j = 1, 2, ..., n} according to the monitoring data, where each Cj represents an influencing factor;

[0111] (202) Through expert scoring or data analysis, the judgment matrix R = (rij)m×n between the influencing factors is obtained, where rij represents the degree of influence of factor i on factor j;

[0112] (203) The judgment matrix R is normalized to obtain the normalized matrix B = (b ij ) m×n ,in,

[0113] (204) The entropy value Hj is calculated according to the normalized matrix B, and the formula is:

[0114]

[0115] in, When fij=0, ln f ij →0;

[0116] (205) Calculate the entropy weight kj of each influencing factor, the formula is:

[0117]

[0118] (206) Construct the direct impact average relationship matrix:

[0119] A=(a ij ) n×n

[0120] Among them, aij represents the influence of factor i on factor j;

[0121] (207) The direct impact average relationship matrix A is standardized to obtain the standardized direct impact matrix N = (n ij ) n×n And the comprehensive influence matrix T = (t ij ) n×n :

[0122] N=lim k→∞ (N 1 +N 2 +...+N k )=N(IN) -1

[0123] Where I is the identity matrix;

[0124] (208) Calculate influence, influence and centrality:

[0125] According to the comprehensive influence matrix T, the influence degree fi, the influence degree ei, the centrality degree ri and the cause degree zi of each influencing factor are calculated. The formula is:

[0126]

[0127] r i =f i +e i

[0128] z i =f i -e i

[0129] (209) Calculate the weight coefficient:

[0130] The weight coefficients w1, w2, w3 are calculated based on the centrality ri. The formula is:

[0131]

[0132] Step three, based on the accident probability component constraint condition, and taking the constraint condition as the objective function of the least squares support vector machine model, taking the key influencing parameters of the strength and stability of the scaffolding as input variables, the least squares support vector machine model is optimized and trained to obtain the optimal prediction model for monitoring the strength and stability of the scaffolding.

[0133] In this step, the decision tree model is used to analyze the key influencing parameters of the strength and stability of the scaffolding, including:

[0134] (301) normalizing the monitoring data;

[0135] (302) Construct a decision tree model:

[0136]

[0137] Where D is the dataset, A is the attribute, Dv is the data subset when the value of attribute A is v, |y| is the number of categories, and pk is the probability of the kth category;

[0138] (303) In the process of building a decision tree, if a node meets the pre-pruning condition, the splitting is stopped and the key influencing parameters are obtained.

[0139] Preferably, step three also includes: using the key influencing parameters identified by the decision tree as input variables of the LSSVM model and the accident probability Pacc as a constraint condition to construct an LSSVM model training model:

[0140]

[0141] Where: w is the weight vector, b is the bias term, ε i is the error term of the ith sample, C is the regularization parameter, φ(·) is the kernel function mapping, i = 1,…,N, N is the number of samples, yi is the actual output of the ith sample, and λ is the weight parameter of the accident probability, which is used to balance the impact of the accident probability in the optimization objective.

[0142] In step 3, the Gaussian kernel function expression of the LSSVM model is as follows:

[0143]

[0144] Among them, x is the input variable, x i is the i-th sample, x j is the jth sample, σ 2 is the kernel width parameter.

[0145] Preferably, in step three, a particle swarm optimization algorithm is used to optimize the parameters of the LSSVM model, wherein the update formula of the particle swarm optimization algorithm includes:

[0146]

[0147] In the formula, is the velocity of particle i at time t, is the position of particle i at time t, z is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers between [0,1], is the individual optimal position of particle i, is the optimal position of the group.

[0148] In addition, according to another aspect of the present invention, a shear wall external scaffolding monitoring system based on an intelligent algorithm is provided, comprising:

[0149] The first main control module is used to build a monitoring system, collect monitoring data of the shear wall external scaffolding according to the monitoring system, and construct a sample data set based on the monitoring data;

[0150] The second main control module is used to input the sample data set into the SD-MOP model to calculate the probability of accidents occurring during the service of the scaffolding;

[0151] The third main control module is used to optimize the least squares support vector machine model based on the accident probability component constraint condition, and use the constraint condition as the objective function of the least squares support vector machine model, and use the key influencing parameters of the strength and stability of the scaffolding as input variables to obtain the optimal prediction model for monitoring the strength and stability of the scaffolding.

