Multi-terminal cooperative deep foundation pit intelligent disaster prevention management and control system

Abstract

This invention discloses a multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits, relating to the field of data monitoring technology. It addresses the problem that the verification of historical monitoring data often relies on manual experience and lacks standardized methods for identifying characteristic time periods and establishing reference standards. This invention identifies undetermined characteristic time periods by calculating the ratio of changes in adjacent time periods and their variance values, allowing the extraction of reference standards to focus on key time periods with strong data clustering and stable correlations. This standard calibration method based on the inherent linkage characteristics of the data avoids the subjective bias of traditional experience-based calibration, ensuring that the criteria for determining "normal / deviation" in subsequent monitoring are more aligned with the actual operational patterns of the project, thus improving the accuracy of risk identification from the source.

Description

Technical Field

[0001] This invention relates to the field of data monitoring technology, specifically to a multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits. Background Technology

[0002] With the acceleration of urbanization, the construction scale of major projects such as high-rise buildings, underground rail transit, and integrated utility tunnels continues to expand. As a key preliminary stage of such projects, deep foundation pit engineering directly affects the overall quality of the project and the safety and stability of surrounding buildings and underground pipelines through its construction safety and disaster prevention management. The construction environment of deep foundation pits is complex and is affected by multiple factors such as geological conditions, hydrological factors, changes in surrounding loads, and construction disturbances. It is prone to disaster risks such as foundation pit deformation, instability of retaining structures, piping, and water inrush. Once an accident occurs, it will not only cause huge economic losses but may also cause serious casualties. Therefore, accurate, real-time, and efficient disaster prevention management of deep foundation pits is of great practical significance.

[0003] Currently, disaster prevention and control in deep foundation pits largely relies on traditional monitoring methods and manual analysis. At the monitoring level, a distributed sensor deployment approach is typically used to independently monitor single parameters such as foundation pit settlement, displacement, groundwater level, and earth pressure. Data from different monitoring points lacks effective correlation and fails to reflect the overall stress and deformation characteristics of the foundation pit system. At the data processing level, post-event data aggregation and analysis are commonly used. Verification of historical monitoring data relies heavily on manual experience and judgment, lacking standardized methods for identifying characteristic time periods and establishing reference standards. This results in low data processing efficiency, high subjectivity, and difficulty in capturing potential early warning signs of risks.

[0004] Disaster prevention and control of deep foundation pits mainly consists of monitoring and data processing. Current technologies, at the monitoring level, typically employ a distributed sensor deployment to independently monitor single parameters such as foundation pit settlement, displacement, groundwater level, and soil pressure. However, the data from each monitoring point lacks effective coordination and correlation, making it difficult to reflect the overall stress and deformation characteristics of the foundation pit system. At the data processing level, for example, Chinese patent application CN120296077A discloses a method and system for controlling the safety monitoring and early warning process of deep foundation pits. However, this method, which uses a single threshold comparison for early warning, cannot accurately assess the degree of deviation and development trend, resulting in low early warning accuracy, frequent false alarms and missed alarms. Furthermore, the coordination and linkage between multiple devices is poor, and there is a lack of efficient data interaction mechanisms between the data monitoring end, analysis end, and early warning end, making it difficult to form a closed-loop management process of "monitoring-analysis-early warning-control." Finally, relying on manual experience for verification is highly subjective and lacks unified judgment standards.

[0005] Therefore, there is an urgent need for an intelligent disaster prevention and control system for deep foundation pits that can achieve multi-terminal collaboration, in-depth data analysis, and accurate trend prediction. Summary of the Invention

[0006] To address the shortcomings of existing technologies that rely on manual experience to verify historical monitoring data, this invention provides a multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits. By establishing standardized methods for verifying historical data and confirming reference standards, it achieves real-time collaborative monitoring of foundation pit parameters and accurate identification of deviation characteristics. Based on quantitative deviation trend analysis, it provides graded early warnings, thereby improving the intelligence level and reliability of disaster prevention and control for deep foundation pits and ensuring the safety of engineering construction.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits, comprising: The data feature analysis end identifies multiple sets of deep foundation pit sensors that collaborate across multiple terminals, receives historical data generated by each set of sensors within a historical period, performs comprehensive verification, and locks in the undetermined feature time period. The parameter ratio confirmation end integrates and processes the verification features associated with the locked undetermined characteristic time period to confirm the reference standard associated with several deep foundation pit sensors. The data monitoring terminal uses multiple sets of deep foundation pit sensors to monitor various parameters of the deep foundation pit in real time. The deviation feature analysis end, based on the real-time monitored parameters, confirms the change characteristics of each parameter within the same time period, and compares and verifies the change characteristics with the reference standard to confirm whether there are any deviation parameters. On the trend feature analysis end, a set of monitoring cycles is determined to monitor the subsequent parameter changes of the deviation parameters, identify the deviation trend of the subsequent parameter changes relative to the reference standard, and issue early warnings based on the degree of deviation of the deviation trend.

