Deep foundation pit monitoring method based on BIM-physical model hybrid simulation

Abstract

The invention provides a deep foundation pit monitoring method based on BIM-physical model hybrid simulation. The method comprises the steps that real-time monitoring data and BIM model parameters of a deep foundation pit are collected; inputting a first model parameter in the BIM model parameters as an initial geometric condition into the initial physical model for simulation calculation to obtain first simulation data, and verifying the first simulation data based on the real-time monitoring data to obtain a verification result index; optimizing the soil mass mechanical parameters in the initial physical model based on the verification result index until the verification result index output in the optimization process meets a preset requirement, and obtaining an optimized physical model; simulating the construction process of the deep foundation pit on the basis of the optimized physical model in combination with a second model parameter in the BIM model parameters, and outputting second simulation data; and performing monitoring and early warning on the deep foundation pit based on the deep foundation pit knowledge graph in combination with the real-time monitoring data and the second simulation data to obtain a monitoring and early warning result. According to the invention, comprehensive monitoring of the deep foundation pit is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of deep foundation pit monitoring, and particularly relates to a deep foundation pit monitoring method based on BIM-physical model hybrid simulation. BACKGROUND

[0002] In the process of urban underground space development, the construction safety of deep foundation pit engineering has always been the focus of attention in the field of engineering construction due to the complex geological conditions, sensitive surrounding environment and other characteristics. During the excavation and subsequent support of the deep foundation pit, problems such as deformation of the enclosure structure, settlement of the surrounding soil, and change of the underground water level are prone to occur. If timely intervention measures are not taken, serious safety accidents such as foundation pit collapse and surrounding building cracking may occur. Therefore, it is crucial to implement accurate and efficient monitoring of deep foundation pits.

[0003] In the prior art, various automatic monitoring methods have been formed for deep foundation pit monitoring, among which the automatic monitoring system based on sensor network is widely used. This method arranges various sensors such as displacement sensors, stress sensors, and osmotic pressure sensors at key positions such as the enclosure structure of the foundation pit, the surrounding soil, and adjacent buildings, collects real-time monitoring data, and sends the data to the monitoring platform through a data transmission module to realize dynamic monitoring of various parameters during the construction of the deep foundation pit.

[0004] However, the automatic monitoring system based on sensor network has a major drawback, which is the spatial limitation of monitoring data. Due to the limitations of engineering cost, construction conditions and other factors, the number and position of sensors can only be arranged at limited key points, resulting in monitoring data that only reflects the state of local points and cannot fully present the mechanical response and deformation characteristics of the entire deep foundation pit and the region where sensors are not arranged. When abnormal deformation or stress concentration occurs in the region where sensors are not arranged, the system has difficulty in early warning, which may delay the best intervention opportunity and pose a hidden danger to engineering safety. SUMMARY

[0005] The present application provides a deep foundation pit monitoring method based on BIM-physical model hybrid simulation to realize comprehensive monitoring of deep foundation pits.

[0006] In a first aspect, the present application provides a deep foundation pit monitoring method based on BIM-physical model hybrid simulation, comprising:

[0007] Based on the sensor network arranged in the deep foundation pit to collect real-time monitoring data of the deep foundation pit, and based on the constructed deep foundation pit building information BIM model to extract BIM model parameters of the deep foundation pit;

[0008] a first simulation data is obtained by inputting a first model parameter in the BIM model parameters as an initial geometric condition into an initial physical model for simulation calculation, and a verification result index is obtained by verifying the first simulation data based on the real-time monitoring data;

[0009] a physical model is optimized based on the verification result index until a verification result index output by the physical model in the optimization process meets a preset requirement, and an optimized physical model is obtained;

[0010] a second simulation data is output by simulating a construction process of the deep foundation pit under a current excavation working condition based on the optimized physical model and a second model parameter in the BIM model parameters;

[0011] a monitoring and early warning result is obtained by monitoring and early warning the deep foundation pit based on a pre-constructed deep foundation pit knowledge graph and the real-time monitoring data and the second simulation data.

[0012] In a second aspect, the present application further provides a deep foundation pit monitoring system based on BIM-physical model hybrid simulation, which is applied to the deep foundation pit monitoring method based on BIM-physical model hybrid simulation as described in any one of the first aspect, and the deep foundation pit monitoring system based on BIM-physical model hybrid simulation comprises:

[0013] a collection module configured to collect real-time monitoring data of the deep foundation pit based on a sensor network arranged in the deep foundation pit, and extract BIM model parameters of the deep foundation pit based on a constructed deep foundation pit building information BIM model;

[0014] a simulation verification module configured to input a first model parameter in the BIM model parameters as an initial geometric condition into an initial physical model for simulation calculation, obtain a first simulation data, and obtain a verification result index by verifying the first simulation data based on the real-time monitoring data;

[0015] a physical model optimization module configured to optimize soil mechanical parameters in the initial physical model based on the verification result index until a verification result index output by the physical model in the optimization process meets a preset requirement, and obtain an optimized physical model;

[0016] a construction simulation module configured to output a second simulation data by simulating a construction process of the deep foundation pit under a current excavation working condition based on the optimized physical model and a second model parameter in the BIM model parameters;

[0017] a monitoring and early warning module configured to obtain a monitoring and early warning result by monitoring and early warning the deep foundation pit based on a pre-constructed deep foundation pit knowledge graph and the real-time monitoring data and the second simulation data.

[0018] The application further provides an electronic device, comprising a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby realizing the deep foundation pit monitoring method based on BIM-physical model hybrid simulation as described above.

[0019] The application further provides a non-transitory computer readable storage medium, wherein the storage medium stores a computer software program, and the computer software program is executed by a processor to realize the deep foundation pit monitoring method based on BIM-physical model hybrid simulation as described above.

[0020] The application further provides a computer program product, comprising a computer program, and the computer program is executed by a processor to realize the deep foundation pit monitoring method based on BIM-physical model hybrid simulation as described above.

[0021] The deep foundation pit monitoring method based on BIM-physical model hybrid simulation provided by the embodiments of the application optimizes the physical model parameters by using real-time monitoring data, improves the accuracy of the model, further generates simulation data of positions without sensors based on the optimized physical model, integrates the simulation data with the measured data to obtain a hybrid simulation data set containing comprehensive regional data, and finally the hybrid simulation data set realizes monitoring and early warning of the deep foundation pit as a whole and the unmonitored area. Therefore, by generating simulation data of positions without sensors and integrating the simulation data with the measured data, the data blank of positions without sensors in the prior art is filled, and comprehensive monitoring of the deep foundation pit is realized. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 is a flowchart of the deep foundation pit monitoring method based on BIM-physical model hybrid simulation provided by the application;

[0023] Figure 2 is a structural schematic diagram of the deep foundation pit monitoring system based on BIM-physical model hybrid simulation provided by the application;

[0024] Figure 3 is an embodiment schematic diagram of the electronic device provided by the embodiments of the application. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application.

[0026] In the description of the present application, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can be explicitly or implicitly included one or more of the features. In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically limited.

[0027] In the description of the present application, the term "for example" is used to indicate "as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily interpreted as more preferred or more advantageous than other embodiments. The following description is given in order to enable any person skilled in the art to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that those skilled in the art can recognize that the present application can be implemented without using these specific details. In other examples, well-known structures and processes will not be described in detail to avoid unnecessary details making the description of the present application obscure.

[0028] Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope consistent with the principles and characteristics disclosed.

[0029] Optionally, referring to Figure 1 , Figure 1 is a flowchart of the deep foundation monitoring method based on BIM-physical model hybrid simulation provided by the present application. The execution subject of the deep foundation monitoring method based on BIM-physical model hybrid simulation in the present application is a deep foundation monitoring system. Therefore, the deep foundation monitoring method based on BIM-physical model hybrid simulation comprises:

[0030] Step 10, collecting real-time monitoring data of the deep foundation based on the sensor network arranged in the deep foundation, and extracting BIM model parameters of the deep foundation based on the constructed deep foundation building information BIM model.

[0031] Optionally, the deep foundation monitoring system collects real-time monitoring data of the deep foundation by means of the sensor network arranged in the deep foundation. The sensors are distributed in key positions of the deep foundation according to a scientific layout scheme, which can capture the state changes of the enclosure structure, support structure and soil in real time, and obtain real-time monitoring data of the deep foundation. The real-time monitoring data includes real-time displacement value of the enclosure structure, real-time stress value of the support structure and real-time state of the soil settlement. On the other hand, the BIM model parameters of the deep foundation are accurately extracted based on the constructed deep foundation building information BIM model.

