A prefabricated outer wall panel cracking risk monitoring method based on strain sensors

Abstract

This invention discloses a method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors, belonging to the field of building construction monitoring technology. The method includes: acquiring real-time strain data and environmental parameters; establishing and applying an environmental compensation model based on the environmental parameters to generate dynamic environmental compensation parameters, and calibrating the real-time strain data using these parameters to obtain calibrated strain data; acquiring construction stage data and calculating strain fluctuation characteristics based on the calibrated strain data to obtain a cracking risk level signal; and triggering a corresponding graded early warning response based on the cracking risk level signal. By establishing an environmental compensation model, integrating construction stage data, calculating the cracking risk level signal, and triggering a graded early warning response, the method can accurately identify and quantify the cracking risk of prefabricated exterior wall panels during construction, achieving proactive preventative management.

Description

Technical Field

[0001] This invention relates to the field of building construction monitoring technology, and in particular to a method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors. Background Technology

[0002] Prefabricated buildings, as a development direction of the modern construction industry, are widely used due to their advantages such as fast construction speed, controllable quality, and environmental friendliness. Prefabricated exterior wall panels are important enclosure components of prefabricated buildings. During various stages of production, transportation, hoisting, and installation, due to the combined effects of various factors such as material shrinkage, temperature changes, construction loads, and uneven foundation settlement, cracks are prone to occur at joints and stress concentration areas, affecting the building's aesthetics, durability, and safety. Therefore, effective monitoring of the cracking risk of prefabricated exterior wall panels during the construction and early operation and maintenance phases is crucial.

[0003] Currently, monitoring of prefabricated exterior wall panels during construction primarily relies on manual inspections and some discrete sensor monitoring. Some projects embed strain or temperature sensors within the wall panels, using a data acquisition system to obtain the stress and strain state of the panels during construction. When sensor readings exceed preset thresholds, the system issues an alarm, alerting management personnel. This method achieves a certain degree of quantitative monitoring of the wall panel condition and represents an improvement over purely manual observation.

[0004] However, existing technologies have significant shortcomings in practical applications. First, the strain data collected by sensors is a superposition of structural strain and strain caused by environmental factors. Existing methods often struggle to effectively separate these two factors, leading to frequent false alarms from monitoring systems caused by drastic changes in ambient temperature and humidity. Second, existing monitoring methods typically ignore individual differences in construction quality and fail to correlate key construction parameters such as grout density with strain data, resulting in a single basis for risk assessment. Furthermore, alarm mechanisms generally employ simple threshold triggering modes, failing to differentiate the severity and potential causes of risks. Their response measures are also relatively passive, lacking automated, tiered processing capabilities. Summary of the Invention

[0005] To address the aforementioned issues, this invention provides a method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors. By establishing an environmental compensation model, integrating construction stage data, calculating cracking risk level signals, and triggering graded early warning responses, this method can accurately identify and quantify the cracking risk of prefabricated exterior wall panels during construction, thereby achieving proactive preventative management.

[0006] The above objectives can be achieved through the following approach: A method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors includes acquiring real-time strain data output by an array of strain sensors pre-deployed on the prefabricated exterior wall panels, and environmental parameters output by environmental temperature and humidity sensors; establishing and applying an environmental compensation model based on the environmental parameters to generate dynamic environmental compensation parameters, and calibrating the real-time strain data using the dynamic environmental compensation parameters to obtain calibrated strain data; acquiring construction stage data associated with the prefabricated exterior wall panels, and calculating strain fluctuation characteristics in conjunction with the calibrated strain data, and calculating a cracking risk level signal based on the strain fluctuation characteristics; and triggering a corresponding graded early warning response action based on the cracking risk level signal.

[0007] Optionally, acquiring real-time strain data includes: deploying a differential layout sensor group containing mutually perpendicular and intersecting sensors in the splicing joints and stress concentration areas of the prefabricated exterior wall panel; synchronously acquiring each sensor in the differential layout sensor group at a preset sampling frequency to obtain raw strain data; and performing filtering and noise reduction processing on the raw strain data to generate the real-time strain data.

[0008] Optionally, generating dynamic environmental compensation parameters includes: acquiring preset historical environmental parameters and strain data at corresponding time points; establishing a temperature-humidity-strain relationship function as the environmental compensation model by regression analysis of the historical environmental parameters and the strain data at the corresponding time points; and inputting the currently collected environmental parameters into the temperature-humidity-strain relationship function to calculate the dynamic environmental compensation parameters.

