A method and system for health monitoring of a smart building

Abstract

The application discloses a kind of health monitoring method and system of intelligent building, belong to building structure health monitoring field, method includes: by multiple sensors real-time acquisition inside and outside intelligent building multidimensional data, multidimensional data include environmental data, the structure data of intelligent building, equipment state data and personnel activity data;Multidimensional data is preprocessed, and multidimensional data after preprocessing is obtained;According to multidimensional data after preprocessing, utilize the health monitoring model that is trained in advance, output the health condition analysis result of intelligent building, it includes the suitable degree of environmental condition, the stable degree of building structure, equipment health degree and the risk degree of personnel activity;When health condition analysis result indicates that there is health anomaly in intelligent building, send early warning signal;According to the type of health anomaly, determine the repair scheme of intelligent building.The method can improve the building security, comfort and management efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of building health monitoring, and in particular to a health monitoring method and system for intelligent buildings. BACKGROUND

[0002] With the rapid advancement of urbanization, intelligent buildings, as an important part of modern city development, are increasingly entering people's daily lives. Intelligent buildings usually integrate information technology, automation control technology, sensing technology and big data analysis technology, which can improve the functionality, comfort and energy efficiency of buildings. However, as the service life of buildings increases and the influence of external environmental changes, the health condition of buildings deteriorates to varying degrees, leading to building structural safety hazards, equipment failures, unsuitable environmental conditions and other problems, thereby affecting the use effect, operation efficiency and personnel safety of buildings.

[0003] At present, the health monitoring of most buildings mainly relies on periodic manual inspection and traditional monitoring equipment, which has the disadvantages of untimely data acquisition, delayed information feedback and untimely maintenance response, and it is difficult to achieve comprehensive, continuous and accurate monitoring of the health condition of buildings.

[0004] Therefore, it is of great significance to develop an intelligent building health monitoring method based on comprehensive data analysis and artificial intelligence optimization to improve the intelligent level of building management, reduce building operation and maintenance costs, prolong the service life of buildings, and ensure personnel safety and comfort. SUMMARY

[0005] Therefore, the embodiments of the present application provide a health monitoring method and system for intelligent buildings to solve the above technical problems.

[0006] To achieve the above-mentioned purpose, in a first aspect, a health monitoring method for intelligent buildings is provided, the method comprising the following steps:

[0007] Real-time acquisition of multi-dimensional data inside and outside the intelligent building by a plurality of sensors arranged at a plurality of target monitoring positions of the intelligent building, the multi-dimensional data including environmental data, structural data of the intelligent building, equipment status data and personnel activity data; the structural data includes displacement, deformation, stress, vibration and crack width of the intelligent building;

[0008] Preprocessing the multi-dimensional data to obtain preprocessed multi-dimensional data;

[0009] According to the preprocessed multi-dimensional data, a pre-trained health monitoring model is used to output the health condition analysis result of the intelligent building, the health condition analysis result including the suitability of environmental conditions, the stability of building structures, the health of equipment and the risk of personnel activities;

[0010] issue a warning signal when the health condition analysis result indicates that the smart building has a health abnormality;

[0011] determine a repair scheme of the smart building according to the type of the health abnormality, the repair scheme being at least associated with building structure repair and reinforcement of the smart building.

[0012] In a second aspect, a health monitoring system of a smart building is provided, and the system comprises:

[0013] a data acquisition module comprising a plurality of sensors arranged at a plurality of target monitoring positions of the smart building, configured to acquire multi-dimensional data inside and outside the smart building in real time, the multi-dimensional data comprising environmental data, structure data of the smart building, equipment state data and personnel activity data, and the structure data comprising displacement, deformation, stress, vibration and crack width of the smart building;

[0014] a data preprocessing module configured to preprocess the multi-dimensional data to obtain preprocessed multi-dimensional data;

[0015] a health analysis module configured to output a health condition analysis result of the smart building by using a pre-trained health monitoring model according to the preprocessed multi-dimensional data, the health condition analysis result comprising suitability of environmental conditions, stability of building structures, health of equipment and risk of personnel activities;

[0016] a warning module configured to issue a warning signal when the health condition analysis result indicates that the smart building has a health abnormality;

[0017] a repair scheme generation module configured to determine a repair scheme of the smart building according to the type of the health abnormality, the repair scheme being at least associated with building structure repair and reinforcement of the smart building.

[0018] The above technical solution has the following beneficial technical effects:

[0019] The smart building health monitoring method realizes real-time, comprehensive evaluation and dynamic optimization of the building health state through multi-dimensional data fusion and a closed-loop feedback mechanism. Through the collaborative monitoring of the environment, structure, equipment and personnel activities, the accuracy and timeliness of abnormal detection are improved; the intelligent diagnosis based on the health monitoring model can accurately locate the abnormal source, and the dynamic iteration of the self-adaptive repair scheme effectively shortens the fault response time and reduces the maintenance cost; at the same time, through the data-driven warning and repair closed-loop management, not only the service life of the building is prolonged, but also the energy utilization efficiency and personnel safety protection capability are optimized, forming an intelligent operation and maintenance system with self-learning ability. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings are used to better understand the present application, and do not constitute undue limitations on the present application. Among them:

[0021] Figure 1 is a flow chart of the health monitoring method of the smart building of the embodiment of the present application;

[0022] Figure 2 is a mind map of the repair scheme of the smart building of the embodiment of the present application;

[0023] Figure 3 is a functional block diagram of the health monitoring system of the smart building of the embodiment of the present application;

[0024] Figure 4 is another functional block diagram of the health monitoring system of the smart building of the embodiment of the present application;

[0025] Figure 5 is a structural schematic diagram of the computer system of the embodiment of the present application. DETAILED DESCRIPTION

[0026] The exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to help understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and structures are omitted in the following description for the sake of clarity and conciseness. Embodiment one

[0027] As shown in Figure 1 , the present embodiment provides a health monitoring method of a smart building, which comprises the following steps:

[0028] S10: Real-time acquisition of multi-dimensional data inside and outside the smart building by a plurality of sensors arranged at a plurality of target monitoring positions of the smart building, wherein the multi-dimensional data comprises environmental data, structural data of the smart building, equipment state data and personnel activity data.

[0029] Specifically, in the present embodiment, various types of sensors are deployed in the smart building to obtain multi-dimensional data in real time. For environmental data, temperature and humidity sensors, carbon dioxide concentration sensors, light intensity sensors, and air quality sensors (e.g., sensors that can detect pollutants such as formaldehyde and PM2.5) are installed in different floors and functional areas to collect environmental parameters such as temperature, humidity, carbon dioxide concentration, light intensity, and pollutant concentration in the air. In terms of building structure data acquisition, pressure sensors, strain sensors, vibration sensors, and displacement sensors are installed at key structural locations of the building, such as beams, columns, walls, foundations, and roofs, to monitor structural stress, deformation, vibration amplitude, and displacement changes in real time. For equipment status data, current sensors, voltage sensors, temperature sensors, and vibration sensors are installed on various equipment in the smart building, such as air conditioning systems, elevators, lighting equipment, water and power supply equipment, and ventilation equipment, to obtain equipment status parameters such as operating current, voltage, operating temperature, and vibration frequency. For personnel activity data, cameras, infrared sensors, and access control systems are deployed at locations such as public areas, entrances, and stairwells. Cameras monitor personnel activity trajectories and gathering conditions through image recognition technology, infrared sensors detect the presence and movement of personnel, and access control systems record personnel entry and exit times and identity information to obtain personnel activity data. All sensors are connected to the data acquisition module through wired or wireless communication to transmit real-time multi-dimensional data to the data processing center.

[0030] S20: Preprocessing the multi-dimensional data to obtain preprocessed multi-dimensional data.

[0031] Specifically, in the present embodiment, when preprocessing the multi-dimensional data obtained in step S10, data cleaning is first performed to remove obviously abnormal data using pre-set rules and algorithms, such as data exceeding the reasonable range caused by sensor failure, data with errors during transmission, etc. Then, data denoising is performed using appropriate denoising algorithms for different types of data, such as Fourier transform for frequency domain filtering of periodic noise in environmental data and equipment status data, and median filtering or Gaussian filtering algorithm for random noise in structural data and personnel activity data. Then, data normalization is performed to convert different types and dimensions of data to a unified numerical range, such as mapping data to the [0, 1] interval using the min-max normalization method, to facilitate subsequent model processing. In addition, for missing data, linear interpolation, polynomial interpolation, or mean filling based on adjacent sensor data are used to complete the data according to the time series characteristics and correlation of the data, ensuring that the preprocessed multi-dimensional data is complete, accurate, and standardized.

[0032] S30: output the health condition analysis result of the smart building according to the pre-processed multi-dimensional data and the pre-trained health monitoring model, the health condition analysis result including the suitability of environmental conditions, the stability of building structures, the health of equipment, and the risk of personnel activities.

[0033] Specifically, in this embodiment, after obtaining the pre-processed multi-dimensional data in step S20, the pre-trained health monitoring model is used for analysis. The health monitoring model is a neural network model based on deep learning, such as a combined model of convolutional neural network (CNN) and long short-term memory network (LSTM), which can effectively process multi-dimensional time series data. In the model training stage, a large amount of historical multi-dimensional data of smart buildings and corresponding manually labeled health condition analysis results are collected as training data sets. The model parameters are optimized through back propagation algorithm and gradient descent method, so that the model can accurately learn the mapping relationship between multi-dimensional data and health conditions. The pre-processed multi-dimensional data is input into the trained health monitoring model, and the health monitoring model outputs the suitability of environmental conditions, the stability of building structures, the health of equipment, and the risk of personnel activities through multi-layer neural network feature extraction and nonlinear transformation. Among them, the suitability of environmental conditions is calculated according to the matching degree of temperature, humidity, air quality and other environmental data with the human comfort interval and the normal operation interval of building equipment; the stability of building structure is determined based on the comparison and analysis of structure data with building design standards and historical normal state data; the health of equipment is evaluated by matching the equipment state data with the normal operation parameter range and fault feature mode of the equipment; the risk of personnel activities is judged according to whether there is abnormal gathering, illegal behavior and other situations in the personnel activity data.