[0032] In an embodiment, in a deep foundation pit engineering, displacement sensors are arranged at different depth positions of the enclosure structure (such as a diaphragm wall), stress sensors are installed at key nodes of the support structure (such as a steel support), and settlement monitoring points are arranged in the soil body around the foundation pit. The sensor network collects real-time displacement values of the enclosure structure at a certain time as 3 mm, real-time stress values of the support structure as 20 MPa, and real-time settlement values of the soil body as 1.5 mm. At the same time, geometric size parameters are extracted from the constructed BIM model of the deep foundation pit, such as the thickness of the diaphragm wall as 800 mm and the depth as 25 m, and the diameter of the steel support as 600 mm.

[0033] Step 20, the first model parameter in the BIM model parameter is input as an initial geometric condition into the initial physical model for simulation calculation to obtain first simulation data, and the first simulation data is verified based on the real-time monitoring data to obtain a verification result index.

[0034] Further, the deep foundation pit monitoring system inputs the first model parameter in the BIM model parameter, that is, the geometric size parameter, as an initial geometric condition into the initial physical model for simulation calculation to obtain first simulation data, wherein the first simulation data includes a first displacement simulation value of the enclosure structure and a first stress simulation value of the support structure. Further, the deep foundation pit monitoring system verifies the first simulation data using real-time monitoring data to obtain a verification result index, specifically as the process of steps 201 to 204.

[0035] In an embodiment, the extracted geometric size parameters such as the thickness of the diaphragm wall as 800 mm, the depth as 25 m, and the diameter of the steel support as 600 mm are input into the initial physical model (such as a finite element analysis model). After simulation calculation, the first displacement simulation value of the enclosure structure is 3.5 mm, and the first stress simulation value of the support structure is 18 MPa. The deep foundation pit monitoring system verifies the first simulation data using the real-time displacement value 3 mm of the enclosure structure and the real-time stress value 20 MPa of the support structure to obtain a verification result index.

[0036] Step 30, based on the verification result index, the soil mechanical parameters in the initial physical model are optimized until the verification result index output by the physical model in the optimization process meets the preset requirement, and an optimized physical model is obtained.

[0037] Further, the deep foundation pit monitoring system optimizes and adjusts the soil mechanical parameters in the initial physical model according to the verification result index, and re-performs simulation calculation and verification by continuously changing the values of the soil mechanical parameters until the verification result index output by the physical model in the optimization process meets the preset requirement, and finally obtains the optimized physical model. In an embodiment, it is assumed that the initial verification result index is 0.8, and the preset requirement is that the verification result index needs to reach 0.9 or above. The deep foundation pit monitoring system finds that the soil mechanical parameters such as the elastic modulus and cohesion of the soil in the initial physical model may have deviations. Therefore, the elastic modulus of the soil is gradually adjusted from 20 MPa to 22 MPa, the cohesion is adjusted from 15 kPa to 16 kPa, and the like. Each time the parameter is adjusted, the new soil mechanical parameters are input into the physical model for simulation calculation to obtain new first simulation data, and the new verification result index is obtained by verification with the real-time monitoring data. After multiple adjustments and calculations, when the soil mechanical parameters are adjusted to an elastic modulus of 23 MPa and a cohesion of 17 kPa, the verification result index reaches 0.92, meeting the preset requirement, and the optimized physical model is obtained at this time.

[0038] In step 40, the construction process of the deep foundation pit under the current excavation working condition is simulated based on the optimized physical model combined with the second model parameter in the BIM model parameter, and second simulation data is output.

[0039] Further, the deep foundation pit monitoring system simulates the construction process of the deep foundation pit under the current excavation working condition by using the optimized physical model combined with the second model parameter in the BIM model parameter, that is, the foundation pit excavation depth and excavation range parameters, and outputs second simulation data, wherein the second simulation data includes second displacement simulation values, second stress simulation values and settlement simulation states of the enclosure structure, the supporting structure and the soil at positions where sensors are not arranged, that is, it covers the related state parameters at positions where sensors are not arranged.

[0040] In an embodiment, the excavation depth of the current deep foundation pit is 10 m, and the excavation range is the east region of the foundation pit. The deep foundation pit monitoring system inputs the foundation pit excavation depth and excavation range parameters into the optimized physical model to simulate the construction process under this excavation working condition. Through simulation calculation, the second simulation data is output, for example, the second displacement simulation value at the top position of the enclosure structure where no displacement sensor is arranged is 2.8 mm; the second stress simulation value at the middle node of the supporting structure where no stress sensor is arranged is 19 MPa; and the settlement simulation state in the south region of the soil where no settlement monitoring point is arranged is 1.2 mm.

[0041] In step 50, the deep foundation pit is monitored and warned based on the pre-constructed deep foundation pit knowledge graph combined with the real-time monitoring data and the second simulation data, and a monitoring and warning result is obtained.

[0042] Further, the deep foundation pit monitoring system is based on a pre-constructed deep foundation pit knowledge graph, which contains knowledge such as characteristics, early warning thresholds, and treatment measures of various abnormal states of the deep foundation pit. The deep foundation pit knowledge graph is combined with real-time monitoring data and second simulation data to comprehensively monitor and early warn the overall state of the deep foundation pit, and obtain a monitoring and early warning result, specifically as the process of steps 501 to 505.

[0043] The embodiment of the present application optimizes the physical model parameters by using real-time monitoring data, improves the accuracy of the model, further generates simulation data of positions where sensors are not arranged based on the optimized physical model, integrates the simulation data with the measured data to obtain a mixed simulation data set containing comprehensive regional data, and finally the mixed simulation data set realizes monitoring and early warning of the deep foundation pit as a whole and the unmonitored area. Therefore, by generating simulation data of the area where sensors are not arranged and integrating the simulation data with the measured data, the data gap in the area where sensors are not arranged in the existing method is filled, and comprehensive monitoring of the deep foundation pit is realized.

[0044] In an embodiment, the process of steps 201 to 204 includes:

[0045] In step 201, real-time displacement monitoring matrices and displacement simulation matrices are respectively constructed based on real-time displacement values and first displacement simulation values.

[0046] Optionally, the deep foundation pit monitoring system respectively constructs real-time displacement monitoring matrices and displacement simulation matrices based on real-time displacement values and first displacement simulation values of the enclosure structure. The real-time displacement monitoring matrices take monitoring points in the enclosure structure as rows and time as columns, and each matrix element accurately records the real-time displacement value of each monitoring point in the enclosure structure at the corresponding time. The displacement simulation matrices also take monitoring points as rows and time as columns, and each element records the first displacement simulation value of each monitoring point in the enclosure structure at the corresponding time.

[0047] Continuing with the above deep foundation pit project, the enclosure structure (underground continuous wall) is provided with three monitoring points, namely monitoring point A, monitoring point B, and monitoring point C, and the monitoring time interval is 1 hour, and a total of three time points are monitored, namely time t1, time t2, and time t3. The real-time displacement values of the enclosure structure monitored in real time are as follows: monitoring point A is 2.8 mm at t1, 3.0 mm at t2, and 3.2 mm at t3; monitoring point B is 2.5 mm at t1, 2.7 mm at t2, and 2.9 mm at t3; and monitoring point C is 3.1 mm at t1, 3.3 mm at t2, and 3.5 mm at t3.

[0048] The real-time displacement monitoring matrix is:

[0049] The first displacement simulation value obtained by the initial physical model simulation is as follows: the monitoring point A is 3.0 mm at t1, 3.2 mm at t2, and 3.4 mm at t3; the monitoring point B is 2.7 mm at t1, 2.9 mm at t2, and 3.1 mm at t3; and the monitoring point C is 3.3 mm at t1, 3.5 mm at t2, and 3.7 mm at t3.

[0050] The displacement simulation matrix is:

[0051] In step 202, the real-time stress monitoring matrix and the stress simulation matrix are respectively constructed based on the real-time stress value and the first stress simulation value.

[0052] Further, the deep foundation pit monitoring system respectively constructs a real-time stress monitoring matrix and a stress simulation matrix based on the real-time stress value and the first stress simulation value of the supporting structure. The real-time stress monitoring matrix takes the monitoring points in the supporting structure as rows and time as columns, and each matrix element records the real-time stress value of each monitoring point in the supporting structure at the corresponding time; the stress simulation matrix also takes the monitoring points as rows and time as columns, and each element records the first stress simulation value of each monitoring point in the supporting structure at the corresponding time.

[0053] In an embodiment, the supporting structure (steel support) is provided with two monitoring points, namely monitoring point D and monitoring point E, and three time points t1, t2 and t3 are monitored. The real-time stress value of the supporting structure monitored in real time is as follows: the monitoring point D is 19 MPa at t1, 20 MPa at t2, and 21 MPa at t3; and the monitoring point E is 18 MPa at t1, 19 MPa at t2, and 20 MPa at t3.

