Shotcrete construction optimization method and system combined with spatial positioning

Abstract

The present invention discloses a method and system for optimizing shotcrete construction combined with spatial positioning, and relates to the technical field related to shotcrete. The method includes: dividing the tunnel section to be constructed based on the wet spraying machine model to determine multiple construction areas; collecting surface point cloud data for three-dimensional modeling, optimizing the sequence of spraying operations with the goal of minimizing the equipment idle time and repeated spraying coverage; optimizing the spraying construction parameters of each construction area in turn according to the optimal block spraying sequence with the goal of minimizing the amount of concrete rebound; and executing the spraying operation of the tunnel section to be constructed according to the optimal construction parameter sequence. The method solves the technical problems existing in the prior art, such as large rebound, poor density, poor durability, high amount of adhesive used, and unstable material adaptability, which lead to poor quality and efficiency of shotcrete construction and high material consumption, and achieves the technical effect of reducing material consumption and improving the quality and efficiency of shotcrete construction.

Description

Technical Field

[0001] The present application relates to the technical field related to shotcrete, and in particular to a shotcrete construction optimization method and system combined with spatial positioning. Background Art

[0002] In recent years, shotcrete technology has been widely used in tunnel construction projects, primarily due to its simple process, efficient construction, unique effects, and economical construction costs. However, despite its significant advantages in certain aspects, shotcrete technology still fails to fully meet the needs of modern engineering technology development compared to traditional mold-forming concrete materials and technologies. In particular, during the construction process of shotcrete, the key material for shotcrete preparation—shotcrete accelerators—has experienced rapid development. Alkali-free liquid accelerator technology has gradually matured, providing a material foundation for the high-performance development of shotcrete. At the same time, the shotcrete forming process has gradually transitioned from dry to wet spraying. Construction equipment is also gradually being domestically produced and intelligently controlled, resulting in significant improvements in the working environment and project quality. However, due to the inherent characteristics of shotcrete construction, problems such as large rebound, poor density, high adhesive usage, and unstable material adaptability still exist, resulting in poor durability of shotcrete, affecting the overall construction quality and efficiency of shotcrete.

[0003] Therefore, the current related technologies have the following technical problems: large rebound, poor density, poor durability, high amount of adhesive used and unstable material adaptability, which lead to poor quality and efficiency of shotcrete construction and high material consumption. Summary of the Invention

[0004] This application solves the technical problems in the prior art such as large rebound, poor density, poor durability, high amount of adhesive used and unstable material adaptability, which lead to poor quality and efficiency of shotcrete construction and high material consumption, by providing a shotcrete construction optimization method and system combined with spatial positioning. It achieves the technical effect of reducing material consumption and improving the quality and efficiency of shotcrete construction.

[0005] The present application provides a shotcrete construction optimization method combined with spatial positioning, the method comprising: dividing a tunnel section to be constructed based on a wet shotcrete machine model to determine a plurality of construction areas; collecting surface point cloud data of the plurality of construction areas for three-dimensional modeling, and using the plurality of three-dimensional models of the construction areas to optimize the sequence of shotcrete operations with the goal of minimizing equipment idle time and repeated shotcrete coverage to obtain an optimal block shotcrete sequence; combining the current concrete mix ratio, surrounding rock feature information, construction environment information and the plurality of three-dimensional models of the construction areas, with the goal of minimizing concrete rebound, optimizing and analyzing the shotcrete construction parameters of each construction area in turn according to the optimal block shotcrete sequence to obtain an optimal construction parameter sequence; and executing the shotcrete operation of the tunnel section to be constructed according to the optimal construction parameter sequence.

[0006] In a possible implementation, the shotcrete construction optimization method combined with spatial positioning also performs the following processing: obtaining several wet spraying machine models of several operable wet spraying machines and several maximum spraying coverage ranges; based on the several maximum spraying coverage ranges, performing collaborative simulation operation analysis on the tunnel section to be constructed, and determining multiple area division schemes; performing division quality evaluation on the multiple area division schemes, selecting the area division scheme corresponding to the maximum division quality coefficient, and obtaining multiple construction areas.

[0007] In a possible implementation, the shotcrete construction optimization method combined with spatial positioning further performs the following processing: obtaining multiple area division schemes, wherein each area division scheme is identified by the number of areas and a number of wet spraying machine operation times; performing variance calculations on the number of wet spraying machine operations of each area division scheme respectively to determine multiple operation time variances; and obtaining multiple division quality coefficients by weighted calculation based on the variances of the multiple number of areas and the multiple number of operations, wherein the division quality coefficient is negatively correlated with the variance of the number of areas and the number of operations.

[0008] In a possible implementation, the shotcrete construction optimization method combined with spatial positioning also performs the following processing: based on the multiple construction areas, the spraying operation sequence is enumerated in combination with several wet spraying machines to generate multiple initial block spraying sequences; the first initial block spraying sequence is randomly selected, and in the spraying operation simulation space, the three-dimensional models of multiple construction areas are used in combination with several wet spraying machines to simulate the spraying operation, and the simulated idle time of several wet spraying machines and the repeated spraying coverage area of multiple construction areas are counted to calculate the first equipment idle time and the first repeated spraying coverage rate; the first sequence fitness is calculated based on the first equipment idle time and the first repeated spraying coverage rate; the multiple sequence fitnesses of the multiple initial block spraying sequences are analyzed in turn, and the initial block spraying sequence with the largest sequence fitness is selected as the optimal block spraying sequence.

[0009] In a possible implementation, the shotcrete construction optimization method combined with spatial positioning also performs the following processing: configuring the first weight and the second weight according to the construction work requirements, wherein the first weight is the work efficiency weight and the second weight is the material loss weight; based on the first weight and the second weight, the inverse of the idle time of the first equipment and the inverse of the first repeated spraying coverage are weightedly calculated to obtain the first sequential fitness.

[0010] In a possible implementation, the shotcrete construction optimization method combined with spatial positioning also performs the following processing: selecting the first shotcrete operation area and the first wet shotcrete machine in the optimal block shotcrete sequence, and obtaining the first shotcrete construction parameters of the first wet shotcrete machine; constructing a first concrete rebound prediction plug-in based on the three-dimensional model of the first construction area, the current concrete mix ratio, the surrounding rock feature information and the construction environment information in combination with a feedforward neural network; using the first concrete rebound prediction plug-in, with the goal of minimizing the amount of concrete rebound, optimizing the first shotcrete construction parameters, obtaining the first optimal shotcrete construction parameters, and adding them to the optimal construction parameter sequence in sequence.

[0011] In a possible implementation, the shotcrete construction optimization method combined with spatial positioning also performs the following processing: obtaining the first surface feature distribution of the three-dimensional model of the first construction area, and expanding the first surface feature distribution, the current concrete mix ratio, the surrounding rock feature information and the construction environment information according to the predetermined tolerance range to obtain similarity comparison conditions; using the similarity comparison conditions as conditional constraints and the first wet spraying machine as the equipment constraint, obtaining a sample shotcrete construction parameter set based on big data retrieval, and counting the concrete rebound amount after different sample shotcrete construction parameters are used to construct a sample concrete rebound amount set; using the sample shotcrete construction parameter set and the sample concrete rebound amount set to train a feedforward neural network until the model converges, and obtaining a first concrete rebound prediction plug-in.