[0009] Optionally, generating the crack risk level signal includes: analyzing the calibrated strain data to obtain the time-domain coefficient of variation and frequency-domain energy distribution; obtaining grouting density data based on the construction stage data; generating a structural crack characteristic signal when the time-domain coefficient of variation is greater than a preset fluctuation threshold and the frequency-domain energy distribution is concentrated in the high-frequency band; generating a non-structural crack risk signal when the time-domain coefficient of variation is less than or equal to the preset fluctuation threshold or the frequency-domain energy distribution is not concentrated in the high-frequency band and the grouting density data is lower than a preset quality standard value; combining the structural crack characteristic signal and the non-structural crack risk signal to generate strain fluctuation characteristics; and coupling the structural crack characteristic signal and the non-structural crack risk signal based on preset weights to generate the crack risk level signal.

[0010] Optionally, the graded early warning response actions include: when the cracking risk level signal is a Level 1 warning, performing data recording and pushing to the management platform; when the cracking risk level signal is a Level 2 warning, activating the enhanced sampling mode of sensors in adjacent areas and generating a manual review instruction; when the cracking risk level signal is a Level 3 warning, sending a stop operation signal to the construction management system and generating a repair plan suggestion.

[0011] Optionally, the enhanced sampling mode includes: increasing the sensor sampling frequency in the affected area to a preset high-frequency mode; calculating the deviation rate in real time based on the newly acquired data in the high-frequency mode and a preset historical data baseline; and updating the crack risk level signal when the deviation rate exceeds a preset deviation threshold.

[0012] Optionally, the preset historical data baseline includes: after the wall panel is installed and stabilized, acquiring the initial sensor readings and construction acceptance data; adjusting the initial sensor readings based on the grouting density and installation verticality in the construction acceptance data; and using the adjusted results as the historical data baseline.

[0013] Optionally, the method further includes: obtaining actual crack repair records, comparing the actual crack repair records with historical early warning records, and generating a matching degree evaluation result; adjusting the internal parameters of the environmental compensation model based on the matching degree evaluation result to generate optimized model parameters.

[0014] Based on the same inventive concept, the present invention also provides a prefabricated exterior wall panel cracking risk monitoring system based on strain sensors, comprising: The multi-dimensional sensing module acquires real-time strain data output by the array of strain sensors pre-installed on the prefabricated exterior wall panels, as well as environmental parameters output by the ambient temperature and humidity sensors. The environmental calibration module establishes and applies an environmental compensation model based on the environmental parameters, generates dynamic environmental compensation parameters, and uses the dynamic environmental compensation parameters to calibrate the real-time strain data to obtain calibrated strain data. The risk calculation module acquires construction stage data associated with the prefabricated exterior wall panel, calculates strain fluctuation characteristics in combination with the calibrated strain data, and calculates crack risk level signal based on strain fluctuation characteristics. The graded early warning module triggers a corresponding graded early warning response action based on the crack risk level signal.

[0015] Compared with the prior art, the present invention has the following advantages: 1. By establishing an environmental compensation model, the strain data collected in real time is dynamically calibrated, effectively eliminating strain interference caused by non-structural factors such as temperature and humidity. This results in obtaining pure data that truly reflects the internal stress state of the wall panel, improving the accuracy of monitoring results and the reliability of risk identification.

[0016] 2. By combining construction phase quality data, such as grout density, with time-domain and frequency-domain characteristic analysis of sensors, a multi-dimensional risk assessment system was constructed. This system can effectively distinguish between structural crack risks and non-structural crack risks, making risk assessment more in-depth and targeted, and avoiding the one-sidedness caused by a single data source.

[0017] 3. Based on an intelligent hierarchical early warning and response mechanism, it can automatically trigger corresponding management actions according to different crack risk level signals. From simple data recording to starting enhanced sampling mode, and then directly linking with the construction management system to suspend operations, it realizes closed-loop management from risk monitoring to proactive intervention, improving the efficiency and timeliness of risk handling.

[0018] 4. By introducing a feedback optimization step, actual crack repair records are used to evaluate and adjust the internal parameters of the monitoring model in reverse. This self-learning and iterative optimization capability allows the performance of the monitoring method to continuously improve with data accumulation, better adapting to the specific conditions of the project site and ensuring the long-term effectiveness and advanced nature of the monitoring system.

[0019] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the 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 based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating a method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors, according to an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram comparing strain data before and after environmental compensation and the crack risk level curve in an embodiment of the present invention.

[0023] Figure 3 This is a schematic diagram of the deviation rate and risk escalation curve under the enhanced sampling mode of this invention.

[0024] Figure 4 This is a schematic diagram of the structure of a prefabricated exterior wall panel cracking risk monitoring system based on strain sensors, according to an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] Reference Figure 1 One embodiment of the present invention proposes a method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors. By establishing an environmental compensation model, integrating data from the construction stage, calculating cracking risk level signals, and triggering graded early warning responses, the method can accurately identify and quantify the cracking risk of prefabricated exterior wall panels during construction, thereby achieving proactive preventive management.

