Optimization method of protective structure of frame house under landslide induced by building on slope

Abstract

The application discloses a method for optimizing a protective structure of a frame house under the action of a landslide induced by building on a cutting slope, and comprises the following steps: collecting and pre-processing multi-source space-time data of a house rear slope and a rear wall; dividing a sliding window and extracting features to obtain partition state parameters; establishing a Bayesian network model to infer the risk probability of each partition structure; optimizing the partition, window and reinforcing rib layout according to the risk probability distribution, forming a construction scheme and implementing the construction scheme; and continuously monitoring in the operation stage and periodically inputting data to dynamically optimize the structure parameters. Through the fusion of multi-source space-time data analysis and Bayesian network inference, the dynamic optimization and the resilience adaptive regulation and control of the protective structure of the frame house rear wall under the influence of the landslide are realized.

Description

Technical Field

[0001] This invention relates to the field of civil engineering and structural safety protection technology, and in particular to a method for optimizing the protective structure of frame houses under landslides induced by slope cutting construction. Background Technology

[0002] With the advancement of mountain development and construction, slope-cutting construction has become widely adopted in hilly and mountainous areas, significantly increasing the risk of geological disasters such as landslides. Existing building protection structures are mostly based on traditional static design and experience-based reinforcement measures, generally employing uniform zoning and conventional reinforcement arrangements. In engineering practice, rear wall protection structures often fail to dynamically analyze multi-source spatiotemporal monitoring data, including spatial zoning state parameters, soil deformation characteristics, rainfall, and geological factors. Structural design struggles to account for the differences in zonal risks and the complex stress changes induced by landslides. Traditional landslide risk assessment methods largely rely on single physical quantities or empirical thresholds, failing to cover the synergistic effects of multiple parameters such as surface deformation, strain, stress, and soil moisture content, and also failing to describe the probability distribution relationship between the expansion of local damage and overall failure between spatial zoning areas.

[0003] Existing structural protection optimization methods lack a closed-loop system for real-time monitoring and dynamic reasoning of zonal risks. During the building's operational phase, protective designs often cannot adjust key parameters such as spatial zoning, window sizes, and reinforcement placement based on monitoring data. Most protective structures become permanently fixed after construction, failing to achieve subsequent adaptive zoning adjustments and structural resilience optimization. Under extreme rainfall or geological disasters, these structures are prone to localized damage and even overall failure. The inability to effectively integrate multi-source monitoring information limits both structural safety and disaster resistance. Current technologies have significant shortcomings in comprehensive zonal risk identification, dynamic multi-parameter fusion, and adaptive structural optimization.

[0004] Therefore, how to provide an optimized method for the protective structure of frame houses under the influence of landslides induced by slope cutting is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] One objective of this invention is to propose an optimization method for the protective structure of frame houses under landslide-induced conditions caused by slope-cutting construction. This invention collects and processes multi-source spatiotemporal monitoring data, extracts state characteristic parameters of each spatial partition of the rear wall using a sliding window transformer, and combines a Bayesian network model to achieve intelligent reasoning and joint assessment of the structural risk probability of spatial partitions. This allows for the optimization design of structural parameters such as spatial partitions, window sizes, and stiffener placement. Furthermore, during the building's operation, periodic updates of monitoring data enable adaptive optimization of the structural protection parameters' resilience. This invention possesses advantages such as multi-source information fusion, accurate risk assessment of partitions, and adaptive structural optimization, thereby improving the safety, durability, and disaster prevention capabilities of building structures in slope-cutting construction scenarios.

[0006] The method for optimizing the protective structure of frame houses under landslide-induced effects induced by slope-cutting construction according to an embodiment of the present invention includes:

[0007] Multi-source spatiotemporal datasets of the rear slope and rear wall area of ​​the house were collected, and the multi-source spatiotemporal datasets were preprocessed to generate standardized multi-source spatiotemporal datasets.

[0008] The standardized multi-source spatiotemporal dataset is divided into sliding windows according to the preset spatial step and time step. The sliding window transformer is used to extract features from the data in each window to obtain the state feature parameters of each spatial partition.

[0009] Using the state feature parameters of each spatial partition as node variables, a Bayesian network model is established. The state feature parameters are input to perform conditional probability inference to obtain the structural risk probability distribution of each spatial partition of the rear wall.

[0010] Based on the structural risk probability distribution, the structural zoning, window size and reinforcement arrangement of the rear wall protection structure are optimized. A grid-shaped embedded column-beam structure is set up in the rear wall to realize the spatial zoning of the wall. Small-sized lighting windows are set in the upper two zoning zones of the grid-shaped structure, and closed walls or reinforcements are set in the remaining zones. The structure is constructed according to the optimized design, and the structural zoning, window size and reinforcement arrangement are implemented in the construction drawings and on site.

[0011] During the building's operation phase, the state characteristic parameters of the rear wall zones are continuously monitored. New monitoring data are periodically input into a sliding window transformer and a Bayesian network model to dynamically update the parameters, thereby achieving adaptive optimization of the building's protective structure's resilience.

[0012] Optionally, the multi-source spatiotemporal dataset specifically includes topographic and geological parameters, rainfall duration, soil moisture content, wall stress parameters, and structural layout information of the area behind the house's back slope and back wall.

[0013] Optionally, the preprocessing of the multi-source spatiotemporal dataset specifically includes format unification, missing value imputation, outlier removal, and data standardization of the multi-source spatiotemporal dataset.

[0014] Optionally, obtaining the state characteristic parameters of each spatial partition includes:

[0015] For each spatial partition and time interval in the standardized multi-source spatiotemporal dataset, the rate of change of four monitoring parameters—surface deformation, strain, stress, and soil moisture content—in the continuous time interval is calculated. The rate of change of the four monitoring parameters is then weighted and fused according to the importance weights of surface deformation, strain, stress, and soil moisture content to obtain the joint change perception index corresponding to each spatial partition and time interval. This determines whether there are sudden extreme changes among the four monitoring parameters—surface deformation, strain, stress, and soil moisture content—and obtains the sudden change monitoring results corresponding to each spatial partition and time interval.

