Double-pipe curtain construction control method and system based on machine learning

Abstract

The invention relates to the technical field of pipe-roofing construction control, in particular to a double-pipe-roofing construction control method and system based on machine learning, and the method comprises the steps: building a soil body model covering various possibilities according to the parameters through deep analysis of various basic parameters of a construction soil body before double-pipe-roofing construction; therefore, the construction quality, the safety, the efficiency and the stability of each construction strategy under different soil body conditions are comprehensively and deeply explored, and the adaptive capacity of each construction strategy is accurately judged, so that the optimal construction strategy is selected to be used for double-pipe curtain construction, and in the actual construction process of the double-pipe curtain, the construction efficiency of the double-pipe curtain is improved. Whether the construction strategy needs to be intervened and controlled or not is dynamically analyzed, and after it is determined that intervention and control are needed, by means of an efficient and accurate screening mechanism, key factors such as the rectification cost, the integrating degree with existing working conditions and the actual performance effect are comprehensively considered, and the most appropriate strategy is rapidly selected for management and control.

Description

Technical Field

[0001] The present invention relates to the technical field of pipe-roof construction control, and more specifically, to a double-tube pipe-roof construction control method and system based on machine learning. Background Art

[0002] In the field of underground engineering, double-tube pipe curtain construction has been widely used in scenarios such as subway crossings and integrated pipeline corridor construction due to its advantages such as non-excavation and good support effects. However, traditional construction methods face significant technical bottlenecks: on the one hand, soil parameters (such as cohesion, internal friction angle, etc.) have natural variability and survey limitations. Traditional single-parameter modeling cannot cover the diversity of actual working conditions, resulting in significant differences between finite element simulation results and on-site results. On the other hand, the selection and adjustment of construction strategies are highly dependent on the experience of engineers and lack a quantitative evaluation system. For example, the determination of key parameters such as jacking sequence and load mode is often based on historical case analogies, and it is difficult to dynamically adapt to fluctuations in soil parameters, resulting in frequent problems such as excessive jacking force and lock stress concentration during construction. Multiple work stoppages are required to adjust strategies, resulting in high construction delay rates and overall costs.

[0003] Existing research attempts to rehearse construction through finite element simulations, but these efforts fail to establish a quantitative correlation between soil parameter variation and strategy adaptation. A few intelligent systems, while incorporating machine learning, focus solely on optimizing a single metric (such as settlement) and lack coordinated control of multi-dimensional construction objectives (safety, quality, and efficiency). Therefore, systematically addressing core issues such as soil uncertainty and delayed strategy adjustments, while achieving intelligent and precise management of dual-tube curtain construction, remains a pressing technical challenge for the industry.

[0004] Based on the above content, the present application discloses a double-tube pipe curtain construction control method and system based on machine learning. Summary of the Invention

[0005] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a double-tube pipe curtain construction control method and system based on machine learning.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The double-tube pipe curtain construction control method based on machine learning has the following steps:

[0008] Step 1: Build a soil double-tube construction simulation model for each set of construction soil variation parameters;

[0009] Step 2: Define construction strategy;

[0010] Step 3: Select and execute a comprehensive strategy;

[0011] Step 4: Regularly determine whether the overall strategy should be adjusted;

[0012] Step 5: After the adjustment is determined, the target replacement strategy is switched to the execution replacement strategy for double-tube curtain construction control.

[0013] Furthermore, the dual-tube pipe-roof construction control system based on machine learning includes:

[0014] The construction soil model building unit obtains various basic parameters of the construction soil before the double-tube pipe curtain is constructed, further generates multiple sets of construction soil variation parameters, and then builds a soil double-tube construction simulation model for each set of construction soil variation parameters;

[0015] The double-tube-roof construction strategy adaptation selection unit defines multiple construction strategies, determines the basic construction parameters of the double-tube-roof, further determines the strategy variation adaptation values ​​of various construction strategies, and then selects the overall strategy to be implemented. The actual double-tube-roof construction is carried out according to the implementation of the overall strategy.