[0008] To better realize this invention, the data feature analysis terminal has the following main functions: Based on the current moment, a set of source tracing cycles is determined. The source tracing cycle is a preset cycle. The parameter data monitored by the deep foundation pit sensor is sorted according to the time characteristics, and the parameter change curve associated with the source tracing cycle is generated synchronously. The horizontal axis of the curve is the time line, and the vertical axis is the parameter data. Confirm the trend of change associated with each set of parameter change curves at adjacent times, and then confirm the ratio of the trend of change in adjacent time periods. Confirm the ratio of the trend of change associated with adjacent time periods, starting from the initial point associated with the parameter change curve and ending at the end point, and record several sets of trend ratios associated with the corresponding parameter change curve. Within different parameter change curves, identify the different trend ratios associated with the same adjacent time periods, and perform variance processing on the identified multiple trend ratios to identify the variance values ​​associated with the corresponding adjacent time periods; if the variance value > Y1, no processing is required; if the variance value ≤ Y1, the corresponding adjacent time period is recorded as a pending time period, where Y1 is a preset value. Several undetermined time periods within the traceability period are identified, and these identified undetermined time periods are marked as undetermined characteristic time periods.

[0009] To better realize this invention, the parameter ratio confirmation terminal has the following main functions: Based on the locked undetermined characteristic time period, the ratio of the change trends associated with different deep foundation pit sensors in the same undetermined characteristic time period is arranged by ratio. A group of deep foundation pit sensors is randomly selected as the main sensor, and other deep foundation pit sensors are used as secondary sensors to complete the process of arranging the ratio of change trends and confirm the change trend ratio column. Keeping the sorting method of the deep foundation pit sensors unchanged, the change trend ratio columns associated with different undetermined characteristic time periods are confirmed in turn; The trend ratio associated with the main sensor is calibrated to 1. According to the calibration process, the trend ratios associated with other secondary sensors in different trend ratio columns are calibrated synchronously. After the calibration is completed, multiple trend ratios associated with the same group of secondary sensors are extracted. The minimum and maximum values ​​are selected as the trend ratio intervals associated with the corresponding secondary sensors. Subsequently, the trend ratio intervals of each group of secondary sensors are confirmed and recorded in turn. The arrangement of the main and secondary sensors and the trend ratio range of different secondary sensors are recorded as a reference standard for the association between several deep foundation pit sensors.

[0010] To better implement this invention, the main functions of the off-feature analysis end are as follows: Based on the various parameters monitored in real time, the parameter ratio columns associated with each parameter during the monitoring period are confirmed using the same confirmation process as the change trend ratio column. The ratio associated with the main sensor in the parameter ratio column is calibrated to 1. Then, it is identified whether the ratio associated with other secondary sensors is within the recorded trend ratio range. If not, the corresponding parameter is recorded as a deviation parameter, and a deviation signal is generated. The deviation signal is transmitted to the trend feature analysis terminal and simultaneously transmitted to the external display terminal. If the ratio associated with other secondary sensors is within the recorded trend ratio range, no processing is required, and continuous monitoring is sufficient.

