Artificial intelligence-based smart building monitoring method, system and medium

Abstract

The present application relates to the field of data processing technology, and discloses a method, system, and medium for intelligent building monitoring based on artificial intelligence. The method includes: completing time series decomposition of pre-processed data to extract features, quantify weights, unify feature mapping, and obtain a feature matrix; accordingly decomposing building variables, encrypting protection parameters, establishing topological relationships, and obtaining status indicators; iteratively identifying anomalies based on input indicators, enhancing rare categories, and confidence grading to obtain early warning data; based on this, predicting usage conditions, optimizing maintenance sequences with multiple objectives, and generating maintenance strategies; compressing and extracting experience from strategies, migrating features across domains, updating knowledge in groups, and constructing a monitoring library. The present application improves the accuracy of building monitoring and the efficiency of maintenance management through technical means such as multi-source data fusion, abnormal pattern recognition, and knowledge migration, and realizes intelligent assessment of building health status and optimized decision-making of maintenance strategies.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to an artificial intelligence-based smart building monitoring method, system, and medium. Background Art

[0002] In the field of building monitoring and maintenance management, traditional monitoring methods rely primarily on manual inspections and regular testing, obtaining information on a building's health status through on-site surveys and non-destructive testing. With the development of the Internet of Things and sensing technology, building monitoring has gradually become automated and networked. Various sensors can now collect real-time structural response data, including physical quantities such as displacement, strain, and acceleration. In data analysis, computer-aided analysis techniques have begun to be applied to process and analyze collected monitoring data to assess the building's condition. Building maintenance management has also gradually established standardized repair and maintenance systems, developing corresponding maintenance strategies for different types of damage, and has accumulated a wealth of practical engineering experience.

[0003] However, existing building monitoring technologies have some obvious shortcomings: first, the collection and analysis of monitoring data lack intelligent means, data processing efficiency is low, and it is difficult to detect potential safety hazards in a timely manner; second, the monitoring system has limited ability to identify abnormal conditions, especially for rare damage patterns, and often cannot accurately judge their degree of danger; third, the extraction and application of maintenance experience are too dependent on manual experience and lack of systematic knowledge management methods, resulting in low maintenance efficiency and difficulty in technology promotion; fourth, monitoring and maintenance experience between different buildings is difficult to effectively share, resulting in waste of resources and affecting the overall improvement of building operation and maintenance management level. Summary of the Invention

[0004] This application provides an artificial intelligence-based smart building monitoring method, system and medium, which is used to improve the accuracy of building monitoring and the efficiency of maintenance management through technical means such as multi-source data fusion, abnormal pattern recognition, and knowledge transfer, and to achieve intelligent assessment of building health status and optimized decision-making on maintenance strategies.

[0005] In the first aspect, the present application provides an artificial intelligence-based smart building monitoring method, which includes: importing building sensor data into edge computing nodes for distributed sampling, performing wavelet transform noise reduction filtering on the high-frequency signals of the sampled data, eliminating abnormal points based on interval statistics, and obtaining a preprocessed data set; completing time series decomposition according to the preprocessed data set to extract data periodic features, quantifying each feature weight according to feature importance, using multi-source feature mapping to unify feature space conversion, and generating a building feature matrix; based on the building feature matrix, obtaining building state variables through multi-dimensional parameter decomposition, and adopting data encryption transformation Sensitive parameter protection is achieved, and a topological structure between parameters is established through correlation calculation to generate building status indicators; the building status indicators are input into a gradient iterative process to identify abnormal patterns, data enhancement processing is performed on rare abnormal categories, and the degree of abnormality is graded in combination with confidence interval calculations to output building early warning data; based on the building early warning data, trend extrapolation is carried out to predict usage conditions, maintenance task priorities are determined through multi-objective optimization, maintenance plans are screened based on benefit ratio calculations, and building maintenance strategies are generated; knowledge compression is applied to the building maintenance strategies to extract maintenance experience, cross-domain mapping is used to transfer knowledge features, maintenance knowledge is updated through group collaboration, and an intelligent monitoring knowledge base is constructed.

[0006] In a second aspect, the present application provides an artificial intelligence-based smart building monitoring system, the artificial intelligence-based smart building monitoring system comprising:

[0007] The sampling module is used to import building sensor data into the edge computing node for distributed sampling, perform wavelet transform noise reduction and filtering on the high-frequency signals of the sampled data, and remove outliers based on the interval statistics method to obtain a preprocessed data set;

[0008] An extraction module is configured to perform time series decomposition according to the preprocessed data set to extract data period features, quantify feature weights according to feature importance, unify feature space transformations using multi-source feature mapping, and generate a building feature matrix;

[0009] Establish a module for obtaining building state variables through multi-dimensional parameter decomposition based on the building characteristic matrix, adopting data encryption transformation to realize sensitive parameter protection, establishing a topological structure between parameters through correlation calculation, and generating building state indicators;

[0010] an identification module for inputting the building status indicators into a gradient iterative process to identify abnormal patterns, performing data enhancement processing on rare abnormal categories, classifying the degree of abnormality in combination with confidence interval calculations, and outputting building early warning data;

[0011] A prediction module is used to predict the usage conditions based on the building early warning data by trend extrapolation, determine the maintenance task priority through multi-objective optimization, select maintenance plans based on the benefit ratio calculation, and generate a building maintenance strategy;

[0012] The updating module is used to apply knowledge compression to the building maintenance strategy to extract maintenance experience, use cross-domain mapping to migrate knowledge features, update maintenance knowledge through group collaboration, and build an intelligent monitoring knowledge base.

[0013] The third aspect of the present application provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, it enables the computer to execute the above-mentioned artificial intelligence-based smart building monitoring method.

[0014] In the technical solution provided by this application, distributed sampling is performed through edge computing nodes to achieve on-site processing and transmission optimization of monitoring data, reduce the data transmission burden, and improve real-time response capabilities; wavelet transform noise reduction filtering and interval statistics are used to eliminate abnormal points, significantly improving the quality and reliability of the original data; time series decomposition and feature extraction are performed based on the preprocessed data set, combined with feature importance quantification and multi-source feature mapping, to achieve accurate expression of building status characteristics; through multi-dimensional parameter decomposition and data encryption transformation, the integrity of building status variables is guaranteed and the security of sensitive data is protected; gradient iteration is used to identify abnormal patterns, and combined with data enhancement processing and confidence interval operations, the accuracy and reliability of abnormal state identification are improved; through trend extrapolation prediction and multi-objective optimization, scientific decision-making of maintenance tasks and optimal allocation of resources are achieved; knowledge compression is used to extract maintenance experience, and through cross-domain mapping and group collaborative updating, a sustainable and evolving intelligent monitoring knowledge base is established, which deeply combines artificial intelligence technology with building monitoring practice and improves monitoring efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 This is a schematic diagram of an embodiment of the smart building monitoring method based on artificial intelligence in the embodiment of the present application;

[0017] Figure 2 This is a schematic diagram of an embodiment of an artificial intelligence-based smart building monitoring system in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The embodiments of the present application provide a method, system and medium for intelligent building monitoring based on artificial intelligence. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In the embodiments of the present application, an embodiment of the smart building monitoring method based on artificial intelligence includes:

[0020] Step S101: Import building sensor data into the edge computing node for distributed sampling, perform wavelet transform noise reduction filtering on the high-frequency signals of the sampled data, remove outliers based on interval statistics, and obtain a preprocessed data set;

[0021] Step S102: Perform time series decomposition according to the preprocessed data set to extract data period features, quantify each feature weight according to feature importance, use multi-source feature mapping to unify feature space transformation, and generate a building feature matrix;

[0022] Step S103: Based on the building feature matrix, obtain building state variables through multi-dimensional parameter decomposition, adopt data encryption transformation to realize sensitive parameter protection, establish the topological structure between parameters through correlation calculation, and generate building state indicators;

[0023] Step S104: Input the building status indicators into the gradient iterative process to identify abnormal patterns, perform data enhancement processing on rare abnormal categories, classify the abnormality degree in combination with confidence interval calculation, and output building early warning data;

[0024] Step S105: Based on the building early warning data, trend extrapolation is performed to predict the usage conditions, maintenance task priorities are determined through multi-objective optimization, maintenance plans are screened based on the benefit ratio calculation, and a building maintenance strategy is generated;

[0025] Step S106: Apply knowledge compression to extract maintenance experience from building maintenance strategies, use cross-domain mapping to migrate knowledge features, update maintenance knowledge through group collaboration, and build an intelligent monitoring knowledge base.

[0026] It is understandable that the execution subject of this application can be an artificial intelligence-based smart building monitoring system, or a terminal or a server, which is not limited here. The embodiment of this application is described by taking the server as the execution subject as an example.

