System for supporting curtain wall construction hanging basket at light well to bear force by means of scaffold

Abstract

The invention relates to the technical field of building construction equipment, and discloses a supporting system for supporting a curtain wall construction hanging basket at a light well to be stressed through a scaffold. The system comprises a scaffold stress monitoring module, a hanging basket attitude calculation module, a supporting force distribution module, a structural deformation early warning module and a self-adaptive leveling module. The scaffold stress monitoring module collects and processes stress data; the hanging basket attitude resolving module generates a dynamic balance parameter; the supporting force distribution module optimizes a supporting force distribution path; the structural deformation early warning module predicts a deformation trend and outputs an early warning level; and the self-adaptive leveling module adjusts the hydraulic expansion amount of the scaffold supporting legs to calibrate the level of the hanging basket platform. All the modules work cooperatively, real-time monitoring and precise control over scaffold stress and hanging basket postures are achieved, construction safety can be effectively improved, construction precision and efficiency can be improved, and the system further has the self-adaptive adjustment capacity so as to adapt to the complex construction environment and meet the curtain wall construction requirement of a light well.

Description

Technical Field

[0001] The present invention relates to the technical field of construction equipment, and particularly to a support system for a curtain wall construction hanging basket relying on a scaffold for force bearing at a light well. Background Technique

[0002] In the field of construction, curtain wall construction at a light well is a complex and challenging task. With the diversification and complexity of modern building designs, the scale and structure of light wells have become increasingly complex, posing higher requirements for construction equipment and technologies. When carrying out curtain wall construction at a light well, construction workers need to rely on construction hanging baskets to complete tasks such as curtain wall installation, maintenance, and cleaning. However, there are many problems with existing support methods for construction hanging baskets.

[0003] Traditional support methods for construction hanging baskets are often relatively simple and direct, mostly by directly hanging the hanging basket on the building structure, such as the roof edge or pre-buried hanging points. When used at a light well, this method faces the problem of uneven structural stress. The building structures around the light well may have different load-bearing capacities and stiffnesses due to design or functional requirements. Directly hanging the hanging basket can easily cause some structures to bear excessive stress, increasing the risk of structural damage. For example, in areas where lightweight materials are used to construct the light well edge, long-term exposure to the concentrated load of the hanging basket may result in wall cracking, local deformation, etc., which not only affects construction safety but also may pose a threat to the overall structural stability of the building.

[0004] In addition, the existing support methods have weak control capabilities for the attitude of the hanging basket. During the construction process, the hanging basket is affected by various factors, such as wind force, the operation of construction workers, and the swaying of the hanging basket itself, resulting in unstable states such as tilting and swinging of the hanging basket. When the hanging basket is in an unstable state, it is difficult for construction workers to accurately carry out curtain wall construction operations, reducing construction efficiency and quality. For example, when installing curtain wall glass, the swaying of the hanging basket makes it difficult to accurately align the glass, increasing the installation difficulty and even possibly causing accidents such as glass breakage. Moreover, the instability of the hanging basket poses a direct threat to the safety of construction workers, increasing the likelihood of safety accidents such as high-altitude falls.

[0005] At the same time, the existing support system lacks a real-time monitoring and effective early warning mechanism for the operating status of scaffolding and hanging baskets. During the construction process, the safety status of scaffolding and hanging baskets is crucial. However, the traditional method cannot timely obtain the stress change of scaffolding nodes and the dynamic balance parameters of hanging baskets. Once problems such as structural deformation of the scaffolding, loosening of connectors, or abnormal swinging of the hanging basket occur, it is difficult to detect and take corresponding measures in time. Often, the problem is only noticed when it has developed to a more serious level, missing the best treatment opportunity, and thus triggering serious safety accidents. For example, a certain node of the scaffolding gradually loosens due to long-term stress, but due to the lack of real-time monitoring, the construction workers fail to detect it in time. As the loosening intensifies, it may eventually lead to partial collapse of the scaffolding.

[0006] In addition, during actual construction, the construction environment at the light well is complex and changeable. Different construction stages, weather conditions, and construction process requirements all require flexible adjustment of the support system. However, most of the existing support systems lack the ability of adaptive adjustment and are difficult to timely adjust the support force distribution, the attitude of the hanging basket, and the structural state of the scaffolding according to the actual situation, unable to meet the complex and changeable construction requirements, seriously restricting the construction progress and quality. In summary, it is of great practical significance to develop a support system for the hanging basket of curtain wall construction at the light well relying on the scaffolding to solve the above problems. Summary of the Invention

[0007] The purpose of the present invention is to provide a support system for the hanging basket of curtain wall construction at the light well relying on the scaffolding to solve the problems raised in the above background technology.

