A bridge maintenance method and system based on improved simulated annealing algorithm

Abstract

The present invention discloses a bridge maintenance method and system based on an improved simulated annealing algorithm, belonging to the field of data processing technology, the method comprises: obtaining bridge scoring data; determining the scoring vector of each bridge and the scoring matrix of all bridges according to the bridge scoring data; determining the positive ideal vector and the negative ideal vector of the scoring matrix; determining the maintenance priority parameters of each bridge according to the positive ideal vector and the negative ideal vector; determining the maintenance sequence of each bridge according to the maintenance priority parameters of each bridge; with the goal of minimizing the total maintenance cost and minimizing the impact on the passage of the bridge network, determining the maintenance plan of each bridge through a bridge maintenance model based on an improved simulated annealing algorithm; wherein the maintenance plan includes: daily maintenance, minor repairs, medium repairs, major repairs and reconstruction. In the present invention, it is helpful to reasonably allocate maintenance resources, focus on and give priority to bridges that need urgent attention, and reduce the safety hazards of bridges.

Description

Technical Field

[0001] The invention belongs to the technical field of data processing, and in particular relates to a bridge maintenance method and system based on an improved simulated annealing algorithm. Background Art

[0002] Bridges are an important part of highways. Ensuring that the in-service highway bridges are in good technical condition is not only conducive to driving safety and comfort, but also can ensure the smooth operation of the highway network and regional social and economic benefits. According to incomplete statistics, more than half of the existing bridges in my country are designed long ago, and are mainly distributed on highways with low technical standards and poor traffic capacity. The common feature of these bridges is that they have different degrees of defects as their service life increases. In addition, the current overloading and over-limit phenomenon is becoming more and more serious, and the design load can no longer meet the current traffic requirements. Therefore, most of them have hidden dangers that affect the safe use of bridges.

[0003] At present, the maintenance of bridges is often carried out by defect assessment. The defect assessment is carried out on each bridge, and maintenance funds are allocated preferentially to bridges with larger defects, and maintenance is carried out on bridges with larger defects.

[0004] However, concentrating maintenance resources mainly on bridges with greater defects may lead to insufficient maintenance of other bridges. This unbalanced resource allocation may cause safety hazards to some bridges.

[0005] At the same time, only using the degree of defect as an evaluation criterion for bridge maintenance priority without fully considering other important factors such as traffic flow, geographical location, age, etc., may lead to a lack of comprehensive understanding of the condition of the entire bridge system and an inability to accurately determine the maintenance priority of the bridge.

[0006] Furthermore, maintenance funds are preferentially allocated to bridges with greater degrees of damage. Maintenance of bridges with greater degrees of damage is carried out without considering the impact of bridge maintenance on people's passage. If parallel bridges are maintained for a long time at the same time, the passage of the bridge network will be greatly reduced, affecting traffic smoothness and reducing people's travel experience. Summary of the invention

[0007] In order to solve the problem that currently maintenance resources are mainly concentrated on bridges with larger defects, which may lead to insufficient maintenance of other bridges, and such unbalanced resource allocation may cause safety hazards to some bridges, and only the degree of defect is used as the evaluation standard for the maintenance priority of bridges, but other important factors such as traffic flow, geographical location, service life, etc. are not fully considered, which may lead to a lack of comprehensive understanding of the status of the entire bridge system, and an inability to accurately determine the maintenance priority of the bridge. Maintenance funds are preferentially allocated to bridges with larger defects, and maintenance is performed on bridges with larger defects without considering the impact of bridge maintenance on people's passage. If bridges with a parallel relationship are maintained for a long time at the same time, the passage of the bridge network will be greatly reduced, affecting the smoothness of traffic and reducing people's travel experience. The present invention provides a bridge maintenance method and system based on an improved simulated annealing algorithm.

[0008] First aspect

[0009] The present invention provides a bridge maintenance method based on an improved simulated annealing algorithm, comprising:

[0010] S1: Obtain bridge rating data;

[0011] S2: Determine a scoring vector for each bridge and a scoring matrix for all bridges according to the bridge scoring data;

[0012] S3: Determine the positive ideal vector and the negative ideal vector of the scoring matrix;

[0013] S4: determining maintenance priority parameters of each bridge according to the positive ideal vector and the negative ideal vector;

[0014] S5: Determine the maintenance sequence of each bridge according to the maintenance priority parameters of each bridge;

[0015] S6: With the goal of minimizing the total maintenance cost and minimizing the impact on bridge network traffic, the maintenance plan for each bridge is determined through a bridge maintenance model based on an improved simulated annealing algorithm;

[0016] Among them, the maintenance plan includes: daily maintenance, minor repairs, medium repairs, major repairs and reconstruction.