[0027] Specifically, distributed sampling of building sensor data is performed through edge computing nodes. Edge computing nodes are data processing units distributed across each floor of a building. These nodes can process sensor data locally, reducing the burden of data transmission. During the sampling process, edge computing nodes dynamically adjust the sampling frequency based on the degree of data change: when rapid data changes are detected, the sampling frequency is increased to capture the changes; when the data is relatively stable, the sampling frequency is reduced to conserve computing resources. The collected high-frequency signals are then subjected to wavelet transform denoising and filtering. The wavelet transform effectively separates noise components from the signal by decomposing the signal into wavelet coefficients of different scales. Specifically, the wavelet transform first selects an appropriate wavelet basis function (such as the db4 wavelet) to decompose the original signal into coefficients at multiple scales. Then, thresholding is performed on each scale coefficient to remove the wavelet coefficients corresponding to the noise. Finally, the signal is reconstructed to obtain the de-noised data. Taking building structure vibration monitoring as an example, the acceleration signals collected by sensors often contain high-frequency noise. The wavelet transform can effectively filter out this interference and preserve the true structural vibration response.

[0028] The statistical characteristics of the data (mean, standard deviation) are calculated, and then the outlier threshold is determined based on the 3σ criterion. Data points that deviate from the mean by more than three standard deviations are marked as outliers. Labeled outliers are replaced by interpolation of adjacent data to ensure data continuity. The processed data form a preprocessed dataset that more clearly reflects the true state of the building. During the time series decomposition phase, the preprocessed dataset is subjected to periodic analysis to extract the periodic characteristics of the data. The time domain signal is converted to the frequency domain using Fourier transform to identify the main periodic components. For building monitoring data, important periodic characteristics include daily variation cycles (such as temperature and load changes) and weekly variation cycles (such as usage patterns). Based on the extracted periodic characteristics, the importance of each feature is calculated, that is, the degree to which the feature contributes to the judgment of the building status. Feature importance is quantified using indicators such as information entropy or variance contribution rate. Features with high importance receive higher weights in subsequent analysis.

[0029] The multi-source feature mapping process transforms features from different sensors and physical quantities into a unified feature space. Each feature is normalized to a uniform numerical range. Then, an orthogonal transformation is used to establish mapping relationships between features, generating a building feature matrix. Each row in the feature matrix represents a time point, and each column corresponds to a feature dimension. The matrix element values represent the strength or degree of the feature. The building feature matrix undergoes multidimensional parameter decomposition to obtain variables reflecting different aspects of the building's state. This decomposition process uses dimensionality reduction methods such as principal component analysis to extract key state characteristics. Sensitive state parameters (such as stress data of key structural components) are protected using data encryption to ensure data security. By calculating correlation coefficients between parameters and establishing topological relationships between them, a building state indicator system is formed. To identify abnormal building states, the building state indicators are input into a gradient iteration process. Gradient iteration continuously adjusts parameters to minimize prediction error and gradually identify abnormal patterns. For rare anomaly categories with a small number of cases, data augmentation is used to expand the sample. Data augmentation involves adding random perturbations and combining features to generate new anomaly samples. Confidence interval calculations, based on statistical distribution characteristics, quantitatively grade the degree of anomalies and output building early warning data. Trend extrapolation prediction analyzes development trends based on building early warning data during the operating condition phase. Time series analysis methods are used to predict the changing trends of various state parameters and, combined with the influence of environmental factors, derive a forecast of operating conditions for a period of time in the future. Maintenance task priorities are determined based on multiple objectives: maintenance urgency, resource constraints, and maintenance effectiveness. A multi-objective optimization algorithm is used to find the optimal balance between multiple objectives and form a task priority ranking. Benefit ratio calculations further evaluate the input-output ratio of different maintenance solutions to select the optimal maintenance strategy.

[0030] During the knowledge compression process to extract maintenance experience, maintenance strategies are structured and analyzed to extract core maintenance rules and experiences. Through cross-domain mapping, maintenance experience gained in one building is transformed into knowledge features that can be applied to other similar buildings. A collaborative update mechanism allows monitoring systems across multiple buildings to share and exchange maintenance experience, continuously optimizing maintenance knowledge and building an intelligent monitoring knowledge base.

[0031] In the embodiment of the present application, distributed sampling is performed through edge computing nodes to achieve on-site processing and transmission optimization of monitoring data, reduce the data transmission burden, and improve real-time response capabilities; wavelet transform noise reduction filtering and interval statistics are used to eliminate abnormal points, which significantly improves the quality and reliability of the original data; time series decomposition and feature extraction are performed based on the preprocessed data set, combined with feature importance quantification and multi-source feature mapping, to achieve accurate expression of building status characteristics; through multi-dimensional parameter decomposition and data encryption transformation, the integrity of building status variables is guaranteed and the security of sensitive data is protected; gradient iteration is used to identify abnormal patterns, and combined with data enhancement processing and confidence interval operations, the accuracy and reliability of abnormal state identification are improved; through trend extrapolation prediction and multi-objective optimization, scientific decision-making of maintenance tasks and optimal allocation of resources are achieved; knowledge compression is used to extract maintenance experience, and through cross-domain mapping and group collaborative updating, a sustainable and evolving intelligent monitoring knowledge base is established, which deeply combines artificial intelligence technology with building monitoring practice and improves monitoring efficiency and accuracy.

[0032] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0033] (1) By sorting the building sensor data by timestamp, grouping and slicing the data using dynamic window length, and adjusting the slicing parameters according to the data distribution characteristics, the initial data segments are obtained;

[0034] (2) Mark the missing data points in the initial data segment, establish an interpolation benchmark based on the changing trend of the previous and next data, supplement the missing positions through piecewise linear interpolation, and combine the data continuity test to obtain a complete data sequence;

[0035] (3) Based on the sampling density distribution of the complete data sequence, the data sampling threshold of the edge computing node is partitioned and set. The sampling time interval is determined by adaptive adjustment of the data change rate. Combined with the cross-validation of the data between nodes, the distributed sampling data is obtained.

[0036] (4) Using the distributed sampling data as the basic signal, multi-scale wavelet basis function decomposition is performed, the energy proportion of the decomposed high-frequency signal is calculated, the filtering threshold is set by evaluating the importance of the wavelet transform coefficient, and the high-frequency signal is filtered to obtain the noise-reduced data;

[0037] (5) Sliding segment the noise reduction data according to fixed length, calculate the abnormality judgment benchmark based on interval statistical characteristics, classify the data points into abnormal levels according to the 3σ criterion, mark them according to the quantitative index of the abnormality degree, and obtain abnormal data points;

[0038] (6) Perform correlation analysis on abnormal data points and adjacent data, select the optimal replacement value based on the data distribution law, repair and reconstruct the data breakpoints through piecewise smoothing function, and combine data consistency verification to obtain the preprocessed data set.

[0039] Specifically, the timestamp records the precise moment of data collection, including complete information such as year, month, day, hour, minute, and second. The hierarchical sorting process first progressively sorts the data according to the different timestamp levels (year, month, day, etc.) to ensure the temporal integrity of the data. The dynamic window length refers to the adaptive adjustment of the data analysis time span based on data characteristics. Different window lengths are used for different building monitoring parameters: structural vibration data requires a shorter window (e.g., 1 minute) to capture transient responses, while temperature changes require a longer window (e.g., 1 hour) to reflect evolving data. Data slicing divides a continuous data stream into several interrelated data segments along the temporal dimension. Slicing parameters include window length, overlap ratio, and sampling interval, which are dynamically adjusted based on data distribution characteristics. Data distribution characteristics are characterized by calculating statistics such as the coefficient of variation, kurtosis, and skewness to describe the degree of dispersion and distribution of the data. When data fluctuates significantly, the window length is reduced and the overlap ratio is increased to capture rapidly changing characteristics. When data is relatively stable, the window length is increased to reduce redundant data.

[0040] Missing data point location marking is the process of identifying blank points or invalid values in a data series. Missing data can be caused by sensor failure, communication interruption, or external interference. The location process identifies the location and duration of missing points by examining the temporal continuity and validity of the data. The interpolation benchmark is established based on the changing trend of the data before and after the missing point. Local characteristics of the data (such as slope and curvature) are analyzed to determine the appropriate interpolation method. Piecewise linear interpolation is a commonly used interpolation method, employing different interpolation strategies for different types of data: linear interpolation is used for slowly changing data (such as temperature), while higher-order interpolation methods are used for rapidly changing data (such as acceleration). The sampling density distribution of a complete data series reflects the data distribution characteristics in the time domain. Sampling density is measured by the number of data points per unit time. A higher sampling density means more detailed data capture. The data sampling threshold of an edge computing node is the condition that triggers data collection. It includes a time threshold and a change threshold. Zoning is to adopt different sampling strategies for different areas based on the importance and changing characteristics of the data: a higher sampling density is used for critical areas (such as major load-bearing components), while a relatively lower sampling density is used for non-critical areas.

[0041] Adaptive adjustment of the data change rate is the core mechanism for dynamically optimizing the sampling interval. When monitored data changes rapidly, shortening the sampling interval improves data accuracy; when data changes slowly, increasing the sampling interval reduces data redundancy. Inter-node data cross-validation ensures the reliability of sampled data by comparing the consistency of data from adjacent nodes. Data from adjacent nodes should exhibit a certain degree of correlation and continuity; data that deviates significantly from this characteristic requires special marking and processing.