[0008] To achieve the above purpose, the present invention provides the following technical solutions: A support system for the hanging basket of curtain wall construction at the light well relying on the scaffolding, the system includes: A scaffolding stress monitoring module for collecting real-time stress data of scaffolding nodes through multi-source sensors. The multi-source sensors include a strain gauge array, an inclinometer, and a distributed pressure sensor, and perform noise separation and feature extraction on the stress data through a time-frequency analysis algorithm; A hanging basket attitude calculation module for combining the laser point cloud scanning results and the sling tension data to construct a kinematic constraint equation of the hanging basket, and generating dynamic balance parameters of the hanging basket through an adaptive filtering algorithm; A support force distribution module for generating an optimized distribution path of the support force of the scaffolding nodes through a dynamic programming algorithm according to the real-time stress data of the scaffolding nodes and the dynamic balance parameters of the hanging basket; A structural deformation early warning module for predicting the deformation trend of the scaffolding nodes and outputting an early warning level through a transfer learning model based on the optimized distribution path of the support force and the historical deformation data of the scaffolding; An adaptive leveling module, which is used to adjust the hydraulic telescopic amount of the scaffolding support feet according to the warning level and the dynamic balance parameters of the hanging basket, so as to realize the dynamic horizontal calibration of the hanging basket platform.

[0009] Preferably, the execution steps of the scaffolding stress monitoring module include: Perform wavelet packet decomposition on the output signals of the strain gauge array, extract the stress fluctuation components in different frequency bands, and construct a topological network of the stress transmission path according to the spatial distribution density of the distributed pressure sensors; Based on the topological network, perform non-linear interpolation on the stress fluctuation components to generate a three-dimensional stress field distribution map of the scaffolding nodes.

[0010] Preferably, the execution steps of the hanging basket attitude calculation module include: Perform Euler angle transformation on the laser point cloud scanning result to generate the initial pose matrix of the hanging basket suspension point; Fuse the time-domain integration result of the sling tension data and the initial pose matrix to construct a kinematic constraint equation of the hanging basket; Iteratively optimize the kinematic constraint equation by the sliding window least squares method, and output the dynamic balance parameters of the hanging basket.

[0011] Preferably, the execution steps of the support force distribution module further include: Construct a bearing capacity threshold model for the scaffolding nodes, including the yield strength of the node material, the upper limit of the connecting piece torque, and the foundation settlement tolerance; Input the optimized support force distribution path into the Monte Carlo simulator to generate a probability distribution heat map of the node forces, and perform dynamic shunting of the support forces on the nodes that exceed the bearing capacity threshold according to the probability distribution heat map.

[0012] Preferably, the execution steps of the structural deformation warning module further include: Perform time series slicing on the historical deformation data of the scaffolding to construct a time convolution kernel of the deformation characteristics; Perform correlation analysis on the time convolution kernel and the current deformation trend through a gated recurrent unit network to generate a predicted value of the deformation acceleration; Based on the predicted value of the deformation acceleration, divide the warning level threshold and trigger a hierarchical alarm signal.

[0013] Preferably, the scaffolding stress monitoring module further includes: introducing an adversarial generation network, where the generator is used to simulate the stress distribution under extreme load conditions, the discriminator is used to evaluate the distribution consistency between the measured stress data and the simulated data, and the parameters of the generator and the discriminator are optimized through the backpropagation algorithm.

[0014] Preferably, the execution steps of the hanging basket attitude calculation module further include: Construct a dynamic model of the hanging basket swing, including the elastic deformation coefficient of the suspension cable, the wind load disturbance factor, and the offset of the center of mass of the hanging basket; Input the dynamic balance parameters of the hanging basket into the dynamic model, and solve the boundary of the stable region of the hanging basket swing through the Hamiltonian optimization algorithm; Dynamically correct the weight coefficient of the kinematic constraint equation of the hanging basket according to the boundary of the stable region.

[0015] Preferably, the execution steps of the support force distribution module further include: introducing a dynamic load balancing module, predicting the spatio-temporal change trend of the hanging basket load during the construction process through a long short-term memory network, coupling and analyzing the spatio-temporal change trend with the optimal support force distribution path, and generating an adaptive reinforcement strategy for the scaffold nodes.

