A corrosion test system for tunnel lining steel bars and a corrosion rate monitoring method

Abstract

The present invention provides a corrosion test system for tunnel lining steel bars and a corrosion rate monitoring method, which relates to the technical field of tunnel engineering, and includes: constructing a prediction model, where the hidden layer weights and biases of the prediction model are determined by an artificial ecosystem optimization algorithm, and the initial population of the artificial ecosystem optimization algorithm is obtained by cubic mapping; obtaining training samples and measured strain data; training the prediction model with the training samples to obtain a corrosion rate prediction model, where the training samples include lining strain data and steel bar corrosion rate data; inputting the measured strain data into the corrosion rate prediction model to obtain the corrosion rate. The present invention combines ICM, AEO and ELM, and uses the random numbers generated by the chaotic system to initialize the population in the AEO optimization algorithm, which improves the diversity of the population and avoids falling into local optimal solutions. The hyperparameters of ELM are optimized by ICM-AEO to obtain the optimal values of the hidden layer weights and biases, thereby improving the prediction accuracy of the entire prediction model.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel engineering, and in particular, to a corrosion test system for tunnel lining steel bars and a corrosion rate monitoring method. Background Art

[0002] The geological conditions in the western mountainous areas of China are complex. The tunnels constructed need to pass through complex and dangerous geological environments, with many adverse engineering geological conditions. The working environment of the tunnel structure is very complex. Under the long-term action of high-pressure water heads and chemical erosion, the steel bars are often corroded due to excessive chloride ion concentration. After the steel bars are corroded, the volume expands, causing the surrounding concrete to be pulled apart and cracked, and the cracks gradually expand to the surface of the structure. Moreover, the generation of cracks will further accelerate the corrosion of the steel bars. When the corrosion amount of the steel bars reaches a certain level, the bonding force between the steel bars and the concrete will begin to decrease, and the cross-sectional area participating in the force after corrosion decreases, seriously reducing the bearing capacity of the structure and having a significant impact on the safety and durability of the lining structure. However, since the steel bars are embedded inside the concrete, the current non-destructive testing technologies are still unable to directly measure the corrosion amount of the steel bars in the structure. Therefore, it is urgent to establish a new non-destructive intelligent prediction method to realize the continuous monitoring of the corrosion rate of tunnel lining steel bars. Summary of the Invention

[0003] The purpose of the present invention is to provide a corrosion test system for tunnel lining steel bars and a corrosion rate monitoring method to improve the above problems. To achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0004] In the first aspect, the present application provides a corrosion rate monitoring method for tunnel lining steel bars, including:

[0005] Constructing a prediction model, the weights and biases of the hidden layer of the prediction model are determined by an artificial ecosystem optimization algorithm, and the initial population of the artificial ecosystem optimization algorithm is obtained by cubic mapping;

[0006] Obtaining training samples and measured strain data; the training samples are obtained from the tests of a corrosion device, and the corrosion device includes a lining member embedded with multiple steel bars, and multiple strain optical fibers are arranged on the surface of the lining member;

[0007] Training the prediction model with the training samples to obtain a corrosion rate prediction model, where the training samples include lining strain data and steel bar corrosion rate data;

[0008] Inputting the measured strain data into the corrosion rate prediction model to obtain the corrosion rate.

[0009] In the second aspect, the present application also provides a corrosion test system for tunnel lining steel bars, including:

[0010] The first module is used to construct a prediction model. The weights and biases of the hidden layer of the prediction model are determined by an artificial ecosystem optimization algorithm, and the initial population of the artificial ecosystem optimization algorithm is obtained by cubic mapping.

[0011] The second module is used to obtain training samples and measured strain data. The training samples are obtained from the corrosion device test. The corrosion device includes a lining member embedded with multiple steel bars, and multiple strain optical fibers are arranged on the surface of the lining member.

[0012] The third module is used to train the prediction model with the training samples to obtain a corrosion rate prediction model. The training samples include lining strain data and steel bar corrosion rate data.

[0013] The fourth module is used to input the measured strain data into the corrosion rate prediction model to obtain the corrosion rate.

[0014] The beneficial effects of the present invention are as follows:

[0015] The present invention constructs an ICM-AEO-ELM prediction model, combines ICM, AEO and ELM, can initialize the population in the AEO optimization algorithm by random numbers generated by the chaotic system, improve the diversity of the population, and avoid falling into local optimal solutions. Use ICM-AEO to optimize the hyperparameters of ELM to obtain the optimal values of the weights and biases of the hidden layer in the extreme learning machine, thereby improving the prediction accuracy of the entire prediction model. Learn the training samples obtained from the experiment according to the prediction model, and finally form an accurate corrosion rate prediction model, providing a reference for on-site non-destructive detection of the corrosion rate of lining steel bars.

