Stress monitoring method and device

Abstract

The invention relates to a stress monitoring method and device and a storage medium, and belongs to the field of Internet of Things, the method identifies the trend of strain change according to stress and strain data monitored in real time, and divides the construction process into a dynamic strain period and a stable strain period. In a stable strain period, the system adopts a relatively high initial alarm threshold value, so that unnecessary false alarms are reduced, and the construction efficiency is improved; and in a dynamic strain period, the system dynamically reduces an actual alarm threshold according to a strain prediction result, so that the alarm sensitivity is improved, and potential structure risks are ensured to be captured in time. The invention further provides a stress monitoring device and a storage medium.

Description

Technical Field

[0001] The present invention belongs to the field of Internet of Things, and in particular relates to a stress monitoring method and device. Background Art

[0002] The Internet of Things (IoT) information collection system based on the Building Information Model (BIM) visualization platform is a system that integrates BIM technology and IoT technology, and is used to monitor and manage various types of information of construction projects in real time. In this system, the BIM visualization platform provides a three-dimensional digital model that can fully display all aspects of the building, including structure, equipment, and space layout. IoT devices, such as sensors and smart devices, are installed inside and outside the building, and can collect various data including temperature, humidity, air quality, energy consumption, equipment status, etc. in real time. These data are transmitted to the BIM platform via wireless network, updated and displayed in real time in the three-dimensional model, so that managers can intuitively view the real-time status of each part of the building.

[0003] When carrying out construction work, it is necessary to collect the stress data of the building, which is a key means to ensure the safety of the building structure and extend its service life. By monitoring the stress data in real time, the system can accurately capture the response changes of the building structure under various loads, and promptly detect possible structural problems or potential damage, such as cracks, deformations or local instability. These data not only provide a reliable basis for the daily maintenance of the building, but also can quickly assess the degree of damage and safety status of the structure when disaster events (such as earthquakes or strong winds) occur, help formulate effective emergency response and repair strategies, and ensure the safety and reliability of the building.

[0004] In the prior art, a fixed alarm threshold is usually set for the collected stress data to monitor the construction process. During the construction process, especially when the structure is modified, new loads are added, or important supporting components are removed, stress changes are frequent and uncertain. The use of fixed alarm thresholds will have some serious impacts on stress data collection and monitoring, and cannot adapt to the dynamic changes of stress during the construction process. Summary of the invention

[0005] In view of the above deficiencies in the prior art, the purpose of the invention is to provide a stress monitoring method and device to dynamically adjust the alarm threshold to adapt to the dynamic changes of stress during the construction process and reduce the probability of false alarms.

[0006] A first aspect of the present invention provides a stress monitoring method, comprising:

[0007] S1, collecting stress data, and preprocessing the stress data to obtain preprocessed stress data;

[0008] S2, extracting features from the preprocessed stress data, and determining a strain coefficient according to the extracted features;

[0009] S3, dividing the construction process into a dynamic strain period and a stable strain period according to the strain coefficient;

[0010] S4, setting the initial alarm threshold for each monitoring period;

[0011] S5, dynamically adjusting the actual alarm threshold according to the initial alarm threshold and the strain factor during the dynamic strain period;

[0012] S6, performing real-time monitoring of stress according to the calculated actual alarm threshold.

[0013] The stress monitoring method of the present invention identifies the trend of strain change based on the real-time monitored stress and strain data, and divides the construction process into a dynamic strain period and a stable strain period. In the stable strain period, the system adopts an initial alarm threshold greater than the first initial threshold to reduce unnecessary false alarms and improve construction efficiency; while in the dynamic strain period, the system dynamically lowers the actual alarm threshold according to the strain prediction results, improves the alarm sensitivity, and ensures that potential structural risks are captured in a timely manner.

[0014] Furthermore, the stress data collected in S1 includes:

[0015] Transmit stress data collected by field sensors to a central server or cloud storage in real time;

[0016] Integrate the collected stress data with the Building Information Model (BIM) platform;

[0017] The BIM platform is used to monitor and analyze the integrated stress data in real time.

[0018] Further, preprocessing the stress data includes:

[0019] The stress data is subjected to noise removal, missing value filling or standardization processing.

[0020] Furthermore, feature extraction is performed on the preprocessed stress data, and the strain coefficient is determined according to the extracted features, including:

[0021] The extracted features include the frequency, degree of deviation and cumulative change of peak values ​​in the stress data during the monitoring period;

[0022] Generate a stress peak deviation index and a stress accumulation index according to the frequency of occurrence of the peak, the degree of deviation and the cumulative change;

[0023] A gauge factor is generated based on the stress peak deviation index and the stress accumulation index.

[0024] Further, generating a stress peak deviation index according to the frequency of occurrence of the peak value, the degree of deviation and the cumulative change includes:

[0025] During the monitoring period, the stress data time series is traversed to detect the local peak point of the stress data;

[0026] Calculate the time difference between two consecutive local peak points to obtain the distance between adjacent local peak points;

[0027] Calculate the absolute difference between the time intervals of adjacent local peak points;

[0028] The absolute differences in the time intervals between all adjacent local peak points are weighted summed to generate the stress peak deviation index.

[0029] Furthermore, the stress accumulation index is generated according to the frequency of peak occurrence, degree of deviation and cumulative change, including:

[0030] The collected stress data is recorded as S(t) in time series, where t is a time variable and S(t) represents the stress value at time t;

[0031] Calculate the instantaneous rate of change of stress S′(t) is the instantaneous rate of change of stress at time t;

[0032] The instantaneous rate of change of stress S'(t) is integrated during the monitoring period to obtain the cumulative amount of stress change Where A is the cumulative amount of stress change, indicating the total stress change during the monitoring period, |S′(t)| is the absolute value of the instantaneous change rate, t0 and t n Respectively represent the start time and end time of the monitoring period;

[0033] The stress accumulation index is generated according to the following formula:

[0034]

[0035] Among them, SAI μ is the stress accumulation index, which is used to measure the overall change of stress during the monitoring period. n -t0 is the length of the monitoring period.

[0036] Further, generating a strain factor according to the stress peak deviation index and the stress accumulation index includes:

[0037] Input the stress peak deviation index and stress accumulation index into a pre-trained machine learning model to generate the gauge factor; or

[0038] The gauge factor Strain is generated according to the following formula Coff :

[0039]

[0040] Among them, SPDI μ is the stress peak deviation index, SAI μ is the stress accumulation index, They are stress peak deviation index SPDI μ and stress accumulation index SAI μ The preset scaling factor of Both are greater than 0.