[0034] S40: when the health condition analysis result indicates that the smart building has health abnormalities, an early warning signal is issued.

[0035] Specifically, in the present embodiment, when any one or more of the suitability of the environmental conditions, the stability of the building structure, the health of the equipment, or the risk of the personnel activities exceeds the preset threshold value in the health condition analysis result output in step S30, indicating that the smart building has a health anomaly, the system will issue a warning signal. The warning signal includes various forms such as sound warning, light warning, short message warning, and system interface prompt. For example, when the suitability of the environmental conditions is lower than the safety threshold value, a beeping alarm sound is emitted in the corresponding area of the smart building, and a warning is prompted by flashing the light; when the stability of the building structure abnormally decreases, in addition to the on-site sound and light warning, a short message warning is also sent to the relevant personnel of the building management department, notifying them to take immediate action; when the health of the equipment is detected to be about to fail, abnormal equipment information is displayed on the monitoring system interface of the smart building, and a specific prompt sound is emitted; when the risk of personnel activities is high, for example, it is detected that personnel gathering may cause a safety accident, a safety prompt is emitted through the broadcast system, and warning information is displayed on the display screen in the relevant area. The issuance of the warning signal can timely remind the relevant personnel to pay attention to the health anomaly of the smart building, so as to quickly take countermeasures.

[0036] S50: determining a repair scheme of the smart building according to the type of the health anomaly, the repair scheme being at least associated with repair and reinforcement of the smart building.

[0037] Specifically, in the present embodiment, according to the type of the health anomaly determined in step S40, the system will automatically determine the corresponding repair scheme. If the type of the health anomaly is that the environmental conditions are unsuitable, for example, the temperature is too high or too low, the air quality is not up to standard, etc., the repair scheme can include automatically adjusting the operating parameters of the air conditioning system, increasing the operating frequency of the ventilation equipment, or starting the air purification equipment, etc., to improve the environmental conditions. When the type of the health anomaly is that the building structure is unstable or deformed, the system will suggest to immediately stop the use of the relevant area, arrange professional building detection personnel to conduct detailed inspection and evaluation of the structure, formulate a structure reinforcement or repair scheme according to the detection result, and notify the construction unit to carry out construction. For equipment health anomaly, such as equipment failure or performance degradation, the repair scheme includes automatically switching to a backup device, and generating a device maintenance work order to notify the equipment maintenance personnel to repair or replace parts. If the type of the health anomaly is that the personnel activities are risky or abnormal, for example, there is a safety hazard in the personnel gathering area, the repair scheme includes guiding personnel to evacuate in an orderly manner through broadcast, setting warning signs in the risk area, increasing security personnel for on-site management, etc. After the repair scheme is determined, the system will send the scheme to the relevant executing departments or personnel, and track the repair process to ensure that the health anomaly of the smart building is timely and effectively handled, and the normal operating state is restored.

[0038] As Figure 2As shown, in some embodiments, when the building structure abnormality type is structure deformation, a first repair scheme associated with repair and reinforcement of the smart building is determined as follows:

[0039] For the first deformation range of slight deformation (deformation within the allowable deviation range but close to the upper limit value), the stress condition of the deformation part is analyzed in combination with the original building structure design drawings. If the deformation is caused by local load concentration, the load at the part can be reduced by adjusting the use function, for example, moving heavy equipment away from the area. According to the construction specification, the structure members around the deformation part are checked, and if connection loosening is found, the connection is tightened according to the specification requirements, such as tightening the bolts, re-welding the joints, etc. The reinforcement measure of pasting carbon fiber cloth is adopted, according to the shape and size of the deformation part, the appropriate carbon fiber cloth is cut, the concrete surface is treated according to the construction specification requirements, and then the structure glue is applied to paste the carbon fiber cloth on the surface of the deformation part to enhance the tensile capacity of the structure and limit the further development of the deformation.

[0040] For the second deformation range of moderate deformation (deformation exceeds the allowable deviation range but does not affect the overall stability of the structure), an unloading scheme is developed in combination with the building structure design and construction specification. By setting up temporary support structures such as steel supports or jacks above the deformation part, the upper load is partially transferred to reduce the stress on the deformation part. For concrete structures, the cross-section reinforcement method can be used. According to the structure calculation, the size and reinforcement of the added concrete are determined, the original structure surface is treated by chiseling and cleaning, the reinforcement is implanted, and then the concrete is poured to make the added part work together with the original structure to improve the bearing capacity and stiffness of the structure. For steel structure deformation, the stiffening rib welding method can be used for reinforcement. According to the deformation condition and design specification requirements, stiffening ribs are welded at the weak parts of the steel beam or steel column to enhance the local stability and overall stiffness of the structure.

[0041] For the third deformation range of severe deformation (large deformation and affecting the overall stability of the structure), personnel are immediately organized to evacuate the site, and obvious warning signs are set up to prevent unrelated personnel from entering the dangerous area. A detailed overall reinforcement scheme is developed, and the external prestressing reinforcement method is used. Prestressed tendons are arranged outside the structure to apply a reverse force to the structure through tensioning of the prestressed tendons to offset part of the deformation and improve the stress state of the structure. Part of the severely deformed and irreparable structure members are removed and rebuilt according to the original design and construction specification requirements. During the removal and reconstruction process, the protection of the surrounding structure is ensured to avoid further damage. The first deformation range, the second deformation range, and the third deformation range increase in turn.

[0042] In some embodiments, when the building structure abnormality type is structure crack, a second repair scheme associated with repair and reinforcement of the smart building is determined as follows:

[0043] For micro cracks with a first width range (crack width less than 0.05mm), the cracks are cleaned to remove dust and debris from the surface. According to the construction specifications, surface sealing method is used for treatment. Epoxy mortar and other materials are used to coat the surface of the cracks to prevent water and harmful media from entering and improve the durability of the structure.

[0044] For general cracks with a second width range (crack width between 0.05mm - 0.3mm), pressure grouting treatment is used for the cracks. First, drill holes along both sides of the crack, then use pressure grouting equipment to inject epoxy resin and other grouting materials into the crack to fill the crack gap and restore the integrity and waterproof performance of the structure. Check the structural components around the crack, if stress concentration caused by temperature changes, concrete shrinkage and other reasons is found, steel plates or carbon fiber cloth can be pasted on both sides of the crack for reinforcement to disperse stress and prevent further expansion of the crack.

[0045] For severe cracks with a third width range (crack width greater than 0.3mm or crack penetrating structural components), detailed detection and analysis are needed first to determine the specific causes of the cracks. Causes include foundation settlement, structural overload, concrete quality problems, construction defects, etc. After analyzing the causes of the cracks, different treatment methods are taken according to the specific circumstances. If the cracks are caused by foundation settlement, the foundation needs to be reinforced. Reinforcement methods include using cast-in-place piles, static pressure piles and other measures to improve the bearing capacity of the foundation and prevent further expansion of the cracks. If the cracks are caused by structural overload, the stressed parts need to be redesigned or strengthened, such as by adding support structures or strengthening the load-bearing capacity of beams and columns. In addition, if the cracks are caused by concrete quality problems or construction defects, the damaged parts need to be removed and the concrete needs to be poured again to restore the integrity of the structure. Repair measures should include cleaning and repairing the cracks. First, remove loose materials such as dust, debris, etc. from the cracks, then choose appropriate repair materials (such as epoxy resin, epoxy mortar, etc.) according to the width and depth of the cracks to fill and seal to prevent water and harmful substances from entering. In addition, for larger cracks or insufficient structural bearing capacity, steel plate reinforcement and carbon fiber cloth reinforcement can be used. By pasting steel plates or carbon fiber cloth on both sides of the crack, the strength and durability of the structure are enhanced to restore the integrity of the structure.

[0046] For penetrating cracks, a combination of steel plate pasting and pressure grouting can be used for repair. First, pressure grouting is used for the cracks, then steel plates are pasted on both sides of the cracks, and the steel plates are connected to the structural components by bolts or welding to enhance the bearing capacity and integrity of the structure.

[0047] In some embodiments, when the building structure anomaly type is structural material performance deterioration, the following third repair scheme associated with the repair and reinforcement of the smart building is determined:

[0048] For concrete material deterioration (e.g., carbonation, reinforcement corrosion, etc.), for a concrete structure with mild carbonation, a concrete protective agent can be applied to prevent further intrusion of harmful gases such as carbon dioxide and to slow down the carbonation process. If corrosion of the reinforcement is found, the concrete at the corrosion site is first removed until the uncorroded reinforcement is exposed. The reinforcement surface is then treated, such as by sanding, chemical rust removal, etc., and then painted with anti-rust paint. The removed concrete is repaired according to the construction specification requirements. Polymer concrete or high-strength non-shrinkage grouting material can be used for filling to ensure that the repaired concrete is tightly combined with the original structure and the load-bearing capacity of the structure is restored.

[0049] For steel structure material deterioration (e.g., steel corrosion, fatigue damage, etc.), for steel surface corrosion, treatment is performed according to the degree of corrosion. Mild corrosion can be treated by sandblasting to remove the rust layer on the steel surface, and then applying a corrosion-resistant coating. Severe corrosion requires cutting and replacing the severely corroded parts, and the replaced steel needs to be treated for corrosion. If the steel structure has fatigue damage, the redundancy of the structure can be increased or reinforcement measures can be taken to improve the fatigue resistance of the structure. For example, steel plates or carbon fiber cloth can be welded or bonded to the tension area of the steel beam to share part of the stress and reduce the impact of fatigue damage. Regularly inspect and maintain the steel structure, check and tighten the connection parts of the structure according to the design and construction specifications to ensure the safety and reliability of the structure.

