Building safety data analysis method and system based on building safety database

Abstract

The invention relates to the technical field of building safety data analysis based on a building safety database, in particular to a building safety data analysis method and system based on the building safety database. Presetting a risk propagation association relationship among the displacement sensor groups; calculating the instantaneous change rate of the displacement data; identifying that any displacement sensor group has entered an accelerated displacement trend, and marking the accelerated displacement trend as a local abnormal event; performing linkage search on a displacement sensor group associated with the local abnormal event by using an incremental time window and a spatial range; and if the linkage search finds that the plurality of displacement sensor groups with the risk propagation association relationship all present an accelerated displacement trend, aggregating to generate a regional linkage instability early warning. According to the method, local abnormal events can be found in time, so that the analysis accuracy is improved.

Description

Technical Field

[0001] This invention relates to the technical field of building safety data analysis based on a building safety database, and specifically to a method and system for building safety data analysis based on a building safety database. Background Technology

[0002] In the safety management of construction projects, existing construction safety data analysis systems typically rely on construction safety databases to store and process safety data. The core of this system is a set of rules for identifying high-risk work behaviors, primarily derived from data summaries of traditional construction projects (such as steel structure installation and concrete pouring). Therefore, when handling routine construction activities, the system can accurately identify problems, such as insufficient protection during high-altitude operations, crane overloading, or abnormal concrete pouring speeds. The construction safety database is also designed around the characteristics of these traditional projects, facilitating the storage and retrieval of relevant risk data to assist the analysis system in making judgments.

[0003] Faced with changes in project types, existing high-risk operation identification rules are proving inadequate when dealing with data specific to deep foundation pit and underground structure construction. For example, when processing data on support structure deformation monitoring (such as retaining pile inclination and stress changes in support beams) and groundwater control parameters (such as dewatering well water levels and drainage volume), the system cannot identify or correlate these data for analysis. This is because the initial rules lack feature extraction and pattern matching logic for these new data types. The system cannot understand the significance of continuous local deformation of the retaining structure, nor can it link abnormal fluctuations in groundwater levels with potential soil collapse. This insufficient ability to handle new risk data results in existing analysis methods providing very incomplete coverage of the unique hazards of deep foundation pit and underground structure construction. Summary of the Invention

[0004] The purpose of this invention is to address the aforementioned shortcomings by proposing a building safety data analysis method and system based on a building safety database.

[0005] The present invention adopts the following technical solution:

[0006] A building safety data analysis method based on a building safety database, comprising the following steps:

[0007] Displacement sensors within the deep foundation pit monitoring area are grouped, and risk propagation relationships between each displacement sensor group are preset based on the geological conditions of the deep foundation pit.

[0008] Continuously acquire displacement data from each displacement sensor group and calculate the instantaneous rate of change of the displacement data;

[0009] The instantaneous change rate of the displacement data meets a set change feature, any displacement sensor group is identified to have entered an accelerating displacement trend, and the accelerating displacement trend is marked as a local abnormal event;

[0010] Based on the local abnormal event, a linkage search is performed on displacement sensor groups associated with the local abnormal event according to a preset risk propagation correlation relationship, and the linkage search is used to find whether the associated displacement sensor groups present an accelerating displacement trend;

[0011] If the linkage search finds that multiple displacement sensor groups with the risk propagation correlation relationship all present the accelerating displacement trend, a regional linkage instability early warning is generated by aggregation;

[0012] When the preset risk propagation correlation relationship fails to reflect the deep foundation pit geological conditions, the step of generating the regional linkage instability early warning by aggregation includes:

[0013] Identifying the local abnormal event;

[0014] Starting an omnidirectional adjacent group search, the omnidirectional adjacent group search is used to send a probe signal to all displacement sensor groups physically adjacent to the displacement sensor group where the local abnormal event occurs, to find whether a corresponding accelerating displacement trend also occurs in a time period after a time point immediately following occurrence of the local abnormal event, and to mark as a subsequent local abnormal event;

[0015] For any subsequent local abnormal event found in the omnidirectional adjacent group search, a spatiotemporal correlation degree between the subsequent local abnormal event and the local abnormal event is calculated, the spatiotemporal correlation degree comprehensively considers a time interval and a spatial distance between the subsequent local abnormal event and the local abnormal event;

[0016] According to the spatiotemporal correlation degree, a candidate risk propagation path is established, the candidate risk propagation path is used to infer a risk propagation direction;

[0017] If a risk propagation direction corresponding to a certain candidate risk propagation path is repeatedly verified in actual data, the risk propagation direction is marked as a dynamic candidate path, and the priority of the dynamic candidate path in subsequent linkage scanning is improved;

[0018] If multiple displacement sensor groups associated along the dynamic candidate path are found to present the accelerating displacement trend in a specific spatiotemporal range, a regional linkage instability early warning is generated by aggregation.

[0019] By the technical scheme, the early signs of instability of the deep foundation pit structure can be effectively recognized, the grouping of the displacement sensor groups is performed, the risk propagation correlation is preset, the monitoring of the instantaneous change rate is combined, the local abnormal event can be found in time, and when the acceleration displacement trend is presented in multiple correlation groups, the regional linkage instability early warning is generated by aggregation, so that the problem that the existing technology cannot comprehensively cover the unique danger of the deep foundation pit and underground structure construction and the key dynamic displacement data loss leads to the reduction of the early warning accuracy is solved, and the unexpected technical effect that the early signs of instability of the structure can be accurately captured is achieved.

[0020] Further, the method further comprises:

[0021] According to the aggregation of the regional linkage instability early warning, corresponding regional linkage instability early warning information is generated;

[0022] Real-time acquisition of dynamic environmental data of the deep foundation pit construction site, the dynamic environmental data including real-time rainfall, surrounding construction vibration intensity and underground water pumping rate change;

[0023] Correlation analysis is performed on the dynamic environmental data and the regional linkage instability early warning information;

[0024] According to the correlation analysis result, the urgency of the regional linkage instability early warning is corrected or the potential influence range of the regional linkage instability early warning is enhanced.

[0025] Further, the regional linkage instability early warning information includes a unique identifier of the early warning, an occurrence time, an occurrence position, a warning type and an initial risk level, so as to improve the standardization of subsequent correlation analysis.

[0026] Further, the grouping of the displacement sensors in the deep foundation pit monitoring area is performed, and according to the geological conditions of the deep foundation pit, the risk propagation correlation between the displacement sensor groups is preset, and the step comprises:

[0027] Real-time acquisition of geological monitoring data of the deep foundation pit construction site, the geological monitoring data indicating the geological condition change;

[0028] According to the geological monitoring data, the geological condition change event is identified;

[0029] According to the geological condition change event, the influence of the geological condition change on the grouping of the displacement sensors is evaluated;

[0030] According to the evaluation result, the grouping of the displacement sensors in the affected deep foundation pit monitoring area is adjusted;

[0031] According to the adjusted grouping of the displacement sensors and the geological condition change, the risk propagation correlation between the displacement sensor groups is updated;

[0032] The updated displacement sensor group division and its corresponding risk propagation correlation are used in subsequent steps.

[0033] Further, the step of identifying that any displacement sensor group has entered an accelerating displacement trend and marking the accelerating displacement trend as a local abnormal event comprises:

[0034] Real-time acquisition of local environment data corresponding to the displacement sensor group position;

[0035] Matching the local environment data with the identified accelerating displacement trend;

[0036] If the matching result shows that the accelerating displacement trend is consistent with the non-structural displacement response characteristics caused by environmental interference, the early warning priority of the accelerating displacement trend is reduced;

[0037] If the matching result shows that the correlation between the accelerating displacement trend and the environmental interference is low, the local abnormal event state of the accelerating displacement trend is maintained.

[0038] Further, the step of identifying that any displacement sensor group has entered an accelerating displacement trend and marking the accelerating displacement trend as a local abnormal event comprises:

[0039] Identifying the geological horizon where the displacement sensor group is located;

[0040] Acquiring current construction stage information;

[0041] Acquiring environmental conditions corresponding to the position of the displacement sensor group;

[0042] According to the geological horizon, the current construction stage information and the environmental conditions, adjust the judgment threshold and duration standard for identifying the accelerating displacement trend;

[0043] When the displacement data of the displacement sensor group meets the adjusted judgment threshold and duration standard, mark the accelerating displacement trend as a local abnormal event.

[0044] Further, the step of identifying that any displacement sensor group has entered an accelerating displacement trend and marking the accelerating displacement trend as a local abnormal event comprises:

[0045] Real-time monitoring of the continuity and stability of the displacement data stream of the displacement sensor group;

[0046] When the monitoring finds that the displacement data stream of the displacement sensor group has intermittent interruption, sudden jump of data value or long-term deviation from the normal working range, start the displacement sensor self-diagnosis program, check the power supply, communication link and internal state of the displacement sensor group, and obtain the abnormal displacement sensor group;

[0047] cross-comparing displacement data of the abnormal displacement sensor group with displacement data of an adjacent displacement sensor group;

[0048] if the cross-comparing result shows that the displacement data of the adjacent displacement sensor group is normal and does not show the corresponding accelerated displacement trend, marking the abnormality as displacement fluctuation caused by displacement sensor failure, and excluding it from the local abnormal event;

[0049] if the self-diagnosis result shows that the displacement sensor group is working normally, and the cross-comparing result shows that the adjacent displacement sensor group is an associated accelerated displacement trend, maintaining the local abnormal event status of the accelerated displacement trend.

