A shield tunnel monitoring sensor maintenance and replacement method, device, electronic equipment and storage medium

Abstract

The present invention provides a shield tunnel monitoring sensor maintenance and replacement method, device, electronic device and storage medium, including converting the old sensor maintenance and replacement problem into a mathematical model, initializing all algorithm parameters; using the MOSAO algorithm for preliminary solution, and using the result as the initial population P0 of the SPEA‑II algorithm and the external archive #imgabs0# to iteratively calculate the fitness F(i) of all population individuals, and using SPEA‑II to search and update the external archive, update the mating pool, and update the population individuals to form a new population; until the set number of iterations is reached, the search is stopped, the Pareto front in the external archive is output, and converted into a corresponding sensor maintenance and update plan. The present invention adopts the above-mentioned shield tunnel monitoring sensor maintenance and replacement method, device, electronic device and storage medium, solves the problem of replacing old sensors, solves the specific layout of newly installed sensors, and effectively improves the search efficiency.

Description

Technical Field

[0001] The invention relates to the field of shield tunnel structure monitoring, and in particular to a shield tunnel monitoring sensor maintenance and replacement method, device, electronic equipment and storage medium. Background Art

[0002] In the structural health monitoring of shield tunnels, as the tunnel is put into operation, a large number of FBG sensors will be arranged at key sections for health monitoring in the early stage of shield tunnel health monitoring. However, after the tunnel is put into long-term use, the monitoring sensors need to be replaced. In order to reduce the monitoring cost, it is no longer necessary to install sensors at all locations. Based on historical monitoring data, the key locations that need maintenance and replacement are selected, and new sensors are installed. Most of these tasks are performed by engineers according to subjective engineering experience, without a reliable theoretical basis, resulting in inaccurate measurement results that cannot meet the structural morphology perception accuracy and speed required by modern tunnel maintenance work. To solve this problem, this patent proposes a maintenance and replacement method to determine the location where the sensor needs to be reinstalled.

[0003] In order to control the monitoring accuracy and installation cost at the same time, it is defined as a multi-objective optimization problem. By comparing the solution results of traditional multi-objective optimization technology, it is found that the robustness of general algorithms is poor in the face of special problems, and it is necessary to study methods suitable for this problem. This patent proposes a new multi-objective optimization method to solve the problem of replacing old sensors. This method optimizes the search speed of SPEA-II and the search stability of MOSAO. First, the initial solution is obtained by searching with MOSAO, and then SPEA-II is used for search, which effectively improves the search efficiency. Finally, it provides a solution for the maintenance and update of shield tunnel monitoring sensors. Summary of the invention

[0004] The purpose of the present invention is to provide a shield tunnel monitoring sensor maintenance and replacement method, device, electronic equipment and storage medium, which solves the problem of replacing old sensors and solves the specific layout of new sensors. The method optimizes the search speed of the (Strength Pareto Evolutionary Algorithm) SPEA-II method and the search stability of the (Multi-objective SnowAblation Optimization algorithm) MOSAO method. First, the initial Pareto frontier is obtained by using MOSAO search as the initial population and external archives of SPEA-II, and then SPEA-II is used for search. Finally, a solution is provided for the maintenance and update of shield tunnel monitoring sensors, which effectively improves the search efficiency.

[0005] To achieve the above-mentioned purpose, the present invention provides a shield tunnel monitoring sensor maintenance and replacement method, including constructing a problem data set based on historical monitoring data of a tunnel health monitoring system, converting the old sensor maintenance and update problem into a mathematical model, and initializing all algorithm parameters; the historical monitoring data includes historical strain monitoring data of the section where the sensor needs to be replaced;

[0006] The MOSAO algorithm is used for preliminary solution, and the result is used as the initial population P0 of SPEA-II and external archive

[0007] Iteratively calculate the fitness F(i) of all individuals in the population, and use SPEA-II to search and update the external archive, update the mating pool, and update the individuals in the population to form a new population; stop the search after reaching the set number of iterations, output the Pareto frontier in the external archive, and convert it into the corresponding sensor maintenance update plan.

[0008] Preferably, the maintenance and update problem of old sensors is transformed into a mathematical model, including: after removing all sensors, it is necessary to determine the location where new sensors need to be reinstalled among the original sensor locations, and define each solution as a binary number, "1" and "0"

[0009] They represent installation or not respectively, and the decimal solution range of the replacement plan is obtained.

[0010] Preferably, all parameters of the initialization algorithm include the initialization population size N, the external archive size, the MOSAO iteration number N1, the SPEA-II iteration number N2, and the solution space range.