[0016] Based on the joint change perception index and the sudden change monitoring results, each spatial partition and each time interval is adaptively divided into sliding windows. When the joint change perception index is higher than the preset threshold or the sudden change monitoring result is positive, the spatial partition and time interval are divided into sliding windows using the first spatial window size and the first time window step size to obtain the first type of sliding window. When the joint change perception index is lower than or equal to the preset threshold and the sudden change monitoring result is negative, the spatial partition and time interval are divided into sliding windows using the second spatial window size and the second time window step size to obtain the second type of sliding window. The first spatial window size and the first time window step size are preset fine-grained parameters, and the second spatial window size and the second time window step size are preset wide-scale parameters. According to the principles of spatial location continuity and temporal series continuity, all sliding window pairs that are directly adjacent in space or time are identified, and an adjacent sliding window set is established.

[0017] For the first type of sliding window and the second type of sliding window, global statistical features, local extreme value features, rate of change features and segmented interval features are extracted within the sliding window according to spatial scale and time scale, respectively, to generate multi-scale feature subsets;

[0018] The extracted global statistical features, local extreme value features, rate of change features, and segmented interval features are concatenated and weighted to generate a multi-scale feature vector for each sliding window.

[0019] For each pair of sliding windows that are directly adjacent in space or time in the adjacent sliding window set, a sliding window overlap strategy is executed. While maintaining the original window boundary sequence, the boundaries between adjacent sliding windows are extended inward according to the set overlap length, forming a set of sliding window pairs with data overlap areas in spatial location or time series.

[0020] For the overlapping region data corresponding to each pair of sliding windows in the set of sliding window pairs, the trend of the overlapping region data is used to extrapolate the multi-scale feature vector of the sliding window boundary. The multi-scale feature vector generated by the trend extrapolation is fused with the multi-scale feature vector of the original overlapping region using Bayesian smoothing weighting to obtain the multi-scale feature vector after boundary continuity processing and anomaly correction. If feature mutations or abnormal residuals occur in the overlapping region data, the residual correction method is used to correct the multi-scale feature vector after boundary continuity processing and anomaly correction, as well as the multi-scale feature vector of the corresponding adjacent sliding window.

[0021] By summing the multi-scale feature vectors with the multi-scale feature vectors after boundary continuity processing and anomaly correction, multi-dimensional state feature parameters corresponding to each spatial partition and each time interval are generated, and the state feature parameters of each spatial partition are obtained.

[0022] Optionally, obtaining the structural risk probability distribution of each spatial partition of the rear wall includes:

[0023] The state characteristic parameters of each spatial partition are used as candidate node variables. Based on the spatial distribution characteristics and changing trends of the state characteristic parameters, the spatial partition node structure is dynamically divided to determine the spatial partition node set.

[0024] For a given set of spatial partition nodes, based on the abnormal changes in state characteristic parameters and the differences in risk distribution, spatial partition nodes with state mutations are subdivided into multiple spatial partition sub-nodes, and spatial partition nodes with highly correlated states or balanced risks are merged into a single spatial partition node to obtain a set of spatial partition nodes.

[0025] Using each spatial partition node in the spatial partition node set as the input node, and four types of monitoring parameters—surface deformation, strain, stress, and soil moisture content—as external disaster-causing factor nodes, a multi-layer Bayesian network model structure containing spatial partition nodes, external disaster-causing factor nodes, and overall structural influence nodes is pre-set in the multi-layer Bayesian network model structure as the output node for the overall structural failure probability.

[0026] For each node in the multi-layer Bayesian network model structure, based on historical monitoring data, real-time collected data and external disaster-causing environmental data, the conditional probability distribution of each node is updated regularly to form a set of conditional probability tables driven by multi-source data.

[0027] Input the state feature parameters of each spatial partition node in the set of conditional probability tables and the set of spatial partition nodes. Using the Bayesian inference method, find the corresponding combination of state parameters in the conditional probability table and read the conditional probability of local destruction of the spatial partition node under the combination of state parameters. If there are multiple parent nodes or multiple observation information, then according to the probability propagation mechanism, the probability weighting and normalization of the state of all parent nodes are performed in turn to obtain the local destruction probability of each spatial partition node under the current observation information.

[0028] For the local damage probability of each spatial partition node in the spatial partition node set, a probabilistic joint inference function is used to calculate the overall structural failure probability of the node affected by the overall structure.

[0029] Based on the multi-layer Bayesian network model structure and the local destruction probability of each spatial partition node in the spatial partition node set, the correlation between spatial partition nodes is analyzed. Network edge connections are established between spatial partition nodes with significant correlation, and network edge connections between spatial partition nodes with low correlation are deleted to obtain the dynamically adjusted Bayesian network model structure.

[0030] The system outputs the local failure probability of each spatial partition node in the set of spatial partition nodes, the overall structural failure probability of the nodes affected by the overall structure, and the structural risk probability distribution corresponding to the dynamically adjusted Bayesian network model structure, thereby obtaining the structural risk probability distribution of each spatial partition of the rear wall.

[0031] Optionally, based on the structural risk probability distribution, the structural zoning, window sizes, and reinforcement arrangement of the rear wall protective structure are optimized. A grid-shaped embedded column-beam structure is established in the rear wall to achieve spatial zoning of the wall. Small-sized skylights are installed in the upper two zones of the grid-shaped structure, while the remaining zones are enclosed walls or reinforced with ribs. The structure is constructed according to the optimized design, and the structural zoning, window sizes, and reinforcement arrangement are implemented in the construction drawings and on-site implementation, including:

[0032] Based on the structural risk probability distribution of each spatial partition, and combined with the spatial partition parameters, window size parameters and stiffener arrangement parameters of the rear wall structure, a structural protection optimization objective function is established.

[0033] Based on the structural protection optimization objective function, the spatial partition parameters, window size parameters, and stiffener arrangement parameters are constrained and optimized. During the optimization process, the allowable range and design constraints of the number and size of spatial partitions, window size and location, and stiffener arrangement are limited according to structural design specifications and safety standards. Under the premise that all constraints are met, the optimal spatial partition scheme, optimal window size scheme, and optimal stiffener arrangement scheme with the lowest structural risk probability and reasonable structural protection cost are determined.

[0034] The optimal space zoning scheme is applied to the rear wall structure. A grid-shaped embedded column-beam structure is set up in the rear wall structure to divide the rear wall space into zones. The number and size of the space zones are determined according to the optimal space zoning scheme.

