Tunnel anchor safety performance evaluation method and system based on cloud computing and storage medium

Abstract

The invention discloses a tunnel anchor safety performance evaluation method and system based on cloud computing and a storage medium. The method comprises the steps that the conduction force of a suspension bridge main cable corresponding to a tunnel anchor is analyzed; rock mass characteristic parameters of an anchor location area corresponding to the tunnel anchor are obtained, and anchor location risk parameters corresponding to the tunnel anchor are analyzed based on the rock mass characteristic parameters; obtaining anchor plug body parameters of the tunnel anchor, and analyzing the uplift bearing capacity of the tunnel anchor based on the anchor plug body parameters; and performing evaluation processing on the conduction force, the uplift bearing capacity and the anchor address risk parameters based on a central node in cloud computing to generate a safety evaluation coefficient, and evaluating the safety performance of the tunnel anchor according to the safety evaluation coefficient. According to the method, the safety performance of the tunnel anchor is evaluated, all factors influencing the safety performance of the tunnel anchor are fully considered, and the evaluation accuracy is improved; and meanwhile, distributed processing is carried out through cloud computing, so that the analysis efficiency is improved, and the safety performance of the tunnel anchor is quickly and accurately evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of suspension bridges, and in particular to a cloud computing-based tunnel anchor safety performance evaluation method, system and storage medium. Background Art

[0002] Suspension bridges are one of the most commonly used bridge types in bridge engineering. The main components include main beams, suspenders, main cables, main towers and anchors. Among them, the main beam is the main load-bearing component of the bridge deck, and most of them are made of steel structures; the suspenders are the force-transmitting components that suspend the main beam on the main cables. The main cables are the main load-bearing components of the entire bridge, which determine the load and span capacity of the suspension bridge. The main towers are the main load-bearing components of the vertical load of the entire bridge. Anchors are key components that anchor the main cables at both ends, and can firmly anchor the weight carried by the main cables to ensure that they are not pulled up or moved.

[0003] Generally speaking, the anchoring forms of the main cable of a suspension bridge can be mainly divided into self-anchoring and ground-anchoring. The self-anchoring type is to anchor the main cable directly on the stiffening beam. The ground-anchoring type is further divided into gravity anchoring and tunnel anchoring. Gravity anchoring mainly forms an anchor by excavating a foundation pit and pouring a large volume of concrete, relying on its own gravity to resist the tension of the main cable. Tunnel anchoring mainly forms an anchor plug by excavating a tunnel in the rock mass, pouring concrete in the tunnel and working together with the surrounding rock to withstand the tension of the main cable.

[0004] Compared with gravity anchors, the volume of tunnel anchors is only 20% to 25% of that of gravity anchors, and has less impact on the surrounding environment, and its application is gradually increasing. In the process of designing tunnel anchors to anchor suspension bridges, the safe and stable anchoring of the main cable is a crucial issue for the normal operation of suspension bridges, and the safety performance of tunnel anchors needs to be fully evaluated. However, the current safety performance evaluation of tunnel anchors is relatively inaccurate, and it is difficult to quickly evaluate due to the large number of related parameters involved. In order to avoid the occurrence of risks, higher parameters are set for evaluation. Although the safety of the evaluation is higher, it also brings about the problem of over-design, such as the designed anchor plug is too large or too long. Therefore, how to quickly and accurately evaluate the safety performance of tunnel anchors is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The main purpose of the present invention is to provide a cloud computing-based tunnel anchor safety performance evaluation method, system and storage medium, aiming to solve the technical problem of how to quickly and accurately evaluate the safety performance of tunnel anchors.

[0006] To achieve the above object, the present invention provides a tunnel anchor security performance evaluation method based on cloud computing, wherein the tunnel anchor security performance evaluation includes:

[0007] Based on the first cloud node in the cloud computing, analyzing the conductive force of the main cable of the suspension bridge corresponding to the tunnel anchor;

[0008] Acquiring rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters;

[0009] Acquiring anchor plug body parameters of the tunnel anchor based on the third cloud node in the cloud computing, and analyzing the pull-out bearing capacity of the tunnel anchor based on the anchor plug body parameters;

[0010] Based on the central node in the cloud computing, the conductivity, pull-out bearing capacity and anchor site risk parameters are evaluated and processed to generate a safety assessment coefficient, and the safety performance of the tunnel anchor is evaluated based on the safety assessment coefficient.

[0011] Preferably, the step of analyzing the conductive force of the main cable of the suspension bridge corresponding to the tunnel anchor based on the first cloud node in the cloud computing includes:

[0012] Reading the bridge body conduction force corresponding to the main cable of the suspension bridge based on the first cloud node, and obtaining historical climate data of the environment in which the main cable of the suspension bridge is located;

[0013] According to the change trend of wind data in the historical climate data, the maximum wind force and wind direction within a preset period are predicted, and the wind force consistent with the direction of the main cable of the suspension bridge is calculated according to the maximum wind force and wind direction. The calculation formula is:

[0014]

[0015] Among them, Fa is the wind force, Fmax is the maximum wind force, θ is the angle between the wind direction and the main cable direction of the suspension bridge, K1 is the wind force level coefficient, k(θ) is the variable wind direction coefficient, It is used to calculate the bending vibration frequency of the main cable of the suspension bridge. L is the height of the main cable of the suspension bridge, E is the elastic modulus of the main cable of the suspension bridge, I is the section polar inertia moment of the main cable of the suspension bridge, and A is the cross-sectional area of ​​the main cable of the suspension bridge. is the annual coefficient corresponding to the maximum wind force;

[0016] The conductive force of the bridge body is corrected according to the wind force to obtain the conductive force.

[0017] Preferably, the step of acquiring the rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing the anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters includes:

[0018] Determine an extended area corresponding to the anchor site area based on the second cloud node, and obtain rock mass characteristic parameters corresponding to the extended area, wherein the rock mass characteristic parameters include rock mass type, rock mass morphology, a first proportion corresponding to each of the rock mass types, and a second proportion corresponding to each of the rock mass morphologies;

[0019] The first proportions and the second proportions are transmitted to a preset model for calculation and processing to obtain the minimum fracture force of the rock mass in the extended area. The calculation formula is:

[0020]

[0021] Wherein, W is the minimum breaking force, Ei is the connection weight from the i-th hidden layer of the preset model to the output layer, x1, x2, x3... are the first proportions, y1, y2, y3... are the second proportions, f is the input function, and bi is the output of the i-th hidden layer of the preset model;

[0022] Obtaining historical geological disaster data of the anchor site area, and predicting the probability of geological disasters occurring in the anchor site area within a preset time period and the type of geological disasters occurring based on the displayed historical geological disaster data;

[0023] According to the probability and type, a maximum probability within a preset time period is generated, and the maximum probability and the minimum rupture force are generated as anchor site risk parameters.

[0024] Preferably, the anchor plug body parameters include the front end face area, rear end face area, axial length, anchor plug body inclination angle, concrete coefficient, anchor plug body positioning coefficient, anchor plug body contact area, and anchor plug body wedge angle of the anchor plug body corresponding to the tunnel anchor;

[0025] The step of analyzing the pull-out bearing capacity of the tunnel anchor based on the anchor plug body parameters comprises:

[0026] Calculating the volume of the anchor plug body according to the front end surface area, the rear end surface area and the axial length; and determining the gravity of the anchor plug body according to the volume;

[0027] According to the inclination angle of the anchor plug body and the wedge angle of the anchor plug body, the gravity is divided into a first gravity component along the main cable direction of the suspension bridge and a second gravity component perpendicular to the outer surface of the anchor plug body;

[0028] Obtaining a friction coefficient corresponding to the anchor plug body, and generating rock resistance according to the second gravity component and the friction coefficient; dividing the rock resistance into a first rock resistance along the main cable direction of the suspension bridge and a second rock resistance perpendicular to the main cable direction of the suspension bridge according to the anchor plug body inclination angle and the anchor plug body wedge angle;

[0029] Obtaining a gravity component coefficient corresponding to the first gravity component and a resistance component coefficient corresponding to the rock mass resistance;

[0030] The pull-out bearing capacity is calculated according to the first gravity component, the first rock mass resistance, the second rock mass resistance, the gravity component coefficient, the resistance component coefficient, the concrete coefficient, the anchor body positioning coefficient and the anchor body contact area. The calculation formula is:

[0031]

[0032] Among them, F b is the pull-out bearing capacity, t1 is the concrete coefficient, t2 is the anchor plug positioning coefficient, W g is the first gravity component, r g is the gravity component coefficient, B z1 is the first rock mass resistance, B z2 is the second rock mass resistance, A is the contact area of ​​the anchor plug, r z is the resistance component coefficient.