[0012] In a possible implementation, the shotcrete construction optimization method combined with spatial positioning further performs the following processing: obtaining a first shotcrete construction parameter threshold of a first wet shotcrete machine, wherein the first shotcrete construction parameter includes the wind speed, spraying distance, spraying angle, and layer thickness of the wet shotcrete machine; randomly selecting multiple initial construction parameters within the first shotcrete construction parameter threshold; using the first concrete rebound prediction plug-in, respectively predicting the multiple initial construction parameters and outputting multiple predicted rebound amounts; based on the multiple predicted rebound amounts, optimizing the first shotcrete construction parameters to obtain the first optimal shotcrete construction parameters.

[0013] In a possible implementation, the shotcrete construction optimization method combined with spatial positioning further performs the following processing: taking the initial construction parameters as the initial solution, sorting the multiple initial construction parameters from small to large according to the predicted rebound amount to generate an initial solution sequence; setting the first K solutions of the initial solution sequence as optimal solutions, and setting the last J solutions as inferior solutions, where J is M times K, and M is an integer greater than 2; using the K optimal solutions to perform equivalue clustering on the J inferior solutions to obtain K solution thresholds, and within the K solution thresholds, adjusting the inferior solutions in the direction of the optimal solution according to the optimal step length. The K updated solution thresholds are obtained, where if the adjusted inferior solution does not meet the first shotcrete construction parameter threshold, no adjustment is performed; the first concrete rebound prediction plug-in is used to predict the rebound amount of the inferior solutions of the K updated solution thresholds, and K updated solution thresholds are identified. If the predicted rebound amount of the updated inferior solution within the same updated solution threshold is less than the predicted rebound amount of the optimal solution, the inferior solution is used to replace the optimal solution; iterative optimization is performed until a predetermined number of convergences is reached, K current solution thresholds are output, and the solution with the current minimum predicted rebound amount is selected as the first optimal shotcrete construction parameter.

[0014] The present application also provides a shotcrete construction optimization system combined with spatial positioning, including: a construction area determination module, which is used to divide the tunnel section to be constructed in combination with the wet spraying machine model and determine multiple construction areas; an optimal block spraying sequence acquisition module, which is used to collect surface point cloud data of the multiple construction areas for three-dimensional modeling, and use multiple three-dimensional models of construction areas to optimize the spraying operation sequence with the goal of minimizing equipment idle time and repeated spraying coverage to obtain the optimal block spraying sequence; an optimal construction parameter sequence acquisition module, which is used to combine the current concrete mix ratio, surrounding rock feature information, construction environment information and the multiple three-dimensional models of construction areas, with the goal of minimizing concrete rebound, and optimize and analyze the spraying construction parameters of each construction area in turn according to the optimal block spraying sequence to obtain the optimal construction parameter sequence; a tunnel spraying operation execution module, which is used to execute the spraying operation of the tunnel section to be constructed according to the optimal construction parameter sequence.

[0015] The application proposes a shotcrete construction optimization method and system that combines spatial positioning, divides the tunnel section to be constructed in combination with the wet spraying machine model, and determines multiple construction areas; collects surface point cloud data for three-dimensional modeling, and optimizes the sequence of spraying operations with the goal of minimizing equipment idle time and repeated spraying coverage; optimizes and analyzes the spraying construction parameters of each construction area in turn according to the optimal block spraying sequence with the goal of minimizing concrete rebound; and executes the spraying operation of the tunnel section to be constructed according to the optimal construction parameter sequence. This solves the technical problems existing in the prior art, such as large rebound, poor density, poor durability, high adhesive usage, and unstable material adaptability, which lead to poor quality and efficiency of shotcrete construction and high material consumption, and achieves the technical effect of reducing material consumption and improving the quality and efficiency of shotcrete construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 A schematic flow chart of a shotcrete construction optimization method combined with spatial positioning provided in an embodiment of the present application.

[0018] Figure 2 This is a schematic diagram of the structure of the shotcrete construction optimization system combined with spatial positioning provided in an embodiment of the present application.

[0019] Explanation of reference numerals: construction area determination module 10 , optimal block spraying sequence acquisition module 20 , optimal construction parameter sequence acquisition module 30 , tunnel spraying operation execution module 40 . DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0023] The embodiment of the present application provides a method for optimizing shotcrete construction in combination with spatial positioning, such as Figure 1 As shown, the method includes:

[0024] Step S100: dividing the tunnel section to be constructed based on the type of wet spraying machine to determine multiple construction areas.

[0025] Preferably, the entire tunnel construction section is reasonably divided into several relatively independent construction units based on the model parameters of the wet spraying machine and the specific conditions of the tunnel to be constructed. The wet spraying machine is a mechanical equipment used for shotcrete construction, which is used to transport wet concrete mixed in a certain proportion to a nozzle through a concrete pump, add an accelerator at the nozzle, and use compressed air to spray the concrete at high speed onto the sprayed surface to form a concrete support layer, effectively reducing dust and rebound during the spraying process and improving the density and strength of the concrete. Specifically, based on the model performance parameters of the wet spraying machine (including spraying capacity, spraying distance and height, working efficiency, etc.), and taking into account the characteristics of the tunnel project (such as tunnel shape and size, geological conditions, construction difficulty, etc.), the tunnel section to be constructed is divided into multiple construction areas. For example, based on the spraying capacity of the wet spraying machine, the concrete spraying volume of each construction area is matched with the spraying capacity of the wet spraying machine within a certain period of time, so as to avoid excessive fatigue of the wet spraying machine or excessive spraying capacity.

[0026] Preferably, for large-section tunnels or tunnels with high heights, wet spraying machines with larger spraying distances and heights should be selected, and the tunnels should be divided into different construction areas along the height and width directions according to their performance to ensure that the wet spraying machine can effectively cover the construction surface. For circular tunnels, the tunnel circumference can be divided into several fan-shaped construction areas according to the spraying range of the wet spraying machine. For horseshoe-shaped tunnels, they can be divided into different construction areas such as the vault and side walls to facilitate the wet spraying machine to carry out targeted spraying operations. In areas with complex geological conditions and broken rocks, it may be necessary to divide the construction area into smaller areas to control the thickness and quality of the shotcrete and ensure construction safety. In areas with better geological conditions, the construction area can be appropriately increased. The construction difficulty and risk level of different parts of the tunnel vary. For example, the construction difficulty and risk level of parts such as intersections and cross-section changes in the tunnel are relatively high. By comprehensively considering the wet spraying machine model and various factors of the tunnel project, the tunnel section can be scientifically and rationally divided and multiple construction areas can be determined. This can make shotcrete construction more efficient and orderly, improve construction quality and efficiency, and reduce construction costs and risks.

[0027] Furthermore, step S100 also includes step S110, obtaining several wet spraying machine models of several operable wet spraying machines and several maximum spraying coverage ranges; step S120, based on the several maximum spraying coverage ranges, performing collaborative simulation operation analysis on the tunnel section to be constructed, and determining multiple area division schemes; step S130, performing division quality evaluation on the multiple area division schemes, selecting the area division scheme corresponding to the maximum division quality coefficient, and obtaining multiple construction areas.