[0017] Second aspect

[0018] The present invention provides a bridge maintenance system based on an improved simulated annealing algorithm, comprising a processor and a memory for storing processor executable instructions; the processor is configured to call the instructions stored in the memory to execute the bridge maintenance method based on the improved simulated annealing algorithm in the first aspect.

[0019] Compared with the prior art, the present invention has at least the following beneficial technical effects:

[0020] (1) In the present invention, by integrating bridge scoring data, such as health score, bridge type score, usage type score, traffic flow score, geographical location score and service life score, the maintenance priority parameters of each bridge are comprehensively and accurately determined according to the positive ideal vector and the negative ideal vector, and the maintenance sequence of each bridge can be listed in an orderly manner, avoiding the concentration of maintenance resources on bridges with larger defects, which helps to reasonably allocate maintenance resources, give priority to bridges that need urgent attention, and reduce safety hazards of bridges.

[0021] (2) In the present invention, the final maintenance plan for each bridge is determined with the goal of minimizing the total maintenance cost and the impact on the traffic of the bridge network, which fully considers the impact of maintenance work on traffic, helps to ensure the traffic of the bridge network, improve traffic smoothness, balance the relationship between maintenance work and social transportation, and minimize interference with people's travel. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The preferred implementation modes will be described below in a clear and understandable manner with reference to the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of the present invention.

[0023] Figure 1 It is a flow chart of a bridge maintenance method based on an improved simulated annealing algorithm provided by the present invention.

[0024] Figure 2 It is a structural schematic diagram of a bridge maintenance system based on an improved simulated annealing algorithm provided by the present invention. DETAILED DESCRIPTION

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0026] In order to simplify the drawings, only the parts related to the invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0027] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0028] In this document, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection. It can be a mechanical connection or an electrical connection. It can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] In addition, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0030] Example 1

[0031] In one embodiment, the reference specification Figure 1 , showing a flow chart of a bridge maintenance method based on an improved simulated annealing algorithm provided by the present invention.

[0032] The present invention provides a bridge maintenance method based on an improved simulated annealing algorithm, comprising:

[0033] S1: Obtain bridge rating data.

[0034] Among them, the bridge scoring data includes: health score, bridge type score, usage type score, traffic flow score, geographical location score and service life score.

[0035] It should be noted that the maintenance priority of a bridge is often related to the current health of the bridge, bridge type, usage type, traffic flow, geographical location and age.

[0036] The current health of a bridge directly affects the safety of its structure. A healthier bridge may not require urgent maintenance, while a bridge in poor health may have structural defects and require more urgent attention and maintenance to ensure safe passage. Different types of bridge structures are stressed and damaged in different ways. Different bridge types may have different needs for different types of maintenance and repair work. Therefore, understanding the type of bridge can help determine the appropriate maintenance measures. The type of use of a bridge can also affect the stress and wear on its structure. For example, a vehicular bridge that carries heavy traffic may be more susceptible to wear and tear than a pedestrian bridge, and therefore may require more frequent inspections and maintenance. Traffic volume is an important consideration because bridges with high traffic volume may be subject to greater loads, causing the structure to be more susceptible to damage. Therefore, for bridges with high traffic volume, more intensive structural assessments and maintenance may be required. Geographical location affects the environmental conditions of the bridge, such as climate, humidity, etc., which may accelerate the corrosion and aging of the bridge structure. Bridges located in coastal areas or areas with high humidity may require more frequent maintenance. The age of a bridge is directly related to its aging and degree of structural wear. Aging bridges may require more frequent inspections and maintenance to ensure their safety and reliability.

[0037] S2: Based on the bridge scoring data, determine the scoring vector of each bridge and the scoring matrix of all bridges.

[0038] The score vector of each bridge is [a1, a2, …, a6], where a1 represents the health score, a2 represents the bridge type score, a3 represents the usage type score, a4 represents the traffic flow score, a5 represents the geographical location score, and a6 represents the service life score.

[0039] Optionally, the health score, bridge type score, usage type score, traffic flow score, geographic location score, and age score may be based on a uniform percentage system.

[0040] Furthermore, if the scoring ranges of the health score, bridge type score, usage type score, traffic flow score, geographic location score, and service life score are different, each scoring item needs to be normalized to eliminate the impact of the dimension.