[0027] The method described in this embodiment specifically includes: Acquire real-time strain data from an array of strain sensors pre-installed on prefabricated exterior wall panels, as well as environmental parameters from ambient temperature and humidity sensors. An environmental compensation model is established and applied based on the environmental parameters to generate dynamic environmental compensation parameters. The real-time strain data is then calibrated using the dynamic environmental compensation parameters to obtain calibrated strain data. Acquire construction stage data associated with the prefabricated exterior wall panel, and calculate strain fluctuation characteristics based on the calibrated strain data. Calculate crack risk level signal based on the strain fluctuation characteristics. The corresponding graded early warning response action is triggered based on the crack risk level signal.

[0028] Specifically, a sensor network deployed at key locations on prefabricated exterior wall panels synchronously acquires the structure's real-time strain response and the surrounding temperature and humidity parameters, forming a multi-source data foundation. The core lies in establishing and applying a dynamic environmental compensation model. By analyzing historical data, it reveals the quantitative relationship between environmental factors and strain, thereby removing non-structural interference from the monitoring data in real time and refining the calibrated strain data to accurately reflect the structure's stress state. Integrating quality data from the construction phase, the calibrated strain signal undergoes fluctuation characteristic analysis. Through comprehensive evaluation logic, it calculates and outputs crack risk level signals that characterize different risk degrees. Ultimately, this risk level signal serves as a decision command, automatically triggering preset graded early warning response actions, forming a complete closed loop of risk discovery, assessment, and handling. By introducing the environmental compensation model, it effectively overcomes the signal distortion problem caused by environmental changes in traditional strain monitoring, improves the signal-to-noise ratio of the monitoring data and the accuracy of risk identification, and avoids false alarms or missed alarms caused by temperature and humidity changes. Secondly, it integrates construction quality data and performs in-depth feature mining on the strain signals after purification, enabling it not only to detect risks but also to make preliminary judgments on the potential causes of those risks, thus improving the depth and insight of early warnings. Finally, by establishing an automated, tiered early warning and response mechanism, monitoring results are directly translated into specific management and intervention actions, achieving a shift from passive monitoring to proactive prevention. This allows for timely and effective control of risk development, ensuring the long-term safety and durability of prefabricated building exterior wall panels and enhancing the level of intelligent management throughout the entire project lifecycle.

[0029] Optionally, acquiring real-time strain data includes: In the splicing joints and stress concentration areas of the prefabricated exterior wall panels, a differential layout sensor group containing sensors that are perpendicularly and intersecting each other is installed. The raw strain data is obtained by synchronously acquiring data from each sensor in the differential layout sensor group at a preset sampling frequency. The original strain data is filtered and denoised to generate the real-time strain data.

[0030] Specifically, sensor arrays are pre-deployed at stress-weak points in prefabricated exterior wall panels, namely splicing joints and stress concentration areas. Splicing joints are the connections between different wall panel units, prone to stress due to installation errors, inadequate grouting, or uneven settlement. Stress concentration areas refer to geometrically discontinuous locations such as openings, corners, and the perimeter of embedded parts on the wall panel, where localized stress amplification occurs under load, serving as the starting points for cracks. Differential sensor arrays are deployed at splicing joints and stress concentration areas. These arrays contain multiple mutually perpendicular and intersecting arrays of strain sensors. For example, biaxial strain gauges orthogonally arranged at 0° and 90° or triaxial strain rosettes distributed at 0°, 45°, and 90° are used, and each array of strain sensors within the differential sensor array is synchronously sampled at a preset sampling frequency. Synchronous sampling ensures that at any given moment, the strain values ​​acquired in all directions correspond to the same stress state. The selection of the preset sampling frequency needs to balance the monitoring objective and data processing capabilities. For a process like wall panel cracking, where gradual and abrupt changes coexist, the sampling frequency must be sufficient to capture the details of stress abrupt changes. The data sequence output by this process is the raw strain data. Digital filtering techniques are used to filter and denoise the raw strain data. For example, a moving average filter is applied to smooth the data to reduce the influence of high-frequency random noise. The calculation process of the moving average filter is shown below: , in, This represents the real-time strain data generated at time t, i.e., the filtered output value. This represents the raw strain data acquired at time ti. N represents the size of the filtering window, which is a preset integer whose value determines the smoothness of the filtering.

[0031] Optionally, the generated dynamic environment compensation parameters include: Acquire preset historical environmental parameters and corresponding strain data at time points; By using regression analysis of the historical environmental parameters and the strain data at the corresponding time points, a temperature-humidity-strain relationship function is established as the environmental compensation model. The currently collected environmental parameters are input into the temperature-humidity-strain relationship function to calculate the dynamic environmental compensation parameters.

