Tunneling risk identification method, system and equipment of tunnel boring machine

Abstract

The invention discloses a tunneling risk identification method, system and equipment of a tunnel boring machine. The tunneling risk identification method of the tunnel boring machine comprises the following steps: obtaining multi-source key data of a target engineering tunnel boring machine (TBM); inputting the target engineering TBM multi-source key data into a tunneling risk knowledge inference model to obtain a first tunneling risk identification result of the TBM; inputting the target engineering TBM multi-source key data into a data driving model to obtain a second tunneling risk identification result of the TBM; and fusing the first tunneling risk judgment result and the second tunneling risk judgment result of the TBM to obtain a final tunneling risk prediction result of the TBM. According to the embodiment of the invention, accurate judgment and interpretability tracing of the tunneling risk under the complex geological condition are realized, and thus the tunnel boring machine can be assisted in safe and efficient construction.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of civil engineering, in particular to a tunnel boring machine (TBM) tunneling risk identification method, system and device. BACKGROUND

[0002] The TBM (Tunnel Boring Machine) method has the advantages of fast construction speed, high efficiency, small influence on the surrounding environment, safety and environmental protection, etc. in the process of excavating deep and long tunnels, but is restricted by complex geological conditions. During the tunneling process, risks such as cutter wear, cutter disc jamming, shield jamming, and changes in surrounding rock strength may occur. Through data research, current technical solutions related to TBM tunneling risks mainly focus on TBM jamming risk prediction, mainly including: The Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, proposed a "TBM jamming risk prediction method and system". This method mainly obtains the mechanical indicators of the tunneling rock mass by obtaining the target rock mass parameters based on the TBM jamming target rock mass parameter acquisition unit, obtains the target rock mass parameters, judges and statistically analyzes the Poisson's ratio of the rock mass under different climates, generates rock mass strength parameters and rock mass modulus parameters, clusters the strength characteristics of the rock mass strength parameters to obtain strength category information, and clusters the modulus characteristics of the rock mass modulus parameters to obtain modulus category information, inputs the strength category information into a set of strength and water property risk judgment models for water property risk judgment, and obtains the water property risk judgment result. The jamming category risk analysis is performed by inputting the modulus category information into a set of jamming category analysis models to obtain the jamming risk analysis result.

[0003] Shandong University also proposed a "TBM jamming risk prediction method and system". This method includes statistical analysis of the obtained historical TBM tunneling state parameters and corresponding surrounding rock state parameters to obtain TBM tunneling influence factors affecting the TBM jamming risk level, training of a convolutional neural network based on the TBM tunneling influence factors and the TBM jamming risk level to construct a TBM jamming risk prediction model, and obtaining the TBM jamming risk level under the real-time TBM tunneling state parameters based on the TBM jamming risk prediction model. According to the collected surrounding rock state data and TBM tunneling state parameters, the main influencing factors are obtained by principal component analysis, a TBM jamming early warning model is constructed, real-time prediction of the obtained TBM real-time tunneling parameters is performed, and the TBM jamming risk is pre-judged.

[0004] The Shield and Tunneling Technology State Key Laboratory and North China University of Water Resources and Electric Power proposed an early warning method for preventing TBM jamming by combining TSP and FLAC3D, which can early warn possible TBM jamming events based on the fast convergence speed and fast deformation speed of the tunnel surrounding rock, and the synergistic effect of TSP and FLAC3D.

[0005] However, there are the following disadvantages: due to the difficulty in completely consistent between the actual geology in the TBM tunneling process and the geological exploration report, there is a prediction error caused by inaccurate geological data; mainly aiming at the TBM jam risk prediction, the construction risk warning ability is insufficient for the frequent occurrence of tool wear, surrounding rock hardness change and other construction risks; based on the single project TBM tunneling parameters and surrounding rock data, the jam risk prediction lacks the fusion of expert knowledge and experience, and there may be more misjudgments. SUMMARY

[0006] In view of the above defects or deficiencies in the prior art, it is desirable to provide a tunneling risk identification method, system and equipment of a tunnel boring machine, which has precise identification and traceability of tunneling risk under complex geological conditions, and can assist the safe and efficient construction of the tunnel boring machine.

