Intelligent Microenvironment Control and Structural Health Monitoring System for the Conservation of Historic Buildings

Abstract

This invention relates to the field of historical building conservation technology, specifically to a microenvironment intelligent regulation and structural health monitoring system for historical building conservation. The system includes a deployment module, a data acquisition and screening module, an instruction generation module, and a regulation module. By targeting and validating sensors, it simultaneously collects and screens data on the physicochemical properties of materials and environmental data. A three-layer logical judgment constructs a causal relationship between the environment, materials, and structure. Combined with simulation technology, it avoids secondary damage and dynamically optimizes regulation parameters. This invention achieves deep integration and analysis of these three aspects, accurately identifies damage mechanisms, and enables preventative protection of historical buildings. It significantly improves the intelligence and precision of conservation efforts, providing reliable technical support for cultural heritage protection.

Description

Technical Field

[0001] This invention relates to the field of historical building conservation technology, and more specifically, to a microenvironment intelligent control and structural health monitoring system for the conservation of historical buildings. Background Technology

[0002] Historical buildings often use traditional natural materials such as wood and brick. The stability of these materials is easily affected by multiple factors such as temperature and humidity fluctuations, pollutant erosion, and stress changes over a long period of time. They generally face problems such as material weathering, structural loosening, and damage spread, which seriously threaten the safety of the building itself and the inheritance of cultural value. Therefore, preventive protection with "early prediction and precise intervention" as its core has become a core demand in the industry.

[0003] While existing protection schemes attempt to introduce sensor monitoring and data acquisition technologies, they lack a systematic and collaborative design approach: sensor deployment relies on manual experience and fails to establish scientific screening criteria based on the mechanical properties of building structures and the scarcity of materials; collected data is not rigorously screened for correlation and validity, and invalid and interfering data can easily interfere with the judgment; safety thresholds are set with fixed values ​​and are not dynamically corrected based on the microscopic state of materials; causal correlation identification lacks consideration of the penetration lag of environmental stimuli and synergistic factors, and secondary damage risk assessments are not conducted before the implementation of control measures, resulting in the disconnect between various technical links and the inability to form a closed-loop protection system.

[0004] The core problem with existing technologies is the failure to construct a comprehensive analysis system that integrates the environment, materials, and structural conditions, making it impossible to accurately identify the associated damage mechanisms among the three and thus hindering the implementation of preventative and precise protection for historical buildings. Summary of the Invention

[0005] In view of this, the present invention proposes a micro-environment intelligent regulation and structural health monitoring system for the protection of historical buildings. It aims to solve the problems in existing historical building protection technologies, such as the disconnect between micro-environment monitoring and structural health assessment, lack of scientific criteria for sensor deployment, insufficient accuracy of data collection and correlation analysis, lack of dynamic optimization of material anomaly judgment and control measures, and lack of secondary damage protection. These problems result in the inability to accurately identify the correlation damage mechanism between environment, materials and structure and achieve preventive protection.

[0006] This invention provides a micro-environment intelligent regulation and structural health monitoring system for the protection of historical buildings, comprising: a deployment module configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on the material properties and structurally vulnerable parts of the target historical building; to pre-collect material physical and chemical property data and corresponding regional environmental data for a preset duration; and to determine the effectiveness of the deployment and adjust invalid deployment points.

[0007] The acquisition and screening module is configured to synchronously acquire the physical and chemical property data of the material and the corresponding regional environmental data through a wireless sensor network, screen the acquired data for validity, and transmit valid data sets that meet the correlation requirements.

[0008] The instruction generation module is configured to extract material property change characteristics and environmental stimulus characteristics, determine whether the physical and chemical property data of the material deviate from the safety threshold, and if not, maintain the current monitoring state; if so, determine whether the anomaly is caused by environmental stimulus and whether there is time synchronization, and if not, trigger a self-check; if so, determine whether the material anomaly will cause structural damage risk, and if not, mark it as a minor anomaly; if so, determine it as a high risk and generate a control instruction.

[0009] The control module is configured to match the corresponding microenvironment control terminal according to the control command, collect material property data in real time after the control is started and provide feedback for judgment, and dynamically adjust the control parameters.

[0010] In some embodiments, the deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on its material properties and structurally vulnerable parts. It pre-collects material physical and chemical property data and corresponding regional environmental data for a preset duration, and determines the effectiveness of the deployment. Adjustments are made to invalid deployment points, including:

[0011] Structural mechanics simulation is used to determine whether the target area is a stress concentration area. When the target area is a stress concentration area, the maintenance records of the target area or the coefficient of variation of the moisture content or salinity of the material in the target area are used to determine whether the target area is the critical area.

[0012] When the frequency of damage to the target area in the maintenance record within a preset time is greater than or equal to a preset first threshold, the target area is determined to be the critical area.

[0013] When the coefficient of variation of the moisture content or salinity of the material in the target area is greater than or equal to a preset second threshold, the target area is determined to be the key area.

[0014] In some embodiments, the deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on its material properties and structurally vulnerable parts. It also includes pre-collecting material physical and chemical property data and corresponding regional environmental data for a preset duration, determining the effectiveness of the deployment, and adjusting ineffective deployment points.

[0015] When the target area is not a stress concentration area, determine whether the material in the target area is a scarce type. When the material in the target area is a scarce type, determine whether the target area is the critical area based on the maintenance records of the target area and the coefficient of variation of the moisture content or salinity of the material in the target area.

[0016] When the frequency of damage to the target area in the maintenance record within a preset time is greater than or equal to the first threshold, and the coefficient of variation of the moisture content or salinity of the target area material is greater than or equal to the second threshold, the target area is determined to be the critical area.

[0017] Otherwise, the target area is determined not to be the critical area;

[0018] When the material in the target area is not a scarce type, the target area is determined to be the critical area based on the maintenance records of the target area and the damage diffusion rate of the material in the target area.

[0019] When the frequency of damage to the target area in the maintenance record within a preset time is greater than or equal to the first threshold, and the material damage diffusion rate of the target area is greater than or equal to the preset third threshold, the target area is determined to be the critical area.

[0020] Otherwise, the target area is determined not to be the critical area.