[0033] Preferably, the step of evaluating and processing the conductivity, pull-out bearing capacity and anchor risk parameters based on the central node in the cloud computing to generate a safety assessment coefficient comprises:

[0034] Performing difference calculation on the conductive force and the pull-out bearing capacity based on the central node to obtain a calculation result, and determining a safety factor to be evaluated corresponding to the calculation result according to a correspondence between a preset difference interval and a safety factor;

[0035] The safety factor to be evaluated is evaluated according to the anchor site risk parameter to generate the safety evaluation factor.

[0036] Preferably, the step of evaluating the safety performance of the tunnel anchor according to the safety evaluation coefficient comprises:

[0037] According to the safety assessment coefficient, evaluating whether the safety performance of the tunnel anchor meets the preset conditions;

[0038] If the preset conditions are met, the safety performance evaluation of the tunnel anchor is completed;

[0039] If the preset conditions are not met, a prompt message for adjusting the anchor plug body parameters of the tunnel anchor is output, so that the safety performance of the tunnel anchor can be re-evaluated after the adjustment is completed.

[0040] Preferably, the step of acquiring the rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing the anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters comprises:

[0041] Acquire multiple sample data, and divide the multiple sample data into training samples and test samples, wherein the sample data is a mapping relationship between the proportion of rock mass types and the proportion of rock mass morphology and fracture force;

[0042] Training a preset initial model based on the training sample, and when the training reaches a first preset end condition, testing the preset initial model a preset number of times based on the test sample to obtain a preset number of test results;

[0043] According to the test results of the preset number of times, the loss function value of the preset initial model is calculated, and based on the loss function value, the preset initial model is generated as a preset model, and the calculation formula of the loss function value is:

[0044]

[0045] Among them, Loss is the loss function value, α is the weight factor of the preset initial model, pj is the test result generated by the j-th test sample, and qj is the minimum fracture force corresponding to the j-th test sample.

[0046] Preferably, the step of generating the preset initial model as a preset model based on the loss function value comprises:

[0047] Determine whether the loss function value satisfies a second preset end condition, and if so, terminate the training of the preset initial model and generate the preset initial model as a preset model;

[0048] If the loss function value does not meet the second preset end condition, the model weight of the preset initial model is adjusted, and the adjustment formula is:

[0049]

[0050] Where ΔA m is the model weight adjustment value of the mth intermediate layer of the preset initial model, It is used to calculate the error value of the test result of the middle layer of the mth layer of the preset initial model, where n represents the preset number of times, and S nm is the actual output value of the nth test result in the mth layer of the preset initial model, t nm is the nth theoretical test result in the mth layer of the preset initial model, w m is the connection weight of the mth layer of the preset initial model, E m is the input data of the mth layer of the preset initial model.

[0051] The step of training the preset initial model based on the training sample is performed based on the adjusted model parameters until the loss function value meets the second preset end condition, thereby generating the preset model.

[0052] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a cloud computing-based tunnel anchor safety performance evaluation system, the cloud computing-based tunnel anchor safety performance evaluation system comprising: a memory, a processor, a communication bus, and a control program stored in the memory:

[0053] The communication bus is used to realize the connection and communication between the processor and the memory;

[0054] The processor is used to execute the control program to implement the steps of the cloud computing-based tunnel anchor security performance evaluation method as described above.

[0055] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a storage medium, on which a control program is stored, and when the control program is executed by a processor, the steps of the tunnel anchor security performance evaluation method based on cloud computing as described above are implemented.

[0056] The present invention provides a tunnel anchor safety performance evaluation method, system and storage medium based on cloud computing. The cloud computing includes a first cloud node, a second cloud node, a third cloud node and a central node. The first cloud node is used to analyze the conductive force of the main cable of the suspension bridge corresponding to the tunnel anchor; the second cloud node is used to obtain the rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor, and the anchor site risk parameters corresponding to the tunnel anchor are analyzed based on the rock mass characteristic parameters; and the third cloud node is used to obtain the anchor plug body parameters of the tunnel anchor, and the pull-out bearing capacity of the tunnel anchor is analyzed based on the anchor plug body parameters; and then the conductive force, pull-out bearing capacity and anchor site risk parameters are evaluated and processed through the central node to generate a safety evaluation coefficient, and the safety performance of the tunnel anchor is evaluated according to the safety evaluation coefficient. In this way, by analyzing the conductive force of the main cable of the suspension bridge, the pull-out bearing capacity of the tunnel anchor itself, and the anchor site risk parameters of the anchor site where the tunnel anchor is located that may affect the safety performance of the tunnel anchor, and combining the three to evaluate the safety performance of the tunnel anchor, various factors affecting the safety performance of the tunnel anchor are fully considered, and the evaluation accuracy is improved. At the same time, by dividing cloud computing into the first node, the second node, the third node and the central node for distributed processing, the conductivity, anchor site risk parameters and pull-out bearing capacity can be analyzed simultaneously, which improves the efficiency of the analysis and realizes the rapid and accurate evaluation of the safety performance of the tunnel anchor. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of a first embodiment of a tunnel anchor safety performance evaluation method based on cloud computing of the present invention;

[0058] Figure 2 It is a flow chart of a second embodiment of a tunnel anchor safety performance assessment method based on cloud computing of the present invention;

[0059] Figure 3 It is a flow chart of a third embodiment of a tunnel anchor safety performance assessment method based on cloud computing of the present invention;

[0060] Figure 4 It is a structural schematic diagram of the hardware operating environment involved in an embodiment of a tunnel anchor safety performance evaluation system based on cloud computing of the present invention.

[0061] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0062] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0063] The present invention provides a tunnel anchor safety performance evaluation method based on cloud computing, please refer to Figure 1 , Figure 1 It is a flowchart of the first embodiment of the tunnel anchor security performance assessment method based on cloud computing of the present invention.

[0064] The embodiment of the present invention provides an embodiment of a tunnel anchor security performance evaluation method based on cloud computing. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that here. Specifically, the tunnel anchor security performance evaluation in this embodiment includes:

[0065] Step S10: analyzing the conductive force of the main cable of the suspension bridge corresponding to the tunnel anchor based on the first cloud node in the cloud computing.

[0066] The cloud computing of this embodiment is a distributed system at least divided into a first node, a second node, a third node and a central node, and the first node, the second node and the third node are respectively configured to communicate with the central node. At the same time, a control center is additionally provided, through which the first node, the second node, the third node and the central node are respectively controlled. The cloud computing-based tunnel anchor security performance evaluation method of this embodiment is applied to the control center.

[0067] Understandably, the tunnel anchor is used to anchor the suspension bridge and bear the tension of the main cable of the suspension bridge. The tension mainly includes the force transmitted by the weight of the main beam, the weight of the main cable, the weight of the vehicle traveling on the main beam, and the weight of the auxiliary facilities such as the sling, the main cable protection facilities, the bridge deck pavement, and the guardrail. Usually, when designing a suspension bridge, the bridge deck width and load capacity are designed according to the traffic flow, and then the weight of the bridge deck, the main cable weight, and the weight of the related auxiliary facilities are determined. The tension of the main cable of the suspension bridge that the tunnel anchor has to bear can be determined by this type of weight. In this embodiment, the first cloud node is used to obtain this type of data for analysis, and the corresponding tension of the main cable of the suspension bridge is obtained as the conductive force of the main cable of the suspension bridge corresponding to the tunnel anchor. It should be noted that if any of the data is modified during the design of the suspension bridge, the corresponding first node can obtain and analyze the modified updated data to generate a new conductive force.

