Monitoring method and system for blasting excavation of tunnel surrounding rock in bad section

Abstract

The invention provides a monitoring method and system for blasting excavation of tunnel surrounding rock in a bad section, and relates to the technical field of tunnel construction, and the monitoring method comprises the following steps: respectively obtaining historical fault zone parameters and real-time fault zone parameters of a target section; historical rock mass parameters and real-time rock mass parameters of the target section are obtained respectively; 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 fault zone parameter, the strength parameter and the target reward function to obtain a target monitoring model; and inputting 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. According to the invention, by collecting the related parameters of the fault zone and training the neural network model, the monitoring model with high flexibility and good generalization ability is constructed, the complex relationship between data can be well captured, the construction safety is improved, and a scientific basis and powerful data support are provided 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 of a tunnel in a bad area. Background Art

[0002] Fault zone is a geological structure, the existence of which may lead to discontinuity and strength reduction of rock mass, thereby increasing the complexity and danger of blasting operations. Therefore, there is an urgent need for an accurate and high-performance monitoring model to monitor the state of surrounding rock on the fault zone in real time to 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 tunnel surrounding rock in bad areas to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0004] In a first aspect, the present application provides a method for monitoring blasting excavation of surrounding rock of a tunnel in a poor location, comprising:

[0005] Respectively obtain historical fault zone parameters and real-time fault zone parameters of the target section, wherein the historical fault zone parameters and the real-time fault zone parameters both include fault zone width, fault zone inclination, fault zone strike, fault zone length and fault zone displacement;

[0006] Respectively obtaining historical rock mass parameters and real-time rock mass parameters of the target area, wherein the historical rock mass parameters and the real-time rock mass parameters both include filler types and rock types;

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

[0008] Constructing a reward function based on the fracture zone parameter, the strength parameter and a linear weighting method to obtain a target reward function;

[0009] Based on the fault zone parameter, the strength parameter and the target reward function, a preset neural network model is trained to obtain a target monitoring model, wherein the preset neural network is pre-set with blasting excavation point information;

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

[0011] In a second aspect, the present application also provides a monitoring system for blasting excavation of surrounding rock of tunnels in bad locations, comprising:

[0012] A first acquisition unit is used to respectively acquire historical fault zone parameters and real-time fault zone parameters of a target section, wherein the historical fault zone parameters and the real-time fault zone parameters both include fault zone width, fault zone inclination, fault zone strike, fault zone length and fault zone displacement;

[0013] A second acquisition unit is used to respectively acquire historical rock mass parameters and real-time rock mass parameters of the target section, wherein the historical rock mass parameters and the real-time rock mass parameters both include filler types and rock types;

[0014] An analysis unit, used for analyzing and processing the historical rock mass parameters to obtain strength parameters, wherein the strength parameters include shear strength and compressive strength;

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

[0016] A training unit, used for training a preset neural network model based on the fault zone parameter, the strength parameter and the target reward function to obtain a target monitoring model, wherein the preset neural network is pre-set with blasting excavation point information;

[0017] The input unit inputs 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 result during blasting excavation.

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

[0019] The present invention constructs a monitoring model with strong flexibility and good generalization ability by collecting relevant parameters of the fault zone and training the neural network model. It can better capture the complex relationship between data, improve the safety of construction, 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 following description, and partly become apparent from the description, or be understood by practicing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0022] Figure 1It is a schematic flow chart of a monitoring method for blasting excavation of surrounding rock of a tunnel in a bad location according to an embodiment of the present invention;

[0023] Figure 2 is a chaotic parameter mapping diagram described in an embodiment of the present invention;

[0024] Figure 3 It is a schematic diagram of a monitoring system for blasting excavation of surrounding rock of a tunnel in a poor location as described in an embodiment of the present invention.

[0025] Markings 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 DESCRIPTION

[0026] In order to make the purpose, 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 in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0028] Embodiment 1:

[0029] This embodiment provides a method for monitoring blasting excavation of tunnel surrounding rock in unfavorable areas.

[0030] See also Figure 1 , the figure shows that the method includes step S10, step S20, step S30, step S40, step S50 and step S60.