[0050] In intelligent building health monitoring, structure deformation detection uses total station, level, and other measuring instruments for coordinate and elevation measurement, laser scanners for three-dimensional model acquisition, and strain and displacement sensors for dynamic monitoring. Structure crack detection uses crack width measurement instruments to measure width and non-destructive equipment such as ultrasonic flaw detectors to detect internal cracks. For concrete, rebound hammer, carbonation depth measurement instrument, core sampling, etc. are used to detect strength, carbonation degree, and mechanical properties. For steel structures, magnetic particle flaw detector, ultrasonic thickness gauge, chemical analysis, and fatigue test equipment are used to detect defects, thickness, chemical composition, and fatigue performance.

[0051] The technical scheme above realizes real-time collection of environment, structure, equipment state and personnel activity data of the intelligent building through multi-dimensional sensors, realizes preprocessing of the data such as data cleaning, noise reduction, normalization and missing data completion, and ensures the integrity and reliability of the data; the multi-dimensional data are intelligently analyzed by using a deep learning model, and quantitative evaluation results of the environment suitability degree, the structure stability degree, the equipment health degree and the personnel activity risk degree can be accurately output, thereby realizing systematic diagnosis of the health state of the building; through diversified early warning modes such as sound and light, short message, system interface and the like, an abnormal response mechanism can be triggered in real time, and a closed-loop management system is formed in combination with an automatically generated differential repair scheme (for example, equipment parameter adjustment, structure detection and maintenance, personnel diversion management and the like), thereby effectively improving the comprehensiveness, real-time performance and accuracy of the intelligent building health monitoring, and early identification of environmental safety hazards, structure performance degradation, equipment failure risks and personnel gathering risks is realized, intelligent decision support is provided for safe operation of the building, efficient maintenance of equipment, comfortable environment regulation and control and personnel safety management, manual inspection cost is reduced, and the reliability and emergency response capability of the building system are enhanced. Embodiment Two

[0052] In this embodiment, according to the intelligent building health monitoring method, the step S10 comprises:

[0053] S101: Real-time collection of environment data in the intelligent building by an environment sensor, wherein the environment data comprises temperature, humidity, air quality and illumination intensity.

[0054] In this embodiment, the environment data in the intelligent building is collected by distributedly deployed environment sensors. Specifically, in the areas such as rooms, corridors, halls and equipment rooms on each floor, temperature and humidity sensors are installed at intervals of every 5-10 square meters to collect temperature (accuracy ±0.3℃) and relative humidity (accuracy ±2% RH) in real time; air quality sensors (for example, SPS30 type particulate matter sensor and CCS811 type gas sensor combination) are deployed at the ceiling or ventilation port position to detect PM2.5, PM10 concentration and volatile organic compound content for representing air quality; illumination intensity sensors (for example, BH1750 type digital sensor) are installed near the windows and artificial lighting areas to monitor the illumination intensity (unit: lux) of natural light and artificial light sources in real time. All the environment sensors are connected with the data collection module through Modbus or ZigBee communication protocol to ensure that data is collected at least once per minute and uploaded to the central server.

[0055] S102: Real-time collection of structure data of the intelligent building by a structure health monitoring sensor, wherein the structure data comprises displacement, deformation, stress, vibration and crack width of the intelligent building.

[0056] Specifically, for the collection of intelligent building structure data, structural health monitoring sensors are deployed at key load-bearing parts and vulnerable joint parts of the building. Among them, resistance strain gauges are pasted at beam-column joints, shear wall bottoms, foundation slabs and other positions, and static strain gauges are used to monitor the stress changes of the structure in real time (accuracy ±0.1% FS); laser displacement sensors are installed on the roof, floor overhang parts and elevator shaft inner walls to measure the displacement deformation of the structural members by emitting laser beams (accuracy ±1 μm); acceleration vibration sensors are fixed on the surfaces of each floor slab and core wall to collect structural vibration signals at a sampling frequency of 100 Hz, which are used to analyze vibration frequency, amplitude and other parameters; for masonry walls or concrete structures prone to cracking, crack width sensors are installed at crack monitoring points to measure crack width changes through precise resistance wire deformation (resolution 0.01 mm). The above sensors transmit data to the structural health monitoring subsystem through wired cables (shielded twisted pair) or LoRa wireless modules.

[0057] S103: Real-time collection of equipment state data of the intelligent building through equipment state monitoring sensors, the equipment state data including operation state data of the power system, the heating system, the ventilation system and the air conditioning system.

[0058] Specifically, the collection of equipment state data is realized through special sensors integrated in each system equipment: current transformers and voltage sensors are installed on transformers, power distribution cabinets and power transmission lines of the power system to monitor three-phase voltage, current and active power and other parameters in real time; thermocouple temperature sensors and pressure sensors are deployed on the surfaces of boilers, pipelines and heat exchangers of the heating system to collect water supply temperature, return water pressure and flow data; wind speed sensors and pressure difference sensors are installed at fan, air duct and air inlet positions of the ventilation system to monitor ventilation volume and pipeline pressure difference; temperature sensors, humidity sensors and electronic expansion valve opening degree sensors are installed at the compressor, condenser and terminal air outlet of the air conditioning system to obtain supply air temperature, refrigeration power, heating power and equipment operating current in real time. All equipment sensors are connected to the equipment management system through industrial Ethernet (Modbus TCP protocol) or 485 bus to realize second-level data update.

[0059] S104: Real-time collection of personnel activity data inside the intelligent building through personnel positioning and monitoring devices, the personnel activity data including personnel distribution density, personnel activity trajectory and personnel stay duration in different areas.

[0060] Specifically, the collection of personnel activity data relies on a multi-modal fusion personnel positioning and monitoring device. UWB positioning base stations are deployed on the ceilings of various areas in the intelligent building, and are combined with positioning tags (integrating accelerometers and gyroscopes) worn by personnel to achieve real-time positioning with centimeter-level accuracy, obtain personnel coordinates and activity trajectories; infrared beam sensors are installed in corridors, stairwells and other passageways to count the frequency of personnel flow between areas through a counting module; binocular cameras are installed at main entrances and in elevators, combined with deep learning target detection algorithms (such as YOLOv8) to identify the number of personnel, distribution density and stay duration (achieved through a trajectory tracking algorithm); pressure-sensitive tiles (such as thin film pressure sensor arrays) are laid on the ground in personnel gathering areas such as conference rooms and restaurants to assist in verifying personnel density data. All monitoring devices transmit data to the personnel management server through Wi-Fi or 5G networks, and store the data in the database after privacy protection processing.

[0061] The advantage of the embodiment is that through the joint application of multiple sensors, comprehensive and real-time monitoring of various aspects of the intelligent building is achieved. Environmental sensors provide accurate temperature, humidity and other data, which is beneficial to ensure the suitability of the internal environment of the building; structural health monitoring sensors can detect the stability of the building structure in real time and timely detect possible risks; equipment status monitoring sensors ensure the efficient operation of various equipment in the building and avoid equipment failures; and the collection of personnel activity data helps to optimize the use efficiency and safety management of the building space. This method can provide comprehensive and accurate health status evaluation and early warning for intelligent buildings, effectively improving the safety, comfort and energy efficiency of the building. Embodiment Three

[0062] In the embodiment, the step S20 comprises:

[0063] S201: denoising the multi-dimensional data to obtain purified data.

[0064] Specifically, in the denoising processing stage of step S201, differentiated filtering algorithms are adopted for different types of multi-dimensional data. For environmental data (data with periodic characteristics such as temperature, humidity, etc.), wavelet transform denoising is adopted: first, the time series data is decomposed by multiple layers of wavelet (for example, db4 wavelet basis is selected, and the number of decomposition layers is set to 3 layers), high-frequency noise components are identified and attenuated in the frequency domain, and then the purified signal is reconstructed by inverse wavelet transform; for vibration acceleration signals in structural data, Kalman filter is used for dynamic denoising, state space model of structural vibration is established (state vector includes displacement, velocity and acceleration), residual error between sensor measurement value and predicted value is used to update state estimation recursively, and environmental vibration interference is effectively filtered out; for pulse type noise in equipment state data (such as current transient peak), median filter (window size is set to 5 sampling points) is used to remove isolated noise points; the positioning trajectory jitter problem in personnel activity data is smoothed by moving average filter (window size is set to 30 seconds) to ensure the continuity of position data. All denoising algorithms are implemented through data processing engine (such as Scipy library of Python), supporting multi-thread parallel processing.

[0065] S202: Abnormal data points are removed by performing anomaly detection on the purified data to obtain cleaned data.

[0066] Specifically, in step S202, the detection of abnormal data points is realized by combining statistical methods and machine learning algorithms. First, for numerical data (such as stress, voltage, PM2.5 concentration), IQR (Interquartile Range) method is used to set dynamic threshold: the 25th percentile (Q1) and the 75th percentile (Q3) of the data are calculated, and the abnormal value is defined as the data point less than Q1-1.5IQR or greater than Q3+1.5IQR, which is automatically marked and removed; for time series data (such as structural displacement and device running power), isolated forest algorithm is used to detect local anomalies, and the isolation degree of data points is quantified by constructing random binary tree, and the data points with isolation score exceeding 0.8 are judged as abnormal; for spatial correlation data (such as the correlation between personnel density and area), the spatial distance clustering algorithm (DBSCAN) is used to identify outliers, and the neighborhood radius is set to 2 meters and the minimum sample number is set to 5 people, and the abnormal aggregation data deviating from the main clustering cluster is corrected. During the anomaly detection process, the system automatically generates an abnormal data report, records the abnormal type, occurrence time, and associated sensor number, which is used for model optimization.