[0050] Further, the method comprises:

[0051] receiving a displacement data stream of the displacement sensor group in real time, and segmenting and buffering the displacement data stream of the displacement sensor group;

[0052] calculating the packet loss rate and short-term fluctuation amplitude of each segment of the displacement data stream of the displacement sensor group;

[0053] setting a short time window and a long time window;

[0054] determining whether the packet loss rate or the short-term fluctuation amplitude in the short time window exceeds a preset first threshold, and marking transient abnormality according to the determination result;

[0055] determining whether the occurrence frequency or duration of the transient abnormality in the long time window exceeds a preset second threshold, and marking persistent abnormality according to the determination result;

[0056] determining whether to trigger a displacement sensor failure warning according to the marking result of the transient abnormality or the persistent abnormality.

[0057] Further, the step of receiving a displacement data stream of the displacement sensor group in real time, and segmenting and buffering the displacement data stream of the displacement sensor group comprises:

[0058] receiving a displacement data stream of the displacement sensor group in real time;

[0059] detecting the wireless signal strength or multipath effect of the displacement data stream of the displacement sensor group, and obtaining real-time signal quality;

[0060] when the wireless signal strength is lower than a preset strength threshold or the multipath effect is enhanced, starting an adaptive data receiving mode;

[0061] in the adaptive data receiving mode, enabling a backup communication link or adjusting a data transmission protocol to improve the stability of the displacement data stream of the displacement sensor group;

[0062] According to the real-time signal quality, the segment cache strategy of the displacement data stream of the displacement sensor group is dynamically adjusted, and the continuity of the displacement data stream of the displacement sensor group is improved.

[0063] The received data packet is subjected to integrity check.

[0064] For incomplete or incorrect data packets, retransmission request or local data interpolation recovery is performed to improve the continuity of the displacement data stream of the displacement sensor group.

[0065] The displacement data stream of the displacement sensor group is subjected to segment cache.

[0066] The application also discloses a building safety data analysis system based on a construction database, which is applied to a building safety data analysis method based on a construction database.

[0067] The preset module groups the displacement sensors in the deep foundation pit monitoring area, and presets the risk propagation correlation relationship between the displacement sensor groups according to the geological conditions of the deep foundation pit.

[0068] The processing module continuously acquires the displacement data of the displacement sensor groups and calculates the instantaneous change rate of the displacement data.

[0069] The identification module identifies that any displacement sensor group has entered an accelerated displacement trend based on the fact that the instantaneous change rate of the displacement data meets the set change characteristics, and marks the accelerated displacement trend as a local abnormal event.

[0070] The search module performs linkage search on the displacement sensor groups associated with the local abnormal event in an incremental time window and spatial range based on the local abnormal event and the preset risk propagation correlation relationship, and the linkage search is used to find out whether the associated displacement sensor groups present an accelerated displacement trend.

[0071] The early warning generation module aggregates to generate a regional linkage instability early warning if the linkage search finds that multiple displacement sensor groups with the risk propagation correlation relationship all present an accelerated displacement trend.

[0072] When the preset risk propagation correlation relationship fails to reflect the geological conditions of the deep foundation pit, the step of aggregating to generate a regional linkage instability early warning comprises:

[0073] Identify the local abnormal event.

[0074] Start the omnidirectional adjacent group search, and the omnidirectional adjacent group search is used to send a probe signal to all displacement sensor groups physically adjacent to the displacement sensor group where the local abnormal event occurs, to find out whether a corresponding accelerated displacement trend also appears in a time period after the time point immediately following the occurrence of the local abnormal event, and mark it as a subsequent local abnormal event.

[0075] For any subsequent local anomaly event discovered in the omni-directional neighborhood group search, a spatio-temporal correlation degree between the subsequent local anomaly event and the local anomaly event is calculated, the spatio-temporal correlation degree comprehensively considering a time interval and a spatial distance between the occurrence of the subsequent local anomaly event and the local anomaly event;

[0076] According to the spatio-temporal correlation degree, a candidate risk propagation path is established, the candidate risk propagation path being used to infer a risk propagation direction;

[0077] If the risk propagation direction corresponding to a certain candidate risk propagation path is repeatedly verified in actual data, the risk propagation direction is marked as a dynamic candidate path, and the priority of the dynamic candidate path in subsequent joint scanning is improved;

[0078] If in a specific spatio-temporal range, it is found that multiple displacement sensor groups associated along the dynamic candidate path all present an accelerating displacement trend, a regional joint instability early warning is generated by aggregation.

[0079] Through the technical scheme, the application provides a system-level solution, realizes comprehensive analysis and early warning of deep foundation pit safety data through modular design, can effectively solve the problem of insufficient capacity of the existing system in processing deep foundation pit and underground structure construction specific data, and achieves the unexpected technical effect of accurately capturing early signs of structure instability.

[0080] The application realizes accurate identification and early warning of early signs of structure instability, and significantly improves the intelligent level and risk prevention and control capability of building engineering safety management.

[0081] In order to further understand the features and technical contents of the present application, please refer to the following detailed description and drawings of the present application. However, the provided drawings are only used for reference and illustration, and are not used to limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0082] Figure 1 A method flowchart of a building safety data analysis method based on a construction database according to the present application;

[0083] Figure 2 A structural schematic diagram of a building safety data analysis system based on a construction database according to the present application. DETAILED DESCRIPTION

[0084] The following embodiments are illustrative of the present application and do not limit the scope of the application. The present application can be practiced with other embodiments as well. The disclosure of these subsequent embodiments can be combined with the description of the above embodiments in order to demonstrate various respects of the present application. Various modifications and changes can be made with respect to the above embodiments without departing from the spirit and scope of the present application. It is therefore intended that the present application not be limited to the preferred embodiments and illustrations but cover all within the scope of the appended claims.

[0085] The embodiment provides a building safety data analysis method and system based on a construction database. Figure 1 and Figure 2 are shown.

[0086] Referring to Figure 1 , a building safety data analysis method based on a construction database, the method comprising the following steps:

[0087] Grouping displacement sensors in a deep foundation pit monitoring area, and presetting risk propagation correlation relationships between groups of displacement sensors according to geological conditions of the deep foundation pit;

[0088] Continuously acquiring displacement data of each group of displacement sensors, and calculating instantaneous change rates of the displacement data;

[0089] Based on the instantaneous change rates of the displacement data satisfying set change characteristics, identifying that any group of displacement sensors has entered an accelerated displacement trend, and marking the accelerated displacement trend as a local abnormal event;

[0090] Based on the local abnormal event, according to the preset risk propagation correlation relationship, performing a linkage search on groups of displacement sensors associated with the local abnormal event in an incremental time window and spatial range, the linkage search being used to find whether the associated groups of displacement sensors present an accelerated displacement trend;

[0091] If the linkage search finds that multiple groups of displacement sensors having the risk propagation correlation relationship all present the accelerated displacement trend, generating a regional linkage instability early warning by aggregation;

[0092] When the preset risk propagation correlation relationship fails to reflect the geological conditions of the deep foundation pit, the step of generating the regional linkage instability early warning by aggregation comprises:

[0093] Identifying the local abnormal event;

[0094] initiating an omnidirectional neighboring group search, the omnidirectional neighboring group search being configured to send a probe signal to all displacement sensor groups physically adjacent to the displacement sensor group where the local anomaly event occurs, to search for whether a corresponding accelerated displacement trend also occurs within a time period after a time point immediately following occurrence of the local anomaly event, and to mark as a subsequent local anomaly event;

[0095] for any subsequent local anomaly event found in the omnidirectional neighboring group search, calculating a spatiotemporal correlation degree between the subsequent local anomaly event and the local anomaly event, the spatiotemporal correlation degree comprehensively considering a time interval and a spatial distance between occurrence of the subsequent local anomaly event and the local anomaly event;

[0096] according to the spatiotemporal correlation degree, establishing a candidate risk propagation path, the candidate risk propagation path being configured to infer a risk propagation direction;

[0097] if the risk propagation direction corresponding to a certain candidate risk propagation path is repeatedly verified in actual data, marking the risk propagation direction as a dynamic candidate path, and improving a priority of the dynamic candidate path in subsequent joint scanning;

[0098] if multiple displacement sensor groups associated along the dynamic candidate path are found to present an accelerated displacement trend within a specific spatiotemporal range, generating a regional joint instability early warning in aggregation.