[0031] Step S10. respectively obtain historical fault zone parameters and real-time fault zone parameters of the target section, wherein the historical fault zone parameters and the real-time fault zone parameters both include fault zone width, fault zone inclination, fault zone strike, fault zone length and fault zone displacement;

[0032] Step S20. respectively obtain historical rock mass parameters and real-time rock mass parameters of the target area, wherein the historical rock mass parameters and the real-time rock mass parameters both include filler types and rock types;

[0033] Specifically, the target location in the present application is a location with a fault zone, that is, a bad location. Since the existence of the fault zone will affect the propagation and results of the blasting, the fault zone needs to additionally consider the relevant parameters of the fault zone and the rock parameters in the fault zone compared to the normal location, so as to effectively control the impact of the 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, which include shear strength and compressive strength;

[0035] Specifically, shear strength and compressive strength are key parameters that characterize the mechanical properties of rock mass. These parameters can provide a comprehensive understanding of the bearing capacity, stability and destructive behavior of the rock mass under various stress conditions, providing a scientific basis for subsequent blasting calculations and safety assessments.

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

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

[0038] Step S41. Calculate the fracture zone coefficient and strength coefficient based on the particle swarm optimization algorithm, the fracture zone coefficient includes the fracture zone width coefficient, the fracture zone inclination coefficient, the fracture zone strike coefficient, the fracture zone length coefficient and the fracture zone displacement coefficient, and the strength coefficient includes the shear strength coefficient and the compressive strength coefficient;

[0039] Specifically, the fracture zone coefficient and intensity coefficient of heart rate variability are randomly initialized, and the maximization target reward function is set as the objective function; in each iteration, based on the preset position update formula and fitness function, the fitness function value of the current solution is calculated, the solutions with higher fitness function values ​​are retained, and the positions of the remaining solutions are updated according to the position update formula. As the iteration proceeds, the number of remaining solutions gradually decreases until the number meets the set conditions, and the solution with the largest fitness function value is determined, which corresponds to the optimal weight coefficient.

[0040] Step S42. Based on the fault zone parameters, strength parameters and corresponding preset parameter safety ranges, a reward value is calculated, the parameter safety range includes a fault zone width safety range, a fault zone inclination safety range, a fault zone direction safety angle range, a fault zone length safety range, a fault zone displacement safety range, a shear strength parameter safety range and a compressive strength parameter safety range, the reward value includes a fault zone reward value and a strength reward value, the fault zone reward value includes a fault zone width reward value, a fault zone inclination reward value, a fault zone direction reward value, a fault zone length reward value and a fault zone displacement reward value, the strength reward value includes a shear strength reward value and a 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 a third set threshold value;

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

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

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

[0046] Step S425. Calculate the product of the first ratio and the corresponding preset fault zone adjustment factor to obtain a first product, where the preset fault zone adjustment factor includes a fault zone parameter adjustment factor, and the fault zone parameter adjustment factor includes a fault zone width adjustment factor, a fault zone inclination adjustment factor, a fault zone strike adjustment factor, a fault zone length adjustment factor, and a 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 parameters are not within the preset parameter safety range, the fault zone bonus value J1 calculation formula is:

[0050]

[0051] Among them, J1 is the fault zone reward value; α is the fault zone adjustment factor; MAX is the upper limit of the preset parameter safety range; MIN is the lower limit of the preset parameter safety range; X is the fault 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, the difference between the upper limit value and the lower limit value of the preset parameter safety range is calculated to obtain a third difference value;

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

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

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

[0057] Step S4212. Calculate the product of the second product and the 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;

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

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

[0060] When the strength parameter is not within the preset parameter safety range, the strength reward value J2 is calculated as follows:

[0061]

[0062] Among them, J2 is the strength reward value; β is the strength adjustment factor; MAX is the upper limit of the preset parameter safety range; MIN is the lower limit 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 with the corresponding reward value, and sum the product results to construct a target reward function;

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

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

[0066] Among them, Q is the target reward function; w1 is the fracture zone coefficient; q1 is the fracture zone reward value; w2 is the intensity coefficient; q2 is the intensity reward value;

[0067]

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

[0069]

[0070] Among them, when the strength parameter is within the preset parameter safety range, the strength parameter value is 1; when the strength parameter is not within the preset parameter safety range, the strength parameter value is the value calculated by formula J1; 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. Based on the fault zone parameters, strength parameters and target reward function, the preset neural network model is trained to obtain a target monitoring model, wherein the preset neural network is pre-set with blasting excavation point information;

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

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

[0074] Specifically, the use of chaotic mapping to initialize the sparrow population can perform non-repetitive traversal of the state of the sparrow population within a certain range, so that the sparrow population can be relatively evenly distributed in the entire search space, which not only increases the diversity of the initial sparrow population, but also avoids falling into the local optimal state during the sparrow algorithm search process.

