A monitoring method and system for blasting excavation of surrounding rock in tunnels in poor sections

Abstract

The present invention provides a monitoring method and system for blasting excavation of surrounding rock in a tunnel in a poor section, which relates to the technical field of tunnel construction, and includes respectively obtaining historical fracture zone parameters and real-time fracture zone parameters of a target section; respectively obtaining historical rock mass parameters and real-time rock mass parameters of the target section; analyzing and processing the historical rock mass parameters to obtain strength parameters; obtaining a target reward function; training a preset neural network model based on the fracture zone parameters, strength parameters and target reward function to obtain a target monitoring model; and inputting the real-time fracture zone parameters and real-time rock mass parameters into the target monitoring model to obtain the monitoring result of the surrounding rock state during blasting excavation. By collecting relevant parameters of the fracture zone and training a neural network model, the present invention constructs a monitoring model with strong flexibility and good generalization ability, which can better capture the complex relationships between data, improve the construction safety, and provide a scientific basis and powerful data support for blasting engineering.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction, and in particular, to a monitoring method and system for blasting excavation of surrounding rock in tunnels in poor sections. Background Art

[0002] A fault zone is a geological structure, the existence of which may lead to the discontinuity of rock mass and the reduction of strength, thus increasing the complexity and danger of blasting operations. Therefore, there is an urgent need for a monitoring model with high accuracy to monitor the state of surrounding rock on the fault zone in real time and ensure the safety of blasting construction. Summary of the Invention

[0003] The purpose of the present invention is to provide a monitoring method and system for blasting excavation of surrounding rock in tunnels in poor sections to improve the above problems. To achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0004] In a first aspect, the present application provides a monitoring method for blasting excavation of surrounding rock in tunnels in poor sections, including:

[0005] Obtaining historical fault zone parameters and real-time fault zone parameters of the target section respectively, where both the historical fault zone parameters and the real-time fault zone parameters include fault zone width, fault zone dip angle, fault zone strike, fault zone length, and fault zone displacement;

[0006] Obtaining historical rock mass parameters and real-time rock mass parameters of the target section respectively, where both the historical rock mass parameters and the real-time rock mass parameters include filling material type and rock type;

[0007] Analyzing and processing the historical rock mass parameters to obtain strength parameters, where the strength parameters include shear strength and compressive strength;

[0008] Constructing a reward function based on the fault zone parameters, the strength parameters, and the linear weighted method to obtain a target reward function;

[0009] Training a preset neural network model based on the fault zone parameters, the strength parameters, and the target reward function to obtain a target monitoring model, where the blasting excavation point information is preset in the preset neural network;

[0010] Inputting the real-time fault zone parameters and the real-time rock mass parameters into the target monitoring model to obtain the monitoring result of the surrounding rock state during blasting excavation.

[0011] In a second aspect, the present application further provides a monitoring system for blasting excavation of surrounding rock in tunnels in poor sections, including:

[0012] A first acquisition unit is configured to respectively acquire historical fault zone parameters and real-time fault zone parameters of a target area, where both the historical fault zone parameters and the real-time fault zone parameters include fault zone width, fault zone dip angle, fault zone strike, fault zone length, and fault zone displacement;

[0013] A second acquisition unit is configured to respectively acquire historical rock mass parameters and real-time rock mass parameters of the target area, where both the historical rock mass parameters and the real-time rock mass parameters include filling material types and rock types;

[0014] An analysis unit is configured to analyze and process the historical rock mass parameters to obtain strength parameters, where the strength parameters include shear strength and compressive strength;

[0015] A first construction unit is configured to construct a reward function based on the fault zone parameters, the strength parameters, and the linear weighting method to obtain a target reward function;

[0016] A training unit is configured to train a preset neural network model based on the fault zone parameters, the strength parameters, and the target reward function to obtain a target monitoring model, where blasting excavation point information is preset in the preset neural network;

[0017] An input unit inputs the real-time fault zone parameters and the real-time rock mass parameters into the target monitoring model to obtain a surrounding rock state monitoring result during blasting excavation.

[0018] The beneficial effects of the present invention are as follows:

[0019] By collecting relevant parameters of the fault zone and training a neural network model, the present invention constructs a monitoring model with strong flexibility and good generalization ability, which can better capture the complex relationships between data, improve the construction safety, and provide a scientific basis and strong data support for blasting engineering.

[0020] Other features and advantages of the present invention will be described in the subsequent specification, and, in part, will be obvious from the specification, or can be understood by implementing the embodiments of the present invention. The objectives and other advantages of the present invention can be achieved and obtained by the structures specifically pointed out in the written specification, claims, and drawings. Description of the Drawings

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1Schematic flow chart of the monitoring method for the blasting excavation of surrounding rock in a tunnel in a poor section according to the embodiment of the present invention;

[0023] Figure 2 Chaotic parameter mapping diagram according to the embodiment of the present invention;

[0024] Figure 3 Schematic diagram of the monitoring system for the blasting excavation of surrounding rock in a tunnel in a poor section according to the embodiment of the present invention.

