A method and system for monitoring external scaffolding of a shear wall based on an intelligent algorithm

Abstract

This invention belongs to the field of building engineering technology and specifically discloses a method and system for monitoring shear wall external scaffolding based on intelligent algorithms. It includes: setting up a monitoring system and collecting monitoring data of the shear wall external scaffolding; constructing a sample dataset based on this monitoring data; inputting the sample dataset into an SD-MOP model to calculate the probability of accidents during the scaffolding's service life; and optimizing and training the least squares support vector machine model based on the component constraints of the accident probability, using these constraints as the objective function of the model, and taking the key influencing parameters of the scaffolding's strength and stability as input variables, to obtain the optimal prediction model for monitoring the scaffolding's strength and stability. This invention significantly improves the safety and reliability of scaffolding, reduces construction accidents, protects workers' lives, and ensures the smooth progress of projects.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of building engineering, and more specifically relates to a shear wall outer scaffold monitoring method and system based on an intelligent algorithm. BACKGROUND

[0002] In the field of building construction, the shear wall outer scaffold is a key temporary structure to ensure construction safety and efficiency. However, due to the complex influence of environmental factors, material aging, construction load and other factors, the stability and safety of the scaffold face serious challenges. Traditional scaffold monitoring methods mainly rely on manual inspection and experience-based judgment, which have problems such as low monitoring efficiency, poor accuracy, and insufficient real-time performance, making it difficult to meet the high standards of safety and economy in modern building engineering.

[0003] With the development of intelligent algorithms and sensor technology, monitoring methods based on intelligent algorithms have gradually become a research hotspot. These methods collect multi-dimensional data of the scaffold, use advanced data processing technology to evaluate and predict the stability and safety of the scaffold. However, existing intelligent monitoring methods still face some challenges in practical application:

[0004] Comprehensiveness of data collection: Traditional monitoring systems often only focus on partial parameters such as displacement or load, ignoring the comprehensive influence of environmental factors on the stability of the scaffold. Accuracy and real-time performance of the model: Existing models often lack sufficient accuracy and real-time performance in predicting the probability of scaffold accidents, and cannot respond to changes in scaffold status in a timely manner. Parameter optimization and weight distribution: In multi-objective optimization, how to reasonably distribute the weights of cost, safety and environmental impact is a technical problem. Identification of key influencing parameters: Among numerous influencing factors, accurately identifying the key parameters that most affect the stability and safety of the scaffold is crucial to improving monitoring efficiency and prediction accuracy.

[0005] In addition, during the construction of underground box bodies, the outer wall floor type steel pipe scaffold cannot be connected to the wall element through pre-buried steel pipes. For the construction of such shear wall outer scaffold wall elements, pre-buried short steel pipes are generally used to connect the wall elements. However, pre-buried short steel pipes on the outer wall can cause leakage problems. Generally, the verticality of the scaffold is monitored by a total station, which is a waste of labor. SUMMARY

[0006] In view of the above defects or improvement needs of the prior art, the present application provides a shear wall external scaffold monitoring method based on an intelligent algorithm, which comprehensively considers scaffold use environment data, structure data, material data, displacement data and load data, calculates the accident occurrence probability by using an SD-MOP model, and optimizes training and prediction of the strength and stability of the scaffold by combining a least squares support vector machine model and a decision tree model. In addition, the present method innovatively introduces a weight coefficient determination method, scientifically allocates the weights of different targets by entropy weight method and centrality analysis, and improves the intelligent level and prediction accuracy of the monitoring system. Through these technical means, the present patent aims to provide a more comprehensive, accurate and real-time scaffold monitoring solution to meet the safety and economic needs of modern construction engineering.

[0007] To achieve the above-mentioned purpose, according to one aspect of the present application, a shear wall external scaffold monitoring method based on an intelligent algorithm is provided, comprising the following steps:

[0008] Step one, building a monitoring system and collecting monitoring data of the shear wall external scaffold according to the monitoring system, and constructing a sample data set based on the monitoring data;

[0009] Step two, inputting the sample data set into an SD-MOP model to calculate the accident occurrence probability during the service process of the scaffold;

[0010] Step three, constructing a constraint condition based on the accident occurrence probability, taking the constraint condition as the objective function of a least squares support vector machine model, taking the key influence parameters of the strength and stability of the scaffold as input variables, and optimizing training of the least squares support vector machine model to obtain an optimal prediction model for monitoring the strength and stability of the scaffold.