[0021] In some embodiments, the deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on its material properties and structurally vulnerable parts. It also includes pre-collecting material physical and chemical property data and corresponding regional environmental data for a preset duration, determining the effectiveness of the deployment, and adjusting ineffective deployment points.

[0022] After the material property monitoring sensor and the environmental stimulus monitoring sensor have been deployed for a preset time, it is determined whether the coefficient of variation of the material physical and chemical property data is less than a preset first variation threshold.

[0023] When the coefficient of variation of the material's physical and chemical properties data is less than the first variation threshold, it is determined whether the average difference between the environmental data at this location and the environmental data at the three surrounding adjacent locations is greater than a preset fourth threshold.

[0024] When the coefficient of variation of the material's physical and chemical properties data is less than the first variation threshold, and the average difference between the environmental data at this location and the environmental data at the three adjacent locations is greater than the fourth threshold, the initial deployment is deemed invalid.

[0025] If the initial deployment is deemed invalid, multi-sensor cross-validation is initiated. If the cross-validation pass rate is less than the preset fifth threshold, the sensor is deemed to be faulty.

[0026] When the cross-validation pass rate is greater than or equal to the fifth threshold, it is determined to be a site selection deviation.

[0027] In some embodiments, the acquisition and filtering module is configured to simultaneously acquire the material's physical and chemical properties data and corresponding regional environmental data via a wireless sensor network, perform validity filtering on the acquired data, and transmit valid data sets that meet correlation requirements, including:

[0028] When the deviation of the material property monitoring sensor's three consecutive data acquisitions exceeds a preset first range threshold, the sensor self-calibration is triggered.

[0029] When the deviation after calibration is less than or equal to the preset second range threshold, it is marked as high-priority data and the acquisition frequency is increased.

[0030] When the deviation after calibration exceeds the second range threshold, the backup sensor is activated and the data from the faulty sensor is discarded.

[0031] When the deviation of the environmental data from the average value of the same period in the same region within a preset time is less than the preset sixth threshold, and the fluctuation range of the physical and chemical properties data of the material is less than the preset seventh threshold, it is determined that the environmental material is in dynamic equilibrium, and the collection frequency is reduced.

[0032] Otherwise, the presence of temporary external interference is determined by an environmental disturbance identification algorithm. When the probability of interference is greater than a preset first probability threshold, the data is marked as interference and removed.

[0033] When the interference probability is less than or equal to the first probability threshold, the synchronous acquisition of supplementary sensors near the trigger point is initiated, and the data consistency is compared to determine whether it is a real anomaly.

[0034] In some embodiments, when the acquisition and filtering module is configured to synchronously acquire the material's physical and chemical properties data and corresponding regional environmental data via a wireless sensor network, perform validity filtering on the acquired data, and transmit valid data sets that meet the correlation requirements, it further includes:

[0035] If the same data set shows opposite trends after a preset number of consecutive tests, first determine if the sensor synchronization clock is deviated.

[0036] When the sensor synchronization clock deviates, the clock is calibrated and data is collected again.

[0037] When the sensor's synchronization clock is not deviated, it is determined that data transmission has been lost and re-sampling is initiated.

[0038] In some embodiments, the instruction generation module is configured to extract material property change characteristics and environmental stimulus characteristics, determine whether the material physical and chemical property data deviate from a safety threshold, and if not, maintain the current monitoring state; if so, determine whether the anomaly is caused by environmental stimuli and whether there is temporal synchronization, and if not, trigger a self-check; if so, determine whether the material anomaly will cause structural damage risk, and if not, mark it as a minor anomaly; if so, determine it as high risk and generate a control instruction, including:

[0039] A baseline safety threshold is determined based on accelerated aging test data of the target historical building material. The current micro porosity of the target historical building material is obtained by ultrasonic testing. When the porosity is greater than a preset first multiple of the standard porosity of the target historical building material, the fluctuation range of the safety threshold is reduced.

[0040] When the porosity is less than a preset second multiple of the standard porosity of the target historical building material, the safety threshold fluctuation range is maintained within a preset third range threshold.

[0041] In some embodiments, the instruction generation module is configured to extract material property change characteristics and environmental stimulus characteristics, determine whether the material physical and chemical property data deviate from a safety threshold, and if not, maintain the current monitoring state; if so, determine whether the anomaly is caused by environmental stimuli and has temporal synchronization, and if not, trigger a self-check; if so, determine whether the material anomaly will cause structural damage risk, and if not, mark it as a minor anomaly; if so, determine it as a high risk and generate a control instruction, further including:

[0042] By calculating the penetration lag time of environmental stimuli in the target historical building material through material mass transfer simulation, it is determined whether the onset time of the abnormal physical and chemical property data of the material is within a preset threshold range of the time of occurrence of environmental stimuli plus the penetration lag time.

[0043] When the onset time of the abnormal physical and chemical property data of the material is within a preset threshold range of the time of occurrence of environmental stimulus plus the penetration hysteresis time, it is determined that the time synchronization is satisfied.

[0044] When the onset time of the abnormal physical and chemical properties data of the material is not within the preset threshold range of the time of occurrence of environmental stimulus plus the penetration hysteresis time, it is determined whether there are other environmental synergistic factors.

[0045] When other environmental synergistic factors exist, the overall lag time of the composite factors is recalculated to verify the synchronicity again.

[0046] When no other environmental factors are present, the material anomaly is determined to be caused by non-environmental factors.

[0047] In some embodiments, the control module is configured to match a corresponding microenvironment control terminal according to the control command, collect material property data in real time after control is initiated and provide feedback for judgment, and dynamically adjust the control parameters, including:

[0048] Before initiating control, finite element simulation is used to determine whether the control parameters will cause secondary damage to surrounding materials.

[0049] If the simulation is likely to cause secondary damage to surrounding materials, the parameters will be reduced by a preset threshold gradient and the simulation will be repeated until there is no risk of secondary damage.