[0011] To better realize this invention, the trend feature analysis terminal has the following main functions: Based on the calibrated deviation parameters, a set of monitoring periods is determined, which is a preset period. The parameter ratios for different time periods within the monitoring period are then identified. The ratios associated with the deviation parameters are extracted, and the deviations of these ratios from the trend ratio range are confirmed. The ratio associated at different times is denoted as BZ. k Where k represents different times, if BZ k If the trend ratio exceeds the range, then the maximum value of the trend ratio range (Max) is selected, and (BZ) is used. k -Max)÷Max=XB k Confirm the excess ratio XB associated with the corresponding time point. k If BZ k If the value is below the trend ratio interval, then select the minimum value (Min) of the trend ratio interval and use (Min-BZ) as the criterion. k ) ÷ Min = XB k Confirm the excess ratio XB associated with the corresponding time point. k ; Assess the excess ratio XB at the corresponding time point. k Does it meet the following conditions: XB k If the deviation is ≥20%, an early warning will be issued and an abnormal deviation signal will be generated and displayed simultaneously. If the deviation is not met, monitoring will continue. Beneficial effects

[0012] This invention provides a multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits, which has the following advantages compared with the prior art.

[0013] (1) This invention does not rely on fixed thresholds, human experience, or external models, but autonomously constructs dynamic reference standards through the inherent linkage characteristics of multi-sensor data.

[0014] (2) This invention locks out characteristic time periods by using trend ratio and variance analysis, and constructs a calibration system of “primary-secondary sensor trend ratio interval” to achieve collaborative analysis of multi-source data.

[0015] (3) This invention provides early warning by combining relative proportion deviation judgment with deviation degree quantitative analysis, and has the ability to identify early and predict trends.

[0016] (4) This invention improves the accuracy of identification from the source, reduces false alarms, is compatible with reasonable fluctuations, and realizes early warning, and is applicable to complex and ever-changing deep foundation pit engineering environments.

[0017] (5) This invention locks the period of characteristics to be determined by calculating the ratio of changes in adjacent time periods and the variance value, so that the extraction of reference standards focuses on key time periods with strong data clustering and stable correlation. This standard calibration method based on the inherent linkage characteristics of data avoids the subjective bias of traditional empirical calibration, and ensures that the judgment basis of "normal / deviation" in subsequent monitoring is more in line with the actual operation law of the project, thereby improving the accuracy of risk identification from the source.

[0018] (6) This invention constructs a relative ratio reference system among multiple sensors through the calibration logic of "primary sensor calibration to 1, secondary sensor locking trend ratio interval". This design not only retains the monitoring characteristics of different sensors, but also replaces a single numerical standard with interval thresholds, effectively accommodating the rationality of slight fluctuations in the construction environment and avoiding false alarms caused by "one-size-fits-all" early warning. At the same time, the fixed master-slave arrangement ensures the comparability of monitoring data in multiple time periods, making the cross-cycle parameter change trend analysis more coherent. Attached Figure Description

[0019] Figure 1 This is a schematic diagram illustrating the principle framework of a multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits as described in this invention.

[0020] Figure 2 This is a schematic diagram of the data flow of a multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits as described in this invention.

[0021] Figure 3 A schematic diagram of the main process for implementing a multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits.

[0022] Figure 4 This is a schematic diagram illustrating the specific steps of the intelligent disaster prevention and control method for deep foundation pits in Example 2.

[0023] Figure 5 This is a schematic diagram of the system architecture in Example 7. Detailed Implementation

[0024] 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, and 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. Example 1

[0025] like Figure 1As shown, this embodiment provides a multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits, including a data feature analysis terminal, a parameter ratio confirmation terminal, a deviation feature analysis terminal, a data monitoring terminal, and a trend feature analysis terminal; the data feature analysis terminal, the parameter ratio confirmation terminal, the deviation feature analysis terminal, and the trend feature analysis terminal are electrically connected sequentially from the output node to the input node, and the data monitoring terminal is electrically connected to the input nodes of the deviation feature analysis terminal and the trend feature analysis terminal, respectively.

[0026] like Figure 2 As shown, sensor groups A, B, C, and D illustrate a multi-terminal collaborative deep foundation pit sensor array. The data monitoring terminal continuously acquires measured data from multiple deep foundation pit sensors. Data collected over a period prior to the current moment is used as historical data, input to the data feature analysis terminal to determine the period of characteristics to be determined, and then confirmed by the parameter ratio terminal to establish a reference standard. The measured data collected at the current moment is input from the data monitoring terminal to the trend feature analysis terminal to analyze trends, and also input to the deviation feature analysis terminal to analyze the degree of deviation.