[0042] Multi-scale wavelet basis function decomposition can analyze the characteristics of signals at different scales. When performing wavelet decomposition on building monitoring data, first select a suitable wavelet basis function (such as Daubechies wavelet, Haar wavelet, etc.), and then decompose the signal into sub-signals in different frequency bands. High-frequency signals usually contain noise and interference components, and energy ratio analysis is required to distinguish between effective signals and noise. Energy ratio calculation is to evaluate the importance of the signal by calculating the ratio of the energy of the signal in each frequency band to the total energy. The importance evaluation of wavelet transform coefficients is based on the amplitude and frequency of occurrence of the coefficients to judge their contribution to the original signal. By setting an appropriate threshold, important wavelet coefficients are retained and minor coefficients are suppressed, thereby achieving signal noise reduction. High-frequency signal noise reduction filtering not only removes random noise, but also retains the mutation characteristics of the signal.

[0043] Sliding segmentation divides the denoised data into fixed-length segments with a certain overlap between adjacent segments to ensure data continuity. Interval statistical features include statistics such as mean, standard deviation, and extreme values, which are used to describe the central tendency and dispersion of data. The 3σ criterion is a commonly used anomaly detection method, which classifies data points that deviate from the mean by more than three standard deviations as anomalies. Anomaly classification further classifies anomalies into different levels based on the degree of deviation. The processing of anomalous data points requires considering the temporal and spatial correlation of the data. By analyzing the relationship between anomalies and nearby data points, an appropriate replacement strategy can be determined. Data distribution patterns include characteristics such as periodicity, trend, and randomness, which guide the repair process of anomalies. Piecewise smoothing functions are used to eliminate sudden changes and jumps in the data, ensuring that the repaired data retains its original variation characteristics.

[0044] Taking the structural health monitoring of a high-rise building as an example, the entire data preprocessing process is illustrated in detail. First, data from accelerometers on each floor are timestamped and hierarchically sorted. A 10-minute dynamic window is set to slice the vibration data. Analysis of the data's coefficient of variation reveals that when the building is subjected to wind loads, the volatility of the high-rise vibration data increases. In this case, the window length is shortened to 5 minutes to capture more detail. For missing data points, an interpolation benchmark is established based on the vibration characteristics of the preceding and following moments, and the missing data is supplemented using cubic spline interpolation. Once a complete data sequence is generated, the edge computing node dynamically adjusts the sampling frequency based on the rate of change of the vibration amplitude, increasing the sampling density when significant vibration is detected. The data is decomposed into six layers using the db4 wavelet, analyzing the energy distribution of each scale coefficient and setting a threshold to remove high-frequency noise. Finally, anomaly detection is performed on the processed data. Individual data points are found to exceed the 3σ range, often corresponding to sudden external loads. Comparison and analysis with adjacent sensor data confirms the authenticity of these outliers, and valuable anomaly records are retained.

[0045] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0046] (1) Divide the preprocessed data set into periodic segments on the time axis, identify the decomposition points based on the data change trend, extract the main periodic components through frequency domain transformation, and obtain the data periodic sequence;

[0047] (2) Through multi-scale time division of the data periodic sequence, the phase calibration of the periodic component is completed, and the time series component characteristics are extracted by combining signal reconstruction technology to obtain periodic feature data;

[0048] (3) Quantify the importance based on the periodic characteristic data, calculate the contribution ratio of each feature by the fluctuation amplitude, calibrate the weight parameter by normalization, and obtain the feature weight;

[0049] (4) Perform spatial transformation on the periodic feature data according to the feature weights, use feature projection to complete multi-source data alignment, and convert the coordinate mapping to a unified metric to obtain a unified feature space;

[0050] (5) Reduce the redundant dimensions in the unified feature space, select the dominant feature components based on the information retention threshold, construct the feature expression through dimensional reorganization, and obtain the feature expression vector;

[0051] (6) The feature expression vectors are structured and organized according to the spatiotemporal topological relationship, and the correlation strength between features is described by combining matrix operations. The effective feature combinations are screened through correlation verification to obtain the architectural feature matrix.

[0052] Specifically, intelligent assessment of building structural safety begins with periodic segmentation of preprocessed datasets. Intelligent structural monitoring first requires identifying the characteristic periods of different sensor data types, including diurnal deformations captured by structural deformation sensors (reflecting thermal expansion and contraction caused by temperature stress), weekly variations recorded by strain sensors (reflecting cumulative strains due to building loads), and seasonal periods monitored by displacement sensors (reflecting foundation settlement and concrete creep). Intelligent decomposition point identification, based on the abrupt change characteristics of the structural response data, intelligently calculates first-order strain differences and second-order stress differences to precisely locate moments when significant changes in structural performance occur. Intelligent frequency-domain structural analysis utilizes a fast Fourier transform to convert the building's time-domain response signals into a frequency-domain feature space, extracting the dominant periodic components and establishing a data period sequence. The multi-scale temporal analysis of the building intelligent monitoring system sets specific time windows for different structural response characteristics: a millisecond-level time window is used to monitor structural vibration characteristics (identifying the building's natural frequency and damping ratio), a minute-level time window is used to analyze temperature stress changes (assessing the impact of thermal stress on the structure), and an hour-level time window is used to study the effects of operational loads (monitoring cumulative structural deformation). Phase calibration in intelligent building monitoring ensures precise temporal alignment of structural response data by calculating intelligent cross-correlation functions between different sensor signals. Intelligent signal reconstruction combines the calibrated structural response characteristics at various scales to form a representation of building health.

[0053] During intelligent building safety assessments, the importance of periodic characteristic data is evaluated across multiple intelligent monitoring indicators, including structural response energy, vibration amplitude, and duration. The intelligent structural monitoring system uses peak analysis and root mean square (RMS) calculations to quantify the intensity of changes in the structural response signal. Intelligent feature contribution analysis calculates the weight coefficients of each monitoring indicator in the overall structural performance assessment and uses intelligent normalization to transform structural response parameters representing different physical quantities into a unified evaluation space. Intelligent weight calibration comprehensively considers the impact of each monitoring indicator on structural safety, assigning higher evaluation weights to features reflecting key structural performance. Intelligent spatial transformation transforms the dimensionality of structural periodic characteristic data based on feature weights. Intelligent building monitoring uses principal component analysis to map high-dimensional structural response features to the main deformation modal directions. Intelligent alignment of multi-source data addresses the issue of asynchronous sampling between different types of structural sensors, ensuring strict temporal alignment of all monitoring data through intelligent interpolation and resampling. Intelligent coordinate mapping unifies structural monitoring results from various physical quantities (such as displacement, strain, and acceleration) into a standardized feature space. However, the unified feature space used in intelligent building monitoring suffers from information redundancy, necessitating intelligent dimensionality reduction. The information retention threshold is intelligently calculated based on the cumulative variance contribution rate, ensuring that the key characteristic information of the structural state is retained after dimensionality reduction. Intelligent feature selection considers both the physical significance and engineering application value of the monitoring indicators. The dimensionality reorganization process reorganizes the selected key structural features according to the principles of structural mechanics, constructing an intelligent feature representation with clear engineering significance.

[0054] The intelligent building monitoring system organizes feature expression vectors based on the spatiotemporal topological relationships of the structure, fully considering the building's spatial structure and stress characteristics. Intelligent matrix operations describe the strength of associations between structural features, including calculations of the correlation coefficient matrix and characteristic distance matrix of the structural response. Intelligent correlation verification uses a set correlation threshold to screen for combinations of structural features with significant correlations, forming a building feature matrix.

[0055] For example, a building structure is equipped with an intelligent sensor network, including various monitoring devices such as structural strain sensors, displacement sensors, and accelerometers. The intelligent monitoring system performs periodic analysis on preprocessed data and finds that the temperature strain of the concrete structure exhibits a clear 24-hour periodicity. The building structure's fundamental period is approximately 3 seconds, while the wind-induced structural response exhibits irregular random vibration characteristics. Multi-scale intelligent analysis is used to extract structural features from these different periods: structural vibration characteristics from high-frequency data, and temperature deformation characteristics from low-frequency data.

[0056] In the displacement monitoring data, intelligent fluctuation analysis revealed that the characteristic contribution of top-floor horizontal displacement is the greatest, consistent with the deformation characteristics of high-rise buildings. Temperature strain monitoring revealed that the temperature effect is more pronounced on the middle floors, reflecting the thermal deformation patterns of the building. During the feature space conversion process, the intelligent monitoring system uniformly maps the structural response data of different physical quantities (displacement, strain, acceleration) into a standardized feature space. Intelligent principal component analysis (PCA) dimensionality reduction was performed to retain the main characteristic components that fully describe the structural state. Finally, based on the spatial layout of the structural components and the mechanical transmission relationships, these features were reorganized into a feature matrix reflecting the overall state of the building.