[0035] The optimal window size scheme is applied to the spatial partitioning of the rear wall structure. Lighting windows are set in the upper spatial partition of the grid-shaped embedded column-beam structure. The size of the lighting windows is determined according to the optimal window size scheme. The remaining spatial partitions are arranged with closed walls or reinforcing ribs.

[0036] The optimal stiffener arrangement scheme is applied to each spatial zone of the rear wall structure, and stiffeners are set in the specified spatial zones according to the stiffener arrangement parameters.

[0037] Based on the comprehensive optimization design results, a complete optimized scheme for the rear wall protection structure was formed, including the optimal configuration of space zoning, window size, and reinforcement arrangement;

[0038] Based on the complete optimization plan, structural construction drawings are prepared, specifying the dimensions of each spatial partition, the dimensions and location of each skylight, and the arrangement requirements of each reinforcing rib, generating design documents for engineering construction;

[0039] The prepared structural construction drawings and design documents were applied to the on-site structural construction to implement the optimized design of space zoning, window size and reinforcement arrangement, and then the engineering implementation of the wall protection structure was completed.

[0040] Optionally, the step of continuously monitoring the state characteristic parameters of the rear wall zones during the building's operation phase, periodically inputting new monitoring data into a sliding window transformer and a Bayesian network model, dynamically updating the parameters, and achieving adaptive optimization of the building's protective structure's resilience includes:

[0041] During the building's operation phase, monitoring data from each spatial zone of the rear wall are continuously collected to form a new set of spatial zone status characteristic parameters.

[0042] The collected dataset of spatial zoning characteristic parameters of the rear wall is standardized and preprocessed.

[0043] The newly acquired and preprocessed spatial partition state feature parameter dataset is periodically input into the sliding window transformer for feature extraction and multi-scale feature update.

[0044] The spatial partition state feature parameters output by the sliding window transformer are periodically input into the Bayesian network model to dynamically update the network node parameters and conditional probability distribution.

[0045] Based on the dynamically updated Bayesian network model, the structural risk probability distribution of each spatial partition of the rear wall and the overall structural toughness status are inferred and evaluated in real time.

[0046] Based on the reasoning and evaluation results, the spatial zoning design, window size, and reinforcement arrangement of the building's protective structure are adaptively adjusted and optimized to improve the resilience and adaptability of the building's protective structure. The optimized protective scheme is then implemented in structural maintenance and operation management.

[0047] The beneficial effects of this invention are:

[0048] This invention, through the deep fusion of a sliding window transformer and a Bayesian network model, extracts state features and performs probabilistic inference of structural risks for each spatial partition of the rear wall, achieving dynamic integration of multi-source monitoring information and quantitative assessment of spatial partition risks. By utilizing a structural optimization objective function to jointly optimize spatial partitioning, window dimensions, and stiffener placement, the scientific rigor of the structural design is improved, enhancing the protective structure's ability to cope with complex disaster-prone environments and partition heterogeneity risks. During the building's operation phase, monitoring data is periodically collected and processed, continuously inputting into the sliding window transformer and Bayesian network model to dynamically update structural risk parameters, enabling adaptive adjustment of the structural protection design's resilience and effectively suppressing the propagation of local damage to overall failure. Compared to existing structural protection methods relying on single indicators or static design, this invention achieves precise identification of partition-level risks and dynamic optimization of structural protection parameters, improving the safety and reliability of building structures in landslide-induced environments and demonstrating significant engineering application value. Attached Figure Description

[0049] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0050] Figure 1 The flowchart shows the method for optimizing the protective structure of frame houses under landslide-induced effects when building houses on slopes, as proposed in this invention.

[0051] Figure 2 This is a schematic diagram of the processing flow for extracting spatial partition state feature parameters using a sliding window transformer in the method for optimizing the protective structure of frame houses under landslide-induced slope construction proposed in this invention. Detailed Implementation

[0052] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0053] refer to Figure 1 and Figure 2 Optimization methods for the protective structure of frame houses under landslides induced by slope-cutting construction include:

[0054] Multi-source spatiotemporal datasets of the rear slope and rear wall area of ​​the house were collected, and the multi-source spatiotemporal datasets were preprocessed to generate standardized multi-source spatiotemporal datasets.

[0055] The standardized multi-source spatiotemporal dataset is divided into sliding windows according to the preset spatial step and time step. The sliding window transformer is used to extract features from the data in each window to obtain the state feature parameters of each spatial partition.

[0056] Using the state feature parameters of each spatial partition as node variables, a Bayesian network model is established. The state feature parameters are input to perform conditional probability inference to obtain the structural risk probability distribution of each spatial partition of the rear wall.

[0057] Based on the structural risk probability distribution, the structural zoning, window size and reinforcement arrangement of the rear wall protection structure are optimized. A grid-shaped embedded column-beam structure is set up in the rear wall to realize the spatial zoning of the wall. Small-sized lighting windows are set in the upper two zoning zones of the grid-shaped structure, and closed walls or reinforcements are set in the remaining zones. The structure is constructed according to the optimized design, and the structural zoning, window size and reinforcement arrangement are implemented in the construction drawings and on site.

[0058] During the building's operation phase, the state characteristic parameters of the rear wall zones are continuously monitored. New monitoring data are periodically input into a sliding window transformer and a Bayesian network model to dynamically update the parameters, thereby achieving adaptive optimization of the building's protective structure's resilience.

[0059] This invention achieves comprehensive perception of the dynamic environment and structural state of the rear slope and rear wall area of ​​a building through the collection and standardization of multi-source spatiotemporal datasets. A sliding window transformer is used to extract partitioned features from the standardized data, improving sensitivity to changes in spatial partition states and data utilization efficiency. Conditional probability inference using a Bayesian network model accurately assesses the structural risk probability of each spatial partition of the rear wall, achieving quantification of risk and partition identification. Based on the structural risk probability distribution, the parameters of the rear wall protection structure are optimized, taking into account the rational configuration of spatial partitions, window sizes, and reinforcement arrangement, thus improving structural safety and disaster prevention capabilities. During the building's operation phase, continuous monitoring and periodic data updates enable dynamic adjustment of the sliding window transformer and Bayesian network model, allowing the structural protection scheme to automatically optimize according to environmental changes and actual risks, improving the building's structural resilience and long-term reliability.