[0041] The scoring matrix is ​​as follows:

[0042]

[0043] Among them, A represents the scoring matrix, a ik represents the score of the kth scoring item of the i-th bridge, i = 1, 2, ..., n, n represents the total number of bridges, k = 1, 2, ..., 6.

[0044] S3: Determine the positive ideal vector and the negative ideal vector of the scoring matrix.

[0045] Among them, the positive ideal vector is a vector that represents the optimal value that is expected to be achieved on each indicator in multi-objective decision-making. The construction of the positive ideal vector is usually obtained by selecting the maximum value from each indicator. The positive ideal vector corresponds to the best comprehensive performance state expected by the decision maker.

[0046] Among them, the negative ideal vector is a vector that represents the worst value obtained on each indicator in multi-objective decision-making. The construction of the negative ideal vector is usually obtained by selecting the minimum value from each indicator. The negative ideal vector corresponds to the worst comprehensive performance state expected by the decision maker.

[0047] In a possible implementation, S3 specifically includes sub-steps S301 and S302:

[0048] S301: Determine the maximum value in each column of the scoring matrix and construct a positive ideal vector:

[0049] a + =[a 1,max ,a 2,max ,…,a 6,max ]

[0050] Among them, a + represents a positive ideal vector, a k,max Represents the maximum value among the k-th scoring items.

[0051] S302: Determine the minimum value in each column of the scoring matrix and construct a negative ideal vector:

[0052] a - =[a 1,min ,a 2,min ,…,a 6,min ]

[0053] Among them, a - represents the negative ideal vector, a k,min Represents the minimum value among the k-th scoring items.

[0054] S4: Determine the maintenance priority parameters of each bridge based on the positive ideal vector and the negative ideal vector.

[0055] In a possible implementation, S4 specifically includes sub-steps S401 to S403:

[0056] S401: Calculate the distance between the score vector of each bridge and the positive ideal vector:

[0057]

[0058] in, Represents the distance between the score vector of the i-th bridge and the positive ideal vector.

[0059] S402: Calculate the distance between the score vector of each bridge and the negative ideal vector:

[0060]

[0061] in, Represents the distance between the score vector of the i-th bridge and the negative ideal vector.

[0062] It should be noted that the use of distance calculation to compare the score vector of each bridge with the positive ideal vector and the negative ideal vector makes the decision more objective and scientific, and helps to avoid the influence of subjective judgment and individual preference.

[0063] S403: Calculate the maintenance priority parameter of each bridge according to the distance from the positive ideal vector and the distance from the negative ideal vector:

[0064]

[0065] Among them, pr i Represents the maintenance priority parameter of the i-th bridge.

[0066] It should be noted that the closer the bridge's score vector is to the positive ideal vector, the closer its maintenance priority parameter is to 1, indicating that the better the bridge performs on multiple evaluation indicators, the higher its maintenance priority. Using the closeness of the positive ideal vector as the maintenance priority parameter fully considers the comprehensive impact of multiple evaluation indicators on the maintenance priority. This helps to evaluate the maintenance needs of bridges more comprehensively and scientifically.

[0067] In the present invention, the calculation of maintenance priority parameters helps to allocate maintenance resources more effectively. For bridges with higher priority, maintenance resources can be invested first to ensure their safety and reliability; for bridges with lower priority, the maintenance frequency can be appropriately reduced, so as to make more reasonable use of limited resources.

[0068] S5: Determine the maintenance sequence of each bridge according to the maintenance priority parameters of each bridge.

[0069] In the present invention, by determining the maintenance sequence according to the maintenance priority parameters, the maintenance urgency of the bridge can be determined more objectively, avoiding the influence of subjective factors on maintenance decisions, and ensuring the fairness and impartiality of the decision. Reasonable formulation of the maintenance sequence can ensure that limited maintenance resources are used for the most critical and most needed parts of the entire bridge network, thereby improving the maintenance effect. Giving priority to problematic bridges will help to discover and resolve potential structural defects as early as possible and prevent the problem from further deteriorating. Furthermore, by determining the maintenance sequence according to the maintenance priority parameters, the bridge maintenance work can be managed more scientifically and effectively, maximizing the safety and reliability of the bridge network, while reducing maintenance costs and improving social satisfaction.

[0070] S6: With the goal of minimizing the total maintenance cost and the smallest impact on bridge network traffic, the maintenance plan for each bridge is determined through a bridge maintenance model based on the improved simulated annealing algorithm.

[0071] Among them, the maintenance plan includes: daily maintenance, minor repairs, medium repairs, major repairs and reconstruction.