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

[0076] Step S511. Obtain random position parameters and chaos control parameters of any sparrow, the initial position parameters are within a first set range, and the chaos control parameters are within a second set range;

[0077] Step S512. First calculation operation: calculating 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 value as the second value;

[0079] Step S514. A third calculation operation: calculating the product of the chaos control parameter and the second value as a third value;

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

[0081] Step S516. Repeat 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;

[0082] Specifically, the chaotic mapping formula is:

[0083]

[0084] in, is the k+1th chaos value of sparrow i; is the k-th chaotic value of sparrow i, and its value range is [0,1]; γ is the control parameter of the chaotic system;

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

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

[0087] Specifically, the model is constructed using the initial position parameters of the Sparrow algorithm, and these initialized position parameters will become the initial predictions of the model.

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

[0089] Step S54. Division operation: based on the initial fitness, all sparrows are divided into multiple categories, including discoverers, followers and guards;

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

[0091] Specifically, there are three types of sparrows in the population, including discoverers, followers and sentinels. Different types of sparrows play different roles in the population, that is, the corresponding position update formulas are also different.

[0092] Specifically, step S55 specifically includes step S551, step S552, step S553, step S554, step S555, step S556, step S557, step S558, step S559 and step 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 number of iterations to the maximum number of iterations 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 a preset position update formula based on the type of the target sparrow, and update the initial position parameters of all target sparrows;

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

[0104]

[0105] Among them, e i is the mutation rate of sparrow i; e i,max The maximum mutation rate pre-set for sparrow i; e i,min The minimum mutation rate pre-set for sparrow i; iter i,now is the number of iterations 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] The sparrows that need to be mutated are determined by calculating the mutation rate of each sparrow, and the position update formula is determined according to the types of sparrows that need to be mutated, and the position update operation is performed, and the positions of the sparrows that have not been mutated remain unchanged.

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

[0108] Step S57. Adjust the neural network model based on the fault zone parameters, strength parameters, optimal position parameters, optimal fitness and target reward function to obtain a 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 conducive to the global search of the algorithm, while a smaller number is conducive to faster convergence and local search in 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. As the number of population iterations increases, the proportion of sentinels can be gradually reduced to speed up the convergence of the algorithm.

[0110] The formula for updating the proportion of vigilantes is:

[0111]

[0112] Among them, P is the proportion of vigilant people; P0 is the initial proportion of vigilant people; T is the current number of iterations; iter max is the maximum number of iterations of the population; P min It is the preset minimum value of the ratio of alerters;

[0113] When P>P min When P≤P min When the conditions are met, the iteration ends, the optimal position and the best fitness value are obtained from the global, the optimal weights and thresholds of the neural network are determined, and the optimal weights and thresholds are transmitted back to the convolutional neural network for retraining to obtain the target monitoring model.

[0114] Step S60. 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 and excavation;

[0115] Specifically, in the surrounding rock status monitoring, 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 make timely adjustments to the surrounding rock blasting position and blasting intensity to ensure the safety of blasting and excavation work.

[0116] Embodiment 2:

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

[0118] The first acquisition unit 10 is used to respectively acquire historical fault zone parameters and real-time fault zone parameters of the target section, wherein the historical fault zone parameters and the real-time fault zone parameters both include fault zone width, fault zone inclination, fault zone strike, fault zone length and fault zone displacement;

[0119] A second acquisition unit 20 is used to respectively acquire historical rock mass parameters and real-time rock mass parameters of the target section, wherein the historical rock mass parameters and the real-time rock mass parameters both include filler types and rock types;

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

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

[0122] A training unit 50 is used 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, wherein the preset neural network is pre-set with blasting excavation point information;

[0123] The input unit 60 inputs 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 result during blasting excavation.