[0041] Furthermore, according to the strain coefficient, the construction process is divided into a dynamic strain period and a stable strain period, including:

[0042] If the strain factor is greater than the strain factor reference threshold, the construction process during the monitoring period is divided into a dynamic strain period;

[0043] If the strain factor is less than or equal to the strain factor reference threshold, the construction process during the monitoring period is divided into a stable strain period.

[0044] Further, setting the initial alarm threshold for each monitoring period includes:

[0045] For each monitoring period, an initial alarm threshold is set to be a threshold greater than a first initial threshold;

[0046] Among them, using the first initial threshold can filter out strain fluctuations caused by normal construction activities.

[0047] Furthermore, during the dynamic strain period, dynamically adjusting the actual alarm threshold according to the initial alarm threshold and the strain factor includes:

[0048] For the dynamic strain period, the gauge coefficient difference ΔStrain is calculated. The gauge coefficient difference represents the difference between the current gauge coefficient and the gauge coefficient reference threshold. The gauge coefficient difference is used to evaluate the degree of current strain change relative to the reference value. The gauge coefficient difference ΔStrain is determined according to the following formula: ΔStrain = Strain - Strain ref , Strain is the strain coefficient under dynamic strain period, Strain ref is the gauge factor reference threshold, ΔStrain is the gauge factor difference;

[0049] Based on the strain coefficient difference, the adjustment factor of the alarm threshold is determined. The adjustment factor is used to dynamically lower the alarm threshold and improve the sensitivity of the alarm. The adjustment factor is determined according to the following formula: α=1+exp(-β·ΔStrain), where α is the adjustment factor of the alarm threshold and α>1, exp represents an exponential function, and β is the adjustment coefficient;

[0050] Calculate the actual alarm threshold using the initial alarm threshold and the alarm threshold adjustment factor T init is the initial alarm threshold, T actual is the actual alarm threshold.

[0051] A second aspect of the present invention provides a device for implementing a stress monitoring method, comprising:

[0052] A data acquisition and preprocessing module is configured to collect stress data, preprocess the stress data, and obtain preprocessed stress data;

[0053] A feature extraction and strain prediction module is configured to extract features from the preprocessed stress data and determine a strain coefficient based on the extracted features;

[0054] A strain period division module is configured to divide the construction process into a dynamic strain period and a stable strain period according to the strain coefficient;

[0055] An initial alarm threshold setting module, configured to set an initial alarm threshold for each monitoring period;

[0056] A dynamic alarm threshold adjustment module, configured to dynamically adjust the actual alarm threshold according to the initial alarm threshold and the strain factor during the dynamic strain period;

[0057] The real-time monitoring module is configured to perform real-time monitoring of the strain situation according to the calculated actual alarm threshold.

[0058] A third aspect of the present invention provides a stress monitoring device, comprising a memory, a processor and a user interface;

[0059] The memory is used to store computer programs;

[0060] The user interface is used to interact with the user;

[0061] The processor is used to read the computer program in the memory, and when the processor executes the computer program, the above-mentioned stress monitoring method is implemented.

[0062] According to a fourth aspect of the present invention, a processor-readable storage medium is provided. The processor-readable storage medium stores a computer program. When a processor executes the computer program, the above-mentioned stress monitoring method is implemented.

[0063] The beneficial effects of the present invention are as follows:

[0064] The method and device described in the present invention can slide and search for the optimal position of the target object cross-section in the cross-sectional diagram by setting a series of cross-sectional diagrams on the cross-sectional axis, directly locate and mark the target object area on the selected cross-sectional diagram, fit the three-dimensional contour of the target object through an algorithm and perform image emphasis processing, thereby improving the target search efficiency, solving the problems of low automation level, inaccurate target positioning and marking, high technical level requirements for testers, cumbersome operation and long time consumption of existing methods; at the same time, it fundamentally eliminates the gross errors introduced by inaccurate target selection, effectively ensures the quality of target object marking, and provides reliable training sample data for the realization of related dangerous goods intelligent identification technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The accompanying drawings are only used to illustrate specific embodiments and are not considered to limit the present invention. In the entire drawings, the same reference symbols represent the same components. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0066] Figure 1 A flow chart of a stress monitoring method according to an embodiment of the present invention;

[0067] Figure 2 A schematic diagram of a method for generating a gauge coefficient according to an embodiment of the present invention;

[0068] Figure 3 A schematic diagram of a method for generating a stress peak deviation index according to an embodiment of the present invention;

[0069] Figure 4 A schematic diagram of a stress monitoring device according to an embodiment of the present invention;

[0070] Figure 5 FIG. 4 is a schematic diagram of another stress monitoring device according to an embodiment of the present invention.

[0071] Reference numerals:

[0072] S1, step 1; S2, step 2; S3, step 3; S4, step 4; S5, step 5; S6, step 6; S201, step 201; S202, step 202; S203, step 203; S301, step 301; S302, step 302; S303, step 303; S304, step 304; 401, data acquisition and preprocessing module; 402, feature extraction and strain prediction module; 403, strain time period division module; 404, initial alarm threshold setting module; 405, dynamic alarm threshold adjustment module; 406, real-time monitoring module; 501, processor; 502, memory; 503, user interface. DETAILED DESCRIPTION

[0073] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work should fall within the scope of protection of the present invention.

[0074] Furthermore, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts disclosed in the present invention.

[0075] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the orientation or position relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. The terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0076] SRv6 SFC (Segment Routing over IPv6 Service Function Chain) is a technology that adds SRv6 path information to the original message to guide the message to pass through the application layer service device in sequence along the specified path.

[0077] SC (Service Classifier): Located at the edge of the SRV6SFC service chain network, it is the source node of the service chain path. SC can use different diversion methods to introduce service data into the SRV6TE Policy tunnel for forwarding.

[0078] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of methods and systems consistent with some aspects of the present invention as detailed in the appended claims.