[0028] Preferably, the specific model information of all wet spraying machines used for tunnel construction is obtained, that is, different models of wet spraying machines have different maximum spraying coverage due to differences in design, performance, etc., and the maximum spraying coverage of each wet spraying machine is obtained, wherein the maximum spraying coverage refers to the maximum spatial range in which the wet spraying machine can effectively spray concrete under normal working conditions, which is usually measured by parameters such as horizontal distance and vertical distance. For example, the maximum horizontal spraying distance of some models of wet spraying machines can reach 15 meters, and the maximum vertical spraying height can reach 10 meters; then the maximum spraying coverage data of the wet spraying machine determined is used in combination with the The specific shape, size, geological conditions and other information of the construction tunnel section are analyzed through collaborative simulation on a computer simulation platform. That is, the collaborative operation of multiple wet spraying machines is considered so that the entire tunnel section can be effectively sprayed with concrete, while maximizing construction efficiency, reducing equipment idleness and duplication of work, etc. Through different combinations and planning methods, a variety of different area division schemes can be obtained (i.e., multiple area division schemes are determined). For example, the tunnel can be divided into several sections along the length direction according to the horizontal spraying distance of the wet spraying machine, or the tunnel can be divided into layers along the height direction based on the height of the tunnel and the vertical spraying height of the wet spraying machine.

[0029] Preferably, for the multiple area division schemes determined, a comprehensive consideration is given to multiple factors, such as equipment utilization, construction efficiency, uniformity of concrete spraying, whether there are blind spots in spraying, etc., and a division quality evaluation is performed on the multiple area division schemes. A division quality coefficient is calculated for each scheme. The higher the coefficient, the better the scheme. Finally, the scheme with the largest division quality coefficient is selected from all the schemes. According to this scheme, the tunnel section to be constructed is divided into multiple relatively independent construction areas to ensure that each area is within the effective spraying coverage of the wet spraying machine and that the connection between the various areas is reasonable, so as to facilitate the smooth progress of subsequent spraying operations, thereby improving the quality and efficiency of tunnel shotcrete construction.

[0030] Furthermore, step S130 also includes step S131, obtaining multiple area division schemes, wherein each area division scheme is identified by the number of areas and a number of wet spraying machine operation times; step S132, performing variance calculation on the number of wet spraying machine operations of each area division scheme respectively to determine multiple operation time variances; step S133, obtaining multiple division quality coefficients based on weighted calculation of the variances of the multiple area numbers and the multiple operation times, wherein the division quality coefficient is negatively correlated with the variance of the multiple area numbers and the multiple operation times.

[0031] Preferably, for each area division scheme, the number of areas into which the tunnel section is divided is clearly recorded. For example, Scheme A may divide the tunnel into 5 areas, Scheme B may divide it into 8 areas, etc.; at the same time, the number of times each wet spraying machine needs to operate under the division scheme will also be determined. Different area divisions will result in different task allocations for the wet spraying machine, so the number of operations of the wet spraying machine in each scheme will also be different. For example, in a certain scheme, a wet spraying machine may need to operate in 3 areas, and the time and workload of each operation will also vary according to factors such as the size and shape of the area; then, each area will be divided into 5 areas. The variance calculation of the number of wet spraying machine operations under the domain division scheme is performed to understand the uniformity of the distribution of the number of wet spraying machine operations under this area division scheme. The variance is a statistic used to measure the degree of dispersion of a set of data. Taking scheme A as an example, if there are 3 wet spraying machines and the number of operations are 5, 6, and 7 respectively, the variance of this set of data can be obtained through the variance calculation formula. The larger the variance, the greater the difference in the number of operations between the wet spraying machines. It is possible that some wet spraying machines have too heavy operating tasks while some wet spraying machines are relatively idle; the smaller the variance, the more uniform the distribution of the number of operations and the relatively balanced workload of each wet spraying machine.

[0032] Preferably, a weighted calculation is performed on the variances of the number of zones and the number of operations to obtain the corresponding multiple partitioning quality coefficients. Specifically, different weights are assigned to the number of zones and the variance of the number of operations, and then a weighted calculation is performed. Generally speaking, a greater number of zones may mean greater difficulty in construction organization and coordination, and the relatively small area of each zone may cause the wet spraying machine to waste more time and resources when switching zones, so the partitioning quality coefficient will be lower. A larger variance in the number of operations indicates a more unbalanced distribution of wet spraying machine tasks, affecting construction efficiency and overall quality, which will also reduce the partitioning quality coefficient. For example, if Plan B has a large number of zones and a large variance in the number of operations, the calculated partitioning quality coefficient will be relatively small, indicating that the quality of this plan is relatively poor. On the other hand, if Plan A has a moderate number of zones and a small variance in the number of operations, its partitioning quality coefficient will be large, indicating that Plan A is superior. Through scientific quantitative methods, the quality of different zone partitioning schemes is evaluated by comprehensively considering factors such as the rationality of zone division and the balance of wet spraying machine operations, so as to select the optimal scheme and improve the overall efficiency and quality of tunnel shotcrete construction.

[0033] In step S200, surface point cloud data of the multiple construction areas are collected for three-dimensional modeling. The three-dimensional models of the multiple construction areas are used to optimize the spraying operation sequence with the goal of minimizing the equipment idle time and repeated spraying coverage to obtain the optimal block spraying sequence.

[0034] Preferably, surface point cloud data of multiple construction areas are obtained through specific measurement equipment (such as laser scanners, etc.), that is, a series of discrete points containing spatial coordinate information of the object surface. Specifically, in tunnel construction, for multiple construction areas that have been divided, a laser scanner or other equipment is used to scan the surface of each area, and the three-dimensional coordinates (x, y, z coordinates) of a large number of points on the surface as well as possible color, reflection intensity and other information are collected to obtain the surface point cloud data of each construction area. The collected point cloud data is then used to process and fit these discrete points through specialized three-dimensional modeling software (such as AutoCAD, Revit, 3ds Max, etc.) to construct a three-dimensional model of each construction area, which intuitively displays the shape, size, spatial position and other information of the construction area.

[0035] Preferably, the goal is to minimize the idle time of equipment and the repeated spraying coverage. In tunnel shotcrete construction, the use cost of equipment such as wet spraying machines is high. Excessive idle time of equipment will lead to low construction efficiency and increase construction costs. It is hoped that by reasonably arranging the sequence of spraying operations, the equipment can work as continuously as possible and reduce the waiting and idle time of equipment; repeated spraying will cause waste of concrete materials and may affect the quality and structural performance of concrete. It is necessary to try to avoid excessive repeated spraying in the same area so that the concrete spraying coverage of each area can achieve the best effect and avoid unnecessary repeated coverage; then based on the two goals, the three-dimensional models of multiple construction areas that have been constructed are used in combination with the performance parameters of equipment such as wet spraying machines. Based on the requirements of the spraying process (such as spraying range, spraying speed, etc.) and construction process (such as initial setting time of concrete, etc.), optimization algorithms (such as genetic algorithm, simulated annealing algorithm, etc.) are used to analyze and evaluate all possible spraying operation sequences, calculate the idle time of the equipment and the repeated spraying coverage rate under each operation sequence, and find the spraying operation sequence that can minimize the idle time of the equipment and the repeated spraying coverage rate through continuous comparison and screening; the spraying operation sequence that can ultimately meet the goals of minimizing the idle time of the equipment and the repeated spraying coverage rate is the optimal block spraying sequence. Performing spraying operations according to this optimal sequence can improve construction efficiency, reduce costs, ensure construction quality, and achieve optimization of tunnel shotcrete construction.