[0016] The construction strategy optimization and analysis unit regularly determines whether adjustments to the overall implementation strategy are needed during the construction of the double-tube curtain.

[0017] The construction strategy optimization control unit, when determining that the execution of the comprehensive strategy needs to be adjusted, marks the execution of the comprehensive strategy as the target replacement strategy, and switches the target replacement strategy to the execution replacement strategy to perform double-tube pipe curtain construction control.

[0018] Furthermore, the generation process of multiple construction soil variation parameter sets is as follows: determining the parameter variation interval of each basic parameter, further generating multiple variation parameters of each basic parameter, and randomly combining the variation parameters of each basic parameter to generate multiple construction soil variation parameter sets.

[0019] Furthermore, the process of determining the strategy variation adaptation value of the construction strategy is as follows: select a construction strategy, import the construction control parameters corresponding to this construction strategy and the basic construction parameters of the double-tube pipe curtain into the soil double-tube construction simulation model of each construction soil variation parameter set respectively, further obtain the pipe curtain construction evaluation value of the soil double-tube construction simulation model corresponding to each construction soil variation parameter set, perform cumulative average calculation on the pipe curtain construction evaluation values ​​of the soil double-tube construction simulation model corresponding to all construction soil variation parameter sets, calculate the mean of the pipe curtain construction evaluation, obtain the mean of the variation parameter evaluation difference, perform difference calculation on the mean of the pipe curtain construction evaluation and the mean of the variation parameter evaluation difference, and calculate the strategy variation adaptation value of the construction strategy.

[0020] Furthermore, the process of obtaining the mean difference of variation parameter estimation is as follows: all the construction soil variation parameter sets corresponding to the pipe curtain construction estimation values ​​of the soil double-tube construction simulation model are compared pairwise, the absolute difference between each two compared pipe curtain construction estimation values ​​is calculated, and the variation parameter estimation difference value is calculated, and all the variation parameter estimation difference values ​​are cumulatively averaged to calculate the mean difference of variation parameter estimation.

[0021] Furthermore, each set of construction soil variation parameters corresponds to the pipe curtain construction evaluation value of the soil double-tube construction simulation model, and the acquisition process is as follows: the soil double-tube construction simulation model is controlled to perform simulated construction. During the simulated construction, various safety and quality monitoring data of the double-tube pipe curtain construction are collected in real time. After the simulated construction is completed, the simulated construction duration is determined, and the collected safety and quality monitoring data are simultaneously extracted to extract various safety and quality monitoring features. The various safety and quality monitoring features are integrated into a comprehensive safety and quality monitoring feature set in the form of a feature set, and the comprehensive safety and quality monitoring feature set is imported into the safety and quality control machine learning model. The safety and quality control machine learning model derives a comprehensive safety and quality evaluation value, and the comprehensive safety and quality evaluation value is ratioed with the simulated construction duration to calculate the pipe curtain construction evaluation value.

[0022] Furthermore, it is determined regularly whether the implementation of the comprehensive strategy needs to be adjusted: various safety and quality monitoring data of the double-tube pipe-curtain construction are collected in real time, and the pipe-curtain construction evaluation value of the double-tube pipe-curtain construction is updated regularly. When the pipe-curtain construction evaluation value of the double-tube pipe-curtain construction is less than the construction evaluation threshold, it is determined that the implementation of the comprehensive strategy needs to be adjusted.

[0023] Furthermore, the selection process of the execution replacement strategy is as follows: the remaining construction strategies are marked as control optimization strategies, the control replacement value of each control optimization strategy is further determined, and the control optimization strategy with the largest control replacement value is marked as the execution replacement strategy.