[0057] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0058] (1) Structural displacement, deformation stress, and vibration acceleration are extracted from the building feature matrix and split into multiple dimensions. The building load-bearing parameters are reconstructed through primary and secondary stress analysis. The building mechanical characteristics are obtained through inter-layer response decomposition, and a parameter decomposition sequence is obtained.

[0059] (2) Extract local features of the material stiffness coefficient, structural damping ratio, and natural frequency in the parameter decomposition sequence, calibrate the core indicators based on the deformation law of reinforced concrete structures, and obtain the building state variables through static and dynamic coupling analysis;

[0060] (3) Crack width, deflection change, and strain data in the building state variables are classified according to their sensitivity, and the structural stress and strain data are scrambled using a key, and sensitive parameters are protected through layered encryption.

[0061] (4) Analyze the foundation settlement, wall cracking degree and floor crack data from the sensitive parameter protection, build connection relationships with structural stress and strain as nodes, screen key associations according to safety thresholds, and obtain topological basic data;

[0062] (5) Extract the transfer characteristics of beam-column deformation, node displacement value and structural stiffness coefficient in the topological basic data, construct the damage propagation network through correlation strength calculation, characterize the variable dependency through the topological structure between parameters, and obtain the correlation topology map;

[0063] (6) The structural safety, component integrity and durability indicators in the associated topological map are reconstructed and combined, the building structure status is described through bearing capacity verification, and the building status indicators are obtained through hierarchical analysis.

[0064] Specifically, key structural parameters are extracted from the characteristic matrix collected by the building's intelligent sensor network. Structural displacement reflects the building's deformation state under external loads. The intelligent monitoring system uses displacement sensors to capture inter-story displacements in real time. Deformation stress values, measured by strain sensors, measure the stress state of structural components, reflecting the load-bearing system's stress conditions. Vibration acceleration, monitored by accelerometers, monitors the building's dynamic response characteristics. Intelligent multi-dimensional decomposition decomposes these physical quantities according to their spatial distribution and time series, determining the stress state of key load-bearing components through primary and secondary stress analysis. Inter-story response decomposition technology decomposes the overall building response into the relative responses of each floor, thereby generating a description of the building's mechanical characteristics. The parameter decomposition sequence in intelligent building monitoring includes key mechanical parameters of both materials and structures. Material stiffness coefficients reflect the deformation characteristics of structural materials and are calculated through intelligent strain analysis. Structural damping ratios characterize the building's ability to dissipate vibration energy and are intelligently identified through free vibration attenuation curves. Natural frequencies represent the building's inherent dynamic characteristics and are intelligently extracted through the structural response under environmental excitation. Local feature extraction technology addresses the nonlinear deformation characteristics of reinforced concrete structures, establishing a mapping between deformation patterns and material properties. Static-dynamic coupling analysis takes into account static performance (such as bearing capacity) and dynamic characteristics (such as damping characteristics) to form a set of building state variables.

[0065] Sensitivity analysis of building state variables is extremely important. Crack width is a direct indicator for assessing the extent of structural damage, and intelligent monitoring tracks it in real time through crack monitoring sensors. Deflection changes reflect the degree of component deformation and are precisely measured using laser displacement sensors. Strain data reflects the stress state within the material. Sensitivity is categorized based on the degree to which these parameters affect structural safety. Intelligent encryption algorithms are used to protect sensitive data, and a layered encryption strategy ensures data security. Key structural performance indicators are extracted from sensitive parameters. Foundation settlement reflects the stability of the foundation and is intelligently monitored through precise leveling. Wall cracking indicates the integrity of load-bearing walls and is quantified using intelligent image recognition technology. Floor slab crack data reflects changes in the load-bearing capacity of the floor slab. Using structural stress and strain as fundamental nodes, a mechanical correlation network is established between components, and important structural response correlations are screened by setting safety thresholds.

[0066] The topological basic data for intelligent building monitoring includes structural deformation characteristics. The deformation of beams and columns reflects the stress state of the main structure, the displacement value of the node represents the deformation of key connection parts, and the structural stiffness coefficient reflects the overall anti-deformation ability. Through intelligent correlation analysis, a damage propagation network is established to reveal the development law and propagation path of structural damage. The topological structure between parameters describes the mutual influence relationship between each monitoring indicator, forming a correlation topology map. By analyzing the correlation topology map, the health status of the building structure is evaluated. Structural safety is a comprehensive indicator to measure the reliability of the overall structure. The integrity of the component reflects the damage state of each component, and the durability index predicts the long-term performance of the structure. The current status of the structure is quantitatively evaluated through bearing capacity verification, and the building status index is obtained by combining the hierarchical analysis method.

[0067] For example, this building utilizes a reinforced concrete frame shear wall structure, and its intelligent monitoring system utilizes a multi-layered sensor network. During routine monitoring, the intelligent analysis system first extracts interstory displacement angles from displacement sensor data. This data is combined with concrete strain measured by strain sensors and structural vibration responses collected by accelerometers to form a preliminary parameter decomposition sequence through multi-dimensional data fusion. Subsequently, based on the concrete elastic modulus and steel bar strain hardening properties determined from material test data, combined with the measured structural damping ratio (obtained through environmental vibration testing) and natural frequency (obtained through intelligent spectrum analysis), a building state variable system is established. If the intelligent monitoring system detects a crack in a shear wall, it immediately initiates localized, intensified monitoring: intelligent crack monitors continuously track crack development while adding additional strain monitoring points along the wall. This sensitive data is stored in a database after undergoing multiple encryption steps. If the intelligent analysis identifies a trend of uneven foundation settlement, multi-source data correlation analysis is initiated: settlement observation data is intelligently correlated with superstructure deformation data to identify patterns of stress redistribution caused by settlement and predict potential damage development pathways.

[0068] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0069] (1) The crack growth rate, foundation settlement, and concrete strength change rate in the building status indicators are subjected to gradient optimization iteration. The numerical range is limited by the foundation bearing capacity boundary constraint, and the parameter update amount is calculated through structural response analysis to obtain the iterative optimization result;

[0070] (2) The distribution characteristics of shear wall cracking degree, steel bar corrosion rate, and concrete carbonization depth were extracted from the iterative optimization results. The damage types were divided through cluster analysis. Rare structural defects were screened by structural deformation distance to obtain rare anomaly categories.

[0071] (3) Structural crack patterns, deformation mutations, and vibration responses in rare anomaly categories are sampled according to the damage probability distribution. Typical damage samples are generated through component stress perturbations, and abnormal working conditions are supplemented in the structural feature space to obtain an enhanced data set.

[0072] (4) Statistically analyze the material strength degradation, anchoring performance loss, and structural stiffness degradation rate in the enhanced data set, calculate the confidence limit based on the structural reliability, and obtain the damage threshold through failure probability density estimation to obtain the confidence interval boundary;

[0073] (5) Quantify the structural bearing capacity loss, seismic performance degradation, and durability attenuation based on the confidence interval boundary. Determine the damage level by hazard level classification. Calibrate the abnormality level according to the degree of structural response deviation to obtain the abnormality degree index.

[0074] (6) The abnormality index is associated with the dynamic characteristics of the building structure, and warning information is generated through structural safety judgment. The impact range is analyzed based on the damage expansion mechanism to obtain building warning data.

[0075] It should be noted that the crack growth rate is determined by continuously tracking the rate of change of crack width over time using intelligent crack monitoring equipment. Foundation settlement is measured by measuring the vertical displacement of the foundation using high-precision settlement monitoring instruments. The concrete strength change rate is assessed using intelligent nondestructive testing equipment to assess concrete strength degradation. During the intelligent gradient optimization process, foundation bearing capacity boundary constraints ensure that the calculated results are consistent with project reality. Structural response analysis continuously updates the values of various parameters to achieve iterative optimization results that meet project requirements.

[0076] Damage identification in intelligent building monitoring extracts key damage features from iterative optimization results. Shear wall cracking is monitored in real time using intelligent image recognition technology. Rebar corrosion rates are assessed using electrochemical impedance spectroscopy. Concrete carbonization depth is measured using an intelligent carbonization detector to measure the depth of the carbonization front. Intelligent clustering analysis groups these damage features based on similarity. Structural deformation distance calculations identify anomalies that differ significantly from common damage patterns, thereby generating rare anomaly categories. The intelligent monitoring system performs data enhancement on these identified rare anomaly categories. Structural crack patterns include characteristics such as crack direction, width, and depth. Deformation mutations reflect the instantaneous deformation of structural components, while vibration responses describe changes in the structure's dynamic characteristics. Sampling is performed based on the damage probability distribution, generating new damage conditions by altering the component stress state. This enriches the sample library of abnormal conditions and forms an enhanced dataset.

[0077] In structural reliability analysis, it is necessary to accurately calculate the confidence limit. First, the calculation formula for the probability of structural failure is defined as:

[0078]

[0079] Among them, R f represents the probability of structural failure, is the joint probability density function of the structural parameters, ψ(g(x)) is the limit state function, and g(x) is the structural performance function.