[0025] Reference signs in the figure: 10, first acquisition unit; 20, second acquisition unit; 30, analysis unit; 40, first construction unit; 50, training unit; 60, input unit. Detailed implementation manners

[0026] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. Components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Therefore, the detailed description of the embodiments of the present invention provided herein is not intended to limit the scope of the claimed invention, but is merely representative of selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0027] It should be noted that: like reference numerals and letters denote like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive distinction and cannot be construed as indicating or implying relative importance.

[0028] Embodiment 1:

[0029] This embodiment provides a monitoring method for the blasting excavation of surrounding rock in a tunnel in a poor section.

[0030] Refer to Figure 1 , the figure shows that this method includes steps S10, step S20, step S30, step S40, step S50 and step S60.

[0031] Step S10. Respectively obtain the historical fracture zone parameters and real-time fracture zone parameters of the target section. Both the historical fracture zone parameters and the real-time fracture zone parameters include fracture zone width, fracture zone dip angle, fracture zone strike, fracture zone length and fracture zone displacement;

[0032] Step S20. Obtain the historical rock mass parameters and real-time rock mass parameters of the target section respectively. Both the historical rock mass parameters and the real-time rock mass parameters include the types of fillers and the types of rocks.

[0033] Specifically, in this application, the target section is a section with a fault zone, which is an adverse section. Due to the existence of the fault zone, it will affect the propagation and results of blasting. Compared with the normal section, the fault section needs to consider the relevant parameters of the fault zone and the rock mass parameters in the fault zone additionally, so as to effectively control the impact of blasting on the fault zone and the surrounding environment and ensure the safety and effectiveness of the blasting project.

[0034] Step S30. Analyze and process the historical rock mass parameters to obtain strength parameters, where the strength parameters include shear strength and compressive strength.

[0035] Specifically, the shear strength and compressive strength are key parameters characterizing the mechanical properties of the rock mass. Through these parameters, the bearing capacity, stability of the rock mass and its failure behavior under various stress conditions can be comprehensively understood, providing a scientific basis for subsequent blasting calculations and safety assessments.

[0036] Step S40. Construct a reward function based on the fault zone parameters, strength parameters and the linear weighting method to obtain the target reward function.

[0037] Specifically, step S40 specifically includes step S41, step S42 and step S43:

[0038] Step S41. Calculate the fault zone coefficients and strength coefficients based on the particle swarm optimization algorithm. The fault zone coefficients include the fault zone width coefficient, fault zone dip angle coefficient, fault zone strike coefficient, fault zone length coefficient and fault zone displacement coefficient, and the strength coefficients include the shear strength coefficient and the compressive strength coefficient.

[0039] Specifically, randomly initialize the fault zone coefficients and strength coefficients of the heart rate variability, and set the maximization of the target reward function as the objective function; in each iteration, calculate the fitness function value of the current solution based on the preset position update formula and fitness function, retain the solution with a higher fitness function value, and update the positions of the remaining solutions according to the position update formula. As the iteration progresses, the number of the remaining solutions gradually decreases until the number meets the set conditions, and the solution with the largest fitness function value is determined from them, which corresponds to the optimal weight coefficient.

[0040] Step S42. Calculate the reward value based on the fault zone parameters, strength parameters, and the corresponding preset parameter safety ranges. The parameter safety ranges include the safety range of the fault zone width, the safety range of the fault zone dip angle, the safety range of the fault zone strike angle, the safety range of the fault zone length, the safety range of the fault zone displacement, the safety range of the shear strength parameter, and the safety range of the compressive strength parameter. The reward value includes the fault zone reward value and the strength reward value. The fault zone reward value includes the fault zone width reward value, the fault zone dip angle reward value, the fault zone strike reward value, the fault zone length reward value, and the fault zone displacement reward value. The strength reward value includes the shear strength reward value and the compressive strength reward value;

[0041] Specifically, step S42 specifically includes step S421, step S422, step S423, step S424, step S425, step S426, step S427, step S428, step S429, step S4210, step S4211, step S4212, and step S4213:

[0042] Step S421. When the fault zone parameter is within the preset parameter safety range, the fault zone parameter is the third set threshold;

[0043] Step S422. When the fault zone parameter is not within the preset parameter safety range, calculate the difference between the upper limit value of the preset parameter safety range and the fault zone parameter to obtain the first difference;

[0044] Step S423. Calculate the difference between the upper limit value and the lower limit value of the preset parameter safety range to obtain the second difference;

[0045] Step S424. Calculate the ratio of the first difference to the second difference to obtain the first ratio;

