Construction data analysis optimization method and system based on tunnel excavation integrated management system

Abstract

The invention belongs to the technical field of tunnel engineering, and particularly relates to a construction data analysis optimization method and system based on a tunnel excavation integrated management system, and the scheme breaks through the traditional design, construction and evaluation link splitting state, forms a closed-loop management system capable of continuous self-optimization, and improves the construction efficiency. By comparing the deviation between the expected effect and the actual effect, not only can accurate effect quantitative evaluation and cost analysis be completed, but also the model correction factor is updated in real time through the deviation result, so that the whole scheme can learn and continuously optimize the prediction and decision precision in each blasting practice, and by repeatedly executing the closed-loop process, the prediction efficiency is improved. The whole scheme can be evolved continuously in the tunnel construction process, continuous improvement of the construction technology is finally achieved, and then the maximization of comprehensive benefits in the whole life cycle is achieved.

Description

Technical Field

[0001] This invention belongs to the field of tunnel engineering technology, specifically relating to a construction data analysis and optimization method and system based on a comprehensive tunnel excavation management system. Background Technology

[0002] As tunnel engineering progresses towards deeper, larger cross-sections, and more complex geological conditions, the safety, efficiency, and economy of tunnel blasting construction face increasingly stringent requirements. While traditional integrated tunnel excavation management systems have integrated some construction data, they still suffer from numerous shortcomings and difficulties in terms of data comprehensiveness and utilization. Specifically: In terms of construction data collection, traditional methods rely on manual logging and limited borehole sampling, which makes it difficult to accurately reflect the spatial variability of rock masses. Furthermore, various data sources (such as geology, borehole data, and explosive data) are scattered and lack a unified spatiotemporal benchmark and fusion mechanism, resulting in a serious disconnect between data collection, subsequent analysis, and decision-making.

[0003] In terms of optimizing blasting parameters, existing solutions mainly rely on static empirical formulas and expert evaluation, without making effective use of historical data, and are somewhat subjective, making it difficult to adapt to different working conditions.

[0004] In terms of cost control and effectiveness evaluation, existing solutions typically focus only on direct material consumption in cost accounting, neglecting the cascading costs and potential risk costs of blasting quality affecting subsequent processes. Effectiveness evaluations mostly focus on isolated indicators of a single blast, with weighting primarily relying on subjective, manually set weights. This lack of a holistic lifecycle analysis and objective, comprehensive evaluation system results in insufficient foresight in management decisions and prevents the maximization of economic benefits throughout the entire lifecycle. Summary of the Invention

[0005] This invention addresses the problems existing in the prior art by providing a construction data analysis and optimization method and system based on a comprehensive tunnel excavation management system, effectively solving the problems present in the prior art.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: Construction data analysis and optimization methods based on a tunnel excavation integrated management system include: Step 1: Obtain historical point cloud data of the tunnel face before and after blasting, time-series data and trajectory data of the drilling process, acoustic signals and spectral characteristics, as well as charge records and equipment consumption statistics from the tunnel excavation integrated management system. After data preprocessing and feature engineering, geological features, design features and effect features are obtained respectively. Step 2: Based on the current geological characteristics, similar cases are screened from the pre-constructed historical case design-effect relationship database through similarity calculation to obtain a set of similar cases. The historical case design-effect relationship database is constructed based on the geological characteristics, design characteristics, effect characteristics, and blasting comprehensive score of historical cases. Step 3: Based on the current geological characteristics, blastability index, obtained similar case set, preset engineering constraints and engineering priorities, a recommended blasting design scheme and its expected effect are obtained through a pre-constructed optimization model that integrates experience and mechanism. Step 4: Perform tunnel blasting based on the recommended blasting design scheme and acquire data through Step 1; perform a quantitative evaluation of the actual effect based on the acquired data to obtain the actual effect of the current blasting design scheme; update the correction factor in the optimization model based on the deviation between the actual effect and the expected effect; repeat Step 1 to Step 4 until the construction of the current tunnel is completed.

[0007] Preferably, the optimization model employs the following processing mechanism: based on the design parameters in the set of similar cases, initial recommended design parameters are determined by weighted averaging; based on the obtained initial recommended design parameters, adjustments are made according to preset project priorities to obtain adjusted recommended design parameters; based on the adjusted recommended design parameters, a recommended blasting design scheme is obtained after constraint checks; simultaneously, based on the recommended blasting design scheme and current geological characteristics, a physical model based on energy distribution is used, combined with a correction factor calculated based on the set of similar cases, to achieve comprehensive prediction of the effect and obtain the expected results.