[0007] In a first aspect, an embodiment of the present application provides a training method of a tunneling risk identification model of a tunnel boring machine, comprising: obtaining target engineering TBM multi-source key data; inputting the target engineering TBM multi-source key data into a tunneling risk knowledge reasoning model to obtain a first tunneling risk identification result of a TBM, wherein the tunneling risk knowledge reasoning model comprises a TBM tunneling risk knowledge graph, and the TBM tunneling risk knowledge graph is obtained based on multi-project TBM historical multi-source data; inputting the target engineering TBM multi-source key data into a data-driven model to obtain a second tunneling risk identification result of the TBM, wherein the data-driven model is obtained based on a plurality of data correlation condition judgment thresholds set according to feature values of each dimension data item and relationships between data in the multi-project TBM historical multi-source data; fusing the first tunneling risk identification result and the second tunneling risk identification result of the TBM to obtain a final tunneling risk prediction result of the TBM.

[0008] In some examples, further comprising: obtaining multi-project TBM historical multi-source data; normalizing and standardizing the multi-project TBM historical multi-source data; selecting TBM data matched with a target project from the processed multi-project TBM historical multi-source data; generating feature parameters based on the TBM data; extracting mileages and times of construction data tunneling risk events, classifying the selected TBM data according to mileages and times corresponding to risk events, and taking risk events as data labels; generating a tunneling risk event knowledge base.

[0009] In some examples, before inputting the target engineering TBM multi-source key data into the tunneling risk knowledge reasoning model to obtain a first tunneling risk identification result of the TBM, the method further comprises: associating TBM data and feature parameters corresponding to the mileage and data time from the tunneling risk event knowledge base with the risk event as the theme; statistically analyzing the associated TBM data and feature parameters corresponding to the mileage and data time, and constructing new entities, relationships and attributes; generating the TBM tunneling risk knowledge graph according to the new entities, relationships and attributes; obtaining the tunneling risk knowledge reasoning model according to the TBM tunneling risk knowledge graph.

[0010] In some examples, before inputting the target engineering TBM multi-source key data into the data-driven model to obtain a second tunneling risk identification result of the TBM, the method further comprises: setting a multi-data correlation condition judgment threshold according to the feature values of each dimension data item and the relationship between the data in the multi-engineering TBM historical multi-source data; constructing the data-driven model according to the multi-data correlation condition judgment threshold, wherein the threshold is used to represent whether the data is an abnormal value.

[0011] In some examples, the fusion of the first tunneling risk identification result of the TBM and the second tunneling risk identification result to obtain the final tunneling risk prediction result of the TBM comprises: obtaining a knowledge-driven identification weight coefficient and a data-driven identification weight coefficient; obtaining the final tunneling risk prediction result of the TBM according to the knowledge-driven identification weight coefficient, the data-driven identification weight coefficient, the first tunneling risk identification result of the TBM and the second tunneling risk identification result.

[0012] In some examples, the method further comprises: receiving a user input weight coefficient setting instruction, and setting the knowledge-driven identification weight coefficient and the data-driven identification weight coefficient according to the weight coefficient setting instruction; or setting the knowledge-driven identification weight coefficient and the data-driven identification weight coefficient to default values.

[0013] In some examples, after obtaining the final tunneling risk prediction result of the TBM, the method further comprises: determining an early warning level according to the final tunneling risk prediction result of the TBM, wherein the early warning level is at least two levels.

[0014] In a second aspect, the embodiments of the present application provide a tunnel boring machine tunneling risk identification system, comprising: An acquisition module is configured to obtain target engineering TBM multi-source key data. An execution module is configured to input the target engineering TBM multi-source key data into a tunneling risk knowledge reasoning model to obtain a first tunneling risk identification result of the TBM, and input the target engineering TBM multi-source key data into a data-driven model to obtain a second tunneling risk identification result of the TBM, wherein the data input into the data-driven model is obtained based on a plurality of data correlation condition judgment thresholds set according to feature values of each dimension data item and relationships between data in multi-engineering TBM historical multi-source data, the tunneling risk knowledge reasoning model comprises a TBM tunneling risk knowledge graph, and the TBM tunneling risk knowledge graph is obtained based on multi-engineering TBM historical multi-source data. A prediction module is configured to fuse the first tunneling risk identification result of the TBM and the second tunneling risk identification result to obtain a final tunneling risk prediction result of the TBM.