[0036] Furthermore, step S200 also includes step S210, based on the multiple construction areas, combining several wet spraying machines to enumerate the spraying operation sequence, and generate multiple initial block spraying sequences; step S220, randomly selecting the first initial block spraying sequence, in the spraying operation simulation space, using multiple three-dimensional models of the construction areas, combined with several wet spraying machines to simulate the spraying operation, counting the simulated idle time of several wet spraying machines and the repeated spraying coverage area of multiple construction areas, and calculating the first equipment idle time and the first repeated spraying coverage rate; step S230, calculating the first sequence fitness based on the first equipment idle time and the first repeated spraying coverage rate; step S240, sequentially analyzing and obtaining multiple sequence fitnesses of multiple initial block spraying sequences, and selecting the initial block spraying sequence with the maximum sequence fitness as the optimal block spraying sequence.

[0037] Preferably, on the basis of the multiple construction areas that have been divided, several wet spraying machines participating in the construction are considered, and by enumerating all possible spraying operation sequence combinations, multiple different initial block spraying sequences are obtained. For example, assuming there are 3 construction areas (A, B, C) and 2 wet spraying machines, the possible spraying sequences are A→B→C, A→C→B, B→A→C, etc. These different sequence combinations are the initial block spraying sequences; then, one is randomly selected from the multiple generated initial block spraying sequences as the first sequence to be analyzed (i.e., the first initial block spraying sequence), and in a simulated spraying operation space (which can be a virtual environment created by computer software), based on the previously established three-dimensional models of the multiple construction areas (including information such as the shape, size, spatial position, etc. of the areas), and considering the performance parameters (such as spraying range, spraying speed, etc.) of the several wet spraying machines participating in the construction, the process of performing the spraying operation according to this initial sequence is simulated.

[0038] Preferably, during the simulated spraying operation, the time that each wet spraying machine is in an idle state (i.e., no spraying operation is performed) is recorded, and the idle time of all wet spraying machines is added together to obtain the total simulated idle time, i.e., the first equipment idle time; at the same time, the area of repeated spraying in each construction area when the spraying operation is carried out in this order is counted, and the proportion of the repeated spraying area to the total area of the area is calculated to obtain the repeated spraying coverage area of multiple construction areas, and then the overall first repeated spraying coverage rate is calculated. The first equipment idle time and the first repeated spraying coverage are weightedly calculated to obtain the first sequence fitness of the initial block spraying sequence. Among them, the shorter the equipment idle time and the lower the repeated spraying coverage, the higher the sequence fitness, which means higher construction efficiency and less material waste. Each initial block spraying sequence is simulated, counted and calculated to obtain their corresponding sequence fitness. Then, the sizes of these sequence fitnesses are compared to find the initial block spraying sequence corresponding to the sequence fitness with the largest value, and this sequence is determined as the optimal block spraying sequence. In the subsequent actual tunnel shotcrete construction, operations are carried out according to this optimal block spraying sequence in the hope of achieving the best construction effect, improving construction efficiency and quality, and reducing costs.

[0039] Furthermore, step S230 also includes step S231, configuring the first weight and the second weight according to the construction work requirements, wherein the first weight is the work efficiency weight and the second weight is the material loss weight; step S232, based on the first weight and the second weight, performing a weighted calculation on the inverse of the idle time of the first equipment and the inverse of the first repeated spraying coverage rate to obtain the first sequential fitness.

[0040] Preferably, in tunnel shotcrete construction, construction work requirements may have different emphases, for example, sometimes more emphasis is placed on construction efficiency, and sometimes more attention is paid to material loss. According to actual construction needs, weight values are set for the two aspects of work efficiency and material loss respectively, wherein the work efficiency weight (first weight) is used to measure the importance of the work efficiency factor when evaluating the spraying sequence; the material loss weight (second weight) is used to measure the importance of the material loss factor; the value range of these two weight values is usually between 0 and 1, and their sum is 1. For example, if the current construction particularly emphasizes work efficiency , the first weight may be set to 0.7 and the second weight may be set to 0.3; the reciprocal of the idle time of the first device is taken. The shorter the idle time of the device, the larger the reciprocal, which means the higher the operating efficiency; similarly, the reciprocal of the first repeated spraying coverage is taken. The lower the repeated spraying coverage, the larger the reciprocal, which means less material loss; according to the set first weight (operation efficiency weight) and second weight (material loss weight), these two reciprocals are weightedly calculated to obtain the corresponding first-order fitness. The larger this value is, the better the comprehensive performance of the spraying sequence in meeting operating efficiency and controlling material loss.

[0041] Step S300, combining the current concrete mix ratio, surrounding rock feature information, construction environment information and the three-dimensional models of the multiple construction areas, with the goal of minimizing concrete rebound, according to the optimal block spraying sequence, the spraying construction parameters of each construction area are optimized and analyzed in turn to obtain the optimal construction parameter sequence.

[0042] Preferably, different concrete mix ratios affect its fluidity, adhesion, and other properties, which in turn affect the amount of rebound during the spraying process. For example, different proportions of components such as cement, aggregate, and admixtures will result in different consistency and setting speed of concrete. A reasonable mix ratio can enable concrete to better adhere to the surrounding rock surface and reduce rebound. The properties of the surrounding rock, such as hardness, surface roughness, and crack development, have a significant impact on the amount of concrete rebound. Concrete is not easy to adhere to hard and smooth surrounding rock surfaces, and the rebound may be large. However, concrete is more easily embedded in surrounding rock with a certain degree of roughness or cracks, and the rebound is relatively small. Construction environment information includes environmental factors such as temperature, humidity, and wind speed at the construction site. A high temperature and dry environment may cause the concrete moisture to evaporate too quickly, affecting its adhesion and leading to increased rebound. Strong winds may blow away the sprayed concrete, also increasing the rebound. Multiple three-dimensional models of construction areas can intuitively display geometric information such as the shape, size, and spatial position of each construction area. Different area shapes and spatial layouts will affect construction parameters such as spraying angle and distance, and thus affect the rebound.

[0043] Preferably, the goal is to minimize the amount of concrete rebound, where concrete rebound is a common problem in shotcrete construction. Excessive rebound not only causes material waste and increases construction costs, but may also affect the quality and structural performance of shotcrete. Then, according to the optimal block spraying sequence, the spraying construction parameters of each construction area are optimized and analyzed in turn to ensure the orderliness and efficiency of the construction process. Specifically, the spraying construction parameters mainly include spraying pressure, spraying distance, spraying angle, spraying speed, etc. These parameters are interrelated and have a direct impact on the amount of concrete rebound. For example, excessive spraying pressure may cause concrete to rebound after impacting the surrounding rock surface. , increasing the rebound amount; if the spraying distance is too far, the concrete will disperse during the flight, reduce its adhesion, and also increase the rebound amount; for each construction area, combined with the various information mentioned above, analyze the concrete rebound amount under different construction parameter combinations, and find the parameter combination that minimizes the rebound amount by continuously adjusting the parameter values; then obtain the optimal construction parameters corresponding to each area, and arrange these parameters in the order of spraying to form an optimal construction parameter sequence. Construction personnel can use the corresponding optimal parameters for spraying operations in different construction areas according to this sequence, thereby effectively reducing the concrete rebound amount and improving construction quality and efficiency.

