Method, system and storage medium for making mid- to long-term maintenance decisions for bridge groups

Abstract

The present invention discloses a method, system and storage medium for making mid- and long-term maintenance decisions for a bridge group. The method first obtains the annual technical condition historical scores of each bridge from the database of the road network bridge group, and determines the actual performance influencing factors of the bridge; then establishes a fuzzy neural network model, takes the parameters corresponding to the actual performance influencing factors as input, and takes the annual technical condition historical scores as label output, trains the model accordingly, and obtains the corresponding bridge performance prediction model after passing the test; uses each bridge performance prediction model to obtain the annual technical condition prediction score of each bridge within a set period in the future; obtains the performance improvement benefits of the bridge under unit maintenance expenditure cost based on the maintenance record of the bridge; finally, establishes a decision generation model based on the multi-objective raccoon optimization algorithm, and outputs the mid- and long-term maintenance decision of the bridge group. The present invention can intelligently provide scientific and reliable mid- and long-term maintenance decisions for bridge groups.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge maintenance, and in particular to a method, system and storage medium for making mid- to long-term maintenance decisions for a bridge group. Background Art

[0002] The maintenance work of road network bridge groups is to repair bridges with existing problems. Since the funds for bridge maintenance are limited, it is necessary to make bridge maintenance decisions, reasonably allocate and use limited funds, ensure that the bridge group is at the prescribed service level, and make the best use of the maintenance funds.

[0003] For multiple bridges in a bridge group, they are usually prioritized according to factors such as their importance, risk level, and maintenance cost, and those bridges that have the greatest impact on traffic and safety are prioritized to generate maintenance decisions. However, this decision-making method faces some challenges: on the one hand, it relies on expert opinions, has poor real-time performance, and requires a lot of manpower to manually analyze monitoring and detection data, lacks efficient automatic means, and has a low degree of digitization and intelligence; on the other hand, it can only select high-importance bridges as maintenance objects in the short term, and cannot generate scientific and reliable maintenance decisions in the medium and long term.

[0004] In summary, how to intelligently provide scientific and reliable mid- and long-term maintenance decisions for bridge groups is an urgent problem to be solved in the field of bridge maintenance technology. Summary of the invention

[0005] In order to solve the technical problems existing in the prior art, the present invention provides a method, system and storage medium for making mid- to long-term maintenance decisions for bridge groups. The present invention can intelligently provide scientific and reliable mid- to long-term maintenance decisions for bridge groups.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The present invention discloses a method for making medium- to long-term maintenance decisions for a bridge group, comprising the following steps, namely S1 to S5.

[0008] S1. Obtain the annual technical condition historical score of each bridge from the database of the road network bridge group, and determine the actual performance influencing factors of the bridge; the parameters corresponding to the actual performance influencing factors include basic bridge information and meteorological data.

[0009] S2. Establish a fuzzy neural network model, take the parameters corresponding to the actual performance influencing factors of each bridge as input, and take the annual technical condition historical score of each bridge as label output, train the fuzzy neural network model accordingly and obtain the bridge performance prediction model after passing the test.

[0010] S3. Using the bridge performance prediction model, basic bridge information and a time limit set in the future, N Simulated meteorological data in the past year to obtain the future N Annual technical condition forecast score for the year.

[0011] S4. Based on the repair and maintenance records of bridges, obtain the performance improvement benefits of each bridge at unit maintenance expenditure cost.

[0012] S5. Establish a decision generation model based on the multi-objective raccoon optimization algorithm, taking the annual technical condition prediction score of each bridge within a set period in the future and the performance improvement benefit of each bridge under unit maintenance expenditure cost as input, and taking the lowest total maintenance expenditure cost and the highest total technical condition score of the road network bridge group as double constraints, so as to output the medium- and long-term maintenance decision of the bridge group, which includes the maintenance time nodes and the maintenance bridge objects.

[0013] As a further improvement of the above solution, step S5 includes the following specific steps, namely S51~S52.

[0014] S51. Establish the initialization state of the annual technical condition prediction score of the road network bridge group, and then perform random initialization allocation of the maintenance expenditure cost to obtain the initialization population of the state space.