[0008] Furthermore, based on the recommended blasting design scheme and current geological characteristics, an initial prediction result is obtained using a physical model based on energy distribution, specifically employing the following formula: Calculate the total amount of reagent per well: Calculate the area of ​​the perforated mesh: Calculate energy per unit area: Expected Outcomes: in, For linear charge density, For the depth of the borehole, For the length of the blockage, The hole spacing, For row spacing, The distance from the blast center to the monitoring point is the distance between the blast point and the monitoring point. To improve the energy utilization rate of explosives, The median block size of the rock after blasting, as predicted by the physical model. This is a block size prediction index. The over-excavation rate predicted by the physical model. The peak vibrational velocity of the particle predicted by the physical model. The semi-porosity predicted by the physical model. For block size prediction coefficient, For block size prediction constant, For over-excavation prediction coefficient, This is the over-excavation constant. The over-excavation attenuation coefficient is... This is the vibration field coefficient.

[0009] Furthermore, the calculation of the correction factor based on the set of similar cases specifically adopts the following process: For each case in the set of similar cases, calculate its physical model prediction value; Based on the physical model predictions for each case, calculate the correction factor separately: in, This is the median block size correction factor. This is the over-excavation rate correction factor. This is the peak vibration velocity correction factor for particles. Let be the similarity weight corresponding to the i-th similar case in the set of similar cases, and N be the number of cases in the set of similar cases. The median block size corresponding to the i-th similar case. Let i be the overmining rate corresponding to the i-th similar case. Let be the peak vibration velocity of the particle corresponding to the i-th similar case.

[0010] Furthermore, based on the obtained initial prediction results and correction factors, a comprehensive prediction is made to obtain the expected results, specifically: in, The median block size is the result of comprehensive prediction. The over-excavation rate is a comprehensive prediction. To comprehensively predict the peak vibration velocity of the particles, The half-hole ratio is the half-hole ratio recalculated using the corrected over-excavation ratio.

[0011] Furthermore, the updating of the correction factor in the optimization model specifically includes the following processing steps: Based on the obtained deviation, when the parameter meets the condition of consecutive preset number of same-direction deviations and the deviation exceeds 15%, the correction factor is updated. The specific update process is as follows: in, This is the updated median block size correction factor. This is the updated over-excavation rate correction factor. This is the updated peak particle velocity correction factor. This is the previous median block size correction factor. This is the over-excavation rate correction factor from before. This is the previous peak particle vibration velocity correction factor. The actual median block size, This represents the actual over-excavation rate. This represents the actual peak vibration velocity of the particle. The median block size predicted by the physical model. The over-excavation rate predicted by the physical model. This refers to the peak vibrational velocity of the particles predicted by the physical model.

[0012] Furthermore, when the overall score exceeds a preset threshold, the current blasting design scheme is added to the historical case design-effect relationship database to update the database, thereby affecting subsequent scheme optimization.

[0013] The construction data analysis and optimization system based on the tunnel excavation integrated management system includes: The data acquisition unit is used to acquire historical point cloud data of the tunnel face before and after blasting, time-series data and trajectory data of the drilling process, acoustic signals and spectral characteristics, as well as charge records and equipment consumption statistics from the tunnel excavation integrated management system. After data preprocessing and feature engineering, geological features, design features and effect features are obtained respectively. The similar case set construction unit is used to filter similar cases from a pre-built historical case design-effect relationship database based on the current geological characteristics and through similarity calculation to obtain a similar case set. The historical case design-effect relationship database is constructed based on the geological characteristics, design characteristics, effect characteristics, and blasting comprehensive scores of historical cases. The design scheme recommendation unit is used to obtain recommended blasting design schemes and their expected effects based on current geological characteristics, blastability index, obtained similar case set, preset engineering constraints and engineering priorities, through a pre-constructed optimization model that integrates experience and mechanism. The analysis and optimization unit is used to perform tunnel blasting based on the recommended blasting design scheme and acquire data through step one; perform a quantitative evaluation of the actual effect based on the acquired data to obtain the actual effect of the current blasting design scheme; update the correction factor in the optimization model based on the deviation between the actual effect and the expected effect; repeat the above process until the construction of the current tunnel is completed.