[0099] The "deep foundation pit" referred to in the present application refers to a foundation pit engineering with an excavation depth exceeding a certain standard (for example, 5 meters), characterized by poor soil stability, complex underground water, and high construction risk. The "displacement sensor" is a device for measuring the position change of an object, which is mainly used in the present application to monitor the displacement of the deep foundation pit enclosure structure, the surrounding soil or the building during construction. The "displacement sensor group" refers to the logical division of multiple displacement sensors according to their geographical location, monitoring object or function to form a set for centralized management and analysis. The "risk propagation correlation" refers to the potential connection between different displacement sensor groups due to geological conditions, structural connection or construction activities, etc. When an abnormal displacement occurs in one group, it may cause displacement in other groups. The "instantaneous change rate" refers to the change speed of displacement data within a very short time, which can sensitively reflect the dynamic change trend of the structure or soil, and is a key indicator for judging instability acceleration. The "local abnormal event" refers to the instantaneous change rate of displacement data of a displacement sensor group meeting the set change characteristics, indicating that the group has entered an accelerated displacement trend, but has not reached the degree of regional instability. The "linkage search" is a process based on the pre-set risk propagation correlation, which systematically explores the displacement sensor groups associated with the local abnormal event in an incremental time window and spatial range, aiming to find out whether there is a chain reaction. The "regional linkage instability early warning" is a high-level warning issued by the system when the linkage search finds that multiple displacement sensor groups with risk propagation correlation all show an accelerated displacement trend, indicating that the deep foundation pit may have a regional overall instability.

[0100] When grouping the displacement sensors in the monitoring area of the deep foundation pit and pre-setting the risk propagation correlation between the displacement sensor groups according to the geological conditions of the deep foundation pit, various methods can be used. For example, according to the planar layout and geological stratification of the deep foundation pit, adjacent displacement sensors can be divided into a group. Specifically, if there is a soft soil layer on one side of the deep foundation pit, all displacement sensors in this area can be divided into a group, and a high risk propagation correlation between this group and adjacent groups can be pre-set. Another way is to group according to the type and stress characteristics of the supporting structure of the deep foundation pit. For example, displacement sensors on the same support beam can be divided into a group, and the risk propagation correlation can be pre-set according to the force transmission path of the support beam. When pre-setting the risk propagation correlation, it can be manually set based on historical monitoring data and expert experience, or it can be preliminarily set through geological survey reports and numerical simulation results.

[0101] The displacement data of each displacement sensor group is continuously acquired, and the instantaneous change rate of the displacement data is calculated. The acquisition of displacement data can be through wired or wireless communication, and the data collected by the displacement sensor is transmitted to the data processing center in real time. For example, the displacement sensor can upload the displacement data to the cloud platform through the LoRaWAN network. When calculating the instantaneous change rate of the displacement data, the difference method can be used. Specifically, the instantaneous change rate can be obtained by subtracting the displacement data at the previous time from the displacement data at the current time, and then dividing by the time interval. For example, if the displacement data is collected every 10 minutes, the instantaneous change rate can be represented as ΔL / Δt, where ΔL is the displacement change in 10 minutes, and Δt is 10 minutes.

[0102] Based on the instantaneous change rate of the displacement data meeting the set change characteristics, it is identified that any displacement sensor group has entered an accelerating displacement trend, and the accelerating displacement trend is marked as a local abnormal event. The set change characteristics can include that the absolute value of the instantaneous change rate exceeds a certain threshold, or the instantaneous change rate continuously increases within a period of time. For example, if the instantaneous change rate of a certain displacement sensor group exceeds 5 mm / h for 30 consecutive minutes, it can be considered that the group has entered an accelerating displacement trend. After identifying the accelerating displacement trend, the system marks it as a local abnormal event and records the time, location and displacement data of the event.

[0103] Based on the local abnormal event, according to the preset risk propagation association relationship, the displacement sensor groups associated with the local abnormal event are searched in an incremental time window and spatial range, and the search is used to find out whether the associated displacement sensor groups present an accelerating displacement trend. The search can start from the directly associated groups of the local abnormal event group and gradually expand the search range. For example, if group A has a local abnormal event and group A has a risk propagation association relationship with group B and group C, the system will first search group B and group C. The time window of the search can start from 1 hour after the event occurs, and gradually increase to 2 hours, 4 hours, etc. The spatial range can be expanded from the directly adjacent groups to the secondary adjacent groups.

[0104] If the search finds that multiple displacement sensor groups with risk propagation association relationship all present an accelerating displacement trend, a regional joint instability warning is generated. For example, if group A, group B and group C are found to present an accelerating displacement trend in the search, and they have a risk propagation association relationship, the system will generate a regional joint instability warning. The warning information can include the range of the instability region, the warning level, the recommended emergency measures, etc.

[0105] Specifically, identifying a local abnormal event refers to identifying that any displacement sensor group has entered an accelerating displacement trend according to the instantaneous change rate of the displacement data meeting the set change characteristics, and marking the accelerating displacement trend as a local abnormal event.

[0106] Among them, the omnidirectional adjacent group search can be understood as an active detection mechanism, which aims to break through the limitation of the preset correlation relationship, and find potential risk propagation that is not covered by the preset correlation relationship by sending a probe signal to the physically adjacent displacement sensor group. The probe signal aims to find out whether these adjacent groups also appear an accelerating displacement trend in the time period after the time point immediately following the occurrence of the local abnormal event, and mark them as subsequent local abnormal events.

[0107] In practical application, the spatio-temporal correlation degree is a quantitative index that comprehensively considers the time interval and spatial distance between the subsequent local abnormal event and the local abnormal event, for example, a weighted average or multi-dimensional distance calculation can be used, and the purpose is to evaluate the closeness of the two abnormal events in time and space, so as to judge whether there is a causal or propagation relationship between them.

[0108] Further, according to the spatio-temporal correlation degree, a candidate risk propagation path can be established, which is used to infer the risk propagation direction. For example, if a subsequent local abnormal event occurs immediately after a local abnormal event in time and the spatial distance is close, it can be inferred that the risk may propagate along the direction between the two groups.

[0109] As a preferred embodiment, if the risk propagation direction corresponding to a certain candidate risk propagation path is repeatedly verified in actual data, for example, through multiple confirmations of historical data backtracking or real-time monitoring, the risk propagation direction is marked as a dynamic candidate path, and its priority in subsequent joint scanning is improved. The purpose is to learn and adapt to the actual risk propagation mode through data verification, and improve the accuracy and efficiency of early warning.

[0110] Thus, if multiple displacement sensor groups associated along the dynamic candidate path are found to have an accelerating displacement trend within a certain spatio-temporal range, a regional joint instability early warning is generated.

[0111] In some preferred embodiments, it is assumed that during the construction of a deep foundation pit, due to the sudden change of underground water level or unknown abnormality of local soil properties, the preset risk propagation correlation relationship fails to accurately capture the new potential slip surface. At this time, the displacement sensor group A located in a certain region of the deep foundation pit is first identified to enter an accelerating displacement trend, and is marked as a local abnormal event.

[0112] The system then initiates an omnidirectional neighborhood group search, sending out probe signals to groups B, C, D, etc. that are physically adjacent to group A. In a short time after the anomaly in group A, group B and group C are also found to exhibit accelerated displacement trends and are marked as subsequent local anomaly events. The system then calculates the spatiotemporal correlation between group B and group A, and the spatiotemporal correlation between group C and group A. If the spatiotemporal correlation between group B and group A is found to be much higher than that between group C and group A, the system establishes a candidate risk propagation path from group A to group B.

[0113] With the continuation of monitoring, if the risk propagation direction from group A to group B is repeatedly verified in subsequent similar events, for example, at other time points or under similar working conditions, the anomaly in group A always occurs immediately after the anomaly in group B, then the propagation direction will be marked as a dynamic candidate path and given a higher priority in subsequent joint scanning. Finally, if group A and group B are found to exhibit accelerated displacement trends along the dynamic candidate path within a certain spatiotemporal range, the system generates a regional joint instability early warning. In this way, even if the preset correlation relationship is imperfect, the system can dynamically learn and adapt to the actual risk propagation mode in a data-driven manner, thereby providing more accurate and timely early warnings.

[0114] The application further provides a building safety data analysis method based on a construction database, which further comprises:

[0115] According to the generated regional joint instability early warning, corresponding regional joint instability early warning information is generated;

[0116] Real-time dynamic environmental data of the deep foundation pit construction site are acquired, and the dynamic environmental data include real-time rainfall, surrounding construction vibration intensity, and underground water pumping rate change;

[0117] The dynamic environmental data are associated with the regional joint instability early warning information for correlation analysis;

[0118] According to the correlation analysis result, the urgency of the regional joint instability early warning is corrected or the potential influence range of the regional joint instability early warning is enhanced.

[0119] Specifically, after the generated regional joint instability early warning, the system generates corresponding regional joint instability early warning information according to the early warning.

[0120] Among them, real-time acquisition of dynamic environmental data of deep foundation pit construction site refers to continuously collecting environmental parameters closely related to the stability of deep foundation pit through various environmental monitoring equipment deployed on the construction site. These dynamic environmental data specifically include real-time rainfall, surrounding construction vibration intensity and underground water pumping rate change. Real-time rainfall is used to assess the influence of surface water infiltration on soil moisture content and seepage pressure; surrounding construction vibration intensity is used to assess the disturbance of external construction activities on the stability of deep foundation pit structure; underground water pumping rate change is used to assess the influence of underground water level fluctuation on soil effective stress. The real-time nature of these data ensures timely response to environmental changes, and the purpose is to provide the latest external influencing factors for the correction and enhancement of early warning.