[0079] In the prior art, a fixed alarm threshold is usually set for the collected stress data to monitor the construction process. During the construction process, for example, when the structure is modified, a new load is added, or important supporting components are removed, the stress changes frequently and uncertainly. The use of a fixed alarm threshold will have a serious impact on the stress data collection and monitoring, because the fixed alarm threshold cannot adapt to the dynamic changes of stress during the construction process. For example, the following two situations:

[0080] 1. In the case of frequent and uncertain stress changes, if the alarm threshold is set high, the system may not be able to capture potential risk signals in time, resulting in failure to detect structural problems in time, thereby increasing the risk of structural instability or collapse. For example, when the structure is subjected to uneven loads or sudden external forces (such as wind loads and earthquake loads), the system may not be able to immediately issue an alarm when the structural stress exceeds the safety limit, thereby increasing the risk of structural instability or collapse. This situation is particularly dangerous in high-risk operations, as failure to respond in time may lead to catastrophic consequences.

[0081] 2. When the structure is stable and the external conditions are good, a fixed lower alarm threshold may trigger a large number of false alarms and unnecessary alarms, disrupting the normal construction process and thus ignoring the real structural risks. For example, normal stress fluctuations caused by slight mechanical vibrations or equipment operation, although judged to exceed the low threshold in the system, do not actually pose a real structural risk. In this case, the system frequently issues false alarms, causing on-site construction personnel to repeatedly stop their work to check and confirm these alarms.

[0082] In view of the problems existing in the prior art, the present invention proposes a stress monitoring method. Through the Internet of Things information collection system based on the BIM visualization platform, combined with the feature extraction of stress data and the application of machine learning models, the alarm threshold can be dynamically adjusted to effectively solve the problems caused by the fixed alarm threshold.

[0083] The present invention provides a stress monitoring method, such as Figure 1 As shown, the method includes steps S1 to S6:

[0084] S1, collecting stress data, preprocessing the stress data, and obtaining preprocessed stress data;

[0085] S2, extracting features from the preprocessed stress data and determining the strain coefficient based on the extracted features;

[0086] S3, according to the strain coefficient, the construction process is divided into a dynamic strain period and a stable strain period;

[0087] S4, setting the initial alarm threshold for each monitoring period;

[0088] S5, dynamically adjusting the actual alarm threshold according to the initial alarm threshold and the strain factor during the dynamic strain period;

[0089] S6, performing real-time monitoring of stress according to the calculated actual alarm threshold.

[0090] As an optional example, in the present invention, the construction process may be a building construction process.

[0091] The stress monitoring method of the present invention can identify the trend of strain changes according to the real-time monitored stress and strain data during the construction process, and divide the construction process into a dynamic strain period and a stable strain period. During the stable strain period, the system adopts a higher initial alarm threshold to reduce unnecessary false alarms and improve construction efficiency; while during the dynamic strain period, the system dynamically lowers the actual alarm threshold according to the strain prediction results to improve the alarm sensitivity and ensure that potential structural risks are captured in time. This intelligent monitoring and dynamic adjustment mechanism can not only reduce false alarms and missed alarms, but also enhance the real-time monitoring capability of structural safety, significantly improving the safety and management efficiency during the construction process.

[0092] As an optional example, the stress data collected in S1 includes:

[0093] Transmit stress data collected by field sensors to a central server or cloud storage in real time;

[0094] Integrate the collected stress data with the Building Information Model (BIM) platform;

[0095] The BIM platform is used to monitor and analyze the integrated stress data in real time.

[0096] For example, the collection of stress data in S1 can be achieved through the following steps A, B, and C:

[0097] Step A: Sensor deployment and planning at the construction site.

[0098] This step includes selecting appropriate locations to install stress sensors, which are usually key parts of the structure, such as beams, columns, supporting structures, etc., which can effectively capture the key points of stress changes. As an optional example, the type of sensor can be a stress sensor that is high-precision, durable, and adaptable to changes in the construction environment. At the same time, considering the comprehensiveness and accuracy of data collection, the number and layout density of sensors need to be configured according to the complexity of the building structure and the needs of the construction stage to ensure that the stress data of each key area can be effectively monitored.

[0099] After the sensor is installed, the data acquisition system is configured. The data acquisition system includes a data acquisition device and a wireless data transmission device to transmit the stress data collected by the field sensor to a central server or cloud storage in real time.

[0100] The configuration of the data acquisition system needs to ensure the stability and security of data transmission to avoid data loss or tampering. As an optional example, the sampling frequency and data format can also be set to ensure that the collected data has high time resolution and a unified format to facilitate subsequent data processing and analysis.

[0101] Step B: Integrate the collected stress data with the BIM platform.

[0102] The BIM platform is a digital model that contains information about the entire life cycle of a building. By integrating with real-time stress data, these dynamic data can be directly mapped to the three-dimensional building model. The process of data integration may involve associating real-time data streams with corresponding structural elements in the BIM model to ensure that the data is visualized at the correct location and time. To achieve this, it is necessary to develop an interface or use existing plug-ins to connect the data acquisition system and the BIM platform so that data can be automatically imported and updated into the BIM model to provide real-time stress monitoring.

[0103] Step C: Use the BIM platform to monitor and analyze the integrated stress data in real time.

[0104] The BIM platform can not only provide a three-dimensional visual building model, but also update and visualize stress data in real time, allowing construction managers to intuitively view the stress status of each part of the building. As an optional example, on this basis, the BIM platform can integrate data analysis tools to perform real-time analysis of stress data, such as identifying abnormal stress changes and predicting potential structural problems. This real-time monitoring and analysis function can help the construction management team respond quickly and take timely measures to prevent the development and deterioration of structural problems, ensuring the safety and smooth progress of the construction process.

[0105] As an optional example, in the above S1, the preprocessing of stress data includes:

[0106] Remove noise, fill missing values ​​or standardize stress data.

[0107] Preprocessing is data cleaning, including noise removal, missing value filling, and standardization, etc., to ensure the integrity and consistency of the data, remove outliers in the data, and make the stress data comparable during analysis through normalization or standardization methods, so as to provide data input for subsequent feature extraction and analysis.

[0108] After the processing of S1 above, the pre-processed stress data is obtained.

[0109] As an optional example, the above S2 extracts features from the pre-processed stress data and determines the strain coefficient based on the extracted features. In this step, feature extraction is performed on the cleaned and pre-processed stress data. Based on the extracted features, the trained machine learning model is used to predict the strain data during the monitoring period to identify the strain change trend during the construction process.

[0110] Specifically, Figure 2 As shown, including S201, S202 and S203:

[0111] S201. The extracted features include the frequency, degree of deviation and cumulative change of peak values ​​in the stress data during a monitoring period.