[0044] Furthermore, step S300 also includes step S310, selecting the first spraying operation area and the first wet spraying machine in the optimal block spraying sequence, and obtaining the first spraying construction parameters of the first wet spraying machine; step S320, based on the three-dimensional model of the first construction area, the current concrete mix ratio, the surrounding rock feature information and the construction environment information, combined with the feedforward neural network to construct a first concrete rebound prediction plug-in; step S330, using the first concrete rebound prediction plug-in, with the goal of minimizing the concrete rebound amount, to optimize the first spraying construction parameters, obtain the first optimal spraying construction parameters, and add them to the optimal construction parameter sequence in sequence.

[0045] Preferably, in the determined optimal block spraying sequence, the first area that needs to be sprayed is selected, and at the same time, a wet spraying machine for operation in this area is selected, namely the first wet spraying machine, and the spraying construction parameters currently set for the first wet spraying machine are obtained, which may include spraying pressure, spraying speed, spraying angle, nozzle diameter, etc., which directly affect the effect and quality of sprayed concrete; the three-dimensional model of the first construction area is used to understand the shape, size, spatial position and other information of the area; the current concrete mix ratio determines the performance of the concrete, such as strength, fluidity, etc.; the surrounding rock characteristic information includes the type, hardness, stability, etc. of the surrounding rock, and different surrounding rock conditions have a great influence on the adhesion and rebound of the sprayed concrete; the construction environment information such as temperature, humidity, ventilation conditions, etc. will also affect the solidification and rebound of the concrete.

[0046] Preferably, the feedforward neural network is a unidirectional multi-layered neural network, including an input layer, a hidden layer and an output layer. The input data is passed layer by layer, and after weighted summation and activation function processing of the neurons in each layer, the output result is finally obtained. Specifically, the collected first construction area three-dimensional model, concrete mix ratio, surrounding rock feature information and construction environment information are used as inputs of the feedforward neural network, and the concrete rebound amount is used as output. The neural network is trained with a large amount of sample data to learn the complex mapping relationship between these input factors and the concrete rebound amount, thereby constructing a first concrete rebound prediction plug-in; then the first The concrete rebound prediction plug-in takes the first spraying construction parameters of the first wet spraying machine as input and predicts the concrete rebound under these parameters. The first spraying construction parameters are continuously adjusted through optimization algorithms (such as genetic algorithms and particle swarm algorithms). The parameters are then input into the prediction plug-in again to observe changes in the concrete rebound in order to find a set of parameters that minimize the concrete rebound, namely the first optimal spraying construction parameters. Finally, this set of first optimal spraying construction parameters is sequentially added to the optimal construction parameter sequence so that the entire tunnel section to be constructed can be subsequently sprayed according to this optimized parameter sequence, thereby improving construction quality and reducing material waste and costs.

[0047] Furthermore, step S320 further includes step S321, obtaining the first surface feature distribution of the three-dimensional model of the first construction area, and expanding the first surface feature distribution, the current concrete mix ratio, the surrounding rock feature information and the construction environment information according to the predetermined tolerance range to obtain similarity comparison conditions; step S322, using the similarity comparison conditions as conditional constraints and the first wet spraying machine as equipment constraints, obtaining a sample spraying construction parameter set based on big data retrieval, and counting the concrete rebound amount after different sample spraying construction parameters are used to construct a sample concrete rebound amount set; step S323, using the sample spraying construction parameter set and the sample concrete rebound amount set to train a feedforward neural network until the model converges to obtain a first concrete rebound prediction plug-in.

[0048] Preferably, by analyzing the three-dimensional model of the first construction area, various surface feature information of the area is extracted, such as surface roughness, flatness, concavity and convexity, and crack distribution. This feature information is quantified and represented in a certain manner to form a first surface feature distribution. A tolerance interval is pre-set to appropriately expand each piece of information. Specifically, for the first surface feature distribution, based on its quantized value, the tolerance interval is adjusted within a certain range to obtain a possible surface feature distribution. For the current concrete mix ratio, the proportions of various components (such as cement, aggregate, and admixtures) are fine-tuned within the tolerance interval. Surrounding rock feature information, such as indicators such as surrounding rock hardness and stability, is expanded within the tolerance interval. Construction environment information, such as temperature and humidity, is also varied within the tolerance interval. This information expansion yields similar comparison conditions for subsequent retrieval of similar sample data.

[0049] Preferably, with similar comparison conditions as restrictions, construction cases similar to these conditions are searched in the big data platform or database. At the same time, the first wet spraying machine is used as the equipment constraint to ensure that the equipment used in the retrieved sample cases is the same as or similar to the first wet spraying machine used in the current construction; the spraying construction parameters such as spraying pressure, spraying speed, spraying angle, etc. are extracted from the retrieved sample cases to form a sample spraying construction parameter set; for each sample spraying construction parameter, the concrete rebound amount generated after the actual operation is counted, and these rebound amount data are collected to construct a sample concrete rebound amount set; then the sample spraying construction parameter set is used as a feedforward neural network The feedforward neural network is trained using the network's input data and the sample concrete rebound set as the corresponding output data. During the training process, the neural network will continuously adjust its own weights and thresholds based on the relationship between the input data and the output data to minimize the error between the predicted value and the actual value. As the training progresses, when the model error reaches an acceptable range, that is, when the model converges, the training process ends. At this time, the feedforward neural network obtained has the ability to predict the concrete rebound based on the input spraying construction parameters. It is encapsulated into the first concrete rebound prediction plug-in for subsequent construction parameter optimization and concrete rebound prediction.

[0050] Furthermore, step S330 also includes step S331, obtaining a first spraying construction parameter threshold of the first wet spraying machine, wherein the first spraying construction parameter includes the wind speed, spraying distance, spraying angle and layer thickness of the wet spraying machine; step S332, randomly selecting multiple initial construction parameters within the first spraying construction parameter threshold; step S333, using the first concrete rebound prediction plug-in to predict the multiple initial construction parameters respectively, and output multiple predicted rebound amounts; step S334, based on the multiple predicted rebound amounts, optimizing the first spraying construction parameters to obtain the first optimal spraying construction parameters.

[0051] Preferably, the first spraying construction parameter threshold of the first wet spraying machine is determined according to the performance of the wet spraying machine, the characteristics of the concrete material, the construction specifications and the previous construction experience, that is, the wind speed, spraying distance, spraying angle and layer thickness of the wet spraying machine are determined, and the value range of the construction parameters is limited to ensure the safety and quality controllability of the construction process; within the range specified by the first spraying construction parameter threshold, a plurality of different parameter combinations are randomly selected as the initial construction parameters, so as to more comprehensively explore the influence of different parameter combinations on the concrete rebound amount and avoid missing the possible optimal solution; using the constructed first concrete rebound prediction plug-in, each initial construction parameter is input into the plug-in respectively , that is, based on the input construction parameters and the model obtained by internal training, the possible concrete rebound amount when the spraying operation is carried out under the parameters is predicted, thereby obtaining multiple predicted rebound amounts; finally, based on the multiple predicted rebound amounts, the first spraying construction parameter optimization is performed to find the first spraying construction parameter that minimizes the rebound amount, that is, by comparing the predicted rebound amounts corresponding to different initial construction parameters, analyzing the differences and patterns between them, and finally determining a set of construction parameters that can achieve the optimal (e.g., minimum) concrete rebound amount, namely the first optimal spraying construction parameters, which are used in actual spraying operations to achieve the goals of reducing concrete rebound, improving construction quality and efficiency, etc.