[0054] The real-time stress monitoring matrix is:

[0055] The first stress simulation value is as follows: the monitoring point D is 17 MPa at t1, 18 MPa at t2, and 19 MPa at t3; and the monitoring point E is 16 MPa at t1, 17 MPa at t2, and 18 MPa at t3.

[0056] The stress simulation matrix is:

[0057] In step 203, the displacement deviation degree between the real-time displacement value and the first displacement simulation value of each monitoring point in the supporting structure at each time point is calculated based on the real-time displacement monitoring matrix and the displacement simulation matrix, and the stress deviation degree between the real-time stress value and the first stress simulation value of each monitoring point in the supporting structure at each time point is calculated based on the real-time stress monitoring matrix and the stress simulation matrix.

[0058] Further, for the enclosure, the deep foundation pit monitoring system obtains the displacement deviation degree of each monitoring point at each time through the difference calculation of the corresponding elements in the real-time displacement monitoring matrix and the displacement simulation matrix. For the supporting structure, the deep foundation pit monitoring system also calculates the stress deviation degree of each monitoring point at each time based on the difference of the corresponding elements in the real-time stress monitoring matrix and the stress simulation matrix.

[0059] Optionally, the embodiment of the present application calculates the deviation degree in the relative deviation mode, and therefore, the calculation formula of the deviation degree is (|real-time value-simulation value| / real-time value) x 100%.

[0060] Continuing the above embodiment, for the enclosure monitoring point A, the displacement deviation degree at t1 time is (|2.8-3.0| / 2.8) x 100% ≈ 7.14%; the displacement deviation degree at t2 time is (|3.0-3.2| / 3.0) x 100% ≈ 6.67%; the displacement deviation degree at t3 time is (|3.2-3.4| / 3.2) x 100% ≈ 6.25%. For the monitoring point B, the displacement deviation degree at t1 time is (|2.5-2.7| / 2.5) x 100% = 8%; the displacement deviation degree at t2 time is (|2.7-2.9| / 2.7) x 100% ≈ 7.41%; the displacement deviation degree at t3 time is (|2.9-3.1| / 2.9) x 100% ≈ 6.90%. For the monitoring point C, the displacement deviation degree at t1 time is (|3.1-3.3| / 3.1) x 100% ≈ 6.45%; the displacement deviation degree at t2 time is (|3.3-3.5| / 3.3) x 100% ≈ 6.06%; the displacement deviation degree at t3 time is (|3.5-3.7| / 3.5) x 100% ≈ 5.71%.

[0061] For the supporting structure monitoring point D, the stress deviation degree at t1 time is (|19-17| / 19) x 100% ≈ 10.53%; the stress deviation degree at t2 time is (|20-18| / 20) x 100% = 10%; the stress deviation degree at t3 time is (|21-19| / 21) x 100% ≈ 9.52%. For the monitoring point E, the stress deviation degree at t1 time is (|18-16| / 18) x 100% ≈ 11.11%; the stress deviation degree at t2 time is (|19-17| / 19) x 100% ≈ 10.53%; the stress deviation degree at t3 time is (|20-18| / 20) x 100% = 10%.

[0062] Step 204, verification is performed based on the displacement deviation degree of each monitoring point in the enclosure at each time and the stress deviation degree of each monitoring point in the supporting structure at each time, and a verification result index is obtained.

[0063] Further, the deep foundation pit monitoring system performs verification according to the displacement deviation degree of each monitoring point in the enclosure at each time and the stress deviation degree of each monitoring point in the supporting structure at each time, and obtains a verification result index, specifically as the processes of step 2041 to step 2045.

[0064] The embodiment of the present application can systematize and structure the dispersed real-time monitoring data and simulation data by constructing a matrix, so that the corresponding relationship between the data is more clear and intuitive. By calculating the displacement deviation degree and stress deviation degree of each monitoring point at each time, the differences between the simulation data and the actual monitoring data at different positions and different times can be accurately captured. Finally, the verification result index obtained by comprehensive calculation can comprehensively reflect the degree of coincidence between the initial physical model simulation result and the actual monitoring situation, providing data basis for subsequent optimization of the initial physical model based on the verification result index, and ensuring that the optimized physical model can more accurately simulate the actual state of the deep foundation pit.

[0065] In an embodiment, the process of steps 2041 to 2045 includes:

[0066] Step 2041, based on the displacement deviation degree of each monitoring point in the enclosure structure at each time, combined with the spatial distance of each monitoring point to the center of the foundation pit and the cumulative monitoring time at each time, the displacement space-time correlation deviation value of each monitoring point in the enclosure structure at each time is determined.

[0067] Optionally, the deep foundation pit monitoring system introduces the influence factors of space and time dimensions for the displacement deviation degree of each monitoring point in the enclosure structure at each time. Among them, the spatial factor is the spatial distance of each monitoring point to the center of the foundation pit, the closer the distance, the greater the influence on the overall stability of the foundation pit, and the higher the weight; the time factor is the cumulative monitoring time at each time, the longer the cumulative time, the higher the reference value of the data, and the higher the weight. By multiplying the displacement deviation degree and the two weight factors, the displacement space-time correlation deviation value of each monitoring point at each time is calculated.

[0068] In an embodiment, the enclosure structure has monitoring points A, B, and C, and the spatial distances of the monitoring points to the center of the foundation pit are 10 m, 8 m, and 12 m respectively. The distance weight is set to be inversely proportional to the distance (the closer the distance, the higher the weight), and the distance weights are calculated to be 0.12, 0.15, and 0.10 respectively. The cumulative monitoring times at monitoring times t1, t2, and t3 are 1 h, 2 h, and 3 h respectively, and the time weight is proportional to the cumulative time, and the time weights are 0.1, 0.2, and 0.3 respectively. Therefore, the displacement deviation degree of monitoring point A at time t1 is 7.14%, and the displacement space-time correlation deviation value is 7.14% x 0.12 x 0.1 = 0.086%; the deviation degree at time t2 is 6.67%, and the value is 6.67% x 0.12 x 0.2 = 0.160%; the deviation degree at time t3 is 6.25%, and the value is 6.25% x 0.12 x 0.3 = 0.225%.

[0069] Monitoring point B at t1 time deviation 8%, value = 8% x 0.15 x 0.1 = 0.120%; t2 time 7.41%, value = 7.41% x 0.15 x 0.2 = 0.222%; t3 time 6.90%, value = 6.90% x 0.15 x 0.3 = 0.311%.

[0070] Monitoring point C at t1 time 6.45%, value = 6.45% x 0.10 x 0.1 = 0.065%; t2 time 6.06%, value = 6.06% x 0.10 x 0.2 = 0.121%; t3 time 5.71%, value = 5.71% x 0.10 x 0.3 = 0.171%.

[0071] Step 2042, based on the stress deviation degree of each monitoring point in the supporting structure at each time, combined with the supporting depth of each monitoring point and the cumulative monitoring time at each time, the stress space-time correlation deviation value of each monitoring point in the supporting structure at each time is determined.

[0072] Further, the deep foundation pit monitoring system considers the supporting depth and the cumulative monitoring time two space-time factors for the stress deviation degree of each monitoring point in the supporting structure at each time. The deeper the supporting depth, the greater the load on the supporting structure, the more significant the influence on the stress change, and the higher the weight. The longer the cumulative monitoring time, the more the data can reflect the long-term stress state, and the higher the weight. Multiply the stress deviation degree by these two weight factors to get the stress space-time correlation deviation value of each monitoring point at each time.

[0073] In an embodiment, the supporting structure has monitoring points D and E, and the supporting depths are 15m and 10m respectively. The depth weight is proportional to the depth, and the calculated weights are 0.3 and 0.2 respectively. The time weights of the cumulative monitoring times t1, t2 and t3 are the same as before, which are 0.1, 0.2 and 0.3. Therefore, the stress deviation degree of monitoring point D at t1 time is 10.53%, and the stress space-time correlation deviation value = 10.53% x 0.3 x 0.1 = 0.316%; t2 time 10%, value = 10% x 0.3 x 0.2 = 0.600%; t3 time 9.52%, value = 9.52% x 0.3 x 0.3 = 0.857%.

[0074] Monitoring point E at t1 time 11.11%, value = 11.11% x 0.2 x 0.1 = 0.222%; t2 time 10.53%, value = 10.53% x 0.2 x 0.2 = 0.421%; t3 time 10%, value = 10% x 0.2 x 0.3 = 0.600%.

[0075] Step 2043, based on the displacement spatiotemporal correlation deviation value of each monitoring point in the building envelope at each time and the displacement spatiotemporal correlation deviation average value of all monitoring points, the displacement monitoring point group consistency index of the monitoring point group in the time and space dimensions of the building envelope at each time is determined.