[0060] In this embodiment, the multi-source spatiotemporal dataset specifically includes topographic and geological parameters, rainfall duration, soil moisture content, wall stress parameters, and structural layout information of the area behind the house's back slope and back wall.

[0061] In this embodiment, the preprocessing of the multi-source spatiotemporal dataset specifically includes format unification, missing value imputation, outlier removal, and data standardization of the multi-source spatiotemporal dataset.

[0062] In this embodiment, obtaining the state characteristic parameters of each spatial partition includes:

[0063] For each spatial partition and time interval in the standardized multi-source spatiotemporal dataset, the rate of change of four monitoring parameters—surface deformation, strain, stress, and soil moisture content—in the continuous time interval is calculated. The rate of change of the four monitoring parameters is then weighted and fused according to the importance weights of surface deformation, strain, stress, and soil moisture content to obtain the joint change perception index corresponding to each spatial partition and time interval. This determines whether there are sudden extreme changes among the four monitoring parameters—surface deformation, strain, stress, and soil moisture content—and obtains the sudden change monitoring results corresponding to each spatial partition and time interval.

[0064] Based on the joint change perception index and the sudden change monitoring results, each spatial partition and each time interval is adaptively divided into sliding windows. When the joint change perception index is higher than the preset threshold or the sudden change monitoring result is positive, the spatial partition and time interval are divided into sliding windows using the first spatial window size and the first time window step size to obtain the first type of sliding window. When the joint change perception index is lower than or equal to the preset threshold and the sudden change monitoring result is negative, the spatial partition and time interval are divided into sliding windows using the second spatial window size and the second time window step size to obtain the second type of sliding window. The first spatial window size and the first time window step size are preset fine-grained parameters, and the second spatial window size and the second time window step size are preset wide-scale parameters. According to the principles of spatial location continuity and temporal series continuity, all sliding window pairs that are directly adjacent in space or time are identified, and an adjacent sliding window set is established.

[0065] For the first type of sliding window and the second type of sliding window, global statistical features, local extreme value features, rate of change features and segmented interval features are extracted within the sliding window according to spatial scale and time scale, respectively, to generate multi-scale feature subsets;

[0066] The extracted global statistical features, local extreme value features, rate of change features, and segmented interval features are concatenated and weighted to generate a multi-scale feature vector for each sliding window.

[0067] For each pair of sliding windows that are directly adjacent in space or time in the adjacent sliding window set, a sliding window overlap strategy is executed. While maintaining the original window boundary sequence, the boundaries between adjacent sliding windows are extended inward according to the set overlap length, forming a set of sliding window pairs with data overlap areas in spatial location or time series.

[0068] For the overlapping region data corresponding to each pair of sliding windows in the set of sliding window pairs, the trend of the overlapping region data is used to extrapolate the multi-scale feature vector of the sliding window boundary. The multi-scale feature vector generated by the trend extrapolation is fused with the multi-scale feature vector of the original overlapping region using Bayesian smoothing weighting to obtain the multi-scale feature vector after boundary continuity processing and anomaly correction. If feature mutations or abnormal residuals occur in the overlapping region data, the residual correction method is used to correct the multi-scale feature vector after boundary continuity processing and anomaly correction, as well as the multi-scale feature vector of the corresponding adjacent sliding window.

[0069] By summing the multi-scale feature vectors with the multi-scale feature vectors after boundary continuity processing and anomaly correction, multi-dimensional state feature parameters corresponding to each spatial partition and each time interval are generated, and the state feature parameters of each spatial partition are obtained.

[0070] This invention comprehensively reflects the actual deformation and risk status of each spatial partition and time interval by calculating and weighting the dynamic change rate of multidimensional monitoring parameters in a standardized multi-source spatiotemporal dataset, thereby improving the sensitivity and accuracy of anomaly identification. Adaptive sliding window partitioning and window category differentiation enable refined analysis of high-risk segments and efficient processing of low-risk segments, improving data utilization efficiency and analytical granularity. Multi-scale extraction and fusion of global statistical features, local extreme value features, change rate features, and segmented interval features enhances the richness and comprehensiveness of feature representation. Sliding window overlap and trend extrapolation, Bayesian smoothing, and residual correction mechanisms improve the continuity of window boundaries and feature stability under anomaly interference. The summarization of multi-scale features and anomaly-corrected feature parameters ensures that the state feature parameters of each spatial partition are accurate, comprehensive, and robust.

[0071] In this embodiment, obtaining the structural risk probability distribution of each spatial partition of the rear wall includes:

[0072] The state characteristic parameters of each spatial partition are used as candidate node variables. Based on the spatial distribution characteristics and changing trends of the state characteristic parameters, the spatial partition node structure is dynamically divided to determine the spatial partition node set.

[0073] For a given set of spatial partition nodes, based on the abnormal changes in state characteristic parameters and the differences in risk distribution, spatial partition nodes with state mutations are subdivided into multiple spatial partition sub-nodes, and spatial partition nodes with highly correlated states or balanced risks are merged into a single spatial partition node to obtain a set of spatial partition nodes.

[0074] Using each spatial partition node in the spatial partition node set as the input node, and four types of monitoring parameters—surface deformation, strain, stress, and soil moisture content—as external disaster-causing factor nodes, a multi-layer Bayesian network model structure containing spatial partition nodes, external disaster-causing factor nodes, and overall structural influence nodes is pre-set in the multi-layer Bayesian network model structure as the output node for the overall structural failure probability.

[0075] For each node in the multi-layer Bayesian network model structure, based on historical monitoring data, real-time collected data and external disaster-causing environmental data, the conditional probability distribution of each node is updated regularly to form a set of conditional probability tables driven by multi-source data.

[0076] Input the state feature parameters of each spatial partition node in the set of conditional probability tables and the set of spatial partition nodes. Using the Bayesian inference method, find the corresponding combination of state parameters in the conditional probability table and read the conditional probability of local destruction of the spatial partition node under the combination of state parameters. If there are multiple parent nodes or multiple observation information, then according to the probability propagation mechanism, the probability weighting and normalization of the state of all parent nodes are performed in turn to obtain the local destruction probability of each spatial partition node under the current observation information.