[0052] Furthermore, step S334 further includes step A, taking the initial construction parameters as the initial solution, sorting the multiple initial construction parameters from small to large according to the predicted rebound amount to generate an initial solution sequence; step B, setting the first K solutions of the initial solution sequence as optimal solutions, and setting the last J solutions as inferior solutions, where J is M times K, and M is an integer greater than 2; step C, using the K optimal solutions to perform equivalue clustering on the J inferior solutions to obtain K solution thresholds, and within the K solution thresholds, adjusting the inferior solutions in the direction of the optimal solution according to the optimal step length, to obtain K updated solution thresholds. Among them, if the adjusted inferior solution does not meet the first spraying construction parameter threshold, this adjustment will not be performed; in step D, using the first concrete rebound prediction plug-in, the rebound amount of the inferior solutions of the K updated solution thresholds is predicted respectively, and K updated solution thresholds are identified. If the predicted rebound amount of the updated inferior solution within the same updated solution threshold is less than the predicted rebound amount of the optimal solution, the inferior solution is used to replace the optimal solution; in step E, iterative optimization is performed until the predetermined number of convergence times is reached, K current solution thresholds are output, and the solution with the current minimum predicted rebound amount is selected as the first optimal spraying construction parameter.

[0053] Preferably, a plurality of randomly selected initial construction parameters are regarded as initial solutions in the process of finding the optimal solution. The predicted rebound amounts obtained by the first concrete rebound prediction plug-in based on the initial construction parameters are arranged in ascending order to form an initial solution sequence. The predicted rebound amounts corresponding to the initial construction parameters at the front of the sequence are smaller, which means that the concrete rebound may be smaller under these parameters. Then, the first K solutions with smaller predicted rebound amounts are selected as optimal solutions. These solutions are considered to be relatively better construction parameter combinations, and the next J solutions with larger predicted rebound amounts are set as inferior solutions, and it is stipulated that J is M times K, where M, K and J are all positive integers and M is greater than 2, so as to ensure that there are a sufficient number of inferior solutions that can be adjusted and optimized, and also reflect a proportional relationship in the number of optimal solutions and inferior solutions.

[0054] Preferably, K optimal solutions are used as cluster centers, and J inferior solutions are subjected to equal value clustering operation. Specifically, inferior solutions are assigned to K different categories through clustering, and each category corresponds to a solution threshold. Within each solution threshold, inferior solutions are adjusted in the direction of the optimal solution according to the preset optimal step length, so as to make the inferior solutions closer to the optimal solution, thereby possibly reducing the predicted rebound amount. If the adjusted inferior solution exceeds the first spraying construction parameter threshold determined previously (such as the value range of parameters such as wet spraying machine wind speed and spraying distance), this adjustment is not performed to ensure the optimal solution is the best solution. The rationality and safety of the construction parameters are verified, resulting in K updated solution thresholds. For each inferior solution within the K updated solution thresholds, the first concrete rebound prediction plug-in is used again to predict its rebound. The predicted rebound of the updated inferior solution is then compared with the corresponding superior solution within the same updated solution threshold. If the predicted rebound of the updated inferior solution is less than that of the superior solution, indicating that the inferior solution has become better after adjustment, it is replaced with the original superior solution to continuously optimize the solution set. Multiple iterations are performed to find the optimal solution, and each iteration further optimizes the solution. When the pre-set number of convergences (i.e., the maximum number of iterations) is reached, the iterations are terminated, and the K current solution thresholds are output. The solution with the smallest predicted rebound is then selected from these solutions and determined as the first optimal spraying construction parameters, i.e., the spraying construction parameters found in the current optimization process that minimize concrete rebound.

[0055] Step S400: performing the jetting operation of the tunnel section to be constructed according to the optimal construction parameter sequence.

[0056] Preferably, during the tunnel shotcrete construction process, the shotcrete operation of the tunnel section to be constructed is carried out according to the optimal block shotcrete sequence and the optimal construction parameter sequence. Specifically, the construction personnel must strictly carry out the shotcrete operation in each construction area according to the optimal block shotcrete sequence to ensure the efficiency and orderliness of the construction process, and avoid problems such as frequent equipment adjustments, material waste, and reduced construction quality due to unreasonable shotcrete sequence. When performing the shotcrete operation in each construction area, the operator needs to set and adjust the wet shotcrete machine and other construction equipment according to the optimal parameters corresponding to the area in the sequence. For example, when the construction reaches area 1 At this time, according to the parameters corresponding to area 1 in the optimal construction parameter sequence, the spraying pressure of the wet shotcrete machine is adjusted to the specified value, and the spraying distance and angle are also adjusted to the corresponding optimal values. This ensures that the best spraying effect can be achieved in each construction area, reducing the amount of concrete rebound and improving quality indicators such as concrete density and bond strength with the surrounding rock. The construction team will carry out shotcrete operations in each area of the entire tunnel section to be constructed in accordance with the established optimal block spraying sequence and optimal construction parameter sequence. During the operation, it is necessary to monitor the construction status in real time to ensure the accurate implementation of construction parameters and the smooth progress of the shotcrete operation. If the actual situation deviates from the expected, such as sudden changes in surrounding rock conditions, it is necessary to make appropriate adjustments to the construction parameters in a timely manner to ensure that the shotcrete operation can meet the project quality requirements and ultimately complete the shotcrete construction task of the entire tunnel section to be constructed.

[0057] In the above, refer to Figure 1 The sprayed concrete construction optimization method combined with spatial positioning according to an embodiment of the present invention is described in detail. Figure 2 A shotcrete construction optimization system combined with spatial positioning according to an embodiment of the present invention is described.

[0058] The sprayed concrete construction optimization system combined with spatial positioning according to the embodiment of the present invention is used to solve the technical problems existing in the prior art, such as large rebound, poor density, poor durability, high adhesive usage, and unstable material adaptability, which in turn lead to poor sprayed concrete construction quality and efficiency and high material consumption, thereby achieving the technical effect of reducing material consumption and improving sprayed concrete construction quality and efficiency. Figure 2 As shown, the shotcrete construction optimization system combined with spatial positioning includes: a construction area determination module 10, an optimal block spraying sequence acquisition module 20, an optimal construction parameter sequence acquisition module 30, and a tunnel spraying operation execution module 40.

[0059] The construction area determination module 10 is used to divide the tunnel section to be constructed based on the wet spraying machine model and determine multiple construction areas; the optimal block spraying sequence acquisition module 20 is used to collect surface point cloud data of the multiple construction areas for three-dimensional modeling, and use the multiple three-dimensional models of the construction areas to optimize the spraying operation sequence with the goal of minimizing the equipment idle time and repeated spraying coverage to obtain the optimal block spraying sequence; the optimal construction parameter sequence acquisition module 30 is used to combine the current concrete mix ratio, surrounding rock feature information, construction environment information and the multiple three-dimensional models of the construction areas, with the goal of minimizing the concrete rebound amount, and optimize and analyze the spraying construction parameters of each construction area in turn according to the optimal block spraying sequence to obtain the optimal construction parameter sequence; the tunnel spraying operation execution module 40 is used to execute the spraying operation of the tunnel section to be constructed according to the optimal construction parameter sequence.