[0112] In this embodiment, the extracted features include the frequency of occurrence of peak values ​​in stress data during the monitoring period, the degree of deviation, and the cumulative change of stress during the monitoring period. After the features are obtained, the frequency of occurrence of peak values ​​in stress data during the monitoring period, the degree of deviation, and the cumulative change of stress during the monitoring period are analyzed to generate a stress peak deviation index and a stress accumulation index, respectively. The stress peak deviation index and the stress accumulation index are input into a pre-trained machine learning model to generate a strain coefficient, and the strain change trend occurring during the construction process is identified through the strain coefficient.

[0113] As an optional example, a pre-trained machine learning model refers to a model that has been trained and optimized with a large amount of historical stress and strain data (for example, more than 10,000 pieces of data) before application. The model uses known input data (such as stress peak deviation index and stress accumulation index) and corresponding output results (strain change trend) to adjust its internal parameters through repeated iterative learning to minimize prediction errors, so that the model can accurately understand and capture the complex relationship between stress and strain. In practical applications, the fully trained and verified model can quickly and accurately predict the strain change trend that may occur during the construction process, thereby providing real-time decision support for construction management.

[0114] It should be noted that during the construction process, if the frequency and degree of deviation of the peak value in the stress data during the monitoring period are greater, it means that the stress changes are more frequent and uncertain. This situation may mean that the structure is experiencing unstable load changes, such as sudden increase in external force, impact load caused by equipment operation, or unexpected stress fluctuations during construction. Frequent and highly deviated stress peaks show that the structure is in a dynamic strain state and there may be potential structural risks, which require close monitoring and timely response to ensure construction safety.

[0115] S202: Generate a stress peak deviation index and a stress accumulation index according to the frequency of occurrence of the peak value, the degree of deviation and the cumulative change.

[0116] In this step, two indexes are generated: the stress peak deviation index and the stress accumulation index. As a preferred example, the method for generating the stress peak deviation index is as follows: Figure 3 As shown, it includes S301, S302, S303 and S304, which are as follows:

[0117] S301 , during a monitoring period, traverse the stress data time series to detect local peak points of the stress data.

[0118] During the monitoring period, the local maximum point of the stress data, that is, the peak point, is detected by traversing the stress data time series. The window sliding method is used to determine the local peak value, that is, to find the maximum point during the monitoring period. The specific expression is: Where P i is the peak point detected at the i-th time point, s i represents the stress value of the stress data sequence at the i-th time point, N is the total number of stress data, i represents the index or position in the stress data sequence, specifically, i is an integer index used to traverse the entire stress data sequence to check each data point s i Is it a peak point?

[0119] S302: Calculate the time difference between two consecutive local peak points to obtain the distance between adjacent local peak points.

[0120] By calculating the time difference between two consecutive local peak points (calculating the time interval between adjacent local peak points to measure the frequency of peak occurrence), the spacing between adjacent local peak points is obtained. The calculation expression is: Where D j is the time interval between the jth and j+1th peak points, t Pj+1 Indicates the timestamp of the j+1th peak point, t Pj represents the timestamp of the jth peak point, M is the total number of peaks detected;

[0121] S303: Calculate the absolute difference between the time intervals between adjacent local peak points.

[0122] Based on S302, the absolute difference between the time intervals of the local adjacent peak points is calculated to quantify the volatility of the interval time. The calculation expression is: Where, ΔD j It is the absolute difference between the time intervals of the jth and j+1th peak points, indicating the amount of change in the time interval.

[0123] S304 , performing weighted summation on the absolute differences of the time intervals between all adjacent peak points to generate a stress peak deviation index.

[0124] Based on S301, S302 and S03, the stress peak deviation index is generated by weighted summing the absolute difference of the time intervals between all adjacent peak points and using a nonlinear weight function to emphasize the contribution of large deviation intervals to the stress peak deviation index. The generated expression is: Where, SPDI μ is the stress peak deviation index, w j is the weight of the absolute difference in time interval between the jth peak point. The exponential weighting method is used to highlight the impact of larger differences. Its value is determined by the following formula:

[0125] In the formula, e ΔDk It is an exponential operation on the absolute difference in the time interval between the j-th peak points, ensuring that larger differences contribute more to the index.

[0126] In the present invention, it can be known from the stress peak deviation index that during the monitoring period, the greater the performance value of the stress peak deviation index generated after analyzing the frequency and degree of deviation of the peak in the stress data, the greater the frequency and degree of deviation of the peak in the stress data during the monitoring period, which indicates that the stress changes frequently and the uncertainty is more significant. A higher stress peak deviation index reflects the instability of the stress state, which may be affected by frequent load changes or external interference; while a lower stress peak deviation index indicates that the stress peak occurs less frequently and changes less, indicating that the stress changes are relatively stable and the stress state of the structure during the monitoring period is relatively stable. Through this index, construction management personnel can quantify and evaluate the frequency and uncertainty of stress changes during the construction process, so as to make more effective monitoring and response strategies.

[0127] In S202, two indexes are generated: a stress peak deviation index and a stress accumulation index. As a preferred example, the method for generating the stress accumulation index may be the following steps D, E, F and G:

[0128] Step D: Record the collected stress data in time series as S(t), where t is a time variable and S(t) represents the stress value at time t.

[0129] During the monitoring period, the collected stress data is recorded as S(t) in time series, where t is the time variable and S(t) represents the stress value at time t.

[0130] These data are usually discrete and can be acquired by sensors at a high frequency to form a continuous time series.

[0131] Step E: Calculate the instantaneous rate of change of stress S′(t) is the instantaneous rate of change of stress at time t.

[0132] Calculate the instantaneous rate of change of stress, that is, the rate of change of stress at any time t. The rate of change of stress is obtained by calculating the derivative S′(t) of stress S(t) with respect to time t. The instantaneous rate of change can reflect the rate and trend of change of stress during the monitoring period. The calculation expression is: Where S′(t) is the instantaneous rate of change of stress at time t, which indicates the rate of change of stress with time.

[0133] Step F: Integrate the instantaneous rate of change of stress S'(t) during the monitoring period to obtain the cumulative amount of stress change Where A is the cumulative amount of stress change, indicating the total stress change during the monitoring period, |S′(t)| is the absolute value of the instantaneous change rate, t0 and t n Respectively represent the start time and end time of the monitoring period.