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

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

[0013] The environment data includes wind speed, temperature and humidity;

[0014] The material data includes the mechanical property parameters of the scaffold material;

[0015] The scaffold displacement data includes inclination degree data, horizontal and vertical displacement data and settlement data;

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

[0017] As a further preferred, in step two, the SD-MOP model comprises:

[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] In the formula, 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, the weight coefficients are determined by the following method:

[0023] (201) Construct an influence factor set C = {Cj, j = 1, 2, …, n} from the monitoring data, where each Cj represents an influence factor;

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

[0025] (203) Normalize the judgment matrix R to obtain a normalized matrix B = (b ij ) m×n , where

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

[0027]

[0028] where When fij= 0, ln f ij → 0;

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

[0030]

[0031] (206) Construct a direct influence average relationship matrix:

[0032] A = (a ij ) n×n

[0033] wherein aij represents the degree of influence of factor i on factor j;

[0034] (207) Standardizing the direct influence matrix A to obtain a normalized direct influence matrix N = (n ij ) n×n and a comprehensive influence matrix T = (t ij ) n×n :

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

[0036] wherein I is the unit matrix;

[0037] (208) Calculate the influence degree, the influenced degree, the centrality:

[0038] According to the comprehensive influence matrix T, the influence degree fi, the influenced degree ei, the centrality ri and the reason degree zi of each influence factor are calculated, and 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] According to the centrality ri, the weight coefficients w1, w2, w3 are calculated, and the formula is:

[0044]

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

[0046] (301) Normalizing the monitoring data;

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

[0048]

[0049] wherein D is a dataset, A is an attribute, Dv is a subset of data with the value of attribute A being v, |y| is the number of classes, pk is the probability of the kth class;

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

[0051] As a further preferred, the step three further comprises: taking the key influence parameter identified by the decision tree as an input variable of the LSSVM model, taking the accident occurrence probability Pacc as a constraint condition, and constructing the LSSVM model training model:

[0052]

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

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

[0055]

[0056] wherein x is an input variable, x i is the ith sample, x j is the jth sample, and σ 2 is a kernel width parameter.

[0057] As a further preferred, in the 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 comprises:

[0058]

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

[0060] According to another aspect of the present application, a shearing wall external scaffold monitoring system based on an intelligent algorithm is also provided, comprising:

[0061] The first master module is used for building a monitoring system, collecting monitoring data of the external scaffold of the shear wall according to the monitoring system, and constructing a sample data set based on the monitoring data;

[0062] The second master module is used for inputting the sample data set into an SD-MOP model, and calculating an accident occurrence probability of the scaffold in a service process;

[0063] The third master module is used for constructing a constraint condition based on the accident occurrence probability, taking the constraint condition as an objective function of a least squares support vector machine model, taking key influence parameters of the strength and stability of the scaffold as input variables, and optimizing and training the least squares support vector machine model to obtain an optimal prediction model for monitoring the strength and stability of the scaffold.

[0064] As a further preferred, the monitoring system comprises:

[0065] The shear wall;

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

[0067] The telescopic connecting member is connected with the round steel horizontally extended out of the shear wall at one end, and connected with the scaffold at the other end;

[0068] The plurality of reinforcement meters are arranged on the upright columns of the scaffold, and are used for measuring the axial force of the scaffold;

[0069] The plurality of settlement meters are arranged at the bottom of the scaffold, and are used for measuring the settlement of the scaffold;

[0070] The inclination angle measuring module is arranged between the telescopic connecting member and the scaffold, and is used for measuring the inclination angle of the scaffold, the inclination angle measuring module comprising a cylindrical shell, a conical container arranged inside the cylindrical shell, a conductive liquid arranged inside the container, an indicator lamp arranged on the cylindrical shell, a power negative level connected with a wiring terminal at the bottom of the cylindrical shell, and a power positive level connected with a wiring terminal on the side wall of the cylindrical shell, three wiring terminals of different heights arranged on the side wall, and different electronic elements arranged on each wiring terminal, when the upright column of the scaffold is inclined, the container will pour out the conductive liquid, a closed loop is formed through the wiring terminals at both ends, and the indicator lamp is triggered.