[0121] In practical application, the correlation analysis of dynamic environmental data and regional linkage instability early warning information refers to exploring the mutual relationship and influence mechanism between dynamic environmental factors and identified regional linkage instability early warning through data fusion and analysis algorithm. For example, statistical methods, machine learning models or expert system rules can be used to analyze how the urgency or influence range of regional linkage instability early warning may change under the conditions of specific rainfall, vibration intensity or underground water pumping change. The purpose is to reveal the potential aggravation or mitigation of environmental factors on the instability risk of deep foundation pit.

[0122] Further, according to the correlation analysis results, the urgency of regional linkage instability early warning is corrected or the potential influence range of regional linkage instability early warning is enhanced. Urgency correction means adjusting the priority or response time requirement of early warning according to the influence of environmental factors, for example, in extreme rainfall conditions, even if the displacement data does not change much, the early warning level may be elevated. Potential influence range enhancement means expanding the geographical area covered by early warning according to the risk diffusion that environmental factors may cause, for example, in a strong vibration environment, instability risk may spread from local area to surrounding area. The purpose is to make the early warning information more accurately reflect the actual risk situation and guide the site to take more targeted preventive measures.

[0123] In some preferred embodiments, assuming that a regional linkage instability early warning has been generated in a certain deep foundation pit monitoring area, indicating that there is a linkage instability risk in a certain area. At this time, the system will first generate regional linkage instability early warning information containing the early warning time, location, type and initial severity. Subsequently, the system obtains real-time dynamic environmental data of the deep foundation pit construction site, for example, it is monitored that the real-time rainfall reaches 50 millimeters in the past 2 hours, the surrounding construction vibration intensity continues to exceed the safety threshold near the warning area, and the groundwater pumping rate increases significantly in a short time. The system will associate and analyze these dynamic environmental data with the generated regional linkage instability early warning information. The analysis result may show that high rainfall and continuous vibration can significantly accelerate soil softening and structure destruction, and the increase of groundwater pumping rate may lead to effective stress change, further aggravating the instability risk. Based on the correlation analysis result, the system will modify the urgency of the original regional linkage instability early warning, for example, the warning level will be raised from "medium" to "high", and the potential impact range of the warning will be enhanced, for example, the original impact range will be expanded by 10 meters to cover the area that may be further expanded under the influence of environmental factors. Thus, the site management personnel can obtain more accurate and more instructive early warning information, so as to take emergency measures such as evacuation, reinforcement or stop construction in time, effectively avoiding or reducing potential accident losses.

[0124] The application further proposes that the regional linkage instability early warning information includes a unique identifier of the early warning, occurrence time, occurrence location, early warning type and initial risk level, for improving the standardization of subsequent correlation analysis.

[0125] Specifically, the early warning information can be understood as a structured description of the identified regional linkage instability risk, and the early warning type is, for example, soil sliding, local collapse, etc. The purpose is to provide a standardized data basis for subsequent analysis and decision-making.

[0126] The application further proposes the steps of grouping displacement sensors in a deep foundation pit monitoring area, and pre-setting the risk propagation correlation relationship between each displacement sensor group according to the geological conditions of the deep foundation pit, comprising:

[0127] Real-time acquisition of geological monitoring data of the deep foundation pit construction site, the geological monitoring data indicating geological condition changes;

[0128] Identifying a geological condition change event according to the geological monitoring data;

[0129] Evaluating the influence of the geological condition change on the grouping of displacement sensors according to the geological condition change event;

[0130] Adjusting the grouping of displacement sensors in the affected deep foundation pit monitoring area according to the evaluation result;

[0131] According to the adjusted displacement sensor group division and the change of geological conditions, the risk propagation correlation between each displacement sensor group is updated;

[0132] The updated displacement sensor group division and the corresponding risk propagation correlation are used in subsequent steps.

[0133] Specifically, real-time acquisition of geological monitoring data at the deep foundation pit construction site refers to continuously collecting various parameters reflecting changes in geological conditions through various geological monitoring equipment deployed around the deep foundation pit, such as pore water pressure gauges, soil pressure gauges, inclinometers, settlement meters, etc. These geological monitoring data can indicate changes in key geological parameters such as stress, deformation, groundwater level, and soil density.

[0134] Among them, according to the geological monitoring data, the identification of the geological condition change event can be understood as analyzing the real-time acquired geological monitoring data, such as by setting thresholds, trend analysis or anomaly detection algorithms, to determine whether there are significant changes beyond the normal fluctuation range. For example, when the pore water pressure suddenly rises, the soil settlement rate abnormally accelerates, or the inclinometer data indicates that the deep soil layer has a significant displacement, it can be identified as a geological condition change event.

[0135] In practical application, according to the geological condition change event, the influence of the geological condition change on the displacement sensor group division is to analyze the influence of the identified geological condition change event on the physical boundary, geological continuity or mechanical response characteristics of the existing displacement sensor group. For example, if the geological condition change event indicates that a new weak interlayer appears in a certain area or the underground water seepage path changes, the division method of the displacement sensor group in that area may need to be reconsidered.

[0136] Further, according to the evaluation result, adjusting the displacement sensor group division of the affected deep foundation pit monitoring area refers to reconfiguring the displacement sensor group in the specific area affected by the change of geological conditions based on the evaluation result. This may include splitting the original group into multiple subgroups, or merging multiple adjacent groups into one larger group, to better reflect the actual geological structure and potential instability mode.

[0137] Therefore, according to the adjusted displacement sensor group division and the change of geological conditions, the risk propagation correlation between each displacement sensor group is updated, which means that after the adjustment of the displacement sensor group division, the risk propagation path and intensity between each new group are re-evaluated and established. For example, if the geological condition change causes the soil connection between two groups to become weak, the risk propagation correlation between them may be enhanced; conversely, if a new barrier layer appears, the correlation may be weakened.

[0138] Finally, the updated displacement sensor group division and its corresponding risk propagation correlation are used in subsequent steps to ensure that the subsequent displacement data analysis, local anomaly event identification, and regional linkage instability warning generation are based on the latest and most accurate geological conditions and risk propagation models.

[0139] In some preferred embodiments, it is assumed that at the initial stage of deep foundation pit construction, displacement sensor group A and group B are divided into two independent areas according to the survey report, and the risk propagation correlation between them is pre-set to be weak because there is a stable rock layer between them. However, during the construction process, due to continuous heavy rainfall, geological monitoring data shows that the groundwater level rises significantly, and inclinometer data indicates that new cracks have appeared in the rock layer, indicating a change in geological conditions. After the system identifies this change in geological conditions, it will evaluate the impact of the change on the displacement sensor group division. The evaluation result shows that the new cracks may cause the rock layer to become less stable, weakening the geological continuity between group A and group B, and even forming a new potential sliding surface. According to this evaluation result, the system will adjust the displacement sensor group division of the affected deep foundation pit monitoring area, for example, it may separate some sensors near the crack from group A or group B to form a new subgroup C, or redefine the boundaries of group A and group B. At the same time, according to the adjusted displacement sensor group division and the change in geological conditions, the system will update the risk propagation correlation between each displacement sensor group. For example, due to the existence of the crack, the risk propagation correlation between group A and group B may be enhanced, and the correlation between group C and group A or group B may also be re-evaluated. Finally, the updated displacement sensor group division and its corresponding risk propagation correlation are used in subsequent linkage search and warning generation, ensuring that even in complex and changing geological conditions, the system can accurately identify potential regional linkage instability risks.

[0140] The application further proposes that the step of identifying that any displacement sensor group has entered an accelerated displacement trend and marking the accelerated displacement trend as a local anomaly event comprises:

[0141] real-time acquisition of local environmental data corresponding to the position of the displacement sensor group;

[0142] matching the local environmental data with the identified accelerated displacement trend;

[0143] if the matching result shows that the accelerated displacement trend is consistent with the non-structural displacement response characteristics caused by environmental interference, the warning priority of the accelerated displacement trend is reduced;

[0144] if the matching result shows that the correlation between the accelerated displacement trend and environmental interference is low, the local anomaly event state of the accelerated displacement trend is maintained.

[0145] Specifically, real-time acquisition of local environmental data corresponding to the position of the displacement sensor group means that through the deployment of environmental sensors such as rain gauges, thermometers, anemometers, hygrometers, or vibration sensors in the deep foundation pit monitoring area, the environmental parameters related to the position of a specific displacement sensor group are continuously collected. These data can include real-time rainfall, environmental temperature, wind power, humidity, and surrounding construction vibration intensity. The purpose is to provide a basis for subsequent judgment of whether the displacement anomaly is caused by environmental factors.