[0015] S52. Based on the initialization population and state navigation method of the state space, the state space is navigated, with the goal of minimizing the total maintenance expenditure cost of the road network bridge group and maximizing the total technical condition score, and adding the annual technical condition score of the bridge not less than a preset lower limit as the overall constraint of the multi-objective raccoon optimization algorithm.

[0016] As a further improvement of the above solution, the value range of the annual technical condition score of the bridge is [0,100]; the preset lower limit value is 60.

[0017] As a further improvement of the above solution, in step S1, the previous appearance inspection scores of the bridge are obtained from the database and the scores are used as labels for the annual technical condition history scores.

[0018] As a further improvement of the above solution, in step S1, the method for determining the factors affecting the actual performance of the bridge includes the following specific steps, namely S11 to S14.

[0019] S11. Obtain the current basic information of the bridge, including bridge age, span and bridge type;

[0020] S12. Obtain historical meteorological information of the bridge, including extreme temperature, extreme humidity, number of frost days, and number of rain and snow days;

[0021] S13. Take the various parameters of the current basic information and the historical meteorological information as separate specific performance influencing factors, and calculate the correlation coefficient between each specific performance influencing factor and the annual technical status historical score r :

[0022] ;

[0023] In the formula, X i’ and Y i’ Respectively expressed in i’ Parameter values ​​corresponding to specific performance influencing factors of group data and annual technical status historical score values; and They represent the average values ​​of parameters corresponding to specific performance influencing factors and the average values ​​of annual technical status historical scores respectively; n Indicates the data dimension, n ≥30;

[0024] S14. Select a correlation coefficient that is greater than a preset coefficient threshold, and use the specific performance influencing factor corresponding to the correlation coefficient as the actual performance influencing factor of the bridge.

[0025] As a further improvement of the above solution, in step S2, the fuzzy neural network model is established based on the Mamdani fuzzy neural network.

[0026] As a further improvement of the above solution, in step S3, the future set period is 20 years, that is, N =20.

[0027] The present invention also discloses a system for making mid- to long-term maintenance decisions for bridge groups, which applies the above-mentioned method for making mid- to long-term maintenance decisions for bridge groups; the system comprises: a data acquisition module, a prediction module, a benefit acquisition module and a decision generation module.

[0028] The data acquisition module is used to obtain the annual technical condition historical score of each bridge from the database of the road network bridge group and determine the actual performance influencing factors of the bridge; the parameters corresponding to the actual performance influencing factors include basic bridge information and meteorological data.

[0029] The prediction module is used to establish a fuzzy neural network model, taking the parameters corresponding to the actual performance influencing factors of each bridge as input, and taking the annual technical condition historical score of each bridge as label output, based on which the fuzzy neural network model is trained and a bridge performance prediction model is obtained after the test is qualified; the prediction module is also used to use the bridge performance prediction model, the basic information of the bridge, and the future set time limit, that is, N Simulated meteorological data in the past year to obtain the futureN Annual technical condition forecast score for the year.

[0030] The benefit acquisition module is used to obtain the performance improvement benefits of each bridge at unit maintenance expenditure cost based on the repair and maintenance records of the bridges.

[0031] The decision generation module is used to establish a decision generation model based on the multi-objective raccoon optimization algorithm. It takes the annual technical condition prediction score of each bridge within a set period in the future and the performance improvement benefit of each bridge under unit maintenance expenditure cost as input, and takes the lowest total maintenance expenditure cost and the highest total technical condition score of the road network bridge group as double constraints, thereby outputting the medium- and long-term maintenance decision of the bridge group, which includes the maintenance time nodes and the bridge objects to be maintained.