[0060] The specific configuration of the construction area determination module 10 will be described in detail below. The construction area determination module 10 further includes: obtaining multiple models of multiple operational spraying machines and multiple maximum spraying coverage ranges; performing a collaborative simulation analysis on the tunnel section to be constructed based on the multiple maximum spraying coverage ranges to determine multiple area division schemes; and performing a division quality assessment on the multiple area division schemes, selecting the area division scheme corresponding to the maximum division quality coefficient, and obtaining multiple construction areas.

[0061] The specific configuration of the construction area determination module 10 will be described in detail below. The construction area determination module 10 further includes: obtaining multiple area division schemes, where each area division scheme is identified by the number of areas and a number of wet spraying machine operation times; performing variance calculations on the number of wet spraying machine operation times for each area division scheme to determine multiple operation time variances; and performing a weighted calculation based on the variances of the multiple area numbers and the multiple operation times to obtain multiple division quality coefficients, where the division quality coefficients are negatively correlated with the variances of the multiple area numbers and the multiple operation times.

[0062] The specific configuration of the optimal block spraying sequence acquisition module 20 will be described in detail below. The optimal block spraying sequence acquisition module 20 further includes: based on the multiple construction areas, in combination with a number of wet spraying machines, enumerating the spraying operation sequence to generate multiple initial block spraying sequences; randomly selecting a first initial block spraying sequence, in the spraying operation simulation space, using multiple three-dimensional models of the construction areas, in combination with a number of wet spraying machines to simulate the spraying operation, counting the simulated idle time of the several wet spraying machines and the repeated spraying coverage area of the multiple construction areas, and calculating the first equipment idle time and the first repeated spraying coverage rate; calculating the first sequence fitness based on the first equipment idle time and the first repeated spraying coverage rate; sequentially analyzing and obtaining multiple sequence fitnesses of the multiple initial block spraying sequences, and selecting the initial block spraying sequence with the maximum sequence fitness as the optimal block spraying sequence.

[0063] The specific configuration of the optimal segmented spraying sequence acquisition module 20 will be described in detail below. The optimal segmented spraying sequence acquisition module 20 further includes: configuring a first weight and a second weight according to construction work requirements, wherein the first weight is a weight for work efficiency and the second weight is a weight for material loss; and performing a weighted calculation based on the first and second weights on the inverse of the first equipment idle time and the inverse of the first repeated spraying coverage rate to obtain a first sequence fitness.

[0064] The specific configuration of the optimal construction parameter sequence acquisition module 30 will be described in detail below. The optimal construction parameter sequence acquisition module 30 further includes: selecting a first spraying operation area and a first wet spraying machine in the optimal block spraying sequence, and obtaining first spraying construction parameters for the first wet spraying machine; constructing a first concrete rebound prediction plug-in based on the three-dimensional model of the first construction area, the current concrete mix ratio, surrounding rock characteristics, and construction environment information in combination with a feedforward neural network; using the first concrete rebound prediction plug-in, optimizing the first spraying construction parameters with the goal of minimizing concrete rebound, obtaining first optimal spraying construction parameters, and sequentially adding them to the optimal construction parameter sequence.

[0065] The specific configuration of the optimal construction parameter sequence acquisition module 30 will be described in detail below. The optimal construction parameter sequence acquisition module 30 further includes: obtaining a first surface feature distribution of the three-dimensional model of the first construction area, expanding the first surface feature distribution, the current concrete mix ratio, the surrounding rock feature information, and the construction environment information according to a predetermined tolerance range to obtain similarity comparison conditions; using the similarity comparison conditions as conditional constraints and the first wet spraying machine as an equipment constraint, obtaining a sample spraying construction parameter set based on big data retrieval, and calculating the concrete rebound after different sample spraying construction parameters to construct a sample concrete rebound amount set; using the sample spraying construction parameter set and the sample concrete rebound amount set to train a feedforward neural network until the model converges, thereby obtaining a first concrete rebound prediction plug-in.

[0066] The specific configuration of the optimal construction parameter sequence acquisition module 30 will be described in detail below. The optimal construction parameter sequence acquisition module 30 further includes: obtaining a first spraying construction parameter threshold for the first wet spraying machine, where the first spraying construction parameter includes the wet spraying machine wind speed, spraying distance, spraying angle, and layer thickness; randomly selecting multiple initial construction parameters within the first spraying construction parameter threshold; using the first concrete rebound prediction plug-in to predict each of the multiple initial construction parameters and output multiple predicted rebound amounts; and optimizing the first spraying construction parameters based on the multiple predicted rebound amounts to obtain the first optimal spraying construction parameters.

[0067] The specific configuration of the optimal construction parameter sequence acquisition module 30 will be described in detail below. The optimal construction parameter sequence acquisition module 30 further includes: taking the initial construction parameters as the initial solution, sorting the multiple initial construction parameters from small to large according to the predicted rebound amount, and generating an initial solution sequence; setting the first K solutions of the initial solution sequence as optimal solutions, and setting the last J solutions as inferior solutions, where J is M times K, and M is an integer greater than 2; using the K optimal solutions to perform equivalue clustering on the J inferior solutions to obtain K solution thresholds, and within the K solution thresholds, adjusting the inferior solutions in the direction of the optimal solution according to the optimal step length, and obtaining K updated solutions. Threshold, wherein, if the adjusted inferior solution does not meet the first shotcrete construction parameter threshold, no adjustment is performed; using the first concrete rebound prediction plug-in, the rebound amount of the inferior solutions of the K updated solution thresholds is predicted respectively, and K updated solution thresholds are identified. If the predicted rebound amount of the updated inferior solution within the same updated solution threshold is less than the predicted rebound amount of the optimal solution, the inferior solution is used to replace the optimal solution for iterative optimization until the predetermined number of convergences is reached, K current solution thresholds are output, and the solution with the current minimum predicted rebound amount is selected as the first optimal shotcrete construction parameter.

[0068] The shotcrete construction optimization system combined with spatial positioning provided by the embodiment of the present invention can execute the shotcrete construction optimization method combined with spatial positioning provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0069] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0070] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A shotcrete construction optimization method combined with spatial positioning, characterized in that the method include: Divide the tunnel section to be constructed based on the wet spraying machine model and determine multiple construction areas; Collecting surface point cloud data of the multiple construction areas for three-dimensional modeling, and optimizing the spraying operation sequence by minimizing equipment idle time and repeated spraying coverage using the multiple three-dimensional models of the construction areas to obtain the optimal block spraying sequence; Combining the current concrete mix ratio, surrounding rock characteristics, construction environment information, and the three-dimensional models of the multiple construction areas, with the goal of minimizing concrete rebound, and following the optimal block spraying sequence, the spraying construction parameters of each construction area are optimized and analyzed to obtain the optimal construction parameter sequence; Performing the spraying operation of the tunnel section to be constructed according to the optimal construction parameter sequence; The tunnel section to be constructed is divided according to the wet spraying machine model, and multiple construction areas are determined, including: Obtain several wet spraying machine models of several operable wet spraying machines and several maximum spraying coverage areas; Based on the plurality of maximum spraying coverage areas, a collaborative simulation operation analysis is performed on the tunnel section to be constructed to determine multiple area division schemes; Performing a division quality evaluation on the multiple area division schemes, selecting the area division scheme corresponding to the maximum division quality coefficient, and obtaining multiple construction areas; Performing a division quality assessment on the multiple area division schemes, including: Acquire multiple area division schemes, wherein each area division scheme is identified by the number of areas and a number of wet spraying machine operation times; The variance of several wet spraying machine operation times of each area division scheme is calculated to determine the variance of multiple operation times; A plurality of partitioning quality coefficients are obtained by weighted calculation based on the variances of the number of regions and the number of operations, wherein the partitioning quality coefficient is negatively correlated with the variances of the number of regions and the number of operations.