[0046] Step S425. Calculate the product of the first ratio and the corresponding preset fault zone adjustment factor to obtain the first product. The preset fault zone adjustment factor includes the fault zone parameter adjustment factor, and the fault zone parameter adjustment factor includes the fault zone width adjustment factor, the fault zone dip angle adjustment factor, the fault zone strike adjustment factor, the fault zone length adjustment factor, and the fault zone displacement adjustment factor;

[0047] Step S426. Calculate the exponential function value of the first product with the natural constant as the base to obtain the fault zone reward value;

[0048] Specifically, when the fault zone parameter is within the preset parameter safety range, the fault zone reward value J1 = 1;

[0049] When the fault zone parameter is not within the preset parameter safety range, the calculation formula for the fault zone reward value J1 is:

[0050]

[0051] Among them, J1 is the fracture zone reward value; α is the fracture zone adjustment factor; MAX is the upper limit value of the preset parameter safety range; MIN is the lower limit value of the preset parameter safety range; X is the fracture zone parameter.

[0052] Step S427. When the strength parameter is within the preset parameter safety range, the strength parameter is the fourth set threshold;

[0053] Step S428. When the strength parameter is not within the preset parameter safety range, calculate the difference between the upper limit value and the lower limit value of the preset parameter safety range to obtain the third difference;

[0054] Step S429. Calculate the ratio of the strength parameter to the upper limit value of the preset parameter safety range to obtain the second ratio;

[0055] Step S4210. Calculate the difference between the third set threshold and the second ratio to obtain the fourth difference;

[0056] Step S4211. Calculate the product of the fourth difference and the third difference to obtain the second product;

[0057] Step S4212. Calculate the product of the second product and the corresponding preset strength adjustment factor to obtain the third product. The preset strength adjustment factors include the shear strength adjustment factor and the compressive strength adjustment factor;

[0058] Step S4213. Calculate the exponential function value of the third product with the natural constant as the base to obtain the strength reward value;

[0059] Specifically, when the strength parameter is within the preset parameter safety range, the strength reward value J2 = 1;

[0060] When the strength parameter is not within the preset parameter safety range, the calculation formula for the strength reward value J2 is:

[0061]

[0062] Among them, J2 is the strength reward value; β is the strength adjustment factor; MAX is the upper limit value of the preset parameter safety range; MIN is the lower limit value of the preset parameter safety range; Y is the strength parameter.

[0063] Step S43. Calculate the product of the fracture zone coefficient and the strength coefficient and the corresponding reward value, and perform a summation calculation on the product results to construct the target reward function;

[0064] Specifically, the calculation formula for the target reward function is:

[0065] Q = w1 * q1 + w2 * q2

[0066] Wherein, Q is the target reward function; w1 is the fracture zone coefficient; q1 is the fracture zone reward value; w2 is the strength coefficient; q2 is the strength reward value;

[0067]

[0068] Wherein, when the fracture zone parameter is within the preset parameter safety range, the value of the fracture zone parameter is 1; when the fracture zone parameter is not within the preset parameter safety range, the value of the fracture zone parameter is the value calculated by J1; MAX is the upper limit value of the preset parameter safety range; MIN is the lower limit value of the preset parameter safety range

[0069]

[0070] Wherein, when the strength parameter is within the preset parameter safety range, the value of the strength parameter is 1; when the strength parameter is not within the preset parameter safety range, the value of the strength parameter is the value calculated by the J1 formula; MAX is the upper limit value of the preset strength safety range; MIN is the lower limit value of the preset strength safety range.

[0071] Step S50. Train the preset neural network model based on the fracture zone parameter, strength parameter and target reward function to obtain the target monitoring model. The blasting excavation point information is preset in the preset neural network;

[0072] Specifically, step S50 specifically includes step S51, step S52, step S53, step S54, step S55, step S56 and step S57:

[0073] Step S51. Initialize the positions of the sparrow population based on chaotic mapping to obtain multiple initial position parameters;

[0074] Specifically, using chaotic mapping to initialize the sparrow population can traverse the states of the sparrow population without repetition within a certain range, enabling the sparrow population to be relatively evenly distributed in the entire search space, which not only increases the diversity of the initial sparrow population but also avoids the situation of falling into local optimum during the search process of the sparrow algorithm.

[0075] Specifically, step S51 specifically includes step S511, step S512, step S513, step S514, step S515 and step S516:

[0076] Step S511. Obtain the random position parameter and chaotic control parameter of any sparrow. The initial position parameter is within the first set range, and the chaotic control parameter is within the second set range;

[0077] Step S512. First calculation operation: Calculate the product of the initial position parameter and the first set threshold as the first value;

[0078] Step S513. Second calculation operation: Calculate the cosine function value of the first numerical value as the second numerical value;

[0079] Step S514. Third calculation operation: Calculate the product of the chaos control parameter and the second numerical value as the third numerical value;

[0080] Step S515. Fourth calculation operation: Calculate the exponential function value of the third numerical value with the natural constant as the base as the fourth numerical value;

[0081] Step S516. Repeat the first calculation operation, the second calculation operation, the third calculation operation, and the fourth calculation operation until the preset number of repetitions is reached to obtain the initial position parameter;

[0082] Specifically, the chaos mapping formula is:

[0083]

[0084] where is the chaos value of the i-th sparrow at the (k + 1)-th time; is the chaos value of the i-th sparrow at the k-th time, and the value range is [0, 1]; γ is the chaos system control parameter;

[0085] As Figure 2 shown, in this embodiment, the chaos value after mapping each parameter two thousand times is used as the initial position parameter of the sparrow.