[0071] Overall, compared with the prior art, the above technical scheme of the present application mainly has the following technical advantages:

[0072] 1.The present application 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 accident probability of the scaffold during service and predict the strength and stability of the scaffold. This prediction ability significantly improves the safety and reliability of the scaffold, reduces the occurrence of construction accidents, and protects the safety of workers and the smooth progress of the project.

[0073] 2.The present application balances the cost, accident probability and environmental impact through the weight coefficient, so that the construction cost can be effectively controlled and the environmental impact can be reduced under the premise of ensuring safety. Through the key influence parameters identified by the decision tree model, the design and material selection of the scaffold can be more targeted, the resource allocation can be optimized, and the waste can be reduced, so as to maximize the cost-effectiveness.

[0074] 3.The present application 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 state of the scaffold, timely adjust the monitoring strategy, and improve the monitoring efficiency and accuracy. In addition, the intelligence of the system also provides the possibility for remote monitoring and automatic control, and lays the foundation for the development of the future intelligent construction field.

[0075] 4.The present application solves the problem of water leakage caused by traditional pre-buried short steel pipes in shear walls, improves the appearance and overall quality of shear walls, and at the same time, through the support on the perforated steel plate, the angle of the rod can be freely adjusted, the length of the rod can be adjusted, the distance between the outer scaffold and the shear wall can be applied, and the installation efficiency of the wall connecting piece is improved. BRIEF DESCRIPTION OF DRAWINGS

[0076] Figure 1 is a flow chart of a shear wall outer scaffold monitoring method based on intelligent algorithm according to an embodiment of the present application;

[0077] Figure 2 is a structural schematic diagram of the monitoring system according to an embodiment of the present application;

[0078] Figure 3 is Figure 2 a structural schematic diagram of the inclination angle measuring module in

[0079] Figure 4 is Figure 2 a structural schematic diagram of the round steel in

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

[0081] In order to make the objectives, 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 should not be used to limit the present application. In addition, the technical features involved in the various embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0082] As shown in Figure 1 The shear wall outer scaffold monitoring method based on intelligent algorithm provided by the embodiment of the present application comprises the following steps:

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

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

[0085] scaffold usage environment data, scaffold structure data, scaffold material data, scaffold displacement data, and scaffold load data;

[0086] The environment data includes: wind speed, temperature, humidity;

[0087] The material data includes: mechanical property parameters of scaffold materials;

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

[0089] The scaffold load data includes: pressure data, axial force data.

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

[0091] Inclination monitoring: monitor the inclination degree of the outer wall scaffold to evaluate its stability.

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

[0093] Load monitoring: monitor the pressure on the scaffold upright rod to evaluate the load-carrying capacity of the scaffold.

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

[0095] Upright shaft force monitoring: monitoring the shaft force of the upright to prevent structural instability caused by excessive shaft force.

[0096] Upright inclination monitoring: monitoring the inclination angle of the upright to ensure the verticality and stability of the scaffold.

[0097] Upright horizontal displacement monitoring: monitoring the horizontal displacement of the upright to evaluate the horizontal stability of the scaffold.

[0098] Formwork settlement monitoring: for high formwork, monitoring the settlement of the formwork to evaluate the stability of the structure.

[0099] Monitoring camera equipment: real-time monitoring of the construction site through camera equipment to timely discover potential safety hazards.

[0100] The collection and analysis of these monitoring data are crucial for ensuring the safety and stability of scaffold 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] Scaffold environmental data: including wind speed, temperature, humidity and other environmental factors. Scaffold structure data: including the size, structure layout of the scaffold. Scaffold material data: including the mechanical properties of the material, such as yield strength, elastic modulus, etc. Scaffold displacement data: including inclination data, horizontal and vertical displacement data, settlement data. Scaffold load data: including pressure data, shaft force data.

[0103] Step two, input the sample data set into the SD-MOP model, calculate the probability of accidents occurring during the service of the scaffold. Use the SD-MOP model 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] In the formula, T is temperature, W is wind speed, H is humidity, L is the length of the scaffold, E is the elastic modulus, σy is the yield strength, θ is the inclination angle, Δx is the horizontal displacement, Δy is the vertical displacement, S is the settlement, P is the pressure, F is the axial force, C is the cost, Pacc is the probability of accident, E is the environmental impact, w1, w2, w3 are weight coefficients.