[0024] Furthermore, the steps for determining the control substitution value of the control optimization strategy are as follows: select a control optimization strategy, obtain the various construction control parameters corresponding to the control optimization strategy, perform vector processing on the various construction control parameters, and sequentially splice them into a one-dimensional vector A = (a1, a2, ..., a N ), N is the total number of construction control parameters, obtain the construction control parameters corresponding to the target replacement strategy, and perform vector processing on each construction control parameter, and splice them into a one-dimensional vector B=(b1,b2,...,b N ),pass The strategy similarity is calculated, and the strategy variation adaptation value of the control optimization strategy is obtained synchronously. The strategy variation adaptation value is multiplied by the strategy similarity to calculate the control substitution value of the control optimization strategy.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] Before carrying out double-tube pipe-roof construction, the system of the present invention conducts an in-depth analysis of the basic parameters of the construction soil and builds a soil model covering multiple possibilities based on these parameters. This allows for a comprehensive and in-depth exploration of the construction quality, safety, efficiency, and stability of various construction strategies under different soil conditions, accurately determining the adaptability of each construction strategy and selecting the optimal construction strategy for double-tube pipe-roof construction. During the actual construction of the double-tube pipe-roof, a dynamic analysis is performed to determine whether intervention and control of the construction strategy is necessary. Once intervention and control are determined, the system, with its efficient and accurate screening mechanism, comprehensively considers key factors such as rectification costs, compatibility with existing working conditions, and actual performance, to quickly select the most appropriate strategy for control.

[0027] The method of the present invention effectively overcomes the problems of insufficient soil uncertainty and untimely strategy adjustment in traditional construction methods, significantly improves the overall quality, safety and construction efficiency of double-tube pipe-curtain construction, and provides strong support for the intelligent and precise management of underground engineering construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a flow chart of the method of the present invention;

[0029] Figure 2 A flow chart for determining the strategy variation adaptation value of the construction strategy of the present invention;

[0030] Figure 3 Flowchart for obtaining estimated value for pipe roof construction. DETAILED DESCRIPTION

[0031] Example 1, as Figure 1 ,The double-tube pipe curtain construction control method based on machine learning,the steps are as follows:

[0032] Step 1: Build a soil double-tube construction simulation model for each set of construction soil variation parameters;

[0033] Step 2: Define construction strategy;

[0034] Step 3: Select and execute a comprehensive strategy;

[0035] Step 4: Regularly determine whether the overall strategy should be adjusted;

[0036] Step 5: After the adjustment is determined, the target replacement strategy is switched to the execution replacement strategy for double-tube curtain construction control.

[0037] The above method effectively overcomes the problems of traditional construction methods such as insufficient response to soil uncertainty and untimely strategy adjustments, significantly improving the overall quality, safety and construction efficiency of double-tube pipe-curtain construction, and providing strong support for the intelligent and precise management of underground engineering construction.

[0038] Example 2, as Figures 2 to 3 The double-tube-curtain construction control system based on machine learning includes a construction soil model building unit, a double-tube-curtain construction strategy adaptation selection unit, a construction strategy optimization analysis unit, and a construction strategy optimization control unit.

[0039] The construction soil model building unit obtains various basic parameters of the construction soil before the construction of the double-tube pipe curtain (basic parameters include but are not limited to the following parameters: density, cohesion, internal friction angle, elastic modulus, Poisson's ratio, natural moisture content, compression modulus, etc. The basic parameters are obtained through corresponding experiments on the construction soil before construction) and determines the parameter variation range of each basic parameter (each basic parameter is compared with a parameter variation range. The parameter variation range refers to the reasonable fluctuation range of the basic parameters corresponding to the construction land when the double-tube pipe curtain is actually constructed later. It is used to predict the possible variation range of soil parameters during the construction process. This process is to deal with soil uncertainty. The core link of the construction process is to convert the natural variability of soil parameters and the impact of construction disturbances into quantifiable intervals, providing a clear basis for design, construction and risk control), further generate multiple variation parameters of each basic parameter (the multiple variation parameters of a basic parameter are different, and each variation parameter is randomly selected based on the parameter variation interval), randomly combine the variation parameters of each basic parameter, and generate multiple construction soil variation parameter sets (each construction soil variation parameter set contains a variation parameter of each basic parameter), and then build a soil double-tube construction simulation model for each construction soil variation parameter set.