[0146] Among them, matching the local environmental data with the identified accelerating displacement trend can be understood as synchronous analysis of displacement data and environmental data. For example, time series analysis, correlation analysis, or machine learning models can be used to evaluate whether there is a significant synchrony or causal relationship between the accelerating displacement trend and a specific environmental event (such as heavy rainfall, intense vibration, sudden temperature change, etc.). The purpose is to distinguish between structural displacement and non-structural displacement.

[0147] In practical application, if the matching result shows that the accelerating displacement trend is consistent with the response characteristics of non-structural displacement caused by environmental interference, the warning priority of the accelerating displacement trend is reduced. This means that when the analysis shows that the observed accelerating displacement trend is likely to be caused only by environmental factors (for example, sensor expansion due to heat, slight shaking caused by wind load, short-term surface soil displacement caused by surface water infiltration due to rainfall, etc.) rather than deep foundation pit structure instability, the system will not immediately trigger a high-level warning, but will mark it as a lower-level attention event, or only record and continuously observe. This helps to reduce false positives and avoid unnecessary resource investment and panic.

[0148] Further, if the matching result shows that the accelerating displacement trend has low correlation with environmental interference, the local abnormal event state of the accelerating displacement trend is maintained. This means that when there is no significant correlation between the accelerating displacement trend and known environmental interference factors, or its displacement characteristics (such as duration, amplitude, direction, etc.) do not match the non-structural response caused by environmental interference, the system will consider that the accelerating displacement trend is more likely to be a precursor to structural problems of the deep foundation pit, and therefore maintain its warning state as a local abnormal event for further linkage search and risk assessment.

[0149] In some preferred embodiments, if a group of displacement sensors monitors a displacement data instantaneous rate of change exceeding a preset threshold within a short time, it is preliminarily determined that an accelerating displacement trend has occurred. At this time, the system will obtain the local environmental data corresponding to the location of the group of displacement sensors in real time. For example, if it is monitored that the area is experiencing a persistent heavy rainfall at the same time, and historical data shows that this type of rainfall often causes short-term, small-amplitude non-structural displacement of the surface soil, the system will match the current accelerating displacement trend with the heavy rainfall data. If the matching result shows that the characteristics (such as displacement direction, duration, amplitude, etc.) of the accelerating displacement trend are highly consistent with the response characteristics of non-structural displacement caused by heavy rainfall, the system will reduce the warning priority of the accelerating displacement trend and mark it as "displacement fluctuation under environmental influence", rather than immediately triggering a regional linkage instability warning. Conversely, if the accelerating displacement trend occurs without obvious environmental interference, or its characteristics do not match the response caused by environmental interference, the system will maintain its local abnormal event status and start the subsequent linkage search process to assess whether there is a real structural instability risk.

[0150] The present application further proposes a step of identifying that any group of displacement sensors has entered an accelerating displacement trend and marking the accelerating displacement trend as a local abnormal event, which comprises:

[0151] identifying the geological horizon in which the group of displacement sensors is located;

[0152] obtaining current construction stage information;

[0153] obtaining the environmental conditions corresponding to the location of the group of displacement sensors;

[0154] adjusting the judgment threshold and duration criteria for identifying the accelerating displacement trend according to the geological horizon, the current construction stage information and the environmental conditions;

[0155] marking the accelerating displacement trend as a local abnormal event when the displacement data of the group of displacement sensors meets the adjusted judgment threshold and duration criteria.

[0156] Specifically, identifying the geological horizon in which the group of displacement sensors is located means determining the specific geological composition of the soil or rock mass under the monitoring area of each group of displacement sensors. For example, according to geological survey reports, drilling data or geophysical exploration results, the monitoring area of a deep foundation pit can be divided into different geological horizons, such as soft soil layer, sand layer, clay layer, weathered rock layer, etc. Different geological horizons of soil have different mechanical properties and deformation responses, and their displacement rates and modes under the same load or disturbance may differ significantly.

[0157] Among them, obtaining the current construction stage information refers to obtaining the specific construction link of the deep foundation pit project in real time. For example, the construction stage information can include the depth of earth excavation, the progress of supporting structure installation, the situation of groundwater lowering and drainage, the change of surrounding load, etc. Different construction stages will introduce different stress states and disturbance sources, thereby affecting the overall stability and local displacement response of the deep foundation pit.

[0158] In practical applications, obtaining the environmental conditions corresponding to the position of the displacement sensor group refers to collecting external environmental data related to the position of the displacement sensor group. For example, the environmental conditions can include real-time rainfall, environmental temperature, groundwater level change, surrounding construction vibration intensity, etc. These environmental factors, such as soil softening caused by rainfall, material thermal expansion and contraction caused by temperature change, and effective stress change caused by groundwater level fluctuation, can all affect the trend of displacement data.

[0159] Further, adjusting the judgment threshold and duration criteria for identifying the accelerated displacement trend according to the geological horizon, the current construction stage information and the environmental conditions refers to dynamically modifying the critical value and duration requirement for determining whether the displacement sensor group enters the accelerated displacement trend by considering the above dynamic factors. For example, in the case of soft soil layer, deep foundation pit excavation to critical depth and accompanied by continuous heavy rainfall, even a small displacement rate change or a short duration can be considered as an accelerated displacement trend; while in the case of hard rock layer, stable construction load and good environmental conditions, a higher displacement rate change or a longer duration may be required to trigger the warning. The purpose is to make the identification of the accelerated displacement trend more consistent with the actual working conditions, and to improve the sensitivity and accuracy of the warning.

[0160] Thus, when the displacement data of the displacement sensor group meets the adjusted judgment threshold and duration criteria, the accelerated displacement trend is marked as a local abnormal event. This means that only when the displacement data is considered in the dynamic standard of the specific geology, construction and environment background, it is confirmed as a real accelerated displacement trend, thereby avoiding the misjudgment caused by improper static threshold setting.

[0161] In some preferred embodiments, assume that in a deep foundation pit project, groups of displacement sensors are deployed on different geological layers, for example, one part is located in the upper soft clay layer, and the other part is located in the lower hard rock layer. In the early stage of construction, when the foundation pit excavation depth is shallow, and the weather is sunny and the underground water level is stable, the system may use a relatively loose judgment threshold. However, when the construction enters the deep excavation stage, especially when the group of displacement sensors is located in the soft clay layer and encounters continuous heavy rainfall, the system will dynamically tighten the judgment threshold for identifying the accelerated displacement trend and shorten the duration standard according to the obtained geological layer (soft clay), construction stage (deep excavation) and environmental condition (heavy rainfall). For example, under the conditions of soft clay layer and heavy rainfall, even if the displacement rate only increases slightly and the duration is relatively short, it may be immediately marked as a local abnormal event. Conversely, if the group of displacement sensors is located in the hard rock layer, under the same construction stage and environmental conditions, the system may use a relatively high judgment threshold and a longer duration standard to avoid misjudging the small displacement caused by the normal stress release of the rock mass as an accelerated displacement trend. Through this dynamic adjustment mechanism, the system can provide more refined and intelligent safety warnings according to the actual complex situation of the deep foundation pit project, ensuring the accuracy and practicality of the warning.

[0162] The application further proposes that the above step of identifying that any group of displacement sensors has entered an accelerated displacement trend and marking the accelerated displacement trend as a local abnormal event comprises:

[0163] Real-time monitoring of the continuity and stability of the displacement data stream of the group of displacement sensors;

[0164] When monitoring finds that the displacement data stream of the group of displacement sensors has intermittent interruptions, sudden jumps in data values or long-term deviation from the normal working range, start the displacement sensor self-diagnosis program to check the power supply, communication link and internal state of the group of displacement sensors, and obtain the abnormal group of displacement sensors;

[0165] Cross-comparison of the displacement data of the abnormal group of displacement sensors and the adjacent group of displacement sensors;

[0166] If the cross-comparison result shows that the displacement data of the adjacent group of displacement sensors is normal and does not show the corresponding accelerated displacement trend, mark the abnormality as displacement fluctuation caused by displacement sensor failure and exclude it from the local abnormal event;

[0167] If the self-diagnosis result shows that the group of displacement sensors is working normally, and the cross-comparison result shows that the adjacent group of displacement sensors is an associated accelerated displacement trend, maintain the local abnormal event state of the accelerated displacement trend.