[0050] In some embodiments, the control module is configured to match a corresponding microenvironment control terminal according to the control command, collect material property data in real time after the control is initiated and provide feedback for judgment. When dynamically adjusting the control parameters, it further includes:

[0051] Each month, a preset number of data sets of different material types are extracted. The prediction accuracy of the AI ​​correlation model is verified by using a confusion matrix. When the accuracy is less than a preset accuracy threshold, the source of the deviation is located and the factor weights in the model are optimized by using feature importance analysis.

[0052] When the accuracy rate is less than the preset accuracy threshold after optimization and re-verification, a supplementary material damage mechanism experiment is triggered to obtain new mechanism data and then retrain the model.

[0053] Compared with existing technologies, the beneficial effects of this invention are as follows: By scientifically selecting key areas based on building material characteristics and structurally vulnerable parts through a deployment module, combined with pre-collection verification and dynamic adjustment mechanisms, the lack of scientific criteria for sensor deployment is solved, ensuring the homogeneity and reliability of material and environmental data. Through synchronous acquisition, multi-dimensional validity screening, and correlation verification by the acquisition and screening modules, invalid interference data is eliminated, improving data acquisition quality and laying a solid foundation for correlation analysis. The instruction generation module improves the accuracy of material anomaly judgment and damage cause identification through dynamically corrected safety thresholds, three-layer progressive logical judgment, and causal correlation identification assisted by mass transfer simulation, solving the core problem of the disconnect between environmental and structural monitoring. The control module avoids secondary damage risks through finite element simulation and dynamically optimizes control parameters based on material state feedback, achieving precise adaptive control of the microenvironment. In summary, this application achieves deep fusion analysis of environmental stimuli, changes in material properties, and structural health status, accurately identifies associated damage mechanisms, effectively achieves preventative protection of historical buildings, and improves the intelligence and precision of protection.

[0054] The above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0055] Other features and aspects of this disclosure will become clearer from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0056] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0057] Figure 1 This is a functional block diagram of a microenvironment intelligent regulation and structural health monitoring system for the protection of historical buildings provided in an embodiment of the present invention;

[0058] Figure 2 A flowchart of a microenvironment intelligent regulation and structural health monitoring system for the protection of historical buildings, provided in an embodiment of the present invention. Detailed Implementation

[0059] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0060] See Figure 1-2 As shown, a microenvironment intelligent control and structural health monitoring system for the protection of historical buildings according to an embodiment of this application includes:

[0061] The deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on the material properties and structurally vulnerable parts of the target historical building. It collects material physical and chemical property data and corresponding regional environmental data for a preset time period, judges the effectiveness of the deployment, and adjusts invalid deployment points.

[0062] The acquisition and screening module is configured to synchronously acquire the physical and chemical property data of the material and the corresponding regional environmental data through a wireless sensor network, screen the acquired data for validity, and transmit valid data sets that meet the correlation requirements.

[0063] The instruction generation module is configured to extract material property change characteristics and environmental stimulus characteristics, determine whether the physical and chemical property data of the material deviate from the safety threshold, and if not, maintain the current monitoring state; if so, determine whether the anomaly is caused by environmental stimulus and whether there is time synchronization, and if not, trigger a self-check; if so, determine whether the material anomaly will cause structural damage risk, and if not, mark it as a minor anomaly; if so, determine it as a high risk and generate a control instruction.

[0064] The control module is configured to match the corresponding microenvironment control terminal according to the control command, collect material property data in real time after the control is started and provide feedback for judgment, and dynamically adjust the control parameters.

[0065] It should be understood that defining the core components and complete operational process of the system, its essential characteristics include a "deployment module, data acquisition and screening module, instruction generation module, and control module," along with the collaborative operational logic of each module. This is the core technical means to achieve collaborative protection of the "environment-materials-structure." The system's specific components include: material property monitoring sensors (such as moisture content, strain, and salinity sensors), environmental stimulus monitoring sensors (such as temperature, humidity, and pollutant concentration sensors), a wireless sensor network, a central processing unit (carrying the functions of each module), and microenvironment control terminals (humidification / dehumidification / ventilation / purification equipment). The operating principle is a closed-loop mechanism of "deployment-data acquisition-analysis-control": the deployment module first completes the targeted deployment and effectiveness verification of sensors; the data acquisition and screening module simultaneously acquires and screens data from the same source; the instruction generation module constructs causal relationships and generates instructions through three-layer progressive logical judgments; and the control module dynamically adjusts control parameters based on the instructions. Example Description: For Ming and Qing dynasty wooden structures, the deployment module simultaneously deploys strain sensors and temperature and humidity sensors at the mortise and tenon joints. After 72 hours of pre-collection to verify the deployment effectiveness, the acquisition module synchronously collects data at a frequency of 15 minutes per acquisition. If the moisture content of the wooden structure continuously falls below the safety threshold, the instruction generation module, after three layers of judgment, confirms that the risk of structural loosening is caused by continuous drying. The control module then activates the ultrasonic atomization humidification equipment until the moisture content returns to stability. The effect of this technology is that, through the coordinated operation of the four modules, it systematically solves the core problem of the disconnect between environmental monitoring and structural health assessment in existing technologies. It achieves the integration of data acquisition, correlation analysis, and precise control, providing a complete technical solution for the preventive protection of historical buildings and ensuring the intelligence and continuity of the protection process.

[0066] In some specific embodiments, the deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on its material properties and structurally vulnerable parts. It pre-collects material physical and chemical property data and corresponding regional environmental data for a preset duration, and determines the effectiveness of the deployment. Adjustments are made to invalid deployment points, including:

[0067] Structural mechanics simulation is used to determine whether the target area is a stress concentration area. When the target area is a stress concentration area, the maintenance records of the target area or the coefficient of variation of the moisture content or salinity of the material in the target area are used to determine whether the target area is the critical area.

[0068] When the frequency of damage to the target area in the maintenance record within a preset time is greater than or equal to a preset first threshold, the target area is determined to be the critical area.

[0069] When the coefficient of variation of the moisture content or salinity of the material in the target area is greater than or equal to a preset second threshold, the target area is determined to be the key area.