[0109] Preferably, the weight coefficients are determined by the following method:

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

[0111] (202) obtaining a judgment matrix R = (rij)m×n between the influence factors by expert scoring or data analysis, wherein rij represents the influence degree of factor i on factor j;

[0112] (203) normalizing the judgment matrix R to obtain a normalized matrix B = (b ij ) m×n , wherein,

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

[0114]

[0115] wherein, When fij = 0, ln f ij → 0;

[0116] (205) calculating the entropy weight kj of each influence factor, and the formula is:

[0117]

[0118] (206) constructing a direct influence average relationship matrix:

[0119] A = (a ij ) n×n

[0120] wherein, aij represents the influence degree of factor i on factor j;

[0121] (207) standardizing the direct influence average relationship matrix A to obtain a standardized direct influence matrix N = (n ij ) n×n and a comprehensive influence matrix T = (t ij ) n×n :

[0122] N = lim k→∞ (N 1 +N 2 +…+N k ) = N(I-N) -1

[0123] where I is a unit matrix;

[0124] (208) calculating the influence degree, the influenced degree, the centrality:

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

[0126]

[0127] r i = f i + e i

[0128] z i = f i -e i

[0129] (209) calculating the weight coefficient:

[0130] According to the centrality ri, the weight coefficients w1, w2 and w3 are calculated, and the formula is:

[0131]

[0132] Step three, based on the accident occurrence probability component constraint condition, and taking the constraint condition as the objective function of the least squares support vector machine model, taking the key influence parameters of the strength and stability of the scaffold as the 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 scaffold.

[0133] In this step, the decision tree model is used to analyze the key influence parameters of the strength and stability of the scaffold, which specifically includes:

[0134] (301) normalizing the monitoring data;

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

[0136]

[0137] where D is a data set, A is an attribute, Dv is a 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 constructing the decision tree, if a node meets the pre-pruning condition, the splitting is stopped, and the key influence parameter is obtained.

[0139] Preferably, step three further comprises: taking the key influence parameter identified by the decision tree as an input variable of the LSSVM model, taking the accident occurrence probability Pacc as a constraint condition, and constructing an LSSVM model training model:

[0140]

[0141] wherein w is a weight vector, b is a bias term, ε i is an error term of the i th sample, C is a regularization parameter, φ(·) is a kernel function mapping, i = 1, …, N, N is the number of samples, y i is the actual output of the i th sample, λ is a weight parameter of the accident occurrence probability, and is used to balance the influence of the accident occurrence probability in the optimization objective.

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

[0143]

[0144] wherein x is an input variable, x i is the i th sample, x j is the j th sample, and σ 2 is a 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 comprises:

[0146]

[0147] wherein, is the velocity of particle i at time t, is the position of particle i at time t, z is an inertia weight, c 1 and c 2 are learning factors, r 1 and r 2 are random numbers between 0 and 1, is the individual optimal position of particle i, is the group optimal position.

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

[0149] A first master control module is configured to build the monitoring system, collect monitoring data of the shear wall external scaffold according to the monitoring system, and construct a sample data set based on the monitoring data;

[0150] A second master module is configured to input the sample data set into the SD-MOP model, and calculate the accident probability of the scaffold during service;

[0151] A third master module is configured to construct a constraint condition based on the accident probability, and take the constraint condition as an objective function of a least squares support vector machine model, take key influence parameters of the strength and stability of the scaffold as input variables, and optimize and train the least squares support vector machine model to obtain an optimal prediction model for monitoring the strength and stability of the scaffold.

