CN117787105B - Tunnel surrounding rock grading method, device, equipment and readable storage medium - Google Patents

Abstract

The invention provides a method, a device, equipment and a readable storage medium for grading tunnel surrounding rocks, which relate to the technical field of surrounding rock prediction and comprise the steps of acquiring historical surrounding rock data of target surrounding rocks in a historical time period; initializing the sparrow population position based on chaotic mapping to obtain a plurality of initial position parameters; constructing a model based on the initial position parameters to obtain an initial prediction model; training an initial prediction model based on historical surrounding rock data and a sparrow algorithm to obtain a target classification model; inputting real-time surrounding rock data of the target surrounding rock into the target grading model to obtain a real-time surrounding rock grading result of the target surrounding rock. According to the invention, parameters in the convolutional neural network are optimized through the sparrow search algorithm, so that the method can be more quickly and better adapted to the judgment of various working condition models, and a self-adaptive chaotic mapping is adopted, so that a correction step factor is established, the convergence speed of the sparrow search algorithm is improved, and the training efficiency of the model is greatly improved.

Description

A tunnel surrounding rock classification method, device, equipment and readable storage medium

Technical Field

The present invention relates to the technical field of surrounding rock prediction, and in particular to a tunnel surrounding rock classification method, device, equipment and a readable storage medium.

Background technique

Current rock mass classification methods are developed based on previous engineering experience. They do not differentiate between structural resistance, durability and maintainability, and cannot provide design reliability. Therefore, they cannot meet the requirements of modern design specifications.

Summary of the invention

The purpose of the present invention is to provide a tunnel surrounding rock classification method, device, equipment and readable storage medium to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

In a first aspect, the present application provides a tunnel surrounding rock classification method, comprising:

Obtain historical surrounding rock data of target surrounding rock within a historical time period;

Initialize the position of the sparrow population based on chaotic mapping to obtain multiple initial position parameters;

Building a model based on the initial position parameters to obtain an initial prediction model;

The initial prediction model is trained based on the historical surrounding rock data and the Sparrow algorithm to obtain a target classification model;

The real-time surrounding rock data of the target surrounding rock is input into the target classification model to obtain the real-time surrounding rock classification result of the target surrounding rock.

In a second aspect, the present application also provides a tunnel surrounding rock grading device, comprising:

A first acquisition unit is used to acquire historical surrounding rock data of target surrounding rock in a historical time period;

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 construction unit, used to construct a model based on the initial position parameters to obtain an initial prediction model;

A training unit, used for training the initial prediction model using the historical surrounding rock data and the Sparrow algorithm to obtain a target classification model;

The input unit is used to input the real-time surrounding rock data of the target surrounding rock into the target classification model to obtain the real-time surrounding rock classification result of the target surrounding rock.

In a third aspect, the present application also provides a tunnel surrounding rock grading device, comprising:

Memory for storing computer programs;

A processor is used to implement the steps of the tunnel surrounding rock classification method when executing the computer program.

In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned tunnel surrounding rock classification method are implemented.

The beneficial effects of the present invention are:

The present invention optimizes the parameters in the convolutional neural network through the sparrow search algorithm, which can adapt to the discrimination of various working condition models faster and better, and adopts adaptive chaotic mapping to establish a modified step size factor to improve the convergence speed of the sparrow search algorithm, thereby greatly improving the training efficiency of the model.

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 implementing 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

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.

Figure 1 is a schematic diagram of a tunnel surrounding rock classification method according to an embodiment of the present invention;

FIG2 is a parameter mapping diagram described in an embodiment of the present invention;

FIG3 is a schematic structural diagram of a tunnel surrounding rock classification device according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of the structure of the tunnel surrounding rock grading equipment described in an embodiment of the present invention.

Markings in the figure:

10000, first acquisition unit; 20000, initialization unit; 30000, construction unit; 40000, training unit; 50000, input unit; 20100, second acquisition unit; 20200, first calculation unit; 20300, second calculation unit; 20400, third calculation unit; 20500, fourth calculation unit; 20600, repetition unit; 20700, fifth calculation unit; 40100, first determination unit; 40200, division unit; 40300, first update unit; 40400, third acquisition unit; 40500, sixth calculation unit; 40600, seventh calculation unit; 40700, eighth calculation unit; 40800, ninth calculation unit; 40900, second determination unit; 41000, fourth acquisition unit; 41100, The second updating unit; 41200, the third updating unit; 41300, the adjusting unit; 40301, the third determining unit; 40302, the first comparing unit; 40303, the fifth acquiring unit; 40304, the tenth calculating unit; 40305, the first bringing-in unit; 40306, the eleventh calculating unit; 40307, the sixth acquiring unit; 40308, the fourth determining unit; 40309, the second comparing unit; 40310, the twelfth calculating unit; 40311, the second bringing-in unit; 40312, the seventh acquiring unit; 40313, the thirteenth calculating unit; 40314, the third bringing-in unit; 40901, the eighth acquiring unit; 40902, the ninth acquiring unit; 40903, the fifth determining unit; 40904, the fourteenth calculating unit; 40905, the fifteenth calculating unit;

800, tunnel surrounding rock grading equipment; 801, processor; 802, memory; 803, multimedia component; 804, I/O interface; 805, communication component.

