Road and bridge maintenance intelligent management method and system based on big data

Abstract

The application discloses a road and bridge maintenance intelligent management method and system based on big data, and relates to the technical field of data processing.The model is constructed to calculate the maximum allowed traffic blocking time length of each node by acquiring road network basic data, combining topological structure and random traffic flow characteristics, constructing a material attribute matrix based on an environmental sensitive coefficient, accurately calculating the expected total duration of different resource combinations, using a genetic algorithm containing random reset correction and compression operation to iteratively optimize under the dual constraints of physical duration and traffic limit, and outputting optimal maintenance time quota and digital work orders.The application effectively solves the problem of lack of quantitative constraints on traffic blocking time length, automatically eliminates unfeasible schemes and forces the system to match efficient resources through a nonlinear importance penalty and environmental dynamic correction mechanism, maximally compresses road occupancy time under the premise of ensuring the physical feasibility of the scheme, and realizes the best balance between road network traffic efficiency and maintenance resource allocation.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for intelligent management of road and bridge maintenance based on big data. Background Technology

[0002] With the deepening of smart city construction, the scale of urban infrastructure such as roads and bridges is expanding day by day, and has fully entered the stage of large-scale maintenance and operation. The health status of roads and bridges is directly related to the safety of urban operation and the efficiency of residents' travel. Therefore, it is extremely necessary to establish a scientific and efficient maintenance management system to achieve real-time monitoring of facility status, accurate assignment of maintenance tasks, and closed-loop management of maintenance quality. Invention patent CN110298768A discloses a road and bridge maintenance auxiliary decision-making system based on BIM and GIS. It uses mobile positioning technology to collect the trajectory of inspection personnel and analyzes the inspection coverage, timely repair rate of defects, and acceptance rate, thereby eliminating the tediousness of manually searching through massive amounts of data. However, when formulating maintenance plans, existing technologies often focus on the logical closed loop of the maintenance task itself, lacking quantitative consideration of the complex urban traffic flow environment and road network topology. When performing maintenance operations, especially those involving road closures, they rely heavily on manual experience or pre-set fixed frequencies to issue tasks, failing to accurately quantify the pivotal importance of construction nodes in the road network. This makes it difficult to determine the maximum allowable traffic interruption time based on the volatility risk of real-time and historical traffic flow when allocating construction time windows. Existing technologies lack deep collaborative optimization algorithms between maintenance resource allocation and traffic efficiency balance, which can easily lead to a disconnect between maintenance plans and the actual traffic carrying capacity of the road network, resulting in unnecessary traffic congestion or wasted maintenance time. Summary of the Invention

[0003] The technical problem solved by this invention is that existing technologies, when formulating maintenance plans, often focus on the logical closed loop of the maintenance task itself, lacking quantitative consideration of the complex urban traffic flow environment and road network topology. When carrying out maintenance work, especially tasks involving road closures for repair, they rely heavily on manual experience or pre-set fixed frequencies to issue tasks, failing to accurately quantify the pivotal importance of construction nodes in the road network. This easily leads to a disconnect between the maintenance plan and the actual traffic carrying capacity of the road network, thereby causing unnecessary traffic congestion or wasting maintenance time.

[0004] To address the aforementioned technical problems, this invention provides the following technical solution: a road and bridge maintenance intelligent management method based on big data, comprising the following steps: Step S1: Obtain basic data, which includes maintenance tasks, location data, static data, and historical traffic flow data within the target maintenance area; Step S2: Based on the aforementioned basic data, calculate the maximum permissible traffic disruption duration for each maintenance node; Step S3: Based on the maintenance task type, construct a maintenance plan and calculate the estimated total duration of the maintenance plan; Step S4: Using the maximum allowable traffic interruption time as the upper limit, and the allowable traffic interruption time allocated to the maintenance node as the population individuals, an initial population is constructed, and the population individuals are iteratively optimized using a genetic algorithm to obtain the optimal maintenance time quota scheme. The genetic algorithm includes random reset correction and compression operations. Step S5: Generate a maintenance plan based on the optimal maintenance time quota scheme.