[0080] The structural damage threshold is determined by estimating the failure probability density:

[0081]

[0082] Among them, D t is the damage threshold, λ is the correction coefficient, w i is the weight factor, ξ i is the damage characteristic value, θ i is the damage sensitivity, γ i is the uncertainty coefficient, and n is the number of features.

[0083] Structural performance is evaluated based on the confidence interval boundaries. Structural bearing capacity loss is determined through load testing and finite element analysis. Seismic performance degradation is assessed based on changes in the structural period extension rate and damping ratio. Durability attenuation takes into account the deterioration of material properties and the influence of environmental factors. The intelligent hazard level classification takes various indicators into consideration, determines the abnormality level according to the degree of deviation of the structural response from the normal state, and obtains an abnormality degree index. Building intelligent early warning combines the abnormality degree index with the dynamic characteristics of the structure. Dynamic characteristics include parameters such as natural frequency, vibration mode and damping ratio. The correspondence between abnormal state and changes in dynamic characteristics is established through intelligent correlation analysis. Structural weak points are analyzed based on the damage extension mechanism, the potential impact range of the damage is assessed, and building early warning data is generated.

[0084] For example, intelligent monitoring equipment detected cracks in a shear wall. Continuous monitoring revealed an accelerating crack growth rate. Simultaneously, foundation settlement monitoring indicated uneven settlement exceeding alarm thresholds, and a significant decrease in local concrete strength. The intelligent analysis system immediately initiated iterative optimization calculations, factoring in foundation bearing capacity constraints and analyzing the structural response. Data analysis revealed an unusual cracking pattern in the shear wall, significantly different from typical thermal and shrinkage cracks. A combined damage pattern, characterized by the combined effects of steel corrosion and concrete carbonization, was also detected. Intelligent clustering analysis labeled this damage pattern as a rare anomaly. Subsequently, by varying the load conditions, similar damage states were simulated to expand the anomaly sample library. Reliability analysis and failure probability calculations determined the critical damage threshold, and accordingly, a graded warning standard was established. As monitoring continued, the intelligent analysis system detected a significant decrease in local structural stiffness. Comparative analysis of dynamic characteristics predicted the potential damage propagation path, enabling timely warnings.

[0085] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0086] (1) The structural safety, crack propagation rate, and component damage degree in the building early warning data are reconstructed into time series, extracted segment by segment according to the concrete strength degradation cycle, and the component degradation trend is calibrated by displacement deformation spectrum analysis to obtain a trend prediction benchmark;

[0087] (2) Extrapolate the beam and column deformation, reinforcement stress level, and crack depth in the trend prediction benchmark, correct for environmental factors such as earthquakes and wind loads, and obtain the service condition through structural displacement correlation analysis;

[0088] (3) The structural damage level distribution, concrete spalling range, and component bearing capacity changes in the service conditions are screened by reinforcement resource constraints and sorted according to the principle of structural force balance to obtain a task sequence table;

[0089] (4) Match the task sequence list with historical reinforcement records, select the optimal reinforcement combination through structural reinforcement effect evaluation, and obtain the maintenance task priority through bearing capacity recovery comparison;

[0090] (5) Allocate resources for the structural reinforcement schemes with maintenance task priority, determine the construction time by calculating the concrete repair cycle, select the optimal scheme by calculating the benefit ratio, and obtain the maintenance resource allocation;

[0091] (6) The maintenance resource allocation and structural warning level are combined, and a maintenance plan is generated according to the structural reinforcement specification constraints. The maintenance process is constructed according to the construction sequence to obtain the building maintenance strategy.

[0092] Specifically, the structural safety index reflects the overall safety status of the building and is derived through a comprehensive assessment of continuously monitored stress, strain, and displacement data. The crack growth rate describes the rate of structural crack growth over time and is obtained by continuously recording crack width changes using intelligent crack monitoring equipment. The component damage index quantifies the extent of damage to structural components and is assessed based on nondestructive testing data. Intelligent time series reconstruction technology first segments the data according to the natural cycle of concrete strength degradation (typically key time points such as 28 days, 90 days, and 180 days). The data within each time period reflects the degradation characteristics of different stages. Displacement and deformation spectrum analysis converts time domain data into the frequency domain using Fourier transform, identifying the main deformation modes and frequency components, thereby calibrating the component degradation trend. The trend prediction benchmark includes core indicators for the evolution of structural performance. Beam and column deformation is monitored in real time using displacement sensors, reflecting the deformation state of major load-bearing components. Rebar stress levels are measured using strain sensors, indicating the degree of stress on the rebar. Crack depth is determined using nondestructive testing methods such as ultrasonic testing. Intelligent extrapolation calculations are based on this monitoring data, taking into account the influence of environmental factors: seismic loads are corrected using ground motion parameters, and wind loads are calibrated based on wind pressure coefficients and wind-induced vibration effects. Structural displacement correlation analysis establishes correlations between displacements at each monitoring point, resulting in a description of the operating conditions.

[0093] Based on operating condition analysis, intelligent maintenance management assesses the distribution of structural damage levels, creating damage maps that reflect the damage status of each component. The extent of concrete spalling is determined through high-precision 3D scanning, and changes in component bearing capacity are calculated based on load test data. Reinforcement resource constraints include factors such as material availability, construction equipment, and skilled personnel. The principle of structural force equilibrium dictates that the reinforcement sequence must ensure the overall stability of the structure during the repair process. The task sequence table considers these factors and prioritizes repair tasks. Historical reinforcement records contain detailed information on previous repair projects, such as reinforcement plans, construction techniques, and material selection. The intelligent matching process compares and analyzes the current task sequence table with historical records to assess the applicability of different reinforcement options. Structural reinforcement effectiveness evaluation is based on indicators such as the degree of bearing capacity recovery and durability improvement after reinforcement, and a comprehensive score is used to determine the optimal reinforcement combination. Maintenance task prioritization takes into account both project urgency and resource efficiency.

[0094] Maintenance resource allocation is a multi-objective optimization process. For structural reinforcement schemes with different priorities, the resource requirements such as materials, equipment, and manpower are first determined, and the construction sequence is arranged in combination with the maintenance cycle of concrete repair (usually including stages such as demolding, maintenance, and strength reaching standards). The benefit ratio calculation comprehensively considers the maintenance cost investment and performance improvement effect, and selects the implementation plan with the best economic and technical indicators. The maintenance resource allocation plan needs to meet the project quality requirements and construction period constraints. The formulation of the intelligent maintenance strategy for buildings organically combines the maintenance resource allocation with the structural warning level. The structural reinforcement specification has clear requirements for material selection, structural requirements, construction technology, etc., and the maintenance plan must strictly follow these technical specifications. The arrangement of the construction sequence needs to take into account the structural force transmission path to ensure the structural safety during the reinforcement process. The formation of a building maintenance strategy includes implementation plans and quality control measures.

[0095] For example, intelligent monitoring revealed varying degrees of damage to the building's main load-bearing frame, necessitating a scientific repair and reinforcement plan. Time series analysis of building early warning data revealed an accelerating crack growth rate in the frame beams and significant degradation of the concrete strength of some columns. Displacement-deformation spectrum analysis determined the deformation trends of the damaged components and established a trend prediction benchmark. Subsequently, structural performance was extrapolated based on the monitoring data, correcting for environmental factors, taking into account the region's seismic intensity and base wind pressure. Analysis revealed strong displacement correlation in the frame joints, indicating that the damage had impacted the overall performance of the structure. Combined with on-site inspection results, the area of concrete spalling and the extent of steel reinforcement corrosion were determined, leading to the development of a preliminary repair plan. A review of historical repair records revealed that similar frame structures had been reinforced with methods such as steel plate bonding and steel cladding. After comparative analysis, a more suitable carbon fiber reinforcement technology was selected. The repair plan prioritized construction according to the principle of "primary before secondary, upper before lower, and interior before exterior," and scheduled the construction period based on the curing time and strength development of the carbon fiber material. The maintenance strategy formed not only ensures the reinforcement effect, but also minimizes the impact on the building's use function.

[0096] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0097] (1) Extract the processing flow of building maintenance strategy in sections, obtain the operation sequence by disassembling the maintenance steps, organize the core processes in time sequence, and obtain maintenance operation data;

[0098] (2) Compress the maintenance operation data to remove redundancy, extract key feature points through data dimensionality reduction, filter and retain the core content according to the information weight, and obtain maintenance experience;

[0099] (3) Discretely sample maintenance experience, establish cross-domain mapping relationships through feature space transformation, align feature distributions through coordinate transformation, and obtain knowledge features;

[0100] (4) The knowledge features are verified in different building scenarios, the optimal migration path is matched through similarity calculation, and the migration content is selected according to the feature importance to obtain the migration mapping result;

[0101] (5) Perform group distribution analysis on the migration mapping results, select effective knowledge through maintenance effect evaluation, determine the update content according to the group voting mechanism, and obtain maintenance knowledge;

[0102] (6) The maintenance knowledge is organized in a hierarchical structure, a knowledge graph is constructed through association rule mining, and a retrieval index is established through semantic annotation to obtain an intelligent monitoring knowledge base.