[0016] Other features and advantages of the present invention will be described in the subsequent specification, and part of them will become obvious from the specification or be understood by implementing the embodiments of the present invention. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, so they should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flow chart of the corrosion monitoring method for tunnel lining steel bars in the embodiments of the present application;

[0019] Figure 2 It is a schematic structural diagram of the corrosion device in the embodiments of the present application;

[0020] Figure 3 It is a structural diagram of the corrosion test system for tunnel lining steel bars in the embodiments of the present application.

[0021] Markings in the figure: 100 - Lining member; 101 - Corbels; 200 - Optical fiber; 300 - Corrosion component; 400 - Reaction device; 401 - Reaction steel beam; 402 - Rebar; 500 - Jack; 600 - Adjustment device; 601 - Base plate; 602 - Guide block; 710 - First module; 711 - First unit; 712 - Second unit; 713 - First sub - unit; 714 - Second sub - unit; 715 - Third sub - unit; 720 - Second module; 730 - Third module; 740 - Fourth module; 750 - Fifth module; 760 - Sixth module; 770 - Seventh module; 780 - Eighth module. Detailed implementation manners

[0022] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Components of the embodiments of the present invention usually described and illustrated in the accompanying 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 accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts fall within the protection scope of the present invention.

[0023] It should be noted that: Similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0024] Currently, China's specifications mainly qualitatively describe the corrosion status of steel bars through the corrosion potential of steel bars, the resistivity of concrete and the surface disease conditions of the structure. However, these traditional measurement methods for the corrosion rate of lining steel bars are greatly affected by the environment and the measurement results are inaccurate. Therefore, a new corrosion rate monitoring method is needed to improve the prediction accuracy of the corrosion rate and provide a reference for detecting the corrosion rate of lining steel bars on site.

[0025] Embodiment 1:

[0026] See Figure 1 , this embodiment provides a method for monitoring the corrosion rate of tunnel lining steel bars, including: steps S100, S200, S300 and S400;

[0027] S100. Construct a prediction model, where the weights and biases of the hidden layer of the prediction model are determined by an artificial ecosystem optimization algorithm, and the initial population of the artificial ecosystem optimization algorithm is obtained by cubic mapping;

[0028] Generate at least 20 populations in sequence using cubic mapping. During the cubic mapping generation process for each population, fuse the information of the first two generated populations according to a preset weight, and use the last generated population as the target population; use the target population as the initial population.

[0029] ICM mapping (Improved Cubic Map), that is, the improved cubic mapping, helps the swarm intelligence optimization algorithm generate a diverse initial population by introducing a memory effect. Through the memory mechanism, the optimization algorithm can better explore the solution space, reduce redundant individuals in the initial stage, and avoid falling into local optimal solutions.

[0030] In this embodiment, 30 populations are generated using cubic mapping (i.e., the number of iterations of cubic mapping is 29 times), and the m-th population is represented by m.

[0031] The expression of the cubic mapping introducing the memory effect is:

[0032] ;

[0033] where, is the individual state in the (m - 1)-th population, is the individual state in the m-th population, is the individual state in the (m + 1)-th population; , is the weight coefficient of the memory effect. When , the mapping system is a standard cubic mapping. When , the current mapping fully depends on ; , is the control parameter of the cubic mapping. By changing the value of , it can be observed that this chaotic mapping gradually transitions from periodic behavior to chaotic behavior.

[0034] Start iteratively updating the roles of individuals from the initial population. Specifically:

[0035] Update producers, consumers, and decomposers according to the predation relationship between roles and the energy level of roles; The artificial ecosystem optimization algorithm (AEO) is a new swarm intelligence optimization algorithm proposed inspired by the energy flow and the behaviors of producers, consumers, and decomposers in an ecosystem. It mainly includes a production stage, a consumption stage, and a decomposition stage. Organisms represent the feasible solutions to the problem, and decomposers represent the optimal solutions to the problem and gradually approach the theoretical optimal solution as the iteration progresses. The role update process is as follows:

[0036] Producer update: The producer (the worst individual) is decomposed by the decomposer (the best individual) and a random individual Linear coupled iterative update to guide the evolution of herbivores and omnivores, and its expression is:

[0037] ;

[0038] Where: is the population size, is the weighting coefficient, and are the current and maximum iteration times respectively, is a random number; is a random individual within the solution space [L, U] and is a -dimensional random vector.

[0039] Consumer update: Consumers can be divided into herbivores, omnivores, and carnivores according to their feeding characteristics. In the model, they are randomly assigned a role category with probability and updated iteratively according to the following 3 modes.