[0067] S203: The cleaned data is standardized to obtain standardized data.

[0068] Specifically, in step S203, the standardized processing uniformly converts the cleaned data into a standard numerical range according to the input requirements of the subsequent health monitoring model. For a neural network model (such as the CNN-LSTM model of step S30), a min-max normalization is adopted to map the data to the interval [0, 1]; for a distance-based model such as a support vector machine (SVM), a Z-score standardization is adopted to make the data conform to the standard normal distribution. For multi-source heterogeneous data (for example, the unit of temperature is ℃, the unit of stress is MPa, and the unit of light intensity is lx), the system automatically identifies the data dimension and calls the corresponding standardization module, supports online standardization of real-time data stream, and ensures that the standardized data is compatible with the input requirements of multiple models.

[0069] S204: performing time series analysis on the standardized data to obtain preprocessed data.

[0070] Specifically, in the time series analysis stage of step S204, the standardized data is first sorted by timestamp to generate a time series matrix with equal time intervals (for example, 1 minute). For data with missing timestamps, cubic spline interpolation is used for completion to ensure the continuity of the time series; then the sliding window technique (window size is set to 1 hour and step size is set to 10 minutes) is used to extract time series features to generate input samples containing current time data and historical context information (for example, each sample contains multi-dimensional data of the previous 6 time points); for environmental data with strong periodicity (such as diurnal variation of temperature and humidity), Fourier transform is used to extract frequency domain features to identify periodic components (such as 24-hour period and 7-day period) in the data, and the original time domain data is spliced to form a composite feature vector; for the stay duration and trajectory data in personnel activity data, time encoding technology (such as converting the stay duration into the time proportion relative to a day) is used to integrate the time series model. The time series analysis module is developed based on the TensorFlow or PyTorch framework, supports generating preprocessed data conforming to the input format of LSTM, Transformer and other time series models, and outputs data time correlation heat map for adjusting feature weights during model training. Embodiment Four

[0071] In this embodiment, the health monitoring method of the intelligent building comprises the following steps:

[0072] S301: inputting the preprocessed multi-dimensional data into the health monitoring model, wherein the health monitoring model comprises a data fusion layer, a feature extraction layer and a health evaluation layer.

[0073] Specifically, after the multi-dimensional data preprocessing is completed, the preprocessed multi-dimensional data is input to the health monitoring model in the form of a time series matrix. The model adopts a hierarchical architecture design, including a data fusion layer, a feature extraction layer, and a health assessment layer, and is implemented based on the TensorFlow or PyTorch framework. The input data format is a three-dimensional tensor [sample number, time step, data dimension], where the time step corresponds to the uniform time interval (for example, 1 minute) in the preprocessing stage, and the data dimension integrates the standardized features (for example, temperature, stress, device current, and personnel density, etc., a total of 50 dimensions) of four types of data, namely environment, structure, device, and personnel activity. The model input interface supports dynamic data batch loading, and the asynchronous processing of preprocessed data and model calculation is realized through a data queue, thereby improving the real-time monitoring efficiency.

[0074] S302: The data fusion layer performs spatio-temporal alignment and dimension normalization processing on the multi-dimensional data to generate a standardized data set.

[0075] Specifically, the data fusion layer first performs spatio-temporal alignment processing, which includes: for the time dimension, the original sampling frequencies (for example, 100Hz for a structure vibration sensor and 1Hz for an environment sensor) of different sensors are unified to the time step (for example, 1 minute) required by the model input through a resampling algorithm, the mean down-sampling is used for high-frequency data, and the cubic spline interpolation up-sampling is used for low-frequency data; for the spatial dimension, a three-dimensional spatial coordinate mapping table of the intelligent building is established, the structure sensor position (for example, beam column coordinates), the device installation position (for example, air conditioning unit number), and the personnel positioning coordinates (UWB positioning tag coordinates) are uniformly converted into the Building Information Modeling (BIM) coordinate system to form a spatial feature vector containing X / Y / Z coordinates. Secondly, the dimension normalization processing is performed: the cross-type data (for example, the ℃ unit of temperature and the MPa unit of stress) is scaled by standardization, the global mean and standard deviation (based on historical 30-day data statistics) of each dimension data are calculated, the data is converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, and a standardized data set [N, T, D] with unified dimensions is generated (N is the sample number, T is the time step, and D is the fused data dimension).

[0076] S303: The feature extraction layer extracts environment features, structure features, device features, and personnel activity features based on the standardized data set through a convolutional neural network or a graph neural network.

[0077] Specifically, the feature extraction layer processes according to the branch path of data type difference:

[0078] In the environment feature and device feature extraction step, a 1D-CNN (1D-Convolutional Neural Network) is used, three convolutional layers are set for time series data (such as temperature and humidity, time series of device current), the convolution kernel size is 15, 10, 5 (corresponding to 15 minutes, 10 minutes, 5 minutes time window) respectively, the periodic features of different time scales are extracted through the ReLU (Rectified Linear Unit) activation function, and the output dimension of the environment feature vector and the device feature vector is [N, T, 64].

[0079] In the structure feature extraction step, a GNN (Graph Neural Network) is used, the key nodes of the building (such as beams and columns, shear walls) are defined as graph nodes (node number M=200-500), the node attributes include stress, displacement, vibration and other structure data, the edge weights between nodes are set according to the physical connection relationship (such as the stiffness matrix of adjacent beams and columns), the neighborhood node features are aggregated through two layers of GCN (Graph Convolutional Network), the structure coupling features (such as the correlation between node displacement and adjacent beam stress) are extracted, and the output dimension of the structure feature vector is [M, 128].

[0080] In the personnel activity feature extraction step, a ST-GNN (Spatio-Temporal Graph Neural Network) is used, each area of the building is defined as a graph node (node number K=50-100), the node attributes include personnel distribution density and stay time, the edge weights are set according to the region connectivity (such as the rooms connected by the corridor), the time dimension LSTM layer is combined to capture the time sequence rule of personnel flow, and the output dimension of the personnel activity feature vector is [K, 96]. The feature extraction results of each branch are integrated into a comprehensive feature tensor [N, T, 288] (64+128+96) through splicing operation, and input into the health assessment layer.

[0081] S304: The health assessment layer outputs an environment condition suitability score, a building structure stability index, a device health percentage, and a personnel activity risk level according to the environment feature, the structure feature, the device feature, and the personnel activity feature.

[0082] Specifically, the health assessment layer includes four independent evaluation sub-modules, which output quantitative results respectively.

[0083] In the environmental condition suitability scoring submodule, a fully connected neural network (3 layers with 256, 128, and 1 neurons respectively) is used to input the environmental feature vector and output a score between 0 and 100 (80 and above is suitable, 60-80 is critical, and below 60 is unsuitable). During training, the human comfort interval (e.g. temperature 22-26℃, humidity 40%-60%) and the device operation suitable interval are used as labels, and the loss function uses Mean Squared Error (MSE).

[0084] In the building structure stability index submodule, based on the structure feature vector, a risk prediction model (Support Vector Regression SVR) is used to calculate a dimensionless index between 0 and 1 (0.9 and above is stable, 0.7-0.9 is early warning, and below 0.7 is dangerous). During model training, the building design standard stress threshold and historical crack propagation data are used as constraint conditions.

[0085] In the device health percentage submodule, for the device feature vector, an attention mechanism (Attention) is used to focus on key fault features (e.g. abnormal current fluctuation, vibration frequency deviation), and a Softmax classifier is used to output the device health state probability distribution (healthy, sub-healthy, pre-failure, failure), which is converted into a health degree between 0 and 100% (healthy corresponds to 90%-100%, failure corresponds to 0-40%).

[0086] In the personnel activity risk level submodule, a risk assessment decision tree is constructed, inputting personnel activity features (density, trajectory, stay duration), and setting three-level thresholds (low risk, medium risk, high risk), for example, when the regional personnel density is greater than 1.5 people / ㎡ and the stay duration is greater than 30 minutes, it is determined as medium risk. Historical accident data is used to optimize the decision tree branch conditions, and a discrete risk level (1 to 3) is output. The output results of each submodule are synchronized to the visualization interface, supporting real-time health state dynamic rendering and threshold alarm triggering.

[0087] The above technical solution has the advantages that through the collaborative work of the data fusion layer, feature extraction layer and health evaluation layer in the health monitoring model, efficient integration and in-depth analysis of multi-dimensional data are realized. The data fusion layer ensures the uniformity and accuracy of the data through spatio-temporal alignment and dimension normalization processing; the feature extraction layer uses convolutional neural networks or graph neural networks to automatically extract key features from standardized data sets, ensuring comprehensive coverage of environmental, structural, device and personnel activity features; the health evaluation layer outputs accurate health evaluation results based on these features, such as environmental suitability, structural stability, device health degree and personnel activity risk level.

[0088] In some embodiments, the step S304 of outputting the environmental condition suitability score comprises: inputting the environmental features into a pre-constructed environmental suitability evaluation sub-model, the environmental features at least including temperature and humidity data, air quality index, light intensity, and noise decibel value, the environmental suitability evaluation sub-model being trained based on a support vector machine or a random forest algorithm, and the environmental suitability evaluation sub-model being used to grade and quantify the environmental features through a preset environmental standard threshold matrix to generate an environmental condition suitability score of 0-10.

[0089] In some embodiments, the step S304 of outputting the building structure stability index comprises: inputting the structure features into a structure health monitoring sub-model, the structure features at least including building settlement data, wall crack width, beam column stress value, and foundation vibration frequency; the structure health monitoring sub-model being used to calculate a building structure stability index of 0-1 by comparing the difference between a finite element analysis model and real-time monitoring data, in combination with a preset structure safety level knowledge base, wherein the closer the numerical value is to 1, the higher the stability.