[0027] In this embodiment, the data feature analysis end analyzes historical data, calculates the trend ratio and variance value, and automatically identifies the undetermined characteristic periods where the data from multiple sensors change in a consistent and stable manner. This is equivalent to confirming the "golden period" that represents the normal collaborative operation of the system. The parameter ratio confirmation end then sets the primary and secondary sensors within these "golden periods" and calculates the trend ratio range of the secondary sensor relative to the primary sensor. Therefore, this embodiment establishes a dynamic and correlated reference standard through the combination of the data feature analysis end and the parameter ratio confirmation end. This standard is no longer an isolated threshold such as "displacement < 50mm," but rather a collaborative constraint such as "when the displacement at point A changes in this way, how should the earth pressure at point B and the water level at point C change, and how should the change ratio be within a certain range?" This monitoring reference standard accurately reflects the actual laws governing the interaction of various physical quantities in deep foundation pit engineering.

[0028] In this embodiment, the data monitoring terminal provides continuous measured data collected by multiple sensors, which forms the foundation of the system.

[0029] In this embodiment, the deviation feature analysis end converts real-time monitoring data into a parameter ratio series similar to the reference standard and compares it with the previously established trend ratio range. If the change trend of a parameter deviates from the historical normal correlation, i.e., exceeds the trend ratio range, it will be identified as a "deviation parameter" even if its absolute value has not yet reached the danger threshold. This enables the capture of precursors to system instability, significantly advancing the risk identification timeline. For example, before piping occurs, the water level pressure may not have changed drastically, but its correlation with the surrounding earth pressure may have already shown a slight deviation.

[0030] In this embodiment, the trend feature analysis end continuously tracks the identified deviation parameters and quantitatively calculates the degree of deviation; specifically, it quantitatively calculates the excess ratio XB within a monitoring period. k Then, through quantitative analysis of the deviation trend, it is determined whether the anomaly is worsening or mitigating. Only when the deviation reaches a preset threshold, such as ≥20%, is a final warning issued. This upgrades the process from alarm to decision-making, making the warning information more instructive and helping managers assess the urgency of the risk and decide on the appropriate level of response.

[0031] Deep foundation pit construction, compared to other conventional earthwork construction, requires special attention to the risks of pit deformation and instability of the retaining structure, piping, and water inrush. These disasters are often preceded by warning signs of imbalances in related parameters such as settlement, earth pressure, groundwater level, and water pressure. To address the risks of pit deformation and retaining structure instability, this embodiment provides a multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits. By monitoring the synergistic relationship between parameters such as displacement, settlement, and earth pressure, it can identify signs of abnormal stress in the support system before the structure undergoes visible severe deformation or instability. For example, if the displacement of a certain support point changes rapidly while the stress response of other related points fails to keep pace, the system will issue an early warning. Regarding risks such as piping and water inrush, this embodiment's multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits monitors the trend ratio range between water pressure and earth pressure. It can issue a deviation signal even before a surge in water level occurs, but when the linkage between water pressure and the soil structure becomes abnormal, thus buying valuable time for grouting, reinforcement, and other remedial measures.

[0032] Therefore, the multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits provided in this embodiment is an objective and intelligent monitoring and early warning system based on the inherent linkage law of multiple parameters. It achieves early warning by capturing the initial stage of the failure of the collaborative relationship, and achieves in-process judgment by judging the deviation trend. It realizes real-time perception of the overall stability of the deep foundation pit and early risk insight, thus providing the possibility for proactive prevention and control of disaster risks such as foundation pit deformation, instability of retaining structure, piping, and water inrush. Example 2

[0033] This embodiment is a detailed description based on Embodiment 1.

[0034] In this embodiment, the data feature analysis unit identifies multiple sets of deep foundation pit sensors operating in a multi-terminal collaborative manner. It receives historical data generated by each set of sensors within a historical period, then performs comprehensive verification on the received historical data to pinpoint the specific characteristic time period. These multiple sets of deep foundation pit sensors operating in a multi-terminal collaborative manner are typically calibrated in advance by relevant personnel based on experience, and are distinguished from other non-monitored objects by using preset markers.

[0035] Specifically, there is a correlation between several deep foundation pit sensors. This correlation is marked in advance by the operators. During data monitoring, the relevant data monitored by the corresponding sensors are also linked. Therefore, based on this linkage, the data inside the deep foundation pit is monitored and evaluated in real time to confirm whether there is a deviation of a certain parameter. Based on the specific deviation characteristics and degree of deviation confirmed, relevant early warning and prevention measures are taken.