[0068] Furthermore, considering that the suspension bridge will inevitably encounter strong winds during use, the strong winds will have an impact on the suspension bridge, thereby increasing the force transmitted to the tunnel anchor through the main cable of the suspension bridge. Therefore, in order to ensure the accuracy of the safety performance evaluation of the tunnel anchor, it is necessary to correct the tension of the main cable of the suspension bridge based on the wind force to obtain accurate conduction force. Specifically, the step of analyzing the conduction force of the main cable of the suspension bridge corresponding to the tunnel anchor based on the first cloud node in the cloud computing includes:

[0069] Step S11, reading the bridge body conduction force corresponding to the main cable of the suspension bridge based on the first cloud node, and obtaining the historical climate data of the environment in which the main cable of the suspension bridge is located;

[0070] Step S12, predicting the maximum wind force and wind direction within a preset period of time according to the change trend of the wind force data in the historical climate data, and calculating the wind force consistent with the direction of the main cable of the suspension bridge according to the maximum wind force and wind direction;

[0071] Step S13, correcting the bridge body conductive force according to the wind force to obtain the conductive force.

[0072] Furthermore, the first cloud node converts the various weights transmitted by the main cable of the suspension bridge into the bridge body conduction force corresponding to the main cable of the suspension bridge for reading, and obtains the historical climate data of the environment where the main cable of the suspension bridge is located. The historical years of the historical climate data can be set as required, such as historical climate data of the past 5 years, 10 years, 20 years, 50 years, etc.

[0073] Furthermore, wind data is selected from the historical climate data, and the change trend of each wind data is determined according to the formation period of each wind data. The change trend of the wind data can be formed according to a continuous period, for example, a change trend of wind data for 12 consecutive months, or it can be formed according to the same period, for example, a change trend of wind data in March within 10 years, or both can be formed at the same time. Then, based on the change trend of the wind data, the maximum wind force and wind direction within a preset time period are predicted. Among them, the preset time period is a time period pre-set according to the service life of the suspension bridge, such as 80 years, 100 years, etc.

[0074] It is understandable that the wind direction is usually inconsistent with the direction of the main cable of the suspension bridge. Therefore, after the maximum wind force and wind direction are predicted, the wind force along the main cable direction of the suspension bridge can be calculated based on the two. The wind force is usually superimposed on the main cable of the suspension bridge and transmitted to the tunnel anchor. The specific calculation formula is shown in the following formula (1).

[0075]

[0076] Among them, Fa is the wind force, Fmax is the maximum wind force, θ is the angle between the wind direction and the main cable direction of the suspension bridge, K1 is the wind force level coefficient, k(θ) is the variable wind direction coefficient,

[0077] It is used to calculate the bending vibration frequency of the main cable of the suspension bridge. L is the height of the main cable of the suspension bridge, E is the elastic modulus of the main cable of the suspension bridge, I is the section polar inertia moment of the main cable of the suspension bridge, and A is the cross-sectional area of ​​the main cable of the suspension bridge. is the annual coefficient corresponding to the maximum wind force.

[0078] Different wind speed intervals are preset to correspond to different wind speed level coefficients, and the greater the wind speed in the wind speed interval, the greater the corresponding wind speed level coefficient. The determined maximum wind speed is compared with each wind speed interval, the target wind speed interval where the maximum wind speed is located is determined, and the wind speed level coefficient corresponding to the target wind speed interval is found as k1. At the same time, k(θ) is a coefficient pre-set for the possibility of wind direction change of the predicted maximum wind speed, is the fatigue coefficient pre-set for the service life of the suspension bridge. The value in the above formula (1) is the fatigue coefficient of the predicted maximum wind force year.

[0079] Furthermore, after the wind force is calculated by formula (1), the wind force is added to the bridge body conduction force to achieve the correction of the bridge body conduction force by the wind force, and obtain the accurate conduction force transmitted from the main cable of the suspension bridge to the tunnel anchor.

[0080] Step S20, obtaining rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing the anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters.

[0081] Understandably, the area where the tunnel anchor is set is the anchor area. Different anchor areas have different types and forms of rock masses, and the proportion of each rock mass is also different, resulting in different characteristics of different anchor areas, and different risks to the tunnel anchor. For example, a certain anchor area mainly includes sandstone, conglomerate, limestone, etc., and another anchor area mainly includes mudstone, clay rock, shale, slate and other mudstones. After the anchor area is selected, the rock mass type of the anchor area, the proportion of each type of rock mass, and various parameters such as the block structure, layered structure, fragmented structure, and dispersed structure formed by each type of rock mass are determined through geological exploration and other methods. This type of parameter is obtained through the second node in the cloud computing as the rock mass characteristic parameter of the anchor area corresponding to the tunnel anchor, and the rock mass characteristic parameter is analyzed to obtain the anchor risk parameter corresponding to the tunnel anchor, so as to reflect the risk posed by the rock mass structure of the anchor area to the tunnel anchor through the anchor risk parameter. Specifically, the step of acquiring the rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing the anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters includes:

[0082] Step S21, determining an extended area corresponding to the anchor site area based on the second cloud node, and obtaining rock mass characteristic parameters corresponding to the extended area, wherein the rock mass characteristic parameters include rock mass type, rock mass morphology, a first proportion corresponding to each of the rock mass types, and a second proportion corresponding to each of the rock mass morphologies;

[0083] Step S22, transmitting each of the first proportions and each of the second proportions to a preset model for calculation and processing, so as to obtain a minimum fracture force of the rock mass in the expansion area;

[0084] Step S23, obtaining historical geological disaster data of the anchor site area, and predicting the probability of geological disasters occurring in the anchor site area within a preset time period and the type of geological disasters occurring according to the historical geological disaster data;

[0085] Step S24: generating a maximum probability within a preset time period according to the probability and type, and generating the maximum probability and the minimum fracture force as anchor risk parameters.

[0086] Furthermore, although the tunnel anchor bears the tension of the main cable of the suspension bridge through the anchor plug and the surrounding rock mass, the surrounding rock mass used to bear the tension of the main cable of the suspension bridge will not expand infinitely. For example, for a certain tunnel anchor, the surrounding rock mass 5m away from the anchor plug can bear the tension of the main cable of the suspension bridge together with the anchor plug, but the surrounding rock mass 10m away cannot bear the tension of the main cable of the suspension bridge together with the anchor plug. Moreover, after the design of the suspension bridge is determined, the tension of the main cable of the suspension bridge is also determined accordingly. In order to bear the tension, the size parameters of the anchor plug in the tunnel anchor are also determined accordingly. The size area of ​​the surrounding rock mass that bears the tension of the main cable of the suspension bridge corresponding to anchor plugs of different sizes is different. A preset expansion ratio is set in advance between the size of the anchor plug and the size of the surrounding rock mass. For the anchor plug with determined size parameters, the second cloud node determines the expansion area corresponding to the anchor site area according to the preset expansion ratio.

[0087] Furthermore, the various rock mass types and their respective first proportions, as well as the various rock mass morphologies and their respective second proportions in the extended area are analyzed based on the geological exploration data. In addition, a preset model is pre-trained, and the first proportions and the second proportions obtained by the analysis are transmitted to the preset model for calculation and processing to obtain the minimum fracture force of the rock mass in the extended area. The minimum fracture force reflects the force corresponding to the most fracture-prone rock mass in the extended area. As long as the bearing force is greater than the fracture force, the most fracture-prone rock mass will fracture. The calculation formula of the minimum fracture force is specifically shown in the following formula (2).