[0032] Specifically, environmental temperature and humidity sensors deployed near the prefabricated exterior wall panels collect historical environmental parameters, forming multiple sets of time-series data on temperature and humidity. An array of strain sensors pre-deployed on the wall panels synchronously collects strain data at corresponding time points. The selected historical period should be the stage after the wall panels are installed, the structure is stable, and no major construction loads are applied, to ensure that strain changes during this stage are primarily driven by environmental factors. Based on the acquired historical data, a quantitative relationship between temperature / humidity and strain is established using regression analysis, expressed as a function, namely the temperature / humidity-strain relationship function. This function is the environmental compensation model in this invention. Regression analysis is a statistical method used to determine the dependency between two or more variables. In this method, strain data is used as the dependent variable, and environmental temperature and humidity parameters are used as independent variables, to perform multiple linear regression analysis: , in, That is, the strain component calculated by the environmental compensation model that is entirely caused by environmental factors. It is the temperature-strain coupling coefficient, which represents the change in strain caused by a unit temperature change. It is obtained by regression fitting of historical temperature and strain data. This is the humidity-strain coupling coefficient, representing the change in strain caused by a unit change in humidity. It is obtained by regression fitting of historical humidity and strain data. T and H represent the current real-time ambient temperature and humidity values, respectively, output by the ambient temperature and humidity sensor. and Temperature and humidity at the initial moment or a selected reference moment are used as benchmarks for calculating changes in environmental parameters. During monitoring, the real-time collected environmental parameters are substituted into the established temperature-humidity-strain relationship function for calculation. The calculated result is the theoretical strain caused by changes in temperature and humidity under the current environmental conditions, and this value is the dynamic environmental compensation parameter.

[0033] Optionally, generating the crack risk level signal includes: The calibrated strain data were analyzed to obtain the time-domain coefficient of variation and the frequency-domain energy distribution. Based on the construction stage data, the grouting density data is obtained; When the time-domain variation coefficient is greater than a preset fluctuation threshold and the frequency-domain energy distribution is concentrated in the high-frequency band, a structural crack characteristic signal is generated. When the time domain coefficient of variation is less than or equal to the preset fluctuation threshold or the frequency domain energy distribution is not concentrated in the high frequency band, and the grouting density data is lower than the preset quality standard value, a non-structural crack risk signal is generated. By combining structural crack characteristic signals and non-structural crack risk signals, strain fluctuation characteristics are generated. Based on preset weights, the structural crack characteristic signal and the non-structural crack risk signal are coupled and calculated to generate a cracking risk level signal.

[0034] Specifically, statistical analysis is performed on the calibrated strain data in the time domain to calculate the coefficient of variation (COP) within a specific time window. The COP is a dimensionless relative fluctuation index that measures the dispersion of the signal by the ratio of the standard deviation to the mean of the strain data. A rapidly increasing or persistently high COP usually indicates a drastic and unstable change in the internal stress state of the wall panel, directly reflecting the initiation or propagation of cracks. Spectral analysis is then performed on the calibrated strain data within the same time window in the frequency domain to obtain its frequency energy distribution. This is achieved using a Fast Fourier Transform (FFT) to convert the time-domain signal to a frequency-domain signal, analyzing the distribution of signal energy across different frequency ranges. If the frequency energy distribution is concentrated in the high-frequency band, it indicates that the monitoring point may be experiencing or has already experienced rapid microcrack development. Construction stage data associated with the prefabricated exterior wall panels is acquired, including grout density data. Grout density is an indicator of the fullness of grout filling in the joints of the wall panels, obtained through non-destructive testing during the construction quality acceptance phase. When the analysis results show that the time-domain coefficient of variation is greater than the preset fluctuation threshold and its frequency-domain energy distribution is concentrated in the high-frequency band, it is determined to meet the typical characteristics of structural cracks, thus generating a structural crack characteristic signal. Conversely, when the time-domain coefficient of variation does not exceed the preset fluctuation threshold, or the frequency-domain energy distribution does not show a high-frequency concentration phenomenon, that is, the strain signal itself does not show strong abrupt change characteristics, but at the same time, the associated grouting density data is lower than the preset quality standard value, it is determined that there is a potential risk caused by construction quality defects in the area, thus generating a non-structural crack risk signal. The generated structural crack characteristic signal and non-structural crack risk signal are combined to form a comprehensive strain fluctuation characteristic. Finally, the two signals are coupled and calculated based on preset weights to generate the final cracking risk level signal. , Here, RL represents the quantized value of the final calculated crack risk level signal. This is a structural crack characteristic signal, which can take the value 1 or 0, indicating whether the feature exists. This is a non-structural crack risk signal, and its value can also be 1 or 0. and These are preset weighting coefficients corresponding to two different risk signals. Their values ​​are based on engineering experience and assessments of the severity of different crack types; for example, structural cracks are usually given higher weights. The calculated RL value will be mapped to different warning levels, such as Level 1, Level 2, or Level 3. The environmental compensation and risk level calculation logic is shown in Figure 2. After compensation, the strain data accurately reflects the actual stress on the structure, and the risk level dynamically upgrades with the event, corresponding to the Level 3 warning threshold.