[0168] Specifically, the real-time monitoring of the continuity and stability of the displacement data stream of the displacement sensor group means that the system continuously pays attention to the integrity of the data packets received from each displacement sensor group, the transmission delay, the fluctuation range of the data value, and the data update frequency, and other indicators. The purpose is to discover abnormal situations that may exist in data transmission or the sensor itself in a timely manner. Among them, when the monitoring finds that the displacement data stream of the displacement sensor group appears intermittent interruption, sudden jump of data value or long-term deviation from the normal working range, the displacement sensor self-diagnosis program will be started. The self-diagnosis program aims to conduct in-depth inspection on the displacement sensor group with abnormal data stream, specifically including evaluating the power supply state, the connection quality of the communication link and the working state of the internal sensing element of the displacement sensor group, thereby determining whether the displacement sensor group is an abnormal displacement sensor group. The purpose is to preliminarily judge whether the data anomaly is caused by hardware or software failure of the sensor itself. In practical application, cross comparison of displacement data of abnormal displacement sensor group and adjacent displacement sensor group means comparing and analyzing the displacement data reported by the abnormal displacement sensor group with the displacement data of other displacement sensor groups adjacent to its physical position. The purpose is to use spatial correlation to verify the authenticity of abnormal data. Further, if the cross comparison result shows that the displacement data of the adjacent displacement sensor group is normal and does not show the corresponding accelerated displacement trend, the abnormality is marked as displacement fluctuation caused by displacement sensor failure, and it is excluded from the local abnormal event. This means that if the abnormal data is not confirmed by the surrounding sensors, it is inclined to believe that it is a problem of the sensor itself. On the contrary, if the self-diagnosis result shows that the displacement sensor group is working normally, and the cross comparison result shows that the adjacent displacement sensor group also presents the associated accelerated displacement trend, the status of the local abnormal event of the accelerated displacement trend is maintained. This shows that when the sensor itself has no fault and the surrounding sensors also show similar accelerated trend, the accelerated displacement trend is confirmed as a real local abnormal event.

[0169] In some preferred embodiments, suppose a displacement sensor group A within the deep foundation pit monitoring area suddenly reports a significant accelerated displacement trend at a certain time point. The system will first monitor the continuity and stability of the displacement data stream of the displacement sensor group A in real time. If the monitoring finds that its data stream has intermittent interruptions or sudden jumps in data values, the system will immediately start the displacement sensor self-diagnosis program to check the power supply, communication link and internal state of the displacement sensor group A. Specifically, if the self-diagnosis program reports that the communication link of the displacement sensor group A has a fault, and at the same time, through cross comparison, it is found that the displacement data of displacement sensor groups B and C adjacent to the displacement sensor group A are normal and do not show an accelerated displacement trend, then the system will determine that the abnormal data of the displacement sensor group A is a displacement fluctuation caused by sensor failure, and exclude it from the local abnormal event, thereby avoiding false positives. Conversely, if the self-diagnosis result of the displacement sensor group A shows that it is working normally, and the cross comparison result shows that the adjacent displacement sensor groups B and C also show an accelerated displacement trend associated with the displacement sensor group A, then the system will maintain the accelerated displacement trend of the displacement sensor group A as a local abnormal event state, and continue subsequent linkage search and warning generation, ensuring timely response to real deep foundation pit instability risks.

[0170] The application further provides a building safety data analysis method based on a construction database, which comprises the following steps:

[0171] receiving a displacement data stream of a displacement sensor group in real time, and segmenting and buffering the displacement data stream of the displacement sensor group;

[0172] calculating a data packet loss rate and a short-term fluctuation amplitude of each segment of the displacement data stream of the displacement sensor group;

[0173] setting a short-time window and a long-time window;

[0174] judging whether the data packet loss rate or the short-term fluctuation amplitude in the short-time window exceeds a preset first threshold value, and marking a transient abnormality according to the judgment result;

[0175] judging whether the occurrence frequency or the duration of the transient abnormality in the long-time window exceeds a preset second threshold value, and marking a persistent abnormality according to the judgment result;

[0176] deciding whether to trigger a displacement sensor failure warning according to the marking result of the transient abnormality or the persistent abnormality.

[0177] Specifically, the real-time receiving of the displacement data stream of the displacement sensor group refers to the system continuously obtaining the displacement data generated by each displacement sensor group. Segmenting and buffering the displacement data stream of the displacement sensor group can be understood as segmenting and temporarily storing the continuously arriving data stream according to a preset time length or data amount for subsequent data processing and analysis. For example, the data can be buffered and segmented every minute or every 100 data packets collected.

[0178] Among them, the data packet loss rate of each displacement sensor group is calculated by segmenting the displacement data stream, which refers to the difference between the expected number of data packets received and the actual number of data packets received within a certain data stream segment, expressed in percentage. A high data packet loss rate usually indicates a problem with the communication link. The short-term fluctuation amplitude can be understood as the range of displacement data values within a certain data stream segment or the degree of dispersion within a short period of time, which can be measured by calculating the standard deviation, mean absolute deviation, or difference between maximum and minimum values. A large short-term fluctuation amplitude may indicate noise or instability in the sensor itself.

[0179] In practical applications, a short time window and a long time window are set, the purpose of which is to capture both transient data stream anomalies and persistent data stream anomalies. The short time window is usually short, for example, a few seconds to a few minutes, used to quickly respond to sudden data quality problems. The long time window is relatively longer, for example, a few minutes to a few hours, used to accumulate and evaluate the persistence and frequency of data quality problems.

[0180] Further, it is determined whether the data packet loss rate or the short-term fluctuation amplitude within the short time window exceeds a preset first threshold, and the transient anomaly is marked according to the determination result. The first threshold is a critical value set for the data packet loss rate and the short-term fluctuation amplitude, and once any indicator exceeds this threshold within the short time window, it is determined to be a transient anomaly. For example, if the data packet loss rate within the short time window exceeds 5% or the short-term fluctuation amplitude exceeds 0.1 mm, it is marked as a transient anomaly.

[0181] On this basis, it is determined whether the frequency or duration of the transient anomaly within the long time window exceeds a preset second threshold, and the persistent anomaly is marked according to the determination result. The second threshold is set for the cumulative effect of the transient anomaly, aiming to identify those anomalies that are not serious individually but occur frequently or last for a long time. For example, if the transient anomaly occurs more than 3 times or lasts for more than 10 minutes within the long time window, it is marked as a persistent anomaly.

[0182] Finally, according to the marking result of the transient anomaly or the persistent anomaly, it is determined whether to trigger a displacement sensor fault warning. This means that if a transient anomaly or a persistent anomaly is detected, the system will issue a warning, indicating that there may be a displacement sensor fault, prompting the operation and maintenance personnel to check and maintain.

[0183] In some preferred embodiments, it is assumed that a group of displacement sensors in a deep foundation pit monitoring area is continuously transmitting displacement data. The system receives the displacement data stream of the group of displacement sensors in real time and caches it in segments of one minute each.

[0184] At a certain moment, the system calculates that the packet loss rate in the current one-minute segment is 8%, while the first preset threshold is 5%. Since 8% exceeds 5%, the system immediately marks it as a transient anomaly. At the same time, the system also calculates that the short-term fluctuation amplitude of the segment is 0.2 mm, while the first preset threshold is 0.15 mm. Since 0.2 mm exceeds 0.15 mm, it further confirms the occurrence of a transient anomaly.

[0185] The system continues to monitor and finds that similar transient anomalies occur 5 times in different one-minute segments within the next one hour (long time window), while the second preset threshold is 3 times. In addition, the cumulative duration of these transient anomalies reaches 20 minutes, while the second preset threshold is 10 minutes. Given that the frequency and duration of transient anomalies exceed the second threshold, the system determines that this is a persistent anomaly.

[0186] Accordingly, according to the marking result of the persistent anomaly, the system immediately triggers a displacement sensor fault warning and notifies the operation and maintenance personnel that the group of displacement sensors may have a fault. After receiving the warning, the operation and maintenance personnel can quickly check the group of displacement sensors, such as checking its power supply, communication link or internal state, so as to timely eliminate the fault, ensure the accuracy and reliability of subsequent displacement data, and avoid affecting the judgment of the actual displacement trend of the deep foundation pit due to sensor failure.

[0187] The present application further proposes that the step of receiving the displacement data stream of the group of displacement sensors in real time and segmenting and caching the displacement data stream of the group of displacement sensors comprises:

[0188] receiving the displacement data stream of the group of displacement sensors in real time;

[0189] detecting the wireless signal strength or multipath effect of the displacement data stream of the group of displacement sensors and obtaining the real-time signal quality;

[0190] when the wireless signal strength is lower than the preset strength threshold or the multipath effect is enhanced, starting the adaptive data receiving mode;

[0191] In the adaptive data receiving mode, the standby communication link is enabled or the data transmission protocol is adjusted to improve the stability of the displacement data stream of the displacement sensor group;

[0192] According to the real-time signal quality, the segment buffer strategy of the displacement data stream of the displacement sensor group is dynamically adjusted to improve the continuity of the displacement data stream of the displacement sensor group;

[0193] The received data packet is integrity checked;

[0194] For incomplete or incorrect data packets, retransmission request or local data interpolation recovery is performed to improve the continuity of the displacement data stream of the displacement sensor group;

[0195] The displacement data stream of the displacement sensor group is segmented and buffered.

[0196] Specifically, the real-time receiving of the displacement data stream of the displacement sensor group means that the system continuously receives the displacement data generated by each displacement sensor group in the deep foundation pit monitoring area. These data are usually transmitted in the form of data packets through a wireless communication network. Among them, the wireless signal strength or multipath effect of the displacement data stream of the displacement sensor group is detected, and the real-time signal quality is obtained. It can be understood that during data reception, the system will monitor the quality parameters of the wireless communication link synchronously, such as received signal strength indication, signal-to-noise ratio, and the degree of signal fading and distortion caused by multipath propagation. These parameters comprehensively reflect the real-time signal quality of current data transmission. In actual application, when the wireless signal strength is lower than the preset strength threshold or the multipath effect is enhanced, the system will automatically start the adaptive data receiving mode. This mode aims to deal with poor communication environment and ensure the reliability of data transmission.