2. The method for optimizing sprayed concrete construction in combination with spatial positioning according to claim 1, characterized in that: Using multiple 3D models of the construction area, we optimize the spraying sequence to minimize equipment idle time and repeated spraying coverage, and obtain the optimal block spraying sequence, including: Based on the multiple construction areas, a spraying operation sequence is enumerated in combination with a plurality of wet spraying machines to generate multiple initial block spraying sequences; Randomly select the first initial block spraying sequence, use multiple three-dimensional models of construction areas in combination with several wet spraying machines to simulate the spraying operation in the spraying operation simulation space, calculate the simulated idle time of several wet spraying machines and the repeated spraying coverage area of multiple construction areas, and calculate the first equipment idle time and the first repeated spraying coverage rate; Calculating a first sequential fitness according to the idle time of the first device and the first repeated spray coverage rate; A plurality of sequence fitnesses of the plurality of initial block injection sequences are sequentially analyzed and obtained, and the initial block injection sequence with the maximum sequence fitness is selected as the optimal block injection sequence.

3. The method for optimizing shotcrete construction in combination with spatial positioning according to claim 2, characterized in that: The first sequence fitness is calculated according to the idle time of the first device and the first repeated spray coverage rate, including: Configure the first weight and the second weight according to the construction work requirements, wherein the first weight is the work efficiency weight and the second weight is the material loss weight; A weighted calculation is performed on the inverse of the idle time of the first device and the inverse of the first repeated spray coverage rate according to the first weight and the second weight to obtain a first sequential fitness.

4. The method for optimizing shotcrete construction in combination with spatial positioning according to claim 1, characterized in that: Combined with the current concrete mix ratio, surrounding rock characteristics, construction environment information, and the three-dimensional models of the multiple construction areas, with the goal of minimizing concrete rebound, the spraying construction parameters of each construction area are optimized and analyzed in accordance with the optimal block spraying sequence to obtain the optimal construction parameter sequence, including: Selecting a first spraying operation area and a first wet spraying machine in the optimal block spraying sequence, and obtaining first spraying construction parameters of the first wet spraying machine; Based on the three-dimensional model of the first construction area, the current concrete mix ratio, surrounding rock characteristics and construction environment information, a first concrete rebound prediction plug-in is constructed in combination with a feedforward neural network; The first concrete rebound prediction plug-in is used to optimize the first spraying construction parameters with the goal of minimizing the concrete rebound amount, obtain the first optimal spraying construction parameters, and add them to the optimal construction parameter sequence in sequence.

5. The method for optimizing sprayed concrete construction in combination with spatial positioning according to claim 4, characterized in that: Based on the 3D model of the first construction area, the current concrete mix ratio, surrounding rock characteristics, and construction environment information, a first concrete rebound prediction plug-in is constructed in conjunction with a feedforward neural network, including: Obtaining a first surface feature distribution of a three-dimensional model of a first construction area, and expanding the first surface feature distribution, the current concrete mix ratio, surrounding rock feature information, and construction environment information according to a predetermined tolerance range to obtain similarity comparison conditions; Using the similarity comparison condition as a conditional constraint and the first wet spraying machine as an equipment constraint, a sample spraying construction parameter set is obtained based on big data retrieval, and the concrete rebound amounts after operations with different sample spraying construction parameters are counted to construct a sample concrete rebound amount set; The sample spraying construction parameter set and the sample concrete rebound amount set are used to train a feedforward neural network until the model converges, thereby obtaining a first concrete rebound prediction plug-in.

6. The method for optimizing shotcrete construction combined with spatial positioning according to claim 4, characterized in that: Using the first concrete rebound prediction plug-in, optimizing the first spraying construction parameters with the goal of minimizing the concrete rebound amount, and obtaining the first optimal spraying construction parameters, including: Obtaining a first spraying construction parameter threshold value of a first wet spraying machine, wherein the first spraying construction parameter includes a wind speed, a spraying distance, a spraying angle, and a layer thickness of the wet spraying machine; Randomly selecting a plurality of initial construction parameters within the first spraying construction parameter threshold; Using the first concrete rebound prediction plug-in, respectively predict the multiple initial construction parameters and output multiple predicted rebound amounts; Based on the multiple predicted rebound amounts, a first spraying construction parameter optimization is performed to obtain a first optimal spraying construction parameter.

7. The method for optimizing shotcrete construction combined with spatial positioning according to claim 6, characterized in that: Based on the multiple predicted rebound amounts, optimizing the first injection construction parameters to obtain the first optimal injection construction parameters includes: Taking the initial construction parameters as the initial solution, sorting the multiple initial construction parameters from small to large according to the predicted rebound amount to generate an initial solution sequence; The first K solutions of the initial solution sequence are set as optimal solutions, and the last J solutions are set as inferior solutions, where J is M times K, and M is an integer greater than 2; Use K optimal solutions to perform equivalue clustering on J inferior solutions to obtain K solution thresholds. Within the K solution thresholds, adjust the inferior solutions in the direction of the optimal solution according to the optimal step length to obtain K updated solution thresholds. If the adjusted inferior solution does not meet the first injection construction parameter threshold, no adjustment will be made. Using the first concrete rebound prediction plug-in, the rebound amount of the inferior solutions of the K updated solution thresholds is predicted respectively, and the K updated solution thresholds are identified. If the predicted rebound amount of the updated inferior solution within the same updated solution threshold is less than the predicted rebound amount of the optimal solution, the inferior solution is used to replace the optimal solution; Iterative optimization is performed until a predetermined number of convergences is reached, K current solution thresholds are output, and the solution with the current minimum predicted rebound amount is selected as the first optimal spraying construction parameter.

8. The shotcrete construction optimization system combined with spatial positioning is characterized by: The system is used to implement the shotcrete construction optimization method combined with spatial positioning according to any one of claims 1 to 7, and the system comprises: The construction area determination module is used to divide the tunnel section to be constructed according to the wet spraying machine model and determine multiple construction areas; An optimal block spraying sequence acquisition module is used to collect surface point cloud data of the multiple construction areas for three-dimensional modeling. Using the multiple three-dimensional models of the construction areas, the module optimizes the spraying operation sequence with the goal of minimizing equipment idle time and repeated spraying coverage to obtain the optimal block spraying sequence. An optimal construction parameter sequence acquisition module is used to optimize and analyze the spraying construction parameters of each construction area in accordance with the optimal block spraying sequence, based on the current concrete mix ratio, surrounding rock characteristics, construction environment information, and the three-dimensional models of the multiple construction areas, with the goal of minimizing concrete rebound, to obtain the optimal construction parameter sequence; The tunnel spraying operation execution module is used to execute the spraying operation of the tunnel section to be constructed according to the optimal construction parameter sequence.

Images