[0035] Optionally, the tiered early warning response actions include: When the cracking risk level signal is a Level 1 warning, the operation of recording data and pushing it to the management platform is performed. When the cracking risk level signal is a Level II warning, the enhanced sampling mode of the adjacent area sensors is activated and a manual review instruction is generated; When the cracking risk level signal is a Level 3 warning, a work stoppage signal is sent to the construction management system and a repair plan suggestion is generated.

[0036] Specifically, when the calculated crack risk level signal is a Level 1 warning, it indicates that a minor anomaly has been detected. At this time, the system triggers the lowest level of response. First, it automatically records data, marking the entire set of information, including the time the warning was triggered, the corresponding calibrated strain data, environmental parameters, and the calculated crack risk level signal, as an event and storing it in the historical database, generating a log record to alert management personnel. If the crack risk level signal is a Level 2 warning, it activates the enhanced sampling mode of sensors in adjacent areas. The data sampling frequency is increased from the conventional low-frequency mode to a preset high-frequency mode to capture high-frequency dynamic signals such as stress waves caused by expanding cracks. It automatically generates a manual review instruction. This instruction includes the unique number of the warning wall panel, the warning time, relevant sensor data charts, and a preliminary risk type assessment, and is sent to the designated on-site engineer or technical manager, requiring them to conduct an on-site inspection or in-depth data analysis to confirm the authenticity and severity of the risk. When the crack risk level signal reaches a Level 3 warning, it indicates a significant risk of structural damage to the wall panel, and immediate intervention measures are taken, executing the highest priority response. Through a pre-defined system interface, a work stoppage signal is sent, pushing a stoppage order to the mobile phones of construction workers in specific areas to ensure that construction activities that may further affect the wall panels are not affected. Simultaneously, based on identified risk characteristics, such as the presence of structural crack features, a preliminary repair plan suggestion is automatically generated, such as recommending structural reinforcement using high-pressure epoxy resin injection, and an immediate structural safety assessment is conducted.

[0037] Optionally, the enhanced sampling mode includes: Increase the sensor sampling frequency in the affected area to a preset high-frequency mode; The deviation rate is calculated in real time based on the newly acquired data collected in high-frequency mode and the preset historical data baseline. When the deviation rate exceeds the preset deviation threshold, the cracking risk level signal is updated.

[0038] Specifically, when a secondary cracking risk level signal is generated, the sampling frequency of the array strain sensor and the physically adjacent sensor group is increased from the low-frequency mode used for long-term routine monitoring to a preset high-frequency mode. The high-frequency mode is selected based on the typical dynamic characteristics of crack development, aiming to capture transient stress wave signals generated by energy release during minor structural damage events. These signals have extremely short durations and cannot be effectively captured by conventional sampling frequencies. After entering high-frequency mode, real-time analysis of the newly acquired data stream is immediately initiated by calculating the deviation rate. , in, This represents the deviation rate calculated at time t. This refers to the instantaneous value of the newly calibrated strain data acquired at time t in high-frequency mode. The baseline is a preset historical data used as a comparison benchmark. This baseline represents the strain reference value of the prefabricated exterior wall panel after installation and in a stable, risk-free state. The real-time calculated deviation rate is continuously compared with a preset deviation threshold. This preset deviation threshold is a critical value determined based on material mechanical properties, experimental data, and engineering experience, representing the boundary of the structure's transition from a stable to an unstable state. When the deviation rate at any moment exceeds the preset deviation threshold, it is determined that the risk is rapidly deteriorating and is highly likely to have evolved into substantial structural damage. The cracking risk level signal is updated, and the current Level II warning level is automatically upgraded to the highest Level III warning level, thereby triggering a more urgent and decisive graded warning response. The deviation rate calculation and risk escalation logic of the enhanced sampling mode is shown in Figure 3. High-frequency sampling captures instantaneous changes in strain. After the deviation rate exceeds the threshold, the risk level is upgraded from Level II to Level III, triggering emergency intervention. Optionally, the preset historical data baseline includes: After the wall panels are installed and stabilized, obtain the initial sensor readings and construction acceptance data; The initial readings of the sensor are adjusted based on the grout density and installation verticality data from the construction acceptance data. The adjusted results will be used as the historical data baseline.

[0039] Specifically, after the wall panel installation is completed, all connection nodes such as splice joints have been grouted, the grouting material has reached the design strength, and the entire wall panel unit is in a structurally stable state, the initial readings of all pre-deployed array strain sensor groups are acquired. These initial readings primarily reflect the original strain state of the wall panel under the combined effects of its own weight, initial installation prestress, and the ambient temperature and humidity. Key construction and acceptance data related to the wall panel are acquired, particularly grout density and installation verticality. Grout density data, obtained through non-destructive methods such as ultrasonic testing, reflects the fullness of the grout material inside the splice joints; installation verticality data, obtained through measuring tools such as laser plumb bobs, reflects the deviation between the actual installation posture of the wall panel and the design requirements. Using the acquired construction and acceptance data, the initial sensor readings are adjusted. , In this formula, This is the final historical data baseline. This is the initial reading obtained by the sensor after the wall panel has stabilized. f(C,V) is a correction function that represents the strain adjustment caused by construction deviations. C represents the grout density data, and V represents the installation verticality data. Based on regression analysis of a large amount of experimental data, it maps specific density and verticality values ​​to a strain correction value.