[0152] The monitoring system comprises: a shear wall 1; a round steel bar 2, which is an L-shaped structure, one end of which is buried in the shear wall 1, and the other end of which is horizontally extended out of the shear wall 1; a retractable connecting member, one end of which is connected to the round steel bar 2 extending out of the shear wall 1 in a horizontal state, and the other end is connected to a scaffolding; a plurality of steel bar meters, which are arranged on the columns of the scaffolding and are used to measure the axial force of the scaffolding; a plurality of settlement meters, which are arranged at the bottom of the scaffolding and are used to measure the settlement of the scaffolding; an inclination angle measuring module, which is arranged between the retractable connecting member and the scaffolding and is used to measure the inclination angle of the scaffolding, and the inclination angle measuring module comprises a cylindrical shell, a conical container is arranged inside the cylindrical shell, a conductive liquid 9 is arranged inside the container, an indicator light 7 is arranged on the cylindrical shell, a negative pole of a power supply 8 is connected to a connecting terminal 11 at the bottom of the cylinder, and a positive pole of the power supply 8 is connected to a connecting terminal 10 on the side wall of the cylinder. Three wiring terminals 10 of different heights are arranged on the side wall, and different electronic components are arranged on each wiring terminal. When the scaffolding pole is tilted, the container will pour out the conductive liquid, and a closed loop will be formed through the wiring terminals at both ends, thereby triggering the indicator light 7.

[0153] More specifically, determine the position of the wall connection piece in advance, pass the L-shaped 20mm diameter round steel 2 from the first section through the perforated steel plate 3 to the other end, and embed the L-shaped round steel 2 vertically (length 400mm) inside the shear wall (center position). According to the thickness of the shear wall, the length of the other end of the L-shaped steel bar can be adjusted (such as 600mm thick wall length adjusted to 400mm, 800mm thick wall length adjusted to 500mm, and 100mm reserved) to ensure that the perforated steel plate is outside the shear wall and is not affected by the pouring of concrete. After the shear wall concrete is poured and the strength reaches the specified requirements, start connecting the scaffolding and the shear wall 1. An adjustable support is provided on the bolt with a hole, which consists of a base at both ends, a triangle iron and a rotatable tensioning device. The angle can be adjusted by rotating the opening device and the closing device can ensure that it will not rotate. The telescopic rod is composed of two sections. A pop-up fastener is set every 5 cm on the inner rod, which is connected to the corresponding hole of the outer rod so that the rod can be retracted and fixed firmly enough. The side close to the scaffold is connected with a fastener, and the end 20 cm close to the support is provided with a thread and the corresponding nut on the support is fixed to the embedded steel plate by rotation. Adjust the angle and the length of the telescopic rod, select the most suitable position to fix the rod fastener on the vertical pole of the scaffold, and lock the support and the telescopic rod 4 in time after completion to ensure that the entire device is in a rigid connection state after the process is completed. An inclination angle measurement module 6 is provided on the fastener. The inclination angle measurement module 6 is in the shape of a cylinder, and a conical container is set inside the cylinder, and a conductive liquid 9 is set inside the container. An indicator light 7 is provided on the cylinder, and the negative pole of the power supply 8 is connected to the wiring terminal 11 at the bottom of the cylinder, and the positive pole of the power supply 8 is connected to the wiring terminal 10 on the side wall of the cylinder. Three wiring terminals 10 of different heights are provided on the side wall, and different electronic components are provided on each wiring terminal. When the scaffolding pole tilts, the container will pour out the conductive liquid, which will form a closed loop through the terminals at both ends, thereby triggering the indicator light 7. According to the different tilt angles, the larger the angle, the more conductive liquid will be poured out, and the indicator lights will light up in green, yellow, and red in sequence, as follows: ① If it is in a horizontal state, the conductive liquid will not flow out and the alarm indicator light will not be triggered. If it is in a tilted state; ② The angle is less than 0.5°, the first electrical circuit is triggered, and the indicator light turns green; ③ The angle is between 0.5 and 1.5°, the first and second circuits are triggered, and the indicator light turns yellow; ④ The angle is greater than 1.5°, all circuits are triggered, and the indicator light turns red. The verticality of the frame can be judged by the different states of the indicator light 7, and the state of the scaffolding can be monitored for a long time. In the later dismantling of the scaffolding, the embedded round steel is first cut through one side of the perforated steel plate, and the telescopic rod 4, fastener 5 and monitoring system 6 are recycled for reuse.