[0015] In a third aspect, the embodiments of the present application provide a computing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the tunneling risk identification method of the tunnel boring machine according to the first aspect when executing the computer program.

[0016] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the tunneling risk identification method of the tunnel boring machine according to the first aspect.

[0017] The embodiments of the present application improve the robustness of the tunnel boring machine tunneling risk identification by means of knowledge-guided data modeling through a bidirectional fusion mechanism of data features and knowledge graphs, in addition, enhance dynamic adaptability through data feedback knowledge evolution, have precise identification and explainability tracing of tunneling risks under complex geological conditions, and further assist the tunnel boring machine in safe and efficient construction.

[0018] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0019] Other features, objects, and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments thereof as taken in conjunction with the accompanying drawings: Figure 1 A flowchart of a tunnel boring machine tunneling risk identification method according to an embodiment of the present application; Figure 2 Figure 1 shows a schematic diagram of the implementation steps of the tunneling risk identification method of the tunnel boring machine according to an embodiment of the present application; Figure 3 Figure 2 shows a structural block diagram of the tunneling risk identification system of the tunnel boring machine according to an embodiment of the present application; Figure 4 Figure 3 shows a structural schematic diagram of a computing device suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0020] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely intended for the purpose of explaining the related application, and are not limiting on the application. In addition, it should be noted that only parts related to the application are shown in the drawings for ease of description.

[0021] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0022] The tunneling risk identification method, system and device of the tunnel boring machine according to the embodiments of the present application will be described below with reference to the accompanying drawings.

[0023] Figure 1 Figure 1 shows a flowchart of the tunneling risk identification method of the tunnel boring machine according to an embodiment of the present application, as shown in Figure 1 and combined with Figure 2 The tunneling risk identification method of the tunnel boring machine according to an embodiment of the present application comprises the following steps: S101: Obtain target engineering TBM multi-source key data.

[0024] Among them, the target engineering TBM multi-source key data is collected and obtained in real time, which is used to match the knowledge-driven model and the data-driven model, and the target engineering TBM multi-source key data includes but is not limited to: 1. TBM tunneling parameters: total thrust, pushing speed, cutterhead speed, cutterhead torque, penetration, pushing pressure / displacement, shoe pressure / displacement, shield pressure / displacement, tunneling mileage, data time, etc.

[0025] 2. TBM geological data: surrounding rock grade, surrounding rock category, uniaxial compressive strength, rock mass integrity, etc. at the current tunneling mileage and data time.

[0026] S102: Input the target engineering TBM multi-source key data into the tunneling risk knowledge reasoning model to obtain the first tunneling risk identification result of the TBM, wherein the tunneling risk knowledge reasoning model comprises a TBM tunneling risk knowledge graph, and the TBM tunneling risk knowledge graph is obtained based on multi-engineering TBM historical multi-source data.

[0027] In an embodiment of the present application, before the target engineering TBM multi-source key data is input into the tunneling risk knowledge reasoning model to obtain the first tunneling risk judgment result of the TBM, it further includes: obtaining multi-engineering TBM historical multi-source data; normalizing and standardizing the multi-engineering TBM historical multi-source data; screening out TBM data matched with the target engineering from the processed multi-engineering TBM historical multi-source data; generating feature parameters based on the TBM data; extracting the mileage and time of the construction data tunneling risk event, and classifying the screened TBM data according to the mileage and time corresponding to the risk event, and taking the risk event as a data label; generating a tunneling risk event knowledge base.