Detailed ways

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 here 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.

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.

Embodiment 1:

This embodiment provides a tunnel surrounding rock classification method.

Referring to FIG. 1 , it is shown that the method includes step S10000 , step S20000 , step S30000 , step S40000 , and step S50000 .

Step S10000. Obtain historical surrounding rock data of target surrounding rock within a historical time period;

Specifically, the database of tunnel surrounding rock classification design is collected and organized, including the engineering geological conditions of tunnel surrounding rock in different regions, namely topography, stratum lithology, geological structure, meteorological and hydrological conditions, geostress field, etc., and qualitative indicators of surrounding rock, namely rock hardness, rock integrity, degree of interlocking, rock structure, joint weathering conditions, groundwater conditions and geostress conditions, etc.

Step S20000. Initialize the position of the sparrow population based on chaotic mapping to obtain multiple initial position parameters;

Specifically, use The chaotic mapping is used to initialize the sparrow population, which can traverse the state of the sparrow population without repetition within a certain range, and can make the sparrow population 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 search process of the sparrow algorithm.

Specifically, step S20000 includes:

Step S20100. Obtain random position parameters and chaos control parameters of any sparrow, the initial position is within a first set range, and the chaos control parameters are within a second set range;

Step S20200. First calculation operation: calculating the product of the initial position and the first set threshold as the first product;

Step S20300. Second calculation operation: Calculate the sine function value of the first product as the first value;

Step S20400. A third calculation operation: calculating a ratio of the chaos control parameter to a second set threshold as a first ratio;

Step S20500. Fourth calculation operation: calculating the product of the first value and the first ratio as the second product;

Step S20600. 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 the target position parameter;

Step S20700. Calculate the target position parameters corresponding to all sparrows to obtain multiple initial position parameters of the sparrow population;

Specifically, the mathematical expression of chaos mapping is:

; Among them, /> For sparrows/> The first/> The chaos value of this time; /> For sparrows/> First The chaos value of this time ranges from/> ; /> is the control parameter of the chaotic system, and its value range is/> ;

In this embodiment, the chaotic value after mapping each parameter 2,000 times is used as the initial position parameter of the sparrow, as shown in FIG2 , which is a parameter mapping diagram after 2,000 iterations of chaotic mapping.

Step S30000. Build a model based on the initial position parameters to obtain an initial prediction model;

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

Step S40000. Train the initial prediction model based on historical surrounding rock data and the Sparrow algorithm to obtain a target classification model;

Specifically, step S40000 includes:

Step S40100. Based on the initial position parameters of all sparrows, determine the initial fitness of all sparrows;

Specifically, assuming that the number of individuals in the sparrow population is , each sparrow individual as/> A solution in the dimensional solution space, the fitness of the sparrow population is:

;

in, is the fitness of the sparrow population; /> For the sparrows in the population/> In the /> The position of the dimensional space; For sparrows/> individual fitness.

Step S40200. Division operation: divide all sparrows into discoverers, followers and guards based on initial fitness;

Step S40300. Update operation: Update the initial position parameters of all sparrows based on a preset target formula to obtain multiple updated position parameters;

Specifically, step S40300 includes:

Step S40301. Based on all initial fitness, determine the current warning value;

Step S40302. Compare the current warning value with the preset alert warning value to obtain a first comparison result;

Step S40303. When the first comparison result satisfies the first set condition, obtain the finder's upper limit constraint, the finder's lower limit constraint, the first optimal sparrow position parameter, the first worst sparrow position parameter, the constant factor and the first iteration number;

Step S40304. Based on the upper limit constraint, the lower limit constraint, the first optimal sparrow position parameter, the first worst sparrow position parameter, the constant factor and the first iteration number, calculate the adaptive weight;

Step S40305. Substitute the adaptive weight into the preset first target formula to calculate the updated position parameter after the finder updates;

Step S40306. When the first comparison result satisfies the second set condition, the updated position parameter after the finder is updated is calculated based on the preset second target formula;

Specifically, the global search is too dependent on the position of the discoverer. By referring to the spiral upward search method of iterative optimization in the whale optimization algorithm, an adaptive weight factor is introduced, so that when the discoverer in the sparrow algorithm explores the next area after the position is updated, it searches with a larger step size in the early stage and conducts a small step size convergence exploration in the later stage. The position iteration formula of the sparrow discoverer is as follows:

;

;

in, For the first/> After iterations, the number of sparrows in the population/> The first/> Dimensional position; /> is the number of sparrows in the population after the Tth iteration/> The j-th dimension position of; /> is the adaptive weight factor; /> is the maximum number of iterations of the population; /> is a uniform random number, ranging from/> ; /> is the warning value, the value range is/> ; /> is the warning threshold, the value range is/> ; /> is a random number that follows a normal distribution; /> is a matrix with 1 row and d columns; /> For the first/> After iterations, the number of sparrows in the population/> The worst position of For the first/> After iterations, the number of sparrows in the population/> The optimal position of and/> is a constant factor; /> For sparrows/> The upper limit constraint of For sparrows/> The lower limit constraint of

when When , it means that the warning value is less than the safety value. At this time, there are no predators in the foraging environment, and the discoverer can perform extensive search operations; when /> When the predator is detected, it means that some sparrows in the population have already discovered the predator and have issued an early warning to other sparrows in the population. All sparrows need to fly to a safe area to forage for food.

In the embodiment of the present application, the position of the sparrow follower is updated as follows;

;

in, For the first/> After iterations, the number of sparrows in the population/> The first/> Dimensional position; /> For the first/> The position of the worst sparrow in the population after iterations; /> For the first/> After iterations, the number of sparrows in the population/> The first/> Dimensional position; /> is a random number that follows a normal distribution; /> For the first/> After iterations, the number of sparrows in the population/> Location; /> is a uniform random number, ranging from/> ; /> is the spatial dimension; /> For the first/> After iterations, the number of sparrows in the population/> The first/> Dimensional position; /> The number of individuals in the sparrow population is;

when When , it indicates that the i-th follower has not obtained food and is in a hungry state. At this time, it needs to fly to other places to forage for more energy; when /> This indicates that the Each follower can obtain food and gain energy without having to fly to other places to forage.

Step S40307. Obtain the second iteration number;

Step S40308. Based on all initial fitnesses, determine the best fitness and the worst fitness;

Step S40309. Compare the fitness of the alerter with the optimal fitness to obtain a second comparison result;

Step S40310. When the second comparison result satisfies the third setting condition, the step size control parameter is calculated based on the best fitness, the worst fitness, the initial position parameter and the second iteration number;

Step S40311. Substitute the step length control parameter into the preset third target formula to calculate the updated position parameter of the sentinel after the update;

Step S40312. When the second comparison result satisfies the fourth setting condition, obtain the first random factor;

Step S40313. Calculate the initial parameters based on the best fitness, the worst fitness, the initial position parameters, the first random factor and the second iteration number;

Step S40314. Substitute the initial parameters into the preset fourth target formula to calculate the updated position parameters of the sentinel after the update;

Specifically, in order to improve the convergence speed and accuracy of the sparrow algorithm, the step size factor is modified and/> , the step factor correction formula is:

;

;

in, is the fitness of the best sparrow in the current population; /> is the fitness of the worst sparrow in the current population; /> is the current iteration number; /> For initialization parameters; /> is a uniformly distributed random factor;

The position update formula of the sparrow sentinel is:

;

in, For the first/> After iterations, the number of sparrows in the population/> The first/> Dimensional position; /> is the number of sparrows in the population after the Tth iteration/> The first/> Dimensional position; /> For the first/> The position of the best sparrow in the population after iterations; /> For the first/> The position of the worst sparrow in the population after iterations; /> For sparrows/> Individual fitness; /> is the fitness of the worst sparrow in the current population; is the fitness of the best sparrow in the current population; /> The minimum constant to prevent the denominator from being zero; /> and/> is the step size factor, /> The value range is /> ;

when When , it means that the sparrows are at the edge of the population and are very vulnerable to predators; when /> , it means that the sparrows in the middle of the population are also in danger and need to get closer to other sparrows to reduce the risk of being preyed upon.

Step S40400. First acquisition operation: acquiring the maximum mutation rate, the minimum mutation rate, the current number of iterations and the maximum number of iterations;

Step S40500. Fifth calculation operation: Calculate the difference between the maximum mutation rate and the minimum mutation rate as the first difference;

Step S40600. Sixth calculation operation: calculate the ratio of the current number of iterations to the maximum number of iterations as the second ratio;

Step S40700. Seventh calculation operation: Calculate the difference between the third set threshold and the second ratio as the second difference;

Step S40800. Eighth calculation operation: Calculate the fourth power of the second difference and multiply it by the first difference to obtain the target mutation rate;

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:

;

in, is the mutation rate; /> is the preset maximum mutation rate; /> is the preset minimum mutation rate;/> is the number of individuals in the sparrow population; /> is the maximum number of iterations of the population.