[0088]

[0089] Among them, W is the minimum breaking force, Wi is the connection weight from the i-th hidden layer of the preset model to the output layer, x1, x2, x3... are the first proportions, y1, y2, y3... are the second proportions, f is the input function, and bi is the i-th hidden layer output of the preset model.

[0090] Understandably, geological disasters such as earthquakes will have an impact on the rock mass around the tunnel anchor, for example, the rock mass morphology may change. Therefore, in order to reflect whether the rock mass in the expansion area will encounter an earthquake, this embodiment also obtains historical geological disaster data of the anchor area, which, in addition to earthquake data, may also include debris flow data, landslide data, etc. The regularity of the historical geological disaster data is analyzed, and through the regularity of the analysis, the probability and type of geological disasters occurring in the anchor area within a preset time period are predicted. Among them, because the expansion area is adjacent to the anchor area, the predicted probability and type are actually the probability and type of geological disasters occurring in the expansion area.

[0091] Furthermore, different geological disasters have different degrees of damage to rock masses. Among earthquakes, debris flows and landslides, earthquakes are the most destructive. Therefore, for the predicted probability and type, it is also necessary to combine the two to generate the maximum probability within a preset time period. Different correction coefficients are set in advance for different types of geological disasters. The correction coefficient corresponding to earthquakes is the largest. The predicted probability is corrected by different correction coefficients to form a final probability, and then the final probabilities of various types of geological disasters are compared to determine the maximum probability. The maximum probability represents the possibility of the occurrence of the most harmful geological disaster. Thereafter, the generated minimum fracture force and maximum probability are jointly formed into an anchor site risk parameter, which is used to reflect the force of fracture of the rock mass around the anchor plug and the risk of geological disasters.

[0092] Step S30: acquiring the anchor plug body parameters of the tunnel anchor based on the third cloud node in the cloud computing, and analyzing the pull-out bearing capacity of the tunnel anchor based on the anchor plug body parameters.

[0093] Furthermore, the bearing capacity of the tunnel anchor includes both the bearing capacity of its anchor body and the bearing capacity of the surrounding rock mass. The bearing capacity of the anchor body is mainly related to the size, length, wedge angle, etc. of the anchor body. The bearing capacity of the surrounding rock mass is related to the type, shape, and contact condition of the surrounding rock mass with the anchor body. This embodiment obtains such parameters as anchor body parameters through the third cloud node in cloud computing for analysis, obtains the bearing capacity of the tunnel anchor and its surrounding rock mass for bearing the tension of the main cable of the suspension bridge, and uses such bearing capacity as the pull-out bearing capacity.

[0094] Step S40, based on the central node in the cloud computing, the conductivity, pull-out bearing capacity and anchor site risk parameters are evaluated and processed to generate a safety assessment coefficient, and the safety performance of the tunnel anchor is evaluated according to the safety assessment coefficient.

[0095] Further, after obtaining the conductive force, anchor risk parameter and pull-out bearing capacity through the first cloud node, the second cloud node and the third cloud node respectively, the first cloud node, the second cloud node and the third cloud node are controlled to transmit the conductive force, anchor risk parameter and pull-out bearing capacity generated by each of them to the central node in the cloud computing, and the central node performs evaluation and processing to generate a safety assessment coefficient. Specifically, the step of evaluating and processing the conductive force, pull-out bearing capacity and anchor risk parameter based on the central node in the cloud computing to generate a safety assessment coefficient includes:

[0096] Step S41, performing a difference operation on the conductive force and the pull-out bearing capacity based on the central node to obtain a calculation result, and determining a safety factor to be evaluated corresponding to the calculation result according to a correspondence between a preset difference interval and a safety factor;

[0097] Step S42: evaluating the safety factor to be evaluated according to the anchor site risk parameter to generate the safety evaluation factor.

[0098] Furthermore, the conductive force is the maximum force transmitted to the tunnel anchor by the main cable of the suspension bridge, and the pull-out bearing capacity is the bearing capacity provided by the anchor plug and the surrounding rock mass. The size relationship between the two reflects whether the tunnel anchor is sufficient to withstand the tension transmitted by the main cable of the suspension bridge. Therefore, a difference operation is performed between the two to obtain a difference result. In addition, a correspondence between multiple difference intervals and safety factors is pre-set, wherein the greater the difference of the difference interval, the greater the value of the safety factor, indicating that the safety of the tunnel anchor is better. The difference operation can be set as an operation of subtracting the conductive force from the pull-out bearing capacity. If the obtained operation result is a negative value, it means that the tunnel anchor is insufficient to bear the tension transmitted by the main cable of the suspension bridge, and the safety factor is directly set to a negative value, and an alarm is issued. If the obtained operation result is a positive value, the operation result is compared with each difference interval to determine the target difference interval where the operation result is located, and then the safety factor corresponding to the target difference interval is found as the safety factor to be evaluated corresponding to the operation result.

[0099] Understandably, although the calculation result is a positive value, indicating that the tunnel anchor is sufficient to bear the tension transmitted by the main cable of the suspension bridge, risks may still occur due to the influence of external factors, especially when the pull-out bearing capacity is not much greater than the conductive force. In order to further ensure safety, this embodiment also evaluates the safety factor to be evaluated through the anchor site risk parameter to form a final safety assessment factor. Among them, the anchor site risk parameter includes at least the minimum fracture force indicating that the surrounding rock area is most likely to fracture and the maximum probability indicating the possibility of the most serious geological disaster. Once the most serious geological disaster occurs, the minimum fracture force will be further reduced, and the pull-out bearing capacity may be less than the conductive force.

[0100] Furthermore, a correction coefficient corresponding to the minimum fracture force and the maximum probability is pre-set, wherein the larger the value of the maximum probability, the smaller the value of the minimum fracture force, the higher the possibility of the minimum fracture force decreasing, and therefore the smaller the correction coefficient is set; conversely, the smaller the value of the maximum probability, the larger the value of the minimum fracture force, the lower the possibility of the minimum fracture force decreasing, and therefore the larger the correction coefficient is set, and the correction coefficients for other situations are between the two. The correction coefficient corresponding to the anchor risk parameter generated by the second cloud node is determined, and the safety factor to be assessed is corrected by the correction coefficient to form a final more accurate safety assessment coefficient.

[0101] Furthermore, after the final safety assessment coefficient is formed, the safety performance of the tunnel anchor can be evaluated based on it. Specifically, the step of evaluating the safety performance of the tunnel anchor based on the safety assessment coefficient includes:

[0102] Step S43, evaluating whether the safety performance of the tunnel anchor meets a preset condition according to the safety evaluation coefficient;

[0103] Step S44, if the preset conditions are met, completing the safety performance evaluation of the tunnel anchor;

[0104] Step S45: if the preset conditions are not met, a prompt message for adjusting the anchor plug body parameters of the tunnel anchor is output, so that after the adjustment is completed, the safety performance of the tunnel anchor is re-evaluated.

[0105] Furthermore, a preset condition indicating that the tunnel anchor has good safety performance is pre-set, and the preset condition may be a safety reference factor. The generated safety assessment factor is compared with the safety reference factor to evaluate whether the safety performance of the tunnel anchor meets the preset condition. If it is determined through comparison that the safety assessment factor is greater than the safety reference factor, it means that the safety performance of the tunnel anchor meets the preset condition, and construction can be carried out according to the currently designed tunnel anchor, thereby completing the safety performance evaluation of the tunnel anchor. On the contrary, if it is determined through comparison that the safety assessment factor is less than or equal to the safety reference factor, it means that there may be risks in the tunnel anchor, and it is determined that the safety performance of the tunnel anchor does not meet the preset condition. At this time, a prompt message for adjusting the anchor plug body parameters of the tunnel anchor is output to prompt the adjustment of parameters such as the size and length of the tunnel anchor. After the adjustment is completed, the safety performance evaluation request can be triggered again to re-evaluate the safety performance of the tunnel anchor based on the anchor plug body parameters after the adjustment, so as to ensure the safety performance of the tunnel anchor.