[0072] In the present invention, the final maintenance plan for each bridge is determined with the goal of minimizing the total maintenance cost and the impact on the traffic of the bridge network, which fully considers the impact of maintenance work on traffic, helps to ensure the traffic of the bridge network, improve traffic smoothness, balance the relationship between maintenance work and social transportation, and minimize interference with people's travel.

[0073] In a possible implementation, S6 specifically includes sub-steps S601 to S604:

[0074] S601: Combine the possible maintenance schemes for each bridge to obtain multiple bridge maintenance combination schemes X = [X1, X2, ..., X n ], X i represents the maintenance plan of the i-th bridge, i = 1, 2, ..., n, n represents the total number of bridges, X i The value range is [x i1 ,x i2 ,…,x i5 ], x ij represents the situation where the jth maintenance scheme is adopted for the i-th bridge, j = 1, 2, ..., 5. When the jth maintenance scheme is adopted, x ij =1, when the jth maintenance plan is not adopted, x ij =0,x i1 Indicates daily maintenance, x i2 Indicates minor repairs, x i3 Indicates mid-term repair, x i4 Indicates overhaul, x i5 Indicates reconstruction.

[0075] S602: Construct an objective function of the bridge maintenance model with the goal of minimizing the total maintenance cost and the impact on bridge network traffic.

[0076] In a possible implementation, the objective function of the bridge maintenance model is specifically:

[0077] min F(X)=λ1·Po+λ2·G

[0078] Among them, min() represents the minimum function, F() represents the objective function, X represents the bridge maintenance combination plan, Po represents the total maintenance cost, λ1 represents the weight coefficient of the total maintenance cost, G represents the influence of bridge network traffic, and λ2 represents the weight coefficient of the total defect degree.

[0079] Among them, those skilled in the art can set the weight coefficient λ1 of the total maintenance cost and the weight coefficient λ2 of the total defect degree according to actual conditions, and the present invention does not limit this.

[0080] In the present invention, the total maintenance cost and the impact on bridge network traffic are combined in one objective function, which comprehensively considers economic and traffic factors, helps to weigh the two in decision-making and find a balance point to ensure the rationality of maintenance fund allocation while minimizing the impact on traffic smoothness.

[0081] In a possible implementation, the total maintenance cost Po is calculated as follows:

[0082] The maintenance cost of each bridge is determined according to the following formula:

[0083]

[0084] Among them, Po i represents the maintenance cost of the i-th bridge, s i represents the total maintenance area of ​​the i-th bridge, x ij represents the situation where the jth maintenance plan is adopted for the i-th bridge, po j It represents the maintenance cost per unit maintenance area when the j-th maintenance plan is adopted, i = 1, 2, …, n, and n represents the total number of bridges.

[0085] Determine the total maintenance cost Po according to the following formula:

[0086]

[0087] In a possible implementation, the calculation method of the bridge network traffic impact G is:

[0088] The traffic impact of each bridge during maintenance is determined according to the following formula:

[0089]

[0090] Among them, G i represents the traffic impact of the i-th bridge during maintenance, v i represents the traffic flow impact coefficient of the i-th bridge, μ i represents the bridge connection influence coefficient of the i-th bridge, t j It represents the maintenance time per unit maintenance area when the jth maintenance plan is adopted.

[0091] In the present invention, the traffic flow impact coefficient, bridge connection impact coefficient, selection of maintenance plan, maintenance time and maintenance area are comprehensively considered, and the various factors affecting maintenance on traffic are comprehensively considered to improve the accuracy of calculation of the traffic impact of bridge maintenance.

[0092] It should be noted that the introduction of the traffic flow impact coefficient can more comprehensively consider the impact of traffic flow on traffic flow.

[0093] Among them, the traffic flow impact coefficient v i The calculation method is:

[0094]

[0095] Among them, fl i represents the traffic flow of the i-th bridge, and exp represents the exponential function with e as the base.

[0096] In the present invention, a nonlinear relationship is introduced by using the sigmoid function, so that the traffic flow impact coefficient is close to 0 when the traffic flow is small, and gradually approaches 1 when the traffic flow is large. This helps to more accurately reflect the nonlinear relationship of the impact of traffic flow on traffic.

[0097] Among them, the bridge connection influence coefficient μ i The calculation method is:

[0098]

[0099] Among them, c i Represents the number of bridges connected in parallel with the i-th bridge within the preset distance range.