Step S40900. Determine operation: determine the target sparrow based on the target mutation rate, and update and replace the update position parameter based on the preset first formula to obtain the target position parameter;

Specifically, step S40900 includes:

Step S40901. Obtain a second random factor;

Step S40902. Obtain the search range of all sparrows and obtain multiple range parameters;

Step S40903. Determine a minimum value from multiple range parameters as a target range parameter;

Step S40904. Calculate the product of the target range parameter and the second random factor as the third product;

Step S40905. Calculate the sum of the third product and the updated position parameter of the target sparrow to obtain the target position parameter.

Step S40905. Calculate the sum of the third product and the updated position parameter of the target sparrow to obtain the target position parameter.

Specifically, in order to prevent sparrows from clustering too early, the position disturbance variation factor is incorporated, and the calculation formula is:

;

;

in, For the first/> After iterations, the number of sparrows in the population/> The first/> Dimensional position; /> For the first/> After iterations, the number of sparrows in the population/> The first/> Dimensional position; /> is the variation factor; /> is a uniformly distributed random factor; /> For the first/> The search range of each sparrow individual; /> To take the small function.

In the embodiment of the present application, in order to improve the optimization ability of the sparrow algorithm and escape the local optimal problem, the Gaussian-Cauchy mutation is introduced to achieve the purpose of optimizing the algorithm by replacing the parameter variables in the sparrow algorithm. The present application combines the advantages of Gaussian distribution and Cauchy distribution, considers the mutation requirements of different search stages, and designs a Gaussian-Cauchy mutation mechanism to facilitate the retention of sparrow individuals with better fitness positions and enter the next iteration. The expression is as follows:

;

;

in, is the position of the sparrow with better fitness after mutation;/> is the position of the sparrow individual with better fitness in the current population;/> and/> It is a dynamic parameter that is adaptively adjusted with the number of iterations;/> is a random variable that satisfies the Cauchy distribution; /> is a random variable that satisfies Gaussian distribution; /> is the maximum number of iterations of the population; /> is the current iteration number.

Step S41000. Second acquisition operation: acquiring the number of alerters as the target number;

Step S41100. When the target number is greater than the preset minimum value of the alerters, the number of alerters is updated based on the preset second formula, and the division operation is repeated to the second acquisition operation;

Step S41200. When the number of targets is not greater than the minimum value of the alerter, the target optimal sparrow is determined based on the updated position parameter and the target position parameter, and the target optimal position parameter and the target optimal fitness of the target optimal sparrow are determined;

Step S41300. Adjust the initial prediction model based on historical surrounding rock data, target optimal position parameters and target optimal fitness to obtain a target classification model;

Specifically, the position of the optimal population after update is determined by judging the proportion of alerts. A larger number of alerts is conducive to the global search of the algorithm, while a smaller number is conducive to accelerating convergence and performing local search in a small range. A higher proportion of alerts 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 alerts can be gradually reduced to accelerate the convergence of the algorithm.

The formula for updating the proportion of vigilant is:

;

in, The proportion of alert people; /> is the initial ratio of alerters;/> is the current iteration number; /> is the maximum number of iterations of the population; /> It is the preset minimum value of the ratio of alerters;

when When , continue to iterate the sparrow position update operation until the condition is met; when /> When , the conditions are met to end the iteration, obtain the optimal position and the best fitness value from the global, determine the optimal weights and thresholds of the convolutional neural network, and pass the optimal weights and thresholds back to the convolutional neural network for retraining to obtain the target classification model.

Step S50000. Input the real-time surrounding rock data of the target surrounding rock into the target classification model to obtain the real-time surrounding rock classification result of the target surrounding rock;

Specifically, in the surrounding rock classification prediction, the prediction results include the determination of the surrounding rock level, so that the staff can grasp the surrounding rock conditions of the tunnel in real time and make timely adjustments to the surrounding rock level. While meeting the design requirements, through intelligent scheme comparison, the optimal scheme is selected from a large number of design parameters, thereby realizing the informatization of tunnel surrounding rock classification work, greatly saving construction costs, and complying with my country's green and sustainable development concept.

Embodiment 2:

As shown in FIG3 , this embodiment provides a tunnel surrounding rock classification device, the device comprising:

The first acquisition unit 10000 is used to acquire historical surrounding rock data of target surrounding rock in a historical time period;

An initialization unit 20000 is used to initialize the position of the sparrow population based on chaotic mapping to obtain a plurality of initial position parameters;

A construction unit 30000 is used to construct a model based on the initial position parameters to obtain an initial prediction model;

The training unit 40000 is used to train the initial prediction model using historical surrounding rock data and the Sparrow algorithm to obtain a target classification model;

The input unit 50000 is used to input the real-time surrounding rock data of the target surrounding rock into the target classification model to obtain the real-time surrounding rock classification result of the target surrounding rock.