[0016] Preferably, the execution steps of the structural deformation warning module further include: constructing a multi-sensor data residual function, calculating the Mahalanobis distance between the historical deformation data and the real-time deformation data, and minimizing the residual function through a particle swarm optimization algorithm to output the confidence interval of the deformation prediction value.

[0017] Preferably, the execution steps of the adaptive leveling module further include: performing dead zone compensation on the adjustment process of the hydraulic telescopic amount, constructing an inverse model of the hysteresis of the hydraulic cylinder response, and designing a control law for the inverse model through the Lyapunov stability criterion.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: In terms of improving safety performance, the scaffold stress monitoring module collects real-time stress data of scaffold nodes through multi-source sensors such as strain gauge arrays, inclinometers, and distributed pressure sensors, and uses time-frequency analysis algorithms for noise separation and feature extraction to accurately grasp the stress state of the scaffold. By introducing a generative adversarial network to simulate the stress distribution under extreme load conditions, the discriminator evaluates the distribution consistency between the measured and simulated data, and then optimizes the parameters of the generator and the discriminator, making the monitoring of scaffold stress more comprehensive and accurate, discovering potential stress abnormal points in advance, and effectively avoiding scaffold collapse accidents caused by stress concentration. The structural deformation warning module is based on the optimal support force distribution path and the historical deformation data of the scaffold, predicts the deformation trend of the scaffold nodes through a transfer learning model and outputs the warning level. At the same time, it constructs a multi-sensor data residual function, calculates the Mahalanobis distance between the historical and real-time deformation data, and uses a particle swarm optimization algorithm to solve and output the confidence interval of the deformation prediction value, realizing accurate warning of the structural deformation of the scaffold and greatly improving the construction safety guarantee.

[0019] In order to improve the construction accuracy and efficiency, the hanging basket posture solution module combines the laser point cloud scanning results and the cable tension data to construct the kinematic constraint equation of the hanging basket, and generates the dynamic balance parameters of the hanging basket through the adaptive filtering algorithm to ensure that the hanging basket always maintains a stable posture during the construction process. The hanging basket swing dynamics model is constructed to solve the stable domain boundary of the hanging basket swing, and the weight coefficient of the kinematic constraint equation is dynamically corrected to further improve the accuracy of the hanging basket posture control. This enables construction personnel to perform curtain wall construction operations more accurately on a stable hanging basket platform, reduce construction errors caused by hanging basket shaking, and thus improve construction quality and efficiency. The support force distribution module generates the support force optimization distribution path of the scaffolding node through the dynamic programming algorithm according to the real-time stress data of the scaffolding node and the dynamic balance parameters of the hanging basket, reasonably distributes the support force, avoids excessive pressure on local nodes, ensures the overall stability of the scaffolding, and provides a solid foundation for the smooth progress of construction. At the same time, the dynamic load balancing module is introduced to predict the temporal and spatial variation trend of the hanging basket load during the construction process, and generates an adaptive reinforcement strategy by coupling analysis with the support force optimization distribution path, which further improves the stability and reliability of the construction process.

[0020] In terms of adaptive adjustment capability, the adaptive leveling module adjusts the hydraulic expansion and contraction of the scaffolding support legs through the fuzzy control algorithm according to the warning level and the dynamic balance parameters of the hanging basket, thus realizing the dynamic horizontal calibration of the hanging basket platform. Dead zone compensation is performed on the adjustment process of the hydraulic expansion and contraction, an inverse model of the hydraulic cylinder response hysteresis is constructed, and the control law is designed through the Lyapunov stability criterion to ensure the accuracy and stability of the adaptive leveling process. When encountering changes in the construction environment, such as changes in wind force and changes in the position of construction personnel, the system can respond quickly and automatically adjust the posture of the hanging basket and the support force of the scaffolding to adapt to complex and changeable construction needs, reduce manual intervention, and improve the level of automation in construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a working principle diagram of the support system of the curtain wall construction hanging basket at the light well according to the present invention, which relies on the scaffolding to bear the force; Figure 2 Flowchart for extracting steady-state physiological features for the adaptive filtering algorithm; Figure 3 It is the workflow diagram of multi-dimensional decision model-feature fusion layer; Figure 4 This is a flow chart for the hierarchical processing of scaffolding deformation warning. DETAILED DESCRIPTION

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] Please refer to Figures 1-4 , the present invention provides a support system for the force-bearing of the curtain wall construction hanging basket relying on the scaffolding at the light well, and its specific implementation manners will be elaborated in detail below.