[0036] In this embodiment, the parameter ratio confirmation end integrates and processes the verification features associated with the locked undetermined feature time period to confirm the reference standard associated with several deep foundation pit sensors.

[0037] In this embodiment, the data monitoring end uses multiple sets of deep foundation pit sensors to monitor various parameters of the deep foundation pit in real time, and transmits the monitored parameters to the deviation feature analysis end or the trend feature analysis end respectively.

[0038] In this embodiment, the deviation feature analysis end confirms the change characteristics of each parameter in the same time period based on the real-time monitored parameters, and compares and verifies the change characteristics with the reference standard to confirm whether there are any deviation parameters, thus completing the deviation feature calibration process.

[0039] In this embodiment, the trend feature analysis end determines a set of monitoring cycles to monitor the subsequent parameter change process of the deviation parameter, identifies the deviation trend relative to the reference standard in the subsequent parameter change process, and performs early warning processing based on the degree of deviation of the deviation trend.

[0040] Specifically, the main workflow of the multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits described in this embodiment includes four core steps: analyzing data characteristics, establishing reference standards, real-time monitoring and identification of deviations, and trend analysis and early warning. The working principle is as follows: Figure 3 As shown.

[0041] The core idea behind the aforementioned multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits is a method based on the inherent linkage characteristics of data. First, by analyzing historical monitoring data, the system calculates the trend ratio of multiple sensor parameters in adjacent time periods and uses variance analysis to identify characteristic time periods with stable data synergy, replacing manual experience-based calibration with a data-driven approach. Next, within the characteristic time period, based on selecting the primary sensor and calibrating its trend ratio, the trend ratio intervals of the remaining secondary sensors are calculated, establishing a multi-parameter collaborative reference standard. In real-time monitoring, the ratios associated with the secondary sensors in the real-time data are compared with the set trend ratio intervals to identify deviating parameters and continuously track their changing trends, quantitatively calculating the degree of deviation to achieve tiered early warning. This scheme, by focusing on abnormal changes in the collaborative relationships between parameters, transforms the alarm process from isolated threshold alarms to the identification of systemic instability precursors, thereby improving the accuracy and timeliness of deep foundation pit disaster early warning.

[0042] like Figure 4 As shown, the intelligent disaster prevention and control method for deep foundation pits specifically includes steps S1, S2, S3, and S4: Step S1: Through the data feature analysis terminal, identify multiple sets of deep foundation pit sensors with multi-terminal collaboration, receive the historical data generated by each set of sensors in the historical period, and then perform comprehensive verification to lock the undetermined feature time period. Step S2: Through the parameter ratio confirmation terminal, based on the locked undetermined characteristic time period, the verification features associated with the undetermined characteristic time period are integrated and processed to confirm the reference standard associated with several deep foundation pit sensors. Step S3: Obtain measured data from multiple sets of deep foundation pit sensors on each monitored object in the deep foundation pit through the data monitoring terminal; confirm the change characteristics of each parameter in the same time period based on the measured data through the deviation characteristic analysis terminal, and compare and verify the change characteristics with the reference standard to confirm whether there are any deviation parameters. Step S4: Through the trend feature analysis terminal, determine a set of monitoring periods, monitor the subsequent parameter change process of the deviation parameter, identify the deviation trend relative to the reference standard in the subsequent parameter change process, and perform early warning processing based on the degree of deviation of the deviation trend. Example 3

[0043] This embodiment, based on embodiment 1 or embodiment 2, mainly focuses on the data feature analysis end.

[0044] First, regarding the data feature analysis end, the specific methods for comprehensively verifying historical data are as follows.

[0045] Using the current time as the base time, a set of traceability cycles is determined. The traceability cycle is a preset cycle, generally set to 72 hours. The specific cycle value is determined in advance by relevant personnel. Within the traceability cycle, the base time is the end time of the traceability cycle. The parameter data monitored by the deep foundation pit sensor is sorted according to time characteristics, and the parameter change curve associated with the traceability cycle is generated synchronously. The horizontal axis of the curve is the time line, and the vertical axis is the parameter data. The initial time of the time line is the initial time of the traceability cycle, and the end time is the marked base time.