[0154] The installation process of the above monitoring system is as follows: Step 1: According to the requirements of the scaffolding special plan, place points at the locations where wall ties are required; Step 2: First, pass the L-shaped 20mm thick round steel from the first section through the perforated steel plate to the other end, and embed the L-shaped round steel vertically (length 400mm) inside the shear wall (center position). According to the thickness of the shear wall, the length of the other end of the L-shaped steel bar is adjusted differently to ensure that the perforated steel plate is outside the shear wall. Step 3: Pour the shear wall concrete, wait for the concrete strength to meet the specified requirements, and set up the external scaffolding. Step 4: Take out the wall ties and fix them to the embedded steel plate with bolts. Step 5: Adjust the rod angle and rod length, fix the other end of the wall ties with fasteners, and lock the support and rod length in time after fixing. Step 6: Open and check the monitoring system, and implement the monitoring scaffolding status. Step 7: When the external scaffolding is dismantled, recycle the fasteners, retractable rods and monitoring system.

[0155] Based on any of the above embodiments or a combination of multiple embodiments, in this embodiment, the shear wall external scaffolding monitoring based on the intelligent algorithm includes:

[0156] Step 1: Build a monitoring system and collect data

[0157] Environmental data: wind speed (W=10m / s), temperature (T=30°C), humidity (H=60%).

[0158] Structural data: Scaffolding length (L=50m).

[0159] Material data: elastic modulus (E = 200 GPa), yield strength (σy = 250 MPa).

[0160] Displacement data: tilt angle (θ=0.5°), horizontal displacement (Δx=0.01m), vertical displacement (Δy=0.02m), settlement (S=0.005m).

[0161] Load data: pressure (P=1500N), axial force (F=2000N).

[0162] Step 2: SD-MOP model application

[0163] Calculate the probability of an accident occurring (Pacc).

[0164] Step 3: Determination of weight coefficient

[0165] The judgment matrix was constructed through expert scoring, and the entropy weight was calculated to obtain the weight coefficients w1=0.4, w2=0.3, and w3=0.3.

[0166] Step 4: Decision tree model application

[0167] Normalize the monitoring data, build a decision tree model, and identify key influencing parameters.

[0168] Step 5: LSSVM model training and optimization

[0169] The LSSVM model with Gaussian kernel function is used, and the model parameters are optimized by particle swarm optimization algorithm.

[0170] Analyze the data:

[0171] Probability of accident occurrence (Pacc): 0.05.

[0172] Key influencing parameters: wind speed (W), axial force (F).

[0173] Scaffold stability predicted by LSSVM model: 95%.

[0174] Based on any of the above embodiments or a combination of multiple embodiments, in this embodiment, the shear wall external scaffolding monitoring method based on intelligent algorithm includes:

[0175] Project Background: During the construction of a large bridge, it is necessary to monitor the stability and safety of the shear wall external scaffolding.

[0176] Step 1: Build a monitoring system and collect data

[0177] Environmental data: wind speed (W=15m / s), temperature (T=25°C), humidity (H=70%).

[0178] Structural data: Scaffolding length (L=80m).

[0179] Material data: elastic modulus (E=210GPa), yield strength (σy=280MPa).

[0180] Displacement data: tilt angle (θ=0.8°), horizontal displacement (Δx=0.02m), vertical displacement (Δy=0.03m), settlement (S=0.008m).

[0181] Load data: pressure (P=2000N), axial force (F=2500N).

[0182] Step 2: SD-MOP model application

[0183] Calculate the probability of an accident occurring (Pacc).

[0184] Step 3: Determination of weight coefficient

[0185] The judgment matrix was constructed through expert scoring, and the entropy weight was calculated to obtain the weight coefficients w1=0.45, w2=0.25, and w3=0.3.