[0076] Further, the deep foundation monitoring system first calculates the average value of the displacement spatiotemporal correlation deviation value of all monitoring points in the building envelope at each time, i.e. the displacement spatiotemporal correlation deviation average value. Then, 1 is subtracted from the proportion of the sum of the absolute values of the difference between the displacement spatiotemporal correlation deviation value of each monitoring point at each time and the average value to the total deviation value, to obtain the displacement monitoring point group consistency index at each time. The closer the index is to 1, the more consistent the displacement deviation of each monitoring point is in the time and space dimensions.

[0077] Continuing the above example, the displacement spatiotemporal correlation deviation value at t1 time is: A=0.086%, B=0.120%, C=0.065%, the average value=(0.086+0.120+0.065)÷3≈0.090%, the sum of the absolute values of the difference is 0.059, the sum of the total deviation values=0.086+0.120+0.065=0.271, and the displacement monitoring point group consistency index=1-(0.059÷0.271)≈0.782. The value at t2 time: A=0.160%, B=0.222%, C=0.121%, the average value≈(0.160+0.222+0.121)÷3≈0.168%, the sum of the absolute values of the difference is 0.109, the sum of the total deviation values is 0.160+0.222+0.121=0.503, and the displacement monitoring point group consistency index=1-(0.109÷0.503)≈0.783. The value at t3 time: A=0.225%, B=0.311%, C=0.171%, the average value≈(0.225+0.311+0.171)÷3≈0.236%, the sum of the absolute values of the difference is 0.151, the sum of the total deviation values is 0.225+0.311+0.171=0.707, and the displacement monitoring point group consistency index=1-(0.151÷0.707)=0.786.

[0078] Step 2044, based on the stress spatiotemporal correlation deviation value of each monitoring point in the supporting structure at each time and the stress spatiotemporal correlation deviation average value of all monitoring points, the stress monitoring point group consistency index of the monitoring point group in the time and space dimensions of the supporting structure at each time is determined.

[0079] Further, the deep foundation pit monitoring system calculates the average value of the stress space-time correlation deviation of all monitoring points of the supporting structure at each time, and then obtains the stress monitoring point group consistency index at each time by subtracting the proportion of the sum of the absolute values of the difference between the stress space-time correlation deviation value of each monitoring point at each time and the average value from 1. The closer the index is to 1, the better the consistency of the stress deviation of each monitoring point in the space-time dimension.

[0080] In an embodiment, the stress space-time correlation deviation value at t1 time: D = 0.316%, E = 0.222%, the average value = (0.316 + 0.222) ÷ 2 ≈ 0.269%, the sum of the absolute values of the difference is 0.094, the sum of the total deviation values = 0.316 + 0.222 = 0.538, and the stress monitoring point group consistency index = 1 - (0.094 ÷ 0.538) ≈ 0.825.

[0081] The value at t2 time: D = 0.600%, E = 0.421%, the average value ≈ (0.600 + 0.421) ÷ 2 ≈ 0.511%, the sum of the absolute values of the difference is 0.179, the sum of the total deviation values = 0.600 + 0.421 = 1.021, and the stress monitoring point group consistency index = 1 - (0.179 ÷ 1.021) ≈ 0.825.

[0082] The value at t3 time: D = 0.857%, E = 0.600%, the average value ≈ (0.857 + 0.600) ÷ 2 ≈ 0.729%, the sum of the absolute values of the difference is 0.257, the sum of the total deviation values = 0.857 + 0.600 = 1.457, and the stress monitoring point group consistency index = 1 - (0.257 ÷ 1.457) ≈ 0.824.

[0083] Step 2045 verifies based on the displacement monitoring point group consistency index at each time and the stress monitoring point group consistency index at each time to obtain a verification result index.

[0084] Further, the deep foundation pit monitoring system verifies the displacement monitoring point group consistency index at each time and the stress monitoring point group consistency index at each time to obtain a verification result index, specifically as the process of steps 20451 to 20454.

[0085] The embodiment of the application corrects the displacement deviation degree and the stress deviation degree by the spatial distance, the supporting depth and the cumulative monitoring time, obtains the space-time correlation deviation value closer to the actual engineering scene, and therefore the monitoring point group consistency index calculated can reflect the consistency degree of the deviation of different monitoring points in the space-time dimension, and the verification result index obtained through the weighted average comprehensively considers the deviation characteristics of the enclosure structure and the supporting structure at different times, more comprehensively quantifies the fitting degree of the initial physical model simulation data and the real-time monitoring data, and improves the accuracy and rationality of the model verification in deep foundation pit monitoring.

[0086] In an embodiment, the process of step 20451 to step 20454 includes:

[0087] Step 20451, based on the difference value of the displacement consistency index of the enclosure structure at adjacent time points, the displacement deviation evolution trend is determined, and based on the difference value of the stress consistency index of the supporting structure at adjacent time points, the stress deviation evolution trend is determined.

[0088] Optionally, the deep foundation pit monitoring system obtains the displacement monitoring point group consistency index at each time point, and calculates the difference value of the displacement monitoring point group consistency index at adjacent two time points. According to the positive and negative and size of the difference value, the displacement deviation evolution trend is judged, if the difference value is positive, it means that the consistency of the displacement deviation is improving, the deviation evolution trend is good, if the difference value is negative, it means that the consistency of the displacement deviation is decreasing, the deviation evolution trend is poor, and the larger the absolute value of the difference value is, the more obvious the trend change is.

[0089] Continuing the above embodiment, it is known that the displacement monitoring point group consistency index at t1 time point is 0.782, at t2 time point is 0.783, and at t3 time point is 0.786. The adjacent time difference value: t2-t1=0.783-0.782=0.001, t3-t2=0.786-0.783=0.003. Both difference values are positive, and the latter difference value is greater than the former difference value, which means that the displacement deviation evolution trend is continuously good, and the good trend is enhanced.

[0090] Further, the deep foundation pit monitoring system obtains the stress monitoring point group consistency index at each time point, and calculates the difference value of the stress monitoring point group consistency index at adjacent two time points. According to the positive and negative and size of the difference value, the stress deviation evolution trend is judged, if the difference value is positive, it means that the consistency of the stress deviation is improving, the deviation evolution trend is good, if the difference value is negative, it means that the consistency of the stress deviation is decreasing, the deviation evolution trend is poor, and the larger the absolute value is, the more obvious the change is.

[0091] Continuing the above embodiment, the stress monitoring point group consistency index at time t1 is 0.825, at time t2 is 0.825, and at time t3 is 0.824. The adjacent time difference: t2-t1=0.825-0.825=0, t3-t2=0.824-0.825=-0.001. The first difference is 0, indicating that the stress deviation consistency from t1 to t2 has no change; the second difference is negative, indicating that the stress deviation consistency from t2 to t3 has slightly decreased, and the stress deviation evolution trend presents a slight deterioration trend.

[0092] In step 20452, based on the enclosure arrangement density of the deep foundation pit BIM model and the displacement space-time correlation deviation value of each monitoring point in the enclosure at each time, the first spatial distribution coincidence degree between the first displacement simulation value and the real-time displacement value of the enclosure is determined.

[0093] Further, the deep foundation pit monitoring system extracts the enclosure arrangement density from the deep foundation pit BIM model, which reflects the spatial distribution density of the enclosure monitoring points. Combined with the displacement space-time correlation deviation value of each monitoring point in the enclosure at each time, the weighted average value of the displacement space-time correlation deviation value is calculated (with the arrangement density as the weight), and then 1 is subtracted from the weighted average value to obtain the first spatial distribution coincidence degree. The closer the value is to 1, the more consistent the spatial distribution of the first displacement simulation value and the real-time displacement value is.

[0094] In an embodiment, the enclosure arrangement density is extracted from the deep foundation pit BIM model, and the arrangement densities of the regions where monitoring points A, B, and C are located are 0.8, 1.0, and 0.6 respectively (the higher the density value, the more concentrated the monitoring points are), and the weights are distributed in proportion to the density. The total density is 0.8+1.0+0.6=2.4, and the weights of each point are 0.8 / 2.4≈0.333, 1.0 / 2.4≈0.417, and 0.6 / 2.4≈0.25 respectively.

[0095] For the weighted average value of the displacement space-time correlation deviation value at time t1, it is 0.086%×0.333+0.120%×0.417+0.065%×0.25≈0.029%+0.050%+0.016%≈0.095%, and the first spatial distribution coincidence degree is 1-0.095%≈0.999.

[0096] For the weighted average value at time t2, it is 0.160%×0.333+0.222%×0.417+0.121%×0.25≈0.053%+0.093%+0.030%≈0.176%, and the coincidence degree is 1-0.176%≈0.998.