[0134] In this step, the cumulative amount of stress change is obtained by integrating the instantaneous rate of change of stress S'(t) during the monitoring period. The calculation expression is: Where A is the cumulative amount of stress change, indicating the total change amplitude of stress during the monitoring period, and |S′(t)| is the absolute value of the instantaneous change rate, ensuring that all changes are taken into account in the cumulative calculation, whether positive or negative, t0 and t n Respectively represent the start time and end time of the monitoring period.

[0135] Step G: Generate a stress accumulation index according to the following formula:

[0136]

[0137] Among them, SAI μ is the stress accumulation index, which is used to measure the overall change of stress during the monitoring period. n -t0 is the length of the monitoring period.

[0138] The stress accumulation index is a normalized measure of the cumulative amount of stress change and the length of the monitoring period (normalized by dividing the cumulative change by the length of the monitoring period to eliminate the effect of the monitoring period length on the result), and the resulting expression is:

[0139] In the formula, SAI μ is the stress accumulation index, which is a normalized measure used to measure the overall change of stress during the monitoring period. n -t0 is the length of the monitoring period, which is used to normalize the stress accumulation and ensure the standardization of the stress accumulation index.

[0140] After the above steps D to G, the stress accumulation index can be obtained. During the construction process, a large cumulative change in stress during the monitoring period usually indicates that the stress changes frequently and uncertainly. The cumulative change in stress reflects the total change in stress over a period of time. When this amount is large, it means that the stress has experienced multiple significant fluctuations or continuous increases or decreases during the period, which may be caused by construction operations, load changes or external environmental influences. This situation usually indicates that the structure is in an unstable state and requires the attention and additional monitoring of construction managers to ensure structural safety and the smooth progress of the construction process.

[0141] It can be seen from the stress accumulation index that the performance value of the stress accumulation index reflects the frequency and uncertainty of stress changes during the monitoring period. Specifically, if the performance value of the stress accumulation index is larger, it means that the cumulative change of stress during the monitoring period is larger, which indicates that the stress has experienced multiple significant fluctuations or continuous changes during the period, showing that the frequency and uncertainty of stress changes are more significant. This situation usually indicates that there are drastic changes in the load or external environment during the construction process, which may require the construction manager's high attention. On the contrary, if the performance value of the stress accumulation index is smaller, it means that the cumulative amount of stress changes is smaller, which means that the stress is relatively stable, the changes are not frequent, the uncertainty is low, and the construction process is relatively smooth.

[0142] S203, generating a strain coefficient according to the stress peak deviation index and the stress accumulation index;

[0143] As an optional example, generating a gauge factor according to the stress peak deviation index and the stress accumulation index includes:

[0144] Inputting the stress peak deviation index and the stress accumulation index into a pre-trained machine learning model to generate a gauge factor; or

[0145] The gauge factor Strain is generated according to the following formula Coff :

[0146]

[0147] Among them, SPDI μ is the stress peak deviation index, SAI μ is the stress accumulation index, They are stress peak deviation index SPDI μ and stress accumulation index SAI μ The preset scaling factor of Both are greater than 0.

[0148] In the embodiment of the present invention, the machine learning model is not specifically limited here, and can realize the stress peak deviation index SPDI μ and stress accumulation index SAI μ Perform comprehensive analysis to generate the strain coefficient Strain Coff Any machine learning model is available.

[0149] It can be seen from the strain coefficient that during the monitoring period, the greater the performance value of the stress peak deviation index generated after analyzing the frequency and deviation degree of the peak value in the stress data, the greater the performance value of the stress accumulation index generated after analyzing the cumulative change of the stress. In other words, the greater the performance value of the strain coefficient generated by using the trained machine learning model to predict the strain data during the monitoring period, the more frequent the stress changes and the more significant the uncertainty, and vice versa.

[0150] As an optional example, in this embodiment S3, dividing the construction process into a dynamic strain period and a stable strain period according to the strain coefficient includes:

[0151] If the strain factor is greater than the strain factor reference threshold, the construction process in the monitoring period is divided into a dynamic strain period;

[0152] If the strain factor is less than or equal to the strain factor reference threshold, the construction process during the monitoring period is divided into a stable strain period.

[0153] In this step, the construction process can be divided into dynamic strain period and stable strain period through machine learning model, that is, the strain coefficient generated by strain data prediction using the trained machine learning model during the monitoring period is compared and analyzed with the pre-set strain coefficient reference threshold, and the construction process is divided into dynamic strain period and stable strain period. The dynamic strain period refers to the period when the strain changes violently and is unstable, at which time the structure may be subjected to uneven load or be greatly affected by the external environment; the stable strain period refers to the period when the strain changes are small and stable, which usually means that the construction state is relatively stable and the environmental impact is small.

[0154] As an optional example, in this embodiment S4, setting the initial alarm threshold for each monitoring period includes:

[0155] For each monitoring period, an initial alarm threshold is set to be a threshold greater than a first initial threshold;

[0156] The use of the first initial threshold value can filter out slight strain fluctuations caused by normal construction activities.

[0157] An initial alarm threshold is set for each monitoring period (the initial alarm threshold is set relatively high, that is, a threshold greater than the first initial threshold, and a higher initial alarm threshold is used to avoid frequent false alarms). During the stable strain period, the initial alarm threshold is used to monitor the strain situation of the construction process in real time.

[0158] When monitoring construction, an initial alarm threshold needs to be set for each monitoring period. This initial alarm threshold is designed to reduce unnecessary false alarms. By setting a higher initial alarm threshold, the system can ignore some minor strain changes and only issue alarms for significant changes that exceed the threshold, thereby avoiding frequent alarms under stable conditions and interfering with normal construction operations.

[0159] The initial alarm threshold should be higher than the first initial threshold in order to filter out minor strain fluctuations caused by normal construction activities and avoid frequent false alarms due to the system being too sensitive. These fluctuations usually do not pose a threat to the overall safety of the building structure. Therefore, during the stable strain period, the changes in stress and strain are small and the fluctuations are light. Setting an alarm threshold higher than the first initial threshold helps ensure that the system only issues an alarm when there is a real risk. This setting needs to take into account the specific conditions of the construction environment and the results of historical data analysis to ensure that potential risks can be effectively monitored without interfering with normal construction progress.