[0014] An electronic device includes a memory, a processor, and a computer program stored in the memory and running on it. When the processor executes the program, it implements the above-mentioned construction data analysis and optimization method based on a tunnel excavation integrated management system.

[0015] A non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned construction data analysis and optimization method based on a tunnel excavation integrated management system.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are as follows: (1) The solution described in this application provides a construction data analysis and optimization method and system based on a tunnel excavation integrated management system. The solution breaks the traditional separation of design, construction and evaluation links and forms a closed-loop management system that can continuously optimize itself. By comparing the deviation between expected and actual effects, it can not only complete accurate quantitative evaluation of effects and cost analysis, but also update the model correction factor in real time through the deviation results. This allows the entire solution to learn in each blasting practice and continuously optimize the accuracy of prediction and decision-making. By repeatedly executing this closed-loop process, the entire solution can continuously evolve in the tunnel construction process, and ultimately achieve continuous improvement of construction technology, thereby maximizing the comprehensive benefits throughout the entire life cycle.

[0017] (2) The solution described in this application constructs a historical case database based on a pre-built tunnel excavation integrated management system, thereby achieving deep integration of multi-source data such as geological, drilling, charging and effect data. Through the integration of multi-source data, accurate analysis of construction data is achieved, changing the traditional situation of relying on manual experience and isolated data sources.

[0018] (3) The proposed solution in this application is an intelligent decision-making method based on similar cases and combined with the optimization model correction of the integration of experience and mechanism. By automatically learning optimization strategies from historical data and dynamically correcting them in combination with the physical principles of blasting, the adaptive optimization of blasting parameters is realized. This makes parameter design shift from purely experience-dependent to being driven by both experience and mechanism. The solution utilizes the commonalities of historical successful cases and ensures the interpretability and extrapolation ability of the solution through physical principles. At the same time, it makes dynamic adjustments according to project priorities and constraints, making parameter design shift from experience-driven to data and model-driven, which significantly improves the scientific nature of the solution and its adaptability to different geological conditions. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below: Figure 1 This is a flowchart of the construction data analysis and optimization method based on the tunnel excavation integrated management system described in Embodiment 1 of the present invention; Figure 2 This is a flowchart of the data preprocessing and feature engineering described in Embodiment 1 of the present invention; Figure 3 This is a flowchart illustrating the processing of the optimization model that integrates experience and mechanism as described in Embodiment 1 of the present invention. Figure 4 This is a flowchart of the comprehensive prediction process described in Embodiment 1 of the present invention; Figure 5 This is a structural diagram of the construction data analysis and optimization system based on the tunnel excavation integrated management system described in Embodiment 1 of the present invention; Figure 6 This is a schematic diagram of an electronic device structure as described in Embodiment 1 of the present invention. Detailed Implementation

[0020] To better understand the above-mentioned objectives, features and advantages of the present invention, the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0021] Numerous specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways than those described herein, and therefore the invention is not limited to the specific embodiments disclosed in the following specification.

[0022] Example 1: The following detailed description, in conjunction with the accompanying drawings, illustrates the construction data analysis and optimization method based on the integrated tunnel excavation management system described in Embodiment 1.

[0023] like Figure 1 As shown, the construction data analysis and optimization method based on the tunnel excavation integrated management system includes: Step 1: Obtain historical point cloud data of the tunnel face before and after blasting, time-series data and trajectory data of the drilling process, acoustic signals and spectral characteristics, as well as charge records and equipment consumption statistics from the tunnel excavation integrated management system. After data preprocessing and feature engineering, geological features, design features and effect features are obtained respectively. Step 2: Based on the current geological characteristics, similar cases are screened from the pre-constructed historical case design-effect relationship database through similarity calculation to obtain a set of similar cases. The historical case design-effect relationship database is constructed based on the geological characteristics, design characteristics, effect characteristics, and blasting comprehensive score of historical cases. Step 3: Based on the current geological characteristics, blastability index, obtained similar case set, preset engineering constraints and engineering priorities, a recommended blasting design scheme and its expected effect are obtained through a pre-constructed optimization model that integrates experience and mechanism. Step 4: Perform tunnel blasting based on the recommended blasting design scheme and acquire data through Step 1; perform a quantitative evaluation of the actual effect based on the acquired data to obtain the actual effect of the current blasting design scheme; update the correction factor in the optimization model based on the deviation between the actual effect and the expected effect; repeat Step 1 to Step 4 until the construction of the current tunnel is completed.