[0028] On this basis, a tunneling risk knowledge reasoning model can be generated, which specifically includes: taking a risk event as a theme, associating the TBM data and feature parameters corresponding to the mileage and data time from the tunneling risk event knowledge base; statistically analyzing the associated mileage and data time TBM data and feature parameters to construct new entities, relationships and attributes; generating the TBM tunneling risk knowledge graph according to the new entities, relationships and attributes; and generating the tunneling risk knowledge reasoning model according to the TBM tunneling risk knowledge graph.

[0029] Among them, the multi-engineering TBM historical multi-source data includes but is not limited to: 1. TBM tunneling parameters: total thrust, pushing speed, cutterhead speed, cutterhead torque, penetration, pushing pressure / displacement, shoe pressure / displacement, shield pressure / displacement, tunneling mileage, data time, etc.

[0030] 2. TBM design and production data: TBM type, TBM manufacturer, cutterhead diameter, cutter configuration, rated thrust, rated torque, rated speed, maximum pushing speed, maximum power, etc.

[0031] 3. Geological data: surrounding rock grade, surrounding rock category, uniaxial compressive strength, rock mass integrity, etc.

[0032] 4. Construction data: cutter maintenance records, machine jamming event records, surrounding rock change records, etc.

[0033] In a specific application, the historical engineering TBM data and the real-time collected data of the target engineering are screened and processed. The steps include: 1. TBM data normalization and standardization processing, unifying data name, data format, data unit, etc. 2: Select TBM historical tunneling data of multiple projects with the same geology, the same TBM manufacturer / type, similar diameter (within ±500 mm), and key TBM design parameters (within ±10%). 3: Generate relevant feature parameters based on research data, including but not limited to FPI (drillability index), TPI (torque penetration index), variance, mean, median, etc. 4: Extract the mileage and time of construction data tunneling risk events, and classify the filtered TBM historical tunneling data according to the mileage and time corresponding to the risk events, and add data labels to the risk events. 5: Generate tunneling risk event knowledge base.

[0034] Construct a tunneling risk knowledge reasoning model to summarize the rules of historical TBM tunneling risk events and generate a knowledge graph, including the following steps: 1. Statistical knowledge reasoning model: Based on the given risk event, correlate the corresponding TBM tunneling data and feature data at the mileage and data time to construct new entities, relationships, and attributes through statistical analysis; 2. Generate TBM tunneling risk knowledge graph, input real-time TBM tunneling data, match risk time correlation, and give TBM tunneling risk identification results.

[0035] S103: Input the target project TBM multi-source key data into the data-driven model to obtain the second tunneling risk identification result of the TBM, wherein the data input data-driven model is obtained by setting multi-data correlation condition judgment thresholds based on the feature values of each dimension data item in the multi-project TBM historical multi-source data and the relationship between the data.

[0036] In one embodiment of the present application, before inputting the target project TBM multi-source key data into the data-driven model to obtain the second tunneling risk identification result of the TBM, it further includes: setting multi-data correlation condition judgment thresholds according to the feature values of each dimension data item in the multi-project TBM historical multi-source data and the relationship between the data; construct the data-driven model according to the multi-data correlation condition judgment thresholds, wherein the thresholds are used to represent whether the data is an abnormal value.

[0037] In one specific application, a data-driven model is constructed for data-driven tunneling risk identification, including the following steps: 1. Real-time acquisition of TBM data, key data screening and feature extraction to form a time series data set; 2. Set multiple data correlation condition judgment thresholds based on the characteristic values of each dimension data item in the data set and the relationship between the data, and if the thresholds are exceeded, it is an abnormal value, and a data-driven model based on abnormal values is constructed.

[0038] 3. The time series data set is continuously updated into the time series data set according to the sliding window algorithm, the length of the time series data set is 10 minutes, and the real-time key parameters and characteristic parameters are continuously compared with the thresholds. If one or more data exceeds the threshold, refer to the model rule to output the tunneling risk time identification result.

[0039] S104: Fuse the first tunneling risk identification result of the TBM and the second tunneling risk identification result to obtain the final tunneling risk prediction result of the TBM.