[0090] In some embodiments, the step S304 of outputting the equipment health percentage comprises: inputting the equipment features into an equipment failure prediction sub-model, the equipment features at least including elevator operation parameters, air conditioner energy consumption data, power supply system voltage fluctuation value, and water supply and drainage pipeline pressure value; the equipment failure prediction sub-model being used to perform time series analysis on the equipment features based on a Long Short-Term Memory Network (LSTM) or an attention mechanism model, and to generate an equipment health percentage of 0%-100% by calculating the deviation of the current state from the baseline of the normal operation state of the equipment.

[0091] In some embodiments, the step S304 of outputting the personnel activity risk level comprises: inputting the personnel activity features into a personnel safety evaluation sub-model, the personnel activity features at least including personnel density distribution, emergency passage occupancy, fire-fighting equipment usage state, and abnormal behavior recognition data; the personnel safety evaluation sub-model being used to perform risk factor weighted calculation on the personnel activity features based on a combination of a rule engine and machine learning to generate a three-level personnel activity risk level including low risk, medium risk, and high risk.

[0092] In some embodiments, the step S30 further comprises: before outputting the health condition analysis result, performing comprehensive weighted calculation on the environmental condition suitability, building structure stability, equipment health, and personnel activity risk through a preset multi-dimensional weight matrix to generate a building health comprehensive index of 0-100, and the multi-dimensional weight matrix dynamically adjusting the weight coefficients of each dimension according to the use type (residential, commercial, industrial) of the intelligent building.

[0093] In some embodiments, the health monitoring model pre-trained in step S30 is trained by the following steps: collecting historical multi-dimensional data as a training data set, the historical multi-dimensional data including normal operation data, single fault data and composite fault data; performing data enhancement and feature engineering processing on the training data set to generate a standard training set with health labels; training the health monitoring model using a multi-task learning framework, while optimizing the loss functions of four sub-tasks of environmental suitability, structural stability, equipment health and personnel activity risk, the loss function including a combination of mean square error loss and cross-entropy loss.

[0094] In some embodiments, further comprising: introducing an adversarial sample training mechanism during the training process, training the health monitoring model for robustness by generating adversarial samples simulating abnormal data, and improving the model's ability to identify sudden failures and data noise. Embodiment five

[0095] In this embodiment, the health monitoring method of the intelligent building, the step S40 comprises:

[0096] S401: determining the health abnormality type of the intelligent building according to the health condition analysis result, the health abnormality type including environmental condition unsuitability, building structure abnormality or instability, equipment failure, and personnel activity abnormality.

[0097] Specifically, after outputting the health condition analysis result in step S30, the system automatically matches the health abnormality type through preset determination rules. For environmental conditions, when the environmental condition suitability score is less than 60 points and at least continuously for 3 time steps (for example, 3 minutes) below the threshold, it is determined to be an environmental abnormality, which is specifically subdivided into temperature abnormality (less than 18°C or greater than 28°C), humidity abnormality (less than 30% RH or greater than 70% RH), air quality exceeding the standard (PM2.5 greater than 75 μg / m³ or volatile organic compounds greater than 500 ppb), or light abnormality (less than 300 lux or greater than 3000 lux). The determination condition of the building structure abnormality is that the building structure stability index is less than 0.7, or any one of the monitoring values of the structure displacement, stress, and crack width exceeds the design safety threshold (for example, displacement greater than 5 mm, stress greater than 80% of the design value, crack width greater than 0.3 mm), and is associated with vibration frequency abnormality (for example, non-load vibration above 10 Hz occurs). The determination basis of equipment failure is that the equipment health percentage is less than 40%, or the equipment state data (for example, current, voltage, vibration) appears mutation (more than 3 times the standard deviation of the mean value) and lasts for 2 time steps (for example, 2 minutes), combined with the same type of fault history data in the equipment operation log, which is subdivided into power system trip warning, heating pipe pressure abnormality, air conditioner compressor overheating, etc. The determination standard of personnel activity abnormality is that the personnel activity risk level reaches level 3 (high risk), or the personnel density is greater than 2 people / ㎡ and the stay time is greater than 45 minutes, the activity trajectory appears reverse congestion (for example, personnel reverse flow in the stairwell), unauthorized area intrusion, etc. The abnormality type determination rule is stored in the system configuration database, and the administrator can customize the threshold and associated logic through the visual interface.

[0098] S402: For each health abnormality type, set a corresponding early warning trigger condition, the early warning trigger condition including the health condition exceeding a preset threshold.

[0099] Specifically, the system presets multi-level warning trigger conditions for each health anomaly type and supports dynamic configuration. For unsuitable environmental conditions, the system sets three-level warning trigger conditions: primary warning (60-80 points) triggers regional-level prompts, such as displaying current environmental parameters on the LED screen of the floor; medium-level warning (40-60 points) triggers sound and light alarms, using a buzzer and yellow light to prompt; high-level warning (score below 40 points) triggers global warning and device adjustment, such as automatically starting the fresh air system. For building structure abnormalities or instability, a composite trigger mechanism of "single parameter overrun and associated parameter trend" is used, such as triggering an orange warning when the stress of a certain beam column exceeds 70% of the design value and the displacement rate of the adjacent node exceeds 0.5 mm / h; if the stress exceeds 90% of the design value or the crack width increases by more than 0.1 mm per day, a red warning is triggered. The trigger conditions for equipment failure are based on the matching degree of equipment health percentage and failure feature library. When the equipment health is between 30% and 40%, a "pre-failure" warning is triggered to prompt maintenance planning; when the health is below 30% or hard failure features such as current drop and vibration peak appear, an "emergency shutdown" warning is triggered. For abnormal personnel activity, the system dynamically adjusts the trigger conditions according to the risk level and real-time passenger flow. In the low peak period (passenger flow less than 50 people per floor), if the personnel density exceeds 1.5 people / ㎡, a medium-risk warning is triggered; in the high peak period (passenger flow exceeding 200 people per floor), if the personnel density exceeds 2.0 people / ㎡ or there is aggregation and retention (staying time longer than 60 minutes), a high-risk warning is triggered. All trigger conditions contain time window constraints (such as abnormality lasting for 5 minutes before triggering). These rules implement efficient matching of conditional logic through rule engines (such as Drools), ensuring that the system can respond to various health anomaly events in a timely and accurate manner.S403: According to the warning trigger condition, a warning signal is sent.

[0100] Specifically, the early warning signal sending module supports differentiated early warning strategies for multiple channels, multiple levels, and multiple objects. The early warning channels include local sound and light alarms (warning lights and buzzers installed in each area of the building, supporting partition control), remote notifications (SMS / WeChat push to administrator's mobile phone, email sent to the operation and maintenance team, APP pop-up window to remind the duty personnel), system linkage (sending control instructions to the building automation system, such as cutting off the power supply of the faulty equipment; highlighting the abnormal position on the BIM visualization interface and labeling the risk level). The signal content includes the abnormal type (e.g., "3-layer air conditioning system failure"), specific parameters (e.g., "current current 120A, rated current 80A"), occurrence location (accurate to BIM coordinate system X=15.2m, Y=8.5m, Z=3.8m), duration, historical number of similar abnormalities, and recommended response measures (e.g., "Please check the ventilation duct of room 302 immediately"). In terms of priority mechanism, red early warning (structural instability / equipment emergency failure) adopts a triple confirmation mechanism (SMS, phone voice, and on-site broadcast), orange early warning (environmental high-level anomaly / personnel high risk) triggers high-frequency push, yellow early warning (primary anomaly) only flashes on the monitoring interface, early warning signals are distributed asynchronously through a message queue (e.g., RabbitMQ) to ensure reliable transmission in high-concurrency scenarios, and early warning logs are generated and stored in a time series database (InfluxDB) to record early warning time, processing status, and closed-loop results for subsequent fault analysis and model optimization.

[0101] In some embodiments, the step S40 is followed by a step S70: when an environmental class early warning signal is triggered, the ventilation and purification equipment is automatically started and the temperature and humidity control system is adjusted; when a structural class early warning signal is triggered, the abnormal area entrance and exit are automatically locked and heavy equipment operation is prohibited; when a device class early warning signal is triggered, the standby device is switched to and a maintenance work order is generated and pushed to the maintenance unit; when a personnel class early warning signal is triggered, the emergency broadcast system is started and the emergency evacuation indicator light is turned on.

[0102] Specifically, when the environmental condition suitability score is below the preset threshold and the early warning type is determined to be environmental (e.g., temperature and humidity anomaly, air quality exceeding standard), an instruction is automatically sent to the ventilation and air conditioning control system to start the fresh air purification equipment and adjust the temperature and humidity control parameters (e.g., adjust the humidity control target value to the range of 40%-60%), and a linkage signal is sent to the intelligent lighting system to dynamically adjust the light supplement strategy according to the real-time light intensity.

[0103] When the building structure stability index is lower than the safety threshold (e.g. 0.6) or the wall crack width is detected to be out of limit, the system immediately sends instructions to the access control system to lock the exits (e.g. floor evacuation doors, equipment room passages) of the abnormal structure area, and prohibits the heavy equipment (e.g. elevators, cargo lifts) in the area from running through the building automation system, while marking the structure abnormal position in real time in the BIM model and pushing it to the structure engineer terminal.

[0104] If the equipment health percentage is lower than the critical value (e.g. 70%) and it is determined to be a device failure warning (e.g. elevator operation parameter anomaly, power supply system voltage fluctuation out of limit), the system first triggers the standby equipment automatic switching mechanism (e.g. dual power supply system switching, air conditioning unit redundancy starting), and then generates an electronic maintenance work order containing the equipment model, fault code, and historical maintenance record through the work order management module, and pushes it to the management system of the equipment maintenance unit through the application programming interface, and attaches the three-dimensional coordinate map of the equipment installation position.