[0070] It should be understood that the necessary characteristics are "structural mechanics simulation to determine stress concentration points + maintenance records / material coefficient of variation dual criteria." The core technical means is to combine structural mechanics simulation with historical data and material property data to achieve scientific screening of key areas. Its operating principle is as follows: First, the stress distribution of the target historical building is simulated using structural mechanics simulation software (such as ANSYS) to identify stress concentration points such as mortise and tenon joints and load-bearing wall joints. For such areas, multiple conditions do not need to be met simultaneously; only the frequency of damage in the maintenance records over the past 5 years must be greater than or equal to a preset first threshold (an example threshold is 2 times), or the coefficient of variation of material moisture content / salinity must be greater than or equal to a preset second threshold (an example threshold is 0.3) to determine it as a key area. Example: When monitoring a Tang Dynasty brick and stone pagoda, structural mechanics simulation determined that the eaves support was a stress concentration point. A review of the maintenance records revealed that this area had been repaired 3 times (≥2 times) in the past 5 years. Therefore, it was directly listed as a key area and sensors were deployed. The advantages of this technology are: it avoids the blindness of relying on manual experience to select monitoring areas in existing technologies, and ensures the accuracy of key area selection by prioritizing stress concentration points and combining them with quantitative indicators, reducing sensor deployment redundancy, while ensuring the relevance of subsequent data collection, and providing a high-quality data source for correlation analysis.

[0071] In some specific embodiments, the deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on its material properties and structurally vulnerable parts. It pre-collects material physical and chemical property data and corresponding regional environmental data for a preset duration, determines the effectiveness of the deployment, and adjusts ineffective deployment points. The module also includes:

[0072] When the target area is not a stress concentration area, determine whether the material in the target area is a scarce type. When the material in the target area is a scarce type, determine whether the target area is the critical area based on the maintenance records of the target area and the coefficient of variation of the moisture content or salinity of the material in the target area.

[0073] When the frequency of damage to the target area in the maintenance record within a preset time is greater than or equal to the first threshold, and the coefficient of variation of the moisture content or salinity of the target area material is greater than or equal to the second threshold, the target area is determined to be the critical area.

[0074] Otherwise, the target area is determined not to be the critical area;

[0075] When the material in the target area is not a scarce type, the target area is determined to be the critical area based on the maintenance records of the target area and the damage diffusion rate of the material in the target area.

[0076] When the frequency of damage to the target area in the maintenance record within a preset time is greater than or equal to the first threshold, and the material damage diffusion rate of the target area is greater than or equal to the preset third threshold, the target area is determined to be the critical area.

[0077] Otherwise, the target area is determined not to be the critical area.

[0078] It should be understood that the necessary features are "material scarcity determination + multi-condition combination criteria". The technical means is to distinguish material types (scarce / non-scarce) and set differentiated screening conditions to ensure the comprehensiveness of the screening logic. Its operating principle is as follows: For non-stress concentration areas, first determine whether the material is a scarce / irreplaceable type (such as Ming and Qing Dynasty Phoebe zhennan wood, Tang Dynasty rammed earth). If so, it must simultaneously meet "damage frequency in the past 5 years ≥ first threshold" and "material coefficient of variation ≥ second threshold" to be determined as a critical area; if the material is not scarce, it must meet "damage frequency in the past 5 years ≥ first threshold" and "material damage diffusion rate ≥ preset third threshold (exemplary threshold is 0.5mm / year)". Example: The ordinary brick walls of a Qing Dynasty residence (not a stress concentration area, and the material is not scarce) have been repaired twice in the past 5 years (≥2 times), but the damage propagation rate of the bricks is only 0.3 mm / year (<0.5 mm / year), therefore it was not listed as a critical area. However, the rare rosewood window lattices in the same residence (not a stress concentration area, and the material is scarce), which have been repaired twice in the past 5 years and have a moisture content variation coefficient of 0.4 (≥0.3), are therefore identified as critical areas. The effect of this technology is: it overcomes the limitations of a single screening logic. By combining material scarcity and damage indicators, it ensures the key protection of scarce materials while avoiding over-monitoring of non-critical areas, further optimizing the sensor deployment scheme and improving the practicality and economy of the system.

[0079] In some specific embodiments, the deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on its material properties and structurally vulnerable parts. It pre-collects material physical and chemical property data and corresponding regional environmental data for a preset duration, determines the effectiveness of the deployment, and adjusts ineffective deployment points. The module also includes:

[0080] After the material property monitoring sensor and the environmental stimulus monitoring sensor have been deployed for a preset time, it is determined whether the coefficient of variation of the material physical and chemical property data is less than a preset first variation threshold.

[0081] When the coefficient of variation of the material's physical and chemical properties data is less than the first variation threshold, it is determined whether the average difference between the environmental data at this location and the environmental data at the three surrounding adjacent locations is greater than a preset fourth threshold.

[0082] When the coefficient of variation of the material's physical and chemical properties data is less than the first variation threshold, and the average difference between the environmental data at this location and the environmental data at the three adjacent locations is greater than the fourth threshold, the initial deployment is deemed invalid.

[0083] If the initial deployment is deemed invalid, multi-sensor cross-validation is initiated. If the cross-validation pass rate is less than the preset fifth threshold, the sensor is deemed to be faulty.

[0084] When the cross-validation pass rate is greater than or equal to the fifth threshold, it is determined to be a site selection deviation.

[0085] It should be understood that the essential feature is "pre-collected data dual-condition judgment + multi-sensor cross-validation". The technical means is to accurately locate deployment problems (sensor failure / location deviation) by analyzing the fluctuation characteristics and regional consistency of pre-collected data and combining multi-sensor cross-validation. Its operating principle is as follows: After the sensor is deployed, it is pre-collected for 72 hours. First, it is judged whether the coefficient of variation of the material property data is less than the preset first variation threshold (exemplary threshold is 0.05%). If so, it is judged whether the average difference between the environmental data of this point and the three adjacent points is greater than the preset fourth threshold (exemplary threshold is 10%). If both conditions are met, the deployment is initially determined to be invalid. Then, multi-sensor cross-validation is started (comparing the consistency of data from different types of sensors in the same area). If the pass rate is less than the preset fifth threshold (exemplary threshold is 85%), it is judged as a sensor failure and the sensor needs to be replaced. If the pass rate is ≥85%, it is judged as a location deviation and the location needs to be adjusted in combination with material texture or structural stress direction. Example: After pre-collecting data at a certain point on a masonry building, the salinity data had a coefficient of variation of 0.03% (<0.05%), and the ambient humidity differed from surrounding points by 12% (>10%), initially indicating that the deployment was invalid. Cross-validation revealed that the consistency between the strain sensor and salinity sensor data at this point was only 70% (<85%), indicating a sensor malfunction. After replacing the sensor and re-collecting data, the validity verification was passed. The technical effect of this invention is: it effectively avoids data unreliability issues caused by sensor malfunctions or point location deviations. Through scientific validity judgment and precise problem localization, it ensures that sensor deployment meets the data quality requirements for subsequent correlation analysis, providing a guarantee for the overall reliability of the system operation.