[0097] The weighted average value at time t3 is 0.225%*0.333+0.311%*0.417+0.171%*0.25≈0.075%+0.130%+0.043%≈0.248%, and the goodness of fit is 1-0.248%≈0.998.

[0098] In step 20453, based on the support structure spacing of the deep foundation BIM model and the stress space-time correlation deviation value of each monitoring point in the support structure at each time, a second spatial distribution goodness of fit between the first stress simulation value and the real-time stress value of the support structure is determined.

[0099] Further, the deep foundation monitoring system extracts the support structure spacing from the deep foundation BIM model, and the smaller the spacing, the more intensive the support structure. Combined with the stress space-time correlation deviation value of each monitoring point in the support structure at each time, the weighted average value of the stress space-time correlation deviation value is calculated (with the reciprocal of the spacing as the weight, and the smaller the spacing, the greater the weight), and 1 is subtracted from the weighted average value to obtain the second spatial distribution goodness of fit. The closer the value is to 1, the more consistent the spatial distribution of the first stress simulation value and the real-time stress value.

[0100] In an embodiment, the support structure spacing is extracted from the BIM model, and the support structure spacing at the positions of monitoring points D and E is 5m and 8m respectively, and the reciprocal of the spacing is 1 / 5=0.2 and 1 / 8=0.125 respectively. The total reciprocal is 0.2+0.125=0.325, and the weight of each point is 0.2 / 0.325≈0.615 and 0.125 / 0.325≈0.385 respectively.

[0101] The weighted average value of the stress space-time correlation deviation value at time t1 is 0.316%*0.615+0.222%*0.385≈0.194%+0.085%≈0.279%, and the second spatial distribution goodness of fit is 1-0.279%≈0.997.

[0102] The weighted average value at time t2 is 0.600%*0.615+0.421%*0.385≈0.369%+0.162%≈0.531%, and the goodness of fit is 1-0.531%≈0.995.

[0103] The weighted average value at time t3 is 0.857%*0.615+0.600%*0.385≈0.527%+0.231%≈0.758%, and the goodness of fit is 1-0.758%≈0.992.

[0104] In step 20454, based on the displacement deviation evolution trend, the stress deviation evolution trend, the first spatial distribution goodness of fit and the second spatial distribution goodness of fit, a verification result index is obtained.

[0105] Further, the deep foundation pit monitoring system verifies according to the displacement deviation evolution trend, the stress deviation evolution trend, the first spatial distribution coincidence degree and the second spatial distribution coincidence degree to obtain a verification result index, specifically as the process of steps 204541 to 204543.

[0106] The embodiment of the application comprehensively analyzes the deviation of deep foundation pit monitoring data and simulation data from two dimensions of time and space, captures the change characteristics of the deviation over time by determining the evolution trend of displacement and stress deviation, and can timely discover the development trend of the deviation; the embodiment of the application reflects the coincidence degree of the simulation data and the monitoring data in the spatial distribution by calculating the first and second spatial distribution coincidence degrees, considers the influence of the monitoring point arrangement density and the structure spacing, and finally comprehensively weights the time trend and the spatial coincidence degree to obtain the verification result index, which more comprehensively quantifies the simulation effect of the initial physical model, and improves the reliability and effectiveness of the model verification in deep foundation pit monitoring.

[0107] In an embodiment, the process of steps 204541 to 204543 includes:

[0108] In step 204541, the displacement time sequence matching degree is determined based on the displacement deviation evolution trend and the cumulative monitoring time at each time.

[0109] Optionally, the deep foundation pit monitoring system associates the displacement deviation evolution trend with the cumulative monitoring time at each time, and the longer the cumulative monitoring time, the greater the influence weight of the displacement deviation evolution trend at this time on the overall time sequence matching degree. The displacement time sequence matching degree is obtained by multiplying the displacement deviation evolution trend value at each time by the weight of the corresponding cumulative monitoring time and then summing, and the higher the value, the better the matching effect of the displacement deviation on the time sequence.

[0110] Continuing the above embodiment, it is known that the displacement deviation evolution trend is good at t1 (denoted as 1), good at t2 (denoted as 1), and good and the trend is enhanced at t3 (denoted as 1.1). The cumulative monitoring time is 1h at t1, 2h at t2, and 3h at t3, the total time length is 1+2+3=6h, and the time weight at each time is 1 / 6≈0.167, 2 / 6≈0.333, and 3 / 6=0.5 respectively. The displacement time sequence matching degree=1×0.167+1×0.333+1.1×0.5≈0.167+0.333+0.55=1.05 (since the trend is good, the matching degree can be greater than 1).

[0111] In step 204542, the stress time sequence matching degree is determined based on the stress deviation evolution trend and the cumulative monitoring time at each time.

[0112] Further, the deep foundation pit monitoring system combines the stress deviation evolution trend with the cumulative monitoring time at each time, and the longer the cumulative monitoring time, the higher the weight of the stress deviation evolution trend at the corresponding time in the overall time sequence matching degree. The stress time sequence matching degree is calculated by the sum of the product of the stress deviation evolution trend value at each time and the corresponding cumulative monitoring time weight, and the higher the value, the better the matching effect of the stress deviation on the time sequence.

[0113] Continuing the above embodiment, the stress deviation evolution trend is no change at t1 (recorded as 0.95), no change at t2 (recorded as 0.95), and slight deterioration at t3 (recorded as 0.9). The cumulative monitoring time weight is the same as before, t1 is 0.167, t2 is 0.333, and t3 is 0.5. Stress time sequence matching degree = 0.95 × 0.167 + 0.95 × 0.333 + 0.9 × 0.5 ≈ 0.159 + 0.316 + 0.45 = 0.925.

[0114] In step 204543, based on the engineering safety level weight of the deep foundation pit, the displacement time sequence matching degree, the stress time sequence matching degree, the first spatial distribution coincidence degree and the second spatial distribution coincidence degree are combined to obtain a verification result index. The verification result index represents the reliability of the first displacement simulation value and the first stress simulation value.

[0115] Further, the deep foundation pit monitoring system determines the corresponding weight coefficient according to the engineering safety level of the deep foundation pit (for example, the weight coefficient of the first safety level is set to 1.0), and then assigns respective weights to the displacement time sequence matching degree, the stress time sequence matching degree, the first spatial distribution coincidence degree and the second spatial distribution coincidence degree (for example, 0.25, 0.25, 0.25, 0.25 respectively). After multiplying each index by the corresponding weight and summing, multiply by the engineering safety level weight coefficient to obtain the verification result index, which directly reflects the reliability of the first displacement simulation value and the first stress simulation value.

[0116] In an embodiment, assuming that the deep foundation pit engineering safety level is first class, and the engineering safety level weight coefficient is 1.0. The weight of each index is 0.25, the displacement time sequence matching degree is 1.05, the stress time sequence matching degree is 0.925, the average value of the first spatial distribution coincidence degree at t1-t3 is (0.999+0.998+0.998)÷3≈0.998, and the average value of the second spatial distribution coincidence degree is (0.997+0.995+0.992)÷3≈0.995. Verification result index = 1.0 × (1.05 × 0.25 + 0.925 × 0.25 + 0.998 × 0.25 + 0.995 × 0.25) ≈ 1.0 × (0.2625 + 0.2313 + 0.2495 + 0.2488) ≈ 1.0 × 0.9921 = 0.9921.

[0117] The embodiment of the present application highlights the influence of long-term monitoring data on trend judgment by accumulating monitoring time weight, so that the displacement and stress time series matching degree is more in line with the time evolution characteristics of the actual project. At the same time, through the deep foundation engineering safety level weight, the differentiated requirements of model verification accuracy under different safety levels are reflected, so that the verification result is more engineering targeted, and the final verification result index integrates the time series matching degree and the spatial distribution coincidence degree, which can more accurately reflect the reliability of the first displacement simulation value and the first stress simulation value, and effectively improve the authority of model verification in deep foundation monitoring.

[0118] In an embodiment, the process of steps 501 to 505 includes:

[0119] Step 501, based on the entity attribute association rules of the deep foundation knowledge graph, the real-time monitoring data and the second simulation data are respectively mapped with the knowledge graph entity, and the monitoring data mapping result and the simulation data mapping result are obtained.

[0120] Optionally, the deep foundation monitoring system is based on the entity attribute association rules in the pre-constructed deep foundation knowledge graph, which clearly defines the corresponding relationship between different types of data and various entities in the knowledge graph (such as enclosure structure entity, support structure entity, soil entity).