[0024] Scaffold stress monitoring module: This module collects real-time stress data of the scaffold nodes through multi-source sensors such as strain gauge arrays, inclinometers, and distributed pressure sensors. These sensors are reasonably installed at the key node positions of the scaffold and can accurately obtain stress information. After collecting the data, time-frequency analysis algorithms are used to separate noise and extract features from the stress data, removing interference signals and highlighting effective stress features, providing a reliable data basis for subsequent analysis.

[0025] Hanging basket attitude solution module: Combining the laser point cloud scanning results and the sling tension data, a kinematic constraint equation of the hanging basket is constructed, and the dynamic balance parameters of the hanging basket are generated through an adaptive filtering algorithm. Multi-dimensional pose data, laser point cloud scanning results, and sling tension data reflect the state of the hanging basket from different angles. By fusing these data through an adaptive filtering algorithm, the parameters required for the dynamic balance of the hanging basket can be accurately calculated to maintain the stability of the hanging basket during construction.

[0026] Support force distribution module: According to the real-time stress data of the scaffold nodes and the dynamic balance parameters of the hanging basket, an optimal distribution path of the support force of the scaffold nodes is generated through a dynamic programming algorithm. The dynamic programming algorithm will comprehensively consider the bearing capacity of each node, the current stress state, and the balance requirements of the hanging basket, and calculate the most reasonable support force distribution scheme to ensure that the forces on each node of the scaffold are uniform and within a safe range.

[0027] Structural deformation warning module: Based on the optimal support force distribution path and the historical deformation data of the scaffold, a migration learning model is used to predict the deformation trend of the scaffold nodes and output a warning level. The migration learning model can draw on the deformation data and experience of similar scaffold structures in the past, combined with the current support force distribution situation, to accurately predict the deformation trend of the nodes. Different warning levels are divided according to the prediction results to take corresponding measures in a timely manner to ensure construction safety.

[0028] Adaptive leveling module: According to the warning level and the dynamic balance parameters of the hanging basket, the hydraulic telescopic amount of the scaffold support feet is adjusted through a fuzzy control algorithm to achieve the dynamic horizontal calibration of the hanging basket platform. The fuzzy control algorithm intelligently controls the hydraulic telescopic amount according to the changes in the warning level and the dynamic balance parameters of the hanging basket, so that the hanging basket platform always maintains a horizontal state, providing a stable working platform for construction workers.

[0029] The present invention will be further described below in conjunction with Embodiments 1 to 5: Embodiment 1

[0030] This embodiment mainly relates to more detailed implementation steps of the scaffold stress monitoring module.

[0031] In actual construction, the strain gauge array is accurately pasted on the key stress-bearing parts of the scaffold nodes. Its output signal contains rich stress information, but inevitably contains various noises. At this time, wavelet packet decomposition is performed on the output signal of the strain gauge array, and wavelet packet decomposition can decompose the signal into different frequency bands. Let the output signal of the strain gauge array be , after wavelet packet decomposition, stress fluctuation components in different frequency bands are obtained ( , is the number of frequency bands obtained by decomposition).

[0032] According to the spatial distribution density of the distributed pressure sensors, a topological network of the stress transmission path is constructed. The distributed pressure sensors are distributed at different positions of the scaffold, and their distribution density reflects the importance of stress transmission in different regions. By analyzing the positions and measurement data of these sensors, the stress transmission path in the scaffold structure is determined and constructed into a topological network, which clearly shows the propagation relationship of stress between the scaffold nodes.

[0033] Based on the topological network, non-linear interpolation is performed on the stress fluctuation components. On the basis of the constructed topological network, due to the certain discreteness of the stress fluctuation components in space, in order to obtain a more continuous and accurate stress distribution, a non-linear interpolation method is adopted. Through this method, a three-dimensional stress field distribution map of the scaffold nodes is generated, which intuitively shows the stress magnitude and distribution of each scaffold node in a three-dimensional form, facilitating construction workers and managers to understand the stress state of the scaffold in real time, timely discover potential stress concentration areas, and provide strong support for ensuring the safety and stability of the scaffold.