[0024] In specific implementation, such as Figure 2 As shown, the data preprocessing and feature engineering include: The inputs include point cloud data before and after blasting, time-series data and trajectory data during drilling, acoustic signals and spectral characteristics, as well as charge records and equipment consumption. By unifying multi-source data into the tunnel construction coordinate system and aligning time to a unified time reference, spatiotemporal registration of multi-source data is achieved. For the spatiotemporally registered multi-source data, data cleaning is performed; wherein, the data cleaning includes, but is not limited to, outlier extraction, missing data imputation, and noise smoothing. Based on the cleaned multi-source data, feature extraction and multi-source data fusion are performed to obtain geological features, design features, effect features, and blasting index, respectively.

[0025] The geological features are specifically described as follows: ; in, The uniaxial compressive strength of the rock can be obtained by inversion from acoustic signals. The density of the rock can be derived from its lithology. The degree of joint development is obtained through joint analysis of point cloud and acoustic waves. The rock mass integrity coefficient can be calculated from the sound wave velocity. The groundwater impact factor can be estimated based on borehole travel data. This is the damage accumulation factor, which can be calculated from historical vibration data.

[0026] The explosiveness index ( Specifically, it is expressed as follows: in, For the uniaxial compressive strength of rock, For reference rock strength (taken as 150 MPa), For rock density, For reference rock density (taken as 2650 kg / m³) 3 ), As the degree of joint development, The rock mass integrity coefficient. The groundwater influence coefficient is between 0.6 and 1.2. As a damage accumulation factor, , , , , , The weights are dynamic and can be adjusted based on the main controlling factors of the current geological conditions.

[0027] The design features are specifically represented as follows: ; in, The hole spacing, For row spacing, For ultra-deep, For linear charge density, For the length of the blockage, For the delay interval; The effects and characteristics are specifically described as follows: ; in, The median particle size is the bulk size. It is the index of block size distribution uniformity. For over-excavation rate, Half-aperture This represents the peak vibration velocity.

[0028] In practice, the oral history case design-effect association database is constructed based on the geological characteristics, design characteristics, effect characteristics, and blasting comprehensive scores of historical cases.

[0029] In specific implementation, the step of selecting similar cases from the historical case design-effect relationship database based on the current geological feature matrix through similarity calculation to obtain a set of similar cases is as follows: Based on the current geological characteristics, calculate the similarity between each case and all cases in the historical case design-effect relationship database. : =cosine similarity ( ); in, Given the current geological features, Geological features of the i-th case in the historical case study-effect relationship database; Based on the calculated similarity value, combined with a preset threshold Select similarity This example demonstrates how to construct a set of similar cases; the threshold here... The settings can be configured according to actual needs; in this embodiment, they are set as follows: Simultaneously, weights are assigned to each similar case, specifically as follows: in, Let represent the similarity weight of the i-th similar case in the set of similar cases, and N be the number of cases in the set of similar cases.

[0030] In specific implementation, such as Figure 3 As shown, the optimization model employs the following processing mechanism: based on the design parameters in the set of similar cases, initial recommended design parameters are determined by weighted averaging; based on the obtained initial recommended design parameters, adjustments are made according to preset project priorities to obtain adjusted recommended design parameters; based on the adjusted recommended design parameters, a recommended blasting design scheme is obtained after constraint checks; simultaneously, based on the recommended blasting design scheme and current geological characteristics, a physical model based on energy distribution is used, combined with a correction factor calculated based on the set of similar cases, to achieve comprehensive prediction of the effect and obtain the expected results.