[0040] The process of building a soil double-tube construction simulation model based on a set of construction soil variation parameters is as follows: Based on the construction soil variation parameter set, a soil entity is constructed in general finite element software. The range of the soil entity is usually 5-8 times the diameter of the pipe curtain (for example, the pipe curtain burial depth H = 10m, and the soil entity height is 50m). The properties of the soil entity are defined, and loads and boundary conditions are applied. The boundary conditions are: fixed displacement at the bottom of the soil (Ux = Uy = 0), constrained horizontal displacement on both sides (Ux = 0), and the surface is a free boundary. A contact element (Contact) is set between the steel pipe and the soil, and the friction coefficient is defined (μ = 0.3-0.5, adjusted according to the soil type). Load application: Soil self-weight: Gravity load is automatically generated by defining the soil density (ρ), and the soil double-tube construction simulation model is constructed.

[0041] The double-tube curtain construction strategy adapts to the selection unit and defines multiple construction strategies (the construction strategy is manually defined, and the construction control parameters between each construction strategy are different. For example, there are differences in the jacking load, jacking speed, double-tube jacking sequence and other construction control parameters between each construction strategy. For example, construction strategy A adopts double-tube synchronous jacking, and the left and right tube jacking loads are applied simultaneously at 900kN. The double tubes are jacked synchronously at 8mm / min. In construction strategy B, the left tube is jacked first and the right tube is jacked later. The left tube is jacked using graded loading, and the initial load is 800kN. The load was gradually increased to 1300 kN, and then reduced to 1100 kN during the double-tube coordination stage. The jacking speed was 10 to 15 mm / min for the left tube and 12 mm / min for the right tube. The basic construction parameters of the double-tube pipe curtain were determined (the construction parameters of the double-tube pipe curtain included the outer diameter, wall thickness, construction spacing, burial depth, and equivalent stiffness parameters of the double-tube lock connection). The strategy variation adaptation values ​​of various construction strategies were further determined. The construction strategy with the largest strategy variation adaptation value was marked as the implementation comprehensive strategy, and actual double-tube pipe curtain construction was carried out according to the implementation comprehensive strategy.

[0042] The process of determining the strategy variation adaptation value of the construction strategy is as follows: select a construction strategy, import the construction control parameters corresponding to this construction strategy and the basic construction parameters of the double-tube pipe curtain into the soil double-tube construction simulation model of each construction soil variation parameter set respectively (after importing, the soil double-tube construction simulation model can perform double-tube pipe curtain construction based on the construction strategy, create a double-tube entity in the soil double-tube construction simulation model according to the basic construction parameters of the double-tube pipe curtain, and define the material properties of the double-tube entity, and construct the double-tube entity with the construction control parameters corresponding to the construction strategy), and further obtain the soil double-tube construction simulation model corresponding to each construction soil variation parameter set. The pipe curtain construction evaluation value is calculated by accumulating and averaging the pipe curtain construction evaluation values ​​of the soil double-tube construction simulation model corresponding to all the construction soil variation parameter sets, and calculating the mean pipe curtain construction evaluation value. The pipe curtain construction evaluation values ​​of the soil double-tube construction simulation model corresponding to all the construction soil variation parameter sets are compared pairwise, and the absolute difference between each two compared pipe curtain construction evaluation values ​​is calculated to calculate the variation parameter evaluation difference value. The variation parameter evaluation difference values ​​are accumulated and averaged to calculate the variation parameter evaluation difference mean. The difference calculation is performed between the pipe curtain construction evaluation mean and the variation parameter evaluation difference mean, and the strategy variation adaptation value of the construction strategy is calculated.