[0040] Case 1: Herbivores can only prey on producers , and the corresponding behavioral model can be mathematically expressed as:

[0041] ;

[0042] Where: , is the consumption factor improved based on Levy flight, and and are both random numbers obeying the standard normal distribution.

[0043] Case 2: Carnivores can only randomly prey on a consumer with a higher energy level, and the corresponding behavioral model can be expressed as:

[0044] ;

[0045] Where: , .

[0046] Case 3: Omnivores can prey on producers and a random consumer with a higher energy level, and the corresponding behavioral model is:

[0047] , ;

[0048] Where: , is a random number.

[0049] Decomposer update: Each organism in the ecosystem will die and be decomposed by the decomposer The corresponding decomposition behavior model is:

[0050] ;

[0051] Where: , is the decomposition factor and obeys the standard normal distribution, and are both weighting coefficients and is a random number.

[0052] Modify the hidden layer weights and biases of the prediction model according to the roles obtained in each round of update, and input the test set into the prediction model to obtain the classification accuracy corresponding to each role;

[0053] Update the population with the classification accuracy as the energy level (fitness value) of each role, and perform iterative calculations. When the maximum number of iterations is reached or the convergence condition is satisfied, stop the iteration, output the optimal solution of the decomposer, and obtain the optimal values of the hidden layer weights and biases.

[0054] In each iteration, a chaotic sequence is generated by cubic mapping, a perturbation value is generated based on the chaotic sequence mapping, and the individual position is perturbed according to the perturbation value. When the maximum number of iterations is reached or the convergence condition is satisfied, stop the iteration to obtain the optimal values of the hidden layer weights and biases.

[0055] In this application, an extreme learning machine (ELM) is used to construct the model, and the AEO algorithm is used to optimize the optimal values of the hidden layer weights and biases of the extreme learning machine. For the input data, the hidden layer output is calculated through the activation function , and the squared error between the network output and the sample output target matrix is used as the training error objective function to solve the output weights, and the trained weights are used for prediction.

[0056] S200. Obtain training samples and measured strain data; the training samples are obtained from the rusting device test. The rusting device includes a lining member buried with multiple steel bars, and multiple strain optical fibers are arranged on the surface of the lining member;

[0057] The training samples include lining strain data and steel bar corrosion rate data. The acquisition methods of the lining strain data and the steel bar corrosion rate data include:

[0058] Obtain a preset corrosion rate; the preset corrosion rate can be randomly given according to the known steel bar corrosion rate of tunnel linings in the field, and it is used to determine experimental parameters to simulate the real environment;

[0059] Calculate the rusting duration based on the preset rusting rate and test parameters;

[0060] Rust the steel bars according to the test parameters and rusting duration, and measure the lining strain data generated during and after rusting through the strain optical fiber;

[0061] After rusting is completed, take out the rusted steel bars, cut the rusted steel bars into multiple segments with the same length as the layout spacing of the strain optical fiber, and measure the cross-sectional diameter of each segment of the rusted steel bar;

[0062] Based on the cross-sectional diameter and length of the rusted steel bars, calculate the steel bar rusting rate data;

[0063] When obtaining the measured strain data, lay the strain optical fiber on the surface of the tunnel lining to be measured in the same way as the rusting device; using a distributed optical fiber can measure the strain data at multiple points on the tunnel lining to be measured simultaneously.

[0064] S300. Train the prediction model with training samples to obtain a rusting rate prediction model, where the training samples include lining strain data and steel bar rusting rate data;

[0065] S400. Input the measured strain data into the rusting rate prediction model to obtain the rusting rate;

[0066] In the lining structure, generally multiple steel bars are buried at the same time, and the cement cracking stress generated by the rusting of each steel bar will affect the surrounding steel bars, that is, the strain distribution on the lining surface is jointly determined by multiple internal steel bars; in order to improve the prediction accuracy of the model in different situations, this embodiment optimizes the rusting rate prediction model based on the actual situation of the tunnel lining to be measured, specifically as follows:

[0067] Obtain the strain data at multiple points on the surfaces of multiple lining components, construct multiple surface strain matrices, calculate the differences between adjacent elements to construct a distribution gradient matrix, and convert the distribution gradient matrix into a first heat map;

[0068] The strain optical fibers are arranged at equal intervals on the surface of the lining component and are perpendicular to the internal steel bars. The intersection point of each strain optical fiber and the steel bar is the measurement point of the strain optical fiber. Therefore, the measurement points are actually distributed in an array form. Fill the strain data of each point into the matrix according to the actual position to obtain the surface strain matrix; calculate the differences between adjacent elements in the surface strain matrix to construct a distribution gradient matrix, and the distribution gradient matrix can reflect the change of the strain value on the lining.