[0005] Preferably, in step S1, the maintenance task includes maintenance nodes, maintenance task types for maintenance nodes, number of lanes to be closed, and planned construction period. The location data includes the ID, spatial coordinates, and physical distance between each road and bridge maintenance node within the target maintenance area; The static data includes the design traffic capacity of the maintenance nodes, lane number configuration information, the specified physical construction time window, and ambient temperature. The historical traffic flow data includes the average daily traffic flow, daily traffic flow, and time-specific traffic flow at each maintenance node in the target maintenance area within a preset historical period.

[0006] Preferably, in step S2, the process of calculating the maximum permissible traffic disruption duration includes: With the goal of maximizing the overall traffic efficiency of the road network, a function for the maximum permissible traffic interruption duration is constructed. The mathematical expression for the maximum permissible traffic interruption duration is as follows: The mathematical expression for the maximum permissible traffic disruption duration is: ; in, For maintenance nodes Maximum permissible traffic disruption duration This is the largest physically available time window for construction. The confidence level coefficient is... To determine the average traffic flow during the construction period, To determine the standard deviation of traffic flow during the construction period, To maintain the design traffic capacity of the nodes, This is the lane reduction factor. As an adjustment constant, The importance weight of maintenance node i.

[0007] Preferably, the process of calculating the comprehensive importance weight of maintenance nodes specifically includes: The road network topology is constructed by combining the connection relationships of maintenance nodes; The betweenness centrality of all nodes in the road network topology is calculated using the Brandes algorithm. The reciprocal of the sum of the distances from the maintenance node to all other maintenance nodes in the road network topology is used as the compactness. The average daily traffic flow is extracted from historical traffic flow data. The betweenness centrality, compactness, and average daily traffic flow are normalized using the extreme value method. The normalized betweenness centrality, compactness, and average daily traffic volume are used as evaluation indicators to calculate the first weight. The process of calculating the first weight specifically includes: Calculate the feature weight of any maintenance node under any evaluation index. The feature weight is the value of the maintenance node under the evaluation index divided by the sum of the values ​​of the evaluation index of all maintenance nodes. Calculate the information entropy based on the feature weight, and then calculate the first weight of the evaluation index based on the information entropy. The mathematical expression for the first weight is: ; in, For the first The first weight of each evaluation indicator For the first Information entropy of each indicator For the first Information entropy of each indicator; An evaluation matrix is ​​constructed based on the normalized betweenness centrality, compactness, and average daily traffic flow. The rows of the evaluation matrix represent maintenance nodes, and the columns represent the normalized evaluation indicators. Based on the evaluation matrix, the comprehensive information content of the evaluation indicators is calculated, and the mathematical expression for the comprehensive information content is: ; in, For the first The standard deviation of each evaluation indicator For the first The Pearson correlation coefficient between the k-th evaluation index and the k-th evaluation index Characteristic indicators Conflicts with other indicators; The comprehensive information content is normalized to obtain the second weight; The first and second weights are merged using a linear weighting method to obtain the combined weights of each evaluation index. The combined weights of the three indices are then concatenated into a column vector to obtain the combined weight vector. The product of the evaluation matrix and the combined weight vector is used as the importance weight vector, and each element in the importance weight vector is the importance weight of the corresponding target maintenance node.

[0008] Preferably, the process of obtaining the mean traffic flow and the standard deviation of the traffic flow during the planned construction period specifically includes: The planned construction period is divided into time slices according to the preset time window to construct a traffic flow matrix; The values ​​of the elements in the traffic flow matrix represent the actual traffic flow for the corresponding day and time. The mean of all elements in the traffic flow matrix is ​​the mean of the traffic flow during the planned construction period, and the standard deviation of all elements in the traffic flow matrix is ​​the standard deviation of the traffic flow during the planned construction period.