[0046] The trend of change associated with each set of parameter change curves at adjacent time points is confirmed. The parameter data at the next time point is designated as J1, and the parameter data at the previous time point is designated as J2. Then the trend of change = J1 - J2. The ratio of the trend of change in adjacent time periods is then confirmed. The ratio of the trend of change associated with adjacent time periods is confirmed. Starting from the initial point associated with the parameter change curve, the confirmation ends at the end point. Several sets of trend ratios associated with the corresponding parameter change curve are recorded. Specifically, the adjacent time point here is generally 1 minute, that is, there is a trend of change between the previous 1 minute and the next 1 minute. This is the trend of change associated with the corresponding time period. The ratio of the trend of change associated with the previous and next time periods is the confirmed trend ratio.

[0047] Second, regarding the data feature analysis end, the specific method for locking the time period of the desired feature is as follows.

[0048] Within different parameter change curves, identify the different trend ratios associated with the same adjacent time periods, and perform variance processing on the identified multiple trend ratios to determine the variance value associated with the corresponding adjacent time periods. If the variance value > Y1, no processing is required. If the variance value ≤ Y1, the corresponding adjacent time period is recorded as a pending time period, where Y1 is a preset value. Its specific value is determined by the operator based on experience, and this value is generally related to the data size between multiple collaborative sensors.

[0049] Several undetermined time periods within the traceability period are identified, and these identified undetermined time periods are marked as undetermined characteristic time periods.

[0050] Specifically, if the correlation trends within adjacent time periods are relatively clustered, which means they meet the evaluation criteria for the corresponding variance value, then they can be used as a reference standard in the subsequent monitoring process. Therefore, it is necessary to calibrate the characteristic time periods. In the subsequent processing, the reference characteristics generated by multiple sensors between historical periods are used as the standard to comprehensively evaluate whether there are specific errors or deviations in the associated data in the subsequent monitoring process, which can achieve a better disaster prevention and control effect. Example 4

[0051] This embodiment, based on embodiment 1 or embodiment 2, mainly focuses on the parameter ratio confirmation end.

[0052] The specific method for confirming the reference standard between several deep foundation pit sensors at the parameter ratio confirmation end is as follows.

[0053] Based on the locked undetermined characteristic time period, the ratio of the change trends associated with different deep foundation pit sensors in the same undetermined characteristic time period is arranged by ratio. A group of deep foundation pit sensors is randomly selected as the main sensor, and other deep foundation pit sensors are used as secondary sensors to complete the process of arranging the ratio of change trends and confirm the change trend ratio column.

[0054] Keeping the sorting method of the deep foundation pit sensors unchanged, the change trend ratio columns associated with different undetermined characteristic time periods are confirmed in turn.

[0055] The trend ratio associated with the main sensor is calibrated to 1. The trend ratios associated with other secondary sensors in different trend ratio columns are calibrated synchronously according to the calibration process. After the calibration is completed, multiple trend ratios associated with the same group of secondary sensors are extracted. The minimum and maximum values ​​are selected as the trend ratio intervals associated with the corresponding secondary sensors. The trend ratio intervals of each group of secondary sensors are then confirmed and recorded in turn.

[0056] The arrangement of the main and secondary sensors and the trend ratio range of different secondary sensors are recorded as a reference standard for the association between several deep foundation pit sensors.

[0057] Specifically, in the corresponding processing, the ratio change status between different sensors can be confirmed, and several ratio columns can be comprehensively calibrated to make the ratio of the main sensor calibrated to 1, while the ratios of other secondary sensors remain unchanged, thus completing the confirmation process of several deep foundation pit sensor reference standards. Example 5

[0058] This embodiment, based on embodiment 1 or embodiment 2, mainly focuses on the deviation feature analysis end.

[0059] The specific method for confirming the existence of deviation parameters in the deviation feature analysis is as follows.

[0060] Based on the real-time monitored parameters, the same confirmation process as the change trend ratio column is adopted to confirm the parameter ratio column associated with each parameter during the monitoring period.

[0061] The ratios associated with the primary sensor within the parameter ratio column are calibrated to 1. Then, it is identified whether the ratios associated with other secondary sensors are within the recorded trend ratio range. If so, no processing is required, and continuous monitoring is sufficient. If not, the corresponding parameter is recorded as a deviation parameter, and a deviation signal is generated. This deviation signal is transmitted to the trend feature analysis terminal and simultaneously to the external display terminal. Specifically, each parameter, when processed as a ratio, has a corresponding ratio column, which effectively assesses whether there is a serious deviation in the parameter within the corresponding time period and displays the signal in a timely manner. Example 6

[0062] This embodiment, based on embodiment 1 or embodiment 2, mainly focuses on the trend feature analysis end.