[0034] Meanwhile, the scaffolding stress monitoring module also introduces a generative adversarial network. The generator is used to simulate the stress distribution under extreme load conditions. During actual construction, although the scaffolding is under normal load for most of the time, extreme situations such as strong winds and sudden drops of heavy objects may also occur. The generator simulates the stress distribution under these extreme load conditions, and let the simulated stress distribution data be . The discriminator is used to evaluate the measured stress data and the simulated data for distribution consistency. By calculating the difference between the two, indicators such as the Kullback-Leibler Divergence are used to measure. Through the backpropagation algorithm, the parameters of the generator and the discriminator are optimized, so that the generator can more accurately simulate the stress distribution under extreme loads, and the discriminator can more precisely evaluate the difference between the simulated data and the measured data, thereby improving the accuracy and reliability of scaffolding stress monitoring and discovering potential safety hazards in advance.

[0035] Example 2

[0036] This example focuses on the more in-depth implementation steps of the hanging basket attitude solution module.

[0037] After obtaining the laser point cloud scan results, perform Euler angle transformation on the laser point cloud scan results. Laser point cloud scanning can obtain the spatial information around the hanging point of the hanging basket, but this information needs to be converted into a pose matrix form that is convenient for analysis. Let the laser point cloud scan results be represented as a point set , and after Euler angle transformation, generate the initial pose matrix of the hanging point of the hanging basket. Euler angle transformation converts the point cloud data to a suitable coordinate system through rotation operations around different coordinate axes, thereby determining the initial position and attitude of the hanging point of the hanging basket.

[0038] Fuse the time-domain integration result of the sling tension data and the initial pose matrix to construct a kinematic constraint equation for the hanging basket. The sling tension data changes with time, and its time-domain integration is performed. Let the sling tension be , and its time-domain integration result is . Combine this integration result with the initial pose matrix , and considering the motion law and mechanical characteristics of the hanging basket, construct a kinematic constraint equation for the hanging basket. This equation describes the mutual relationship between the parameters of the hanging basket during the motion process, providing an important basis for accurately calculating the dynamic balance parameters of the hanging basket in the future.

[0039] Iteratively optimize the kinematic constraint equation by the sliding window least squares method, and output the dynamic balance parameters of the hanging basket. The sliding window least squares method is an optimization method commonly used in time series data processing. In this embodiment, as time goes by, new measurement data is continuously generated. The sliding window least squares method performs least squares fitting on the data within a fixed-length time window, and continuously adjusts the parameters in the equation, so that the kinematic constraint equation can more accurately reflect the actual motion state of the hanging basket. After multiple iterative optimizations, accurate dynamic balance parameters of the hanging basket are finally output, such as the horizontal offset and tilt angle of the hanging basket. These parameters are crucial for ensuring the stability of the hanging basket during construction.

[0040] In addition, construct a swinging dynamics model of the hanging basket, which includes the elastic deformation coefficient of the suspension cable , the wind load disturbance factor and the centroid offset of the hanging basket . The elastic deformation coefficient of the suspension cable reflects the elastic deformation characteristics of the suspension cable when it is stressed. The wind load disturbance factor reflects the influence degree of the wind on the swinging of the hanging basket. The centroid offset of the hanging basket describes the deviation of the centroid of the hanging basket from the ideal position.

[0041] Input the dynamic balance parameters of the hanging basket into the dynamics model, and solve the boundary of the stable region of the hanging basket swing through the Hamiltonian optimization algorithm. The Hamiltonian optimization algorithm is an optimization method based on the energy principle. In this embodiment, it calculates the boundary of the stable region of the hanging basket swing by analyzing the energy change during the swinging of the hanging basket and combining the dynamic balance parameters of the hanging basket. This stable region boundary determines the range within which the hanging basket can swing stably under different conditions.

[0042] Dynamically correct the weight coefficient of the kinematic constraint equation of the hanging basket according to the stable region boundary. After determining the stable region boundary, adjust the weight coefficient of the kinematic constraint equation of the hanging basket according to the boundary situation. For example, if it is found that the hanging basket is close to the stable region boundary, appropriately increase the weight of the parameters related to stability, so that the kinematic constraint equation pays more attention to maintaining the stability of the hanging basket, thereby further improving the accuracy and stability of the hanging basket attitude solution and ensuring construction safety.

[0043] Embodiment 3

[0044] This embodiment elaborates in detail the further execution steps of the support force distribution module.

[0045] First, construct a bearing capacity threshold model for the scaffolding nodes, which includes the yield strength of the node material , the upper limit of the torque of the connecting piece and the foundation settlement tolerance Yield strength of the node material It refers to the stress value when the node material begins to undergo plastic deformation, and it is one of the important indicators to measure the bearing capacity of the node. Upper limit of the torque of the connector Determines the maximum torque that the connector can withstand on the premise of ensuring a firm connection. Exceeding this upper limit, the connector may become loose or even fail. Tolerance of foundation settlement Specifies the maximum allowable settlement of the foundation. Once the foundation settlement exceeds this tolerance, it may cause the overall structure of the scaffolding to become unstable.