[0121] Therefore, the deep foundation monitoring system matches and associates the real-time monitoring data (including real-time displacement value of enclosure structure, real-time stress value of support structure, real-time state of soil settlement) and the second simulation data (including second displacement simulation value of enclosure structure, second stress simulation value of support structure, simulation state of soil settlement) with the corresponding entities in the knowledge graph respectively, to obtain the monitoring data mapping result and the simulation data mapping result, and ensure the accurate correspondence between data and entities.

[0122] In an embodiment, in the deep foundation pit knowledge graph, the enclosure structure entity is associated with the "displacement value" attribute, the support structure entity is associated with the "stress value" attribute, and the soil entity is associated with the "settlement state" attribute. The real-time monitoring data are: the real-time displacement value of the enclosure structure is 3 mm, the real-time stress value of the support structure is 20 MPa, and the real-time settlement state of the soil is 1.5 mm. The deep foundation pit monitoring system maps these data to the enclosure structure entity, the support structure entity, and the soil entity of the knowledge graph respectively, to obtain the monitoring data mapping result: the enclosure structure entity-displacement value 3 mm, the support structure entity-stress value 20 MPa, and the soil entity-settlement state 1.5 mm. The second simulation data are: the second displacement simulation value of the enclosure structure is 2.8 mm, the second stress simulation value of the support structure is 19 MPa, and the soil settlement simulation state is 1.2 mm. After mapping, the simulation data mapping result is obtained: the enclosure structure entity-displacement value 2.8 mm, the support structure entity-stress value 19 MPa, and the soil entity-settlement state 1.2 mm.

[0123] Step 502, based on the monitoring data mapping result and the simulation data mapping result, attribute extraction is performed in the deep foundation pit knowledge graph to obtain the first attribute feature parameter of the enclosure structure entity, the second attribute feature parameter of the support structure entity, and the third attribute feature parameter of the soil entity.

[0124] Further, based on the monitoring data mapping result and the simulation data mapping result, the deep foundation pit monitoring system performs attribute extraction in the deep foundation pit knowledge graph for the enclosure structure entity, the support structure entity, and the soil entity. The attributes include the basic parameters (such as size, material properties) of the entity, the monitoring parameters (such as real-time monitoring value), and the simulation parameters (such as simulation value), etc. After integration, the first attribute feature parameter of the enclosure structure entity, the second attribute feature parameter of the support structure entity, and the third attribute feature parameter of the soil entity are obtained respectively.

[0125] In an embodiment, based on the monitoring data mapping result and the simulation data mapping result, the following are extracted from the knowledge graph: the first attribute feature parameter of the enclosure structure entity includes thickness 800 mm, depth 25 m, real-time displacement value 3 mm, and second displacement simulation value 2.8 mm; the second attribute feature parameter of the support structure entity includes diameter 600 mm, real-time stress value 20 MPa, and second stress simulation value 19 MPa; and the third attribute feature parameter of the soil entity includes soil property parameters (such as elastic modulus 23 MPa), real-time settlement state 1.5 mm, and settlement simulation state 1.2 mm.

[0126] Step 503, based on the monitoring data mapping result, the simulation data mapping result, the first attribute characteristic parameter, the second attribute characteristic parameter and the third attribute characteristic parameter, the first difference degree of the real-time displacement value of the enclosure structure and the second displacement simulation value, the second difference degree of the real-time stress value of the support structure and the second stress simulation value, and the third difference degree of the real-time state of the soil settlement and the simulation state of the settlement are calculated respectively.

[0127] Further, the deep foundation pit monitoring system combines the monitoring data mapping result, the simulation data mapping result, and the extracted first attribute characteristic parameter, the second attribute characteristic parameter, and the third attribute characteristic parameter to calculate the three types of difference degrees. The first difference degree is calculated by the difference between the real-time displacement value of the enclosure structure and the second displacement simulation value and the attribute characteristic parameter (such as size); the second difference degree is calculated based on the difference between the real-time stress value of the support structure and the second stress simulation value and the attribute characteristic parameter (such as material properties); and the third difference degree is calculated according to the difference between the real-time state of the soil settlement and the simulation state of the settlement and the attribute characteristic parameter (such as soil parameters). The smaller the difference degree, the better the data consistency.

[0128] In an embodiment, the first difference degree is calculated: using the relative difference formula, (|real-time displacement value-second displacement simulation value| / real-time displacement value) x 100% = (|3-2.8| / 3) x 100% ≈ 6.67%. The second difference degree: (|real-time stress value-second stress simulation value| / real-time stress value) x 100% = (|20-19| / 20) x 100% = 5%. The third difference degree: (|settlement real-time state-settlement simulation state| / settlement real-time state) x 100% = (|1.5-1.2| / 1.5) x 100% = 20%.

[0129] Step 504, based on the safety state judgment rules of each type of structure in the deep foundation pit knowledge graph, the first difference degree, the second difference degree and the third difference degree are combined to determine the rule matching degree of the difference between the real-time data and the simulation data conforming to the knowledge graph rules.

[0130] Further, the deep foundation pit monitoring system calls the safety state judgment rules of each type of structure in the deep foundation pit knowledge graph, which stipulate the safety state judgment standards corresponding to different difference degree ranges. The calculated first difference degree, second difference degree and third difference degree are compared with the standards in the knowledge graph rules, and the proportion of the number of difference degrees conforming to the rules in the total number of difference degrees is calculated to obtain the rule matching degree. The higher the matching degree, the more the difference between the data conforms to the safety state rules.

[0131] In an embodiment, the safety state judgment rule in the deep foundation pit knowledge graph is that a difference degree of ≤10% is in line with the safety rule, and >10% is not in line with the safety rule. The first difference degree 6.67% is ≤10%, in line with the rule; the second difference degree 5% is ≤10%, in line with the rule; and the third difference degree 20% is >10%, not in line with the rule. The total difference degree quantity is 3, the quantity in line with the rule is 2, and the rule matching degree = 2 / 3 ≈ 0.67.

[0132] In step 505, the deep foundation pit is monitored and warned based on the rule matching degree in combination with the first attribute feature parameter, the second attribute feature parameter, and the third attribute feature parameter, to obtain a monitoring and warning result.

[0133] Further, the deep foundation pit monitoring system monitors and warns the deep foundation pit according to the rule matching degree in combination with the first attribute feature parameter, the second attribute feature parameter, and the third attribute feature parameter, to obtain a monitoring and warning result, specifically as the processes of steps 5051 to 5054.

[0134] The embodiment of the present application realizes the systematic association of real-time monitoring data and simulation data through the knowledge graph, converts the scattered data into entity attribute feature parameters that can be used for analysis, quantifies the consistency of actual monitoring and simulation results by calculating the data difference degree and the rule matching degree, realizes scientific warning judgment in combination with the safety rules in the knowledge graph, and finally obtains a monitoring and warning result that comprehensively considers the data difference and the structural attribute features. The monitoring and warning result can accurately identify potential safety risks of the deep foundation pit, improve the accuracy and reliability of the deep foundation pit monitoring and warning, and ensure the construction safety of the deep foundation pit project.

[0135] In an embodiment, the processes of steps 5051 to 5054 include:

[0136] In step 5051, the state deviation index of each entity is calculated based on the rule matching degree in combination with the first attribute feature parameter, the second attribute feature parameter, and the third attribute feature parameter. The state deviation index represents the deviation degree of the current state of the entity relative to the normal state in the deep foundation pit knowledge graph.

[0137] Optionally, the deep foundation pit monitoring system compares the actual parameters of each entity with the parameter range of the normal state in the deep foundation pit knowledge graph based on the rule matching degree in combination with the first attribute feature parameter, the second attribute feature parameter, and the third attribute feature parameter. The deviation proportion of the actual parameters from the normal parameter range is calculated, and the deviation proportion is corrected in combination with the rule matching degree, to obtain the state deviation index of each entity. The value range of the state deviation index is 0 to 1, 0 represents no deviation, and 1 represents serious deviation.

[0138] Continue the normal state parameter range in the above deep foundation knowledge graph: enclosure structure displacement difference degree ≤ 10%, supporting structure stress difference degree ≤ 10%, soil body settlement difference degree ≤ 10%. The rule matching degree is 0.67.

[0139] Enclosure structure entity: first difference degree 6.67%, in the normal range, deviation ratio = 6.67% / 10% = 0.667, state deviation index = 0.667 x (1-0.67) ≈ 0.220.

[0140] Supporting structure entity: second difference degree 5%, deviation ratio = 5% / 10% = 0.5, state deviation index = 0.5 x (1-0.67) ≈ 0.165.

[0141] Soil body entity: third difference degree 20%, exceeding the normal range, deviation ratio = 20% / 10% = 2 (taking the upper limit 1), state deviation index = 1 x (1-0.67) ≈ 0.330.

[0142] Step 5052, based on the state deviation index of each entity and the association relationship between entities in the deep foundation knowledge graph, the safety influence degree of the state deviation of each entity on the overall structure of the deep foundation is evaluated.