[0086] In some specific embodiments, the acquisition and filtering module is configured to simultaneously acquire the material's physical and chemical properties data and corresponding regional environmental data via a wireless sensor network, and when filtering the acquired data for validity and transmitting valid data sets that meet correlation requirements, it includes:

[0087] When the deviation of the material property monitoring sensor's three consecutive data acquisitions exceeds a preset first range threshold, the sensor self-calibration is triggered.

[0088] When the deviation after calibration is less than or equal to the preset second range threshold, it is marked as high-priority data and the acquisition frequency is increased.

[0089] When the deviation after calibration exceeds the second range threshold, the backup sensor is activated and the data from the faulty sensor is discarded.

[0090] When the deviation of the environmental data from the average value of the same period in the same region within a preset time is less than the preset sixth threshold, and the fluctuation range of the physical and chemical properties data of the material is less than the preset seventh threshold, it is determined that the environmental material is in dynamic equilibrium, and the collection frequency is reduced.

[0091] Otherwise, the presence of temporary external interference is determined by an environmental disturbance identification algorithm. When the probability of interference is greater than a preset first probability threshold, the data is marked as interference and removed.

[0092] When the interference probability is less than or equal to the first probability threshold, the synchronous acquisition of supplementary sensors near the trigger point is initiated, and the data consistency is compared to determine whether it is a real anomaly.

[0093] It should be understood that the essential features are "sensor self-calibration, dynamic frequency adjustment, interference identification, and supplementary acquisition." The technical means are to eliminate faulty and interfering data through multi-level logical judgment, dynamically optimize the acquisition frequency, and ensure data quality. Its operating principle is as follows: when the deviation of the material sensor's three consecutive acquisition values ​​is greater than the preset first range threshold (exemplary threshold is ±5%), the sensor self-calibration is triggered. If the deviation after calibration is less than or equal to the preset second range threshold (exemplary threshold is ±3%), it is marked as high-priority data and the acquisition frequency is increased to 5 minutes / time. If the deviation still exceeds the limit, the backup sensor is activated. When the deviation of environmental data from the average of the same period in the past three years is less than the preset sixth threshold (exemplary threshold is ±3%) and the fluctuation of material data is less than the preset seventh threshold (exemplary threshold is 0.1% / 24h), it is determined to be "environment-material dynamic balance," and the acquisition frequency is reduced to 30 minutes / time. If a single data anomaly occurs, the interference probability is judged by the environmental disturbance identification algorithm. If the probability is greater than the preset first probability threshold (exemplary threshold is 70%), the data is discarded; otherwise, the supplementary sensor is triggered for synchronous acquisition and verification. Example: A moisture content sensor for a wooden building showed a deviation of 6% (>±5%) for three consecutive measurements. After self-calibration, the deviation was reduced to 2% (≤±3%), which was marked as high-priority data and collected every 5 minutes. At a certain location, environmental data suddenly became abnormal, but material data showed no response. The algorithm identified an interference probability of 80% (>70%), determining it to be interference data caused by visitor contact and removing it. The advantages of this technology are: it effectively solves the problems of insufficient data screening and invalid data interference in the analysis of existing technologies; it reduces system energy consumption through dynamic frequency adjustment; and it ensures data validity through self-calibration and interference identification, providing a high-quality, highly relevant data source for subsequent AI-based correlation analysis.

[0094] In some specific embodiments, the acquisition and filtering module is configured to simultaneously acquire the material's physical and chemical property data and corresponding regional environmental data via a wireless sensor network, filter the acquired data for validity, and transmit valid data sets that meet correlation requirements. The module further includes:

[0095] If the same data set shows opposite trends after a preset number of consecutive tests, first determine if the sensor synchronization clock is deviated.

[0096] When the sensor synchronization clock deviates, the clock is calibrated and data is collected again.

[0097] When the sensor's synchronization clock is not deviated, it is determined that data transmission has been lost and re-sampling is initiated.

[0098] It should be understood that the essential features are "trend reversal judgment, clock calibration, and re-acquisition mechanism." The technical means ensure data correlation by judging the consistency of data trends, calibrating the synchronization clock, and initiating breakpoint resume transmission. Its operating principle is as follows: if the same data set shows an opposite trend between environmental and material data for a preset number of consecutive times (exemplary number is 2 times) (e.g., environmental humidity increases but material moisture content decreases), first check if the sensor synchronization clock is deviated. If so, calibrate the clock and re-acquire data; otherwise, it is determined that data transmission packet loss has occurred, and the breakpoint resume transmission mechanism is initiated to re-acquire data. Example: In a brick area, environmental humidity data increased twice consecutively, but salinity data continued to decrease (opposite trend). Upon inspection, it was found that the sensor synchronization clock was deviated by 2 seconds. After calibrating the clock and re-acquiring data, the data trend returned to consistency (salinity increased synchronously with the increase in environmental humidity), ensuring data correlation. The effect of this technology is: it further strengthens the correlation and reliability of data, avoids invalid correlations caused by clock deviations or transmission packet loss, and ensures that the data transmitted to the instruction generation module accurately reflects the correspondence between "environmental stimulus and material response," laying the foundation for the accuracy of causal correlation judgment.