[0152] The monitoring system comprises a shear wall 1, a circular steel 2 in L-shaped structure, one end of which is embedded 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 with the circular steel 2 horizontally extended out of the shear wall 1, and the other end of which is connected with a scaffold, a plurality of reinforcement meters arranged on the upright 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, and an inclination angle measuring module arranged between the telescopic connecting member and the scaffold for measuring the inclination angle of the scaffold, the inclination angle measuring module comprising a cylindrical shell, a conical container arranged inside the cylindrical shell, a conductive liquid 9 arranged inside the container, an indicator light 7 arranged on the cylindrical shell, a negative terminal of a power supply 8 connected with a bottom terminal 11 of the cylindrical shell, and a positive terminal of the power supply 8 connected with a side wall terminal 10 of the cylindrical shell, three terminals 10 of different heights arranged on the side wall, different electronic elements arranged on each terminal, and the indicator light 7 triggered when the conductive liquid in the container is poured out through the terminals at both ends to form a closed loop when the upright column of the scaffold is inclined.

[0153] More specifically, the position of the wall connecting piece is determined in advance, the L-shaped diameter 20mm round steel 2 is passed through the hole steel plate 3 from the first section to the other end, and the L-shaped round steel 2 is vertically (length 400mm) embedded in the shear wall (center position). According to the thickness of the shear wall, the length of the other end of the L-shaped steel can be adjusted (such as 400mm for 600mm thick wall, 500mm for 800mm thick wall, and 100mm reserved). The hole steel plate is outside the shear wall and is not affected by the pouring of concrete. After the pouring of concrete in the shear wall is completed and the strength reaches the specified requirements, the scaffold and the shear wall 1 are connected. The adjustable support is provided on the hole bolt, which is composed of two end bases, triangular iron and rotatable tightening device. The angle is 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-out buckle is provided on the inner rod every 5cm, which is connected with the corresponding hole of the outer rod to meet the telescopic and fixed rod. The buckle is connected near the scaffold side, and the end 20cm of the support side is provided with a screw thread and a corresponding nut on the support, which is fixed to the embedded steel plate by rotating. The angle and the length of the telescopic rod are adjusted, and the most suitable position is selected to fix the rod buckle on the upright rod of the scaffold. After completion, the support and the telescopic rod 4 are locked in time to ensure that the whole device is in a rigid connection state after the process is completed. The buckle is provided with an inclination angle measuring module 6. The inclination angle measuring module 6 is in the shape of a cylinder, a conical container is arranged in the cylinder, and a conductive liquid 9 is arranged in the container. The cylinder is provided with an indicator light 7, the negative level of the power supply 8 is connected with the wiring terminal 11 at the bottom of the cylinder, and the positive level of the power supply 8 is connected with the wiring 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 elements are arranged on each wiring terminal. When the upright rod of the scaffold is inclined, the container will pour out the conductive liquid, and through the wiring terminals at both ends, a closed circuit is formed, thereby triggering the indicator light 7. According to the inclination angle, the larger the angle, the more the conductive liquid is poured out, and the indicator light is green, yellow and red in turn. Specifically, ① if it is in a horizontal state, the conductive liquid does not flow out, and the alarm indicator light is not triggered. If it is in an inclined state; ② the angle is less than 0.5°, the first electric circuit is triggered, and the indicator light is green; ③ the angle is between 0.5 and 1.5°, the first and second circuits are triggered, and the indicator light is yellow; ④ the angle is greater than 1.5°, all circuits are triggered, and the indicator light is red. The verticality of the frame body is judged by the different states of the indicator light 7, which can long-term monitor the state of the scaffold. In the process of removing the scaffold in the later period, the embedded round steel is cut off through the hole steel plate on one side, the telescopic rod 4, the buckle 5 and the monitoring system 6 are recycled, and can be reused.

[0154] The installation process of the above monitoring system is as follows: step 1: according to the requirements of the special scheme of the scaffold, mark the position where the wall connecting piece is needed to be set; step 2: first, pass the L-shaped 20mm thick round steel from the first section through the hole steel plate to the other end, and vertically (length 400mm) embed the L-shaped steel in the shear wall (center position), according to the thickness of the shear wall, adjust the length of the other end of the L-shaped steel to ensure that the hole steel plate is outside the shear wall; step 3: pour the shear wall concrete, wait for the concrete strength to reach the specified requirements, and set up the outer scaffold; step 4: take out the wall connecting piece, and fix the wall connecting piece to the embedded steel plate through bolts; step 5: adjust the angle and length of the rod, fix the other end of the wall connecting piece through the fastener, and lock the support and the length of the rod in time after the fixing is completed; step 6: open and check the monitoring system, and implement the monitoring of the scaffold state; step 7: when the outer scaffold is removed, the fastener, telescopic rod and monitoring system are recycled.