[0197] In the adaptive data receiving mode, the standby communication link can be enabled, such as switching from the main wireless channel to the auxiliary wireless channel, or switching from wireless communication to the wired standby link (if available). At the same time, the data transmission protocol can also be adjusted, such as reducing the data transmission rate, increasing the error correction coding redundancy, or using more robust modulation and demodulation method, to improve the stability of the displacement data stream of the displacement sensor group. Further, according to the real-time signal quality, the system will dynamically adjust the segment buffer strategy of the displacement data stream of the displacement sensor group. For example, when the signal quality is poor, the size of the buffer segment or the buffer time can be appropriately increased to cope with the delay or intermittent interruption of data transmission, thereby improving the continuity of the displacement data stream of the displacement sensor group.

[0198] In addition, integrity checking of the received data packets is a key step to ensure data accuracy. This is usually achieved through a cyclic redundancy check (CRC) or other checksum algorithm to detect errors in the data during transmission. For incomplete or erroneous data packets, the system will request retransmission, requiring the sender to resend the missing or damaged data packets. If retransmission is not feasible or efficient, local data interpolation recovery techniques can be used to estimate and fill in missing data points based on the previous and subsequent normal data points, to improve the continuity of the displacement data stream of the displacement sensor group. Finally, the displacement data stream processed through the above processes will be segmented and cached, providing a stable, continuous and high-quality data basis for subsequent fault warning analysis.

[0199] In some preferred embodiments, it is assumed that the displacement data stream of a certain displacement sensor group in the deep foundation pit monitoring area is transmitted through a wireless network. When the monitoring system detects that the wireless signal strength of the displacement sensor group suddenly drops from -60 dBm to -85 dBm, accompanied by significant enhancement of multipath effect, the system will immediately start the adaptive data receiving mode. In this mode, the system first tries to switch the communication link of the displacement sensor group from the main 2.4 GHz frequency band to the standby 5.8 GHz frequency band to avoid interference in the current frequency band. If the signal quality is still not ideal after switching, the system will further adjust the data transmission protocol, such as reducing the sending rate of data packets from 100 packets per second to 50 packets per second, and increasing the redundancy of forward error correction code to improve the anti-loss ability of data packets. At the same time, the segmented caching strategy will also be dynamically adjusted, extending the duration of each cache segment from 5 seconds to 10 seconds to tolerate longer instantaneous network interruptions. During data reception, each data packet is subjected to CRC checking. Once a data packet is found to fail the check, the system will immediately initiate a retransmission request to the sender. If the retransmission request fails to succeed within the specified time, the system will estimate and recover the missing displacement data using linear interpolation or polynomial interpolation methods based on the successfully received data points before and after the missing data. Through this series of adaptive receiving, transmission and recovery mechanisms, even in harsh communication conditions, the displacement data stream of the displacement sensor group can still maintain high stability and continuity, ensuring the accuracy of subsequent fault warning analysis.

[0200] Reference Figure 2 The application further proposes a building safety data analysis system based on a construction database, applied to a building safety data analysis method based on a construction database. The system comprises:

[0201] A preset module is configured to group displacement sensors in a deep foundation pit monitoring area, and to preset risk propagation correlation relationships between displacement sensor groups according to the geological conditions of the deep foundation pit;

[0202] a processing module configured to continuously acquire displacement data of each displacement sensor group and calculate an instantaneous change rate of the displacement data;

[0203] an identification module configured to identify that any displacement sensor group has entered an accelerating displacement trend based on the instantaneous change rate of the displacement data satisfying a set change characteristic, and mark the accelerating displacement trend as a local abnormal event;

[0204] a search module configured to, based on the local abnormal event, perform a linkage search on displacement sensor groups associated with the local abnormal event according to a preset risk propagation correlation in an incremental time window and spatial range, the linkage search being used to discover whether the associated displacement sensor groups present an accelerating displacement trend;

[0205] a warning generation module configured to, if the linkage search discovers that multiple displacement sensor groups having the risk propagation correlation all present an accelerating displacement trend, aggregate a regional linkage instability warning;

[0206] When the preset risk propagation correlation fails to reflect the deep foundation pit geological conditions, the step of aggregating the regional linkage instability warning comprises:

[0207] identifying the local abnormal event;

[0208] starting an omnidirectional adjacent group search, the omnidirectional adjacent group search being used to send a probe signal to all displacement sensor groups physically adjacent to the displacement sensor group where the local abnormal event occurs, to find whether a corresponding accelerating displacement trend also appears in a time period after a time point immediately following occurrence of the local abnormal event and mark as a subsequent local abnormal event;

[0209] For any subsequent local abnormal event found in the omnidirectional adjacent group search, calculating a spatio-temporal correlation degree between the subsequent local abnormal event and the local abnormal event, the spatio-temporal correlation degree comprehensively considering a time interval and a spatial distance between the subsequent local abnormal event and the local abnormal event;

[0210] establishing a candidate risk propagation path according to the spatio-temporal correlation degree, the candidate risk propagation path being used to infer a risk propagation direction;

[0211] If a risk propagation direction corresponding to a certain candidate risk propagation path is repeatedly verified in actual data, the risk propagation direction is marked as a dynamic candidate path, and the priority of the dynamic candidate path in subsequent linkage scanning is improved;

[0212] If multiple displacement sensor groups associated along the dynamic candidate path are found to present an accelerating displacement trend in a specific spatio-temporal range, a regional linkage instability warning is aggregated.

[0213] Specifically, the preset module can be a configuration management unit responsible for receiving geological survey data, historical settlement data and expert experience, logically dividing the deep foundation pit monitoring area, and classifying displacement sensors that are physically adjacent or similar in geological conditions to form a displacement sensor group. At the same time, this module is also responsible for establishing and maintaining the risk propagation model between groups, such as using graph theory or probability model to represent the possibility and direction of displacement anomaly propagation between different groups.

[0214] Among them, the processing module can be a data acquisition and processing unit that receives raw displacement data from each displacement sensor group in real time through wireless or wired network. The module pre-processes the received data, including data cleaning, denoising and format conversion, and calculates the displacement change speed of each displacement sensor group in a short time, i.e. the instantaneous change rate, using difference, moving average and other algorithms.

[0215] In practical application, the identification module can be an anomaly detection engine that compares the instantaneous change rate calculated by the processing module with the preset threshold or pattern. When the instantaneous change rate continuously exceeds a certain critical value for a certain period of time or shows a specific nonlinear growth pattern, the identification module will judge that the displacement sensor group has entered an accelerated displacement trend and mark it as a local abnormal event that needs attention.

[0216] Further, the search module can be a risk diffusion analyzer that is activated after the identification module reports a local abnormal event. It uses the risk propagation relationship established by the preset module to start from the group where the local abnormal event occurs, gradually expand the search range (spatially) and extend the observation time (temporally) to detect whether the associated groups also show an accelerated displacement trend, so as to judge whether the risk is spreading.

[0217] Among them, the early warning generation module can be a decision support system that receives the search results of the search module. When multiple displacement sensor groups on the risk propagation path are confirmed to show an accelerated displacement trend at the same time, the early warning generation module will integrate these information to judge the risk of regional instability and aggregate a regional joint instability warning. The warning can include risk level, possible impact range and recommended measures, etc.

[0218] The above disclosed content is only the preferred feasible embodiment of the present application, and is not limited to the protection scope of the present application, so any equivalent technical changes made according to the content of the present application specification and drawings are included in the protection scope of the present application, and furthermore, the elements can be updated as technology develops.

Claims

1. A construction safety data analysis method based on a construction database, characterized by, The method comprises the following steps: Grouping displacement sensors in the monitoring area of the deep foundation pit, and presetting risk propagation correlation between each displacement sensor group according to the geological conditions of the deep foundation pit; Continuously acquiring displacement data of each displacement sensor group, and calculating instantaneous change rate of the displacement data; Based on the fact that the instantaneous change rate of the displacement data meets the set change characteristics, it is identified that any displacement sensor group has entered an accelerated displacement trend, and the accelerated displacement trend is marked as a local abnormal event; Based on the local abnormal event, according to the preset risk propagation correlation, the displacement sensor groups associated with the local abnormal event are searched in an incremental time window and spatial range, and the linkage search is used to find out whether the associated displacement sensor groups present an accelerated displacement trend; If the linkage search finds that multiple displacement sensor groups with risk propagation correlation all present an accelerated displacement trend, a regional linkage instability early warning is generated; When the preset risk propagation correlation fails to reflect the geological conditions of the deep foundation pit, the step of generating the regional linkage instability early warning comprises: Identifying the local abnormal event; Starting an omnidirectional adjacent group search, which is used to send a probe signal to all displacement sensor groups physically adjacent to the displacement sensor group where the local abnormal event occurs, to find out whether a corresponding accelerated displacement trend also occurs in a time period after the time point immediately following the occurrence of the local abnormal event, and mark it as a subsequent local abnormal event; For any subsequent local abnormal event found in the omnidirectional adjacent group search, the spatio-temporal correlation degree between the subsequent local abnormal event and the local abnormal event is calculated, which comprehensively considers the time interval and spatial distance between the subsequent local abnormal event and the local abnormal event; According to the spatio-temporal correlation degree, a candidate risk propagation path is established, which is used to infer the risk propagation direction; If the risk propagation direction corresponding to a certain candidate risk propagation path is repeatedly verified in actual data, the risk propagation direction is marked as a dynamic candidate path, and the priority of the dynamic candidate path in subsequent linkage scanning is improved; If multiple displacement sensor groups associated along the dynamic candidate path are found to present an accelerated displacement trend within a certain spatio-temporal range, a regional linkage instability early warning is generated.