[0077] For the local failure probability of each spatial partition node in the spatial partition node set, a joint probabilistic inference function is used to calculate the overall structural failure probability of the node affected by the overall structure:

[0078] ;

[0079] in, This represents the overall structural failure probability. This represents the total number of nodes in the spatial partition. Let be the probability of local destruction of the i-th spatial partition node. Let be the probability of local destruction of the j-th spatial partition node. The factor representing the collaborative coupling influence between the i-th and j-th spatial partition nodes is... Let be the influence weight of the i-th spatial partition node;

[0080] The overall structural failure probability comprehensively considers the impact of the local damage risk of each spatial partition on the overall structural safety. The safety of the overall structure depends not only on the probability of individual partition failure, but also on the importance of each partition in the structure and the synergistic damage effect between partitions. By introducing influence weights, the dominant role of key partitions in structural safety is highlighted, while the setting of the synergistic coupling factor takes into account the superimposed effect of the overall structural threat when multiple partitions fail simultaneously. This approach breaks through the traditional simple union calculation that relies solely on the probability of independent partitions, and more realistically reflects the overall failure mechanism of complex structural systems under conditions such as local damage transmission and inter-partition interactions, providing a scientific basis for structural safety assessment and protection optimization.

[0081] Based on the multi-layer Bayesian network model structure and the local destruction probability of each spatial partition node in the spatial partition node set, the correlation between spatial partition nodes is analyzed. Network edge connections are established between spatial partition nodes with significant correlation, and network edge connections between spatial partition nodes with low correlation are deleted to obtain the dynamically adjusted Bayesian network model structure.

[0082] The system outputs the local failure probability of each spatial partition node in the set of spatial partition nodes, the overall structural failure probability of the nodes affected by the overall structure, and the structural risk probability distribution corresponding to the dynamically adjusted Bayesian network model structure, thereby obtaining the structural risk probability distribution of each spatial partition of the rear wall.

[0083] This invention accurately reflects the changing trends and risk distribution of structural partition states through dynamic division and adaptive adjustment of spatial partition node structures, achieving refined identification and modeling of partition risks. By combining multi-source monitoring parameters such as surface deformation, strain, stress, and soil moisture content, a multi-layer Bayesian network model is established, organically integrating spatial partition nodes, external disaster-causing factor nodes, and overall structural influence nodes, thus enhancing the systematicness and scientific rigor of structural risk reasoning. Dynamic updates of conditional probability tables driven by multi-source data ensure synchronization between model parameters and actual engineering conditions, providing precise response capabilities for different risk scenarios. Employing Bayesian inference and probability propagation mechanisms, the local failure probability of each spatial partition node can be calculated in real time, and the overall structural failure probability is comprehensively reflected based on the probabilistic joint inference function. The introduction of synergistic coupling factors and partition weights effectively strengthens the comprehensive impact expression of multi-partition linkage damage on overall structural safety. Self-learning optimization of network structure correlation improves the accuracy of characterizing inter-partition dependencies. This invention provides high-quality quantitative assessment of partition risks and overall safety determination for structural protection, enhancing the intelligence and adaptability of structural protection design and improving the safety level of building structures in disaster-induced scenarios such as landslides.

[0084] In this embodiment, based on the structural risk probability distribution, the structural zoning, window sizes, and reinforcement arrangement of the rear wall protective structure are optimized. A grid-shaped embedded column-beam structure is established in the rear wall to achieve spatial zoning of the wall. Small-sized skylights are installed in the upper two zones of the grid-shaped structure, while the remaining zones are equipped with enclosed walls or reinforcements. The structure is constructed according to the optimized design, and the structural zoning, window sizes, and reinforcement arrangement are implemented in the construction drawings and on-site, including:

[0085] Based on the structural risk probability distribution of each spatial zone, and combined with the spatial zone parameters, window size parameters, and stiffener arrangement parameters of the rear wall structure, a structural protection optimization objective function is established:

[0086] ;

[0087] in, Indicates spatial partitioning parameters, Indicates window size parameters, Indicates the parameters for the arrangement of stiffeners. For the first Structural risk probability of spatial partitioning For the structural protection cost function, and These are the weighting coefficients. Let represent the total number of spatial partitions, and min is the operation to find the minimum value.

[0088] The structural protection optimization objective function reflects the goal of simultaneously considering structural risk control and engineering cost optimization in structural protection design. By optimizing the combination of spatial zoning parameters, window size parameters, and stiffener arrangement parameters, the structural risk probability of each spatial zone is effectively reduced, and the investment cost of structural protection is reasonably controlled. Weighting coefficients are used to balance the relative importance of structural safety and economy. The optimization result satisfies both safety performance requirements and economic feasibility. The optimization objective is to find the optimal solution among all feasible parameter configurations, minimizing the weighted sum of structural risk and engineering cost. This breaks away from the traditional single-index optimization model and provides a scientific, systematic, and engineering-guiding parameter configuration scheme for structural protection.

[0089] Based on the structural protection optimization objective function, the spatial partition parameters, window size parameters, and stiffener arrangement parameters are constrained and optimized. During the optimization process, the allowable range and design constraints of the number and size of spatial partitions, window size and location, and stiffener arrangement are limited according to structural design specifications and safety standards. Under the premise that all constraints are met, the optimal spatial partition scheme, optimal window size scheme, and optimal stiffener arrangement scheme with the lowest structural risk probability and reasonable structural protection cost are determined.

[0090] The optimal space zoning scheme is applied to the rear wall structure. A grid-shaped embedded column-beam structure is set up in the rear wall structure to divide the rear wall space into zones. The number and size of the space zones are determined according to the optimal space zoning scheme.

[0091] The optimal window size scheme is applied to the spatial partitioning of the rear wall structure. Lighting windows are set in the upper spatial partition of the grid-shaped embedded column-beam structure. The size of the lighting windows is determined according to the optimal window size scheme. The remaining spatial partitions are arranged with closed walls or reinforcing ribs.

[0092] The optimal stiffener arrangement scheme is applied to each spatial zone of the rear wall structure, and stiffeners are set in the specified spatial zones according to the stiffener arrangement parameters.

[0093] Based on the comprehensive optimization design results, a complete optimized scheme for the rear wall protection structure was formed, including the optimal configuration of space zoning, window size, and reinforcement arrangement;

[0094] Based on the complete optimization plan, structural construction drawings are prepared, specifying the dimensions of each spatial partition, the dimensions and location of each skylight, and the arrangement requirements of each reinforcing rib, generating design documents for engineering construction;

[0095] The prepared structural construction drawings and design documents were applied to the on-site structural construction to implement the optimized design of space zoning, window size and reinforcement arrangement, and then the engineering implementation of the wall protection structure was completed.