[0086] Step S52. Build a model based on the initial position parameter to obtain a neural network model;

[0087] Specifically, use the initial position parameter of the sparrow algorithm to build a model, and these initialized position parameters will become the initial prediction of the model.

[0088] Step S53. Determination operation: Based on the initial position parameters of all sparrows, determine the initial fitness of all sparrows;

[0089] Step S54. Division operation: Divide all sparrows into multiple categories based on the initial fitness, and the categories include discoverers, followers, and vigilant ones;

[0090] Step S55. Update operation: Update the initial position parameters of all sparrows based on the initial fitness and the sparrow categories;

[0091] Specifically, there are three categories in the sparrow population, including discoverers, followers, and vigilant ones. The roles of different types of sparrows in the population are not the same, that is, the corresponding position update formulas are also not the same.

[0092] Specifically, step S55 specifically includes steps S551, S552, S553, S554, S555, S556, S557, S558, S559, and S5510:

[0093] Step S551. Obtain the maximum mutation rate, minimum mutation rate, current iteration number, and initial fitness of any sparrow;

[0094] Step S552. Obtain the optimal fitness of the entire sparrow population and the set maximum number of iterations;

[0095] Step S553. Calculate the difference between the maximum mutation rate and the minimum mutation rate as the fifth value;

[0096] Step S554. Calculate the ratio of the current iteration number to the maximum iteration number as the sixth value;

[0097] Step S555. Calculate the difference between the second set threshold and the sixth value as the seventh value;

[0098] Step S556. Calculate the ratio of the initial fitness to the optimal fitness as the eighth value;

[0099] Step S557. Calculate the difference between the second set threshold and the eighth value as the ninth value;

[0100] Step S558. Calculate the cube of the seventh value as the tenth value;

[0101] Step S559. Calculate the product of the eighth value, the ninth value, and the tenth value to obtain the target mutation rate;

[0102] Step S5510. Determine multiple target sparrows based on the target mutation rate, and determine the preset position update formula based on the types of the target sparrows, and update the initial position parameters of all the target sparrows;

[0103] Specifically, the mutation operation can expand the search space of the sparrow population, but not every sparrow individual needs to perform this operation in each iteration. It needs to be determined by the mutation rate. The mutation rate calculation formula is:

[0104]

[0105] where, e i is the mutation rate of sparrow i; e i,max is the preset maximum mutation rate of sparrow i; e i,min is the preset minimum mutation rate of sparrow i; iter i,now is the iteration number of sparrow i; iter max is the maximum number of iterations of the population; fi,now is the fitness of Sparrow i; f best is the optimal fitness of the population.

[0106] By calculating the mutation rate of each sparrow, the sparrows that need to perform mutation operations are determined, and according to the types of sparrows that need to perform mutation operations, the position update formula is determined to perform the position update operation, and the positions of the sparrows that do not perform mutation operations remain unchanged.

[0107] Step S56. Repeat the determination operation, division operation and update operation until the number of sentinels meets the set threshold, and determine the optimal position parameter and optimal fitness from the corresponding initial position parameters;

[0108] Step S57. Adjust the neural network model based on the fracture zone parameter, strength parameter, optimal position parameter, optimal fitness and target reward function to obtain the target monitoring model;

[0109] Specifically, the position of the optimal population after update is determined by judging the number of sentinels. A larger number of sentinels is beneficial for the algorithm to perform global search, while a smaller number is conducive to accelerating convergence and performing local search within a small range. A higher proportion of sentinels can be given to the population in the early stage of the algorithm to enhance the global search ability of the population, and gradually reduce the proportion of sentinels as the number of population iterations increases to accelerate the convergence speed of the algorithm.

[0110] The update formula for the proportion of sentinels is:

[0111]

[0112] where P is the proportion of sentinels; P0 is the initial proportion of sentinels; T is the current iteration number; iter max is the maximum number of iterations of the population; P min is the preset minimum value of the proportion of sentinels;

[0113] When P > P min , continue to perform the sparrow position update iteration operation until the condition is met; when P ≤ P min , end the iteration when the condition is met, obtain the optimal position and best fitness value from the global, determine the optimal weights and thresholds of the neural network, and send the optimal weights and thresholds back to the convolutional neural network for retraining to obtain the target monitoring model.