[0009] Preferably, in step S3, the specific process of calculating the expected total construction period corresponding to each maintenance plan includes: Based on the maintenance plan, identify the current target maintenance task type, and for the identified task type, extract suitable operation resources from the maintenance operation resource library, including a variety of optional maintenance materials and a variety of optional maintenance equipment combinations; Construct a curing material attribute matrix, wherein the curing material attribute matrix is ​​a behavior curing material, and the standard process waiting time and environmental sensitivity coefficient are listed for each material. The environmental sensitivity coefficient represents the correction ratio of the material curing rate to the unit change in ambient temperature. Construct a construction equipment efficiency matrix, where the matrix consists of construction equipment and lists the time spent on traffic control upon entry, the time spent on core operations, and the time spent opening the site for traffic for each equipment combination. The maintenance material set and the construction equipment set are combined in all possible arrangements to generate a maintenance plan; The mathematical expression for the estimated total construction period corresponding to each maintenance operation plan is as follows: ; in, The time spent on traffic control at the entrance The core task takes time, Traffic disruptions caused by the closure and reopening of the venue Standard processing time for materials. The environmental sensitivity coefficient of the material. The current ambient temperature at the construction site. This is the standard laboratory temperature.

[0010] Preferably, step S4, the process of obtaining the optimal maintenance time quota scheme, specifically includes: For maintenance nodes in the maintenance plan, a maintenance time quota scheme with a preset population size is randomly generated as the initial population. The maintenance time quota scheme includes the allowable traffic interruption time allocated to each maintenance node. The upper limit of the range of allowable traffic interruption time allocated to each maintenance node is the maximum allowable traffic interruption time corresponding to that maintenance node. For each maintenance node in the scheme, the maintenance operation resource library is traversed to obtain all feasible resource combinations that fit the maintenance node, and the minimum expected total duration among them is defined as the minimum total resource duration of the maintenance node. For each maintenance time quota scheme, a comprehensive fitness score is calculated. This comprehensive fitness score aims to minimize the weighted road network interruption duration while satisfying dual constraints. The mathematical expression for the comprehensive fitness score is: ; in, For the plan The overall fitness score, The number of maintenance nodes, The maintenance time quota allocated to maintenance nodes in the maintenance time quota scheme Permissible traffic disruption duration, For maintenance nodes Importance weight, To prevent extremely small positive numbers with a denominator of zero, This is the preset penalty coefficient; For the plan The constraint violation penalty term is expressed mathematically as follows: ; in, For maintenance nodes The minimum total resource duration among all feasible resource combinations. For maintenance nodes The maximum permissible duration of traffic disruption.

[0011] Preferably, the process of obtaining the optimal maintenance time quota scheme further includes: Based on the comprehensive fitness score of each maintenance time quota scheme, offspring schemes are generated through roulette wheel selection and cross-selection. During the mutation phase, each maintenance node in the offspring plan is examined. If the allocated allowable traffic interruption duration is less than its corresponding minimum total resource duration, it is identified as a schedule conflict node. Schedule conflict nodes are then subjected to tiered processing, which includes: If the minimum total resource duration of a project conflict node is greater than the maximum allowable traffic disruption duration, the overall fitness score of the solution will be forcibly set to 0. If the minimum total resource duration of a conflicting node is less than or equal to the maximum allowable traffic disruption duration, a random reset correction is applied to the allowable traffic disruption duration in the plan. The mathematical expression for the random reset correction is: ; in, This indicates that after the repair operation, the first The maintenance plan is assigned to the first New permitted traffic disruption durations at each maintenance node A random number between 0 and 1 For the first The minimum total resource duration among all feasible resource combinations for a maintenance node. For the first The maximum permissible traffic disruption duration for each maintenance node; For non-conflict nodes, maintenance nodes with lower importance weights are selected with a preset probability to perform compression operations. The mathematical expression for the compression operation is: ; in, To indicate that after compression, the first New permitted traffic disruption durations at each maintenance node For the first The minimum total resource duration among all feasible resource combinations for a maintenance node. As the compression factor, For maintenance nodes Permissible traffic disruption duration, For the first The maximum permissible traffic disruption duration for each maintenance node; After the above random reset, correction and compression operations, iterative optimization is carried out until the preset maximum number of iterations is reached. The individual with the highest comprehensive fitness score in the population after the iteration ends is selected as the optimal maintenance time quota scheme.

[0012] Preferably, the process of generating the maintenance plan in step S5 specifically includes: The optimal maintenance time quota scheme is analyzed to obtain the allowable traffic interruption duration allocated to each maintenance node; For each maintenance node, the resource combination that satisfies the allowable traffic interruption duration constraint and has the minimum total resource duration is locked in the maintenance operation resource library; A construction time window is generated based on the allowed traffic disruption duration, and the construction time window is combined with the locked resources and encapsulated into a work order; The work order is sent to the maintenance operation terminal to complete the maintenance operation.