[0040] Optionally, the method further includes: Obtain actual crack repair records, compare the actual crack repair records with historical early warning records, and generate a matching degree assessment result; Based on the matching degree evaluation results, the internal parameters of the environmental compensation model are adjusted to generate optimized model parameters.

[0041] Specifically, actual crack repair records are obtained. These records are derived from maintenance and repair logs in the later stages of the project, detailing information on every actual crack that occurred on the prefabricated exterior wall panels, including the crack's location, shape, size, occurrence time, and confirmed cause. The obtained actual crack repair records are then precisely compared spatiotemporally with historical warning records stored in the system database. For each repair record, all historical warning records from the corresponding sensor within a certain period before the crack occurred are reviewed to confirm whether a warning was successfully issued before the crack actually appeared, and whether the warning level and timing were appropriate. This comparison generates a matching degree evaluation result. This evaluation result can be quantified into multiple indicators, such as the warning recall rate (how many actual cracks were successfully warned of by the system); the warning precision rate (how many of the system's warnings were ultimately confirmed as actual cracks); and the warning lag time. Based on the generated matching degree evaluation result, the internal parameters of the environmental compensation model are adaptively adjusted. If the matching degree evaluation result shows that the system experiences frequent false alarms or missed alarms under certain environmental conditions, then the current environmental compensation model has not completely and accurately isolated the influence of environmental factors. For example, during seasons of drastic temperature changes, frequent false alarms in the system may indicate that the temperature-strain coupling coefficient in the model is set too high, causing the system to misinterpret normal temperature strain as structural strain. Initiating an optimization algorithm, such as gradient descent, with the goal of minimizing the deviation between the warning results and the actual results, automatically adjusts the internal parameters in the environmental compensation model, generates a set of optimized model parameters, and uses these to update the original environmental compensation model.

[0042] Based on the same inventive concept, such as Figure 4 As shown, the present invention also provides a cracking risk monitoring system for prefabricated exterior wall panels based on strain sensors, the system comprising: The multi-dimensional sensing module acquires real-time strain data output by the array of strain sensors pre-installed on the prefabricated exterior wall panels, as well as environmental parameters output by the ambient temperature and humidity sensors. The environmental calibration module establishes and applies an environmental compensation model based on the environmental parameters, generates dynamic environmental compensation parameters, and uses the dynamic environmental compensation parameters to calibrate the real-time strain data to obtain calibrated strain data. The risk calculation module acquires construction stage data associated with the prefabricated exterior wall panel, calculates strain fluctuation characteristics in combination with the calibrated strain data, and calculates crack risk level signal based on strain fluctuation characteristics. The graded early warning module triggers a corresponding graded early warning response action based on the crack risk level signal.

[0043] Example 1: To verify the feasibility of this invention in practice, it was applied to the construction monitoring process of a high-rise prefabricated residential project. During the hoisting, grouting, and subsequent curing stages, the exterior wall panels of this project are susceptible to cracking due to multiple factors such as construction loads, temperature changes, and material shrinkage. Traditional manual inspection methods are difficult to detect early micro-cracks in real time and accurately. This invention aims to solve this problem by providing a proactive and intelligent crack risk monitoring and early warning solution for this project.

[0044] In this embodiment, a differential array of strain sensors was pre-deployed at key locations on exterior wall panel A-12-05 (section A, 12th floor) of the project, including stress concentration areas such as joints and window corners. The sensor array uses biaxial strain gauges orthogonal at 0° and 90° angles, and is equipped with ambient temperature and humidity sensors. The data acquisition system performs routine monitoring at a preset sampling frequency of 1Hz.

[0045] After the wall panel was installed and grouted to a stable state, initial sensor readings were collected. Based on construction acceptance data, the grout density of the wall panel joints was 92%, and there was a slight deviation in installation verticality. The initial sensor readings were adjusted according to a pre-set correction model, generating 25 readings for sensor S-01 at the window corner. The historical data baseline represents the strain state of the point under healthy conditions but with initial construction deviations.

[0046] During the monitoring period, a temperature-humidity-strain relationship function was established as an environmental compensation model based on regression analysis of historical data, where the temperature-strain coupling coefficient was 5. The humidity-strain coupling coefficient is 2. The reference temperature is 20°C and the reference humidity is 60%.

[0047] During a monitoring process on a certain day, the present invention recorded and processed the following series of events, and the specific data are shown in Tables 1 to 3.