[0063] The specific methods for confirming the degree of deviation from the trend in the trend feature analysis are as follows.

[0064] Based on the calibrated deviation parameters, a set of monitoring cycles is determined. These cycles are preset and typically 3 minutes. The parameter ratios for different time periods within each monitoring cycle are then identified. The ratios associated with the deviation parameters are extracted, and the deviations of these ratios from the trend ratio interval are confirmed. The ratios associated with different times are denoted as BZ. k Where k represents different times, if BZ k If the trend ratio exceeds the range, then the maximum value of the trend ratio range (Max) is selected, and (BZ) is used. k -Max)÷Max=XB k Confirm the excess ratio XB associated with the corresponding time point. k If BZ k If the value is below the trend ratio interval, then select the minimum value (Min) of the trend ratio interval and use (Min-BZ) as the criterion. k ) ÷ Min = XB k Confirm the excess ratio XB associated with the corresponding time point. k .

[0065] Assess the excess ratio XB at the corresponding time point. k Does it meet the following conditions: XB k If the deviation is ≥20%, an early warning will be issued and an abnormal deviation signal will be generated and displayed simultaneously. If the deviation is not met, monitoring will continue. Example 7

[0066] This embodiment describes the system architecture based on any one of Embodiments 1 to 6, combined with actual engineering application scenarios.

[0067] like Figure 5As shown in the diagram, the architecture of the intelligent disaster prevention and control system for deep foundation pits illustrates the main layers of the system: data acquisition layer, data analysis layer, database, and output layer.

[0068] The data acquisition layer is designed with data acquisition terminals for collecting data from multiple sets of sensors, including settlement sensors, displacement sensors, earth pressure sensors, and water level sensors. This layer is responsible for collecting various parameter data of the foundation pit. Settlement sensors include: hydrostatic levels, electronic levels used with barcode leveling rods, and total stations used with mechanical settlement markers. Displacement sensors include: total stations, inclinometers, and crack gauges. Earth pressure sensors include: vibrating wire earth pressure cells, resistive earth pressure sensors, and fiber optic grating earth pressure sensors. Water level sensors include: pressure level gauges, ultrasonic level gauges, and radar level gauges.

[0069] The data analysis layer is designed with four core analysis terminals: data feature analysis, parameter ratio confirmation, deviation feature analysis, and trend feature analysis. This layer establishes reference standards and characteristic time periods by analyzing historical data, and performs trend analysis and deviation assessment by analyzing measured data.

[0070] The database is designed with historical databases and experimental databases.

[0071] The output layer includes submodules for executing early warning response procedures, a visual interface, and a report generation module. This layer provides functions such as early warning, visualization, and reporting.

[0072] In another specific implementation, the monitoring object is not limited to one or more of settlement sensors, displacement sensors, soil pressure sensors, and water level sensors. Data collected by stress and strain sensors such as concrete strain gauges and axial force gauges can be added to the collaborative monitoring object for analysis. Different combinations of sensors can also be selected according to actual needs.