[0069] During the experiment, use steel bars of different sizes and arrange them at different intervals to make multiple lining components, and multiple first heat maps can be obtained respectively;

[0070] Obtain the strain data of multiple points on the lining to be measured, construct the measured gradient matrix of the lining to be measured and convert it into a second heat map. It should be noted that when detecting the lining to be measured, strain optical fibers are arranged on it in the same way as the experimental device to obtain a measured gradient matrix with the same size as the distribution gradient matrix, and the second heat map can be obtained based on the same operation.

[0071] Update the training weights for the strain data corresponding to the first heat map based on the similarity between the second heat map and each first heat map.

[0072] In this step, the structural similarity index (SSIM) can be used to evaluate the similarity between heat maps, or the images can be converted into hash values, and then the differences in hash values are compared to evaluate the similarity. A high similarity between heat maps indicates that the strain distribution on the lining to be measured is relatively similar to the strain distribution on the lining component of this experiment. Therefore, the strain data of this lining component has higher reference value for the lining to be measured this time.

[0073] Train the prediction model with the strain data whose training weights have been updated to obtain an updated prediction model. After the update, the test data with similar lining strain distributions has a greater impact on the prediction results, making the prediction results of the prediction model more accurate.

[0074] During actual measurement, due to differences in construction scale, the strain distribution gradient of the lining to be measured may be larger than the strain distribution gradient during the experiment. In order to adjust the strain distribution of linings of different scales to the same scale for comparison; in this step, the data in the distribution gradient matrix and the measured gradient matrix can be normalized respectively. After normalization, the data in both matrices are between [0, 1] and have the same scale.

[0075] As another alternative implementation, the method to adjust the data in the distribution gradient matrix and the measured gradient matrix to the same scale is as follows:

[0076] Calculate the mean value of the strain data of the lining component to obtain the first mean value.

[0077] Calculate the mean value of the strain data of the lining to be measured to obtain the second mean value.

[0078] Scale the strain data of the lining to be measured according to the ratio of the first mean value and the second mean value to obtain processed data.

[0079] Construct the measured strain matrix of the lining to be measured based on the processed data.

[0080] After optimizing the corrosion rate prediction model through the above operations in this step, then input the measured strain data into the optimized corrosion rate prediction model to obtain the corrosion rate.

[0081] Based on the above technical concept, refer to Figure 2 and the present invention provides a rusting device, including a lining member 100, and the lining member 100 includes a reinforcing bar to be rusted buried in concrete;

[0082] An optical fiber 200, the optical fiber 200 is arranged on the surface of the lining member 100, and the optical fiber 200 is perpendicular to the reinforcing bar to be rusted;

[0083] A rusting component 300, the rusting component 300 is connected to the reinforcing bar to be rusted and is used for rusting the reinforcing bar to be rusted;

[0084] A reaction force device 400, the reaction force device 400 is arranged around the outside of the lining member 100, one end of which is in contact with the lining member 100, and there is a gap between the other end and the lining member 100;

[0085] A jack 500, the jack 500 is arranged in the gap between the reaction force device 400 and the lining member 100, the jack 500 is used for applying a load to the lining member 100, and the direction of applying the load is the same as the laying direction of the reinforcing bar to be rusted.

[0086] The rusting test system of the present invention is used to simulate the rusting condition of the lining steel bars and the strain condition of the lining under certain Cl - concentration conditions and under the action of bending moment and axial force. During the rusting process, the concrete will generate rusting cracks consistent with the direction of the steel bar, and tensile strains perpendicular to the direction of the steel bar will be generated on both sides of the cracks. Optical fibers can be arranged at equal intervals in the vertical direction along the direction of the reinforcing bar to be rusted on the concrete surface, and the optical fibers are connected to an optical fiber demodulator to obtain and record the strain values generated by the cracking of the rusting of the steel bar.

[0087] When designing the lining member, it is necessary to obtain design data according to the tunnel site to be monitored, and make a reinforced concrete lining member with corresponding dimensions according to the design data.

[0088] As an alternative implementation manner, corbels 101 are provided at both the upper and lower ends of the lining member 100, and the jack 500 applies a load to the corbels 101. The lining corbel is a support structure arranged in the tunnel lining structure, usually located on the side wall or arch of the tunnel, and is used to support the crane beam, track or other equipment.

[0089] As an alternative implementation manner, the rusting component 300 includes a rusting tank, a stainless steel mesh, a rusting liquid and a power source;

[0090] The stainless steel mesh is placed in the rusting tank, and the rusting liquid submerges the stainless steel mesh;

[0091] The steel bar to be corroded is connected to the positive electrode of the power supply, and the stainless steel mesh is connected to the negative electrode of the power supply.