[0096] This invention achieves a systematic joint design of structural parameters such as spatial zoning, window size, and stiffener arrangement by establishing a structural protection optimization objective function and implementing multi-parameter constraint optimization. It organically combines the structural risk probability distribution with protection costs, effectively controlling project costs while ensuring structural safety and improving the economic rationality of the protection design. Based on the differences in spatial zoning risks, the rear wall structure adopts a grid-shaped embedded column-beam design for spatial zoning, achieving refined control over zoning dimensions and layout, and enhancing the overall load-bearing capacity and stability of the structure. The coordinated design of the optimal window size scheme and stiffener arrangement improves the uniformity of stress distribution and lighting performance of the structure. Construction drawings and design documents are prepared strictly according to the optimization results throughout the entire process, ensuring the efficient implementation of the design scheme on-site.

[0097] In this embodiment, the continuous monitoring of the state characteristic parameters of the rear wall zone during the building's operation phase, and the periodic input of new monitoring data into a sliding window transformer and a Bayesian network model to dynamically update the parameters, thereby achieving adaptive optimization of the building's protective structure's resilience, includes:

[0098] During the building's operation phase, monitoring data from each spatial zone of the rear wall are continuously collected to form a new set of spatial zone status characteristic parameters.

[0099] The collected dataset of spatial zoning characteristic parameters of the rear wall is standardized and preprocessed.

[0100] The newly acquired and preprocessed spatial partition state feature parameter dataset is periodically input into the sliding window transformer for feature extraction and multi-scale feature update.

[0101] The spatial partition state feature parameters output by the sliding window transformer are periodically input into the Bayesian network model to dynamically update the network node parameters and conditional probability distribution.

[0102] Based on the dynamically updated Bayesian network model, the structural risk probability distribution of each spatial partition of the rear wall and the overall structural toughness status are inferred and evaluated in real time.

[0103] Based on the reasoning and evaluation results, the spatial zoning design, window size, and reinforcement arrangement of the building's protective structure are adaptively adjusted and optimized to improve the resilience and adaptability of the building's protective structure. The optimized protective scheme is then implemented in structural maintenance and operation management.

[0104] This invention achieves real-time perception and dynamic data accumulation of structural health status by continuously collecting and preprocessing monitoring data from each spatial zone of the rear wall during the building's operation phase. A sliding window transformer is used to extract and update multi-scale features from new data, improving the responsiveness of the zoning status feature parameters to changes in environmental and operating conditions. The latest feature parameters are periodically input into a Bayesian network model, and the model node parameters and conditional probability distributions are dynamically adjusted to reflect the latest state of structural stress and environmental risk. Based on the dynamically updated Bayesian network model, the structural risk probability distribution and overall structural toughness of each spatial zone of the rear wall are inferred and evaluated in real time, providing data support for the adaptive optimization of structural protection schemes. Based on the inference results, key parameters such as the spatial zoning design of the building's protective structure, window sizes, and stiffener arrangement can be automatically adjusted and applied to maintenance and operation management, enhancing the structural protection's toughness and environmental adaptability. Example

[0105] To verify the feasibility of this invention in practice, it was applied to a mountainous residential community. The developer planned to build several three-story residential buildings on a steep south-facing slope. The site has undulating terrain, with a 30-degree slope at the back, and the geology is mainly silty clay mixed with pebbles, subject to heavy rainfall year-round. Because traditional experience-based back wall designs frequently result in problems such as back wall deformation, water seepage, and even localized structural damage in areas prone to similar geological disasters, the construction company hoped to solve the problem of insufficient safety and resilience of the back wall through advanced structural optimization methods.

[0106] During the implementation of this project, the team selected one of the residential buildings, C2, and applied the method of this invention to optimize the entire lifecycle of the rear wall protection structure. At the initial stage of the project, technicians first deployed multi-source monitoring sensors along the rear slope and rear wall of the building, including 6 ground deformation monitoring points, 8 wall strain points, 8 wall stress points, and 4 soil moisture content monitoring points, automatically collecting data every 30 minutes. The project period lasted from May 2024 to April 2025, spanning a complete flood season.

[0107] After standardized preprocessing, the collected monitoring data is input into a sliding window transformer, which automatically divides the data into adaptive sliding windows for different spatial zones and time intervals. The system automatically extracts the dynamic characteristics of surface deformation rate, strain rate, stress rate, and water content for each zone at different times. In mid-June 2022, Chongqing experienced continuous heavy rain. On a certain day, the surface deformation rate of zone B of the rear wall reached 0.78 mm / d, and the strain rate increased significantly. The system detected that the joint change sensing index of zones B and C exceeded the preset threshold, triggering the fine-grained sliding window division.

[0108] The engineering team constructed a Bayesian network model using multi-scale state feature parameters extracted by a sliding window transformer, incorporating surface deformation, strain, stress, and water content as external disaster-causing nodes into the inference system. The Bayesian model calculates the probability of local damage and overall structural failure for each zone in real time based on the latest data. For example, on June 16, 2024, the day of the torrential rain, the probability of local damage in zone B under the original structural design was as high as 0.28, in zone C it was 0.22, and the probability of overall structural failure reached 0.17.

[0109] Based on the structural optimization objective function, the system automatically performed multiple rounds of parameter iterations on the rear wall space zoning scheme, window dimensions, and reinforcement arrangement. The final determination was to increase the number of zones from the original four to six, with two 0.7m × 0.6m small windows at the top, and the bottom and sides entirely enclosed walls. All zones were reinforced with double layers of ribs. The optimized protective structure scheme, while ensuring safety, only slightly increased the project cost by 6.4%.

[0110] Following the implementation of the optimized design, continuous monitoring from July 2024 to April 2025 showed that the probability of maximum zonal failure of the rear wall decreased to 0.13, and the probability of overall structural failure decreased to 0.06. During the same period, the maximum deformation rate decreased from 0.69 mm / d in the original plan to 0.31 mm / d, and the cumulative number of days with stress exceeding the limit in the rear wall during the rainy season decreased from 14 days to 2 days. After construction, residents reported significant improvements, and no further water seepage or cracking of the rear wall occurred on site.