[0124] In a specific embodiment disclosed in the present application, the first building unit 40 includes:

[0125] A first calculation unit is used to calculate the fracture zone coefficient and the strength coefficient based on the particle swarm optimization algorithm, the fracture zone coefficient includes the fracture zone width coefficient, the fracture zone inclination coefficient, the fracture zone strike coefficient, the fracture zone length coefficient and the fracture zone displacement coefficient, and the strength coefficient includes the shear strength coefficient and the compressive strength coefficient;

[0126] A second calculation unit is used to calculate a reward value based on a fault zone parameter, a strength parameter and a corresponding preset parameter safety range, wherein the parameter safety range includes a fault zone width safety range, a fault zone inclination safety range, a fault zone direction safety angle range, a fault zone length safety range, a fault zone displacement safety range, a shear strength parameter safety range and a compressive strength parameter safety range, and the reward value includes a fault zone reward value and a strength reward value, wherein the fault zone reward value includes a fault zone width reward value, a fault zone inclination reward value, a fault zone direction reward value, a fault zone length reward value and a fault zone displacement reward value, and the strength reward value includes a shear strength reward value and a compressive strength reward value;

[0127] The third calculation unit is used to calculate the product of the fracture zone coefficient and the strength coefficient with the corresponding reward value, and sum the product results to construct a target reward function.

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

[0129] An initialization unit, used for initializing the position of the sparrow population based on chaotic mapping to obtain a plurality of initial position parameters;

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

[0131] The first determining unit is used for determining the operation: determining the initial fitness of all sparrows based on the initial position parameters of all sparrows;

[0132] The division unit is used for division operation: all sparrows are divided into multiple categories based on the initial fitness, including discoverers, followers and guards;

[0133] An updating unit, used for updating operation: based on the initial fitness and the sparrow species, updating the initial position parameters of all sparrows;

[0134] The first repetition unit is used to repeat the determination operation, the division operation and the update operation until the number of the alerters meets the set threshold, and then determine the optimal position parameter and the optimal fitness from the corresponding initial position parameters;

[0135] The adjustment unit is used to adjust the neural network model based on the fault zone parameters, strength parameters, optimal position parameters, optimal fitness and target reward function to obtain the target monitoring model.

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

[0137] A third acquisition unit is used to acquire a random position parameter and a chaos control parameter of any sparrow, wherein the initial position parameter is within a first setting range, and the chaos control parameter is within a second setting range;

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

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

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

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

[0142] The second repeating unit is used to repeat 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 disclosed in the present application, the updating unit includes:

[0144] The fourth acquisition unit is used to obtain the maximum mutation rate, the minimum mutation rate, the current number of iterations and the initial fitness of any sparrow;

[0145] A fifth acquisition unit is used to acquire the optimal fitness of the entire sparrow population and a set maximum number of iterations;

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

[0147] a ninth calculation unit, configured to calculate a ratio of a current number of iterations to a maximum number of iterations as a sixth value;

[0148] a tenth calculating unit, configured to calculate a difference between the second set threshold value and the sixth value as a seventh value;

[0149] an eleventh calculation unit, used to calculate a ratio of the initial fitness to the optimal fitness as an eighth value;

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

[0151] a thirteenth calculating unit, configured to calculate the cube of the seventh value as a tenth value;

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

[0153] The second determination unit determines a plurality of target sparrows based on the 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 disclosed in the present application, the second computing unit includes:

[0155] A first setting unit, used for setting the fault zone parameter to a third set threshold value when the fault zone parameter is within a preset parameter safety range;

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

[0157] A sixteenth calculation unit, used 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 value;

[0158] A seventeenth calculation unit, configured to calculate a 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 fault zone adjustment factor to obtain a first product, wherein the preset fault zone adjustment factor includes a fault zone parameter adjustment factor, and the fault zone parameter adjustment factor includes a fault zone width adjustment factor, a fault zone dip adjustment factor, a fault zone strike adjustment factor, a fault zone length adjustment factor, and a fault zone displacement adjustment factor;

[0160] The nineteenth calculation unit is used to calculate the exponential function value of the first product with the natural constant as the base to obtain the fault zone reward value.

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

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

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

[0164] A twenty-first calculation unit, used for calculating the ratio of the intensity 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 a difference between a third set threshold and the second ratio to obtain a fourth difference;

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

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

[0168] The twenty-fifth calculation unit is used to calculate the exponential function value of the third product with the natural constant as the base to obtain the intensity reward value.