[0032] The present invention also discloses a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the above-mentioned method for making decisions on long-term maintenance of bridge groups are implemented.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. The method for making mid- and long-term maintenance decisions for bridge groups disclosed in the present invention obtains the historical scores of the annual technical conditions of the road network bridges and defines the factors that affect the performance of the bridges, thereby quantifying the input parameters of the bridge performance prediction model, and further exerts the powerful performance prediction advantages under the coupling of multiple factors based on the fuzzy neural network to achieve accurate prediction of the mid- and long-term technical conditions of the bridges. On this basis, the multi-objective raccoon optimization algorithm is used to seek the optimization of maintenance decisions in the state space of multiple constraints and multiple variables, and scientific and reliable maintenance decisions are obtained intelligently, providing strong strategic support for the mid- and long-term maintenance of the current road network bridges, so that appropriate maintenance objects and maintenance time points can be selected in the future mid- and long-term, and limited funds can be reasonably allocated and used to ensure that the bridge group is at the prescribed service level, so that the maintenance and repair funds can play the best benefits.

[0035] 2. The system for making decisions on long-term maintenance of bridge groups and the computer-readable storage medium disclosed in the present invention can produce the same beneficial effects as the above method by applying the above method, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of a method for making mid- to long-term maintenance decisions for a bridge group in Example 1 of the present invention.

[0037] Figure 2 This is a framework diagram of the system for making mid- to long-term maintenance decisions for bridge groups in Example 2 of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Example 1

[0040] See also Figure 1 , this embodiment provides a method for making long-term maintenance decisions for a bridge group, including the following steps, namely S1~S5.

[0041] S1. Obtain the annual technical condition historical scores of each bridge from the database of the road network bridge group, and determine the actual performance influencing factors of the bridge. The parameters corresponding to the actual performance influencing factors include basic bridge information and meteorological data.

[0042] In this embodiment, the value interval of the annual technical condition score of the bridge can be [0,100]. The score of the bridge's appearance inspections can be obtained from the database and used as a label for the annual technical condition history score. It should be noted that the bridge is regularly inspected no more than 3 years / time, generally 2 years / time. In some embodiments, the annual traffic volume data of the bridge is also obtained. Taking a prestressed concrete continuous beam bridge in a certain place as an example, the historical scores of the bridge's technical condition corresponding to the past 5 years are shown in Table 1.

[0043] Table 1: Historical ratings of annual technical conditions of bridges

[0044] ;

[0045] The method for determining the factors affecting the actual performance of the bridge includes the following specific steps, namely S11~S14.

[0046] S11. Obtain the current basic information of the bridge; the basic information includes the age of the bridge, the span and the bridge type. For example, taking the above-mentioned prestressed concrete continuous beam bridge as an example, its basic information is shown in Table 2.

[0047] Table 2: Basic information of bridges

[0048] ;

[0049] S12. Obtain historical meteorological information of the bridge; the historical meteorological information includes parameters such as temperature extremes, humidity extremes, number of frost days, and number of rainy and snowy days.

[0050] S13. Take the various parameters of the current basic information and the historical meteorological information as separate specific performance influencing factors, and calculate the correlation coefficient between each specific performance influencing factor and the annual technical status historical score r :

[0051] ;

[0052] In the formula, X i’ and Y i’ Respectively expressed in i’ Parameter values ​​corresponding to specific performance influencing factors of group data and annual technical status historical score values; and They represent the average values ​​of parameters corresponding to specific performance influencing factors and the average values ​​of annual technical status historical scores respectively; n Indicates the data dimension, n ≥30.

[0053] S14. Select a correlation coefficient that is greater than a preset coefficient threshold, and use the specific performance influencing factor corresponding to the correlation coefficient as the actual performance influencing factor of the bridge.

[0054] S2. Establish a fuzzy neural network model, take the parameters corresponding to the actual performance influencing factors of each bridge as input, and take the annual technical condition historical score of each bridge as label output, train the fuzzy neural network model accordingly and obtain the bridge performance prediction model after passing the test.

[0055] The fuzzy neural network model is established based on the Mamdani fuzzy neural network. The model consists of 5 layers of neural networks, has a strong nonlinear mapping modeling capability, and has strong resistance to noise and interference. It is suitable for nonlinear mapping modeling of bridges under incomplete parameters and parameter interference. For each bridge, the parameters corresponding to the actual performance influencing factors of the bridge, that is, the original data, are used as the first input of the model, and then the output of the previous layer and the original data are used as the input of the next layer, thereby constructing a deep fuzzy neural network model with multiple hidden layers.