2. The construction safety data analysis method based on a construction database according to claim 1, wherein, The method further comprises: Generating corresponding regional linkage instability early warning information according to the generated regional linkage instability early warning; Real-time acquisition of dynamic environmental data of the deep foundation pit construction site, including real-time rainfall, surrounding construction vibration intensity and underground water pumping rate change; Correlation analysis of the dynamic environmental data and the regional linkage instability early warning information; According to the correlation analysis result, the urgency of the regional linkage instability early warning is corrected or the potential impact range of the regional linkage instability early warning is enhanced.

3. The construction safety data analysis method based on a construction database according to claim 2, characterized by, The regional linkage instability early warning information includes a unique identifier of the early warning, occurrence time, occurrence location, early warning type and initial risk level, which is used to improve the standardization of subsequent correlation analysis.

4. The construction safety data analysis method based on a construction database according to claim 1, wherein, The step of grouping displacement sensors in the deep foundation pit monitoring area and presetting the risk propagation correlation relationship between the displacement sensor groups according to the geological conditions of the deep foundation pit comprises: Real-time acquisition of geological monitoring data of the deep foundation pit construction site, the geological monitoring data indicating geological condition changes; According to the geological monitoring data, identify the geological condition change event; According to the geological condition change event, evaluate the influence of the geological condition change on the division of the displacement sensor groups; According to the evaluation result, adjust the division of the displacement sensor groups of the affected deep foundation pit monitoring area; According to the adjusted displacement sensor group division and the geological condition change, update the risk propagation correlation relationship between the displacement sensor groups; The updated displacement sensor group division and its corresponding risk propagation correlation relationship are used in subsequent steps.

5. The construction safety data analysis method based on a construction database according to claim 1, wherein, The step of identifying that any displacement sensor group has entered an accelerating displacement trend and marking the accelerating displacement trend as a local abnormal event comprises: Real-time acquisition of local environmental data corresponding to the position of the displacement sensor group; Matching the local environmental data with the identified accelerating displacement trend; If the matching result shows that the accelerating displacement trend is consistent with the non-structural displacement response characteristics caused by environmental interference, the warning priority of the accelerating displacement trend is reduced; If the matching result shows that the correlation degree of the accelerating displacement trend and the environmental interference is low, the local abnormal event state of the accelerating displacement trend is maintained.

6. The construction safety data analysis method based on a construction database according to claim 1, wherein, The step of identifying that any displacement sensor group has entered an accelerating displacement trend and marking the accelerating displacement trend as a local abnormal event comprises: Identify the geological horizon where the displacement sensor group is located; Acquire the current construction stage information; Acquire the environmental conditions corresponding to the position of the displacement sensor group; According to the geological horizon, the current construction stage information and the environmental conditions, adjust the judgment threshold and duration standard for identifying the accelerating displacement trend; When the displacement data of the displacement sensor group meets the adjusted judgment threshold and duration standard, mark the accelerating displacement trend as a local abnormal event.

7. The construction safety data analysis method based on a construction database according to claim 1, wherein, The step of identifying that any displacement sensor group has entered an accelerating displacement trend and marking the accelerating displacement trend as a local abnormal event comprises: Real-time monitoring of the continuity and stability of the displacement data stream of the displacement sensor group; When the monitoring finds that the displacement data stream of the displacement sensor group has intermittent interruptions, sudden jumps in data values or long-term deviation from the normal working range, start the displacement sensor self-diagnosis program to check the power supply, communication link and internal state of the displacement sensor group, and obtain the abnormal displacement sensor group; Cross-comparison of the displacement data of the abnormal displacement sensor group and the adjacent displacement sensor group; If the cross-comparison result shows that the displacement data of the adjacent displacement sensor group is normal and does not show the corresponding accelerating displacement trend, mark the abnormality as displacement fluctuation caused by displacement sensor failure and exclude it from the local abnormal event; If the self-diagnosis result shows that the displacement sensor group is working normally, and the cross-comparison result shows that the adjacent displacement sensor group is an associated accelerating displacement trend, the local abnormal event state of the accelerating displacement trend is maintained.

8. The construction safety data analysis method based on a construction database according to claim 7, wherein, The method comprises: Real-time receive displacement sensor group displacement data stream, and segment cache displacement sensor group displacement data stream; Calculate the packet loss rate and short-term fluctuation amplitude of each displacement sensor group displacement data stream segment; Set short and long time windows; Determine whether the packet loss rate or short-term fluctuation amplitude in the short time window exceeds the preset first threshold, and mark the transient abnormality according to the determination result; Determine whether the occurrence frequency or duration of transient abnormality in the long time window exceeds the preset second threshold, and mark the persistent abnormality according to the determination result; According to the marking result of transient abnormality or persistent abnormality, decide whether to trigger displacement sensor fault warning.

9. The construction safety data analysis method based on a construction database according to claim 8, wherein, The step of real-time receiving displacement sensor group displacement data stream and segment caching displacement sensor group displacement data stream includes: Real-time receive displacement sensor group displacement data stream; Detect the wireless signal strength or multipath effect of the displacement sensor group displacement data stream, and obtain the real-time signal quality; When the wireless signal strength is lower than the preset strength threshold or the multipath effect is enhanced, start the adaptive data receiving mode; In the adaptive data receiving mode, enable the standby communication link or adjust the data transmission protocol to improve the stability of the displacement sensor group displacement data stream; According to the real-time signal quality, dynamically adjust the segment caching strategy of the displacement sensor group displacement data stream to improve the continuity of the displacement sensor group displacement data stream; Perform integrity check on the received data packet; For incomplete or incorrect data packets, perform retransmission request or use local data interpolation recovery to improve the continuity of the displacement sensor group displacement data stream; Segment cache displacement sensor group displacement data stream.

10. A construction safety data analysis system based on a construction database, applied to a construction safety data analysis method based on a construction database according to claim 1, characterized in that, The system comprises: A preset module groups displacement sensors in a deep foundation pit monitoring area, and presets risk propagation correlation between displacement sensor groups according to the geological conditions of the deep foundation pit; A processing module continuously obtains displacement data of each displacement sensor group and calculates the instantaneous change rate of the displacement data; An identification module identifies that any displacement sensor group has entered an accelerated displacement trend based on the fact that the instantaneous change rate of the displacement data meets a set change characteristic, and marks the accelerated displacement trend as a local abnormal event; A search module performs a linkage search on displacement sensor groups associated with the local abnormal event based on the local abnormal event according to a preset risk propagation correlation, in an incremental time window and spatial range, and the linkage search is used to find out whether the associated displacement sensor groups present an accelerated displacement trend; An early warning generation module generates a regional linkage instability early warning if the linkage search finds that multiple displacement sensor groups with risk propagation correlation all present an accelerated displacement trend; When the preset risk propagation correlation fails to reflect the geological conditions of the deep foundation pit, the step of generating a regional linkage instability early warning includes: Identify the local abnormal event; initiating an omnidirectional neighboring group search, the omnidirectional neighboring group search being configured to send a probe signal to all displacement sensor groups physically adjacent to the displacement sensor group where the local anomaly event occurs, to search for whether a corresponding accelerated displacement trend also occurs within a time period after a time point immediately following occurrence of the local anomaly event, and to mark as a subsequent local anomaly event; for any subsequent local anomaly event found in the omnidirectional neighboring group search, calculating a spatiotemporal correlation degree between the subsequent local anomaly event and the local anomaly event, the spatiotemporal correlation degree comprehensively considering a time interval and a spatial distance between occurrence of the subsequent local anomaly event and the local anomaly event; according to the spatiotemporal correlation degree, establishing a candidate risk propagation path, the candidate risk propagation path being configured to infer a risk propagation direction; if the risk propagation direction corresponding to a certain candidate risk propagation path is repeatedly verified in actual data, marking the risk propagation direction as a dynamic candidate path, and promoting a priority of the dynamic candidate path in subsequent joint scanning; if multiple displacement sensor groups associated along the dynamic candidate path are found to present an accelerated displacement trend within a specific spatiotemporal range, generating a regional joint instability early warning by aggregation.

Images