[0100] In the present invention, the number of connected bridges is placed in the denominator and the nonlinear effect is introduced in the form of a reciprocal. When the number of bridges connected in parallel is small, the bridge connection influence coefficient is large, and the change of the traffic influence degree is more sensitive. When the number of bridges connected in parallel is large, the bridge connection influence coefficient is small, and the change of the traffic influence degree is relatively slow, which helps to more realistically simulate the nonlinear characteristics of the impact of the number of connected bridges on traffic.

[0101] The bridge network traffic impact G is determined according to the following formula:

[0102]

[0103] S603: Set constraints for the bridge maintenance model.

[0104] In a possible implementation, the constraints of the bridge maintenance model include: a maintenance frequency constraint and a cost constraint.

[0105] The maintenance frequency constraint is used to ensure that each bridge is maintained only once. The maintenance frequency constraint is as follows:

[0106]

[0107] Among them, x ij represents the situation where the jth maintenance scheme is adopted for the i-th bridge, j = 1, 2, ..., 5. When the jth maintenance scheme is adopted, x ij =1, when the jth maintenance plan is not adopted, x ij =0,x i1 Indicates daily maintenance, x i2 Indicates minor repairs, x i3 Indicates mid-term repair, x i4 Indicates overhaul, x i5 Indicates reconstruction.

[0108] In the present invention, the maintenance frequency constraint ensures that each bridge is maintained only once, which helps to rationally utilize maintenance resources, avoid excessive maintenance or frequent maintenance, and thus improve resource utilization efficiency.

[0109] Cost constraints are used to ensure that the total maintenance cost is lower than the total cost budget. The cost constraints are as follows:

[0110] Po≤Po max

[0111] Among them, Po max Indicates the total cost budget.

[0112] In the present invention, the cost constraint ensures that the total maintenance cost is lower than the total cost budget, which helps to maintain the economy of the maintenance activities. By carrying out maintenance within the budget, the maintenance goals can be achieved to the greatest extent while avoiding the waste of resources caused by overspending.

[0113] S604: Under the constraints of the constraints, with the goal of minimizing the function value of the objective function, determine the optimal bridge maintenance combination plan through a bridge maintenance model based on an improved simulated annealing algorithm.

[0114] It should be noted that the traditional simulated annealing algorithm can accept a solution that is worse than the current solution as the possibility of a new solution, and it is easier to jump out of the dilemma of the local optimal solution. However, since only one value can be stored at a time and there is a phenomenon of accepting suboptimal solutions, the convergence speed of the algorithm is slow. The present invention proposes a novel simulated annealing algorithm, which introduces a genetic algorithm on the basis of the simulated annealing algorithm. The genetic algorithm introduces mechanisms such as crossover and mutation, which can produce more individual differences and increase the diversity of the search space, which helps to overcome the limitation that only one value can be stored at a time in the simulated annealing algorithm, and explore the solution space more comprehensively. In addition, the genetic algorithm has good global search capabilities, which can improve the convergence speed of the algorithm.

[0115] In a possible implementation manner, S604 specifically includes S6041 to S6049:

[0116] S6041: According to the objective function of the bridge maintenance model, determine the fitness function of the simulated annealing algorithm:

[0117]

[0118] Among them, S() represents the fitness function, F() represents the objective function, X represents the bridge maintenance combination scheme, and γ represents the scaling parameter.

[0119] In the present invention, the relationship between the fitness function and the objective function F(X) is established by the inverse and the scaling parameter. The introduction of the inverse indicates that the maximum value of the fitness function corresponds to the minimum value of the objective function. By adjusting the scaling parameter, the shape of the fitness function can be affected, thereby affecting the search method of the simulated annealing algorithm for the solution space.

[0120] S6042: Initialize the initial temperature T0, the maximum number of iterations m, and the termination temperature T m And the population Q, each individual in the population represents a feasible bridge maintenance combination plan X.

[0121] S6043: Adopt the elite retention strategy to remove the 10% of individuals with the lowest fitness values ​​S6043: Randomly select a current individual.

[0122] In the present invention, the elite retention strategy is adopted to ensure that a part of individuals with the highest fitness values ​​are retained in each generation. This helps to maintain the stability of excellent solutions and prevent them from being forgotten during the evolution process.

[0123] S6044: Randomly select two individuals, perform gene crossover operation, and generate new individuals.

[0124] S6045: Randomly select some individuals, perform gene mutation operations, and generate new individuals.

[0125] In the present invention, two individuals are randomly selected for gene crossover and some individuals are subjected to gene mutation, which introduces diversity, helps to search more areas of the solution space, helps to avoid falling into the local optimal solution, and increases the breadth of the search.

[0126] S6046: Determine the target individual with the highest current fitness value.