[0106] The cloud computing-based tunnel anchor safety performance evaluation method implemented in this embodiment includes a first cloud node, a second cloud node, a third cloud node and a central node. The first cloud node is used to analyze the conduction force of the main cable of the suspension bridge corresponding to the tunnel anchor; the second cloud node is used to obtain the rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor, and the anchor site risk parameters corresponding to the tunnel anchor are analyzed based on the rock mass characteristic parameters; and the third cloud node is used to obtain the anchor plug body parameters of the tunnel anchor, and the pull-out bearing capacity of the tunnel anchor is analyzed based on the anchor plug body parameters; and then the conduction force, pull-out bearing capacity and anchor site risk parameters are evaluated and processed through the central node to generate a safety evaluation coefficient, and the safety performance of the tunnel anchor is evaluated according to the safety evaluation coefficient. In this way, by analyzing the conduction force of the main cable of the suspension bridge, the pull-out bearing capacity of the tunnel anchor itself, and the anchor site risk parameters of the anchor site where the tunnel anchor is located that may affect the safety performance of the tunnel anchor, and combining the three to evaluate the safety performance of the tunnel anchor, various factors affecting the safety performance of the tunnel anchor are fully considered, and the evaluation accuracy is improved. At the same time, by dividing cloud computing into the first node, the second node, the third node and the central node for distributed processing, the conductivity, anchor site risk parameters and pull-out bearing capacity can be analyzed simultaneously, which improves the efficiency of the analysis and realizes the rapid and accurate evaluation of the safety performance of the tunnel anchor.

[0107] For further information, please refer to Figure 2 Based on the first embodiment of the tunnel anchor security performance evaluation method based on cloud computing of the present invention, a second embodiment of the tunnel anchor security performance evaluation method based on cloud computing of the present invention is proposed.

[0108] The difference between the second embodiment of the cloud computing-based tunnel anchor safety performance evaluation method and the first embodiment of the cloud computing-based tunnel anchor safety performance evaluation method is that the anchor plug body parameters include the front end face area, rear end face area, axial length, anchor plug body inclination angle, concrete coefficient, anchor plug body positioning coefficient, anchor plug body contact area, and anchor plug body wedge angle of the anchor plug body corresponding to the tunnel anchor;

[0109] The step of analyzing the pull-out bearing capacity of the tunnel anchor based on the anchor plug body parameters comprises:

[0110] Step S31, calculating the volume of the anchor plug body according to the front end surface area, the rear end surface area and the axial length; and determining the gravity of the anchor plug body according to the volume;

[0111] Step S32, dividing the gravity into a first gravity component along the main cable direction of the suspension bridge and a second gravity component perpendicular to the outer surface of the anchor plug body according to the inclination angle of the anchor plug body and the wedge angle of the anchor plug body;

[0112] Step S33, obtaining a friction coefficient corresponding to the anchor plug body, and generating rock resistance according to the second gravity component and the friction coefficient;

[0113] Step S34, dividing the rock resistance into a first rock resistance along the main cable direction of the suspension bridge and a second rock resistance perpendicular to the main cable direction of the suspension bridge according to the inclination angle of the anchor plug and the wedge angle of the anchor plug;

[0114] Step S35, obtain the gravity component coefficient corresponding to the first gravity component and the resistance component coefficient corresponding to the rock resistance, and calculate the pull-out bearing capacity based on the first gravity component, the first rock resistance, the second rock resistance, the gravity component coefficient, the resistance component coefficient, the concrete coefficient, the anchor body positioning coefficient and the anchor body contact area.

[0115] Furthermore, the anchor body parameters of this embodiment include parameters related to the size of the anchor body. The anchor body is usually a structure that is narrow at the top and wide at the bottom. When the anchor body is under tension, the wide structure at the bottom generates a squeezing force with the surrounding rock mass in the direction of the tension. Such size-related parameters are related to the magnitude of the tension that the anchor body can withstand, and at least include the front end face area, rear end face area, axial length, and wedge angle of the anchor body. At the same time, the anchor body parameters also include parameters related to the formation of the anchor body. Such parameters are also related to the force of the anchor body, and at least include the inclination angle of the anchor body relative to the horizontal plane, the concrete coefficient of the anchor body, the anchor body positioning coefficient used for positioning during the formation of the anchor body, and the contact area of ​​the anchor body where the anchor body contacts the surrounding rock mass.

[0116] Furthermore, when analyzing the pull-out bearing capacity of the tunnel anchor through the anchor body parameters, the volume of the anchor body is first calculated based on the front face area, rear face area and axial length in the anchor body parameters. Then, the required cubic number of concrete is determined based on the volume of the anchor body, and the weight of the concrete forming the anchor body is obtained by combining the cubic number with the expected concrete strength grade and converted into the gravity of the anchor body. Thereafter, the gravity of the anchor body can be decomposed into a first gravity component along the main cable direction of the suspension bridge and a second gravity component perpendicular to the outer surface of the anchor body according to the size of the anchor body inclination angle and the size of the anchor body wedge angle.

[0117] Furthermore, during the tension process, the anchor plug body has friction with the surrounding rock mass. The friction coefficient between the surrounding rock mass and the concrete forming the anchor plug body is detected and stored in advance, and the friction coefficient is obtained and multiplied with the second gravity component to obtain the rock mass resistance. Thereafter, according to the inclination angle of the anchor plug body and the wedge angle of the anchor plug body itself, the rock mass resistance is divided into the first rock mass resistance along the main cable direction of the suspension bridge and the second rock mass resistance perpendicular to the main cable direction of the suspension bridge.

[0118] Furthermore, different coefficients are pre-set for different forces to reflect the magnitude of the effects of different forces against the tension of the main cable of the suspension bridge. For the first gravity component, the corresponding gravity component coefficient is obtained, and for the rock resistance, the corresponding resistance component coefficient is obtained. Then, based on the first gravity component, the first rock resistance, the second rock resistance, the gravity component coefficient, the resistance component coefficient, the concrete coefficient, the anchor body positioning coefficient and the anchor body contact area, the pull-out bearing capacity of the anchor body is calculated. The specific calculation formula is shown in the following formula (3):

[0119]

[0120] Among them, F b is the pull-out bearing capacity, t1 is the concrete coefficient, t2 is the anchor plug positioning coefficient, W g is the first gravity component, r g is the gravity component coefficient, Bz1 is the first rock mass resistance, B z2 is the second rock mass resistance, A is the contact area of ​​the anchor plug, r z is the resistance component coefficient.

[0121] It should be noted that the anchor body formed by concrete of different strength grades has different strengths and can withstand different tensions of the main cable of the suspension bridge. Therefore, different concrete coefficients are pre-set for concrete of different strength grades. The calculated force is corrected by the concrete coefficient, which can make the final calculated pull-out bearing capacity of the anchor body more accurate. At the same time, the anchor body is usually built one by one by multiple sections. The installation positioning accuracy of the next section relative to the previous section has a significant impact on the mechanical properties of the entire anchor body. The possible error size of the installation between each section is determined in advance through the test model, and the anchor body positioning coefficient that represents the overall error size is set for each error size. The calculated force is corrected by the anchor body positioning coefficient and the concrete coefficient, which further improves the accuracy of the pull-out bearing capacity of the anchor body.

[0122] This embodiment calculates the pull-out bearing capacity of the anchor plug body by comprehensively considering various factors that affect the pull-out bearing capacity of the anchor plug body, making the calculation more accurate, thereby improving the accuracy of the tunnel anchor safety performance assessment.

[0123] For further information, please refer to Figure 3 Based on the first and second embodiments of the tunnel anchor security performance evaluation method based on cloud computing of the present invention, a third embodiment of the tunnel anchor security performance evaluation method based on cloud computing of the present invention is proposed.