In a specific implementation disclosed in the present application, the initialization unit 20000 includes:

The second acquisition unit 20100 is used to acquire the random position parameter and chaos control parameter of any sparrow, the initial position is within the first setting range, and the chaos control parameter is within the second setting range;

The first calculation unit 20200 is used for a first calculation operation: calculating the product of the initial position and the first set threshold as a first product;

The second calculation unit 20300 is used for a second calculation operation: calculating a sine function value of the first product as a first value;

The third calculation unit 20400 is used for a third calculation operation: calculating a ratio of the chaos control parameter to a second set threshold as a first ratio;

A fourth calculation unit 20500 is configured to perform a fourth calculation operation: calculating a product of the first value and the first ratio as a second product;

A repeating unit 20600 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 a target position parameter;

The fifth calculating unit 20700 is used to calculate the target position parameters corresponding to all sparrows to obtain a plurality of initial position parameters of the sparrow population.

In a specific implementation manner disclosed in the present application, the training unit 40000 includes:

The first determining unit 40100 is used to determine the initial fitness of all sparrows based on the initial position parameters of all sparrows;

A division unit 40200 is used for a division operation: dividing all sparrows into discoverers, followers and guards based on initial fitness;

The first updating unit 40300 is used for the updating operation: updating the initial position parameters of all sparrows based on a preset target formula to obtain a plurality of updated position parameters;

The third acquisition unit 40400 is used for the first acquisition operation: acquiring the maximum mutation rate, the minimum mutation rate, the current number of iterations and the maximum number of iterations;

The sixth calculation unit 40500 is used for a fifth calculation operation: calculating a difference between the maximum mutation rate and the minimum mutation rate as a first difference;

A seventh calculation unit 40600, configured for a sixth calculation operation: calculating a ratio of a current number of iterations to a maximum number of iterations as a second ratio;

An eighth calculation unit 40700 is configured to perform a seventh calculation operation: calculating a difference between a third set threshold and a second ratio as a second difference;

A ninth calculation unit 40800 is used for an eighth calculation operation: calculating the fourth power of the second difference and multiplying the fourth power of the second difference by the first difference to obtain a target mutation rate;

The second determination unit 40900 is used for determining the operation: determining the target sparrow based on the target mutation rate, and updating and replacing the update position parameter based on the preset first formula to obtain the target position parameter;

The fourth acquisition unit 41000 is used for the second acquisition operation: acquiring the number of alerters as the target number;

A second updating unit 41100 is used to update the number of alerters based on a preset second formula when the number of targets is greater than a preset minimum number of alerters, and to repeat the division operation to the second acquisition operation;

The third updating unit 41200 is used to determine the target optimal sparrow based on the update position parameter and the target position parameter when the target number is not greater than the minimum value of the alerter, and determine the target optimal position parameter and the target optimal fitness of the target optimal sparrow;

The adjustment unit 41300 is used to adjust the initial prediction model based on historical surrounding rock data, target optimal position parameters and target optimal fitness to obtain a target classification model.

In a specific implementation manner disclosed in the present application, the first updating unit 40300 includes:

The third determining unit 40301 is used to determine the current warning value based on all initial fitness levels;

The first comparison unit 40302 is used to compare the current warning value with the preset alert warning value to obtain a first comparison result;

A fifth acquisition unit 40303 is used to acquire the upper limit constraint of the finder, the lower limit constraint of the finder, the first optimal sparrow position parameter, the first worst sparrow position parameter, the constant factor and the first iteration number when the first comparison result satisfies the first set condition;

A tenth calculation unit 40304 is used to calculate the adaptive weight based on the upper limit constraint, the lower limit constraint, the first optimal sparrow position parameter, the first worst sparrow position parameter, the constant factor and the first iteration number;

The first input unit 40305 is used to input the adaptive weight into the preset first target formula to calculate the updated position parameter after the finder updates;

The eleventh calculation unit 40306 is used to calculate the updated position parameter after the finder updates based on the preset second target formula when the first comparison result satisfies the second set condition.

In a specific implementation manner disclosed in the present application, the first updating unit 40300 further includes:

A sixth obtaining unit 40307, used to obtain a second iteration number;

The fourth determining unit 40308 is used to determine the best fitness and the worst fitness based on all the initial fitnesses;

The second comparison unit 40309 is used to compare the fitness of the alerter with the optimal fitness to obtain a second comparison result;

A twelfth calculation unit 40310 is used to calculate a step size control parameter based on the best fitness, the worst fitness, the initial position parameter and the second iteration number when the second comparison result satisfies the third setting condition;

The second input unit 40311 is used to input the step length control parameter into the preset third target formula to calculate the updated position parameter of the sentinel after the update;

A seventh acquisition unit 40312, configured to acquire a first random factor when the second comparison result satisfies a fourth setting condition;

A thirteenth calculating unit 40313 is used to calculate the initial parameters based on the best fitness, the worst fitness, the initial position parameter, the first random factor and the second iteration number;

The third input unit 40314 is used to input the initial parameters into the preset fourth target formula to calculate the updated position parameters of the sentinel after the update.