[0073] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0074] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits, characterized in that, include: The data feature analysis unit is used to identify multiple sets of deep foundation pit sensors with multi-terminal collaboration, and to receive historical data generated by each set of sensors within a historical period. This data is then comprehensively verified to pinpoint the specific characteristic time period. The specific method is as follows: Based on the current moment, a set of source tracing cycles is determined. The source tracing cycle is a preset cycle. The parameter data monitored by the deep foundation pit sensor is sorted according to the time characteristics, and the parameter change curve associated with the source tracing cycle is generated synchronously. The horizontal axis of the curve is the time line, and the vertical axis is the parameter data. Confirm the trend of change associated with each set of parameter change curves at adjacent times, and then confirm the ratio of the trend of change in adjacent time periods. Confirm the ratio of the trend of change associated with adjacent time periods, starting from the initial point associated with the parameter change curve and ending at the end point, and record several sets of trend ratios associated with the corresponding parameter change curve. The specific method for locking the undetermined feature time period is as follows: Within different parameter change curves, identify the different trend ratios associated with the same adjacent time periods, and process the variance of the identified multiple trend ratios to determine the variance values ​​associated with the corresponding adjacent time periods: if the variance value > Y1, no processing is required; if the variance value ≤ Y1, the corresponding adjacent time period is recorded as a pending time period. Where Y1 is a preset value; Several undetermined time periods within the traceability period are identified, and these identified undetermined time periods are marked as undetermined characteristic time periods. The parameter ratio confirmation terminal is used to integrate and process the verification features associated with the locked characteristic time period, and confirm the reference standard associated with several deep foundation pit sensors, specifically in the following way: Based on the locked undetermined characteristic time period, the ratio of the change trends associated with different deep foundation pit sensors in the same undetermined characteristic time period is arranged by ratio. A group of deep foundation pit sensors is randomly selected as the main sensor, and other deep foundation pit sensors are used as secondary sensors to complete the process of arranging the ratio of change trends and confirm the change trend ratio column. Keeping the sorting method of the deep foundation pit sensors unchanged, the change trend ratio columns associated with different undetermined characteristic time periods are confirmed in turn; The trend ratio associated with the main sensor is calibrated to 1. According to the calibration process, the trend ratios associated with other secondary sensors in different trend ratio columns are calibrated synchronously. After the calibration is completed, multiple trend ratios associated with the same group of secondary sensors are extracted. The minimum and maximum values ​​are selected as the trend ratio intervals associated with the corresponding secondary sensors. Subsequently, the trend ratio intervals of each group of secondary sensors are confirmed and recorded in turn. The arrangement of the main and secondary sensors and the trend ratio range of different secondary sensors are recorded as a reference standard for the association between several deep foundation pit sensors. The data monitoring terminal is used to monitor various parameters of the deep foundation pit in real time through multiple sets of deep foundation pit sensors; The deviation feature analysis end is used to confirm the change characteristics of each parameter in the same time period based on the real-time monitored parameters, and compare the change characteristics with the reference standard to confirm whether there are any deviation parameters. The trend feature analysis end is used to determine a set of monitoring periods, monitor the subsequent parameter changes of the deviation parameters, identify the deviation trend relative to the reference standard in the subsequent parameter change process, and issue early warnings based on the degree of deviation of the deviation trend.

2. The multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits according to claim 1, characterized in that, The specific method for confirming the existence of deviation parameters in the deviation feature analysis terminal is as follows: Based on the various parameters monitored in real time, the parameter ratio columns associated with each parameter during the monitoring period are confirmed using the same confirmation process as the change trend ratio column. The ratio associated with the main sensor in the parameter ratio column is calibrated to 1. Then, it is identified whether the ratio associated with other secondary sensors is within the recorded trend ratio range. If not, the corresponding parameter is recorded as a deviation parameter, and a deviation signal is generated. The deviation signal is transmitted to the trend feature analysis terminal and simultaneously transmitted to the external display terminal.

3. The multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits according to claim 2, characterized in that, If the ratios associated with other subsensors are within the recorded trend ratio range, no processing is required; continued monitoring is sufficient.

4. The multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits according to claim 2, characterized in that, The specific method by which the trend feature analysis terminal confirms the degree of deviation from the trend is as follows: Based on the calibrated deviation parameters, a set of monitoring periods is determined, which is a preset period. The parameter ratios for different time periods within the monitoring period are then identified. The ratios associated with the deviation parameters are extracted, and the deviations of these ratios from the trend ratio range are confirmed. The ratio associated with different time is recorded as BZ k , wherein k represents different time, if BZ k exceeds the trend ratio interval, the interval maximum value Max of the trend ratio interval is selected, and (BZ k - Max) ÷ Max = XB k The exceeding ratio XB k associated with the corresponding time is confirmed. Assess the excess ratio XB at the corresponding time point. k Does it meet the following conditions: XB k If the deviation is ≥20%, an early warning will be issued and an abnormal deviation signal will be generated and displayed simultaneously. If the deviation is not met, monitoring will continue.

5. The multi-terminal collaborative intelligent disaster prevention and control system for deep foundation pits according to claim 4, characterized in that, If BZ k If the value is below the trend ratio interval, then select the minimum value (Min) of the trend ratio interval and use (Min - BZ) as the criterion. k ) ÷ Min = XB k Confirm the excess ratio XB associated with the corresponding time point. k .

Images