[0092] The power supply is a constant current DC power supply, and the corrosion solution is a NaCl solution, where the Cl - concentration is determined according to the chloride ion concentration at the tunnel site to be monitored. The Cl - concentration in the corrosion area at the tunnel site can be measured by a chloride ion content detector using the ion selective electrode method (ISE method).

[0093] As an alternative embodiment, the corrosion test system further includes an adjusting device 600. Since the actual force on the tunnel is constantly changing, the adjusting device is provided to adjust the force application position of the jack on the lining. The adjusting device 600 includes a backing plate 601, and a lifting mechanism is connected and arranged below the backing plate 601; the lifting mechanism includes two symmetrically arranged chutes and sliding brackets arranged in the chutes. Each sliding bracket has an X-shaped structure and can rotate around the midpoint. The upper end of the sliding bracket is hinged to the backing plate, and the lower end of the sliding bracket slides in the chute and can be fixed, thereby realizing the lifting adjustment of the backing plate.

[0094] The jack is cylindrical in shape. To prevent the jack from shifting during the application of the load, a guiding block 602 is further provided on the backing plate 601. The jack 500 is arranged inside the guiding block 602, and the jack just engages with the concave structure of the guiding block and will not roll. The two ends of the jack 500 respectively abut against the reaction device 400 and the lining member 100.

[0095] As an alternative embodiment, the reaction device 400 includes two reaction steel beams 401 at both ends, and also includes a threaded steel bar 402 connecting the two reaction steel beams 401; threaded holes are opened at both ends of each reaction steel beam 401; the two ends of the threaded steel bar 402 are respectively connected to the threaded holes of the two reaction steel beams 401, and the threaded steel bar 402 is perpendicular to the reaction steel beam 401, forming a rectangular frame.

[0096] When the jack works, its two ends respectively abut against the reaction steel beam and the lining member, applying a load to the lining member. At the same time, the other end of the lining member is restricted by another reaction steel beam, and the reaction steel beam generates a reaction force on the lining member.

[0097] In addition, a cushion block for raising the reaction steel beam is further provided on the backing plate. After raising, the axis height of the reaction steel beam is kept consistent with that of the jack to ensure that the force is not offset.

[0098] As an alternative embodiment, ordinary steel bars are also provided inside the lining member 100, and the surfaces of the ordinary steel bars are coated with epoxy resin and wrapped with insulating tape. When manufacturing the lining member, multiple steel bars are embedded in the concrete in the transverse, longitudinal, and inclined directions of the corbel. Only the transverse steel bars need to be subjected to corrosion tests, and the other steel bars need to be insulated.

[0099] Based on the corrosion device provided in this application, lining strain data and steel bar corrosion rate data are obtained. The specific operations are as follows:

[0100] First, determine the parameters of the applied load:

[0101] On-site monitoring in the tunnel to obtain the stress data of the lining in the corroded area. Specifically, vibrating wire concrete strain gauges can be arranged on the inner and outer sides of the lining to obtain the inner strain and the outer strain ;

[0102] According to the inner strain and the outer strain calculate the eccentricity of the jack action :

[0103] ;

[0104] In the formula, is the moment of inertia of the lining member, is the cross-sectional thickness of the lining member, is the inner strain, is the outer strain, is the magnitude of the eccentric load, and should be less than the cracking load to avoid the influence of concrete cracking on the corrosion rate;

[0105] The calculation formula for the cracking load is:

[0106] ;

[0107] In the formula, is the plastic coefficient of the section modulus, is the concrete tensile stress limit coefficient, is the standard value of the axial tensile strength of concrete, is the converted cross-sectional area (equivalent the steel bar area to the concrete area), is the resistance moment of the converted interface at the tension edge.

[0108] Before the test, an eccentric load can be estimated first, then calculate the eccentricity , and then judge whether is less than If yes, then you can use this parameter to test, if not, adjust the eccentric load Recalculate until the requirements are met.

[0109] Then determine the duration of corrosion:

[0110] Get the preset corrosion rate;

[0111] Calculating the corrosion duration based on the preset corrosion rate and test parameters, wherein the test parameters include the molar mass of the iron element, the surface current density of the steel bar to be corroded, the radius of the steel bar to be corroded, and the density of the steel bar to be corroded;

[0112] The corroded steel bars are corroded according to the test parameters and the corrosion time, and the lining strain data generated during and after the corrosion process is measured through the optical fiber 200.