[0099] In some specific embodiments, the instruction generation module is configured to extract material property change characteristics and environmental stimulus characteristics, determine whether the material's physical and chemical property data deviate from a safety threshold, and if not, maintain the current monitoring state; if so, determine whether the anomaly is caused by environmental stimuli and whether there is temporal synchronization, and if not, trigger a self-check; if so, determine whether the material anomaly will cause structural damage risk, and if not, mark it as a minor anomaly; if so, determine it as high risk and generate a control instruction, including:

[0100] A baseline safety threshold is determined based on accelerated aging test data of the target historical building material. The current micro porosity of the target historical building material is obtained by ultrasonic testing. When the porosity is greater than a preset first multiple of the standard porosity of the target historical building material, the fluctuation range of the safety threshold is reduced.

[0101] When the porosity is less than a preset second multiple of the standard porosity of the target historical building material, the safety threshold fluctuation range is maintained within a preset third range threshold.

[0102] It should be understood that the essential feature is "accelerated aging test baseline threshold + porosity correction". The technical means is to combine the accelerated aging data of the material with the current microscopic state to dynamically adjust the safety threshold and ensure the accuracy of anomaly judgment. Its operating principle is as follows: First, a baseline safety threshold is determined based on the accelerated aging test data of the target building material (such as a baseline threshold of 8%-12% for moisture content in wood structures). Then, the current microscopic porosity of the material is obtained through ultrasonic testing. If the porosity is greater than a preset first multiple of the standard porosity of this type of material (an example multiple is 1.2 times), the fluctuation range of the safety threshold is reduced (such as from ±10% to ±6%). If the porosity is less than a preset second multiple of the standard porosity (an example multiple is 0.8 times), the preset third range threshold is maintained (an example threshold is ±10%). Example: Ultrasonic testing of the timber in a Ming Dynasty wooden structure revealed a porosity 1.3 times (>1.2 times) that of standard pine. Therefore, the safe moisture content threshold was adjusted from 8%-12% (±10%) to 9%-11% (±6%) to avoid missed damage assessments due to decreased material tolerance. The effect of this technology is that it solves the problem of fixed safety thresholds in existing technologies, which are out of sync with the actual material condition. By dynamically adjusting the safety threshold, the assessment of material anomalies is more closely aligned with the current material performance, improving the accuracy of anomaly detection and providing a scientific basis for subsequent damage risk assessment.

[0103] In some specific embodiments, the instruction generation module is configured to extract material property change characteristics and environmental stimulus characteristics, determine whether the material's physical and chemical property data deviate from a safety threshold, and if not, maintain the current monitoring state; if so, determine whether the anomaly is caused by environmental stimuli and whether there is temporal synchronization, and if not, trigger a self-check; if so, determine whether the material anomaly will cause structural damage risk, and if not, mark it as a minor anomaly; if so, when determining it as high risk and generating a control instruction, it further includes:

[0104] By calculating the penetration lag time of environmental stimuli in the target historical building material through material mass transfer simulation, it is determined whether the onset time of the abnormal physical and chemical property data of the material is within a preset threshold range of the time of occurrence of environmental stimuli plus the penetration lag time.

[0105] When the onset time of the abnormal physical and chemical property data of the material is within a preset threshold range of the time of occurrence of environmental stimulus plus the penetration hysteresis time, it is determined that the time synchronization is satisfied.

[0106] When the onset time of the abnormal physical and chemical properties data of the material is not within the preset threshold range of the time of occurrence of environmental stimulus plus the penetration hysteresis time, it is determined whether there are other environmental synergistic factors.

[0107] When other environmental synergistic factors exist, the overall lag time of the composite factors is recalculated to verify the synchronicity again.

[0108] When no other environmental factors are present, the material anomaly is determined to be caused by non-environmental factors.

[0109] It should be understood that the essential feature is "mass transfer simulation lag time calculation + synergistic factor verification". The technical means is to accurately verify the causal relationship between environmental stimuli and material anomalies through material mass transfer simulation and synergistic factor analysis. Its operating principle is as follows: First, the penetration lag time of environmental stimuli in the target material is calculated through mass transfer simulation (e.g., 12-24 hours for wood structures, 24-48 hours for brick and stone). It is then determined whether the onset time of material anomalies is within the preset threshold range of "environmental stimulus occurrence time + lag time" (exemplary range is ±20%). If so, it is determined that the time synchronization is satisfied; if not, it is checked whether there are other environmental synergistic factors (e.g., simultaneous anomalies in temperature, humidity and SO2 concentration). If so, the comprehensive lag time is recalculated for verification; otherwise, it is determined that the anomaly is not caused by environmental factors. Example: The salinity anomaly in the brickwork of a certain masonry building began 36 hours after a period of high humidity. Mass transfer simulation showed that the penetration lag time of the masonry material was 24-48 hours. The 36-hour period falls within the range of "24 × 1.2 = 28.8 hours" to "48 × 1.2 = 57.6 hours," thus satisfying the time synchronicity requirement. In another masonry area, the strain anomaly began 72 hours after a change in ambient temperature, exceeding the masonry lag time (24-48 hours) and lacking other synergistic factors, thus being determined to be caused by non-environmental factors. The effect of this technology is: it effectively solves the problem of inaccurate causal relationship identification in existing technologies. Through scientific lag time calculation and synergistic factor verification, it accurately distinguishes between material anomalies caused by environmental and non-environmental factors, providing a guarantee for the accurate generation of subsequent control commands.

[0110] In some specific embodiments, the control module is configured to match the corresponding microenvironment control terminal according to the control command, collect material property data in real time after the control is initiated and provide feedback for judgment, and dynamically adjust the control parameters, including:

[0111] Before initiating control, finite element simulation is used to determine whether the control parameters will cause secondary damage to surrounding materials.

[0112] If the simulation is likely to cause secondary damage to surrounding materials, the parameters will be reduced by a preset threshold gradient and the simulation will be repeated until there is no risk of secondary damage.