[0169] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0170] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0171] The above is only a specific embodiment 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 substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A monitoring method for tunnel surrounding rock blasting excavation in bad areas, characterized in that: include: Respectively obtain historical fault zone parameters and real-time fault zone parameters of the target section, wherein the historical fault zone parameters and the real-time fault zone parameters both include fault zone width, fault zone inclination, fault zone strike, fault zone length and fault zone displacement; Respectively obtaining historical rock mass parameters and real-time rock mass parameters of the target area, wherein the historical rock mass parameters and the real-time rock mass parameters both include filler types and rock types; Analyzing and processing the historical rock mass parameters to obtain strength parameters, wherein the strength parameters include shear strength and compressive strength; Constructing a reward function based on the fracture zone parameter, the strength parameter and a linear weighting method to obtain a target reward function; Based on the fault zone parameter, the strength parameter and the target reward function, a preset neural network model is trained to obtain a target monitoring model, wherein the preset neural network is pre-set with blasting excavation point information; The real-time fault zone parameters and the real-time rock mass parameters are input into the target monitoring model to obtain the surrounding rock state monitoring result during blasting excavation.

2. The monitoring method for blasting excavation of tunnel surrounding rock in bad areas according to claim 1 is characterized in that , constructing a reward function based on the fracture zone parameter, the intensity parameter and the linear weighting method to obtain a target reward function, including: Calculate the fracture zone coefficient and strength coefficient based on the particle swarm optimization algorithm, wherein the fracture zone coefficient includes the fracture zone width coefficient, the fracture zone inclination coefficient, the fracture zone strike coefficient, the fracture zone length coefficient and the fracture zone displacement coefficient, and the strength coefficient includes the shear strength coefficient and the compressive strength coefficient; Based on the fault zone parameters, the strength parameters and the corresponding preset parameter safety ranges, a reward value is calculated, the parameter safety range includes a fault zone width safety range, a fault zone inclination safety range, a fault zone direction safety angle range, a fault zone length safety range, a fault zone displacement safety range, a shear strength parameter safety range and a compressive strength parameter safety range, the reward value includes a fault zone reward value and a strength reward value, the fault zone reward value includes a fault zone width reward value, a fault zone inclination reward value, a fault zone direction reward value, a fault zone length reward value and a fault zone displacement reward value, and the strength reward value includes a shear strength reward value and a compressive strength reward value; The product of the fracture zone coefficient and the strength coefficient and the corresponding reward value is calculated, and the product results are summed to construct the target reward function.

3. The monitoring method for blasting excavation of tunnel surrounding rock in bad areas according to claim 1 is characterized in that , based on the fault zone parameters, the strength parameters and the target reward function, the preset neural network model is trained to obtain a target monitoring model, wherein the preset neural network is pre-set with blasting excavation point information, including: Initialize the position of the sparrow population based on chaotic mapping and obtain multiple initial position parameters; Building a model based on the initial position parameters to obtain the neural network model; Determine operation: Based on the initial position parameters of all sparrows, determine the initial fitness of all sparrows; Division operation: dividing all sparrows into multiple categories based on the initial fitness, the categories including discoverers, followers and guards; Update operation: based on the initial fitness and sparrow species, update the initial position parameters of all sparrows; Repeating the determination operation, the division operation and the update operation until the number of the alerters meets a set threshold, and determining the optimal position parameter and the optimal fitness from the corresponding initial position parameters; The neural network model is adjusted 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 tunnel surrounding rock in bad areas according to claim 3 is characterized in that ,Based on the chaotic mapping, the position of the sparrow population is initialized, and multiple initial position parameters are obtained, including: Obtaining a random position parameter and a chaos control parameter of any sparrow, wherein the initial position parameter is within a first setting range, and the chaos control parameter is within a second setting range; A first calculation operation: calculating the product of the initial position parameter and a first set threshold as a first value; A second calculation operation: calculating a cosine function value of the first value as a second value; A third calculation operation: calculating the product of the chaos control parameter and the second value as a third value; A fourth calculation operation: calculating an exponential function value of the third value with a natural constant as a base, as a fourth value; The first calculation operation, the second calculation operation, the third calculation operation and the fourth calculation operation are repeated until a preset number of repetitions is reached to obtain the initial position parameter.