[0114] Step S60. Input the real-time fracture zone parameter and real-time rock mass parameter into the target monitoring model to obtain the surrounding rock state monitoring result during blasting excavation;

[0115] In the case of the whole body, in the monitoring of the surrounding rock state, the monitoring results include whether the current bad section is suitable for blasting and the appropriate blasting intensity. These monitoring results enable the staff to timely adjust the blasting position and intensity of the surrounding rock, ensuring the safety of the blasting excavation work.

[0116] Embodiment 2:

[0117] As Figure 3 shown, this embodiment provides a monitoring system for the blasting excavation of the surrounding rock of a tunnel in a bad section. The system includes:

[0118] The first acquisition unit 10 is used to respectively acquire the historical fracture zone parameters and the real-time fracture zone parameters of the target section. Both the historical fracture zone parameters and the real-time fracture zone parameters include the fracture zone width, fracture zone dip angle, fracture zone strike, fracture zone length, and fracture zone displacement;

[0119] The second acquisition unit 20 is used to respectively acquire the historical rock mass parameters and the real-time rock mass parameters of the target section. Both the historical rock mass parameters and the real-time rock mass parameters include the filling material type and the rock type;

[0120] The analysis unit 30 is used to analyze and process the historical rock mass parameters to obtain strength parameters, and the strength parameters include shear strength and compressive strength;

[0121] The first construction unit 40 is used to construct a reward function based on the fracture zone parameters, strength parameters, and the linear weighted method to obtain a target reward function;

[0122] The training unit 50 is used to train a preset neural network model based on the fracture zone parameters, strength parameters, and the target reward function to obtain a target monitoring model. The blasting excavation point information is preset in the preset neural network;

[0123] The input unit 60 inputs the real-time fracture zone parameters and the real-time rock mass parameters into the target monitoring model to obtain the monitoring results of the surrounding rock state during blasting excavation.

[0124] In a specific implementation manner disclosed in this application, the first construction unit 40 includes:

[0125] The first calculation unit is used to calculate the fracture zone coefficients and strength coefficients based on the particle swarm optimization algorithm. The fracture zone coefficients include the fracture zone width coefficient, fracture zone dip angle coefficient, fracture zone strike coefficient, fracture zone length coefficient, and fracture zone displacement coefficient, and the strength coefficients include the shear strength coefficient and the compressive strength coefficient;

[0126] A second calculation unit, configured to calculate a reward value based on fracture zone parameters, strength parameters, and corresponding preset parameter safety ranges, where the parameter safety ranges include a fracture zone width safety range, a fracture zone dip angle safety range, a fracture zone strike safety angle range, a fracture zone length safety range, a fracture zone displacement safety range, a shear strength parameter safety range, and a compressive strength parameter safety range, and the reward value includes a fracture zone reward value and a strength reward value. The fracture zone reward value includes a fracture zone width reward value, a fracture zone dip angle reward value, a fracture zone strike reward value, a fracture zone length reward value, and a fracture zone displacement reward value. The strength reward value includes a shear strength reward value and a compressive strength reward value;

[0127] A third calculation unit, configured to calculate the product of the fracture zone coefficient and the strength coefficient and the corresponding reward value, and perform a summation calculation on the product results to construct an objective reward function.

[0128] In a specific implementation manner disclosed in this application, the training unit 50 includes:

[0129] An initialization unit, configured to initialize the positions of the sparrow population based on a chaotic mapping to obtain multiple initial position parameters;

[0130] A second construction unit, configured to construct a model based on the initial position parameters to obtain a neural network model;

[0131] A first determination unit, configured to perform an operation: based on the initial position parameters of all sparrows, determine the initial fitness of all sparrows;

[0132] A partitioning unit, configured to perform an operation: based on the initial fitness, partition all sparrows into multiple categories, where the categories include discoverers, followers, and vigilant ones;

[0133] An update unit, configured to perform an operation: based on the initial fitness and the sparrow categories, update the initial position parameters of all sparrows;

[0134] A first repetition unit, configured to repeat the determination operation, the partitioning operation, and the update operation until the number of vigilant ones meets a set threshold, and determine the optimal position parameter and the optimal fitness from the corresponding initial position parameters;

[0135] An adjustment unit, configured to adjust the neural network model based on the fracture zone parameters, the strength parameters, the optimal position parameter, the optimal fitness, and the objective reward function to obtain an objective monitoring model.

[0136] In a specific implementation manner disclosed in this application, the initialization unit includes:

[0137] A third acquisition unit, configured to acquire a random position parameter and a chaotic control parameter of any sparrow, where the initial position parameter is within a first set range, and the chaotic control parameter is within a second set range;

[0138] A fourth calculation unit for a first calculation operation: calculating the product of an initial position parameter and a first set threshold as a first value;

[0139] A fifth calculation unit for a second calculation operation: calculating the cosine function value of the first value as a second value;

[0140] A sixth calculation unit for a third calculation operation: calculating the product of a chaos control parameter and the second value as a third value;

[0141] A seventh calculation unit for a fourth calculation operation: calculating the exponential function value of the third value with the natural constant as the base as a fourth value;

[0142] A second repetition unit for repeating the first calculation operation, the second calculation operation, the third calculation operation, and the fourth calculation operation until a preset number of repetitions is reached to obtain an initial position parameter.