[0056] When the prediction accuracy of the test reaches 95%, the model is saved to obtain the bridge performance prediction model.

[0057] S3. Using the bridge performance prediction model, basic bridge information and a time limit set in the future, N Simulated meteorological data in the past year to obtain the future N Annual technical condition forecast score for the year.

[0058] It should be noted that the bridge age in the basic information of the bridge will change with the years, while the span and bridge type will not change. N When the annual technical condition score is calculated for each year, the bridge age in the basic information of the bridge matches that year. In addition, simulated meteorological data can be obtained by querying historical meteorological data and extracting and simulating the regularity of long and short cycles.

[0059] S4. Based on the repair and maintenance records of bridges, obtain the performance improvement benefits of each bridge at unit maintenance expenditure cost.

[0060] In this embodiment, nonlinear fitting of investment and performance improvement can be performed based on the previous 30 years of maintenance investment and the score increment of the technical condition after maintenance. The function and basic parameters of the nonlinear fitting are determined to obtain the performance improvement coefficient of unit investment under different technical conditions of the bridge as a quantitative representation of the improvement benefit.

[0061] S5. Establish a decision generation model based on the multi-objective raccoon optimization algorithm, taking the annual technical condition prediction score of each bridge within a set period in the future and the performance improvement benefit of each bridge under unit maintenance expenditure cost as input, and taking the lowest total maintenance expenditure cost and the highest total technical condition score of the road network bridge group as double constraints, so as to output the medium- and long-term maintenance decision of the bridge group, which includes the maintenance time nodes and the maintenance bridge objects.

[0062] Step S5 includes the following specific steps, namely S51~S52.

[0063] S51. Establish the initial state of the annual technical condition prediction score of the road network bridge group, and then perform random initialization allocation of the maintenance expenditure cost to obtain the initial population of the state space; wherein, the calculation formula for updating the population state composed of all bridge maintenance parameters is as follows:

[0064] ;

[0065] In the formula, is the individual state of the multi-objective raccoon optimization algorithm, indicating the time node i Bridges j The annual technical status score, is the individual state after the population state is updated; 1< i ≤ N , 1≤ j ≤ M , M is the total number of bridges in the road network bridge group; represents the random update operator used to perform state updates; SW jTo find the optimal upper boundary coefficient, it means that the bridge is not restricted in the maintenance cost. j Annual technical condition rating; To find the optimal lower boundary coefficient, it means at the time node i bridge j Performance improvement benefits per unit maintenance expenditure cost.

[0066] S52. Based on the initialization population of the state space and the state tour method, the state space is toured. The goal is to minimize the total maintenance cost of the road network bridge group and maximize the total technical condition score. The annual technical condition score of the bridge is not less than a preset lower limit (such as 60) as the overall constraint of the multi-objective raccoon optimization algorithm. The tour expression formula of the state space is as follows:

[0067] ;

[0068] ;

[0069] In the formula, Represents the global state of the multi-objective raccoon optimization algorithm after iteration; F i For the time node i The overall constraints of It represents the total technical condition score of the road network bridges after the objective function value is updated; F rand is the objective function value of the individual; is the updated position of the entire individual, i.e., the state after maintenance; X M is the final position after the fitness value is updated, i.e., the medium- and long-term maintenance decision. X M ={ x 1, x 2, x 3,…, x M},in x M Indicates the number M A vector consisting of whether each time history of the bridge is maintained; s is the iterative update rate, which ranges from {0 to 0.2} in decreasing order.

[0070] Example 2

[0071] This embodiment provides a system for making medium- and long-term maintenance decisions for a group of bridges, which can apply the method for making medium- and long-term maintenance decisions for a group of bridges in Example 1. The medium- and long-term maintenance decision-making system 10 for a group of bridges includes: a data acquisition module 101, a prediction module 102, a benefit acquisition module 103 and a decision generation module 104.

[0072] The data acquisition module 101 is used to obtain the annual technical condition historical score of each bridge from the database of the road network bridge group and determine the actual performance influencing factors of the bridge; the parameters corresponding to the actual performance influencing factors include basic bridge information and meteorological data.