In a specific implementation manner disclosed in the present application, the second determining unit 40900 includes:

An eighth obtaining unit 40901, configured to obtain a second random factor;

The ninth acquisition unit 40902 is used to acquire the search range of all sparrows and obtain multiple range parameters;

A fifth determining unit 40903, configured to determine a minimum value from the multiple range parameters as a target range parameter;

A fourteenth calculation unit 40904, used to calculate the product of the target range parameter and the second random factor as a third product;

The fifteenth calculating unit 40905 is used to calculate the sum of the third product and the updated position parameter of the target sparrow to obtain the target position parameter.

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

Embodiment 3:

Corresponding to the above method embodiment, this embodiment further provides a tunnel surrounding rock grading device, and the tunnel surrounding rock grading device described below and the tunnel surrounding rock grading method described above can correspond to each other.

Fig. 4 is a block diagram of a tunnel surrounding rock classification device 800 according to an exemplary embodiment. As shown in Fig. 4, the tunnel surrounding rock classification device 800 may include: a processor 801, a memory 802. The tunnel surrounding rock classification device 800 may also include one or more of a multimedia component 803, an I/O interface 804, and a communication component 805.

The processor 801 is used to control the overall operation of the tunnel surrounding rock classification device 800 to complete all or part of the steps in the tunnel surrounding rock classification method described above. The memory 802 is used to store various types of data to support the operation of the tunnel surrounding rock classification device 800, and these data may include, for example, instructions for any application or method used to operate on the tunnel surrounding rock classification device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and/or input audio signals. For example, the audio component may include a microphone, which is used to receive external audio signals. The received audio signal may be further stored in the memory 802 or sent through the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the tunnel surrounding rock grading device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 may include: Wi-Fi module, Bluetooth module, NFC module.

In an exemplary embodiment, the tunnel surrounding rock grading device 800 can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned tunnel surrounding rock grading method.

In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the tunnel surrounding rock classification method described above are implemented. For example, the computer-readable storage medium may be the memory 802 including the program instructions, and the program instructions may be executed by the processor 801 of the tunnel surrounding rock classification device 800 to complete the tunnel surrounding rock classification method described above.

Embodiment 4:

Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the tunnel surrounding rock classification method described above can be referred to each other.

A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the tunnel surrounding rock classification method of the above method embodiment are implemented.

The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

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.

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 who is familiar with the technical field 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 (8)