[0046] Input the optimized distribution path of the support force into the Monte Carlo simulator to generate a probability distribution heat map of the forces on the nodes. The Monte Carlo simulator is a simulation tool based on probability statistics. In this embodiment, the optimized distribution path of the support force is used as the input, and through a large number of random simulation calculations, the probability distribution of the forces on each node under different conditions is obtained. These probability distributions are presented in the form of a heat map, where the darker the color, the greater the probability that the force on the node exceeds a certain threshold. Construction workers and managers can intuitively see from the heat map which nodes have a greater risk of excessive force.

[0047] Dynamically divert the support force for the nodes that exceed the bearing capacity threshold according to the probability distribution heat map. When it is found from the heat map that the force on certain nodes exceeds their bearing capacity threshold, timely measures are taken to dynamically divert the support force. For example, for a certain node, its actual force exceeds the bearing capacity threshold determined by the comprehensive consideration of the yield strength of the node material, the upper limit of the torque of the connector, and the tolerance of foundation settlement , by adjusting the distribution of the support force of the surrounding nodes, part of the force is transferred to the nodes with surplus bearing capacity to ensure that the force on each node is within the safe range and guarantee the overall stability of the scaffolding.

[0048] At the same time, the support force distribution module introduces a dynamic load balancing module to predict the spatio-temporal change trend of the hanging basket load during the construction process through a long short-term memory network. The long short-term memory network (LSTM) is a special type of recurrent neural network that can effectively handle the long-term dependence problem in time series data. In this embodiment, the LSTM network learns the historical hanging basket load data and relevant information such as construction time and location, and predicts the change trend of the hanging basket load at different time and space positions during the construction process. Let the predicted load change trend be where represents time, represents the spatial position.

[0049] The spatio-temporal change trend Perform a coupling analysis with the optimized load-bearing force distribution path to generate an adaptive reinforcement strategy for the scaffold nodes. By comparing the predicted load change trend and the current optimized load-bearing force distribution path, determine which nodes may bear a large load in the future. For these nodes, formulate corresponding adaptive reinforcement strategies, such as adding support structures, replacing connectors with higher strength, etc., and take preventive measures in advance to ensure that the scaffold can safely and stably withstand the load changes of the hanging basket during construction.

[0050] Example 4

[0051] This embodiment focuses on describing the more detailed implementation steps of the structural deformation warning module.

[0052] Perform time series slicing on the historical deformation data of the scaffold to construct a time convolution kernel for deformation features. The historical deformation data of the scaffold accumulates over time and reflects the deformation conditions of the scaffold at different stages. Through time series slicing, the historical deformation data is divided at a certain time interval, and let the time interval be , to obtain a series of time segment data. Then, construct a time convolution kernel for deformation features based on the data of these time segments. The time convolution kernel can extract the features of the deformation data in the time dimension, such as the trend of deformation, the frequency of change, etc.

[0053] Perform a correlation analysis on the time convolution kernel and the current deformation trend through a gated recurrent unit network to generate a predicted value of deformation acceleration. The gated recurrent unit network (GRU) is a neural network that can effectively handle the problems of information transmission and forgetting in time series data. In this embodiment, the GRU network combines the historical deformation features contained in the time convolution kernel with the current deformation trend for in-depth correlation analysis. Through this analysis, the deformation acceleration of the scaffold nodes is predicted, and let the predicted deformation acceleration be . The deformation acceleration reflects the change of the node deformation speed and is of great significance for judging the stability of the scaffold.

[0054] Based on the predicted value of deformation acceleration, divide the warning level threshold and trigger a graded alarm signal. According to actual engineering experience and safety standards, set different deformation acceleration thresholds to divide the warning levels. For example, when the deformation acceleration is less than the first threshold , it is in a safe state; when is greater than or equal to and less than the second threshold , a yellow warning is issued; when is greater than or equal to When the time comes, a red warning is issued. Once the predicted deformation acceleration reaches the corresponding threshold, the hierarchical alarm signal is immediately triggered to remind the construction workers and management personnel to take corresponding measures, such as stopping construction, inspecting and strengthening the scaffolding, etc., to ensure construction safety.