[0073] The prediction module 102 is used to establish a fuzzy neural network model, using the parameters corresponding to the actual performance influencing factors of each bridge as input, and using the annual technical condition historical score of each bridge as a label output, and training the fuzzy neural network model accordingly and obtaining a bridge performance prediction model after passing the test; the prediction module is also used to use the bridge performance prediction model, the basic information of the bridge, and the future set time limit, that is, N Simulated meteorological data in the past year to obtain the future N Annual technical condition forecast score for the year.

[0074] The benefit acquisition module 103 is used to acquire the performance improvement benefit of each bridge at a unit maintenance expenditure cost based on the maintenance records of the bridges.

[0075] The decision generation module 104 is used to establish a decision generation model based on the multi-objective raccoon optimization algorithm, taking the annual technical condition prediction score of each bridge within a set period in the future and the performance improvement benefit of each bridge under unit maintenance expenditure cost as input, and taking the lowest total maintenance expenditure cost and the highest total technical condition score of the road network bridge group as double constraints, thereby outputting the medium- and long-term maintenance decision of the bridge group, which includes the maintenance time node and the maintenance bridge object.

[0076] Example 3

[0077] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the method for making long-term maintenance decisions for bridge groups in Embodiment 1 are implemented.

[0078] The storage medium may be a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the storage medium may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the storage medium may also be an external storage device of a computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Of course, the storage medium may also include both an internal storage unit of the computer device and its external storage device. In this embodiment, the memory is generally used to store an operating system and various application software installed on the computer device. In addition, the memory may also be used to temporarily store various types of data that have been output or are to be output.

[0079] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for making mid- to long-term maintenance decisions for bridge groups, characterized in that: The following steps are involved: S1. Obtain the annual technical condition historical score of each bridge from the database of the road network bridge group, and determine the actual performance influencing factors of the bridge; the parameters corresponding to the actual performance influencing factors include basic bridge information and meteorological data; S2. Establish a fuzzy neural network model, take the parameters corresponding to the actual performance influencing factors of each bridge as input, and take the annual technical condition historical score of each bridge as label output, train the fuzzy neural network model accordingly and obtain a bridge performance prediction model after passing the test; S3. Using the bridge performance prediction model, basic bridge information and a time limit set in the future, N Simulated meteorological data in the past year to obtain the future N Annual technical condition forecast score within the year; S4. Based on the maintenance records of the bridges, obtain the performance improvement benefits of each bridge at the unit maintenance expenditure cost; S5. Establish a decision generation model based on the multi-objective raccoon optimization algorithm, take the annual technical condition prediction score of each bridge within a set period in the future and the performance improvement benefit of each bridge under the unit maintenance expenditure cost as input, and take the lowest total maintenance expenditure cost and the highest total technical condition score of the road network bridge group as double constraints, so as to output the medium- and long-term maintenance decision of the bridge group, which includes the maintenance time node and the maintenance bridge object; step S5 includes the following specific steps: S51. Establish the initial state of the annual technical condition prediction score of the road network bridge group, and then perform random initialization allocation of the maintenance expenditure cost to obtain the initialization population of the state space; wherein, the calculation formula for updating the population state composed of all bridge maintenance parameters is as follows: ; In the formula, x i,j is the individual state of the multi-objective raccoon optimization algorithm, indicating the time node i Bridges j The annual technical status score, is the individual state after the population state is updated; 1< i ≤ N , 1≤ j ≤ M , M is the total number of bridges in the road network bridge group; rand i,j represents the random update operator used to perform state updates; SW j To find the optimal upper boundary coefficient, it means that the bridge is not restricted in the maintenance cost. j Annual technical condition rating; I i,j To find the optimal lower boundary coefficient, it means at the time node i bridge j Performance improvement benefits per unit maintenance expenditure cost; S52. Based on the initialization population of the state space and the state tour method, the state space is toured, the goal is to minimize the total maintenance cost of the road network bridge group and maximize the total technical condition score, and add the annual technical condition score of the bridge not less than a preset lower limit as the overall constraint of the multi-objective raccoon optimization algorithm; the tour expression formula of the state space is as follows: ； ； In the formula, Represents the global state of the multi-objective raccoon optimization algorithm after iteration; F i For the time node i The overall constraints of It represents the total technical condition score of the road network bridges after the objective function value is updated; F rand is the objective function value of the individual; is the updated position of the entire individual, i.e., the state after maintenance; X M is the final position after the fitness value is updated, i.e., the medium- and long-term maintenance decision. X M ={ x 1, x 2, x 3,…, x M },in x M Indicates the number M A vector consisting of whether each time history of the bridge is maintained; s is the iterative update rate, which ranges from {0 to 0.2} in decreasing order.