[0124] The third embodiment of the cloud computing-based tunnel anchor safety performance assessment method is different from the first and second embodiments of the cloud computing-based tunnel anchor safety performance assessment method in that the step of obtaining the rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing and analyzing the anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters includes:

[0125] Step S50, obtaining a plurality of sample data, and dividing the plurality of sample data into training samples and test samples, wherein the sample data is a mapping relationship between the proportion of rock mass types and the proportion of rock mass morphology and fracture force;

[0126] Step S60, training a preset initial model based on the training sample, and when the training reaches a first preset end condition, testing the preset initial model a preset number of times based on the test sample to obtain a preset number of test results;

[0127] Step S70, calculating the loss function value of the preset initial model according to the test results of the preset number of times, and generating the preset initial model as a preset model based on the loss function value.

[0128] In order to improve the accuracy of the minimum fracture force analysis in the anchor risk parameters, this embodiment obtains a preset model through a large amount of sample data training in advance. Specifically, the sample data is a mapping relationship between rock mass data and minimum fracture force, and the rock mass data is data containing the proportion of different rock mass types and rock mass morphology. For example, for a rock mass W represented by a sample data, it contains a rock mass type proportion A, a rock mass morphology proportion B, and a minimum fracture force C, which means that for the rock mass W, the distribution ratio of each rock mass type is A, the rock mass morphology is B, and the minimum fracture force that causes it to fracture is C.

[0129] Further, after obtaining a large amount of such sample data, each sample data is divided into training samples for training and test samples for testing. In addition, a preset initial model for training and a first preset end condition indicating the end of training are pre-set. The preset initial model is trained by the divided training sample data, and it is determined whether the training reaches the first preset end condition. If the first preset end condition is reached, the preset initial model is tested a preset number of times by the test sample data to obtain the preset number of test results. Among them, the first preset end condition can be set as a duration or a number of times; for example, the training duration is set to 1 hour, 2 hours, 3 hours, etc. as the first preset end condition, or the training number is set to 5 times, 10 times, 20 times, etc. as the first preset end condition. The preset number of times is also pre-set according to the needs. For example, if the accuracy of testing 5 times is higher, the preset number of times can be set to 5 times, or if the accuracy of testing 10 times is higher, the preset number of times can be set to 10 times, etc.

[0130] Furthermore, a loss function is pre-set for the preset initial model, and the loss function of the preset initial model is calculated using the test results obtained for the preset number of times to obtain the loss function value. The calculation formula for calculating the loss function value is specifically shown in the following formula (4).

[0131]

[0132] Among them, Loss is the loss function value, α is the weight factor of the preset initial model, pj is the test result generated by the j-th test sample, and qj is the minimum fracture force corresponding to the j-th test sample.

[0133] Furthermore, the loss function value reflects the performance of the preset initial model after training. The smaller the loss function value, the smaller the loss of the preset initial model, the better the performance, and vice versa. Therefore, the preset initial model can be generated as a preset model based on the size of the preset loss function value. Specifically, the step of generating the preset initial model as a preset model based on the loss function value includes:

[0134] Step S71, determining whether the loss function value satisfies a second preset end condition, and if the second preset end condition is satisfied, ending the training of the preset initial model, and generating the preset initial model as a preset model;

[0135] Step S72, if the loss function value does not meet the second preset end condition, adjusting the model weight of the preset initial model;

[0136] Step S73, executing the step of training the preset initial model based on the training sample based on the adjusted model parameters, until the loss function value meets the second preset end condition, to generate the preset model.

[0137] Furthermore, a second preset end condition is preset, and the second preset end condition is preferably a preset value indicating the size of the loss function value. The calculated loss function value is compared with the preset value, and the comparison is used to determine whether the loss function value meets the second preset end condition. If the loss function value is less than the preset value after comparison, it means that the loss function value is small, and the preset initial model has obtained better performance after training, so it can be determined that the loss function value meets the second preset end condition, and the preset initial model is generated as the preset model.

[0138] On the contrary, if the loss function value is determined to be not less than the preset value through comparison, it means that the loss of the preset initial model is large and training optimization is still required. At this time, the model weight of the preset initial model is adjusted first, and after the adjustment, the preset initial model with new model parameters is iteratively trained again through the training sample parameters. In this way, the loss function value is calculated each time until the calculated loss function value meets the second preset end condition, the model training is completed, and the preset initial model is generated as the preset model. The formula for adjusting the model parameters is specifically shown in the following formula (5).

[0139]

[0140] Where ΔA m is the model weight adjustment value of the mth intermediate layer of the preset initial model, It is used to calculate the error value of the test result of the middle layer of the mth layer of the preset initial model, where n represents the preset number of times and s nmis the actual output value of the nth test result in the mth layer of the preset initial model, t nm is the nth theoretical test result in the mth layer of the preset initial model, w m is the connection weight of the mth layer of the preset initial model, E m is the input data of the mth layer of the preset initial model.

[0141] This embodiment pre-forms a preset model for analyzing the minimum breaking force through training with a large amount of sample data, and optimizes the training through the first preset end condition, the second preset end condition, the loss function value and the model weight, so that the model training is more accurate, thereby improving the accuracy of the analysis of the minimum breaking force.

[0142] In addition, the embodiment of the present invention also provides a cloud computing-based tunnel anchor security performance evaluation system. Figure 4 , Figure 4 It is a structural schematic diagram of the equipment hardware operating environment involved in the cloud computing-based tunnel anchor safety performance evaluation system implementation scheme of the present invention.

[0143] like Figure 4 As shown, the cloud computing-based tunnel anchor security performance evaluation system may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0144] Those skilled in the art will understand that Figure 4 The hardware structure of the cloud computing-based tunnel anchor safety performance evaluation system shown in the figure does not constitute a limitation of the cloud computing-based tunnel anchor safety performance evaluation system, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0145] like Figure 4As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module and a control program. The operating system is a program for managing and controlling the cloud computing-based tunnel anchor security performance evaluation system and software resources, and supports the operation of the network communication module, the user interface module, the control program and other programs or software; the network communication module is used to manage and control the network interface 1004; the user interface module is used to manage and control the user interface 1003.

[0146] exist Figure 4 In the hardware structure of the cloud computing-based tunnel anchor security performance evaluation system shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; the processor 1001 can call the control program stored in the memory 1005 and perform the following operations:

[0147] Based on the first cloud node in the cloud computing, analyzing the conductive force of the main cable of the suspension bridge corresponding to the tunnel anchor;

[0148] Acquiring rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters;

[0149] Acquiring anchor plug body parameters of the tunnel anchor based on the third cloud node in the cloud computing, and analyzing the pull-out bearing capacity of the tunnel anchor based on the anchor plug body parameters;

[0150] Based on the central node in the cloud computing, the conductivity, pull-out bearing capacity and anchor site risk parameters are evaluated and processed to generate a safety assessment coefficient, and the safety performance of the tunnel anchor is evaluated based on the safety assessment coefficient.

[0151] Furthermore, the step of analyzing the conductive force of the main cable of the suspension bridge corresponding to the tunnel anchor based on the first cloud node in the cloud computing includes:

[0152] Reading the bridge body conduction force corresponding to the main cable of the suspension bridge based on the first cloud node, and obtaining historical climate data of the environment in which the main cable of the suspension bridge is located;

[0153] According to the change trend of wind data in the historical climate data, the maximum wind force and wind direction within a preset period are predicted, and the wind force consistent with the direction of the main cable of the suspension bridge is calculated according to the maximum wind force and wind direction. The calculation formula is:

[0154]

[0155] Among them, Fa is the wind force, Fmax is the maximum wind force, θ is the angle between the wind direction and the main cable direction of the suspension bridge, K1 is the wind force level coefficient, k(θ) is the variable wind direction coefficient,

[0156] It is used to calculate the bending vibration frequency of the main cable of the suspension bridge. L is the height of the main cable of the suspension bridge, E is the elastic modulus of the main cable of the suspension bridge, I is the section polar inertia moment of the main cable of the suspension bridge, and A is the cross-sectional area of ​​the main cable of the suspension bridge. is the annual coefficient corresponding to the maximum wind force;

[0157] The conductive force of the bridge body is corrected according to the wind force to obtain the conductive force.