[0031] Specifically, the optimization model includes the following processing steps: (1) Based on the design parameters in the set of similar cases, the initial recommended design parameters are determined by weighted average, specifically: in, For the initial recommended design parameter vector, Let N be the design parameter vector for the i-th case in the set of similar cases, and N be the number of cases in the set of similar cases. Let be the similarity weight corresponding to the i-th similar case in the set of similar cases; (2) Based on the obtained initial recommended design parameters, adjustments are made according to the preset project priority to obtain the adjusted recommended design parameters, specifically: When the preset project priority is "cost control": in, These are the adjusted recommended design parameters; here The purpose of vectoring is to increase the aperture spacing and row spacing by 5% to increase the aperture size, and decrease the charge density by 5% to reduce the unit consumption. When the preset project priority is "quality control": Vector here The aim is to reduce the hole spacing and row spacing by 5% to improve the uniformity of crushing, and to increase the charge density by 5% to ensure the crushing effect. When the preset project priority is "safety control": Vector here The aim is to reduce the charge density by 10% to reduce vibration and increase the plugging length by 10% to prevent punching. (3) Based on the adjusted recommended design parameters, and after checking the constraints, the recommended blasting design scheme is obtained. Specifically: The main constraints include: When the constraints are met ; If the constraints are not met, then the closest match within the constraint range is selected. Feasible solution .

[0032] (4) Based on the recommended blasting design scheme and current geological characteristics, a physical model based on energy distribution is adopted, combined with a correction factor calculated based on a set of similar cases, to achieve a comprehensive prediction of the effect and obtain the expected results, such as... Figure 4 As shown, specifically: 1) Based on the recommended blasting design scheme and current geological features The initial prediction results are obtained using a physical model based on energy distribution, specifically using the following formula: Calculate the total amount of reagent per well: Calculate the area of ​​the perforated mesh: Calculate energy per unit area: Expected Outcomes: in, For linear charge density, For the depth of the borehole, For the length of the blockage, The hole spacing, For row spacing, The distance from the blast center to the monitoring point is the distance between the blast point and the monitoring point. To improve the energy utilization rate of explosives, The median block size of the rock after blasting, as predicted by the physical model. This is a block size prediction index. The over-excavation rate predicted by the physical model. The peak vibrational velocity of the particle predicted by the physical model. The semi-porosity predicted by the physical model. For block size prediction coefficient, For block size prediction constant, For over-excavation prediction coefficient, This is the over-excavation constant. The over-excavation attenuation coefficient is... This is the vibration field coefficient.

[0033] 2) The correction factor is calculated based on a set of similar cases, specifically using the following process: For each case in the set of similar cases, calculate its physical model prediction value, and obtain , and ;in, Let be the median block size of the rock after blasting predicted by the physical model for the i-th case. Let be the over-excavation rate predicted by the physical model for the i-th case. Let be the peak vibrational velocity of the particle predicted by the physical model for the i-th case. Based on the physical model predictions for each case, calculate the correction factor separately: in, This is the median block size correction factor. This is the over-excavation rate correction factor. This is the peak vibration velocity correction factor for particles. Let be the similarity weight corresponding to the i-th similar case in the set of similar cases, and N be the number of cases in the set of similar cases. The median block size corresponding to the i-th similar case. Let i be the overmining rate corresponding to the i-th similar case. The peak vibration velocity of the particle corresponding to the i-th similar case; 3) Based on the obtained initial prediction results and correction factors, a comprehensive prediction is made to obtain the expected results, specifically: in, The median block size is the result of comprehensive prediction. The over-excavation rate is a comprehensive prediction. To comprehensively predict the peak vibration velocity of the particles, The half-hole ratio is the half-hole ratio recalculated using the corrected over-excavation ratio.

[0034] In specific implementation, the actual effect quantitative evaluation is performed based on the obtained data to obtain the actual effect of the current blasting design scheme; based on the deviation between the actual effect and the expected effect, the correction factor in the optimization model is updated, specifically including the following processing steps: The actual effect of the current blasting design scheme is obtained through calculation. ;in, The actual median block size, This represents the actual over-excavation rate. This represents the actual half-porosity. This represents the actual peak vibration velocity of the particle. Calculate the deviation between the actual effect and the expected effect separately, including , , and ;by For example: Understandably, the deviations in other effect parameters are also obtained based on the above method, and will not be elaborated here.

[0035] Based on the obtained deviation, when the parameter meets the condition that the deviation in the same direction exceeds 15% for a consecutive preset number of times, the correction factor is updated. The specific update process is as follows: in, This is the updated median block size correction factor. This is the updated over-excavation rate correction factor. This is the updated peak particle velocity correction factor. This is the previous median block size correction factor. This is the over-excavation rate correction factor from before. This is the previous peak particle vibration velocity correction factor. The actual median block size, This represents the actual over-excavation rate. This represents the actual peak vibration velocity of the particle. The median block size predicted by the physical model. The over-excavation rate predicted by the physical model. This refers to the peak vibrational velocity of the particles predicted by the physical model.