[0160] As an optional example, in S5 of this embodiment, in the dynamic strain period, dynamically adjusting the actual alarm threshold according to the initial alarm threshold and the strain coefficient includes:

[0161] For the dynamic strain period, the strain coefficient difference ΔStrain is calculated. The strain coefficient difference represents the difference between the current strain coefficient and the strain coefficient reference threshold. The strain coefficient difference is used to evaluate the degree of the current strain change relative to the reference value. The strain coefficient difference ΔStrain is determined according to the following formula: ΔStrain = Strain - Strain ref , Strain is the strain coefficient under dynamic strain period, Strain ref is the gauge factor reference threshold, ΔStrain is the gauge factor difference;

[0162] Based on the strain coefficient difference, an adjustment factor of the alarm threshold is determined, and the adjustment factor is used to dynamically lower the alarm threshold to improve the sensitivity of the alarm. The adjustment factor is determined according to the following formula: α=1+exp(-β·ΔStrain), wherein α is the adjustment factor of the alarm threshold and α>1, exp represents an exponential function, and β is the adjustment coefficient;

[0163] Calculate the actual alarm threshold using the initial alarm threshold and the alarm threshold adjustment factor T init is the initial alarm threshold, T actual is the actual alarm threshold.

[0164] That is, in S5, during the dynamic strain period, the actual alarm threshold is dynamically adjusted based on the initial alarm threshold and the strain prediction result, and the actual alarm threshold is dynamically lowered to improve the sensitivity of the alarm;

[0165] During the dynamic response period, based on the initial alarm threshold and the strain prediction results, the actual alarm threshold is dynamically adjusted and the actual alarm threshold is dynamically lowered. The specific steps are as follows:

[0166] For the dynamic strain period, the gauge factor difference is calculated, which represents the difference between the current gauge factor and the gauge factor reference threshold. The gauge factor difference is used to evaluate the degree of current strain change relative to the reference value. The calculation expression is: ΔStrain = Strain-Strain ref , where Strain is the strain coefficient under dynamic strain period, Strain ref is the reference threshold of the strain coefficient, ΔStrain is the strain coefficient difference, which reflects the degree of deviation between the current strain state and the reference value;

[0167] Based on the strain coefficient difference, the adjustment factor of the alarm threshold is determined. The adjustment factor is used to dynamically lower the alarm threshold and improve the sensitivity of the alarm (the calculation of the adjustment factor can be based on a nonlinear function (such as an exponential function) to increase the sensitivity while avoiding excessive threshold adjustment). The calculation expression of the adjustment factor is: α=1+exp(-β·ΔStrain), where α is the adjustment factor of the alarm threshold, which is used to dynamically adjust the alarm threshold, α>1 is used to lower the threshold, exp represents the exponential function, which is used for the nonlinear adjustment factor, and β is the adjustment coefficient, which controls the rate of change of the alarm threshold adjustment factor and is adjusted as needed;

[0168] The actual alarm threshold is calculated using the initial alarm threshold and the alarm threshold adjustment factor. The actual alarm threshold is used to monitor the strain in real time to ensure that abnormal conditions can be captured more sensitively during periods of frequent strain changes. The calculation expression for the actual alarm threshold is: Where, T init is the initial alarm threshold, which is set to a higher value to avoid frequent false alarms during the stable period. actual is the actual alarm threshold, which is adjusted downward based on the adjustment factor to improve monitoring sensitivity;

[0169] During the dynamic response period, the actual alarm threshold is dynamically adjusted, and the calculation expression for the dynamic adjustment is: Among them, Strain>Strain ref The denominator in the expression is the adjustment factor α of the alarm threshold.

[0170] After the above step S5, the actual alarm threshold after dynamic adjustment is calculated in real time. In S6, the stress is monitored in real time according to the calculated actual alarm threshold.

[0171] It should be noted that the calculation formulas in this embodiment are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0172] The stress monitoring method of the present invention, through the Internet of Things information collection system based on the BIM visualization platform, combines the feature extraction of stress data and the application of machine learning models, dynamically adjusts the alarm threshold, and effectively solves the problems caused by the fixed alarm threshold. Specifically, the method of the present invention can identify the trend of strain changes according to the real-time monitored stress and strain data during the construction process (for example, during the construction process of infrastructure planning of telecommunications operators), and divide the construction process into a dynamic strain period and a stable strain period. In the stable strain period, the system adopts a higher initial alarm threshold to reduce unnecessary false alarms and improve construction efficiency; while in the dynamic strain period, the system dynamically lowers the actual alarm threshold according to the strain prediction results, improves the sensitivity of the alarm, and ensures that potential structural risks are captured in time. The intelligent monitoring and dynamic adjustment mechanism of the present invention can not only reduce false alarms and missed alarms, but also enhance the real-time monitoring capability of structural safety, significantly improving the safety and management efficiency during the construction process.

[0173] Based on the same inventive concept, another specific embodiment of the present invention discloses a stress monitoring device, such as Figure 4 As shown, incl.

[0174] The data acquisition and preprocessing module 401 is configured to collect stress data, preprocess the stress data, and obtain preprocessed stress data;

[0175] The feature extraction and strain prediction module 402 is configured to extract features from the preprocessed stress data and determine the strain coefficient according to the extracted features;

[0176] The strain period division module 403 is configured to divide the construction process into a dynamic strain period and a stable strain period according to the strain coefficient;

[0177] An initial alarm threshold setting module 404 is configured to set an initial alarm threshold for each monitoring period;

[0178] A dynamic alarm threshold adjustment module 405 is configured to dynamically adjust the actual alarm threshold according to the initial alarm threshold and the strain factor during the dynamic strain period;

[0179] The real-time monitoring module 406 is configured to perform real-time monitoring of the strain situation according to the calculated actual alarm threshold.

[0180] As an optional example, the data acquisition and preprocessing module 401 is further configured to collect stress data according to the following steps:

[0181] Transmit stress data collected by field sensors to a central server or cloud storage in real time;

[0182] Integrate the collected stress data with the Building Information Model (BIM) platform;

[0183] The BIM platform is used to monitor and analyze the integrated stress data in real time.

[0184] Preferably, preprocessing the stress data includes:

[0185] Remove noise, fill missing values ​​or standardize stress data.

[0186] As an optional example, the feature extraction and strain prediction module 402 is further configured to determine the gauge factor according to the following steps:

[0187] The extracted features include the frequency, degree of deviation and cumulative change of peak values ​​in the stress data during the monitoring period;

[0188] Generate a stress peak deviation index and a stress accumulation index according to the frequency of occurrence of the peak, the degree of deviation and the cumulative change;

[0189] A gauge factor is generated based on the stress peak deviation index and the stress accumulation index.