1. A tunnel surrounding rock classification method, characterized by comprising: Obtain historical surrounding rock data of target surrounding rock within a historical time period; Initialize the position of the sparrow population based on chaotic mapping to obtain multiple initial position parameters; Building a model based on the initial position parameters to obtain an initial prediction model; The initial prediction model is trained based on the historical surrounding rock data and the Sparrow algorithm to obtain a target classification model; Inputting the real-time surrounding rock data of the target surrounding rock into the target classification model to obtain the real-time surrounding rock classification result of the target surrounding rock; The initial prediction model is trained based on the historical surrounding rock data and the sparrow algorithm to obtain a target classification model, including: Based on the initial position parameters of all sparrows, determining the initial fitness of all sparrows; Division operation: dividing all sparrows into discoverers, followers and guards based on the initial fitness; Update operation: Update the initial position parameters of all sparrows based on the preset target formula to obtain multiple updated position parameters; The first acquisition operation: obtaining the maximum mutation rate, the minimum mutation rate, the current number of iterations and the maximum number of iterations; A fifth calculation operation: calculating a difference between the maximum mutation rate and the minimum mutation rate as a first difference; Sixth calculation operation: calculating a ratio of the current number of iterations to the maximum number of iterations as a second ratio; A seventh calculation operation: calculating a difference between a third set threshold and the second ratio as a second difference; An eighth calculation operation: calculating the fourth power of the second difference and multiplying the fourth power by the first difference to obtain a target mutation rate; Determine operation: determine the target sparrow based on the target mutation rate, and update and replace the update position parameter based on a preset first formula to obtain the target position parameter; The second acquisition operation: acquiring the number of the alerters as the target number; When the target number is greater than a preset minimum number of alerters, updating the number of alerters based on a preset second formula, and repeating the division operation to the second acquisition operation; When the number of targets is not greater than the minimum value of the alerters, determining the target optimal sparrow based on the updated position parameter and the target position parameter, and determining the target optimal position parameter and target optimal fitness of the target optimal sparrow; Adjust the initial prediction model based on the historical surrounding rock data, the target optimal position parameters and the target optimal fitness to obtain the target classification model; Among them, the update operation: based on the preset target formula, the initial position parameters of all sparrows are updated to obtain multiple updated position parameters, including: Get the second iteration number; Based on all initial fitness, determine the best fitness and the worst fitness; Comparing the fitness of the sentinel with the optimal fitness to obtain a second comparison result; When the second comparison result satisfies a third setting condition, a step size control parameter is calculated based on the optimal fitness, the worst fitness, the initial position parameter and the second iteration number; Substituting the step length control parameter into a preset third target formula, and calculating the updated position parameter of the sentinel after the update; When the second comparison result satisfies a fourth set condition, obtaining a first random factor; Calculate and obtain initial parameters based on the optimal fitness, the worst fitness, the initial position parameter, the first random factor, and the second number of iterations; Substituting the initial parameters into the preset fourth target formula, and calculating the updated position parameters of the alerter after the update; Wherein, the fourth objective formula is: in, is the j-th position of sparrow i in the population after the T+1th iteration;/> is the j-th position of sparrow i in the population after the T-th iteration;/> is the position of the best sparrow in the population after the Tth iteration;/> is the position of the worst sparrow in the population after the Tth iteration; _fi is the individual fitness of sparrow i; _fw is the fitness of the worst sparrow in the current population; _fg is the fitness of the best sparrow in the current population; ε is the minimum constant to prevent the denominator from being zero; t is the current number of iterations; Si is the initialization parameter; rand is a uniformly distributed random factor; /> and B are step factors, and the value range of B is [0, 1]. 2. The tunnel surrounding rock classification method according to claim 1 is characterized in that the position of the sparrow population is initialized based on chaotic mapping to obtain multiple initial position parameters, including: Obtaining a random position parameter and a chaos control parameter of any sparrow, wherein the initial position is within a first setting range, and the chaos control parameter is within a second setting range; First calculation operation: calculating the product of the initial position and a first set threshold as a first product; A second calculation operation: calculating a sine function value of the first product as a first value; A third calculation operation: calculating a ratio of the chaos control parameter to a second set threshold as a first ratio; Fourth calculation operation: calculating the product of the first value and the first ratio as a second product; 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 a target position parameter; Calculate the target position parameters corresponding to all sparrows to obtain a plurality of initial position parameters of the sparrow population. 3. The tunnel surrounding rock classification method according to claim 1 is characterized in that the updating operation updates the initial position parameters of all sparrows based on a preset target formula to obtain multiple updated position parameters, including: Based on all initial fitness, determine the current warning value; Comparing the current warning value with a preset alert warning value to obtain a first comparison result; When the first comparison result satisfies the first set condition, obtaining the upper limit constraint of the finder, the lower limit constraint of the finder, the first optimal sparrow position parameter, the first worst sparrow position parameter, the constant factor and the first number of iterations; Calculate an adaptive weight based on the upper limit constraint, the lower limit constraint, the first optimal sparrow position parameter, the first worst sparrow position parameter, the constant factor and the first number of iterations; Substituting the adaptive weight into a preset first target formula, and calculating the updated position parameter after the discoverer updates; When the first comparison result satisfies a second set condition, the updated position parameter after being updated by the discoverer is calculated based on a preset second target formula. 