[0036] In practical implementation, based on the actual effects and the overall cost of the current blasting design scheme, a comprehensive score is obtained for the current blasting design scheme. Based on the obtained comprehensive score, the current blasting design scheme is added to the historical case design-effect relationship database. Specifically: The comprehensive cost Including direct costs and cascading costs Specifically, it is expressed as follows: in, For direct costs, For cascading costs, For the cost of explosives, For detonator costs, For labor costs, For equipment costs, To cover the cost of over-excavation repair, To cover the cost of excavation, The cost of secondary crushing of large pieces.

[0037] Based on the calculated total cost, calculate the unit consumption cost separately. and cost savings Specifically: in, This refers to the excavation volume.

[0038] Based on the obtained comprehensive cost Unit cost and the actual effect of the current blasting design scheme. The quality score, cost score, and safety score are calculated separately using the following formulas: Quality rating: Cost rating: Safety rating: Based on the obtained quality score, cost score, and safety score, a comprehensive score is calculated to obtain the comprehensive score result, as follows: in, For unit consumption cost, The baseline unit cost can be obtained from the average unit cost of each case in a set of similar cases.

[0039] Furthermore, when the overall scoring results If the value exceeds a preset threshold, the current blasting design scheme will be added to the historical case design-effect relationship database to update the database and thus affect the optimization of subsequent schemes.

[0040] In practical implementation, the tunnel excavation integrated management system includes at least the following modules: (1) A three-dimensional laser scanning module, which is used to collect point cloud data, scanning attitude parameters, and timing information of the face before and after blasting based on a three-dimensional laser scanning device (such as a handheld mobile scanning device or a high-precision three-dimensional laser scanner); specifically: Pre-blasting point cloud data: the original set of three-dimensional coordinate points, including spatial coordinates (X, Y, Z), reflection intensity values, and color information; Post-blast point cloud data: a set of three-dimensional coordinate points in the same control point coordinate system as the pre-blast point cloud; Scanning posture parameters: location of each monitoring point, scanning range, and accuracy information; Timing information: timestamps for each scan time.

[0041] (2) Intelligent drilling parameter monitoring module, which is used to collect drilling process time-series data, drilling trajectory data, drilling completion report and drilling anomaly record based on intelligent drilling monitoring equipment; specifically: Drilling process time-series data: depth, inclination angle, rotational speed, torque, propulsion pressure, and vibration acceleration in the time-series sequence; Drilling trajectory data: a sequence of three-dimensional spatial trajectory points of the borehole; Drilling completion report: final hole depth, inclination angle, and hole quality evaluation; Drilling anomaly record: time, location, and characteristic parameters of stuck drill and skipped drill.

[0042] (3) Acoustic rock identification module, which is used to extract data such as raw acoustic signals, spectral feature vectors, rock identification results, and geological anomaly early warning based on acoustic equipment; wherein: Raw sound wave signal: time-series sound pressure data; Spectral eigenvectors: MFCC coefficients (13-dimensional), short-time energy, zero-crossing rate, and spectral centroid; Rock identification results: rock type classification, rock strength estimate, joint surface detection markers; Geological anomaly early warning: identification and marking of lithological abrupt changes, cavities, and fracture zones.

[0043] (4) Electronic tag-based explosive cartridge management module, which is used to electronically record the use of various civil explosive materials (e.g., detonators, explosives, detonating cords, etc.) based on RFID technology or other electronic tag technology, including explosive cartridge loading records, explosive loading integrity reports, and material consumption statistics; wherein: Drug roll loading record: Drug roll ID, hole number, loading time, three-dimensional coordinates (X, Y, Z) and operator; Explosive charge integrity report: A comparison of the designed explosive charge table with the actual explosive charge. Equipment consumption statistics: quantity and batch information of explosives, detonators, and detonating cords consumed.

[0044] It is understood that the tunnel excavation integrated management system of the scheme described in this embodiment includes at least the above-mentioned modules for use in the subsequent steps of the scheme described in this embodiment. Those skilled in the art should know that the system may also include various other functions, but since the scheme described in this embodiment does not involve the use of other modules, they will not be described in detail here.