[0011] Preferably, the fitness F(i) of all individuals in the population is calculated, including

[0012] F(i)=R(i)+D(i) (1)

[0013]

[0014] in, is the Euclidean distance between the i-th individual and the k-th nearest neighbor in the target space, P t is the t-th generation population, is the external archive of the tth generation, R(i) represents the rough fitness value of the ith individual, which means the sum of the number of individuals dominated by all individuals j that dominate individual i in the evolutionary population and the external population, where S(i) represents the strength value of the ith individual, which means the sum of the number of individuals dominated by individual i in the evolutionary population and the external population. D(i) is the density function corresponding to the ith individual.

[0015] Preferably, the updating of the external archive includes comparing all current individuals with the external archive and updating the archive. When the number exceeds the archive capacity, pruning is performed through clustering operations, and the individuals with the smallest nearest neighbor distances are removed one by one.

[0016] Preferably, the mating pool is updated: the tournament size is k, k individuals are randomly selected from the external archive, the individual with the best fitness value is selected from the k individuals, and added to the mating pool, and the tournament rules are repeatedly used to update the mating pool until the mating pool size reaches N.

[0017] Preferably, the updating of population individuals: when performing a crossover operation, two parent individuals are randomly selected from the mating pool, a crossover point is randomly selected, and the parts of the two parent individuals after the crossover point are exchanged to generate two new offspring individuals;

[0018] When performing a mutation operation, each gene in each individual is mutated with a set mutation probability, and the gene is modified to a new random value;

[0019] Merge the two parts of new individuals and randomly select N individuals to form a new population.

[0020] A shield tunnel monitoring sensor maintenance and replacement device, comprising:

[0021] The data acquisition module is used to construct a problem dataset based on the historical monitoring data of the tunnel health monitoring system;

[0022] The model conversion module is used to convert the problem of better maintenance of old sensors into a mathematical model;

[0023] The parameter initialization module is used to initialize the population size N, the external file size, the MOSAO iteration number N1, the SPEA-II iteration number N2, and the solution space range;

[0024] The population initialization module is used to perform preliminary solutions using the MOSAO algorithm. The results are used as the initial population P0 of SPEA-II and external archives.

[0025] The new population formation module is used to iteratively calculate the fitness F(i) of all population individuals, and use SPEA-II to search and update external archives, mating pools, and population individuals to form a new population;

[0026] The scheme output module is used to stop the search after reaching the set number of iterations, output the Pareto frontier in the external archive, and convert it into the corresponding sensor maintenance update scheme.

[0027] An electronic device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the processor implements the steps of a shield tunnel monitoring sensor maintenance and replacement method.

[0028] A storage medium stores computer executable instructions, which, when loaded and executed by a processor, implement the steps of a shield tunnel monitoring sensor maintenance and replacement method.

[0029] Therefore, the present invention adopts the above-mentioned shield tunnel monitoring sensor maintenance and replacement method, device, electronic device and storage medium, and the technical effects are as follows:

[0030] (1) The algorithm proposed in this patent effectively solves the maintenance and replacement problem of FBG sensor elements in the shield tunnel monitoring section, and provides theoretical support for structural health monitoring. The Pareto frontier of the problem can be obtained through algorithm solution, providing a more comprehensive and optimized solution, and effectively improving the accuracy and reliability of the monitoring system.

[0031] (2) This method takes into account the trade-off between monitoring performance and cost. By optimizing the sensor layout, it can reduce the cost of maintenance and update while ensuring the monitoring accuracy of the monitoring system.

[0032] (3) By combining the advantages of the two optimization algorithms, this method can effectively improve the search efficiency and stability, find better solutions, and complete the search process in a shorter time.

[0033] (4) Experiments show that the new method SPEA-III saves 66% of computing time compared to the original SPEA-II. In the calculation results, the new scheme uses 17 sensors, the installation cost is reduced by 32%, and the decimal solution of the sensor replacement scheme is '13575402'. The root mean square error of the reconstruction of the new scheme in the simulation experiment data set is less than 11.61, the average accuracy is above 95.15%, the minimum accuracy is above 83.24%, and the minimum goodness of fit is 0.9946. Even in the prototype experiment, its average accuracy is above 93.86%. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flowchart of a shield tunnel monitoring sensor maintenance and replacement method according to the present invention;

[0035] Figure 2 A schematic diagram of a shield tunnel monitoring sensor maintenance and replacement device according to the present invention;

[0036] Figure 3 For the original sensor layout;

[0037] Figure 4 A replacement solution for output. DETAILED DESCRIPTION

[0038] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0039] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0040] Embodiment 1

[0041] like Figure 1 As shown, the present invention provides a shield tunnel monitoring sensor maintenance and replacement method, comprising:

[0042] Based on the historical monitoring data of the tunnel health monitoring system, a dataset of the problem is constructed. The historical monitoring data includes the historical strain monitoring data of the sections where sensors need to be replaced.