[0055] In addition, a multi-sensor data residual function is constructed to calculate the Mahalanobis distance between the historical deformation data and the real-time deformation data. Let the historical deformation data be , and the real-time deformation data be , the multi-sensor data residual function be , and the Mahalanobis distance be . The Mahalanobis distance can consider the covariance information of the data and more accurately measure the degree of difference between two sets of data. By calculating the Mahalanobis distance, the deviation of the real-time deformation data from the historical data can be judged.

[0056] The residual function is minimized by the particle swarm optimization algorithm, and the confidence interval of the deformation prediction value is output. The particle swarm optimization algorithm (PSO) is an optimization algorithm based on swarm intelligence. In this embodiment, the PSO algorithm continuously adjusts the positions and velocities of the particles to find the parameter combination that minimizes the residual function. After multiple iterative optimizations, the confidence interval of the deformation prediction value is obtained. The confidence interval reflects the reliability of the deformation prediction value, and the construction workers and management personnel can more accurately evaluate the deformation of the scaffolding according to the confidence interval and formulate more reasonable safety measures.

[0057] Embodiment 5

[0058] This embodiment focuses on the in-depth execution steps of the adaptive leveling module. In the adaptive leveling module, the hydraulic telescopic amount of the scaffolding support feet is adjusted according to the warning level and the dynamic balance parameters of the hanging basket. It is crucial to implement dead zone compensation for the adjustment of the hydraulic telescopic amount in this process.

[0059] When the hydraulic system operates, due to factors such as the friction between mechanical components and the viscosity of the hydraulic oil, there is a dead zone phenomenon. When the input signal varies within a specific range, the hydraulic cylinder will not respond immediately, which will affect the leveling accuracy of the hanging basket platform. To solve this problem, an inverse model of the hydraulic cylinder response hysteresis is constructed. Let the control signal input to the hydraulic cylinder be , the hydraulic telescopic amount output by the hydraulic cylinder be , in actual situations, the response relationship of the hydraulic cylinder can be expressed as a complex non-linear function , but there is a dead zone effect. The constructed inverse model , whose purpose is to reverse-derive the input control signal that can eliminate the dead zone effect by performing reverse derivation on the output hydraulic telescopic amount For example, within the dead zone, the input signal in the forward model may change but the output has no response, while the inverse model can calculate an appropriate input signal based on the desired output quantity to compensate for the deviation caused by the dead zone.

[0060] The control law of the inverse model is designed through the Lyapunov stability criterion to ensure the stability of the entire system. The Lyapunov stability criterion is a powerful tool for analyzing the stability of dynamic systems. Define the Lyapunov function as , which is a function of the system state variables (here the hydraulic telescopic amount ), and satisfies ( ), . Take the derivative of with respect to time , and when designing the control law, it is necessary to make . This means that as time goes by, the value of the Lyapunov function continuously decreases, and the energy of the system gradually reduces, thus ensuring the stability of the system.

[0061] In actual operation, first judge the safety status of the scaffolding and the hanging basket according to the early warning level. If the early warning level indicates a certain risk, combined with the dynamic balance parameters of the hanging basket, determine the hydraulic telescopic amount that needs to be adjusted. Calculate the input control signal considering dead zone compensation through the inverse model , and then adjust and optimize the input signal according to the control law designed based on the Lyapunov stability criterion. For example, if it is detected that the hanging basket tilts to one side, determine the hydraulic telescopic amount that needs to be increased or decreased for some support feet according to the degree of tilt (provided by the dynamic balance parameters of the hanging basket). Calculate the preliminary control signal through the inverse model, and then fine-tune the signal using the Lyapunov stability criterion to ensure that during the adjustment process, the hydraulic system operates stably without oscillation or out-of-control situations. After such processing, accurately control the hydraulic telescopic amount of the scaffolding support feet to achieve high-precision dynamic horizontal calibration of the hanging basket platform, creating a safe and stable working environment for curtain wall construction workers and improving construction efficiency and quality.