[0045] Example 2: In one or more embodiments, as shown in 5, based on the method described in Embodiment 1, a construction data analysis and optimization system based on a tunnel excavation integrated management system is provided, including: The data acquisition unit is used to acquire historical point cloud data of the tunnel face before and after blasting, time-series data and trajectory data of the drilling process, acoustic signals and spectral characteristics, as well as charge records and equipment consumption statistics from the tunnel excavation integrated management system. After data preprocessing and feature engineering, geological features, design features and effect features are obtained respectively. The similar case set construction unit is used to filter similar cases from a pre-built historical case design-effect relationship database based on the current geological characteristics and through similarity calculation to obtain a similar case set. The historical case design-effect relationship database is constructed based on the geological characteristics, design characteristics, effect characteristics, and blasting comprehensive scores of historical cases. The design scheme recommendation unit is used to obtain recommended blasting design schemes and their expected effects based on current geological characteristics, blastability index, obtained similar case set, preset engineering constraints and engineering priorities, through a pre-constructed optimization model that integrates experience and mechanism. The analysis and optimization unit is used to perform tunnel blasting based on the recommended blasting design scheme and acquire data through step one; perform a quantitative evaluation of the actual effect based on the acquired data to obtain the actual effect of the current blasting design scheme; update the correction factor in the optimization model based on the deviation between the actual effect and the expected effect; repeat the above process until the construction of the current tunnel is completed.

[0046] In further embodiments, the following is also provided: like Figure 6 As shown, an electronic device includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor. When executed by the processor, the computer instructions perform the methods described in the above embodiments. For brevity, further details are omitted here.

[0047] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0048] Memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of memory may also include non-volatile random access memory. For example, memory may also store information about the device type.

[0049] A computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the methods described in the above embodiments.

[0050] The methods described in the above embodiments can be directly executed by a hardware processor, or executed by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0051] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications or equivalent changes made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A construction data analysis and optimization method based on a tunnel excavation integrated management system, characterized in that, include: Step 1: Obtain historical point cloud data of the tunnel face before and after blasting, time-series data and trajectory data of the drilling process, acoustic signals and spectral characteristics, as well as charge records and equipment consumption statistics from the tunnel excavation integrated management system. After data preprocessing and feature engineering, geological features, design features and effect features are obtained respectively. Step 2: Based on the current geological characteristics, similar cases are screened from the pre-constructed historical case design-effect relationship database through similarity calculation to obtain a set of similar cases. The historical case design-effect relationship database is constructed based on the geological characteristics, design characteristics, effect characteristics, and blasting comprehensive score of historical cases. Step 3: Based on the current geological characteristics, blastability index, obtained similar case set, preset engineering constraints and engineering priorities, a recommended blasting design scheme and its expected effect are obtained through a pre-constructed optimization model that integrates experience and mechanism. Step 4: Perform tunnel blasting based on the recommended blasting design scheme and acquire data through Step 1; perform a quantitative evaluation of the actual effect based on the acquired data to obtain the actual effect of the current blasting design scheme; update the correction factor in the optimization model based on the deviation between the actual effect and the expected effect; repeat Step 1 to Step 4 until the construction of the current tunnel is completed.

2. The construction data analysis and optimization method based on a tunnel excavation integrated management system as described in claim 1, characterized in that, The optimization model employs the following processing mechanism: based on the design parameters in the set of similar cases, the initial recommended design parameters are determined by weighted averaging; based on the obtained initial recommended design parameters, adjustments are made according to the preset project priority to obtain the adjusted recommended design parameters; Based on the adjusted recommended design parameters and after constraint checks, a recommended blasting design scheme is obtained. At the same time, based on the recommended blasting design scheme and the current geological characteristics, a physical model based on energy distribution is adopted, combined with a correction factor calculated based on a set of similar cases, to achieve a comprehensive prediction of the effect and obtain the expected results.

3. The construction data analysis and optimization method based on the tunnel excavation integrated management system as described in claim 2, characterized in that, Based on the recommended blasting design scheme and current geological characteristics, an energy distribution-based physical model is used to obtain initial prediction results, specifically using the following formula: Calculate the total amount of reagent per well: Calculate the area of ​​the perforated mesh: Calculate energy per unit area: Expected Outcomes: in, For linear charge density, For the depth of the borehole, For the length of the blockage, The hole spacing, For row spacing, The distance from the blast center to the monitoring point is the distance between the blast point and the monitoring point. To improve the energy utilization rate of explosives, The median block size of the rock after blasting, as predicted by the physical model. This is a block size prediction index. The over-excavation rate predicted by the physical model. The peak vibrational velocity of the particle predicted by the physical model. The semi-porosity predicted by the physical model. For block size prediction coefficient, For block size prediction constant, For over-excavation prediction coefficient, This is the over-excavation constant. The over-excavation attenuation coefficient is... This is the vibration field coefficient.