[0143] In a specific implementation manner disclosed in the present application, the update unit includes:

[0144] A fourth acquisition unit for acquiring the maximum mutation rate, the minimum mutation rate, the current iteration number, and the initial fitness of any sparrow;

[0145] A fifth acquisition unit for acquiring the optimal fitness of the entire sparrow population and the set maximum number of iterations;

[0146] An eighth calculation unit for calculating the difference between the maximum mutation rate and the minimum mutation rate as a fifth value;

[0147] A ninth calculation unit for calculating the ratio of the current iteration number to the maximum iteration number as a sixth value;

[0148] A tenth calculation unit for calculating the difference between a second set threshold and the sixth value as a seventh value;

[0149] An eleventh calculation unit for calculating the ratio of the initial fitness to the optimal fitness as an eighth value;

[0150] A twelfth calculation unit for calculating the difference between a second set threshold and the eighth value as a ninth value;

[0151] A thirteenth calculation unit for calculating the cube of the seventh value as a tenth value;

[0152] A fourteenth calculation unit for calculating the product of the eighth value, the ninth value, and the tenth value to obtain a target mutation rate;

[0153] A second determination unit, which determines a plurality of target sparrows based on a target mutation rate, determines a preset position update formula based on the types of the target sparrows, and updates the initial position parameters of all the target sparrows.

[0154] In a specific implementation manner disclosed in the present application, the second calculation unit includes:

[0155] A first setting unit, configured to set the fracture zone parameter as a third set threshold when the fracture zone parameter is within a preset parameter safety range;

[0156] A fifteenth calculation unit, configured to calculate the difference between the upper limit value of the preset parameter safety range and the fracture zone parameter to obtain a first difference when the fracture zone parameter is not within the preset parameter safety range;

[0157] A sixteenth calculation unit, configured to calculate the difference between the upper limit value and the lower limit value of the preset parameter safety range to obtain a second difference;

[0158] A seventeenth calculation unit, configured to calculate the ratio of the first difference to the second difference to obtain a first ratio;

[0159] An eighteenth calculation unit, configured to calculate the product of the first ratio and a corresponding preset fracture zone adjustment factor to obtain a first product, where the preset fracture zone adjustment factor includes a fracture zone parameter adjustment factor, and the fracture zone parameter adjustment factor includes a fracture zone width adjustment factor, a fracture zone dip angle adjustment factor, a fracture zone strike adjustment factor, a fracture zone length adjustment factor, and a fracture zone displacement adjustment factor;

[0160] A nineteenth calculation unit, configured to calculate the exponential function value of the first product with the natural constant as the base to obtain a fracture zone reward value.

[0161] In a specific implementation manner disclosed in the present application, the second calculation unit further includes:

[0162] A second setting unit, configured to set the strength parameter as a fourth set threshold when the strength parameter is within a preset parameter safety range;

[0163] A twentieth calculation unit, configured to calculate the difference between the upper limit value and the lower limit value of the preset parameter safety range to obtain a third difference when the strength parameter is not within the preset parameter safety range;

[0164] A twenty-first calculation unit, configured to calculate the ratio of the strength parameter to the upper limit value of the preset parameter safety range to obtain a second ratio;

[0165] A twenty-second calculation unit, configured to calculate the difference between the third set threshold and the second ratio to obtain a fourth difference;

[0166] A twenty-third calculation unit, configured to calculate the product of the fourth difference and the third difference to obtain a second product;

[0167] A twenty-fourth calculation unit, configured to calculate a product of the second product and a corresponding preset strength adjustment factor to obtain a third product, where the preset strength adjustment factor includes a shear strength adjustment factor and a compressive strength adjustment factor;

[0168] A twenty-fifth calculation unit, configured to calculate an exponential function value with the natural constant as the base of the third product to obtain a strength reward value.

[0169] It should be noted that regarding the system in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0170] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0171] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present invention, and all should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A monitoring method for blasting excavation of surrounding rock in tunnels in poor sections, characterized in that, Including: Respectively obtain the historical fault zone parameters and real-time fault zone parameters of the target area. Both the historical fault zone parameters and the real-time fault zone parameters include fault zone width, fault zone dip angle, fault zone strike, fault zone length, and fault zone displacement; Respectively obtain the historical rock mass parameters and real-time rock mass parameters of the target area. Both the historical rock mass parameters and the real-time rock mass parameters include filling material types and rock types; Analyze and process the historical rock mass parameters to obtain strength parameters, where the strength parameters include shear strength and compressive strength; Construct a reward function based on the fault zone parameters, the strength parameters, and the linear weighted method to obtain a target reward function; Train a preset neural network model based on the fault zone parameters, the strength parameters, and the target reward function to obtain a target monitoring model. The blasting excavation point information is pre-set in the preset neural network; Input the real-time fault zone parameters and the real-time rock mass parameters into the target monitoring model to obtain the surrounding rock state monitoring results during blasting excavation.