[0143] Further, the deep foundation monitoring system assigns a corresponding influence weight to each entity according to the association relationship between entities in the deep foundation knowledge graph (such as the interaction relationship between the enclosure structure and the soil body, and the supporting structure and the enclosure structure). The closer the association, the higher the weight of the entity that has a greater influence on the overall structure. Multiply the state deviation index of each entity by the corresponding influence weight to obtain the safety influence degree of the state deviation of each entity on the overall structure of the deep foundation. The higher the influence degree, the greater the threat to the overall safety.

[0144] In an embodiment, the entity association relationship in the deep foundation knowledge graph provides that the influence weight of the enclosure structure is 0.4, the influence weight of the supporting structure is 0.3, and the influence weight of the soil body is 0.3.

[0145] Enclosure structure safety influence degree = state deviation index 0.220 x 0.4 = 0.088.

[0146] Supporting structure safety influence degree = state deviation index 0.165 x 0.3 = 0.0495.

[0147] Soil body safety influence degree = state deviation index 0.330 x 0.3 = 0.099.

[0148] Step 5053, based on the safety influence degree of each entity, the influence coordination analysis between multiple entities is performed to determine whether there is a safety risk superposition situation caused by the interaction of multiple entities.

[0149] Further, the deep foundation pit monitoring system comprehensively analyzes the safety influence degrees of each entity, and judges whether the safety influence degrees of multiple entities all exceed a preset threshold value. If so, the correlation between the entities is further analyzed to determine whether the state deviation of the entities will interact and amplify the safety risk, that is, whether there is a safety risk superposition situation.

[0150] In an embodiment, the preset safety influence degree threshold value is 0.08. The safety influence degree of the enclosure structure is 0.088>0.08, the safety influence degree of the soil body is 0.099>0.08, and the safety influence degree of the supporting structure is 0.0495<0.08. The enclosure structure and the soil body in the deep foundation pit knowledge graph are closely correlated, and the state deviation of the two will influence each other. Therefore, it is determined that there is a safety risk superposition situation caused by the interaction of the enclosure structure and the soil body.

[0151] In step 5054, the deep foundation pit is monitored and warned based on the safety risk superposition situation, and a monitoring and warning result is obtained.

[0152] Further, the deep foundation pit monitoring system determines a warning level according to the safety risk superposition situation and the size of the safety influence degree. If there is no safety risk superposition and the safety influence degree is low, no warning is given. If there is a superposition situation or the safety influence degree is high, a corresponding level of warning (such as general warning or serious warning) is given according to the number of superposed entities and the influence degree value, and the warning reason is specified, and a monitoring and warning result is obtained.

[0153] In an embodiment, there is a safety risk superposition situation of the enclosure structure and the soil body, and the safety influence degrees of the two are 0.088 and 0.099 respectively. The deep foundation pit monitoring system determines to give a general warning, and the monitoring and warning result is: there is a safety risk superposition caused by the interaction of the state deviation of the deep foundation pit enclosure structure and the soil body, a general warning is given, and it is suggested to strengthen the synchronous monitoring and analysis of the displacement of the enclosure structure and the settlement of the soil body.

[0154] The embodiment of the present application quantifies the deviation degree of each entity from the normal state by calculating the state deviation indicator, evaluates the safety influence degree on the overall structure in combination with the correlation between the entities, and further identifies the safety risk superposition situation, so that the final monitoring and warning result not only considers the abnormality of a single entity, but also pays attention to the superimposed risk caused by the interaction between the entities, making the warning more comprehensive and targeted. Therefore, potential safety hazards of the deep foundation pit can be accurately captured, and comprehensive monitoring of the deep foundation pit is realized.

[0155] Further, the deep foundation pit monitoring system based on BIM-physical model hybrid simulation provided by the present application is described below, and the deep foundation pit monitoring system based on BIM-physical model hybrid simulation described below can be correspondingly referred to the deep foundation pit monitoring method based on BIM-physical model hybrid simulation described above.

[0156] Referring to Figure 2 , Figure 2 is a structural schematic diagram of a deep foundation pit monitoring system based on BIM-physical model hybrid simulation provided by the application, the deep foundation pit monitoring system based on BIM-physical model hybrid simulation comprises:

[0157] The acquisition module 210 is configured to acquire real-time monitoring data of the deep foundation pit based on a sensor network arranged in the deep foundation pit, and extract BIM model parameters of the deep foundation pit based on a constructed deep foundation pit building information BIM model;

[0158] The simulation verification module 220 is configured to input a first model parameter in the BIM model parameters into an initial physical model as an initial geometric condition to perform simulation calculation, obtain first simulation data, and verify the first simulation data based on the real-time monitoring data to obtain a verification result index;

[0159] The physical model optimization module 230 is configured to optimize soil mechanical parameters in the initial physical model based on the verification result index until the verification result index output by the physical model in the optimization process meets a preset requirement, and obtain an optimized physical model;

[0160] The construction simulation module 240 is configured to simulate a construction process of the deep foundation pit under a current excavation working condition based on the optimized physical model and a second model parameter in the BIM model parameters, and output second simulation data;

[0161] The monitoring and early warning module 250 is configured to monitor and early warn the deep foundation pit based on a pre-constructed deep foundation pit knowledge graph, the real-time monitoring data and the second simulation data, and obtain a monitoring and early warning result.

[0162] The embodiment of the application optimizes the physical model parameters by using the real-time monitoring data, improves the model accuracy, further generates simulation data of positions where sensors are not arranged based on the optimized physical model, integrates the simulation data with the measured data to obtain a hybrid simulation data set containing comprehensive regional data, and finally the hybrid simulation data set realizes monitoring and early warning of the deep foundation pit as a whole and the unmonitored region. Therefore, by generating simulation data of regions where sensors are not arranged and integrating the simulation data with the measured data, the data blank of regions where sensors are not arranged in the existing method is filled, and comprehensive monitoring of the deep foundation pit is realized.

[0163] Please refer to Figure 3 , Figure 3 is an embodiment schematic diagram of an electronic device provided by the application. As Figure 3As shown, the embodiment of the present application provides an electronic device 300, which comprises a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320, and the processor 320 implements the processes of steps 10 to 50 when executing the computer program 311.

[0164] It should be noted that in the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0165] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0166] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 a system for implementing the functions specified in one or more flows and / or blocks.

[0167] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction system, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 a system for implementing the functions specified in one or more flows and / or blocks.

[0168] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1steps of the functions specified in the block or blocks.

[0169] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the preferred embodiments by those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are intended to encompass within their scope all such variations and modifications as are included within the scope of the application.

[0170] It is apparent that those skilled in the art can make modifications and variations to the application without departing from the scope of the application. Therefore, the application is intended to cover all such modifications and variations as come within the scope of the following claims and their equivalents.

Claims

1. A method for monitoring deep foundation pits based on BIM-physical model hybrid simulation, characterized in that, include: The system collects real-time monitoring data of the deep foundation pit based on a sensor network installed in the deep foundation pit, and extracts BIM model parameters of the deep foundation pit based on the constructed building information BIM model of the deep foundation pit. The first model parameter in the BIM model parameters is used as the initial geometric condition input into the initial physical model for simulation calculation to obtain the first simulation data. The first simulation data is then verified based on the real-time monitoring data to obtain the verification result index. The soil mechanical parameters in the initial physical model are optimized based on the verification result index until the verification result index output by the physical model during the optimization process meets the preset requirements, thus obtaining the optimized physical model. Based on the optimized physical model and the second model parameter in the BIM model parameters, the construction process of the deep foundation pit under the current excavation conditions is simulated, and the second simulation data is output. Based on the pre-constructed deep foundation pit knowledge graph, combined with the real-time monitoring data and the second simulation data, the deep foundation pit is monitored and warned, and the monitoring and warning results are obtained.