[0190] As an optional example, the feature extraction and strain prediction module 402 is further configured to generate a stress peak deviation index according to the following steps:

[0191] During the monitoring period, the stress data time series is traversed to detect the local peak point of the stress data;

[0192] Calculate the time difference between two consecutive local peak points to obtain the distance between adjacent local peak points;

[0193] Calculate the absolute difference between the time intervals of adjacent local peak points;

[0194] The absolute differences in the time intervals between all adjacent local peak points are weighted summed to generate the stress peak deviation index.

[0195] As an optional example, the feature extraction and strain prediction module 402 is further configured to generate a stress accumulation index according to the following steps:

[0196] The collected stress data is recorded as S(t) in time series, where t is a time variable and S(t) represents the stress value at time t;

[0197] Calculate the instantaneous rate of change of stress S′(t) is the instantaneous rate of change of stress at time t;

[0198] The instantaneous rate of change of stress S'(t) is integrated during the monitoring period to obtain the cumulative amount of stress change Where A is the cumulative amount of stress change, indicating the total stress change during the monitoring period, |S′(t)| is the absolute value of the instantaneous change rate, t0 and t n Respectively represent the start time and end time of the monitoring period;

[0199] The stress accumulation index is generated according to the following formula:

[0200]

[0201] Among them, SAI μ is the stress accumulation index, which is used to measure the overall change of stress during the monitoring period. n -t0 is the length of the monitoring period.

[0202] As an optional example, the feature extraction and strain prediction module 402 is further configured to generate a gauge factor according to the following steps:

[0203] Inputting the stress peak deviation index and the stress accumulation index into a pre-trained machine learning model to generate a gauge factor; or

[0204] The gauge factor Strain is generated according to the following formula Coff :

[0205]

[0206] Among them, SPDI μ is the stress peak deviation index, SAI μ is the stress accumulation index, They are stress peak deviation index SPDI μ and stress accumulation index SAI μ The preset scaling factor of Both are greater than 0.

[0207] As an optional example, the strain period division module 403 is further configured to:

[0208] If the strain factor is greater than the strain factor reference threshold, the construction process in the monitoring period is divided into a dynamic strain period;

[0209] If the strain factor is less than or equal to the strain factor reference threshold, the construction process during the monitoring period is divided into a stable strain period.

[0210] As an optional example, the initial alarm threshold setting module 404 is configured to set an initial alarm threshold for each monitoring period, including:

[0211] The initial alarm threshold for each monitoring period is set to a threshold greater than the first initial threshold;

[0212] The use of the first initial threshold value can filter out slight strain fluctuations caused by normal construction activities.

[0213] The dynamic alarm threshold adjustment module 405 is further configured to dynamically adjust the actual alarm threshold according to the following steps:

[0214] For the dynamic strain period, the strain coefficient difference ΔStrain is calculated. The strain coefficient difference represents the difference between the current strain coefficient and the strain coefficient reference threshold. The strain coefficient difference is used to evaluate the degree of the current strain change relative to the reference value. The strain coefficient difference ΔStrain is determined according to the following formula: ΔStrain = Strain - Strain ref , Strain is the strain coefficient under dynamic strain period, Strain ref is the gauge factor reference threshold, ΔStrain is the gauge factor difference;

[0215] Based on the strain coefficient difference, an adjustment factor of the alarm threshold is determined, and the adjustment factor is used to dynamically lower the alarm threshold to improve the sensitivity of the alarm. The adjustment factor is determined according to the following formula: α=1+exp(-β·ΔStrain), wherein α is the adjustment factor of the alarm threshold and α>1, exp represents an exponential function, and β is the adjustment coefficient;

[0216] Calculate the actual alarm threshold using the initial alarm threshold and the alarm threshold adjustment factor T init is the initial alarm threshold, T actual is the actual alarm threshold.

[0217] It should be noted that the stress monitoring device provided in this embodiment belongs to the same inventive concept as the above-mentioned stress monitoring method, can solve the same technical problems, and can achieve the same technical effects, and the similarities will not be repeated here.

[0218] In a third aspect, the present invention provides a stress monitoring device, such as Figure 5 As shown, it includes: a memory 502 and one or more processors 501.

[0219] One or more application programs are stored in the memory 502, and the one or more application programs are suitable for being executed by the one or more processors 501 to implement the following steps:

[0220] S1, collecting stress data, and preprocessing the stress data to obtain preprocessed stress data;

[0221] S2, extracting features from the preprocessed stress data, and determining a strain coefficient according to the extracted features;

[0222] S3, dividing the construction process into a dynamic strain period and a stable strain period according to the strain coefficient;

[0223] S4, setting the initial alarm threshold for each monitoring period;

[0224] S5, dynamically adjusting the actual alarm threshold according to the initial alarm threshold and the strain factor during the dynamic strain period;

[0225] S6, performing real-time monitoring of stress according to the calculated actual alarm threshold.

[0226] like Figure 5 As shown, the stress monitoring device includes: a processor 501 and a memory 502. The processor 501 and the memory 502 are connected, such as through a bus.

[0227] The structure of the stress monitoring device does not constitute a limitation on the embodiments of the present invention.

[0228] Processor 501 may be a CPU, a general purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 501 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0229] The bus may include a path to transmit information between the above components. The bus may be a PCI bus or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0230] The memory 502 may be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an EEPROM, a CD-ROM or other optical disk storage, an optical disk storage (including a compressed optical disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0231] As an optional example, one or more application programs are stored in the memory 502 , and the one or more application programs are suitable for being executed by the one or more processors 501 to implement any of the above-mentioned stress monitoring methods.

[0232] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program can be loaded and executed by a processor to perform the stress monitoring method described in the first aspect.

[0233] The applicant of the present invention has made a detailed explanation and description of the implementation examples of the present invention in conjunction with the drawings in the specification. However, those skilled in the art should understand that the above implementation examples are only preferred implementation schemes of the present invention, and the detailed description is only to help readers better understand the spirit of the present invention, but not to limit the scope of protection of the present invention. On the contrary, any improvements or modifications based on the inventive spirit of the present invention should fall within the scope of protection of the present invention.

[0234] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the above embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or replacements that can be easily thought of by those skilled in the art within the technical scope disclosed in the present invention should be covered within the protection scope of the present invention.