[0048] At 2:30 PM, the ambient temperature rose from 32℃ to 35℃, while the humidity remained stable. The raw strain data collected by the S-01 sensor fluctuated. After noise reduction via moving average filtering, the real-time strain data was 98... The system application environmental compensation model calculated the environmental compensation parameter to be 75. The calibrated strain data is 23. The risk level is close to the historical baseline and remains at a safe level.

[0049] At 15:10, heavy tower crane operations were observed in the vicinity, and the strain data from the S-01 sensor, after calibration, began to show slight non-periodic fluctuations. Analysis of the data for this period revealed a slight increase in the time-domain coefficient of variation, but it did not exceed the preset fluctuation threshold for structural cracks. However, combined with data from the construction phase where the grout density at this location was below standard, the system determined that there was a risk of non-structural cracks and generated a non-structural crack risk signal. Based on weights of 0.7 and 0.3, and using the coupled calculation formula, the crack risk level value RL = 0.3 was calculated. The system triggered a Level 1 warning, recorded the event, and alerted management personnel.

[0050] At 15:45, a tower crane performed a large-tonnage component hoisting operation, and the strain data of the S-01 sensor, after calibration, experienced a sharp jump. Analysis revealed that the time-domain coefficient of variation during this period exceeded the preset fluctuation threshold, and the frequency-domain energy distribution was concentrated in the high-frequency range. The system determined that a sudden change in structural stress had occurred, generating a structural crack characteristic signal. The calculated crack risk level value RL=0.7, triggering a level-two warning.

[0051] Upon triggering the Level 2 warning, the system immediately activated the enhanced sampling mode of sensors in adjacent areas, increasing the sampling frequency to 50Hz, and sent a manual verification command to the site. In high-frequency mode, the system calculates the new data in real time relative to the historical data baseline of 25. The deviation rate. At 15:46:02, the instantaneous strain value acquired by the high-frequency mode reached 48. The calculated deviation rate was 0.92. This value exceeded the preset deviation threshold of 0.5, indicating that structural damage was developing rapidly. The system immediately updated the crack risk level signal to a level three warning.

[0052] The moment the Level 3 warning was triggered, the system sent a stop-work signal to the construction management system via an interface, requiring the immediate cessation of relevant tower crane operations. Simultaneously, based on its expert knowledge base, the system generated a repair plan recommendation: a high-risk signal of structural cracking was detected at the corner of the window opening in wall panel A-12-05. The system recommended immediately suspending surrounding construction, organizing personnel for on-site investigation, and preparing to use high-pressure epoxy resin injection for structural reinforcement.

[0053] Later, the project team optimized the model based on actual crack repair records. They discovered that the system had generated several false alarms in low-temperature winter conditions. By comparing the repair records with historical warning records and generating a matching degree assessment, the system automatically fine-tuned the internal parameters of the environmental compensation model, optimizing the temperature-strain coupling coefficient, thereby improving the accuracy of warnings under similar environmental conditions.

[0054] Table 1. Strain Monitoring and Environmental Compensation Data for Prefabricated Exterior Wall Panels A-12-05

[0055] Table 2. Analysis of Cracking Risk Characteristics and Graded Early Warning Response Data

[0056] Table 3. Enhanced Sampling Mode and Risk Escalation Judgment Data Table

[0057] Tables 1 to 3 above record the application data of the present invention in a real construction scenario, showing in detail the entire process from data collection, environmental compensation, risk identification to graded response.

[0058] The data in Table 1 show that the present invention effectively eliminates strain interference caused by temperature changes through an environmental compensation model, and obtains calibrated strain data that can truly reflect the stress on the structure, laying the foundation for accurate subsequent judgment.

[0059] Table 2 clearly demonstrates how this method integrates time-domain, frequency-domain features, and construction quality information to accurately classify risks and trigger response actions that match the risk level, thus realizing a shift from passive monitoring to proactive management.

[0060] The data in Table 3 demonstrates the effectiveness of the enhanced sampling mode. By switching to high-frequency sampling and calculating the bias rate in real time during high-risk moments, the rapid evolution of damage can be captured on a millisecond timescale, enabling timely risk escalation decisions and gaining valuable time for intervention.

[0061] In summary, this embodiment verifies that the present invention can improve the accuracy, timeliness, and intelligence level of prefabricated exterior wall panel crack risk monitoring, effectively ensuring construction safety and the long-term durability of building structures.

[0062] It should be noted that the electrical connections between the various units described above do not necessarily represent direct or indirect connections. Any indirect connection method can be applied to the embodiments of the present invention as long as it achieves the purpose of the present invention. The above descriptions are merely exemplary embodiments of the present invention and should not be construed as limiting the scope of the present invention.

[0063] All equivalent changes and modifications made in accordance with the teachings of this invention are still within the scope of this invention. Those skilled in the art will readily conceive of other embodiments of this invention upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this invention that follow the general principles of this invention and include common knowledge or conventional techniques in the art not described herein.