[0111] Table 1 Comparison of Structural Safety Performance Before and After Optimization

[0112]

[0113] Table 1 above compares the main technical indicators and engineering results of the structure protection before and after optimization. After optimization, the number of spatial zones in the rear wall increased from 4 to 6, achieving more detailed zone management and risk sharing. The size of the upper skylight was reduced from 1.2×0.8 meters to 0.7×0.6 meters, effectively limiting the weak areas at the window openings and improving the overall strength of the wall. The number of reinforcing ribs increased from 1 to 2 per zone, enhancing local deformation resistance. Structural optimization reduced risk-related indicators; the probability of maximum zone failure decreased from 0.28 to 0.13, and the probability of overall structural failure decreased from 0.17 to 0.06, significantly improving the safety margin of the structure. The maximum deformation rate also decreased significantly, indicating that the controllability of wall deformation under extreme rainfall and other disaster environments was improved. The cumulative number of days with stress exceeding limits during the rainy season decreased from 14 days to 2 days, enhancing the long-term reliability of the structure. Although the cost of the optimized protective structure increased slightly, by only 4,500 yuan, the number of reports of water seepage and cracking in the rear wall decreased from 6 to 0, and resident satisfaction increased from 78% to 94%. The optimization measures of this invention achieve a coordinated balance between structural safety, functionality, and economy, enhancing the practicality of the protective structure of houses built on mountain slopes and improving residents' confidence in their residence.

[0114] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for optimizing the protective structure of frame houses under landslide-induced effects caused by slope-cutting construction, characterized in that, include: Collect multi-source spatiotemporal datasets of the rear slope and rear wall area of ​​the house, including topographic and geological parameters, rainfall duration, soil moisture content, wall stress parameters and structural layout information of the rear slope and rear wall area. Preprocess the multi-source spatiotemporal datasets to generate standardized multi-source spatiotemporal datasets. The standardized multi-source spatiotemporal dataset is divided into sliding windows according to the preset spatial step and time step. The sliding window transformer is used to extract features from the data in each window to obtain the state feature parameters of each spatial partition. Using the state feature parameters of each spatial partition as node variables, a Bayesian network model is established. The state feature parameters are input to perform conditional probability inference to obtain the structural risk probability distribution of each spatial partition of the rear wall. Based on the structural risk probability distribution, the structural zoning, window size and reinforcement arrangement of the rear wall protection structure are optimized. A grid-shaped embedded column-beam structure is set up in the rear wall to realize the spatial zoning of the wall. Small-sized lighting windows are set in the upper two zoning zones of the grid-shaped structure, and closed walls or reinforcements are set in the remaining zones. The structure is constructed according to the optimized design, and the structural zoning, window size and reinforcement arrangement are implemented in the construction drawings and on site. During the building's operation phase, the state characteristic parameters of the rear wall zones are continuously monitored. New monitoring data are periodically input into a sliding window transformer and a Bayesian network model to dynamically update the parameters and achieve adaptive optimization of the building's protective structure's resilience. The process of obtaining the structural risk probability distribution of each spatial partition of the rear wall includes: The state characteristic parameters of each spatial partition are used as candidate node variables. Based on the spatial distribution characteristics and changing trends of the state characteristic parameters, the spatial partition node structure is dynamically divided to determine the spatial partition node set. For a given set of spatial partition nodes, based on the abnormal changes in state characteristic parameters and the differences in risk distribution, spatial partition nodes with state mutations are subdivided into multiple spatial partition sub-nodes, and spatial partition nodes with highly correlated states or balanced risks are merged into a single spatial partition node to obtain a set of spatial partition nodes. Using each spatial partition node in the spatial partition node set as the input node, and four types of monitoring parameters—surface deformation, strain, stress, and soil moisture content—as external disaster-causing factor nodes, a multi-layer Bayesian network model structure containing spatial partition nodes, external disaster-causing factor nodes, and overall structural influence nodes is pre-set in the multi-layer Bayesian network model structure as the output node for the overall structural failure probability. For each node in the multi-layer Bayesian network model structure, based on historical monitoring data, real-time collected data and external disaster-causing environmental data, the conditional probability distribution of each node is updated regularly to form a set of conditional probability tables driven by multi-source data. Input the state feature parameters of each spatial partition node in the set of conditional probability tables and the set of spatial partition nodes. Using the Bayesian inference method, find the corresponding combination of state parameters in the conditional probability table and read the conditional probability of local destruction of the spatial partition node under the combination of state parameters. If there are multiple parent nodes or multiple observation information, then according to the probability propagation mechanism, the probability weighting and normalization of the state of all parent nodes are performed in turn to obtain the local destruction probability of each spatial partition node under the current observation information. For the local damage probability of each spatial partition node in the spatial partition node set, a probabilistic joint inference function is used to calculate the overall structural failure probability of the node affected by the overall structure. Based on the multi-layer Bayesian network model structure and the local destruction probability of each spatial partition node in the spatial partition node set, the correlation between spatial partition nodes is analyzed. Network edge connections are established between spatial partition nodes with significant correlation, and network edge connections between spatial partition nodes with low correlation are deleted to obtain the dynamically adjusted Bayesian network model structure. The system outputs the local failure probability of each spatial partition node in the set of spatial partition nodes, the overall structural failure probability of the nodes affected by the overall structure, and the structural risk probability distribution corresponding to the dynamically adjusted Bayesian network model structure, thereby obtaining the structural risk probability distribution of each spatial partition of the rear wall.

2. The method for optimizing the protective structure of frame houses under landslide-induced slope construction as described in claim 1, characterized in that, The preprocessing of the multi-source spatiotemporal dataset specifically includes format unification, missing value imputation, outlier removal, and data standardization.