[0113] Specifically, first preset a suitable corrosion rate, and calculate the corrosion duration according to the preset corrosion rate. The calculation formula is as follows:

[0114] ;

[0115] In the formula, is the molar mass of iron, 56 g / mol, The current density on the surface of the steel bar to be corroded should be less than or equal to 500 , For the duration of rust, is the Faraday constant, 96500C / mol, is the radius of the steel bar to be corroded, The density of the steel bars to be corroded.

[0116] According to the parameters determined above, the corrosion test is carried out, the steel bar to be corroded is connected to the positive electrode of the constant current DC power supply, the stainless steel mesh is connected to the negative electrode of the constant current DC power supply, the power is turned on for corrosion, and the eccentric load is applied to the lining component at the same time; the strain value measured by the optical fiber during and after the corrosion process is recorded.

[0117] After the corrosion is complete, the corroded steel bars are taken out and cleaned with a rust removal liquid to remove the corrosion products on the surface of the corroded steel bars;

[0118] The length is the same as the optical fiber 200 layout spacing. Cut off multiple sections of corroded steel bars and measure the cross-sectional diameter of each section of corroded steel bars. It should be noted that the setting position of each optical fiber corresponds to the buried position of a section of corroded steel bars. Therefore, the strain of the optical fiber is caused by the cracks caused by the corrosion of the section of steel bars. The data of each optical fiber corresponds to a section of corroded steel bars one by one, forming a strain-corrosion rate data set.

[0119] Based on the cross-sectional diameter and length of the corroded steel bars, the steel bar corrosion rate data is calculated.

[0120] For each cross-section of the corroded steel bars, the diameter along the transverse ribs and the diameter perpendicular to the transverse ribs are measured respectively. Take and The average value of is used as the corrosion diameter of the remaining cross-section of the corroded steel bar ,

[0121] The calculation formula for the steel bar corrosion rate is:

[0122] ;

[0123] In the formula, is the steel bar corrosion rate, is the length of the corroded steel bar, is the corrosion diameter.

[0124] Taking a certain tunnel as an example, the corrosion rate monitoring method for the tunnel lining steel bars of this application is described:

[0125] The length of a certain tunnel is 8624.5 m (average length of the left and right tunnels), the maximum buried depth of the tunnel body is 923.2 m, the gypsum-bearing strata are rich in gypsum minerals, and the tunnel site area is severely eroded by chlorate, resulting in a series of diseases such as corrosion of the lining steel bars, cracking, spalling, surface crystallization, and strength degradation of the concrete. The "diagnosis and treatment" engineering requirements of the tunnel are urgent.

[0126] Based on the actual on-site situation, determine the magnitude of the eccentric load applied during the test , the eccentricity , and the NaCl solution concentration is 3%. To avoid differences in test results from the corrosion of steel bars under natural conditions due to excessive current density, the current density for this test is taken as , the nominal diameter of the corroded steel bar , the target corrosion zone length is . Substituting into the above formula, it can be calculated that when the corrosion test is carried out for 674.4 h (i.e., 28.1 days), the mass corrosion rate of the steel bar can reach or so. During the corrosion period, the current magnitude of each steel bar to be corroded. During the test, the 4 steel bars to be corroded of each component are connected in parallel as anodes and share a DC power supply, and the power supply output current is 1590 mA. The optical fibers are laid within the range consistent with the corrosion zone, with a spacing . After the corrosion is completed, the concrete is damaged, the steel bars are taken out, and the steel bars are intercepted at a spacing for the calculation of the steel bar corrosion rate, and a total of 264 training data are obtained. Some training samples are shown in Table 1.

[0127] Table 1 Training samples

[0128]

[0129] Based on the prediction model of the present application, the above training samples are trained; in addition, some test components for testing are prepared, the actual corrosion rate of the test components is obtained according to the piezoelectric ceramic technology, and then the corrosion rate of the test components is predicted by using the above prediction model. According to the obtained partial actual data and predicted data, the prediction error rate is calculated. As shown in Table 2, the prediction error rate between the partial data prediction and the actual value is generally within 10%, and the average error rate is 5.935%. It can be seen that the above prediction model has good accuracy.

[0130] Table 2 Prediction samples and prediction error rates

[0131]

[0132] Example 2:

[0133] Refer to Figure 3 , this embodiment provides a corrosion test system for tunnel lining steel bars, including:

[0134] The first module 710 is used to construct a prediction model, the weights and biases of the hidden layer of the prediction model are determined by the artificial ecosystem optimization algorithm, and the initial population of the artificial ecosystem optimization algorithm is obtained by cubic mapping;

[0135] The second module 720 is used to obtain training samples and measured strain data; the training samples are obtained from the tests of the corrosion device, and the corrosion device includes a lining component embedded with multiple steel bars, and multiple strain optical fibers are arranged on the surface of the lining component;

[0136] The third module 730 is used to train the prediction model with the training samples to obtain a corrosion rate prediction model, and the training samples include lining strain data and steel bar corrosion rate data;

[0137] The fourth module 740 is used to input the measured strain data into the corrosion rate prediction model to obtain the corrosion rate.