4. The construction data analysis and optimization method based on the tunnel excavation integrated management system as described in claim 3, characterized in that, The calculation of the correction factor based on a set of similar cases specifically adopts the following process: For each case in the set of similar cases, calculate its physical model prediction value; Based on the physical model predictions for each case, calculate the correction factor separately: in, This is the median block size correction factor. This is the over-excavation rate correction factor. This is the peak vibration velocity correction factor for particles. Let be the similarity weight corresponding to the i-th similar case in the set of similar cases, and N be the number of cases in the set of similar cases. The median block size corresponding to the i-th similar case. Let i be the overmining rate corresponding to the i-th similar case. Let be the peak vibration velocity of the particle corresponding to the i-th similar case.

5. The construction data analysis and optimization method based on the tunnel excavation integrated management system as described in claim 4, characterized in that, Based on the obtained initial prediction results and correction factors, a comprehensive prediction is made to obtain the expected results, specifically: in, The median block size is the result of comprehensive prediction. The over-excavation rate is a comprehensive prediction. To comprehensively predict the peak vibration velocity of the particles, The half-hole ratio is the half-hole ratio recalculated using the corrected over-excavation ratio.

6. The construction data analysis and optimization method based on the tunnel excavation integrated management system as described in claim 1, characterized in that, The updating of the correction factor in the optimization model specifically includes the following processing steps: Based on the obtained deviation, when the parameter meets the condition of consecutive preset number of same-direction deviations and the deviation exceeds 15%, the correction factor is updated. The specific update process is as follows: in, This is the updated median block size correction factor. This is the updated over-excavation rate correction factor. This is the updated peak particle velocity correction factor. This is the previous median block size correction factor. This is the over-excavation rate correction factor from before. This is the previous peak particle vibration velocity correction factor. The actual median block size, This represents the actual over-excavation rate. This represents the actual peak vibration velocity of the particle. The median block size predicted by the physical model. The over-excavation rate predicted by the physical model. This refers to the peak vibrational velocity of the particles predicted by the physical model.

7. The construction data analysis and optimization method based on a tunnel excavation integrated management system as described in claim 1, characterized in that, When the overall score exceeds the preset threshold, the current blasting design scheme is added to the historical case design-effect relationship database to update the database and thus affect the optimization of subsequent schemes.

8. A construction data analysis and optimization system based on a tunnel excavation integrated management system, characterized in that, include: The data acquisition unit is used to acquire historical point cloud data of the tunnel face before and after blasting, time-series data and trajectory data of the drilling process, acoustic signals and spectral characteristics, as well as charge records and equipment consumption statistics from the tunnel excavation integrated management system. After data preprocessing and feature engineering, geological features, design features and effect features are obtained respectively. The similar case set construction unit is used to filter similar cases from a pre-built historical case design-effect relationship database based on the current geological characteristics and through similarity calculation to obtain a similar case set. The historical case design-effect relationship database is constructed based on the geological characteristics, design characteristics, effect characteristics, and blasting comprehensive scores of historical cases. The design scheme recommendation unit is used to obtain recommended blasting design schemes and their expected effects based on current geological characteristics, blastability index, obtained similar case set, preset engineering constraints and engineering priorities, through a pre-constructed optimization model that integrates experience and mechanism. The analysis and optimization unit is used to perform tunnel blasting based on the recommended blasting design scheme and acquire data through step one; perform a quantitative evaluation of the actual effect based on the acquired data to obtain the actual effect of the current blasting design scheme; update the correction factor in the optimization model based on the deviation between the actual effect and the expected effect; repeat the above process until the construction of the current tunnel is completed.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and running thereon, wherein the processor executes the program to implement the construction data analysis and optimization method based on a tunnel excavation integrated management system as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the construction data analysis and optimization method based on a tunnel excavation integrated management system as described in any one of claims 1-7.

Images