[0158] Furthermore, the step of obtaining the rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing the anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters includes:

[0159] Determine an extended area corresponding to the anchor site area based on the second cloud node, and obtain rock mass characteristic parameters corresponding to the extended area, wherein the rock mass characteristic parameters include rock mass type, rock mass morphology, a first proportion corresponding to each of the rock mass types, and a second proportion corresponding to each of the rock mass morphologies;

[0160] The first proportions and the second proportions are transmitted to a preset model for calculation and processing to obtain the minimum fracture force of the rock mass in the extended area. The calculation formula is:

[0161]

[0162] Among them, W is the minimum breaking force, Wi is the connection weight from the i-th hidden layer of the preset model to the output layer, x1, x2, x3... are the first proportions, y1, y2, y3... are the second proportions, f is the input function, and bi is the i-th hidden layer output of the preset model.

[0163] Obtaining historical geological disaster data of the anchor site area, and predicting the probability of geological disasters occurring in the anchor site area within a preset time period and the type of geological disasters occurring based on the displayed historical geological disaster data;

[0164] According to the probability and type, a maximum probability within a preset time period is generated, and the maximum probability and the minimum rupture force are generated as anchor site risk parameters.

[0165] Furthermore, the anchor plug body parameters include the front end face area, rear end face area, axial length, anchor plug body inclination angle, concrete coefficient, anchor plug body positioning coefficient, anchor plug body contact area, and anchor plug body wedge angle of the anchor plug body corresponding to the tunnel anchor;

[0166] The step of analyzing the pull-out bearing capacity of the tunnel anchor based on the anchor plug body parameters comprises:

[0167] Calculating the volume of the anchor plug body according to the front end surface area, the rear end surface area and the axial length; and determining the gravity of the anchor plug body according to the volume;

[0168] According to the inclination angle of the anchor plug body and the wedge angle of the anchor plug body, the gravity is divided into a first gravity component along the main cable direction of the suspension bridge and a second gravity component perpendicular to the outer surface of the anchor plug body;

[0169] Obtaining a friction coefficient corresponding to the anchor plug body, and generating rock resistance according to the second gravity component and the friction coefficient; dividing the rock resistance into a first rock resistance along the main cable direction of the suspension bridge and a second rock resistance perpendicular to the main cable direction of the suspension bridge according to the anchor plug body inclination angle and the anchor plug body wedge angle;

[0170] Obtaining a gravity component coefficient corresponding to the first gravity component and a resistance component coefficient corresponding to the rock mass resistance;

[0171] The pull-out bearing capacity is calculated according to the first gravity component, the first rock mass resistance, the second rock mass resistance, the gravity component coefficient, the resistance component coefficient, the concrete coefficient, the anchor body positioning coefficient and the anchor body contact area. The calculation formula is:

[0172]

[0173] Among them, F b is the pull-out bearing capacity, t1 is the concrete coefficient, t2 is the anchor plug positioning coefficient, W g is the first gravity component, r g is the gravity component coefficient, B z1 is the first rock mass resistance, B z2 is the second rock mass resistance, A is the contact area of ​​the anchor plug, r z is the resistance component coefficient.

[0174] Furthermore, the step of evaluating and processing the conductivity, pull-out bearing capacity and anchor risk parameters based on the central node in the cloud computing to generate a safety assessment coefficient includes:

[0175] Performing difference calculation on the conductive force and the pull-out bearing capacity based on the central node to obtain a calculation result, and determining a safety factor to be evaluated corresponding to the calculation result according to a correspondence between a preset difference interval and a safety factor;

[0176] The safety factor to be evaluated is evaluated according to the anchor site risk parameter to generate the safety evaluation factor.

[0177] Furthermore, the step of evaluating the safety performance of the tunnel anchor according to the safety evaluation coefficient includes:

[0178] According to the safety assessment coefficient, evaluating whether the safety performance of the tunnel anchor meets the preset conditions;

[0179] If the preset conditions are met, the safety performance evaluation of the tunnel anchor is completed;

[0180] If the preset conditions are not met, a prompt message for adjusting the anchor plug body parameters of the tunnel anchor is output, so that the safety performance of the tunnel anchor can be re-evaluated after the adjustment is completed.

[0181] Furthermore, the step of obtaining the rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing the anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters includes:

[0182] Acquire multiple sample data, and divide the multiple sample data into training samples and test samples, wherein the sample data is a mapping relationship between the proportion of rock mass types and the proportion of rock mass morphology and fracture force;

[0183] Training a preset initial model based on the training sample, and when the training reaches a first preset end condition, testing the preset initial model a preset number of times based on the test sample to obtain a preset number of test results;

[0184] According to the test results of the preset number of times, the loss function value of the preset initial model is calculated, and based on the loss function value, the preset initial model is generated as a preset model, and the calculation formula of the loss function value is:

[0185]

[0186] Among them, Loss is the loss function value, α is the weight factor of the preset initial model, pj is the test result generated by the j-th test sample, and qj is the minimum fracture force corresponding to the j-th test sample.

[0187] Furthermore, the step of generating the preset initial model into a preset model based on the loss function value includes:

[0188] Determine whether the loss function value satisfies a second preset end condition, and if so, terminate the training of the preset initial model and generate the preset initial model as a preset model;

[0189] If the loss function value does not meet the second preset end condition, the model weight of the preset initial model is adjusted, and the adjustment formula is:

[0190]

[0191] Where ΔA m is the model weight adjustment value of the mth intermediate layer of the preset initial model, It is used to calculate the error value of the test result of the middle layer of the mth layer of the preset initial model, where n represents the preset number of times and s nm is the actual output value of the nth test result in the mth layer of the preset initial model, t nm is the nth theoretical test result in the mth layer of the preset initial model, W m is the connection weight of the mth layer of the preset initial model, E m is the input data of the mth layer of the preset initial model.

[0192] The step of training the preset initial model based on the training sample is performed based on the adjusted model parameters until the loss function value meets the second preset end condition, thereby generating the preset model.

[0193] The specific implementation of the cloud computing-based tunnel anchor safety performance evaluation system of the present invention is basically the same as the various embodiments of the cloud computing-based tunnel anchor safety performance evaluation method described above, and will not be repeated here.

[0194] The embodiment of the present invention further provides a storage medium having a control program stored thereon, and when the control program is executed by a processor, the steps of the tunnel anchor security performance evaluation method based on cloud computing are implemented.

[0195] The storage medium of the present invention may be a computer-readable storage medium, and its specific implementation is substantially the same as the above-mentioned embodiments of the cloud computing-based tunnel anchor security performance evaluation method, which will not be described in detail here.

[0196] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims. All equivalent structures or equivalent process changes made using the contents of the specification and drawings of the present invention, or directly or indirectly used in other related technical fields, are protected by the present invention.

Claims

1. A tunnel anchor security performance evaluation method based on cloud computing, characterized in that: The tunnel anchor safety performance evaluation method comprises: Based on the first cloud node in the cloud computing, analyzing the conductive force of the main cable of the suspension bridge corresponding to the tunnel anchor; Acquiring rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters; Acquiring anchor plug body parameters of the tunnel anchor based on the third cloud node in the cloud computing, and analyzing the pull-out bearing capacity of the tunnel anchor based on the anchor plug body parameters; Based on the central node in the cloud computing, the conductivity, pull-out bearing capacity and anchor site risk parameters are evaluated and processed to generate a safety assessment coefficient, and the safety performance of the tunnel anchor is evaluated based on the safety assessment coefficient.