[0043] Each set of construction soil variation parameters corresponds to the pipe curtain construction evaluation value of the soil double-tube construction simulation model. The acquisition process is as follows: control the soil double-tube construction simulation model to perform simulated construction. During the simulated construction, various safety and quality monitoring data of the double-tube pipe curtain construction are collected in real time (safety and quality monitoring data include surface settlement data, lock shear stress, soil horizontal displacement data, steel pipe front end axial force, mid-span bending moment. The purpose of collecting these safety and quality monitoring data is to control the safety and quality of the double-tube pipe curtain construction). After the simulated construction is completed, the simulated construction time is determined (the total time from the start of the simulated construction to the completion of the simulated construction), and the acquisition time is simultaneously Feature extraction is performed on the various safety and quality monitoring data collected, and various safety and quality monitoring features are extracted (taking surface settlement data as an example, features such as maximum settlement and settlement rate can be extracted; taking lock shear stress as an example, features such as stress mean and stress fluctuation amplitude can be extracted). Various safety and quality monitoring features are integrated into a comprehensive safety and quality monitoring feature set in the form of a feature set, and the comprehensive safety and quality monitoring feature set is imported into the safety and quality control machine learning model. The safety and quality control machine learning model derives a comprehensive safety and quality evaluation value, and the ratio of the comprehensive safety and quality evaluation value to the simulated construction time is calculated to calculate the pipe curtain construction evaluation value.

[0044] The steps for building a safety and quality control machine learning model are as follows: Multiple comprehensive safety and quality monitoring feature sets are collected, a neural network model is constructed, and the constructed neural network model is trained using the comprehensive safety and quality monitoring feature sets as the basic data. During the training process, each comprehensive safety and quality monitoring feature set is assigned a comprehensive safety and quality assessment value. The comprehensive safety and quality assessment value ranges from 1 to 100. The size of the comprehensive safety and quality assessment value has a clear meaning: a larger value indicates better construction quality, higher safety, and higher efficiency in double-tube pipe-roof construction. The multiple comprehensive safety and quality monitoring feature sets are then divided into training, validation, and test sets according to a specific ratio of 70%:15%:15%. The neural network model is repeatedly trained using the training set, and its performance during the training phase is verified using the validation set. Model parameters are adjusted based on the verification results. Hyperparameter tuning, overfitting prevention, and training monitoring are implemented. The final model is evaluated using a test set that was not involved in training to ensure that the results are independent of data snooping during the training process. Finally, the safety and quality control machine learning model is completed.

[0045] The construction strategy optimization and analysis unit collects various safety and quality monitoring data of the double-tube pipe curtain construction in real time during the double-tube pipe curtain construction process, and regularly updates the pipe curtain construction evaluation value of the double-tube pipe curtain construction (the corresponding periodic time interval is set according to the actual needs of the double-tube pipe curtain construction). When the pipe curtain construction evaluation value of the double-tube pipe curtain construction is less than the construction evaluation threshold (the construction evaluation threshold is set based on construction standards, risk tolerance, historical data experience and regulatory requirements), it is determined that the implementation of the comprehensive strategy needs to be adjusted (otherwise, there is no need to adjust the implementation of the comprehensive strategy).

[0046] The construction strategy optimization control unit, when determining that the execution of the comprehensive strategy needs to be adjusted, marks the execution of the comprehensive strategy as the target replacement strategy, marks the remaining construction strategies as the control optimization strategies, further determines the control substitution value of each control optimization strategy, marks the control optimization strategy with the largest control substitution value as the execution replacement strategy, and switches the target replacement strategy to the execution replacement strategy for double-tube and pipe-curtain construction control.