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

6. The monitoring method for blasting excavation of tunnel surrounding rock in bad areas according to claim 2 is characterized in that ,The target reward function calculation formula is: Q=w1*q1+w2*q2+w3*q3+w4*q4+w5*q5+w6*q6+w7*q7 Among them, Q is the target reward function; w1 is the fault zone width coefficient; q1 is the fault zone width reward value; w2 is the fault zone inclination coefficient; q2 is the fault zone inclination reward value; w3 is the fault zone direction coefficient; q3 is the fault zone direction reward value; w4 is the fault zone length coefficient; q4 is the fault zone length reward value; w5 is the fault 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 tunnel surrounding rock in bad areas according to claim 5 is characterized in that ,The calculation formula of the fracture zone reward value is: Among them, J is the fault zone reward value; α is the adjustment factor; MAX is the upper limit of the preset parameter safety range; MIN is the lower limit of the preset parameter safety range; X is the fault zone parameter.

8. A monitoring system for tunnel surrounding rock blasting excavation in bad areas, characterized in that: include: A first acquisition unit is used to respectively acquire historical fault zone parameters and real-time fault zone parameters of a target section, wherein the historical fault zone parameters and the real-time fault zone parameters both include fault zone width, fault zone inclination, fault zone strike, fault zone length and fault zone displacement; A second acquisition unit is used to respectively acquire historical rock mass parameters and real-time rock mass parameters of the target section, wherein the historical rock mass parameters and the real-time rock mass parameters both include filler types and rock types; An analysis unit, used for analyzing and processing the historical rock mass parameters to obtain strength parameters, wherein the strength parameters include shear strength and compressive strength; A first construction unit is used to construct a reward function based on the fracture zone parameter, the strength parameter and a linear weighting method to obtain a target reward function; A training unit, used for training a preset neural network model based on the fault zone parameter, the strength parameter and the target reward function to obtain a target monitoring model, wherein the preset neural network is pre-set with blasting excavation point information; The input unit inputs 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 result during blasting excavation.

9. The monitoring system for tunnel surrounding rock blasting excavation in bad terrain according to claim 8, characterized in that: The first building block comprises: A first calculation unit is used to calculate the fracture zone coefficient and the strength coefficient based on the particle swarm optimization algorithm, wherein the fracture zone coefficient includes the fracture zone width coefficient, the fracture zone inclination coefficient, the fracture zone strike coefficient, the fracture zone length coefficient and the fracture zone displacement coefficient, and the strength coefficient includes the shear strength coefficient and the compressive strength coefficient; a second calculation unit, for calculating a reward value based on the fault zone parameter, the strength parameter and a corresponding preset parameter safety range, wherein the parameter safety range includes a fault zone width safety range, a fault zone inclination safety range, a fault zone direction safety angle range, a fault zone length safety range, a fault zone displacement safety range, a shear strength parameter safety range and a compressive strength parameter safety range, the reward value includes a fault zone reward value and a strength reward value, the fault zone reward value includes a fault zone width reward value, a fault zone inclination reward value, a fault zone direction reward value, a fault zone length reward value and a fault zone displacement reward value, and the strength reward value includes a shear strength reward value and a compressive strength reward value; The third calculation unit is used to calculate the product of the fracture zone coefficient and the strength coefficient with the corresponding reward value, and sum the product results to construct the target reward function.

10. The monitoring system for tunnel surrounding rock blasting excavation in bad areas according to claim 8, characterized in that: The training unit comprises: An initialization unit, used for initializing the position of the sparrow population based on chaotic mapping to obtain a plurality of initial position parameters; A second construction unit is used to construct a model based on the initial position parameters to obtain the neural network model; The first determining unit is used for determining the operation: determining the initial fitness of all sparrows based on the initial position parameters of all sparrows; A division unit, used for a division operation: dividing all sparrows into a plurality of categories based on the initial fitness, the categories including discoverers, followers and guards; An updating unit, used for an updating operation: updating the initial position parameters of all sparrows based on the initial fitness and the sparrow species; A first repeating unit is used to repeat the determining operation, the dividing operation and the updating operation until the number of the alerters meets a set threshold, and then determine the optimal position parameter and the optimal fitness from the corresponding initial position parameters; An adjustment unit is used to adjust the neural network model based on the fault zone parameter, the strength parameter, the optimal position parameter, the optimal fitness and the target reward function to obtain the target monitoring model.

Images