2. The tunnel anchor safety performance evaluation method according to claim 1, characterized in that: The step of analyzing the conductive force of the main cable of the suspension bridge corresponding to the tunnel anchor based on the first cloud node in the cloud computing comprises: Reading the bridge body conduction force corresponding to the main cable of the suspension bridge based on the first cloud node, and obtaining historical climate data of the environment in which the main cable of the suspension bridge is located; According to the change trend of wind data in the historical climate data, the maximum wind force and wind direction within a preset period are predicted, and the wind force consistent with the direction of the main cable of the suspension bridge is calculated according to the maximum wind force and wind direction. The calculation formula is: Among them, Fa is the wind force, Fmax is the maximum wind force, θ is the angle between the wind direction and the main cable direction of the suspension bridge, K1 is the wind force level coefficient, k(θ) is the variable wind direction coefficient, It is used to calculate the bending vibration frequency of the main cable of the suspension bridge. L is the height of the main cable of the suspension bridge, E is the elastic modulus of the main cable of the suspension bridge, I is the section polar inertia moment of the main cable of the suspension bridge, and A is the cross-sectional area of ​​the main cable of the suspension bridge. is the annual coefficient corresponding to the maximum wind force; The conductive force of the bridge body is corrected according to the wind force to obtain the conductive force.

3. The tunnel anchor safety performance evaluation method according to claim 1, characterized in that: The step of acquiring the rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing the anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters includes: Determine an extended area corresponding to the anchor site area based on the second cloud node, and obtain rock mass characteristic parameters corresponding to the extended area, wherein the rock mass characteristic parameters include rock mass type, rock mass morphology, a first proportion corresponding to each of the rock mass types, and a second proportion corresponding to each of the rock mass morphologies; The first proportions and the second proportions are transmitted to a preset model for calculation and processing to obtain the minimum fracture force of the rock mass in the extended area. The calculation formula is: Wherein, W is the minimum breaking force, Wi is the connection weight from the i-th hidden layer of the preset model to the output layer, x1, x2, x3... are the first proportions, y1, y2, y3... are the second proportions, f is the input function, and bi is the output of the i-th hidden layer of the preset model; Obtaining historical geological disaster data of the anchor site area, and predicting the probability of geological disasters occurring in the anchor site area within a preset time period and the type of geological disasters occurring based on the displayed historical geological disaster data; According to the probability and type, a maximum probability within a preset time period is generated, and the maximum probability and the minimum rupture force are generated as anchor site risk parameters.

4. The tunnel anchor safety performance evaluation method according to claim 1, characterized in that: The anchor plug body parameters include the front end face area, rear end face area, axial length, anchor plug body inclination angle, concrete coefficient, anchor plug body positioning coefficient, anchor plug body contact area, and anchor plug body wedge angle of the anchor plug body corresponding to the tunnel anchor; The step of analyzing the pull-out bearing capacity of the tunnel anchor based on the anchor plug body parameters comprises: Calculating the volume of the anchor plug body according to the front end surface area, the rear end surface area and the axial length; and determining the gravity of the anchor plug body according to the volume; According to the inclination angle of the anchor plug body and the wedge angle of the anchor plug body, the gravity is divided into a first gravity component along the main cable direction of the suspension bridge and a second gravity component perpendicular to the outer surface of the anchor plug body; Obtaining a friction coefficient corresponding to the anchor plug body, and generating rock resistance according to the second gravity component and the friction coefficient; dividing the rock resistance into a first rock resistance along the main cable direction of the suspension bridge and a second rock resistance perpendicular to the main cable direction of the suspension bridge according to the anchor plug body inclination angle and the anchor plug body wedge angle; Obtaining a gravity component coefficient corresponding to the first gravity component and a resistance component coefficient corresponding to the rock mass resistance; The pull-out bearing capacity is calculated according to the first gravity component, the first rock mass resistance, the second rock mass resistance, the gravity component coefficient, the resistance component coefficient, the concrete coefficient, the anchor body positioning coefficient and the anchor body contact area. The calculation formula is: Among them, Fb is the pull-out bearing capacity, t1 is the concrete coefficient, t2 is the anchor plug positioning coefficient, and W g is the first gravity component, r g is the gravity component coefficient, B z1 is the first rock mass resistance, B z2 is the second rock mass resistance, A is the contact area of ​​the anchor plug, r z is the resistance component coefficient.

5. The tunnel anchor safety performance evaluation method according to claim 1, characterized in that: The step of evaluating and processing the conductivity, pull-out bearing capacity and anchor risk parameters based on the central node in the cloud computing to generate a safety assessment coefficient comprises: Performing difference calculation on the conductive force and the pull-out bearing capacity based on the central node to obtain a calculation result, and determining a safety factor to be evaluated corresponding to the calculation result according to a correspondence between a preset difference interval and a safety factor; The safety factor to be evaluated is evaluated according to the anchor site risk parameter to generate the safety evaluation factor.

6. The tunnel anchor safety performance evaluation method according to any one of claims 1 to 5, characterized in that: The step of evaluating the safety performance of the tunnel anchor according to the safety evaluation coefficient comprises: According to the safety assessment coefficient, evaluating whether the safety performance of the tunnel anchor meets the preset conditions; If the preset conditions are met, the safety performance evaluation of the tunnel anchor is completed; If the preset conditions are not met, a prompt message for adjusting the anchor plug body parameters of the tunnel anchor is output, so that the safety performance of the tunnel anchor can be re-evaluated after the adjustment is completed.

7. The tunnel anchor safety performance evaluation method according to any one of claims 1 to 5, characterized in that: The step of obtaining the rock mass characteristic parameters of the anchor site area corresponding to the tunnel anchor based on the second cloud node in the cloud computing, and analyzing the anchor site risk parameters corresponding to the tunnel anchor based on the rock mass characteristic parameters includes: Acquire multiple sample data, and divide the multiple sample data into training samples and test samples, wherein the sample data is a mapping relationship between the proportion of rock mass types and the proportion of rock mass morphology and fracture force; Training a preset initial model based on the training sample, and when the training reaches a first preset end condition, testing the preset initial model a preset number of times based on the test sample to obtain a preset number of test results; According to the test results of the preset number of times, the loss function value of the preset initial model is calculated, and based on the loss function value, the preset initial model is generated as a preset model, and the calculation formula of the loss function value is: Among them, Loss is the loss function value, α is the weight factor of the preset initial model, and p j The test result generated for the jth test sample, q j is the minimum breaking force corresponding to the jth test sample.

8. The tunnel anchor safety performance evaluation method according to claim 7, characterized in that: The step of generating the preset initial model into a preset model based on the loss function value comprises: Determine whether the loss function value satisfies a second preset end condition, and if so, terminate the training of the preset initial model and generate the preset initial model as a preset model; If the loss function value does not meet the second preset end condition, the model weight of the preset initial model is adjusted, and the adjustment formula is: Where ΔA m is the model weight adjustment value of the mth intermediate layer of the preset initial model, It is used to calculate the error value of the test result of the middle layer of the mth layer of the preset initial model, where n represents the preset number of times and s nm is the actual output value of the nth test result in the mth layer of the preset initial model, t nm is the nth theoretical test result in the mth layer of the preset initial model, W m is the connection weight of the mth layer of the preset initial model, E m is the input data of the mth layer of the preset initial model. The step of training the preset initial model based on the training sample is performed based on the adjusted model parameters until the loss function value meets the second preset end condition, thereby generating the preset model.

9. A cloud computing-based tunnel anchor safety performance evaluation system, characterized in that: The cloud computing-based tunnel anchor safety performance evaluation system includes: a memory, a processor, a communication bus, and a control program stored in the memory: The communication bus is used to realize the connection and communication between the processor and the memory; The processor is used to execute the control program to implement the steps of the cloud computing-based tunnel anchor security performance evaluation method as described in any one of claims 1-8.

10. A storage medium, characterized in that: The storage medium stores a control program, and when the control program is executed by the processor, the steps of the cloud computing-based tunnel anchor security performance evaluation method as described in any one of claims 1 to 8 are implemented.

Images