[0013] The road and bridge maintenance intelligent management system based on big data includes a data collection module, a traffic flow prediction module, a maintenance plan generation module, an optimization module, and a maintenance module. The acquisition module is used to acquire basic data, which includes maintenance tasks, location data, static data and historical traffic flow data within the target maintenance area. The traffic flow prediction module is used to calculate the maximum allowable traffic interruption time for each maintenance node based on the basic data. The maintenance plan generation module is used to construct a maintenance plan based on the maintenance task type and calculate the estimated total duration of the maintenance plan. The optimization module is used to construct an initial population with the maximum allowable traffic interruption time as the upper limit and the allowable traffic interruption time allocated to the maintenance nodes as the population individuals, and to use a genetic algorithm to iteratively optimize the population individuals to obtain the optimal maintenance time quota scheme. The genetic algorithm includes random reset correction and compression operations. The maintenance module is used to generate a maintenance plan based on the optimal maintenance time quota scheme.

[0014] The beneficial effects of this invention are as follows: This invention constructs a traffic saturation term by introducing a confidence level coefficient and the standard deviation of traffic flow, and establishes a nonlinear penalty mechanism by combining the comprehensive importance weight of road network nodes. As the importance of maintenance nodes increases, the allowable traffic interruption time decreases exponentially, avoiding regional traffic paralysis caused by excessive occupation of core nodes. In the calculation of the maintenance plan's duration, a dynamic correlation mechanism between the environmental sensitivity coefficient and the waiting time of material standard processes is introduced. By constructing a maintenance material attribute matrix, the estimated total duration can be calculated based on the real-time ambient temperature at the construction site. A genetic algorithm with repair and compression operations is used to achieve intelligent optimization of maintenance time quotas. Through the constraint violation penalty term in the comprehensive fitness scoring function, physically infeasible solutions can be automatically identified and eliminated during the evolution process. This ensures that the final generated maintenance plan can minimize road occupancy time while strictly adhering to traffic congestion control red lines, achieving the optimal balance between road maintenance efficiency and urban traffic flow. Attached Figure Description

[0015] Figure 1 A flowchart illustrating the steps of a road and bridge maintenance intelligent management method based on big data, provided as an embodiment of the present invention. Detailed Implementation

[0016] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0017] Example 1, referring to Figure 1 It provides a smart management method for road and bridge maintenance based on big data, including the following steps: Step S1: Obtain basic data, which includes maintenance tasks, location data, static data, and historical traffic flow data within the target maintenance area; Step S2: Based on the basic data, calculate the maximum allowable traffic disruption duration for each maintenance node; Step S3: Based on the maintenance task type, construct a maintenance plan and calculate the estimated total duration of the maintenance plan; Step S4: Using the maximum allowable traffic interruption time as the upper limit and the allowable traffic interruption time allocated to the maintenance nodes as the population individuals, construct an initial population, and use a genetic algorithm to iteratively optimize the population individuals to obtain the optimal maintenance time quota scheme. The genetic algorithm includes random reset correction and compression operations. Step S5: Generate a maintenance plan based on the optimal maintenance time quota scheme.

[0018] Unlike traditional methods that rely solely on experience to formulate maintenance plans, this approach introduces a genetic algorithm with repair and compensation operations. It can automatically find the optimal maintenance time quota that meets physical schedule requirements and minimizes traffic impact, using the calculated maximum allowable traffic interruption duration as a rigid upper limit. This not only achieves a scientific balance between maintenance schedule and traffic flow, but also ensures that the final maintenance plan is theoretically globally optimal through iterative optimization of the algorithm, effectively improving the level of intelligence in road and bridge maintenance management.

[0019] In step S1, the maintenance tasks include maintenance nodes, the type of maintenance task for each maintenance node, the number of lanes to be closed, and the planned construction period. Location data includes the ID, spatial coordinates, and physical distance between each road and bridge maintenance node within the target maintenance area; Static data includes the design capacity of maintenance nodes, lane number configuration information, specified physical construction time windows, and ambient temperature; Historical traffic flow data includes the average daily traffic volume, daily traffic volume, and time-specific traffic volume of each maintenance node in the target maintenance area within a preset historical period.