[0062] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.​

[0063] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A supporting system for a construction hanging basket of a curtain wall at a light well relying on a scaffold for force bearing, characterized in that including: A scaffolding stress monitoring module, which is used to collect real-time stress data of scaffolding nodes through multi-source sensors. The multi-source sensors include a strain gauge array, an inclinometer, and a distributed pressure sensor, and perform noise separation and feature extraction on the stress data through a time-frequency analysis algorithm; A hanging basket attitude solution module, which is used to combine the laser point cloud scanning results and the sling tension data to construct a kinematic constraint equation of the hanging basket, and generate dynamic balance parameters of the hanging basket through an adaptive filtering algorithm; A support force distribution module, which is used to generate an optimized distribution path of the support force of the scaffolding nodes through a dynamic programming algorithm according to the real-time stress data of the scaffolding nodes and the dynamic balance parameters of the hanging basket; A structural deformation warning module, which is used to predict the deformation trend of the scaffolding nodes based on the optimized support force distribution path and the historical deformation data of the scaffolding, and output a warning level through a transfer learning model; An adaptive leveling module, which is used to adjust the hydraulic expansion amount of the scaffolding support feet through a fuzzy control algorithm according to the warning level and the dynamic balance parameters of the hanging basket, so as to realize the dynamic horizontal calibration of the hanging basket platform.

2. The support system according to claim 1, characterized in that, The execution steps of the scaffolding stress monitoring module include: Perform wavelet packet decomposition on the output signal of the strain gauge array, extract stress fluctuation components in different frequency bands, and construct a topological network of the stress transfer path according to the spatial distribution density of the distributed pressure sensor; Perform non-linear interpolation on the stress fluctuation components based on the topological network to generate a three-dimensional stress field distribution map of the scaffolding nodes.

3. The support system according to claim 1, characterized in that, The execution steps of the hanging basket attitude solution module include: Perform Euler angle transformation on the laser point cloud scanning results to generate an initial pose matrix of the hanging basket suspension point; Fuse the time-domain integration result of the sling tension data and the initial pose matrix to construct a kinematic constraint equation of the hanging basket; Iteratively optimize the kinematic constraint equation through the sliding window least squares method, and output the dynamic balance parameters of the hanging basket.

4. The support system according to claim 1, wherein The execution steps of the support force distribution module further include: Construct a bearing capacity threshold model of the scaffolding nodes, including the yield strength of the node material, the upper limit of the connecting piece torque, and the foundation settlement tolerance; Input the optimized support force distribution path into the Monte Carlo simulator to generate a probability distribution heat map of the node forces, and dynamically shunt the support forces of the nodes exceeding the bearing capacity threshold according to the probability distribution heat map.

5. The support system according to claim 1, characterized in that, The execution steps of the structural deformation warning module further include: Perform time series slicing on the historical deformation data of the scaffolding to construct a time convolution kernel of the deformation features; Perform correlation analysis on the time convolution kernel and the current deformation trend through a gated recurrent unit network to generate a deformation acceleration prediction value; Divide the warning level threshold based on the deformation acceleration prediction value and trigger a hierarchical alarm signal.

6. The support system according to claim 2, wherein The scaffolding stress monitoring module further includes: introducing a generative adversarial network, where the generator is used to simulate the stress distribution under extreme load conditions, the discriminator is used to evaluate the distribution consistency between the measured stress data and the simulated data, and the parameters of the generator and the discriminator are optimized through the backpropagation algorithm.

7. The support system according to claim 3, wherein The execution steps of the hanging basket attitude solution module further include: Build a dynamic model of the hanging basket swing, including the elastic deformation coefficient of the sling, the wind load disturbance factor, and the centroid offset of the hanging basket; Input the dynamic balance parameters of the hanging basket into the dynamic model, and solve the boundary of the stable region of the hanging basket swing through the Hamiltonian optimization algorithm; Dynamically correct the weight coefficient of the kinematic constraint equation of the hanging basket according to the boundary of the stable region.

8. The support system according to claim 4, wherein The execution steps of the support force distribution module further include: introducing a dynamic load balancing module, predicting the spatio-temporal change trend of the hanging basket load during the construction process through a long short-term memory network, coupling and analyzing the spatio-temporal change trend with the support force optimized distribution path, and generating an adaptive reinforcement strategy for the scaffolding nodes.

9. The support system according to claim 5, characterized in that, The execution steps of the structural deformation warning module further include: constructing a multi-sensor data residual function, calculating the Mahalanobis distance between the historical deformation data and the real-time deformation data, minimizing the residual function through a particle swarm optimization algorithm, and outputting the confidence interval of the deformation prediction value.

10. The support system according to claim 1, characterized in that, The execution steps of the adaptive leveling module further include: performing dead zone compensation on the adjustment process of the hydraulic telescopic amount, constructing an inverse model of the hysteresis of the hydraulic cylinder response, and designing a control law for the inverse model through the Lyapunov stability criterion.

Images