[0040] In an embodiment of the present application, the fusion of the first tunneling risk identification result of the TBM and the second tunneling risk identification result to obtain the final tunneling risk prediction result of the TBM comprises: obtaining a knowledge-driven identification weight coefficient and a data-driven identification weight coefficient; obtaining the final tunneling risk prediction result of the TBM according to the knowledge-driven identification weight coefficient, the data-driven identification weight coefficient, the first tunneling risk identification result of the TBM and the second tunneling risk identification result.

[0041] Wherein, the weight coefficient can be determined by the following way: receiving the weight coefficient setting instruction input by the user, and setting the knowledge-driven identification weight coefficient and the data-driven identification weight coefficient according to the weight coefficient setting instruction; or setting the knowledge-driven identification weight coefficient and the data-driven identification weight coefficient to default values.

[0042] Specifically, the knowledge-driven identification probability and the data-driven identification probability are fused based on the efficacy coefficient method to give the tunneling risk identification prediction. The fusion identification formula is H=k1X+k2Y, wherein k1 is the data-driven identification weight coefficient. k2 is the knowledge-driven identification weight coefficient. X is the data-driven tunneling risk, and Y is the knowledge-driven tunneling risk. For example: the default weight coefficient is 0.5, the data-driven tunneling risk is 80 points, and the knowledge-driven risk is 60 points. The fusion identification probability is 0.5*80+0.5*60=70.

[0043] After obtaining the final tunneling risk prediction result of the TBM, the tunneling risk identification method of the tunnel boring machine according to the embodiments of the present application can further comprise: determining an early warning level according to the final tunneling risk prediction result of the TBM, wherein the early warning level is at least two levels.

[0044] For example: the fusion identification probability is greater than 60, and a first-level warning is performed; the fusion identification probability is greater than 80, and a second-level warning is performed; the fusion identification probability is greater than 90, and a third-level warning is performed; wherein the TBM tunneling risk identification event includes tool wear, cutter head jamming, shield jamming, increased surrounding rock strength, and the like.

[0045] According to the tunneling risk identification method of the tunnel boring machine, through the bidirectional fusion mechanism of data features and a knowledge graph, the robustness of the tunneling risk identification of the tunnel boring machine is improved by means of knowledge-guided data modeling. In addition, the dynamic adaptability is enhanced by data feedback knowledge evolution, and the tunnel boring machine is assisted to construct safely and efficiently.

[0046] Figure 3 is a structural block diagram of the tunneling risk identification system of the tunnel boring machine according to an embodiment of the present application, as Figure 3 The tunneling risk identification system of the tunnel boring machine according to an embodiment of the present application includes an acquisition module 310, an execution module 320, and a prediction module 330, wherein: The acquisition module 310 is configured to obtain target engineering TBM multi-source key data. The execution module 320 is configured to input the target engineering TBM multi-source key data into a tunneling risk knowledge reasoning model to obtain a first tunneling risk identification result of the TBM, and input the target engineering TBM multi-source key data into a data-driven model to obtain a second tunneling risk identification result of the TBM. The data input into the data-driven model is obtained based on a plurality of data correlation condition judgment thresholds set according to feature values of each dimension data item and relationships between data in multi-engineering TBM historical multi-source data. The tunneling risk knowledge reasoning model includes a TBM tunneling risk knowledge graph, and the TBM tunneling risk knowledge graph is obtained based on multi-engineering TBM historical multi-source data. The prediction module 330 is configured to fuse the first tunneling risk identification result of the TBM and the second tunneling risk identification result to obtain a final tunneling risk prediction result of the TBM.

[0047] According to the tunneling risk identification system of the tunnel boring machine, through the bidirectional fusion mechanism of data features and a knowledge graph, the robustness of the tunneling risk identification of the tunnel boring machine is improved by means of knowledge-guided data modeling. In addition, the dynamic adaptability is enhanced by data feedback knowledge evolution, and the tunnel boring machine is assisted to construct safely and efficiently.

[0048] It should be noted that the specific implementation manner of the tunneling risk identification system of the tunnel boring machine according to the embodiments of the present application is similar to that of the tunneling risk identification method of the tunnel boring machine according to the embodiments of the present application, and specific details are described in the method part, which will not be repeated here.