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

[0156] Step one: build the monitoring system and collect data

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

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

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

[0160] Displacement data: inclination 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 two: SD-MOP model application

[0163] Calculate the accident occurrence probability (Pacc).

[0164] Step three: determination of weight coefficient

[0165] Construct a judgment matrix by expert scoring and calculate the entropy weight to obtain the weight coefficient w1=0.4, w2=0.3, w3=0.3.

[0166] Step four: application of decision tree model

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

[0168] Step five: LSSVM model training and optimization

[0169] Use the LSSVM model with a Gaussian kernel function, and optimize the model parameters using the particle swarm optimization algorithm.

[0170] Data analysis:

[0171] Accident probability (Pacc): 0.05.

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

[0173] LSSVM model prediction of scaffold stability: 95%.

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

[0175] Engineering background: During the construction of a large bridge, the stability and safety of the external scaffold of the shear wall need to be monitored.

[0176] Step one: Set up the monitoring system and collect data

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

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

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

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

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

[0182] Step two: SD-MOP model application

[0183] Calculate the accident probability (Pacc).

[0184] Step three: Determination of weight coefficients

[0185] Construct a judgment matrix through expert scoring and calculate the entropy weight to obtain the weight coefficients w1=0.45, w2=0.25, w3=0.3.

[0186] Step four: Decision tree model application

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

[0188] Step five: LSSVM model training and optimization

[0189] Use the LSSVM model with a Gaussian kernel function and optimize the model parameters using the particle swarm optimization algorithm.

[0190] Data analysis:

[0191] Accident probability (Pacc): 0.08.

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

[0193] LSSVM model predicted scaffold stability: 90%.

[0194] Key scaffold parameters were collected through the monitoring system, and the SD-MOP model and LSSVM model were applied to predict the stability of the scaffold and the probability of accidents. Through these data, engineers can evaluate the safety of the scaffold and take necessary preventive measures.

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

Claims

1. A method for monitoring external scaffolding of shear walls based on intelligent algorithms, characterized in that, Includes the following steps: Step 1: Build a monitoring system and collect monitoring data of the shear wall scaffolding based on the monitoring system, and construct a sample dataset based on the monitoring data; Step 2: Input the sample dataset into the SD-MOP model to calculate the probability of accidents during the service life of the scaffolding; Step 3: Based on the component constraint condition of the accident occurrence probability, and using the constraint condition as the objective function of the least squares support vector machine model, the key influencing parameters of the scaffold strength and stability are used as input variables to optimize and train the least squares support vector machine model to obtain the optimal prediction model for monitoring the strength and stability of the scaffold. In step one, the monitoring data includes: Scaffolding usage environment data, scaffolding structure data, scaffolding material data, scaffolding displacement data, and scaffolding load data; The environmental data includes: wind speed, temperature, and humidity; The material data includes: mechanical property parameters of the scaffolding material; The scaffold displacement data includes: tilt data, horizontal and vertical displacement data, and settlement data; The scaffold load data includes: pressure data and axial force data; In step two, 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 In the formula, T is temperature, W is wind speed, H is humidity, L is scaffold length, E is elastic modulus, σy is yield strength, θ is tilt 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 weighting coefficients. The weighting coefficients are determined using the following method: (201) Construct a set of influencing factors C = {Cj, j = 1, 2, ..., n} based on the monitoring data, where each Cj represents an influencing factor; (202) Obtain the judgment matrix R = (rij)m×n among the influencing factors through expert scoring or data analysis, where r ij This indicates the degree of influence of factor i on factor j; (203) Normalize the judgment matrix R to obtain the normalized matrix B = (b ij ) m×n ,in, (204) Calculate the entropy value Hj based on the normalized matrix B, using the following formula: in, When fij = 0, ln f ij →0; (205) Calculate the entropy weight kj of each influencing factor, using the following formula: (206) Construct the matrix of direct influence on the average relationship: A=(a ij ) n×n Among them, a ij This indicates the degree of influence of factor i on factor j; (207) Standardize the average direct influence matrix A to obtain the standardized direct influence 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, affectedness, and centrality: Based on the comprehensive influence matrix T, calculate the influence degree fi, the degree of being influenced ei, the centrality degree ri, and the causality degree zi of each influencing factor, using the following formula: r i =f i +e i z i =f i -e i (209) Calculate the weighting coefficients: The weight coefficients w1, w2, w3 are calculated based on the centrality ri using the following formula:

2. The method for monitoring shear wall scaffolding based on intelligent algorithms according to claim 1, characterized in that, In step three, a decision tree model is used to analyze the key influencing parameters of the scaffolding's strength and stability, specifically including: (301) Normalize the monitoring data; (302) Constructing a decision tree model: Where D is the dataset, A is the attribute, Dv is the subset of data when the value of attribute A is v, |y| is the number of categories, and pk is the probability of the k-th category; (303) In the process of constructing the decision tree, if a node meets the pre-pruning condition, the splitting is stopped and the key influence parameters are obtained.

3. The method for monitoring shear wall scaffolding based on intelligent algorithms according to claim 1, characterized in that, Step three also includes: using the key impact parameters identified by the decision tree as input variables for the LSSVM model, and the accident occurrence probability Pacc as a constraint, to construct and train the LSSVM model. Where: w is the weight vector, b is the bias term, and ε is the weight vector. i Let be the error term of the i-th sample, C be the regularization parameter, φ(·) be the kernel function mapping, i = 1, ..., N, where N is the number of samples, yi be the actual output of the i-th sample, and λ be the weighting parameter for the probability of accident occurrence, used to balance the influence of the probability of accident occurrence on the optimization objective.

4. The method for monitoring shear wall scaffolding based on intelligent algorithms according to claim 3, characterized in that, In step three, the Gaussian kernel function expression of the LSSVM model is as follows: Where x is the input variable, x i For the i-th sample, x j For the j-th sample, σ 2 This is the kernel width parameter.

5. The method for monitoring shear wall scaffolding based on intelligent algorithms according to claim 4, characterized in that, In step three, the particle swarm optimization algorithm is used to optimize the parameters of the LSSVM model. The update formula for the particle swarm optimization algorithm includes: In the formula, It is the velocity of particle i at time t. Let be the position of particle i at time t, z be the inertia weight, c1 and c2 be the learning factors, and r1 and r2 be random numbers between [0,1]. It is the optimal position of particle i. It is the optimal position for the group.

6. A shear wall external scaffolding monitoring system based on intelligent algorithms, characterized in that, include: The first main control module is used to build a monitoring system and to construct a sample dataset based on the monitoring data of the shear wall scaffolding collected by the monitoring system. The second main control module is used to input the sample dataset into the SD-MOP model to calculate the probability of accidents during the service life of the scaffolding; The third main control module is used to optimize and train the least squares support vector machine model based on the constraint conditions of the accident occurrence probability components, and using the constraint conditions as the objective function of the least squares support vector machine model, and using the key influencing parameters of the strength and stability of the scaffold as input variables, so as to obtain the optimal prediction model for monitoring the strength and stability of the scaffold. The monitoring system includes: Shear wall (1); Round steel (2), which is an L-shaped structure, with one end embedded in the shear wall (1) and the other end extending horizontally out of the shear wall (1); A telescopic connecting member, one end of which is connected to a round steel (2) that extends horizontally out of the shear wall (1), and the other end is connected to the scaffolding; Multiple rebar gauges are installed on the uprights of the scaffold to measure the axial force of the scaffold. Multiple settlement gauges are installed at the bottom of the scaffold to measure the settlement of the scaffold; The tilt angle measuring module is located between the telescopic connecting member and the scaffold and is used to measure the tilt angle of the scaffold. The tilt angle measuring module includes a cylindrical shell and a conical container inside the cylindrical shell. The container contains conductive liquid (9). An indicator light (7) is provided on the cylindrical shell. The negative terminal of the power supply (8) is connected to the terminal (11) at the bottom of the cylinder, and the positive terminal of the power supply (8) is connected to the terminal (10) on the side wall of the cylinder. Three terminals (10) at different heights are provided on the side wall. Each terminal has a different electronic component. When the scaffold upright tilts, the container will pour out conductive liquid, which forms a closed circuit through the terminals at both ends, thereby triggering the indicator light (7).

Images