2. The deep foundation pit monitoring method based on BIM-physical model hybrid simulation according to claim 1, characterized in that, Real-time monitoring data includes real-time displacement values ​​of the retaining structure and real-time stress values ​​of the support structure; the first simulation data includes the first simulated displacement values ​​of the retaining structure and the first simulated stress values ​​of the support structure. The first simulation data was validated based on real-time monitoring data to obtain validation result indices, including: Based on the real-time displacement value and the first simulated displacement value, a real-time displacement monitoring matrix and a displacement simulation matrix are constructed respectively; each matrix element in the real-time displacement monitoring matrix represents the real-time displacement value of each monitoring point in the retaining structure at each time moment; each matrix element in the displacement simulation matrix represents the first simulated displacement value of each monitoring point in the retaining structure at each time moment. Based on the real-time stress value and the first simulated stress value, a real-time stress monitoring matrix and a stress simulation matrix are constructed respectively; each matrix element in the real-time stress monitoring matrix represents the real-time stress value of each monitoring point in the support structure at each time; each matrix element in the stress simulation matrix represents the first simulated stress value of each monitoring point in the support structure at each time. Based on the real-time displacement monitoring matrix and the displacement simulation matrix, the displacement deviation between the real-time displacement value and the first displacement simulation value of each monitoring point in the retaining structure at each moment is calculated, and based on the real-time stress monitoring matrix and the stress simulation matrix, the stress deviation between the real-time stress value and the first stress simulation value of each monitoring point in the support structure at each moment is calculated. The verification result index is obtained by verifying the displacement deviation of each monitoring point in the retaining structure at each time and the stress deviation of each monitoring point in the support structure at each time.

3. The deep foundation pit monitoring method based on BIM-physical model hybrid simulation according to claim 2, characterized in that, The verification results are obtained by verifying the displacement deviation of each monitoring point in the retaining structure at each time step and the stress deviation of each monitoring point in the support structure at each time step, including: Based on the displacement deviation of each monitoring point in the retaining structure at each time, combined with the spatial distance from each monitoring point to the center of the pit and the cumulative monitoring time at each time, the spatiotemporal correlation deviation value of the displacement of each monitoring point in the retaining structure at each time is determined. Based on the stress deviation of each monitoring point in the support structure at each time, combined with the support depth of each monitoring point and the cumulative monitoring time at each time, the stress spatiotemporal correlation deviation value of each monitoring point in the support structure at each time is determined. Based on the displacement spatiotemporal correlation deviation value of each monitoring point in the enclosure structure at each time and the average displacement spatiotemporal correlation deviation of all monitoring points, the consistency index of the displacement monitoring point group in the spatiotemporal dimension of the enclosure structure at each time is determined. Based on the stress spatiotemporal correlation deviation value of each monitoring point in the support structure at each time and the average stress spatiotemporal correlation deviation of all monitoring points, the stress monitoring point group consistency index of the monitoring point group in the spatiotemporal dimension of the support structure at each time is determined. The verification results were obtained by verifying the consistency index of the displacement monitoring point group at each time point and the consistency index of the stress monitoring point group at each time point.

4. The deep foundation pit monitoring method based on BIM-physical model hybrid simulation according to claim 3, characterized in that, The verification is performed based on the consistency index of the displacement monitoring point group at each time step and the consistency index of the stress monitoring point group at each time step, resulting in the verification result index, including: The evolution trend of displacement deviation is determined based on the difference in the displacement consistency index of the retaining structure at adjacent time points, and the evolution trend of stress deviation is determined based on the difference in the stress consistency index of the support structure at adjacent time points. Based on the layout density of the retaining structure of the deep foundation pit BIM model and the spatiotemporal correlation deviation of the displacement of each monitoring point in the retaining structure at each time, the first spatial distribution consistency between the first simulated displacement value and the real-time displacement value of the retaining structure is determined. Based on the spacing of the support structure and the stress spatiotemporal correlation deviation of each monitoring point in the support structure at each moment in the deep foundation pit BIM model, the second spatial distribution consistency between the first simulated stress value and the real-time stress value of the support structure is determined. The verification results index is obtained based on the evolution trends of displacement deviation, stress deviation, and the consistency between the first and second spatial distributions.

5. The deep foundation pit monitoring method based on BIM-physical model hybrid simulation according to claim 4, characterized in that, The verification is based on the evolution trend of displacement deviation, the evolution trend of stress deviation, the consistency of the first spatial distribution, and the consistency of the second spatial distribution, resulting in a verification result index, including: Based on the displacement deviation evolution trend and the cumulative monitoring time at each moment, the displacement time series matching degree is determined; Based on the stress deviation evolution trend and the cumulative monitoring time at each moment, the stress time series matching degree is determined; Based on the engineering safety level weight of deep foundation pits, combined with the displacement time series matching degree, the stress time series matching degree, the first spatial distribution consistency degree, and the second spatial distribution consistency degree, a verification result index is obtained; the verification result index characterizes the reliability of the first displacement simulation value and the first stress simulation value.

6. The deep foundation pit monitoring method based on BIM-physical model hybrid simulation according to claim 1, characterized in that, Real-time monitoring data includes real-time displacement values ​​of the retaining structure, real-time stress values ​​of the support structure, and real-time settlement status of the soil; second simulation data includes second displacement simulation values, second stress simulation values, and settlement simulation status of the retaining structure, support structure, and soil at locations where sensors are not installed. The method of monitoring and issuing early warnings for deep foundation pits based on a pre-constructed knowledge graph of deep foundation pits, combined with the real-time monitoring data and the second simulation data, yields monitoring and early warning results, including: The entity attribute association rules based on the deep foundation pit knowledge graph map real-time monitoring data and second simulation data to knowledge graph entities respectively, to obtain the monitoring data mapping results and the simulation data mapping results. Based on the monitoring data mapping results and the simulation data mapping results, attribute extraction is performed on the deep foundation pit knowledge graph to obtain the first attribute feature parameters of the retaining structure entity, the second attribute feature parameters of the support structure entity, and the third attribute feature parameters of the soil entity. Based on the monitoring data mapping results and the simulation data mapping results, combined with the first attribute feature parameters, the second attribute feature parameters and the third attribute feature parameters, the first degree of difference between the real-time displacement value and the second displacement simulation value of the retaining structure, the second degree of difference between the real-time stress value and the second stress simulation value of the support structure, and the third degree of difference between the real-time settlement state and the settlement simulation state of the soil are calculated respectively. Based on the safety status judgment rules of various structures in the deep foundation pit knowledge graph, combined with the first difference degree, the second difference degree, and the third difference degree, the rule matching degree of the difference between real-time data and simulated data conforms to the knowledge graph rules. Based on the rule matching degree combined with the first attribute feature parameter, the second attribute feature parameter and the third attribute feature parameter, the deep foundation pit is monitored and warned, and the monitoring and warning results are obtained.

7. The deep foundation pit monitoring method based on BIM-physical model hybrid simulation according to claim 6, characterized in that, The monitoring and early warning of deep foundation pits based on the rule matching degree combined with the first attribute feature parameter, the second attribute feature parameter, and the third attribute feature parameter yields monitoring and early warning results, including: Based on the rule matching degree combined with the first attribute feature parameter, the second attribute feature parameter and the third attribute feature parameter, the state deviation index of each entity is calculated; the state deviation index represents the degree of deviation of the current state of the entity from the normal state in the deep foundation pit knowledge graph; Based on the state deviation index of each entity and the relationship between entities in the deep foundation pit knowledge graph, the safety impact of the state deviation of each entity on the overall structure of the deep foundation pit is evaluated. Based on the security impact of each entity, a collaborative analysis of the impact between multiple entities is conducted to determine whether there is a situation where multiple entities interact to cause the superposition of security risks. Based on the aforementioned superimposed safety risks, monitoring and early warning of deep foundation pits are conducted to obtain monitoring and early warning results.

8. A deep foundation pit monitoring system based on BIM-physical model hybrid simulation, characterized in that, The deep foundation pit monitoring method based on BIM-physical model hybrid simulation as described in any one of claims 1 to 7, wherein the deep foundation pit monitoring system based on BIM-physical model hybrid simulation comprises: The data acquisition module is used to collect real-time monitoring data of the deep foundation pit based on the sensor network set up in the deep foundation pit, and to extract the BIM model parameters of the deep foundation pit based on the constructed building information BIM model of the deep foundation pit. The simulation verification module is used to input the first model parameter in the BIM model parameters as the initial geometric conditions into the initial physical model for simulation calculation, obtain the first simulation data, and verify the first simulation data based on the real-time monitoring data to obtain the verification result index. The physical model optimization module is used to optimize the soil mechanical parameters in the initial physical model based on the verification result index until the verification result index output by the physical model during the optimization process meets the preset requirements, thus obtaining the optimized physical model. The construction simulation module is used to simulate the construction process of the deep foundation pit under the current excavation conditions based on the optimized physical model and the second model parameters in the BIM model parameters, and output the second simulation data. The monitoring and early warning module is used to monitor and warn of deep foundation pits based on a pre-constructed deep foundation pit knowledge graph combined with the real-time monitoring data and the second simulation data, and obtain monitoring and early warning results.

9. An electronic device, characterized in that, The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the program to implement the deep foundation pit monitoring method based on BIM-physical model hybrid simulation as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, wherein a computer software program is stored therein, characterized in that, When the processor executes the program, it implements the deep foundation pit monitoring method based on BIM-physical model hybrid simulation as described in any one of claims 1 to 7.

Images