2. The monitoring method for blasting excavation of surrounding rock in tunnels in poor sections according to claim 1, characterized in that , Constructing a reward function based on the fault zone parameters, the strength parameters, and the linear weighted method to obtain a target reward function, including: Calculate the fault zone coefficients and strength coefficients based on the particle swarm optimization algorithm. The fault zone coefficients include fault zone width coefficient, fault zone dip angle coefficient, fault zone strike coefficient, fault zone length coefficient, and fault zone displacement coefficient. The strength coefficients include shear strength coefficient and compressive strength coefficient; Calculate the reward values based on the fault zone parameters, the strength parameters, and the corresponding preset parameter safety ranges. The parameter safety ranges include fault zone width safety range, fault zone dip angle safety range, fault zone strike safety angle range, fault zone length safety range, fault zone displacement safety range, shear strength parameter safety range, and compressive strength parameter safety range. The reward values include fault zone reward values and strength reward values. The fault zone reward values include fault zone width reward value, fault zone dip angle reward value, fault zone strike reward value, fault zone length reward value, and fault zone displacement reward value. The strength reward values include shear strength reward value and compressive strength reward value; Calculate the product of the fault zone coefficients and the strength coefficients and the corresponding reward values, and sum the product results to construct the target reward function.

3. The monitoring method for blasting excavation of surrounding rock in tunnels in poor sections according to claim 1, wherein , Training a preset neural network model based on the fault zone parameters, the strength parameters, and the target reward function to obtain a target monitoring model. The blasting excavation point information is pre-set in the preset neural network, including: Initialize the positions of the sparrow population based on chaotic mapping to obtain multiple initial position parameters; Construct a model based on the initial position parameters to obtain the neural network model; Determine the operation: Based on the initial position parameters of all sparrows, determine the initial fitness of all sparrows; Partition operation: Divide all sparrows into multiple categories based on the initial fitness. The categories include discoverers, followers, and vigilants; Update operation: Update the initial position parameters of all sparrows based on the initial fitness and sparrow categories; Repeat the determination operation, the division operation, and the update operation until the number of sentinels meets the set threshold, and then determine the optimal position parameter and the optimal fitness from the corresponding initial position parameters; Adjust the neural network model based on the fracture zone parameter, the strength parameter, the optimal position parameter, the optimal fitness, and the target reward function to obtain the target monitoring model.

4. The monitoring method for blasting excavation of surrounding rock in tunnels in poor sections according to claim 3, characterized in that , Initialize the positions of the sparrow population based on the chaotic mapping to obtain multiple initial position parameters, including: Obtain the random position parameter and the chaotic control parameter of any sparrow. The initial position parameter is within the first set range, and the chaotic control parameter is within the second set range; First calculation operation: Calculate the product of the initial position parameter and the first set threshold as the first value; Second calculation operation: Calculate the cosine function value of the first value as the second value; Third calculation operation: Calculate the product of the chaotic control parameter and the second value as the third value; Fourth calculation operation: Calculate the exponential function value of the third value with the natural constant as the base as the fourth value; Repeat the first calculation operation, the second calculation operation, the third calculation operation, and the fourth calculation operation until the preset number of repetitions is reached to obtain the initial position parameter.

5. The monitoring method for blasting excavation of surrounding rock in tunnels in poor sections according to claim 2, characterized in that , Calculate the reward value based on the fracture zone parameter, the strength parameter, and the corresponding preset parameter safety range, including: When the fracture zone parameter is within the preset parameter safety range, the fracture zone parameter is the third set threshold; When the fracture zone parameter is not within the preset parameter safety range, calculate the difference between the upper limit value of the preset parameter safety range and the fracture zone parameter to obtain the first difference; Calculate the difference between the upper limit value and the lower limit value of the preset parameter safety range to obtain the second difference; Calculate the ratio of the first difference to the second difference to obtain the first ratio; Calculate the product of the first ratio and the corresponding preset fracture zone adjustment factor to obtain the first product. The preset fracture zone adjustment factor includes the fracture zone parameter adjustment factor, and the fracture zone parameter adjustment factor includes the fracture zone width adjustment factor, the fracture zone dip angle adjustment factor, the fracture zone strike adjustment factor, the fracture zone length adjustment factor, and the fracture zone displacement adjustment factor; Calculate the exponential function value of the first product with the natural constant as the base to obtain the fracture zone reward value.