[0047] The specific steps for determining the control substitution value of the control optimization strategy are as follows: select a control optimization strategy, obtain the various construction control parameters corresponding to the control optimization strategy, perform vector processing on the various construction control parameters, and sequentially splice them into a one-dimensional vector A = (a1, a2, ..., a N ), N is the total number of construction control parameters (construction control parameters include but are not limited to the following: jacking sequence, left pipe initial jacking force, left pipe maximum jacking force, right pipe initial jacking force, right pipe maximum jacking force, vector processing method, taking the jacking sequence as an example, the synchronous jacking vector is 0, and the left-first-right-later jacking vector is 1), obtain the various construction control parameters corresponding to the target replacement strategy, perform vector processing on each construction control parameter, and splice them in sequence into a one-dimensional vector B = (b1, b2, ..., b N ),pass The strategy similarity is calculated, and the strategy variation adaptation value of the control optimization strategy is obtained synchronously. The strategy variation adaptation value is multiplied by the strategy similarity to calculate the control substitution value of the control optimization strategy.

[0048] Before carrying out double-tube pipe-roof construction, the above-mentioned system conducts an in-depth analysis of the basic parameters of the construction soil and builds a soil model covering various possibilities based on these parameters. This allows for a comprehensive and in-depth exploration of the construction quality, safety, efficiency, and stability of various construction strategies under different soil conditions, accurately determines the adaptability of each construction strategy, and thus selects the optimal construction strategy for double-tube pipe-roof construction. During the actual construction of the double-tube pipe-roof, a dynamic analysis is performed to determine whether intervention and control of the construction strategy is necessary. Once intervention and control are determined to be necessary, the system uses an efficient and accurate screening mechanism to comprehensively consider key factors such as rectification costs, compatibility with existing working conditions, and actual performance effects to quickly select the most appropriate strategy for control.

[0049] The above formulas are all dimensionless and numerically calculated, and the preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0050] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0051] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0052] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0053] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0054] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0055] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0056] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A double-tube pipe-roof construction control method based on machine learning, characterized in that: Here are the steps: Step 1: Build a soil double-tube construction simulation model for each set of construction soil variation parameters; Step 2: Define construction strategy; Step 3: Select and execute a comprehensive strategy; Step 4: Regularly determine whether the overall strategy should be adjusted; Step 5: After the adjustment is determined, the target replacement strategy is switched to the execution replacement strategy for double-tube curtain construction control.

2. A double-tube-roof construction control system based on machine learning, applied to the double-tube-roof construction control method based on machine learning according to claim 1, characterized in that: include: The construction soil model building unit obtains various basic parameters of the construction soil before the double-tube pipe curtain is constructed, further generates multiple sets of construction soil variation parameters, and then builds a soil double-tube construction simulation model for each set of construction soil variation parameters; The double-tube-roof construction strategy adaptation selection unit defines multiple construction strategies, determines the basic construction parameters of the double-tube-roof, further determines the strategy variation adaptation values ​​of various construction strategies, and then selects the overall strategy to be implemented. The actual double-tube-roof construction is carried out according to the implementation of the overall strategy. The construction strategy optimization and analysis unit regularly determines whether adjustments to the overall implementation strategy are needed during the construction of the double-tube curtain. The construction strategy optimization control unit, when determining that the execution of the comprehensive strategy needs to be adjusted, marks the execution of the comprehensive strategy as the target replacement strategy, and switches the target replacement strategy to the execution replacement strategy to perform double-tube pipe curtain construction control.

3. The dual-tube pipe-roof construction control system based on machine learning according to claim 2 is characterized in that: The generation process of multiple construction soil variation parameter sets is as follows: determine the parameter variation interval of each basic parameter, further generate multiple variation parameters of each basic parameter, and randomly combine the variation parameters of each basic parameter to generate multiple construction soil variation parameter sets.