[0105] When the personnel activity risk level is determined to be "high risk" (e.g. excessive personnel density, emergency passage congestion), the system immediately starts the emergency response program: plays the pre-recorded emergency evacuation voice through the broadcast control system, synchronously lights up all the emergency evacuation indicator lights in the building and dynamically marks the optimal escape path in the digital twin model; sends pre-starting instructions (e.g. fire pump preheating, smoke exhaust fan standby) to the fire control system, while uploading the real-time personnel distribution heat map and camera monitoring screen to the city emergency management platform after encryption.

[0106] The above linkage control steps realize data interaction between different subsystems through pre-set equipment linkage protocols (e.g. Modbus / TCP, BACnet), all linkage instructions are attached with time stamp and operation log, and are stored through blockchain technology to ensure the traceability and operation standardization of the emergency response process. Embodiment six

[0107] In this embodiment, the health monitoring method of the intelligent building comprises the following steps:

[0108] S501: According to the type of the health anomaly, the abnormal target object corresponding to the health anomaly is identified, and the abnormal target object includes the ventilation system, the load-bearing structure, the elevator equipment or the personnel intensive area of the intelligent building.

[0109] Specifically, after determining the health anomaly type in step S41, the system automatically identifies the abnormal target object by relying on the preset mapping relationship table and building information model (BIM) through the association algorithm of the spatial coordinates of the sensor and the physical entity. When the health anomaly type is an unsuitable environmental condition, if the temperature or humidity monitoring value exceeds the comfortable interval, the system locates to the corresponding air conditioning unit, humidifier or dehumidifier according to the deployment position of the abnormal data corresponding sensor (for example, the temperature and humidity sensor of the air outlet of the air conditioner on a certain floor); if the air quality parameter (for example, PM2.5) is over standard, it is associated to the fresh air system, air purification equipment or ventilation duct. For the case of unstable building structure, the system accurately locks the specific load-bearing structural components (for example, 3 layers of 2 frame beams, the bottom node of the shear wall of the underground 1 layer) through the coordinate data of the structural sensor (such as beam column strain gauge, crack sensor) combined with the three-dimensional spatial positioning of the BIM model. For equipment failure, the system matches the equipment account database through the unique ID of the equipment state sensor (such as the vibration sensor code of the elevator traction machine, the number of power distribution cabinet current transformer), and directly locates to the fault equipment (for example, the control cabinet of No. 5 elevator, the compressor of the central air conditioner on the 2nd floor). When there is an abnormal personnel activity, the system determines the specific area where the personnel gather based on the coordinate data of the Ultra-Wideband (UWB) positioning tag or the analysis result of the camera video, and associates the access control system, monitoring equipment and fire fighting facilities in the area as auxiliary target objects to ensure that the physical entity of the repair scheme is clearly pointed.

[0110] S502: retrieve at least one basic repair strategy matched with the type of the health anomaly and the abnormal target object from a preset repair strategy database, wherein the repair strategy database stores basic repair strategies for different health anomaly types and abnormal target objects.

[0111] Specifically, the repair strategy database is built with a relational database (e.g., PostgreSQL), and its storage structure is designed as a five-tuple data model containing abnormal type, target object, basic repair strategy, execution priority, and safety constraint. For example, for the abnormal combination of “environmental conditions unsuitable - ventilation system”, the basic strategies stored in the database include: when the PM2.5 concentration exceeds 150 μg / m³, automatically trigger the control instruction to turn on the fresh air system to the maximum air volume and close the return air valve; when volatile organic compounds leakage is detected, execute the safety strategy of cutting off the ventilation pipeline of the contaminated area and starting the air purification equipment. For the abnormal scenario of “building structure instability - load-bearing beam column”, if the beam column stress reaches 70% of the design value and the displacement growth rate exceeds 0.5 mm / h, the system retrieves the early warning strategy of arranging unmanned aerial vehicle infrared scanning of the structure surface and deploying temporary monitoring points; if the stress exceeds 90% of the design value or the crack width increases by more than 0.1 mm per day, the emergency strategy of starting the temporary support reinforcement program of the structure and prohibiting personnel from entering the area is executed. For “equipment failure - elevator equipment”, when the equipment health is in the pre-failure stage of 30%-40%, the system generates a maintenance strategy to trigger the standby elevator to run and push a maintenance work order to the maintenance team; if hard failure characteristics such as current drop or vibration peak are detected, the safety strategy of immediately stopping the equipment operation and cutting off the power supply is retrieved. For “abnormal personnel activity - personnel intensive area”, when the personnel density exceeds 1.5 people / ㎡ during the low peak period, the medium-risk strategy of prompting orderly evacuation through the broadcast system is executed; when the density exceeds 2.0 people / ㎡ during the peak period or the gathering and staying time exceeds 60 minutes, the high-risk strategy of linking the access control to limit the entry of the area and notifying the security personnel for on-site control is started. When the strategy is retrieved, the system matches the combination conditions of abnormal type and target object through SQL query language, and automatically retrieves the latest version of the strategy, supporting historical strategy version tracing and safety compliance verification.

[0112] S503: According to the pre-processed multi-dimensional data and historical repair records, the retrieved basic repair strategy is optimized to generate a repair scheme for the intelligent building.

[0113] Specifically, the optimization process of the basic repair strategy combines real-time multidimensional data with historical repair experience, and realizes dynamic adjustment through data fusion analysis and machine learning algorithms. In the real-time data-driven optimization link, the system uses a rule engine to analyze pre-processed environmental temperature and humidity gradients, structural displacement change rates, equipment current fluctuation curves, and other parameters. For example, for air conditioning system temperature adjustment strategies, the system dynamically generates air supply temperature compensation parameters (compensation value = 0.6 x (maximum temperature - minimum temperature)) by calculating the standard deviation of the temperature distribution of each area on the current floor, so that the air supply strategy adapts to real-time environmental differences. In the historical case matching link, the system uses the K-nearest neighbor (K-NN) algorithm to retrieve the top 5 cases with the highest similarity to the current abnormal scene from the historical repair logs (including fault scene description, strategy execution steps, repair time consumption, energy consumption changes, and other fields) stored in the time series database, and extracts the execution process with the highest average repair efficiency. For example, when dealing with elevator door failures, the system reuses the "three-level troubleshooting process" (first detect door lock sensor signal, then check control circuit voltage, and finally test mechanical part wear) with the shortest time consumption in historical cases, and adjusts the priority of each troubleshooting step according to the service life and operating load of the current equipment (for example, old equipment is given priority to check mechanical parts). The optimized repair scheme includes specific control instructions (such as adjusting the fresh air valve opening degree on the 3rd floor to 85% and keeping it for 30 minutes), responsible departments and personnel, time window requirements (such as completing preliminary structural stability evaluation within 20 minutes), and safety check rules (such as confirming that the regional personnel evacuation status has been completed before execution), which are pushed to the building automation system or operation and maintenance management platform in real time through the application programming interface, realizing the intelligent generation and precise execution of the repair scheme.

[0114] The above technical solution is based on the spatial linkage positioning technology of BIM and sensor coordinates, which concretizes the repair target from abstract abnormal types to specific physical entities (such as a certain device or structural node on a certain floor), so that the response efficiency of operation and maintenance personnel is improved. In addition, through the real-time data-driven rule engine and the machine learning algorithm of historical case reuse, the technical problem that fixed preset strategies are difficult to adapt to complex scene changes is solved. Moreover, the deep integration of the repair strategy database with the BIM model, equipment account, and historical log forms a full life cycle closed-loop management system of "monitoring, early warning, repair, and recording", providing data support for building preventive maintenance. Embodiment Seven

[0115] In this embodiment, the intelligent building health monitoring method further includes the following steps:

[0116] S60: After the implementation of the repair scheme for the smart building, the repair effect is monitored in real time, and the repair effect is evaluated whether it reaches the predetermined standard by comparing the health condition analysis results before and after the repair. If the repair effect does not reach the predetermined standard, the repair scheme is adjusted and implemented again until the predetermined standard is reached.

[0117] Specifically, step S60 includes:

[0118] S601: After the implementation of the repair scheme, the multi-dimensional data of the smart building is collected and monitored in real time.

[0119] After the implementation of the repair scheme for the smart building, the system immediately starts the real-time data collection and monitoring work. To ensure that the repaired condition can be fully and timely reflected, the data collection range covers the multi-dimensional data of the smart building, including environmental data (such as temperature, humidity, air quality, etc.), structural data (such as stress, displacement, structural deformation, cracks, etc. of the building structure), equipment state data (such as operation parameters, energy consumption, etc. of various equipment) and personnel activity data (such as the distribution and flow of personnel, etc.).

[0120] During the data collection process, the same sensor network as the previous monitoring is used, and these sensors are reasonably deployed at various key positions of the building. For example, environmental sensors are distributed on different floors and areas to obtain accurate environmental parameters; structural sensors are installed on the main load-bearing structures of the building to monitor the mechanical properties of the structure in real time; equipment sensors are connected to various equipment to collect equipment operation status information; personnel activity monitoring is realized through cameras, access control systems and other equipment.

[0121] To ensure the real-time and accuracy of the data, the system uses a high-speed data transmission protocol to transmit the data collected by the sensors to the data processing center in a timely manner. In addition, to deal with data loss or errors, a data verification and retransmission mechanism is also set up.

[0122] S602: According to the multi-dimensional data, a health monitoring model is used to generate the health condition analysis results after the repair.