[0127] S6047: Generate neighborhood individuals based on the target individual.

[0128] S6048: Compare the fitness values ​​of the current individual and the neighboring individuals. When the fitness value of the neighboring individual is greater than the fitness value of the current individual, the neighboring individual is used to replace the current individual. When the fitness value of the neighboring individual is less than the fitness value of the current individual, the neighboring individual is used to replace the current individual with a replacement probability P. The replacement probability P is specifically:

[0129]

[0130] Where P represents the probability of replacement, e represents the base of the natural logarithm, and X new represents the neighborhood individuals, S(X new ) represents the fitness value of the neighborhood individual, X best represents the target individual, S(X best ) represents the fitness value of the target individual, and T represents the current temperature.

[0131] In the present invention, through the neighborhood search and replacement strategy, the algorithm can generate neighborhood individuals according to the target individual and replace the current individual according to a certain probability. This helps to retain excellent solutions during the search process, while allowing a certain degree of possibility of accepting inferior solutions during the search process.

[0132] S6049: Determine whether the number of iterations has reached the maximum number of iterations m, or whether the current temperature has reached the termination temperature T m If yes, output the best bridge maintenance combination plan. Otherwise, update the temperature, perform chaotic perturbation on the individual positions with fitness less than the average, and return to S6043.

[0133] It should be noted that the maximum number of iterations and the termination temperature are set, which helps to control the number of iterations of the algorithm and avoid unnecessary calculations. At the same time, the temperature is reduced in the later stages of the algorithm to improve the accuracy of local search.

[0134] Among them, the temperature update method is:

[0135]

[0136] Where α represents the temperature drop coefficient, T irepresents the temperature at the i-th iteration, T0 represents the initial temperature, i represents the number of iterations, and I represents the number of cooling times.

[0137] In the present invention, a larger temperature change can be made in the early iteration, and the temperature change can be gradually reduced in the later stage, so as to balance the capabilities of global search and local search. At the same time, there is a temperature recovery process in the later stage of the algorithm, which helps the algorithm to jump out of the local optimal solution and is more likely to find the global optimal solution.

[0138] The specific method of performing chaotic perturbation on the individual positions with fitness less than the average is:

[0139] Y i+1 =ηY i (1-Y i )

[0140] Among them, Y i+1 represents the individual position at the i+1th iteration, Y i represents the individual position at the i-th iteration, and η represents the disturbance parameter.

[0141] In the present invention, the positions of particles whose fitness is less than the average in each iteration are chaotically perturbed, which can introduce more randomness and diversity, help improve the quality of initial particles and the diversity of the population, enhance the efficiency of the algorithm and the global search capability, effectively avoid the occurrence of premature convergence of the algorithm, and improve the coverage of the search space.

[0142] Compared with the prior art, the present invention has at least the following beneficial technical effects:

[0143] (1) In the present invention, by integrating bridge scoring data, such as health score, bridge type score, usage type score, traffic flow score, geographical location score and service life score, the maintenance priority parameters of each bridge are comprehensively and accurately determined according to the positive ideal vector and the negative ideal vector, and the maintenance sequence of each bridge can be listed in an orderly manner, avoiding the concentration of maintenance resources on bridges with larger defects, which helps to reasonably allocate maintenance resources, give priority to bridges that need urgent attention, and reduce safety hazards of bridges.

[0144] (2) In the present invention, the final maintenance plan for each bridge is determined with the goal of minimizing the total maintenance cost and the impact on the traffic of the bridge network, which fully considers the impact of maintenance work on traffic, helps to ensure the traffic of the bridge network, improve traffic smoothness, balance the relationship between maintenance work and social transportation, and minimize interference with people's travel.

[0145] Example 2

[0146] In one embodiment, the reference specification Figure 2, showing a structural schematic diagram of a bridge maintenance system based on an improved simulated annealing algorithm provided by the present invention.

[0147] The present invention provides a bridge maintenance system based on an improved simulated annealing algorithm, comprising a processor 201 and a memory 202 for storing executable instructions of the processor 201. The processor 201 is configured to call the instructions stored in the memory 202 to execute the bridge maintenance method based on the improved simulated annealing algorithm in Example 1.

[0148] The bridge maintenance system based on the improved simulated annealing algorithm provided by the present invention can realize the steps and effects of the bridge maintenance method based on the improved simulated annealing algorithm in the above-mentioned embodiment 1. To avoid repetition, the present invention will not go into details.