2. The method for making mid- to long-term maintenance decisions for bridge groups according to claim 1, characterized in that: The value range of the annual technical condition score of the bridge is [0,100]; the preset lower limit is 60.

3. The method for making mid- to long-term maintenance decisions for bridge groups according to claim 1, characterized in that: In step S1, the previous appearance inspection scores of the bridge are obtained from the database and the scores are used as labels for the annual technical condition history scores.

4. The method for making mid- to long-term maintenance decisions for bridge groups according to claim 1 is characterized in that: In step S1, the method for determining the factors affecting the actual performance of the bridge includes the following specific steps: S11. Obtain the current basic information of the bridge, including bridge age, span and bridge type; S12. Obtain historical meteorological information of the bridge, including extreme temperature, extreme humidity, number of frost days, and number of rain and snow days; S13. Take the various parameters of the current basic information and the historical meteorological information as separate specific performance influencing factors, and calculate the correlation coefficient between each specific performance influencing factor and the annual technical status historical score r : ； In the formula, X i’ and Y i’ Respectively expressed in i’ Parameter values ​​corresponding to specific performance influencing factors of group data and annual technical status historical score values; and They represent the average values ​​of parameters corresponding to specific performance influencing factors and the average values ​​of annual technical status historical scores respectively; n Indicates the data dimension, n ≥30; S14. Select a correlation coefficient that is greater than a preset coefficient threshold, and use the specific performance influencing factor corresponding to the correlation coefficient as the actual performance influencing factor of the bridge.

5. The method for making mid- to long-term maintenance decisions for bridge groups according to claim 1 is characterized in that: In step S2, the fuzzy neural network model is established based on the Mamdani fuzzy neural network.

6. The method for making mid- to long-term maintenance decisions for bridge groups according to claim 1, characterized in that: In step S3, the future set period is 20 years, that is, N =20.

7. A system for making decisions on long-term maintenance of bridge groups, characterized by: The method for making a mid- to long-term maintenance decision for a bridge group as claimed in any one of claims 1 to 6 is applied; the making system comprises: A data acquisition module, which is used to obtain the annual technical condition historical score of each bridge from the database of the road network bridge group and determine the actual performance influencing factors of the bridge; the parameters corresponding to the actual performance influencing factors include basic bridge information and meteorological data; The prediction module is used to establish a fuzzy neural network model, which takes the parameters corresponding to the actual performance influencing factors of each bridge as input and the annual technical condition historical score of each bridge as label output, and trains the fuzzy neural network model accordingly and obtains the bridge performance prediction model after passing the test; the prediction module is also used to use the bridge performance prediction model, the basic information of the bridge and the future set deadline, that is, N Simulated meteorological data in the past year to obtain the future N Annual technical condition forecast score within the year; A benefit acquisition module, which is used to obtain the performance improvement benefits of each bridge at a unit maintenance expenditure cost based on the maintenance records of the bridges; and The decision generation module is used to establish a decision generation model based on the multi-objective raccoon optimization algorithm. It takes the annual technical condition prediction score of each bridge within a set period in the future and the performance improvement benefit of each bridge under unit maintenance expenditure cost as input, and takes the lowest total maintenance expenditure cost and the highest total technical condition score of the road network bridge group as dual constraints, thereby outputting the medium- and long-term maintenance decision of the bridge group, which includes the maintenance time node and the maintenance bridge object.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for making a long-term maintenance decision for a bridge group as described in any one of claims 1 to 6 are implemented.

Images