[0043] The maintenance and update problem of old sensors is transformed into a mathematical model: After all sensors are removed, it is necessary to determine the positions of the original 28 sensors where new sensors need to be reinstalled. Each solution can be defined as a 28-bit binary number, "1" and "0" represent whether the sensor is installed or not, so the decimal solution range of the replacement solution is [0,228-1], such as Figure 3 shown.

[0044] Initialize all algorithm parameters: set the population size to N = 100, the maximum number of iterations for MOSAO and SPEA-II to N1 = 700 and N2 = 300 respectively, and the external archive capacity to 30.

[0045] The MOSAO algorithm is used for preliminary solution, and the result is used as the initial population P0 of SPEA-II and external archive Complete population initialization.

[0046] Iteratively calculate the fitness F(i) of all individuals in the population, and use SPEA-II search to update the external archive, update the mating pool, and update the population individuals to form a new population.

[0047] Calculate the fitness F(i) of all initial individuals, including

[0048] F(i)=R(i)+D(i) (1)

[0049]

[0050] in, is the Euclidean distance between the i-th individual and the k-th nearest neighbor in the target space, P tis the t-th generation population, is the external archive of the tth generation, R(i) represents the rough fitness value of the ith individual, which means the sum of the number of individuals dominated by all individuals j that dominate individual i in the evolutionary population and the external population, where S(i) represents the strength value of the ith individual, which means the sum of the number of individuals dominated by individual i in the evolutionary population and the external population. D(i) is the density function corresponding to the ith individual.

[0051] Updating the external archive includes comparing all current individuals with the external archive for non-dominance and updating the archive When the number exceeds the archive capacity, pruning is performed through clustering operations, and the individuals with the smallest nearest neighbor distances are removed one by one.

[0052] Update the mating pool: The tournament size is k, k individuals are randomly selected from the external archive, the individual with the best fitness value is selected from these k individuals, added to the mating pool, and the tournament rules are repeatedly used to update the mating pool until the mating pool size reaches N.

[0053] Update population individuals: When performing a crossover operation, randomly select two parent individuals from the mating pool, randomly select a crossover point, exchange the parts of the two parent individuals after the crossover point, and generate two new offspring individuals;

[0054] When performing a mutation operation, each gene in each individual is mutated with a set mutation probability, and the gene is modified to a new random value;

[0055] Merge the two parts of new individuals and randomly select N individuals to form a new population.

[0056] The search stops when the set number of iterations is reached: when the number of iterations is greater than N2, it means that the termination condition is met and the search stops; otherwise, the number of iterations increases by 1 and the above iterative calculation continues.

[0057] Output the Pareto frontier in the external archive and convert it into the corresponding sensor maintenance and update plan. By analyzing all Pareto solutions, the optimal layout of 17 sensors is used to replace the old sensors. The decimal solution is '13575402'. The results are as follows Figure 4 shown.

[0058] like Figure 2 As shown, a shield tunnel monitoring sensor maintenance and replacement device comprises

[0059] The data acquisition module is used to construct a problem dataset based on the historical monitoring data of the tunnel health monitoring system;

[0060] The model conversion module is used to convert the maintenance and update problems of old sensors into mathematical models;

[0061] The parameter initialization module is used to initialize the population size N, the external file size, the MOSAO iteration number N1, the SPEA-II iteration number N2, and the solution space range;

[0062] The population initialization module is used to perform preliminary solutions using the MOSAO algorithm. The results are used as the initial population P0 of SPEA-II and external archives.

[0063] The new population formation module is used to iteratively calculate the fitness F(i) of all population individuals, and use SPEA-II to search and update external archives, mating pools, and population individuals to form a new population;

[0064] The scheme output module is used to stop the search after reaching the set number of iterations, output the Pareto frontier in the external archive, and convert it into the corresponding sensor maintenance update scheme.

[0065] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, which will not be repeated here.

[0066] The present application also provides a storage medium on which a computer program is stored, and when the computer program is executed, the steps provided in the above embodiment can be implemented. The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0067] The present application also provides an electronic device, which may include a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps provided in the above embodiment may be implemented. Of course, the electronic device may also include various network interfaces, power supplies and other components.