[0123] After collecting the repaired multi-dimensional data, the system inputs these data into the health monitoring model. The health monitoring model performs a series of processing and analysis on the input multi-dimensional data. First, the data is pre-processed, including denoising, normalization and other operations, to improve the quality and usability of the data. Then, through the data fusion layer in the model, different types of data are spatio-temporally aligned and dimensionally normalized to generate a standardized data set. Next, the feature extraction layer extracts environmental features, structural features, device features and personnel activity features based on the standardized data set through convolutional neural networks or graph neural networks. Finally, the health assessment layer outputs the repaired health condition analysis results, including environmental condition suitability score, building structure stability index, device health percentage and personnel activity risk level, according to these features.

[0124] S603: Compare the health condition analysis results before and after repair to determine whether the repair effect meets the predetermined standards.

[0125] After obtaining the health condition analysis results after repair, the system compares them in detail with the health condition analysis results before repair. In order to more accurately evaluate the repair effect, the system pre-sets a series of predetermined standards, which are formulated according to the design requirements of intelligent buildings, safety specifications and actual use needs.

[0126] For the environmental condition suitability score, if the score before repair is low, the predetermined standard sets a certain score increase, for example, more than 10 points. For the building structure stability index, the predetermined standard stipulates that the index fluctuation range should be within a small interval, for example, ±5%. For the device health percentage, the predetermined standard requires to reach a certain threshold, for example, more than 60%. For the personnel activity risk level, the predetermined standard sets a decrease of at least one level.

[0127] The system will analyze each evaluation index one by one, calculate the difference or change rate before and after repair. If all evaluation indexes meet the predetermined standards, it is determined that the repair effect meets the requirements; otherwise, it is determined that the repair effect does not meet the predetermined standards.

[0128] S604: If the repair effect does not meet the predetermined standards, adjust the repair scheme.

[0129] When it is determined that the repair effect does not meet the predetermined standards, the system will immediately start the adjustment mechanism of the repair scheme. The basis for adjusting the scheme mainly comes from two aspects: one is the historical repair record database, and the other is the expert rule engine.

[0130] The system retrieves similar cases from the historical repair record database, uses the Case-Based Reasoning (CBR) algorithm to analyze the effective repair strategies and adjustment methods in these cases, extracts the difference parameters from the current situation, and makes preliminary corrections to the existing repair scheme.

[0131] The expert rule engine conducts in-depth causal analysis on the health indicators that do not meet the standards. For example, if the environmental condition suitability score does not meet the predetermined standard, the expert rule engine traces the deviations of parameters such as ventilation system adjustment valve opening, fresh air volume, etc. from the repair scheme set values, finds out the factors affecting the repair effect, and generates corresponding parameter adjustment instructions.

[0132] Based on the analysis results of the above two aspects, the system will comprehensively adjust the repair scheme, including adjusting the operating parameters of the equipment, adding or reducing certain repair measures, extending the repair time, etc.

[0133] S605: According to the adjusted repair scheme, the system re-performs the repair, and repeats steps S601 to S604 until the repair effect reaches the predetermined standard.

[0134] According to the adjusted repair scheme, the system will re-perform the repair of the intelligent building. During the repair process, the system will strictly follow the adjusted scheme to execute each repair measure, ensuring the accuracy and effectiveness of the repair work.

[0135] After the repair is completed, the system will again repeat steps S601 to S604, that is, real-time collection and monitoring of multi-dimensional data of intelligent buildings, use of health monitoring model to generate health condition analysis results after repair, comparison with results before repair, judgment of whether the repair effect meets the predetermined standard. If it still does not meet the predetermined standard, the system will continue to adjust the repair scheme and re-perform the repair, and so on, until the health condition analysis results of consecutive multiple monitoring periods (for example, 3 monitoring periods, each period is 1 hour) meet the predetermined standard.

[0136] The technical scheme of the intelligent building health monitoring method regarding the repair effect evaluation and scheme adjustment forms a complete and closed-loop repair effect evaluation and adjustment system, ensuring that the repair work can achieve the expected goal. After the implementation of the repair scheme, the health monitoring model is used to generate analysis results by collecting multi-dimensional data in real time, which can comprehensively and accurately reflect the health condition of the building after repair. The results before and after repair are compared and the repair effect is judged according to the predetermined standard, so that the evaluation process is objective and scientific. If the repair effect does not meet the standard, the repair scheme is adjusted by combining historical repair records and expert rule engine, which ensures the rationality and effectiveness of the adjustment. Through the process of continuous monitoring, evaluation and adjustment, until the repair effect meets the predetermined standard, the quality and efficiency of the repair work are improved, and the safety hidden danger caused by incomplete repair is reduced. Embodiment eight

[0137] As shown in Figure 3 The embodiment provides an intelligent building health monitoring system, which comprises:

[0138] A data acquisition module comprising a plurality of sensors arranged at a plurality of target monitoring positions of the intelligent building, configured to acquire multi-dimensional data inside and outside the intelligent building in real time through the plurality of sensors, wherein the multi-dimensional data comprises environmental data, structural data of the intelligent building, equipment state data and personnel activity data;

[0139] A data preprocessing module configured to preprocess the multi-dimensional data to obtain preprocessed multi-dimensional data;

[0140] A health analysis module configured to output a health condition analysis result of the intelligent building by using a pre-trained health monitoring model according to the preprocessed multi-dimensional data, wherein the health condition analysis result comprises a suitability degree of environmental conditions, a stability degree of building structures, a health degree of equipment and a risk degree of personnel activities;

[0141] An early warning module configured to issue a warning signal when the health condition analysis result indicates that the intelligent building has a health abnormality;

[0142] A repair scheme generation module configured to determine a repair scheme of the intelligent building according to the type of the health abnormality, wherein the repair scheme is at least associated with repair and reinforcement of the intelligent building.

[0143] In a further embodiment, the data acquisition module comprises:

[0144] An environmental data acquisition unit configured to acquire environmental data inside the intelligent building in real time through an environmental sensor, wherein the environmental data comprises temperature, humidity, air quality and illumination intensity;

[0145] a structural data collection unit configured to collect structural data of the smart building in real time through structural health monitoring sensors, the structural data including displacement, deformation, stress, vibration and crack width of the smart building;

[0146] a device state collection unit configured to collect device state data of the smart building in real time through device state monitoring sensors, the device state data including operation state data of the power system, heating system, ventilation system and air conditioning system;

[0147] a personnel activity collection unit configured to collect personnel activity data inside the smart building in real time through personnel positioning and monitoring devices, the personnel activity data including distribution density of personnel, activity trajectory of personnel and stay duration of personnel in different areas.

[0148] In further embodiments, the data preprocessing module comprises:

[0149] a denoising processing unit configured to perform denoising processing on the multi-dimensional data to obtain purified data;

[0150] an anomaly detection unit configured to perform anomaly detection on the purified data to remove abnormal data points to obtain cleaned data;

[0151] a standardization processing unit configured to perform standardization processing on the cleaned data to obtain standardized data;

[0152] a time series analysis unit configured to perform time series analysis on the standardized data to obtain preprocessed data.

[0153] In further embodiments, the health analysis module comprises:

[0154] a health monitoring model comprising a data fusion layer, a feature extraction layer and a health evaluation layer;

[0155] the data fusion layer is configured to perform spatio-temporal alignment and dimension normalization processing on the preprocessed multi-dimensional data to generate a standardized data set;

[0156] the feature extraction layer is configured to extract environmental features, structural features, device features and personnel activity features based on the standardized data set through a convolutional neural network or a graph neural network;

[0157] the health evaluation layer is configured to output environmental condition suitability score, building structure stability index, device health percentage and personnel activity risk level according to the environmental features, the structural features, the device features and the personnel activity features, respectively.

[0158] As Figure 4As shown, in a further embodiment, the early warning module includes:

[0159] Anomaly type determination unit is configured to determine the health anomaly type of the intelligent building based on the health status analysis results. The health anomaly type includes unsuitable environmental conditions, abnormal building structure, equipment failure, and abnormal personnel activity.

[0160] The early warning triggering condition setting unit is configured to set corresponding early warning triggering conditions for each type of health abnormality, wherein the early warning triggering conditions include the health status exceeding a preset threshold;

[0161] The warning signal sending unit is configured to send a warning signal according to the warning triggering conditions.

[0162] In a further embodiment, the repair scheme generation module includes:

[0163] An abnormal target identification unit is configured to identify the abnormal target object corresponding to the health abnormality based on the type of the health abnormality. The abnormal target object includes the ventilation system, load-bearing structure, elevator equipment, or densely populated area of ​​the intelligent building.

[0164] The repair strategy retrieval unit is configured to retrieve at least one basic repair strategy that matches the type of the health abnormality and the abnormal target object from a preset repair strategy database. The repair strategy database stores basic repair strategies for different types of health abnormalities and the abnormal target objects.

[0165] The strategy optimization unit is configured to optimize the retrieved basic repair strategy based on the preprocessed multidimensional data and historical repair records, and generate a repair plan for the smart building.

[0166] like Figure 3 As shown, in a further embodiment, the system further includes:

[0167] The repair effect evaluation module is configured to monitor the repair effect in real time after the repair plan for the intelligent building is implemented. By comparing the health status analysis results before and after the repair, it evaluates whether the repair effect meets the predetermined standard. If the repair effect does not meet the predetermined standard, the repair plan is adjusted and reimplemented until the predetermined standard is met. During reimplementation, a re-monitoring command is sent to the data acquisition module.

[0168] In a further embodiment, the repair effect evaluation module includes:

[0169] The data acquisition unit after repair is configured to collect and monitor multi-dimensional data of the smart building in real time after the repair plan is implemented;

[0170] The post-repair analysis unit is configured to generate a post-repair health condition analysis result using a health monitoring model according to the multi-dimensional data.

[0171] The effect comparison unit is configured to compare the pre-repair health condition analysis result with the post-repair health condition analysis result to determine whether the repair effect meets a predetermined standard.