[0103] Specifically, segmented processing, based on the characteristics of structural maintenance projects, divides maintenance strategies into a preparation phase (including site surveys and scheme design), an implementation phase (including structural reinforcement and material repair), and an acceptance phase (including quality inspection and performance evaluation). Intelligent maintenance step decomposition breaks down the work content of each phase into specific operational units. For example, crack repair steps include crack cleaning, grouting material preparation, and pressure grouting. These operational units are organized in a time-sequential manner according to construction processes and quality control requirements to generate standardized maintenance operation data. Intelligent compression processing of maintenance operation data is achieved by removing redundant operations and optimizing process steps. Data dimensionality reduction techniques are used to extract key feature points, such as control parameters and quality inspection standards for key processes. Information weighting is calculated based on the degree of impact of each operational step on the maintenance outcome, with higher-weighted content including structural reinforcement processes, material ratio parameters, and maintenance conditions. The maintenance experience obtained through screening and organization reflects the most valuable technical points in engineering practice.

[0104] Discrete sampling of maintenance experience is the basis of knowledge transfer. By selecting representative sample points in maintenance experience, feature space transformation is performed. The establishment of cross-domain mapping relationship can be expressed as:

[0105]

[0106] Among them, M(x) is the mapping function, α i is the feature importance coefficient, ω i is the weight factor, h i (x) is the feature conversion function, σ is the activation function, β iis the bias parameter, η is the mapping error, and n is the feature dimension. Coordinate transformation is used to align features across different maintenance scenarios, resulting in standardized knowledge features. The knowledge features are validated across multiple building maintenance scenarios. Similarity calculations are used to identify target scenarios suitable for knowledge transfer, taking into account factors such as building type, structural form, and damage characteristics. Feature importance assessment is based on the verified results of the transfer performance, prioritizing transfer content that performs well across multiple scenarios to form the transfer mapping results.

[0107] Group distribution analysis focuses on the applicability of knowledge across different buildings. Maintenance effectiveness evaluation uses multiple indicators, including the degree of bearing capacity recovery, durability improvement effect, and construction quality compliance rate. The group voting mechanism uses statistical analysis to determine the maintenance knowledge with the greatest promotional value, and screens out technical content that has been verified to have good practical effects and a wide range of applications. The construction of the intelligent knowledge base adopts a hierarchical organizational structure. The first layer is the basic knowledge layer, which contains basic information such as material properties and structural requirements; the middle layer is the technical process layer, which includes detailed processes for various repair and reinforcement methods; the upper layer is the experience decision-making layer, which provides maintenance plan selection recommendations under different damage conditions. Association rule mining technology is used to establish connections between knowledge units to form a knowledge graph. Semantic annotation uses professional terminology to index knowledge content and establish multi-dimensional retrieval channels.

[0108] For example, a frame structure building experiences concrete cracking and rebar corrosion, necessitating structural repair. First, relevant maintenance processes are extracted from the maintenance strategy library, including processes such as crack repair, rebar anti-corrosion, and concrete patching. Intelligent analysis breaks these processes down into specific steps, such as crack repair, which includes crack detection and location, crack cleaning, epoxy resin preparation, pressure grouting, and curing, forming an operational sequence. Data compression preserves the most critical technical parameters, including the relationship between crack width and grouting material selection, the pressure control range for pressure grouting, and curing temperature and humidity requirements. These insights are then transformed into feature space to establish a knowledge mapping relationship with similar buildings. The applicability of these insights is verified in repair projects on other similar buildings, and maintenance knowledge is continuously optimized through performance evaluation. This validated maintenance knowledge is then organized into an intelligent monitoring knowledge base to provide technical support for subsequent building maintenance projects.

[0109] In a specific embodiment, the step of discretely sampling maintenance experience includes:

[0110] (1) The structural crack repair process, concrete reinforcement methods, and component reinforcement measures in maintenance experience are selected for sampling points in a time sequence. Discrete data nodes are obtained by disassembling the maintenance process flow. The sampling positions are calibrated according to the construction specification requirements to obtain a discrete sampling sequence.

[0111] (2) Characteristic analysis is performed on the crack sealing depth, concrete strength improvement value, and steel corrosion treatment degree in the discrete sampling sequence. A parameter mapping relationship is established through structural reinforcement effect evaluation. The characteristic space is calibrated by the bearing capacity recovery rate to obtain the space conversion benchmark;

[0112] (3) The component reinforcement process, structural reinforcement method, and durability improvement measures in the spatial conversion benchmark are mapped across domains, and characteristic correspondence is established by calculating the degree of damage repair. The mapping parameters are determined according to the requirements of the reinforcement specification to obtain the cross-domain characteristic relationship;

[0113] (4) The coordinate system of the concrete repair process, crack treatment method and steel protection measures in the cross-domain feature relationship is transformed, and a feature description system is established through quantitative analysis of the reinforcement effect. The coordinate benchmark is calibrated through the structural performance improvement index to obtain an aligned coordinate system;

[0114] (5) The structural reinforcement parameters, repair process indicators and reinforcement effect evaluation under the aligned coordinate system are reorganized, and the feature verification standard is established through the repair quality evaluation. The effective features are screened according to the requirements of the engineering specifications to obtain the feature distribution map;

[0115] (6) Knowledge extraction is performed on the reinforcement process flow, repair quality indicators and durability evaluation parameters in the characteristic distribution map, and a characteristic knowledge system is constructed through maintenance experience summary. The knowledge characteristics are obtained through repair effect verification.

[0116] The structural crack repair process develops specific repair plans for different types of cracks (such as temperature cracks, load cracks, and settlement cracks). Each crack type has its own specific treatment process, such as surface coating for fine cracks, low-pressure grouting for small cracks, and pressure grouting for through cracks. Concrete reinforcement methods include increasing the cross-section, attaching steel plates, and encapsulating steel sections, each with its own applicable conditions and construction key points. Component reinforcement measures are tailored to different component types, such as beams, columns, and slabs, using corresponding reinforcement technologies, such as rebar reinforcement for beams and carbon fiber winding for columns. These process flows are chronologically broken down into key nodes, such as material preparation, surface treatment, reinforcement construction, and maintenance, forming a discrete sampling sequence. Within the discrete sampling sequence, the crack sealing depth is a key indicator for evaluating the effectiveness of crack repair. The actual filling depth of the grouting material is measured using ultrasonic testing and other methods. The concrete strength increase is determined by rebound testing, core drilling, and other testing methods. The degree of steel corrosion treatment is evaluated through electrochemical testing to assess the anti-corrosion effect. The effectiveness of structural reinforcement is assessed through load testing and dynamic testing to verify the improved load-bearing capacity of reinforced components. Through these characteristic analyses, parameter mapping relationships are established, converting qualitative process parameters into quantitative evaluation indicators, forming a standardized feature space.

[0117] The various technical measures within the spatial transformation benchmark require cross-domain mapping to ensure their applicability to diverse building maintenance scenarios. The mapping of component reinforcement processes considers factors such as material properties, construction techniques, and environmental conditions. The mapping of structural reinforcement methods requires an assessment of structural type, stress characteristics, and operational requirements. Durability enhancement measures focus on indicators such as environmental impact, service life, and maintenance costs. By quantitatively calculating the extent of damage repair, characteristic relationships between different maintenance scenarios are established to ensure the effective translation of technical measures. Coordinate system transformation of cross-domain characteristic relationships is a key step in achieving knowledge standardization. Concrete repair processes, including surface repair, crack grouting, and partial replacement, require unified evaluation criteria. Crack treatment methods involve technical parameters such as grouting material selection, pressure control, and curing requirements, which require standardization. Rebar protection measures, including cathodic protection, anti-corrosion coatings, and epoxy resin sealing, require a quantitative evaluation of their effectiveness. Through quantitative analysis of reinforcement effectiveness, unified measurement standards for various technical indicators are established, forming a standardized, aligned coordinate system.

[0118] During feature reorganization within the aligned coordinate system, structural reinforcement parameters include technical indicators such as material strength, structural requirements, and construction techniques; repair process indicators encompass key parameters such as material ratio, construction temperature, and curing conditions; and reinforcement effect evaluation encompasses aspects such as increased bearing capacity, improved durability, and construction quality. Through repair quality assessment, feature verification standards are established, comprehensively considering technical feasibility, economic rationality, and construction operability to select the most valuable technical features. Knowledge extraction from feature distribution maps is the final step in developing standardized maintenance experience. Knowledge extraction of the reinforcement process includes the basis for process selection, key construction operation points, and quality control measures; extraction of repair quality indicators focuses on testing methods, acceptance criteria, and assessment rules; and durability evaluation parameters address environmental factors, service life, and maintenance cycles. Through systematic summarization of repair experience, a feature knowledge system is constructed, providing a scientific basis for intelligent building monitoring and maintenance.