[0149] Compared with the prior art, the present invention has at least the following beneficial technical effects:

[0150] (1) In the present invention, by integrating bridge scoring data, such as health score, bridge type score, usage type score, traffic flow score, geographical location score and service life score, the maintenance priority parameters of each bridge are comprehensively and accurately determined according to the positive ideal vector and the negative ideal vector, and the maintenance sequence of each bridge can be listed in an orderly manner, avoiding the concentration of maintenance resources on bridges with larger defects, which helps to reasonably allocate maintenance resources, give priority to bridges that need urgent attention, and reduce safety hazards of bridges.

[0151] (2) In the present invention, the final maintenance plan for each bridge is determined with the goal of minimizing the total maintenance cost and the impact on the traffic of the bridge network, which fully considers the impact of maintenance work on traffic, helps to ensure the traffic of the bridge network, improve traffic smoothness, balance the relationship between maintenance work and social transportation, and minimize interference with people's travel.

[0152] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0153] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A bridge maintenance method based on an improved simulated annealing algorithm, characterized in that: include: S1: Obtain bridge scoring data; S2: Determine a scoring vector for each bridge and a scoring matrix for all bridges according to the bridge scoring data; S3: Determine the positive ideal vector and the negative ideal vector of the scoring matrix; S4: determining maintenance priority parameters of each bridge according to the positive ideal vector and the negative ideal vector; S5: Determine the maintenance sequence of each bridge according to the maintenance priority parameters of each bridge; S6: With the goal of minimizing the total maintenance cost and minimizing the impact on bridge network traffic, the maintenance plan for each bridge is determined through a bridge maintenance model based on an improved simulated annealing algorithm; The maintenance plan includes: daily maintenance, minor repairs, medium repairs, major repairs and reconstruction; Wherein, the S6 specifically includes: S601: Combine the possible maintenance schemes for each bridge to obtain multiple bridge maintenance combination schemes X = [X1, X2, ..., X n ], X i represents the maintenance plan of the i-th bridge, i = 1, 2, ..., n, n represents the total number of bridges, X i The value range is [x i1 ,x i2 ,…,x i5 ], x ij represents the situation where the jth maintenance scheme is adopted for the i-th bridge, j = 1, 2, ..., 5. When the jth maintenance scheme is adopted, x ij =1, when the jth maintenance plan is not adopted, x ij =0,x i1 Indicates daily maintenance, x i2 Indicates minor repairs, x i3 Indicates mid-term repair, x i4 Indicates overhaul, x i5 It means reconstruction; S602: constructing an objective function of the bridge maintenance model with the goal of minimizing the total maintenance cost and minimizing the impact on bridge network traffic; S603: Setting constraint conditions for the bridge maintenance model; S604: Under the constraint of the constraint condition, with the minimum function value of the objective function as the goal, determine the optimal bridge maintenance combination plan through the bridge maintenance model based on the improved simulated annealing algorithm; Among them, the objective function of the bridge maintenance model is specifically: minF(X)=λ1·Po+λ2·G Among them, min() represents the minimum function, F() represents the objective function, X represents the bridge maintenance combination plan, Po represents the total maintenance cost, λ1 represents the weight coefficient of the total maintenance cost, G represents the influence of bridge network traffic, and λ2 represents the weight coefficient of the total defect degree; The constraints of the bridge maintenance model include: maintenance frequency constraint and cost constraint; The maintenance frequency constraint is used to ensure that each bridge is maintained only once. The maintenance frequency constraint is specifically: Among them, x ij represents the situation where the jth maintenance scheme is adopted for the i-th bridge, j = 1, 2, ..., 5. When the jth maintenance scheme is adopted, x ij =1, when the jth maintenance plan is not adopted, x ij =0,x i1 Indicates daily maintenance, x i2 Indicates minor repairs, x i3 Indicates mid-term repair, x i4 Indicates overhaul, x i5 It means reconstruction; The cost constraint is used to ensure that the total maintenance cost is lower than the total cost budget. The cost constraint is specifically: Po≤Po max Among them, Po max Indicates the total cost budget; The total maintenance cost Po is calculated as follows: The maintenance cost of each bridge is determined according to the following formula: Among them, Po i represents the maintenance cost of the i-th bridge, s i represents the total maintenance area of ​​the i-th bridge, x ij represents the situation where the jth maintenance plan is adopted for the i-th bridge, po j represents the maintenance cost per unit maintenance area when the jth maintenance plan is adopted, i = 1, 2, …, n, where n represents the total number of bridges; Determine the total maintenance cost Po according to the following formula:

2. The bridge maintenance method based on the improved simulated annealing algorithm according to claim 1 is characterized in that: The bridge scoring data includes: health score, bridge type score, usage type score, traffic flow score, geographical location score and service life score; The score vector of each bridge is specifically: [a1, a2, ..., a6], where a1 represents the health score, a2 represents the bridge type score, a3 represents the use type score, a4 represents the traffic flow score, a5 represents the geographical location score, and a6 represents the service life score; The scoring matrix is ​​specifically: Among them, A represents the scoring matrix, a ik represents the score of the kth scoring item of the i-th bridge, i = 1, 2, ..., n, n represents the total number of bridges, k = 1, 2, ..., 6.