3. The method for optimizing the protective structure of frame houses under landslide-induced slope construction as described in claim 1, characterized in that, The process of obtaining the state characteristic parameters of each spatial partition includes: For each spatial partition and time interval in the standardized multi-source spatiotemporal dataset, the rate of change of four monitoring parameters—surface deformation, strain, stress, and soil moisture content—in the continuous time interval is calculated. The rate of change of the four monitoring parameters is then weighted and fused according to the importance weights of surface deformation, strain, stress, and soil moisture content to obtain the joint change perception index corresponding to each spatial partition and time interval. This determines whether there are sudden extreme changes among the four monitoring parameters—surface deformation, strain, stress, and soil moisture content—and obtains the sudden change monitoring results corresponding to each spatial partition and time interval. Based on the joint change perception index and the sudden change monitoring results, each spatial partition and each time interval is adaptively divided into sliding windows. When the joint change perception index is higher than the preset threshold or the sudden change monitoring result is positive, the spatial partition and time interval are divided into sliding windows using the first spatial window size and the first time window step size to obtain the first type of sliding window. When the joint change perception index is lower than or equal to the preset threshold and the sudden change monitoring result is negative, the spatial partition and time interval are divided into sliding windows using the second spatial window size and the second time window step size to obtain the second type of sliding window. The first spatial window size and the first time window step size are preset fine-grained parameters, and the second spatial window size and the second time window step size are preset wide-scale parameters. According to the principles of spatial location continuity and temporal series continuity, all sliding window pairs that are directly adjacent in space or time are identified, and an adjacent sliding window set is established. For the first type of sliding window and the second type of sliding window, global statistical features, local extreme value features, rate of change features and segmented interval features are extracted within the sliding window according to spatial scale and time scale, respectively, to generate multi-scale feature subsets; The extracted global statistical features, local extreme value features, rate of change features, and segmented interval features are concatenated and weighted to generate a multi-scale feature vector for each sliding window. For each pair of sliding windows that are directly adjacent in space or time in the adjacent sliding window set, a sliding window overlap strategy is executed. While maintaining the original window boundary sequence, the boundaries between adjacent sliding windows are extended inward according to the set overlap length, forming a set of sliding window pairs with data overlap areas in spatial location or time series. For the overlapping region data corresponding to each pair of sliding windows in the set of sliding window pairs, the trend of the overlapping region data is used to extrapolate the multi-scale feature vector of the sliding window boundary. The multi-scale feature vector generated by the trend extrapolation is fused with the multi-scale feature vector of the original overlapping region using Bayesian smoothing weighting to obtain the multi-scale feature vector after boundary continuity processing and anomaly correction. If feature mutations or abnormal residuals occur in the overlapping region data, the residual correction method is used to correct the multi-scale feature vector after boundary continuity processing and anomaly correction, as well as the multi-scale feature vector of the corresponding adjacent sliding window. By summing the multi-scale feature vectors with the multi-scale feature vectors after boundary continuity processing and anomaly correction, multi-dimensional state feature parameters corresponding to each spatial partition and each time interval are generated, and the state feature parameters of each spatial partition are obtained.

4. The method for optimizing the protective structure of frame houses under landslide-induced slope construction as described in claim 1, characterized in that, Based on the structural risk probability distribution, the structural zoning, window sizes, and reinforcement arrangement of the rear wall protective structure are optimized. A grid-shaped embedded column-beam structure is established in the rear wall to achieve spatial zoning. Small-sized skylights are installed in the upper two zones of the grid-shaped structure, while the remaining zones are enclosed walls or reinforced with ribs. Structural construction is carried out according to the optimized design, and the structural zoning, window sizes, and reinforcement arrangement are implemented in the construction drawings and on-site, including: Based on the structural risk probability distribution of each spatial partition, and combined with the spatial partition parameters, window size parameters and stiffener arrangement parameters of the rear wall structure, a structural protection optimization objective function is established. Based on the structural protection optimization objective function, the spatial partition parameters, window size parameters, and stiffener arrangement parameters are constrained and optimized. During the optimization process, the allowable range and design constraints of the number and size of spatial partitions, window size and location, and stiffener arrangement are limited according to structural design specifications and safety standards. Under the premise that all constraints are met, the optimal spatial partition scheme, optimal window size scheme, and optimal stiffener arrangement scheme with the lowest structural risk probability and reasonable structural protection cost are determined. The optimal space zoning scheme is applied to the rear wall structure. A grid-shaped embedded column-beam structure is set up in the rear wall structure to divide the rear wall space into zones. The number and size of the space zones are determined according to the optimal space zoning scheme. The optimal window size scheme is applied to the spatial partitioning of the rear wall structure. Lighting windows are set in the upper spatial partition of the grid-shaped embedded column-beam structure. The size of the lighting windows is determined according to the optimal window size scheme. The remaining spatial partitions are arranged with closed walls or reinforcing ribs. The optimal stiffener arrangement scheme is applied to each spatial zone of the rear wall structure, and stiffeners are set in the specified spatial zones according to the stiffener arrangement parameters. Based on the comprehensive optimization design results, a complete optimized scheme for the rear wall protection structure was formed, including the optimal configuration of space zoning, window size, and reinforcement arrangement; Based on the complete optimization plan, structural construction drawings are prepared, specifying the dimensions of each spatial partition, the dimensions and location of each skylight, and the arrangement requirements of each reinforcing rib, generating design documents for engineering construction; The prepared structural construction drawings and design documents were applied to the on-site structural construction to implement the optimized design of space zoning, window size and reinforcement arrangement, and then the engineering implementation of the wall protection structure was completed.

5. The method for optimizing the protective structure of frame houses under landslide-induced slope construction as described in claim 1, characterized in that, The process of continuously monitoring the state characteristic parameters of the rear wall zones during the building's operation phase, periodically inputting new monitoring data into a sliding window transformer and a Bayesian network model to dynamically update parameters, and achieving adaptive optimization of the building's protective structure's resilience includes: During the building's operation phase, monitoring data from each spatial zone of the rear wall are continuously collected to form a new set of spatial zone status characteristic parameters. The collected dataset of spatial zoning characteristic parameters of the rear wall is standardized and preprocessed. The newly acquired and preprocessed spatial partition state feature parameter dataset is periodically input into the sliding window transformer for feature extraction and multi-scale feature update. The spatial partition state feature parameters output by the sliding window transformer are periodically input into the Bayesian network model to dynamically update the network node parameters and conditional probability distribution. Based on the dynamically updated Bayesian network model, the structural risk probability distribution of each spatial partition of the rear wall and the overall structural toughness status are inferred and evaluated in real time. Based on the reasoning and evaluation results, the spatial zoning design, window size, and reinforcement arrangement of the building's protective structure are adaptively adjusted and optimized to improve the resilience and adaptability of the building's protective structure. The optimized protective scheme is then implemented in structural maintenance and operation management.

Images