[0119] For example, a building's exterior wall suffers from extensive cracks and concrete spalling, necessitating systematic repair and reinforcement. First, the repair process is extracted from a database of similar cases. The crack type and damage severity are analyzed to select an appropriate repair process. Through discretization, the repair process is broken down into key nodes, such as cleaning, grouting, patching, and maintenance, and the control parameters for each node are recorded. The repair results are then quantitatively evaluated. Ultrasonic testing is used to confirm the grouting integrity of the cracks, and rebound testing is used to measure the concrete strength recovery in the repaired area. These test data are standardized to form measurable characteristic indicators. Comparative analysis with other similar engineering cases establishes a mapping between repair processes and effectiveness evaluation. Successful repair experiences are translated into standardized process specifications, including material selection criteria, construction process requirements, and quality control measures. These experiences are then adapted to different building maintenance scenarios through feature space transformation. Through practical verification, they are continuously refined and optimized to form a maintenance knowledge system.

[0120] The above describes the smart building monitoring method based on artificial intelligence in the embodiment of the present application. The following describes the smart building monitoring system based on artificial intelligence in the embodiment of the present application. Figure 2 In the embodiments of the present application, an embodiment of the smart building monitoring system based on artificial intelligence includes:

[0121] Sampling module 201 is used to import building sensor data into edge computing nodes for distributed sampling, perform wavelet transform noise reduction filtering on the high-frequency signals of the sampled data, and remove outliers based on interval statistics to obtain a preprocessed data set;

[0122] Extraction module 202, configured to perform time series decomposition according to the preprocessed data set to extract data periodic features, quantify feature weights according to feature importance, unify feature space transformations using multi-source feature mapping, and generate a building feature matrix;

[0123] Establishing module 203, for obtaining building state variables through multi-dimensional parameter decomposition based on the building characteristic matrix, adopting data encryption transformation to realize sensitive parameter protection, establishing a topological structure between parameters through correlation calculation, and generating building state indicators;

[0124] Identification module 204, for inputting the building status indicators into a gradient iterative process to identify abnormal patterns, performing data enhancement processing on rare abnormal categories, classifying the degree of abnormality in combination with confidence interval calculations, and outputting building early warning data;

[0125] Prediction module 205, configured to predict usage conditions based on trend extrapolation of the building early warning data, determine maintenance task priorities through multi-objective optimization, select maintenance plans based on benefit ratio calculations, and generate a building maintenance strategy;

[0126] Update module 206 is used to apply knowledge compression to the building maintenance strategy to extract maintenance experience, use cross-domain mapping to migrate knowledge features, and update maintenance knowledge through group collaboration to build an intelligent monitoring knowledge base.

[0127] Through the collaborative cooperation of the above-mentioned components, distributed sampling is carried out through edge computing nodes, which enables on-site processing and transmission optimization of monitoring data, reduces the data transmission burden, and improves real-time response capabilities; wavelet transform noise reduction filtering and interval statistics are used to eliminate outliers, significantly improving the quality and reliability of the original data; time series decomposition and feature extraction are performed based on the preprocessed data set, combined with feature importance quantification and multi-source feature mapping, to achieve accurate expression of building status characteristics; through multi-dimensional parameter decomposition and data encryption transformation, the integrity of building status variables is guaranteed while the security of sensitive data is protected; gradient iteration is used to identify abnormal patterns, and combined with data enhancement processing and confidence interval operations, the accuracy and reliability of abnormal state identification are improved; through trend extrapolation prediction and multi-objective optimization, scientific decision-making for maintenance tasks and optimal allocation of resources are achieved; knowledge compression is used to extract maintenance experience, and through cross-domain mapping and group collaborative updating, a sustainable and evolving intelligent monitoring knowledge base is established, which deeply integrates artificial intelligence technology with building monitoring practice and improves monitoring efficiency and accuracy.

[0128] The present application also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the artificial intelligence-based smart building monitoring method.

[0129] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0130] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0131] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A smart building monitoring method based on artificial intelligence, characterized in that: The artificial intelligence-based smart building monitoring method includes: Import building sensor data into edge computing nodes for distributed sampling, perform wavelet transform noise reduction and filtering on the high-frequency signals of the sampled data, and remove outliers based on interval statistics to obtain a preprocessed data set; Performing time series decomposition according to the preprocessed data set to extract data period features, quantifying feature weights according to feature importance, and using multi-source feature mapping to unify feature space transformation to generate a building feature matrix; Based on the building characteristic matrix, building state variables are obtained through multi-dimensional parameter decomposition, sensitive parameters are protected by data encryption transformation, and a topological structure between parameters is established through correlation calculation to generate building state indicators; Input the building status indicators into a gradient iterative process to identify abnormal patterns, perform data enhancement processing on rare abnormal categories, classify the degree of abnormality in combination with confidence interval calculation, and output building early warning data; Based on the building early warning data, trend extrapolation is carried out to predict the usage conditions, maintenance task priorities are determined through multi-objective optimization, maintenance plans are screened based on benefit ratio calculations, and building maintenance strategies are generated; The building maintenance strategy is applied with knowledge compression to extract maintenance experience, knowledge features are transferred using cross-domain mapping, maintenance knowledge is updated through group collaboration, and an intelligent monitoring knowledge base is constructed.

2. The method for monitoring smart buildings based on artificial intelligence according to claim 1, characterized in that: The method imports the building sensor data into the edge computing node for distributed sampling, performs wavelet transform noise reduction filtering on the high-frequency signal of the sampled data, and removes abnormal points based on the interval statistics method to obtain a preprocessed data set, including: By sorting the building sensor data by timestamp, grouping and slicing the data using dynamic window length, and adjusting the slicing parameters according to the data distribution characteristics, the initial data fragments are obtained. The missing data points in the initial data segment are located and marked, an interpolation benchmark is established based on the changing trend of the previous and next data, the missing positions are supplemented by piecewise linear interpolation, and a complete data sequence is obtained by combining data continuity test; According to the sampling density distribution of the complete data sequence, the data sampling threshold of the edge computing node is partitioned and set, the sampling time interval is determined by adaptive adjustment of the data change rate, and the distributed sampling data is obtained by combining cross-validation of data between nodes; Using the distributed sampling data as a basic signal, multi-scale wavelet basis function decomposition is performed, energy proportion of the decomposed high-frequency signal is calculated, filtering thresholds are set by evaluating the importance of wavelet transform coefficients, and denoising data is obtained by filtering the high-frequency signal; The noise reduction data is segmented into sliding segments of fixed length, anomaly determination benchmarks are calculated based on interval statistical characteristics, data points are classified into abnormal levels using the 3σ criterion, and abnormal data points are marked based on quantitative indicators of abnormality levels to obtain abnormal data points; The abnormal data points are correlated with adjacent data, the optimal replacement value is selected based on the data distribution law, the data breakpoints are repaired and reconstructed through a piecewise smoothing function, and the preprocessed data set is obtained by combining data consistency verification.

3. The method for monitoring smart buildings based on artificial intelligence according to claim 1, characterized in that: The method of performing time series decomposition according to the preprocessed data set to extract data period features, quantifying each feature weight according to feature importance, and using multi-source feature mapping to unify feature space transformation to generate a building feature matrix includes: Divide the preprocessed data set into periodic segments on the time axis, identify decomposition points according to the data change trend, extract the main periodic components through frequency domain transformation, and obtain a data periodic sequence; Through multi-scale time division of the data periodic sequence, phase calibration is completed for the periodic component, and the time series component features are extracted in combination with signal reconstruction technology to obtain periodic feature data; Quantifying the importance based on the periodic characteristic data, calculating the contribution ratio of each characteristic through the fluctuation amplitude, and calibrating the weight parameter by normalization to obtain the characteristic weight; Performing spatial transformation on the periodic feature data according to the feature weights, aligning multi-source data using feature projection, and converting the coordinates to a unified metric to obtain a unified feature space; Reducing redundant dimensions in the unified feature space, selecting dominant feature components according to an information retention threshold, constructing feature expressions through dimensional reorganization, and obtaining feature expression vectors; The feature expression vectors are structured and organized according to the spatiotemporal topological relationship, and the correlation strength between features is described by combining matrix operations. The effective feature combination is screened through correlation verification to obtain the building feature matrix.