[0068] Therefore, the present invention adopts the above-mentioned shield tunnel monitoring sensor maintenance and replacement method, device, electronic equipment and storage medium to solve the problem of replacing old sensors and solve the specific layout of new sensors. The method optimizes the search speed of the SPEA-II method and the search stability of the MOSAO method. First, the initial Pareto frontier is obtained by using MOSAO search as the initial population and external archives of SPEA-II, and then SPEA-II is used for search. Finally, a solution is provided for the maintenance and update of shield tunnel monitoring sensors, effectively improving the search efficiency.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A shield tunnel monitoring sensor maintenance and replacement method, characterized in that: include: Based on the historical monitoring data of the tunnel health monitoring system, a data set of the problem is constructed, the maintenance and replacement problem of old sensors is converted into a mathematical model, and all parameters of the algorithm are initialized; the historical monitoring data includes the historical strain monitoring data of the section where the sensor needs to be replaced; The MOSAO algorithm is used for preliminary solution, and the result is used as the initial population P0 of SPEA-II and external archive Iteratively calculate the fitness F(i) of all individuals in the population, and use SPEA-II to search and update the external archive, update the mating pool, and update the individuals in the population to form a new population; stop the search after reaching the set number of iterations, output the Pareto frontier in the external archive, and convert it into the corresponding sensor maintenance update plan.

2. A shield tunnel monitoring sensor maintenance and replacement method according to claim 1, characterized in that: The maintenance and replacement problem of old sensors is converted into a mathematical model, including: after removing all sensors, it is necessary to determine the positions of the original sensors where new sensors need to be reinstalled. Each solution is defined as a binary number, "1" and "0" represent whether they are installed or not, respectively, and the decimal solution range of the replacement solution is obtained.

3. A shield tunnel monitoring sensor maintenance and replacement method according to claim 1, characterized in that: All parameters of the initialization algorithm include the initialization population size N, the external file size, the number of MOSAO iterations N1, the number of SPEA-II iterations N2, and the solution space range.

4. A shield tunnel monitoring sensor maintenance and replacement method according to claim 1, characterized in that: Calculate the fitness F(i) of all individuals in the population, including F(i)=R(i)+D(i) (1) in, is the Euclidean distance between the i-th individual and the k-th nearest neighbor in the target space, P t is the t-th generation population, is the external archive of the tth generation, R(i) represents the rough fitness value of the ith individual, which means the sum of the number of other individuals dominated by all individuals j that dominate individual i in the evolutionary population and the external population, where S(i) represents the strength value of the ith individual, which means the sum of the number of individuals dominated by individual i in the evolutionary population and the external population, and D(i) is the density function corresponding to the ith individual.

5. A shield tunnel monitoring sensor maintenance and replacement method according to claim 4, characterized in that: The updating of the external archive includes comparing all current individuals with the external archive for non-dominance and updating the archive. When the number exceeds the archive capacity, pruning is performed through clustering operations, and the individuals with the smallest nearest neighbor distances are removed one by one.

6. A shield tunnel monitoring sensor maintenance and replacement method according to claim 5, characterized in that: The mating pool is updated as follows: the tournament size is k, k individuals are randomly selected from the external archive, the individual with the best fitness value is selected from the k individuals, and added to the mating pool, and the tournament rules are repeatedly used to update the mating pool until the mating pool size reaches N.

7. A shield tunnel monitoring sensor maintenance and replacement method according to claim 6, characterized in that: The updating of population individuals: when performing a crossover operation, two parent individuals are randomly selected from the mating pool, a crossover point is randomly selected, and the parts of the two parent individuals after the crossover point are exchanged to generate two new offspring individuals; When performing a mutation operation, each gene in each individual is mutated with a set mutation probability, and the gene is modified to a new random value; Merge the two parts of new individuals and randomly select N individuals to form a new population.

8. A shield tunnel monitoring sensor maintenance and replacement device, characterized in that: A data acquisition module is included for constructing a problem data set, where the problem data set is based on historical monitoring data of a tunnel health monitoring system; The model conversion module is used to convert the maintenance and replacement problem of old sensors into a mathematical model; The parameter initialization module is used to initialize the population size N, the external file size, the number of MOSAO iterations N1, the number of SPEA-II iterations N2, and the solution space range; The population initialization module is used to perform preliminary solutions using the MOSAO algorithm. The results are used as the initial population P0 of SPEA-II and external archives. The new population formation module is used to iteratively calculate the fitness F(i) of all population individuals, and use SPEA-II to search and update external archives, mating pools, and population individuals to form a new population; The scheme output module is used to stop the search after reaching the set number of iterations, output the Pareto frontier in the external archive, and convert it into the corresponding sensor maintenance update scheme.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, it implements the steps of a shield tunnel monitoring sensor maintenance and replacement method as claimed in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores computer executable instructions, which, when loaded and executed by a processor, implement the steps of a shield tunnel monitoring sensor maintenance and replacement method as described in any one of claims 1 to 7.

Images