[0138] As an optional implementation manner, the first module 710 includes:

[0139] The first unit 711 is used to sequentially generate at least 20 populations by using cubic mapping. In the cubic mapping process of each population, the information of the first two generated populations is fused according to a preset weight, and the last generated population is used as the target population; the target population is used as the initial population;

[0140] The second unit 712 is used to iteratively update the roles of individuals starting from the initial population; in each iteration, a cubic mapping is adopted to generate a chaotic sequence, a perturbation value is generated based on the chaotic sequence mapping, the individual positions are perturbed according to the perturbation value, and when the maximum number of iterations is reached or the convergence condition is satisfied, the iteration is stopped to obtain the optimal values of the hidden layer weights and biases.

[0141] As an alternative implementation, the second unit 712 includes:

[0142] The first subunit 713 is used to update producers, consumers, and decomposers according to the predation relationship between roles and the energy levels of roles;

[0143] The second subunit 714 is used to modify the hidden layer weights and biases of the prediction model according to the roles obtained in each round of update, and input the test set into the prediction model to obtain the classification accuracy corresponding to each role;

[0144] The third subunit 715 is used to update the classification accuracy as the energy levels of each role to the population, perform iterative calculations, stop the iteration when the maximum number of iterations is reached or the convergence condition is satisfied, output the optimal solution of the decomposer, and obtain the optimal values of the hidden layer weights and biases.

[0145] As an alternative implementation, the rust test system further includes:

[0146] The fifth module 750 is used to obtain the strain data of multiple points on the surfaces of multiple lining members, construct multiple surface strain matrices, calculate the differences between adjacent elements to construct a distribution gradient matrix, and convert the distribution gradient matrix into a first heat map;

[0147] The sixth module 760 is used to obtain the strain data of multiple points on the to-be-tested lining, construct the measured gradient matrix of the to-be-tested lining and convert it into a second heat map;

[0148] The seventh module 770 is used to update the training weights of the strain data corresponding to the first heat map based on the similarity between the second heat map and each first heat map;

[0149] The eighth module 780 is used to train the prediction model with the strain data whose training weights have been updated to obtain an updated prediction model.

[0150] As described above, the above are only the specific implementation manners of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for monitoring the corrosion rate of tunnel lining steel bars, characterized in that: include: Constructing a prediction model, wherein the hidden layer weights and biases of the prediction model are determined by an artificial ecosystem optimization algorithm, and the initial population of the artificial ecosystem optimization algorithm is obtained by cubic mapping; Acquire training samples and measured strain data; the training samples are obtained by a corrosion device test, the corrosion device includes a lining component in which a plurality of steel bars are buried, and a plurality of strain optical fibers are arranged on the surface of the lining component; The prediction model is trained by training samples to obtain a corrosion rate prediction model, wherein the training samples include lining strain data and steel bar corrosion rate data; The measured strain data is input into the corrosion rate prediction model to obtain the corrosion rate; The method further comprises: Acquire strain data of multiple points on the surfaces of multiple lining components, construct multiple surface strain matrices, calculate the difference between adjacent elements to construct a distribution gradient matrix, and convert the distribution gradient matrix into a first heat map; Acquire strain data of multiple points on the lining to be tested, construct a measured gradient matrix of the lining to be tested and convert it into a second heat map; updating training weights for strain data corresponding to the first heat map based on a similarity between the second heat map and each of the first heat maps; The prediction model is trained using the strain data with updated training weights to obtain an updated prediction model.

2. The method for monitoring the corrosion rate of tunnel lining steel bars according to claim 1, characterized in that: The constructing of the prediction model comprises: At least 20 populations are generated in sequence by using cubic mapping, and during the cubic mapping process of each population generation, information of the first two generated populations is fused according to a preset weight, and the last generated population is used as the target population; and the target population is used as the initial population; Iteratively update the roles of individuals starting from the initial population; in each iteration, a chaotic sequence is generated by using a cubic mapping, a disturbance value is generated based on the chaotic sequence mapping, and the individual position is disturbed according to the disturbance value. When the maximum number of iterations is reached or the convergence condition is met, the iteration is stopped to obtain the optimal values ​​of the hidden layer weights and biases.