[0186] Step 4: Decision tree model application

[0187] Normalize the monitoring data, build a decision tree model, and identify key influencing parameters.

[0188] Step 5: LSSVM model training and optimization

[0189] The LSSVM model with Gaussian kernel function is used, and the model parameters are optimized by particle swarm optimization algorithm.

[0190] Analyze the data:

[0191] Probability of accident (Pacc): 0.08.

[0192] Key influencing parameters: wind speed (W), elastic modulus (E).

[0193] Scaffold stability predicted by LSSVM model: 90%.

[0194] The key scaffolding parameters were collected through the monitoring system, and the SD-MOP model and LSSVM model were applied to predict the stability and accident probability of the scaffolding. With these data, engineers can evaluate the safety of the scaffolding and take necessary preventive measures.

[0195] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A shear wall external scaffolding monitoring method based on intelligent algorithm, characterized in that: The following steps are involved: Step 1: Build a monitoring system, collect monitoring data of the shear wall external scaffolding according to the monitoring system, and construct a sample data set based on the monitoring data; Step 2: Input the sample data set into the SD-MOP model to calculate the probability of accidents occurring during the service of the scaffolding; Step three, based on the accident probability component constraint condition, and taking the constraint condition as the objective function of the least squares support vector machine model, taking the key influencing parameters of the strength and stability of the scaffolding as input variables, the least squares support vector machine model is optimized and trained to obtain the optimal prediction model for monitoring the strength and stability of the scaffolding.

2. According to claim 1, a shear wall external scaffolding monitoring method based on intelligent algorithm is characterized in that: In step 1, the monitoring data includes: Scaffolding use environment data, scaffolding structure data, scaffolding material data, scaffolding displacement data and scaffolding load data; Wherein, the environmental data includes: wind speed, temperature, humidity; The material data include: mechanical property parameters of scaffolding materials; The scaffolding displacement data includes: inclination data, horizontal displacement and vertical displacement data, and settlement data; The scaffolding load data includes: pressure data and axial force data.

3. According to claim 2, a shear wall external scaffolding monitoring method based on intelligent algorithm is characterized in that: In step 2, the SD-MOP model includes: P acc =f(T,W,H,L,E,σ y ,θ,Δx,Δy,S,P,F) F 目 =min(w1·C+w2·P acc +w3·E) g(E,σ y ,P,F)≤0 Where T is temperature, W is wind speed, H is humidity, L is scaffold length, E is elastic modulus, σy is yield strength, θ is inclination angle, Δx is horizontal displacement, Δy is vertical displacement, S is settlement, P is pressure, F is axial force, C is cost, Pacc is accident probability, E is environmental impact, and w1, w2, w3 are weight coefficients.

4. A shear wall external scaffolding monitoring method based on intelligent algorithm according to claim 3, characterized in that: The weight coefficient is determined by the following method: (201) Construct an influencing factor set C = {Cj, j = 1, 2, ..., n} according to the monitoring data, where each Cj represents an influencing factor; (202) Through expert scoring or data analysis, the judgment matrix R = (rij)m×n between the influencing factors is obtained, where r ij Indicates the degree of influence of factor i on factor j; (203) The judgment matrix R is normalized to obtain the normalized matrix B = (b ij ) m×n ,in, (204) The entropy value Hj is calculated according to the normalized matrix B, and the formula is: in, When fij=0, ln f ij →0; (205) Calculate the entropy weight kj of each influencing factor, the formula is: (206) Construct the direct impact average relationship matrix: A(a ij )n n×n Among them, a ij Indicates the influence of factor i on factor j; (207) The direct impact average relationship matrix A is standardized to obtain the standardized direct impact matrix N = (n ij ) n×n And the comprehensive influence matrix T = (t ij ) n×n : N=lim k→∞ (N 1 +N 2 +...+N k )=N(I-N) -1 Where I is the identity matrix; (208) Calculate influence, influence and centrality: According to the comprehensive influence matrix T, the influence degree fi, the influence degree ei, the centrality degree ri and the cause degree zi of each influencing factor are calculated. The formula is: r i =f i +e i z i =f i -e i (209) Calculate the weight coefficient: The weight coefficients w1, w2, w3 are calculated based on the centrality ri. The formula is:

5. The method for monitoring external scaffolding of shear walls based on intelligent algorithm according to claim 1 is characterized in that: In step three, the decision tree model is used to analyze the key influencing parameters of the strength and stability of the scaffolding, including: (301) normalizing the monitoring data; (302) Construct a decision tree model: Where D is the data set, A is the attribute, Dv is the data subset when the value of attribute A is v, |y| is the number of categories, and pk is the probability of the kth category; (303) In the process of building a decision tree, if a node meets the pre-pruning condition, the splitting is stopped and the key influencing parameters are obtained.

6. The method for monitoring external scaffolding of shear walls based on intelligent algorithm according to claim 1 is characterized in that: Step three also includes: using the key influencing parameters identified by the decision tree as input variables of the LSSVM model and the accident probability Pacc as a constraint condition to build an LSSVM model training model: Where: w is the weight vector, b is the bias term, ε i is the error term of the ith sample, C is the regularization parameter, φ(·) is the kernel function mapping, i = 1,…,N, N is the number of samples, yi is the actual output of the ith sample, and λ is the weight parameter of the accident probability, which is used to balance the impact of the accident probability in the optimization objective.

7. The method for monitoring external scaffolding of shear walls based on intelligent algorithm according to claim 1 is characterized in that: In step 3, the Gaussian kernel function expression of the LSSVM model is as follows: Among them, x is the input variable, x i is the i-th sample, x j is the jth sample, σ 2 is the kernel width parameter.

8. The method for monitoring external scaffolding of shear walls based on intelligent algorithm according to claim 1 is characterized in that: In step 3, the particle swarm optimization algorithm is used to optimize the parameters of the LSSVM model, where the update formula of the particle swarm optimization algorithm includes: In the formula, is the velocity of particle i at time t, is the position of particle i at time t, z is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers between [0,1], is the individual optimal position of particle i, is the optimal position of the group.

9. A shear wall external scaffolding monitoring system based on intelligent algorithm, characterized in that: include: The first main control module is used to build a monitoring system, collect monitoring data of the shear wall external scaffolding according to the monitoring system, and construct a sample data set based on the monitoring data; The second main control module is used to input the sample data set into the SD-MOP model to calculate the probability of accidents occurring during the service of the scaffolding; The third main control module is used to optimize the least squares support vector machine model based on the accident probability component constraint condition, and use the constraint condition as the objective function of the least squares support vector machine model, and use the key influencing parameters of the strength and stability of the scaffolding as input variables to obtain the optimal prediction model for monitoring the strength and stability of the scaffolding.

10. The shear wall external scaffolding monitoring system based on intelligent algorithm according to claim 9 is characterized in that: The monitoring system comprises: Shear wall (1); A round steel (2), the round steel (2) being an L-shaped structure, one end of which is buried in the shear wall (1) and the other end of which is horizontally extended out of the shear wall (1); A telescopic connecting member, one end of which is connected to a round steel bar (2) extending horizontally out of the shear wall (1), and the other end of which is connected to a scaffold; A plurality of steel bar meters, provided on the columns of the scaffold, for measuring the axial force of the scaffold; A plurality of settlement meters, arranged at the bottom of the scaffold, for measuring the settlement of the scaffold; The tilt angle measuring module is arranged between the telescopic connecting member and the scaffolding, and is used to measure the tilt angle of the scaffolding. The tilt angle measuring module comprises a cylindrical shell, a conical container is arranged inside the cylindrical shell, a conductive liquid (9) is arranged inside the container, an indicator light (7) is arranged on the cylindrical shell, a negative pole of a power source (8) is connected to a connecting terminal (11) at the bottom of the cylinder, and a positive pole of the power source (8) is connected to a connecting terminal (10) on the side wall of the cylinder. Three connecting terminals (10) of different heights are arranged on the side wall, and each connecting terminal is provided with different electronic components. When the scaffolding pole tilts, the container will pour out the conductive liquid, and a closed loop is formed through the connecting terminals at both ends, thereby triggering the indicator light (7).

Images