[0020] Step S2, the process of calculating the maximum permissible traffic disruption duration includes: With the goal of maximizing the overall traffic efficiency of the road network, a function for the maximum permissible traffic interruption duration is constructed. The mathematical expression for the maximum permissible traffic interruption duration is as follows: The mathematical expression for the maximum permissible traffic disruption duration is: ; in, For maintenance nodes Maximum permissible traffic disruption duration This refers to the maximum physically available time window for construction, such as a maximum nighttime road closure of 8 hours. This is the confidence level coefficient, used to set the reliability level of traffic congestion control. In this embodiment, the confidence level is set to 95%, corresponding to the coefficient under a normal distribution. This means that there is a 95% probability that construction will not cause serious congestion. To determine the average traffic flow during the construction period, statistical analysis of the traffic flow matrix was performed to represent the general traffic demand during that period. To determine the standard deviation of traffic flow during the construction period, statistical analysis of the traffic flow matrix was conducted. The standard deviation was introduced to quantify the volatility risk of traffic flow, serving as a safety margin for handling sudden traffic peaks. The design traffic capacity (unit: vehicles / hour) for maintenance nodes is derived from road design specifications and drawing data. This is the lane reduction factor, derived from the planned number of lanes to be closed. For example, if two lanes out of a two-way four-lane road are closed for construction, then... It is 0.5. For the adjustment constant (preferred in this embodiment) ), used for dimensional normalization adjustment, Assign importance weights to maintenance node i; For traffic saturation, the numerator This represents the predicted peak traffic flow that takes into account the risk of random fluctuations, compared to using only the mean. This introduces the standard deviation. and confidence coefficient It can effectively cover random fluctuations in traffic flow, improve the robustness of quota calculation, and reduce the denominator. This represents the remaining traffic capacity of the road segment during construction. Overall, it characterizes the traffic saturation level of the road segment during construction. A higher traffic saturation level means a smaller proportion of time during which complete traffic closure is permissible; if the traffic saturation level is greater than 1, then... If the designed traffic capacity is exceeded, the maximum permissible traffic disruption duration of 0.5 hours will be used as the protection mechanism. An exponential function is used as the importance penalty term. As the denominator, the aim is to introduce a non-linear penalty mechanism. As the importance weight of maintenance nodes increases linearly, the allowable traffic interruption time will decrease exponentially, thereby implementing stricter control over key maintenance nodes. The calculated allowable traffic disruption duration is based on the overall importance of the maintenance node in the road network. and the risk of traffic flow fluctuations during that period To ensure the overall traffic efficiency of the road network, maintenance procedures that require traffic closure at this maintenance node must be completed within the permitted traffic closure duration.

[0021] This invention constructs a maximum permissible traffic interruption duration function, introducing a confidence level coefficient and traffic flow standard deviation to construct a traffic saturation term. This effectively quantifies and covers the risk of random fluctuations in traffic flow during the planned construction period, significantly improving the robustness of quota calculation in the face of sudden traffic peaks. More importantly, the function uses a denominator term with node importance weight as the exponent, establishing a nonlinear penalty mechanism. As the importance of maintenance nodes increases, their permissible traffic interruption duration decreases exponentially. This design ensures the strictest schedule control for key transportation hubs, effectively preventing regional road network traffic paralysis caused by excessive occupation of core nodes.