[0049] Reference will now be made to Figure 4 , Figure 4 A structural diagram of a computing device suitable for use in implementing embodiments of the present application is shown.

[0050] As Figure 4 shown, the computer system includes a central processing unit (CPU) 1001 which can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 1002 or loaded from a storage section 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation instructions of the system are also stored. The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0051] The following components are connected to the I / O interface 1005; an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as necessary. A removable media 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 1010 as necessary, so that a computer program read out therefrom is installed into the storage section 1008 as necessary.

[0052] In particular, the processes described above with reference to the flowcharts Figure 1 may be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product comprising a computer program carrying computer program code for executing the methods illustrated by the flowcharts. In such an embodiment, the computer program comprises program code for executing the methods illustrated by the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network by the communication section 1009 and / or installed from the removable media 1011. When the computer program is executed by the central processing unit (CPU) 1001, the above-described functions defined in the system of the present application are performed.

[0053] It should be noted that the computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium or a combination thereof. The computer-readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer-readable storage medium can include, but are not limited to, the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer-readable storage medium can be any tangible medium that contains or stores a program used by an instruction execution system, apparatus, or device to function according to the program. In the present application, a computer-readable signal medium can include a computer-readable storage medium as described above, and a computer-readable signal medium can also be a computer-readable storage medium as described above in which case the computer-readable signal medium is a computer-readable storage medium that is also a computer-readable signal medium.

[0054] The flow diagrams and the block diagrams in the drawings are illustrations of possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may be executed in the reverse order, depending on the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0055] The units or modules described in the embodiments of the present application can be implemented in software or hardware. The described units or modules can also be arranged in a processor. In some cases, the names of the units or modules do not constitute a limitation on the units or modules themselves.

[0056] As another aspect, the present application also provides a computer readable storage medium, which can be included in the computing device described in the above embodiments, or can exist separately and not be assembled into the computing device. The computer readable storage medium stores one or more programs, when the programs are used by one or more processors to execute the tunneling risk identification method of the TBM described in the present application. That is, obtaining target engineering TBM multi-source key data; inputting the target engineering TBM multi-source key data into a tunneling risk knowledge reasoning model to obtain a first tunneling risk identification result of the TBM, wherein the tunneling risk knowledge reasoning model includes a TBM tunneling risk knowledge graph, and the TBM tunneling risk knowledge graph is obtained based on multi-engineering TBM historical multi-source data; inputting the target engineering TBM multi-source key data into a data-driven model to obtain a second tunneling risk identification result of the TBM, wherein the data-driven model is obtained based on a plurality of data correlation condition judgment thresholds set according to feature values of each dimension data item and relationships between data in the multi-engineering TBM historical multi-source data; fusing the first tunneling risk identification result and the second tunneling risk identification result of the TBM to obtain a final tunneling risk prediction result of the TBM.

[0057] The above description is only the preferred embodiments of the present application and the explanation of the applied technical principles. Those skilled in the art should understand that the disclosed range in the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and also covers other technical solutions formed by any combination of the above technical features or equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features disclosed in the present application (but not limited to) having similar functions to form technical solutions.

Claims

1. A method for identifying tunneling risks using a tunnel boring machine, characterized in that, include: Obtain multi-source key data of the target project TBM; The multi-source key data of the TBM in the target project are input into the tunneling risk knowledge reasoning model to obtain the first tunneling risk identification result of the TBM. The tunneling risk knowledge reasoning model includes a TBM tunneling risk knowledge graph, which is obtained based on historical multi-source data of TBMs in multiple projects. The target project TBM multi-source key data is input into the data-driven model to obtain the second tunneling risk identification result of the TBM. The data input into the data-driven model is obtained by setting a multi-data association condition judgment threshold based on the feature values ​​of each dimension of data items and the relationship between data in the historical multi-source data of multi-project TBMs. The first tunneling risk identification result and the second tunneling risk identification result of the TBM are combined to obtain the final tunneling risk prediction result of the TBM.