6. The monitoring method for the blasting excavation of surrounding rock in tunnels in poor ground sections according to claim 2, characterized in that , The calculation formula of the target reward function is: Q = w1*q1 + w2*q2 + w3*q3 + w4*q4 + w5*q5 + w6*q6 + w7*q7 Where Q is the target reward function; w1 is the fracture zone width coefficient; q1 is the fracture zone width reward value; w2 is the fracture zone dip angle coefficient; q2 is the fracture zone dip angle reward value; w3 is the fracture zone strike coefficient; q3 is the fracture zone strike reward value; w4 is the fracture zone length coefficient; q4 is the fracture zone length reward value; w5 is the fracture zone displacement coefficient; q5 is; w6 is the shear strength coefficient; q6 is the shear strength reward value; w7 is the compressive strength coefficient; q7 is the compressive strength reward value.

7. The monitoring method for blasting excavation of surrounding rock in tunnels in poor sections according to claim 5, characterized in that , The calculation formula of the fracture zone reward value is: Wherein, J is the fracture zone reward value; α is the adjustment factor; MAX is the upper limit value of the preset parameter safety range; MIN is the lower limit value of the preset parameter safety range; X is the fracture zone parameter.

8. A monitoring system for blasting excavation of tunnel surrounding rock in poor sections, characterized in that, Including: A first acquisition unit, configured to respectively acquire the historical fracture zone parameters and the real-time fracture zone parameters of the target area, where the historical fracture zone parameters and the real-time fracture zone parameters both include the fracture zone width, fracture zone dip angle, fracture zone strike, fracture zone length, and fracture zone displacement; A second acquisition unit, configured to respectively acquire the historical rock mass parameters and the real-time rock mass parameters of the target area, where the historical rock mass parameters and the real-time rock mass parameters both include the filling material type and the rock type; An analysis unit, configured to analyze and process the historical rock mass parameters to obtain strength parameters, where the strength parameters include shear strength and compressive strength; A first construction unit, configured to construct a reward function based on the fracture zone parameters, the strength parameters, and the linear weighted method to obtain a target reward function; A training unit, configured to train a preset neural network model based on the fracture zone parameters, the strength parameters, and the target reward function to obtain a target monitoring model, where the blasting excavation point information is pre-set in the preset neural network; An input unit, configured to input the real-time fracture zone parameters and the real-time rock mass parameters into the target monitoring model to obtain the surrounding rock state monitoring result during blasting excavation.

9. The monitoring system for blasting excavation of surrounding rock in tunnels in poor sections according to claim 8, characterized in that, The first construction unit includes: A first calculation unit, configured to calculate the fracture zone coefficient and the strength coefficient based on the particle swarm optimization algorithm, where the fracture zone coefficient includes the fracture zone width coefficient, fracture zone dip angle coefficient, fracture zone strike coefficient, fracture zone length coefficient, and fracture zone displacement coefficient, and the strength coefficient includes the shear strength coefficient and the compressive strength coefficient; A second calculation unit, configured to calculate the reward value based on the fracture zone parameters, the strength parameters, and the corresponding preset parameter safety range, where the parameter safety range includes the fracture zone width safety range, fracture zone dip angle safety range, fracture zone strike safety angle range, fracture zone length safety range, fracture zone displacement safety range, shear strength parameter safety range, and compressive strength parameter safety range, the reward value includes the fracture zone reward value and the strength reward value, the fracture zone reward value includes the fracture zone width reward value, fracture zone dip angle reward value, fracture zone strike reward value, fracture zone length reward value, and fracture zone displacement reward value, and the strength reward value includes the shear strength reward value and the compressive strength reward value; A third calculation unit, configured to calculate the product of the fracture zone coefficient and the strength coefficient and the corresponding reward value, and perform a summation calculation on the product results to construct the target reward function.

10. The monitoring system for blasting excavation of surrounding rock in tunnels in poor sections according to claim 8, characterized in that, The training unit includes: An initialization unit, configured to initialize the sparrow population position based on the chaotic mapping to obtain a plurality of initial position parameters; A second construction unit, configured to construct a model based on the initial position parameters to obtain the neural network model; A first determination unit, configured to determine an operation: based on the initial position parameters of all sparrows, determine the initial fitness of all sparrows; A division unit for division operations: dividing all sparrows into multiple categories based on the initial fitness, where the categories include discoverers, followers, and vigilant ones; An update unit for update operations: updating the initial position parameters of all sparrows based on the initial fitness and sparrow categories; A first repetition unit for repeating the determination operation, the division operation, and the update operation until the number of vigilant ones meets a set threshold, and then determining the optimal position parameters and the optimal fitness from the corresponding initial position parameters; An adjustment unit for adjusting the neural network model based on the fracture zone parameter, the strength parameter, the optimal position parameter, the optimal fitness, and the target reward function to obtain the target monitoring model.

Images