3. The bridge maintenance method based on the improved simulated annealing algorithm according to claim 2 is characterized in that: The S3 specifically includes: S301: Determine the maximum value in each column of the scoring matrix and construct a positive ideal vector: a + =[a 1,max ,a 2,max ,…,a 6,max ] Among them, a + represents a positive ideal vector, a k,max represents the maximum value among the k-th scoring items; S302: Determine the minimum value in each column of the scoring matrix and construct a negative ideal vector: a - =[a 1,min ,a 2,min ,…,a 6,min ] Among them, a - represents the negative ideal vector, a k,min Represents the minimum value among the k-th scoring items.

4. The bridge maintenance method based on the improved simulated annealing algorithm according to claim 3 is characterized in that: The S4 specifically includes: S401: Calculate the distance between the score vector of each bridge and the positive ideal vector: in, represents the distance between the score vector of the i-th bridge and the positive ideal vector; S402: Calculate the distance between the score vector of each bridge and the negative ideal vector: in, represents the distance between the score vector of the i-th bridge and the negative ideal vector; S403: Calculate the maintenance priority parameter of each bridge according to the distance from the positive ideal vector and the distance from the negative ideal vector: Among them, pr i Represents the maintenance priority parameter of the i-th bridge.

5. The bridge maintenance method based on the improved simulated annealing algorithm according to claim 1 is characterized in that: The calculation method of the bridge network traffic impact G is: The traffic impact of each bridge during maintenance is determined according to the following formula: Among them, G i represents the traffic impact of the i-th bridge during maintenance, v i represents the traffic flow impact coefficient of the i-th bridge, μ i represents the bridge connection influence coefficient of the i-th bridge, t j It represents the maintenance time per unit maintenance area when the jth maintenance plan is adopted; The bridge network traffic impact G is determined according to the following formula:

6. The bridge maintenance method based on the improved simulated annealing algorithm according to claim 1 is characterized in that: The S604 specifically includes: S6041: Determine the fitness function of the simulated annealing algorithm according to the objective function of the bridge maintenance model: Among them, S() represents the fitness function, F() represents the objective function, X represents the bridge maintenance combination scheme, and γ represents the scaling parameter; S6042: Initialize the initial temperature T0, the maximum number of iterations m, and the termination temperature T m and population Q, where each individual represents a feasible bridge maintenance combination plan X; S6043: Adopt the elite retention strategy and remove the 10% of individuals with the lowest fitness values ​​S6043: Randomly select a current individual; S6044: Randomly select two individuals, perform gene crossover operation, and generate new individuals; S6045: Randomly select some individuals, perform gene mutation operations, and generate new individuals; S6046: Determine the target individual with the highest current fitness value; S6047: Generate a neighborhood individual according to the target individual; S6048: Compare the fitness values ​​of the current individual and the neighborhood individual; when the fitness value of the neighborhood individual is greater than the fitness value of the current individual, use the neighborhood individual to replace the current individual; when the fitness value of the neighborhood individual is less than the fitness value of the current individual, use the neighborhood individual to replace the current individual with a replacement probability P; the replacement probability P is specifically: Where P represents the probability of replacement, e represents the base of the natural logarithm, and X new represents the neighborhood individuals, S(X new ) represents the fitness value of the neighborhood individual, X best represents the target individual, S(X best ) represents the fitness value of the target individual, and T represents the current temperature; S6049: Determine whether the number of iterations has reached the maximum number of iterations m, or whether the current temperature has reached the termination temperature T m ; If so, output the best bridge maintenance combination plan; otherwise, update the temperature, perform chaotic perturbations on the individual positions with fitness values ​​less than the average, and return to S6043.

7. A bridge maintenance system based on an improved simulated annealing algorithm, characterized in that: It comprises a processor and a memory for storing processor executable instructions; the processor is configured to call the instructions stored in the memory to execute the bridge maintenance method based on the improved simulated annealing algorithm as described in any one of claims 1 to 6.

Images