4. The dual-tube pipe-roof construction control system based on machine learning according to claim 2 is characterized in that: The process of determining the strategy variation adaptation value of the construction strategy is as follows: select a construction strategy, import the construction control parameters and basic construction parameters of the double-tube pipe curtain corresponding to this construction strategy into the soil double-tube construction simulation model of each construction soil variation parameter set, further obtain the pipe curtain construction evaluation value of the soil double-tube construction simulation model corresponding to each construction soil variation parameter set, add up and average the pipe curtain construction evaluation values ​​of the soil double-tube construction simulation model corresponding to all construction soil variation parameter sets, calculate the mean of the pipe curtain construction evaluation, obtain the mean of the variation parameter evaluation difference, perform difference calculation on the mean of the pipe curtain construction evaluation and the mean of the variation parameter evaluation difference, and calculate the strategy variation adaptation value of the construction strategy.

5. The dual-tube pipe-roof construction control system based on machine learning according to claim 4 is characterized in that: The process of obtaining the mean difference of variation parameter estimation is as follows: all the construction soil variation parameter sets corresponding to the pipe curtain construction estimation values ​​of the soil double-tube construction simulation model are compared pairwise, the absolute difference between each two compared pipe curtain construction estimation values ​​is calculated to obtain the variation parameter estimation difference value, and all the variation parameter estimation difference values ​​are cumulatively averaged to calculate the mean difference of variation parameter estimation.

6. The dual-tube pipe-roof construction control system based on machine learning according to claim 4 is characterized in that: Each set of construction soil variation parameters corresponds to the pipe curtain construction evaluation value of the soil double-tube construction simulation model. The acquisition process is as follows: the soil double-tube construction simulation model is controlled to perform simulated construction. During the simulated construction process, various safety and quality monitoring data of the double-tube pipe curtain construction are collected in real time. After the simulated construction is completed, the simulated construction duration is determined, and feature extraction is performed on the collected various safety and quality monitoring data simultaneously to extract various safety and quality monitoring features. The various safety and quality monitoring features are integrated into a comprehensive safety and quality monitoring feature set in the form of a feature set, and the comprehensive safety and quality monitoring feature set is imported into the safety and quality control machine learning model. The safety and quality control machine learning model derives a comprehensive safety and quality evaluation value, and the comprehensive safety and quality evaluation value is ratioed with the simulated construction duration to calculate the pipe curtain construction evaluation value.

7. The dual-tube pipe-roof construction control system based on machine learning according to claim 2 is characterized in that: Regularly determine whether adjustments to the overall strategy need to be made: Real-time collection of various safety and quality monitoring data for double-tube pipe-curtain construction is conducted, and the pipe-curtain construction evaluation value of the double-tube pipe-curtain construction is regularly updated. When the pipe-curtain construction evaluation value of the double-tube pipe-curtain construction is less than the construction evaluation threshold, it is determined that adjustments to the overall strategy need to be made.

8. The dual-tube pipe-roof construction control system based on machine learning according to claim 2 is characterized in that: The selection process of the execution replacement strategy is as follows: mark the remaining construction strategies as control optimization strategies, further determine the control replacement value of each control optimization strategy, and mark the control optimization strategy with the largest control replacement value as the execution replacement strategy.

9. The dual-tube-roof construction control system based on machine learning according to claim 2 is characterized in that: The specific steps for determining the control substitution value of the control optimization strategy are as follows: select a control optimization strategy, obtain the various construction control parameters corresponding to the control optimization strategy, perform vector processing on the various construction control parameters, and sequentially splice them into a one-dimensional vector A = (a1, a2, ..., a N ), N is the total number of construction control parameters, obtain the construction control parameters corresponding to the target replacement strategy, and perform vector processing on each construction control parameter, and splice them into a one-dimensional vector B=(b1,b2,...,b N ),pass The strategy similarity is calculated, and the strategy variation adaptation value of the control optimization strategy is obtained synchronously. The strategy variation adaptation value is multiplied by the strategy similarity to calculate the control substitution value of the control optimization strategy.

Images