[0113] It should be understood that the essential feature is "finite element simulation secondary damage assessment + gradient parameter adjustment". The technical means is to predict the impact of control parameters on surrounding materials through finite element simulation and dynamically adjust the parameters to avoid secondary damage. Its operating principle is as follows: Before starting control, the mechanical impact of preset control parameters (such as humidification rate and ventilation speed) on surrounding materials is analyzed using finite element simulation software (such as ABAQUS). If the simulation results show that secondary damage will occur (e.g., wind speed > 2.5 m / s leading to the peeling of crumbling bricks), the parameters are reduced by a preset threshold gradient (an example gradient of 5%) and the simulation is repeated until there is no risk of secondary damage before the control equipment is started. Example: A crumbling brick wall needs to have its ventilation equipment activated to reduce humidity. The preset ventilation speed is 3 m / s. Finite element simulation shows that this speed will cause the brick surface to peel off. The speed is reduced to 2.4 m / s by a 5% gradient. After another simulation, there is no risk of secondary damage, and the equipment is started. The technology achieves the following results: it solves the problem that existing control measures lack secondary damage protection and are prone to causing additional damage to historical buildings. By verifying the safety of the control process and optimizing the parameters before control, it ensures the safety of the control process, realizes "protective control", and avoids irreversible damage caused by improper intervention.

[0114] In some specific embodiments, the control module is configured to match the corresponding microenvironment control terminal according to the control command, collect material property data in real time after the control is initiated and provide feedback for judgment. When dynamically adjusting the control parameters, it further includes:

[0115] Each month, a preset number of data sets of different material types are extracted. The prediction accuracy of the AI ​​correlation model is verified by using a confusion matrix. When the accuracy is less than a preset accuracy threshold, the source of the deviation is located and the factor weights in the model are optimized by using feature importance analysis.

[0116] When the accuracy rate is less than the preset accuracy threshold after optimization and re-verification, a supplementary material damage mechanism experiment is triggered to obtain new mechanism data and then retrain the model.

[0117] It should be understood that the essential features are "confusion matrix model verification + feature importance analysis + mechanism supplementary experiments". The technical means is to continuously improve the accuracy of system judgment and control through data verification and model optimization. Its operating principle is as follows: no less than 50 sets of data of different material types are extracted each month, and the prediction accuracy of the AI ​​correlation model is verified by the confusion matrix. If the accuracy is less than the preset accuracy threshold (the example threshold is 90%), the source of deviation is located by feature importance analysis (such as not considering the coupling effect of water content and salinity) and the model factor weights are optimized. If the accuracy is still not up to standard after optimization, a material damage mechanism supplementary experiment is triggered (such as a salt precipitation experiment simulating different temperatures and humidity), and the model is retrained after obtaining new data. Example Description: After three months of system application, 50 sets of data from timber, brick, and rammed earth materials were extracted for verification. The model prediction accuracy was 85% (<90%). Feature importance analysis revealed that the coupling effect of moisture content and salinity in timber was not considered. After optimizing the factor weights, the accuracy improved to 92%. In another batch of verification, the accuracy was still 88% after optimization, triggering a supplementary salt precipitation test for brick materials. After supplementing the data, the model accuracy reached 93%. The technical effect is: it enables continuous iterative optimization of the system's technical solution, solves the problem of fixed models and difficulty in adapting to different materials or scenarios in existing technologies, and continuously improves the accuracy of AI correlation judgment and the precision of control through a closed-loop optimization mechanism, ensuring the long-term stable operation of the system and adapting to the protection needs of different types of historical buildings.

[0118] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0120] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0121] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A microenvironment intelligent control and structural health monitoring system for the preservation of historical buildings, characterized in that, include: The deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on the material properties and structurally vulnerable parts of the target historical building. It collects material physical and chemical property data and corresponding regional environmental data for a preset time period, judges the effectiveness of the deployment, and adjusts invalid deployment points. The acquisition and screening module is configured to synchronously acquire the physical and chemical property data of the material and the corresponding regional environmental data through a wireless sensor network, screen the acquired data for validity, and transmit valid data sets that meet the correlation requirements. The instruction generation module is configured to extract material property change characteristics and environmental stimulus characteristics, determine whether the physical and chemical property data of the material deviate from the safety threshold, and if not, maintain the current monitoring status; if so, determine whether the anomaly is caused by environmental stimulus and whether there is time synchronization, and if not, trigger self-check; if so, determine whether the material anomaly will cause structural damage risk, and if not, mark it as a minor anomaly. If so, it is judged as high risk and a control order is generated; The control module is configured to match the corresponding microenvironment control terminal according to the control command, collect material property data in real time after the control is started and provide feedback for judgment, and dynamically adjust the control parameters. A baseline safety threshold is determined based on accelerated aging test data of the target historical building material. The current micro porosity of the target historical building material is obtained by ultrasonic testing. When the porosity is greater than a preset first multiple of the standard porosity of the target historical building material, the fluctuation range of the safety threshold is reduced. When the porosity is less than a preset second multiple of the standard porosity of the target historical building material, the safety threshold fluctuation range is maintained within a preset third range threshold. By calculating the penetration lag time of environmental stimuli in the target historical building material through material mass transfer simulation, it is determined whether the onset time of the abnormal physical and chemical property data of the material is within a preset threshold range of the time of occurrence of environmental stimuli plus the penetration lag time. When the onset time of the abnormal physical and chemical property data of the material is within a preset threshold range of the time of occurrence of environmental stimulus plus the penetration hysteresis time, it is determined that the time synchronization is satisfied. When the onset time of the abnormal physical and chemical properties data of the material is not within the preset threshold range of the time of occurrence of environmental stimulus plus the penetration hysteresis time, it is determined whether there are other environmental synergistic factors. When other environmental synergistic factors exist, the overall lag time of the composite factors is recalculated to verify the synchronicity again. When no other environmental factors are present, the material anomaly is determined to be caused by non-environmental factors.

2. The intelligent microenvironment control and structural health monitoring system for the preservation of historical buildings according to claim 1, characterized in that, The deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on its material properties and structurally vulnerable parts. It pre-collects material physical and chemical property data and corresponding regional environmental data for a preset duration, and determines the effectiveness of the deployment. Adjustments are made to invalid deployment points, including: Structural mechanics simulation is used to determine whether the target area is a stress concentration area. When the target area is a stress concentration area, the maintenance records of the target area or the coefficient of variation of the moisture content or salinity of the material in the target area are used to determine whether the target area is the critical area. When the frequency of damage to the target area in the maintenance record within a preset time is greater than or equal to a preset first threshold, the target area is determined to be the critical area. When the coefficient of variation of the moisture content or salinity of the material in the target area is greater than or equal to a preset second threshold, the target area is determined to be the key area.