[0022] The process of assigning comprehensive importance weights to maintenance nodes specifically includes: Roads or bridges with unique IDs are used as maintenance nodes, and the road network topology is constructed by combining the connection relationships of the maintenance nodes. The betweenness centrality of all nodes in the road network topology is calculated using the Brandes algorithm. The reciprocal of the sum of the distances from the maintenance node to all other maintenance nodes in the road network topology is used as the compactness. The average daily traffic flow is extracted from historical traffic flow data, and the extreme value method is used to normalize the betweenness centrality, compactness, and average daily traffic flow. The normalized betweenness centrality, compactness, and average daily traffic volume are used as evaluation indicators to calculate the first weight. The process of calculating the first weight specifically includes: Calculate the feature weight of any maintenance node under any evaluation index, calculate the information entropy based on the feature weight, and then calculate the first weight of the evaluation index based on the information entropy. The mathematical expression for the characteristic proportion is: ; in, For the first Under the evaluation index, the first The characteristic proportion of each maintenance node The number of maintenance nodes, For the first The first maintenance node The numerical values ​​of each evaluation indicator; The mathematical expression for information entropy is: ; in, For the first Information entropy of each indicator The number of maintenance nodes, For the first The first indicator The characteristic proportion of each maintenance node; The mathematical expression for the first weight is: ; in, For the first The first weight of each evaluation indicator For the first Information entropy of each indicator For the first Information entropy of each indicator The weight is the sum of the information entropy of the three evaluation indicators. It reflects the amount of information carried by the indicator itself; the greater the data difference, the higher the weight. An evaluation matrix is ​​constructed based on the normalized betweenness centrality, compactness, and average daily traffic flow. The rows of the evaluation matrix represent maintenance nodes, and the columns represent the normalized evaluation indicators. Based on the evaluation matrix, the comprehensive information content of the evaluation indicators is calculated. The mathematical expression for the comprehensive information content is: ; in, For the first The standard deviation of each evaluation indicator For the first The Pearson correlation coefficient between the k-th evaluation index and the k-th evaluation index Characteristic indicators The stronger the correlation with other indicators, the greater the potential conflict. The closer it is to 1), the less conflict there is and the less information there is. Normalize the total information to obtain the second weight. The first and second weights are merged using a linear weighting method to obtain the combined weights of each evaluation index. The combined weights of the three indices are then concatenated into a column vector to obtain the combined weight vector. The product of the evaluation matrix and the combined weight vector is used as the importance weight vector, and each element in the importance weight vector is the importance weight of the corresponding target maintenance node.

[0023] This embodiment aims to solve the technical problem of lacking quantitative constraints on traffic interruption duration in the prior art. By establishing a mathematical model based on the road network topology and random traffic flow characteristics, the maximum allowable traffic interruption duration of each road segment in a specific time period is calculated, i.e., the spatial and temporal right-of-way quota, which serves as a rigid constraint condition for subsequent lower-level operation matching. In order to objectively quantify the importance of each road segment in the road network, this embodiment adopts a combined weighting strategy to calculate the importance weight of each maintenance node; The betweenness centrality of all maintenance nodes in a road network topology is calculated using Brandes' algorithm. The mathematical expression for betweenness centrality is: ; in, Represents maintenance nodes in the network To the maintenance point The total number of shortest paths, Indicates maintenance nodes To the maintenance point The shortest path passes through maintenance nodes The number of paths, betweenness centrality reflects the mediating ability of a maintenance node as a road network hub. The larger the betweenness centrality value, the stronger the mediating role of the maintenance node as a transportation hub. In order to balance the discreteness of the data with the correlation between the indicators, a linear weighting method is used to fuse the first weight and the second weight, and the weight coefficients of the first weight and the second weight are both 0.5. The range of values ​​for importance weights is: The higher the importance weight value, the more critical the topological position of the maintenance node in the road network, and the more significant the road network-level impact of traffic interruption on it. Therefore, the traffic interruption duration allocated to the maintenance node should be more stringent.

[0024] This invention employs a combined weighting strategy to calculate the comprehensive importance of maintenance nodes, effectively overcoming the one-sidedness of single-indicator evaluation. It uses the Brandes algorithm to calculate betweenness centrality to characterize the node's hub-and-spoke capability, combining density and average daily traffic flow to comprehensively measure the node's topological position and actual load. In weight calculation, information entropy is used to determine objective weights to reflect data differences, while Pearson correlation coefficient is used to calculate the conflict between indicators and adjust the weights accordingly. Finally, through linear weighted fusion, the invention retains the information content of the indicators themselves while eliminating the influence of information redundancy between indicators, making the calculated node importance weights more objective and accurate.

[0025] The process of obtaining the mean and standard deviation of traffic flow during the planned construction period specifically includes: The planned construction period is divided into time slices according to the preset time window to construct a traffic flow matrix; The values ​​of the elements in the traffic flow matrix represent the actual traffic flow for the corresponding day and time. The mean of all elements in the traffic flow matrix is ​​the mean of the traffic flow during the planned construction period, and the standard deviation of all elements in the traffic flow matrix is ​​the standard deviation of the traffic flow during the planned construction period.