[0172] The scheme adjustment unit is configured to adjust the repair scheme if the repair effect does not meet the predetermined standard.

[0173] The cycle execution unit is configured to re-perform the repair according to the adjusted repair scheme, and repeat the data collection, analysis, comparison and adjustment steps until the repair effect meets the predetermined standard.

[0174] In further embodiments, the system further comprises:

[0175] The early warning linkage execution module is configured to perform corresponding operations according to the early warning type after the early warning signal is sent:

[0176] When an environment type early warning signal is triggered, the linkage starts the ventilation and purification equipment and adjusts the temperature and humidity control system;

[0177] When a structure type early warning signal is triggered, the abnormal area entrance and exit are automatically locked and heavy equipment operation is prohibited;

[0178] When a device type early warning signal is triggered, the standby device is switched to and a maintenance work order is generated and pushed to the maintenance unit;

[0179] When a personnel type early warning signal is triggered, the emergency broadcast system is started and the emergency evacuation indicator light is turned on.

[0180] The embodiment of the application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize any one of the above methods.

[0181] The application also provides an electronic device. The electronic device of the embodiment of the application comprises one or more processors, and a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided by the application.

[0182] Reference will be made to the following description Figure 5 which shows a structural schematic diagram of a computer system 800 suitable for implementing the electronic device of the embodiment of the application. Figure 5 The electronic device shown is only an example, and should not bring any limitation to the functions and use range of the embodiment of the application.

[0183] As Figure 5As shown, the computer system 500 includes a central processing unit (CPU) 501 which can perform various appropriate actions and processes in accordance with programs stored in a read only memory (ROM) 502 or programs loaded from a storage section 505 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the computer system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0184] Connected to the I / O interface 505 are an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as necessary. A removable recording medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 510 as necessary, so that a computer program read therefrom is installed into the storage section 505 as necessary.

[0185] The specific embodiments described above are not to be taken advantage of as limiting the scope of the application. As those skilled in the art will appreciate, numerous modifications, combinations, sub-combinations, and alternatives can be made in accordance with this application without departing from the scope of the application. Any such modifications, equivalents, alternatives, and combinations, etc., are thus intended to fall within the scope of the application.

Claims

1. A health monitoring method for intelligent buildings, characterized in that, The method includes the following steps: S10: Real-time acquisition of multi-dimensional data of the interior and exterior of the intelligent building through multiple sensors installed at multiple target monitoring locations in the intelligent building. The multi-dimensional data includes environmental data, structural data of the intelligent building, equipment status data, and personnel activity data. The structural data includes the displacement, deformation, stress, vibration, and crack width of the intelligent building. S20: Preprocess the multidimensional data to obtain preprocessed multidimensional data; S30: Based on the preprocessed multidimensional data, using a pre-trained health monitoring model, output the health status analysis results of the intelligent building. The health status analysis results include the suitability of environmental conditions, the stability of the building structure, the health status of equipment, and the risk level of personnel activities. S40: When the health status analysis results indicate that the smart building has a health abnormality, an early warning signal is issued; S50: Based on the type of the health abnormality, determine a repair plan for the intelligent building, the repair plan being at least related to the structural repair and reinforcement of the intelligent building; Step S30 includes: S301: Input the preprocessed multidimensional data into the health monitoring model, which includes a data fusion layer, a feature extraction layer, and a health assessment layer; S302: The data fusion layer performs spatiotemporal alignment and dimension normalization on the multidimensional data to generate a standardized dataset; S303: The feature extraction layer extracts environmental features, structural features, equipment features, and personnel activity features based on the standardized dataset using a convolutional neural network or a graph neural network; S304: The health assessment layer outputs an environmental condition suitability score, a building structure stability index, an equipment health percentage, and a personnel activity risk level based on the environmental characteristics, structural characteristics, equipment characteristics, and personnel activity characteristics, respectively. The health assessment layer includes: The environmental suitability scoring submodule uses a fully connected neural network, taking an environmental feature vector as input and outputting a score. The building structure stability index submodule calculates a dimensionless index based on structural feature vectors and a risk prediction model. The Equipment Health Percentage submodule uses an attention mechanism to process key fault features based on the equipment feature vector, and outputs the probability distribution of equipment health status through a Softmax classifier, which is then converted into a health score. The personnel activity risk level submodule constructs a risk assessment decision tree, inputs personnel activity characteristics, sets three-level thresholds, optimizes the decision tree branch conditions by combining historical accident data, and outputs discrete risk levels.

2. The health monitoring method for intelligent buildings according to claim 1, characterized in that, Step S10 includes: S101: Real-time collection of environmental data inside the intelligent building via environmental sensors, including temperature, humidity, air quality, and light intensity; S102: Collect structural data of the intelligent building in real time through structural health monitoring sensors; S103: The equipment status data of the intelligent building is collected in real time through equipment status monitoring sensors. The equipment status data includes the operating status data of the power system, heating system, ventilation system, and air conditioning system. S104: Collect real-time personnel activity data inside the intelligent building through personnel positioning and monitoring devices. The personnel activity data includes personnel distribution density, personnel activity trajectory, and personnel stay duration in different areas.

3. The health monitoring method for intelligent buildings according to claim 1, characterized in that, The environmental data is collected by temperature and humidity sensors, carbon dioxide concentration sensors, light intensity sensors and air quality sensors distributed in various functional areas of the smart building. The structural data of the intelligent building is collected by pressure sensors, strain sensors, vibration sensors and displacement sensors installed at the target structural parts of the intelligent building, including beams, columns, walls, foundations and roofs; The equipment status data is collected by current sensors, voltage sensors, temperature sensors, and vibration sensors installed on air conditioning systems, elevators, lighting equipment, water and power supply equipment, and ventilation equipment. The personnel activity data is collected through cameras, infrared sensors, and access control systems deployed in the public areas, entrances, and stairwells of smart buildings.

4. The health monitoring method for intelligent buildings according to claim 1, characterized in that, Step S50 includes: when the type of health anomaly is a structural anomaly in the intelligent building, matching a corresponding repair plan according to the type of structural anomaly in the intelligent building: When the type of structural anomaly is structural deformation, the first repair plan is executed based on the deformation amount classification. When the type of structural anomaly is structural crack, a second repair plan is implemented based on the crack width classification. When the type of structural anomaly is structural material performance degradation, a third repair scheme is implemented based on the material type. The structural deformation is detected using a total station, level, laser scanner, strain sensor, and displacement sensor; the structural cracks are detected using a crack width gauge and ultrasonic flaw detector; and the material performance degradation is detected using a rebound hammer or carbonation depth measuring instrument for concrete, and a magnetic particle flaw detector or ultrasonic thickness gauge for steel structures.

5. The health monitoring method for intelligent buildings according to claim 4, characterized in that, The first repair solution includes: For minor deformation within the first deformation range, perform the following operations: adjust the load configuration, retighten the connectors, and attach carbon fiber cloth to the surface of the deformed area. For moderate deformation within the second deformation range, perform the following operations: install steel supports or jacks to transfer the load, insert steel bars into the concrete structure and pour concrete, and weld stiffening ribs to the steel structure for reinforcement. For severe deformation within the third deformation range, perform the following actions: initiate personnel evacuation and warning measures, apply reverse force using external prestressing tendons, and dismantle irreparable structural components; The first deformation range, the second deformation range, and the third deformation range increase sequentially.

6. The health monitoring method for intelligent buildings according to claim 4, characterized in that, The second repair solution includes: For cracks within the first width range, epoxy putty is used for surface sealing treatment; For cracks in the second width range, pressure grouting is used to fill the cracks with epoxy resin and then steel plates or carbon fiber cloth are bonded to them. For cracks within the third width range, foundation reinforcement or a combination of grouting and steel plate bonding repair methods are adopted. The first width range, the second width range, and the third width range increase sequentially.

7. The health monitoring method for intelligent buildings according to claim 4, characterized in that, The third repair solution includes: To address concrete deterioration, perform the following steps: apply a concrete protectant to delay carbonation, remove rust and paint the corroded areas after chiseling them out, and repair the chiseled areas with polymer concrete. To address steel structure deterioration, perform the following steps: sandblasting to remove rust, then applying anti-corrosion coating, welding steel plates, or attaching carbon fiber cloth.

8. The health monitoring method for intelligent buildings according to claim 1, characterized in that, The method further includes the following steps: S60: After implementing the repair plan for the intelligent building, monitor the repair effect in real time, and evaluate whether the repair effect meets the predetermined standard by comparing the health status analysis results before and after the repair; if the repair effect does not meet the predetermined standard, adjust the repair plan and re-implement it until the predetermined standard is met.

9. A health monitoring system for intelligent buildings, characterized in that, The system executes the health monitoring method for intelligent buildings according to any one of claims 1-8, and the system comprises: The data acquisition module includes multiple sensors installed at various target monitoring locations within the intelligent building, configured to acquire multidimensional data of the building's interior and exterior in real time. This multidimensional data includes environmental data, structural data of the intelligent building, equipment status data, and personnel activity data. The structural data includes the intelligent building's displacement, deformation, stress, vibration, and crack width. The data preprocessing module is configured to preprocess the multidimensional data to obtain preprocessed multidimensional data. The health analysis module is configured to output the health status analysis results of the smart building based on the pre-processed multidimensional data and a pre-trained health monitoring model. The health status analysis results include the suitability of environmental conditions, the stability of the building structure, the health status of equipment, and the risk level of personnel activities. The early warning module is configured to issue an early warning signal when the health status analysis results indicate that the smart building has a health abnormality; The repair plan generation module is configured to determine a repair plan for the smart building based on the type of health abnormality, wherein the repair plan is at least related to the structural repair and reinforcement of the smart building.

Images