2. The method for identifying tunneling risks of a tunnel boring machine according to claim 1, characterized in that, Also includes: Obtain historical multi-source data of TBM from multiple projects; The historical multi-source data of the multi-project TBM are normalized and standardized. Select TBM data that matches the target project from the processed multi-project TBM historical multi-source data; Based on the TBM data, feature parameters are generated; Extract the mileage and time of tunneling risk events from the construction data, and classify the filtered TBM data according to the mileage and time corresponding to the risk events, and use the risk events as data tags; Generate a knowledge base for tunneling risk events.

3. The method for identifying tunneling risks of a tunnel boring machine according to claim 2, characterized in that, Before inputting the multi-source key data of the target project TBM into the tunneling risk knowledge reasoning model to obtain the first tunneling risk identification result of the TBM, the following steps are also included: Taking risk events as the theme, TBM data and feature parameters with corresponding mileage and data time are associated from the tunneling risk event knowledge base; Perform statistical analysis on the associated mileage and data time TBM data and feature parameters to construct new entities, relationships and attributes; Based on the new entities, relationships, and attributes, the TBM tunneling risk knowledge graph is generated; The tunneling risk knowledge reasoning model is obtained based on the TBM tunneling risk knowledge graph.

4. The method for identifying tunneling risks of a tunnel boring machine according to claim 1, characterized in that, Before inputting the multi-source key data of the target project TBM into the data-driven model to obtain the second tunneling risk identification result of the TBM, the following steps are also included: Based on the feature values ​​of each dimension of data items and the relationship between data in the historical multi-source data of the multi-project TBM, a multi-data association condition judgment threshold is set. The data-driven model is constructed based on the threshold determined by the multiple data association conditions, wherein the threshold is used to characterize whether the data is an outlier.

5. The method for identifying tunneling risks of a tunnel boring machine according to any one of claims 1-4, characterized in that, The process of fusing the first tunneling risk identification result and the second tunneling risk identification result of the TBM to obtain the final tunneling risk prediction result of the TBM includes: Obtain the knowledge-driven identification weight coefficient and the data-driven identification weight coefficient; Based on the knowledge-driven identification weight coefficient, the data-driven identification weight coefficient, the first tunneling risk identification result of the TBM, and the second tunneling risk identification result, the final tunneling risk prediction result of the TBM is obtained.

6. The method for identifying tunneling risks of a tunnel boring machine according to claim 5, characterized in that, Also includes: Receive the user's input instruction to set the weight coefficients, and set the knowledge-driven identification weight coefficients and data-driven identification weight coefficients according to the instruction. or, Set the knowledge-driven identification weight coefficient and the data-driven identification weight coefficient to their default values.

7. The method for identifying tunneling risks of a tunnel boring machine according to claim 1, characterized in that, After obtaining the final tunneling risk prediction result of the TBM, the following is also included: Based on the final tunneling risk prediction results of the TBM, an early warning level is determined, wherein the early warning level is at least two levels.

8. A tunnel boring machine risk assessment system, characterized in that, include: The acquisition module is used to obtain multi-source key data of the target project TBM; The execution module is used to input the multi-source key data of the target project TBM into the tunneling risk knowledge reasoning model to obtain the first tunneling risk identification result of the TBM, and input the multi-source key data of the target project TBM into the data-driven model to obtain the second tunneling risk identification result of the TBM. The data input data-driven model is obtained by setting a multi-data association condition judgment threshold based on the feature values ​​of each dimension of data items and the relationship between data in the historical multi-source data of multi-project TBMs. The tunneling risk knowledge reasoning model includes a TBM tunneling risk knowledge graph, which is obtained based on the historical multi-source data of multi-project TBMs. The prediction module is used to fuse the first tunneling risk identification result and the second tunneling risk identification result of the TBM to obtain the final tunneling risk prediction result of the TBM.

9. A computing device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the tunneling risk identification method for a tunnel boring machine according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the tunneling risk identification method for a tunnel boring machine according to any one of claims 1-7.

Images