4. A tunnel surrounding rock classification device, characterized by comprising: A first acquisition unit is used to acquire historical surrounding rock data of target surrounding rock in a historical time period; 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 construction unit, used to construct a model based on the initial position parameters to obtain an initial prediction model; A training unit, used for training the initial prediction model using the historical surrounding rock data and the Sparrow algorithm to obtain a target classification model; An input unit, used for inputting the real-time surrounding rock data of the target surrounding rock into the target classification model to obtain the real-time surrounding rock classification result of the target surrounding rock; Wherein, the training unit comprises: A first determining unit, configured to determine 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 discoverers, followers and guards based on the initial fitness; The first updating unit is used for updating operation: updating the initial position parameters of all sparrows based on a preset target formula to obtain a plurality of updated position parameters; A third acquisition unit, used for the first acquisition operation: acquiring the maximum mutation rate, the minimum mutation rate, the current number of iterations and the maximum number of iterations; A sixth calculation unit, configured for a fifth calculation operation: calculating a difference between the maximum mutation rate and the minimum mutation rate as a first difference; a seventh calculation unit, configured for a sixth calculation operation: calculating a ratio of the current number of iterations to the maximum number of iterations as a second ratio; an eighth calculation unit, configured for a seventh calculation operation: calculating a difference between a third set threshold and the second ratio as a second difference; A ninth calculation unit, configured to perform an eighth calculation operation: calculating the fourth power of the second difference and multiplying the fourth power of the second difference by the first difference to obtain a target mutation rate; A second determination unit is used for determining an operation: determining a target sparrow based on the target mutation rate, and updating and replacing the update position parameter based on a preset first formula to obtain a target position parameter; A fourth acquisition unit is used for a second acquisition operation: acquiring the number of the alerters as a target number; A second updating unit, configured to update the number of alerters based on a preset second formula when the target number is greater than a preset minimum number of alerters, and repeat the division operation to the second acquisition operation; A third updating unit is used for determining a target optimal sparrow based on the update position parameter and the target position parameter when the target number is not greater than the minimum value of the alerter, and determining a target optimal position parameter and a target optimal fitness of the target optimal sparrow; An adjustment unit, configured to adjust the initial prediction model based on the historical surrounding rock data, the target optimal position parameter and the target optimal fitness to obtain the target classification model; Wherein, the first updating unit includes: A sixth obtaining unit, used to obtain a second iteration number; A fourth determining unit, used for determining the best fitness and the worst fitness based on all the initial fitnesses; A second comparison unit, used for comparing the fitness of the alerter with the optimal fitness to obtain a second comparison result; a twelfth calculation unit, configured to calculate a step size control parameter based on the optimal fitness, the worst fitness, the initial position parameter and the second number of iterations when the second comparison result satisfies a third set condition; A second input unit is used to input the step length control parameter into a preset third target formula to calculate the updated position parameter of the sentinel after the update; a seventh acquisition unit, configured to acquire a first random factor when the second comparison result satisfies a fourth setting condition; A thirteenth calculation unit, configured to calculate an initial parameter based on the optimal fitness, the worst fitness, the initial position parameter, the first random factor, and the second number of iterations; A third input unit is used to input the initial parameters into a preset fourth target formula to calculate and obtain the updated position parameters of the alerter after the update; Wherein, the fourth objective formula is: in, is the j-th position of sparrow i in the population after the T+1th iteration;/> is the j-th position of sparrow i in the population after the T-th iteration;/> is the position of the best sparrow in the population after the Tth iteration;/> is the position of the worst sparrow in the population after the Tth iteration; _fi is the individual fitness of sparrow i; _fw is the fitness of the worst sparrow in the current population; _fg is the fitness of the best sparrow in the current population; ε is the minimum constant to prevent the denominator from being zero; t is the current number of iterations; Si is the initialization parameter; rand is a uniformly distributed random factor; /> and B are step factors, and the value range of B is [0, 1]. 5. The tunnel surrounding rock classification device according to claim 4, characterized in that the initialization unit comprises: A second acquisition unit is used to acquire a random position parameter and a chaos control parameter of any sparrow, wherein the initial position is within a first setting range, and the chaos control parameter is within a second setting range; A first calculation unit, configured for a first calculation operation: calculating a product of the initial position and a first set threshold as a first product; The second computing unit is used for A second calculation operation: calculating a sine function value of the first product as a first value; A third calculation unit is used for a third calculation operation: calculating a ratio of the chaos control parameter to a second set threshold as a first ratio; a fourth calculation unit, configured for a fourth calculation operation: calculating a product of the first value and the first ratio as a second product; a repeating unit, configured 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 a target position parameter; The fifth calculation unit is used to calculate the target position parameters corresponding to all sparrows to obtain a plurality of initial position parameters of the sparrow population. 6. The tunnel surrounding rock grading device according to claim 4, characterized in that the first updating unit comprises: A third determining unit, configured to determine a current warning value based on all initial fitness levels; A first comparison unit, used for comparing the current warning value with a preset alert warning value to obtain a first comparison result; a fifth acquisition unit, configured to acquire, when the first comparison result satisfies a first set condition, an upper limit constraint of the finder, a lower limit constraint of the finder, a first optimal sparrow position parameter, a first worst sparrow position parameter, a constant factor, and a first number of iterations; a tenth calculation unit, configured to calculate an adaptive weight based on the upper limit constraint, the lower limit constraint, the first optimal sparrow position parameter, the first worst sparrow position parameter, the constant factor, and the first number of iterations; A first input unit, used for inputting the adaptive weight into a preset first target formula to calculate and obtain the updated position parameter after the discoverer updates; An eleventh calculation unit is used to calculate the updated position parameter after the finder updates based on a preset second target formula when the first comparison result satisfies a second set condition. 7. A tunnel surrounding rock classification device, characterized by comprising: Memory for storing computer programs; A processor is used to implement the steps of the tunnel surrounding rock classification method as claimed in any one of claims 1 to 3 when executing the computer program. 8. A readable storage medium, characterized in that a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the steps of the tunnel surrounding rock classification method according to any one of claims 1 to 3 are implemented.