Claims

1. A method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors, characterized in that, include: Acquire real-time strain data from an array of strain sensors pre-installed on prefabricated exterior wall panels, as well as environmental parameters from ambient temperature and humidity sensors. An environmental compensation model is established and applied based on the environmental parameters to generate dynamic environmental compensation parameters. The real-time strain data is then calibrated using the dynamic environmental compensation parameters to obtain calibrated strain data. Acquire construction stage data associated with the prefabricated exterior wall panel, and calculate strain fluctuation characteristics based on the calibrated strain data. Calculate crack risk level signal based on the strain fluctuation characteristics. The corresponding graded early warning response action is triggered based on the crack risk level signal.

2. The method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors according to claim 1, characterized in that, The acquisition of real-time strain data includes: In the splicing joints and stress concentration areas of the prefabricated exterior wall panels, a differential layout sensor group containing sensors that are perpendicularly and intersecting each other is installed. The raw strain data is obtained by synchronously acquiring data from each sensor in the differential layout sensor group at a preset sampling frequency. The original strain data is filtered and denoised to generate the real-time strain data.

3. The method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors according to claim 1, characterized in that, The generated dynamic environment compensation parameters include: Acquire preset historical environmental parameters and corresponding strain data at time points; By using regression analysis of the historical environmental parameters and the strain data at the corresponding time points, a temperature-humidity-strain relationship function is established as the environmental compensation model. The currently collected environmental parameters are input into the temperature-humidity-strain relationship function to calculate the dynamic environmental compensation parameters.

4. The method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors according to claim 1, characterized in that, The generated crack risk level signal includes: The calibrated strain data were analyzed to obtain the time-domain coefficient of variation and the frequency-domain energy distribution. Based on the construction stage data, the grouting density data is obtained; When the time-domain variation coefficient is greater than a preset fluctuation threshold and the frequency-domain energy distribution is concentrated in the high-frequency band, a structural crack characteristic signal is generated. When the time domain coefficient of variation is less than or equal to the preset fluctuation threshold or the frequency domain energy distribution is not concentrated in the high frequency band, and the grouting density data is lower than the preset quality standard value, a non-structural crack risk signal is generated. By combining structural crack characteristic signals and non-structural crack risk signals, strain fluctuation characteristics are generated. Based on preset weights, the structural crack characteristic signal and the non-structural crack risk signal are coupled and calculated to generate a cracking risk level signal.

5. The method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors according to claim 1, characterized in that, The tiered early warning response actions include: When the cracking risk level signal is a Level 1 warning, the operation of recording data and pushing it to the management platform is performed. When the cracking risk level signal is a Level II warning, the enhanced sampling mode of the adjacent area sensors is activated and a manual review instruction is generated; When the cracking risk level signal is a Level 3 warning, a work stoppage signal is sent to the construction management system and a repair plan suggestion is generated.

6. The method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors according to claim 5, characterized in that, The enhanced sampling mode includes: Increase the sensor sampling frequency in the affected area to a preset high-frequency mode; The deviation rate is calculated in real time based on the newly acquired data collected in high-frequency mode and the preset historical data baseline. When the deviation rate exceeds the preset deviation threshold, the cracking risk level signal is updated.

7. The method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors according to claim 6, characterized in that, The preset historical data baseline includes: After the wall panels are installed and stabilized, obtain the initial sensor readings and construction acceptance data; The initial readings of the sensor are adjusted based on the grout density and installation verticality data from the construction acceptance data. The adjusted results will be used as the historical data baseline.

8. The method for monitoring the cracking risk of prefabricated exterior wall panels based on strain sensors according to claim 1, characterized in that, The method further includes: Obtain actual crack repair records, compare the actual crack repair records with historical early warning records, and generate a matching degree assessment result; Based on the matching degree evaluation results, the internal parameters of the environmental compensation model are adjusted to generate optimized model parameters.

9. A strain sensor-based prefabricated exterior wall panel cracking risk monitoring system, applied to the strain sensor-based prefabricated exterior wall panel cracking risk monitoring method as described in any one of claims 1-8, characterized in that, The system includes: The multi-dimensional sensing module acquires real-time strain data output by the array of strain sensors pre-installed on the prefabricated exterior wall panels, as well as environmental parameters output by the ambient temperature and humidity sensors. The environmental calibration module establishes and applies an environmental compensation model based on the environmental parameters, generates dynamic environmental compensation parameters, and uses the dynamic environmental compensation parameters to calibrate the real-time strain data to obtain calibrated strain data. The risk calculation module acquires construction stage data associated with the prefabricated exterior wall panel, calculates strain fluctuation characteristics in combination with the calibrated strain data, and calculates crack risk level signal based on strain fluctuation characteristics. The graded early warning module triggers a corresponding graded early warning response action based on the crack risk level signal.

Images