Claims

1. A stress monitoring method, characterized in that: include: S1, collecting stress data, and preprocessing the stress data to obtain preprocessed stress data; S2, extracting features from the preprocessed stress data, and determining a strain coefficient according to the extracted features; S3, dividing the construction process into a dynamic strain period and a stable strain period according to the strain coefficient; S4, setting the initial alarm threshold for each monitoring period; S5, dynamically adjusting the actual alarm threshold according to the initial alarm threshold and the strain factor during the dynamic strain period; S6, performing real-time monitoring of stress according to the calculated actual alarm threshold; The collecting of stress data comprises: Transmit stress data collected by field sensors to a central server or cloud storage in real time; Integrate the collected stress data with the Building Information Model (BIM) platform; Using the BIM platform to monitor and analyze the integrated stress data in real time; The preprocessing of the stress data comprises: The stress data is subjected to noise removal, missing value filling or standardization processing.

2. A stress monitoring method according to claim 1, characterized in that: The extracting features of the preprocessed stress data and determining the strain coefficient according to the extracted features comprises: The extracted features include the frequency, degree of deviation and cumulative change of peak values ​​in the stress data during the monitoring period; Generate a stress peak deviation index and a stress accumulation index according to the frequency of occurrence of the peak, the degree of deviation and the cumulative change; A gauge factor is generated based on the stress peak deviation index and the stress accumulation index.

3. A stress monitoring method according to claim 2, characterized in that: Generating the stress peak deviation index according to the frequency, deviation degree and cumulative change of the peak value comprises: During the monitoring period, the stress data time series is traversed to detect the local peak point of the stress data; Calculate the time difference between two consecutive local peak points to obtain the distance between adjacent peak points; Calculate the absolute difference between the time intervals of adjacent local peak points; The absolute differences in the time intervals between all adjacent local peak points are weighted summed to generate the stress peak deviation index.

4. A stress monitoring method according to claim 2, characterized in that: Generating the stress accumulation index according to the frequency of occurrence of the peak value, the degree of deviation and the cumulative change comprises: The collected stress data is recorded as S(t) in time series, where t is a time variable and S(t) represents the stress value at time t; Calculate the instantaneous rate of change of stress S′(t) is the instantaneous rate of change of stress at time t; The instantaneous rate of change of stress S'(t) is integrated during the monitoring period to obtain the cumulative amount of stress change Where A is the cumulative amount of stress change, indicating the total stress change during the monitoring period, |S′(t)| is the absolute value of the instantaneous change rate, t0 and t n Respectively represent the start time and end time of the monitoring period; The stress accumulation index is generated according to the following formula: Among them, SAI μ is the stress accumulation index, which is used to measure the overall change of stress during the monitoring period. n -t0 is the length of the monitoring period.

5. A stress monitoring method according to claim 2, characterized in that: Generating a gauge factor according to the stress peak deviation index and the stress accumulation index comprises: Inputting the stress peak deviation index and the stress accumulation index into a pre-trained machine learning model to generate a gauge factor; or The gauge factor Strain is generated according to the following formula Coff : Among them, SPDI μ is the stress peak deviation index, SAI μ is the stress accumulation index, They are stress peak deviation index SPDI μ and stress accumulation index SAI μ The preset scaling factor of Both are greater than 0.

6. A stress monitoring method according to claim 1, characterized in that: The construction process is divided into a dynamic strain period and a stable strain period according to the strain coefficient, including: If the strain factor is greater than the strain factor reference threshold, the construction process in the monitoring period is divided into a dynamic strain period; If the strain factor is less than or equal to the strain factor reference threshold, the construction process in the monitoring period is divided into a stable strain period; The setting of the initial alarm threshold for each monitoring period includes: The initial alarm threshold for each monitoring period is set to a threshold greater than the first initial threshold; The use of the first initial threshold value can filter out strain fluctuations caused by normal construction activities.

7. A stress monitoring method according to claim 1, characterized in that: The dynamically adjusting the actual alarm threshold according to the initial alarm threshold and the strain factor during the dynamic strain period includes: For the dynamic strain period, the gauge coefficient difference ΔStrain is calculated. The gauge coefficient difference represents the difference between the current gauge coefficient and the gauge coefficient reference threshold. The gauge coefficient difference is used to evaluate the degree of the current strain change relative to the reference value. The gauge coefficient difference ΔStrain is determined according to the following formula: ΔStrain = Strain - Strain ref , Strain is the strain coefficient under dynamic strain period, Strain ref is the gauge factor reference threshold, ΔStrain is the gauge factor difference; Based on the strain coefficient difference, an adjustment factor of the alarm threshold is determined, and the adjustment factor is used to dynamically lower the alarm threshold to improve the sensitivity of the alarm. The adjustment factor is determined according to the following formula: α=1+exp(-β·ΔStrain), wherein α is the adjustment factor of the alarm threshold and α>1, exp represents an exponential function, and β is the adjustment coefficient; Calculate the actual alarm threshold using the initial alarm threshold and the alarm threshold adjustment factor T init is the initial alarm threshold, T actual is the actual alarm threshold.

8. A stress monitoring device, characterized in that: For implementing the stress monitoring method according to any one of claims 1 to 7, the device comprises: A data acquisition and preprocessing module is configured to collect stress data, preprocess the stress data, and obtain preprocessed stress data; A feature extraction and strain prediction module is configured to extract features from the preprocessed stress data and determine a strain coefficient based on the extracted features; A strain period division module is configured to divide the construction process into a dynamic strain period and a stable strain period according to the strain coefficient; An initial alarm threshold setting module, configured to set an initial alarm threshold for each monitoring period; A dynamic alarm threshold adjustment module, configured to dynamically adjust the actual alarm threshold according to the initial alarm threshold and the strain factor during the dynamic strain period; The real-time monitoring module is configured to perform real-time monitoring of the strain situation according to the calculated actual alarm threshold.

9. A stress monitoring device, characterized in that: including a memory, a processor and a user interface; The memory is used to store computer programs; The user interface is used to interact with the user; The processor is used to read the computer program in the memory, and when the processor executes the computer program, the stress monitoring method according to any one of claims 1 to 7 is implemented.

10. A processor-readable storage medium, characterized in that: The processor-readable storage medium stores a computer program, and when the processor executes the computer program, the stress monitoring method according to any one of claims 1 to 7 is implemented.

Images