3. The intelligent microenvironment control and structural health monitoring system for the preservation of historical buildings according to claim 2, characterized in that, The deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on its material properties and structurally vulnerable parts. It collects material physical and chemical property data and corresponding regional environmental data for a preset duration, determines the effectiveness of the deployment, and adjusts ineffective deployment points. The module also includes: When the target area is not a stress concentration area, determine whether the material in the target area is a scarce type. When the material in the target area is a scarce type, determine whether the target area is the critical area based on the maintenance records of the target area and the coefficient of variation of the moisture content or salinity of the material in the target area. When the frequency of damage to the target area in the maintenance record within a preset time is greater than or equal to the first threshold, and the coefficient of variation of the moisture content or salinity of the target area material is greater than or equal to the second threshold, the target area is determined to be the critical area. Otherwise, the target area is determined not to be the critical area; When the material in the target area is not of a scarce type, the target area is determined to be the critical area based on the maintenance records of the target area and the damage diffusion rate of the material in the target area. When the frequency of damage to the target area in the maintenance record within a preset time is greater than or equal to the first threshold, and the material damage diffusion rate of the target area is greater than or equal to the preset third threshold, the target area is determined to be the critical area. Otherwise, the target area is determined not to be the critical area.

4. The intelligent microenvironment control and structural health monitoring system for the preservation of historical buildings according to claim 3, characterized in that, The deployment module is configured to simultaneously deploy material property monitoring sensors and environmental stimulus monitoring sensors in key areas of the target historical building based on its material properties and structurally vulnerable parts. It collects material physical and chemical property data and corresponding regional environmental data for a preset duration, determines the effectiveness of the deployment, and adjusts ineffective deployment points. The module also includes: After the material property monitoring sensor and the environmental stimulus monitoring sensor have been deployed for a preset time, it is determined whether the coefficient of variation of the material physical and chemical property data is less than a preset first variation threshold. When the coefficient of variation of the material's physical and chemical properties data is less than the first variation threshold, it is determined whether the average difference between the environmental data at this location and the environmental data at the three surrounding adjacent locations is greater than a preset fourth threshold. When the coefficient of variation of the material's physical and chemical properties data is less than the first variation threshold, and the average difference between the environmental data at this location and the environmental data at the three adjacent locations is greater than the fourth threshold, the initial deployment is deemed invalid. If the initial deployment is deemed invalid, multi-sensor cross-validation is initiated. If the cross-validation pass rate is less than the preset fifth threshold, the sensor is deemed to be faulty. When the cross-validation pass rate is greater than or equal to the fifth threshold, it is determined to be a site selection deviation.

5. A microenvironment intelligent control and structural health monitoring system for the preservation of historical buildings according to claim 4, characterized in that, The acquisition and filtering module is configured to synchronously acquire the material's physical and chemical properties data and corresponding regional environmental data via a wireless sensor network, filter the acquired data for validity, and transmit valid data sets that meet correlation requirements, including: When the deviation of the material property monitoring sensor's three consecutive data acquisitions exceeds a preset first range threshold, the sensor self-calibration is triggered. When the deviation after calibration is less than or equal to the preset second range threshold, it is marked as high-priority data and the acquisition frequency is increased. When the deviation after calibration exceeds the second range threshold, the backup sensor is activated and the data from the faulty sensor is discarded. When the deviation of the environmental data from the average value of the same period in the same region within a preset time is less than the preset sixth threshold, and the fluctuation range of the physical and chemical properties data of the material is less than the preset seventh threshold, it is determined that the environmental material is in dynamic equilibrium, and the collection frequency is reduced. Otherwise, the presence of temporary external interference is determined by an environmental disturbance identification algorithm. When the probability of interference is greater than a preset first probability threshold, it is marked as interference data and removed. When the interference probability is less than or equal to the first probability threshold, the synchronous acquisition of supplementary sensors near the trigger point is initiated, and the data consistency is compared to determine whether it is a real anomaly.

6. A microenvironment intelligent control and structural health monitoring system for the preservation of historical buildings according to claim 5, characterized in that, The acquisition and filtering module is configured to synchronously acquire the material's physical and chemical properties data and corresponding regional environmental data via a wireless sensor network, filter the acquired data for validity, and transmit valid data sets that meet the correlation requirements. It also includes: If the same data set shows opposite trends after a preset number of consecutive tests, first determine if the sensor synchronization clock is deviated. When the sensor synchronization clock deviates, the clock is calibrated and data is collected again. When the sensor's synchronization clock is not deviated, it is determined that data transmission has been lost and re-sampling is initiated.

7. A microenvironment intelligent control and structural health monitoring system for the preservation of historical buildings according to claim 6, characterized in that, The control module is configured to match the corresponding microenvironment control terminal according to the control command, collect material property data in real time after the control is started and provide feedback for judgment, and dynamically adjust the control parameters, including: Before initiating control, finite element simulation is used to determine whether the control parameters will cause secondary damage to surrounding materials. If the simulation is likely to cause secondary damage to surrounding materials, the parameters will be reduced by a preset threshold gradient and the simulation will be repeated until there is no risk of secondary damage.

8. A microenvironment intelligent control and structural health monitoring system for the preservation of historical buildings according to claim 7, characterized in that, The control module is configured to match the corresponding microenvironment control terminal according to the control command, collect material property data in real time after the control is started and provide feedback for judgment. When dynamically adjusting the control parameters, it also includes: Each month, a preset number of data sets of different material types are extracted. The prediction accuracy of the AI ​​correlation model is verified by using a confusion matrix. When the accuracy is less than a preset accuracy threshold, the source of the deviation is located and the factor weights in the model are optimized by using feature importance analysis. When the accuracy rate is less than the preset accuracy threshold after optimization and re-verification, a supplementary material damage mechanism experiment is triggered to obtain new mechanism data and then the model is retrained.

Images