3. The method for monitoring the corrosion rate of tunnel lining steel bars according to claim 2, characterized in that: Iteratively updating the roles of individuals starting from the initial population includes: Producers, consumers, and decomposers are updated based on the predator-prey relationships between roles and the energy levels of the roles; The hidden layer weights and biases of the prediction model are modified according to the roles obtained in each round of updates, and the test set is input into the prediction model to obtain the classification accuracy corresponding to each role; The classification accuracy is used as the energy level of each role to update the population, and iterative calculation is performed. When the maximum number of iterations is reached or the convergence condition is met, the iteration is stopped, the optimal solution of the decomposer is output, and the optimal values ​​of the hidden layer weights and biases are obtained.

4. The method for monitoring the corrosion rate of tunnel lining steel bars according to claim 1, characterized in that: Obtain strain data of multiple points on the lining to be tested and construct the measured strain matrix of the lining to be tested, including: Calculating the mean of the strain data of the lining component to obtain a first mean; Calculate the mean of the strain data of the lining to be tested to obtain a second mean; Scaling the strain data of the lining to be measured according to the ratio of the first mean value to the second mean value to obtain processed data; A measured strain matrix of the lining to be measured is constructed based on the processed data.

5. The method for monitoring the corrosion rate of tunnel lining steel bars according to claim 1, characterized in that: The method for obtaining the lining strain data and the steel bar corrosion rate data comprises: Get the preset corrosion rate; Calculating the corrosion duration based on the preset corrosion rate and test parameters; The steel bars are corroded according to the test parameters and corrosion duration, and the lining strain data generated during and after the corrosion process is measured by strain optical fiber; After the corrosion is complete, the corroded steel bars are taken out, and multiple sections of the corroded steel bars are cut at the same length as the spacing of the strain optical fiber layout, and the cross-sectional diameter of each section of the corroded steel bars is measured; The steel bar corrosion rate data is calculated based on the cross-sectional diameter and length of the corroded steel bar.

6. A tunnel lining steel corrosion testing system, characterized in that: include: The first module is used to construct a prediction model, wherein the hidden layer weights and biases of the prediction model are determined by an artificial ecosystem optimization algorithm, and the initial population of the artificial ecosystem optimization algorithm is obtained by cubic mapping; The second module is used to obtain training samples and measured strain data; The training samples are obtained from a corrosion device test, wherein the corrosion device includes a lining component in which a plurality of steel bars are buried, and a plurality of strain optical fibers are arranged on the surface of the lining component; The third module is used to train the prediction model through training samples to obtain a corrosion rate prediction model, wherein the training samples include lining strain data and steel corrosion rate data; The fourth module is used to input the measured strain data into the corrosion rate prediction model to obtain the corrosion rate; The system further comprises: The fifth module is used to obtain strain data of multiple points on the surface of multiple lining components, construct multiple surface strain matrices, calculate the difference between adjacent elements to construct a distribution gradient matrix, and convert the distribution gradient matrix into a first heat map; The sixth module is used to obtain strain data of multiple points on the lining to be tested, construct a measured gradient matrix of the lining to be tested and convert it into a second thermal map; A seventh module, configured to update training weights for strain data corresponding to the first heat map based on a similarity between the second heat map and each of the first heat maps; The eighth module is used to train the prediction model using the strain data with updated training weights to obtain an updated prediction model.

7. A tunnel lining steel bar corrosion testing system according to claim 6, characterized in that: The first module includes: The first unit is used to sequentially generate at least 20 populations by using cubic mapping, and in the cubic mapping process of each population generation, information of the first two generated populations is fused according to a preset weight, and the last generated population is used as the target population; and the target population is used as the initial population; The second unit is used to iteratively update the role of the individual starting from the initial population; in each iteration, a cubic mapping is used to generate a chaotic sequence, a disturbance value is generated based on the chaotic sequence mapping, and the individual position is disturbed according to the disturbance value. When the maximum number of iterations is reached or the convergence condition is met, the iteration is stopped to obtain the optimal value of the hidden layer weight and bias.

8. A tunnel lining steel bar corrosion testing system according to claim 7, characterized in that: The second unit comprises: The first subunit is used to update producers, consumers and decomposers according to the predator-prey relationship between roles and the energy level of roles; The second subunit is used to modify the hidden layer weights and biases of the prediction model according to the roles obtained in each round of updates, and input the test set into the prediction model to obtain the classification accuracy corresponding to each role; The third subunit is used to update the classification accuracy as the energy level of each role to the population, perform iterative calculation, and stop the iteration when the maximum number of iterations is reached or the convergence condition is met, output the optimal solution of the decomposer, and obtain the optimal values ​​of the hidden layer weights and biases.

Images