4. The method for monitoring smart buildings based on artificial intelligence according to claim 1, characterized in that: The method is based on the building feature matrix, obtains building state variables through multi-dimensional parameter decomposition, adopts data encryption transformation to realize sensitive parameter protection, establishes the topological structure between parameters through correlation operation, and generates building state indicators, including: Extracting structural displacement, deformation stress value and vibration acceleration from the building feature matrix for multi-dimensional decomposition, reconstructing the building load-bearing parameters through primary and secondary stress analysis, obtaining the building mechanical characteristics through inter-layer response decomposition, and obtaining a parameter decomposition sequence; Extract local features of the material stiffness coefficient, structural damping ratio and natural frequency in the parameter decomposition sequence, calibrate core indicators according to the deformation law of reinforced concrete structure, and obtain the building state variables through static and dynamic coupling analysis; Crack width, deflection change, and strain data in the building state variables are classified according to their sensitivity, and the structural stress and strain data are scrambled using a key to obtain the sensitive parameter protection through layered encryption; The foundation settlement, wall cracking degree and floor cracking data are parsed from the sensitive parameter protection, the structural stress and strain are used as nodes to build a connection relationship, and the key associations are screened according to the safety threshold to obtain the topological basic data; Extracting the transfer characteristics of beam-column deformation, node displacement value and structural stiffness coefficient in the topological basic data, constructing a damage propagation network through correlation strength calculation, and characterizing the variable dependency through the topological structure between parameters to obtain a correlation topology map; The structural safety, component integrity and durability indicators in the associated topological map are reconstructed and combined, the building structure status is described through bearing capacity verification, and the building status indicator is obtained through hierarchical analysis.

5. The method for monitoring smart buildings based on artificial intelligence according to claim 1, characterized in that: The method includes inputting the building status indicators into a gradient iterative process to identify abnormal patterns, performing data enhancement processing on rare abnormal categories, grading the degree of abnormality in combination with confidence interval calculation, and outputting building early warning data, including: The crack growth rate, foundation settlement, and concrete strength change rate in the building status indicators are subjected to gradient optimization iteration, the numerical range is limited by the foundation bearing capacity boundary constraint, and the parameter update amount is calculated through structural response analysis to obtain an iterative optimization result; Extracting the distribution characteristics of shear wall cracking degree, steel bar corrosion rate and concrete carbonization depth from the iterative optimization results, classifying the damage types through cluster analysis, and screening rare structural defects through structural deformation distance to obtain the rare anomaly category; Structural crack patterns, deformation mutations, and vibration responses in the rare anomaly categories are sampled according to the damage probability distribution, typical damage samples are generated through component stress perturbation, and abnormal working conditions are supplemented in the structural feature space to obtain an enhanced data set; Statistically analyzing the material strength degradation, anchoring performance loss, and structural stiffness degradation rate in the enhanced data set, calculating confidence limits based on structural reliability, and obtaining damage thresholds through failure probability density estimation to obtain confidence interval boundaries; The structural bearing capacity loss, seismic performance degradation and durability attenuation are quantified based on the confidence interval boundary, the damage level is determined by hazard level classification, and the abnormality level is calibrated according to the degree of deviation of the structural response to obtain an abnormality degree index; The abnormality index is associated with the dynamic characteristics of the building structure, and warning information is generated through structural safety judgment. The impact range is analyzed based on the damage expansion mechanism to obtain the building warning data.

6. The method for monitoring smart buildings based on artificial intelligence according to claim 1, characterized in that: The method of predicting the usage condition based on the building early warning data by trend extrapolation, determining the maintenance task priority through multi-objective optimization, screening the maintenance plan based on the benefit ratio calculation, and generating the building maintenance strategy includes: Reconstructing the structural safety, crack propagation rate, and component damage degree in the building early warning data into time series, extracting them in sections according to the concrete strength degradation cycle, and calibrating the component degradation trend through displacement and deformation spectrum analysis to obtain a trend prediction benchmark; The beam and column deformation, reinforcement stress level, and crack depth in the trend prediction benchmark are extrapolated and calculated, and after correction for environmental factors such as earthquakes and wind loads, the operating condition is obtained through structural displacement correlation analysis. The structural damage level distribution, concrete spalling range and component bearing capacity changes in the said use conditions are screened by reinforcement resource constraints and sorted according to the principle of structural force balance to obtain a task sequence table; Matching the task sequence table with historical reinforcement records, selecting the optimal reinforcement combination through structural reinforcement effect evaluation, and obtaining the maintenance task priority through bearing capacity recovery comparison; Allocate resources for the structural reinforcement scheme with the maintenance task priority, determine the construction time by calculating the concrete repair cycle, select the optimal scheme by calculating the benefit ratio, and obtain the maintenance resource configuration; The maintenance resource configuration is combined with the structural warning level, a maintenance plan is generated according to the structural reinforcement specification constraints, and a maintenance process is constructed according to the construction sequence to obtain the building maintenance strategy.

7. The method for monitoring smart buildings based on artificial intelligence according to claim 1, characterized in that: The method of applying knowledge compression to the building maintenance strategy to extract maintenance experience, utilizing cross-domain mapping to migrate knowledge features, and updating maintenance knowledge through group collaboration to construct an intelligent monitoring knowledge base includes: Extract the processing flow of the building maintenance strategy in sections, disassemble the maintenance steps to obtain the operation sequence, organize the core processes in chronological order, and obtain maintenance operation data; Compressing the maintenance operation data to remove redundancy, extracting key feature points through data dimensionality reduction, and filtering and retaining core content according to information weight to obtain the maintenance experience; Discrete sampling is performed on the maintenance experience, a cross-domain mapping relationship is established through feature space transformation, and feature distribution is aligned through coordinate transformation to obtain the knowledge feature; The knowledge features are verified in different building scenarios, the optimal migration path is matched through similarity calculation, and the migration content is selected according to the feature importance to obtain the migration mapping result; Performing group distribution analysis on the migration mapping results, screening effective knowledge through maintenance effect evaluation, and determining update content according to a group voting mechanism to obtain the maintenance knowledge; The maintenance knowledge is organized according to a hierarchical structure, a knowledge graph is constructed through association rule mining, and a retrieval index is established through semantic annotation to obtain the intelligent monitoring knowledge base.

8. The method for monitoring smart buildings based on artificial intelligence according to claim 7, characterized in that: The discrete sampling of the maintenance experience, establishing a cross-domain mapping relationship through feature space transformation, and aligning feature distribution through coordinate transformation to obtain the knowledge features include: The structural crack repair process, concrete reinforcement methods and component reinforcement measures in the maintenance experience are selected for sampling points in a time sequence, and the maintenance process is disassembled to obtain discrete data nodes. The sampling positions are calibrated according to the construction specification requirements to obtain a discrete sampling sequence; Performing feature analysis on the crack sealing depth, concrete strength improvement value, and steel corrosion treatment degree in the discrete sampling sequence, establishing a parameter mapping relationship through structural reinforcement effect evaluation, calibrating the feature space through the bearing capacity recovery rate, and obtaining a space conversion benchmark; The component reinforcement process, structural reinforcement method and durability improvement measures in the spatial conversion benchmark are cross-domain mapped, and a characteristic correspondence is established by calculating the degree of damage repair. The mapping parameters are determined according to the requirements of the reinforcement specification to obtain a cross-domain characteristic relationship; The concrete repair process, crack treatment method, and steel protection measures in the cross-domain feature relationship are transformed into coordinate systems. A feature description system is established through quantitative analysis of the reinforcement effect. The coordinate reference is calibrated using the structural performance improvement index to obtain an aligned coordinate system. The structural reinforcement parameters, repair process indicators and reinforcement effect evaluation under the aligned coordinate system are reorganized, feature verification standards are established through repair quality evaluation, and effective features are screened according to engineering specifications to obtain a feature distribution map; Knowledge extraction is performed on the reinforcement process flow, repair quality indicators and durability evaluation parameters in the characteristic distribution map, a characteristic knowledge system is constructed based on maintenance experience summary, and the knowledge characteristics are obtained through repair effect verification.

9. An artificial intelligence-based smart building monitoring system, used to implement the artificial intelligence-based smart building monitoring method according to any one of claims 1 to 8, characterized in that: The artificial intelligence-based smart building monitoring system includes: The sampling module is used to import building sensor data into the edge computing node for distributed sampling, perform wavelet transform noise reduction and filtering on the high-frequency signals of the sampled data, and remove outliers based on the interval statistics method to obtain a preprocessed data set; An extraction module is configured to perform time series decomposition according to the preprocessed data set to extract data period features, quantify feature weights according to feature importance, unify feature space transformations using multi-source feature mapping, and generate a building feature matrix; Establish a module for obtaining building state variables through multi-dimensional parameter decomposition based on the building characteristic matrix, adopting data encryption transformation to realize sensitive parameter protection, establishing a topological structure between parameters through correlation calculation, and generating building state indicators; an identification module for inputting the building status indicators into a gradient iterative process to identify abnormal patterns, performing data enhancement processing on rare abnormal categories, classifying the degree of abnormality in combination with confidence interval calculations, and outputting building early warning data; A prediction module is used to predict the usage conditions based on the building early warning data by trend extrapolation, determine the maintenance task priority through multi-objective optimization, select maintenance plans based on the benefit ratio calculation, and generate a building maintenance strategy; The updating module is used to apply knowledge compression to the building maintenance strategy to extract maintenance experience, use cross-domain mapping to migrate knowledge features, update maintenance knowledge through group collaboration, and build an intelligent monitoring knowledge base.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the artificial intelligence-based smart building monitoring method according to any one of claims 1 to 8 is implemented.

Images