[0026] In a specific embodiment of the present invention, historical traffic flow data for each day of the past year for the target maintenance section during the planned construction period, such as from 22:00 to 06:00 the next day, is extracted and structured into a traffic flow matrix. The row vectors of the traffic flow matrix represent the traffic flow on different days at the same time, and the column vectors of the traffic flow matrix represent the traffic flow at different times on the same day. In this embodiment, the planned construction period is sliced ​​into time windows (15 minutes in this embodiment). The elements of the traffic flow matrix represent the actual traffic flow on the corresponding day and at the corresponding time, in units of vehicles per hour.

[0027] This invention constructs a structured traffic flow matrix by finely slicing the planned construction period into preset windows. This not only obtains the mean traffic flow but also accurately extracts the standard deviation of traffic flow through matrix statistical analysis, thereby capturing the traffic flow fluctuation characteristics of different dates at the same time. Compared with using only coarse daily average traffic data, this method can reveal the discrete characteristics of traffic flow at a micro time scale, providing input parameters for calculating the risk margin in the maximum allowable traffic interruption duration and ensuring the model's sensitivity to traffic tidal phenomena.

[0028] Step S3, the specific process of calculating the expected total construction period for each maintenance plan includes: Based on the maintenance plan, identify the current target maintenance task type, and for the identified task type, extract suitable operation resources from the maintenance operation resource library, including a variety of optional maintenance materials and a variety of optional maintenance equipment combinations; If the target maintenance task is asphalt repair, there are multiple maintenance materials available, including hot-mix asphalt and cold-mix asphalt, and multiple maintenance equipment combinations available, including combinations of large milling machines and pavers, and combinations of small excavators and manual paving. Construct a maintenance material attribute matrix. The maintenance material attribute matrix is ​​used to list the behavioral maintenance materials, including the standard process waiting time and environmental sensitivity coefficient for each material. The environmental sensitivity coefficient represents the correction ratio of the material curing rate to a unit change in ambient temperature. For example, for repair and painting operations, the standard process waiting time refers to the time required for the material to cure, dry and cool. The environmental sensitivity coefficient is used to describe the degree of influence of temperature and humidity on the process waiting time. For example, asphalt cooling is affected by air temperature, and paint drying is affected by humidity. Construct a construction equipment efficiency matrix, where the construction equipment is the behavior and listed as the time for entry traffic control, core operation time and exit traffic opening time for each equipment combination; By arranging and combining all the sets of maintenance materials and construction equipment, a maintenance plan is generated. The mathematical expression for the estimated total construction period corresponding to each maintenance operation plan is as follows: ; in, The time spent on traffic control at the entrance The core task takes time, Traffic disruptions caused by the closure and reopening of the venue Standard processing time for materials. This is the material's environmental sensitivity coefficient, representing the percentage increase in curing time for every 1°C change in temperature. This coefficient is obtained from the material manufacturer. The current ambient temperature at the construction site. The standard laboratory temperature is 25°C in this example.

[0029] In one specific embodiment of the present invention, the maintenance resource library is a pre-set digital database that stores detailed parameters of materials and equipment required to complete various road and bridge maintenance tasks. Specifically, the maintenance resource library contains two core dimensions of data: maintenance material properties and construction equipment. The curing material properties are recorded, including the physicochemical characteristics of each optional material, such as the standard process waiting time, which refers to the time required for the material to cure, dry, and cool under standard conditions (e.g., 25°C). This is a correction factor used to characterize the effect of temperature or humidity changes on the curing speed of materials (e.g., how much the curing time increases by a percentage for every 1°C decrease in temperature). The construction equipment section records the operational efficiency of different combinations of mechanical equipment, including various equipment combination schemes for specific tasks. For example, for road repair, it can be a large-scale combination of large milling machines and pavers, or a small-scale combination of small excavators and manual paving. The core parameters are the time for traffic control upon entry, the time for equipment entry and placement and setting up of barriers, the core operation time, the actual time for excavation and filling operations, the time for clearing the site and opening up traffic, and the time for cleaning up the site and removing barriers. By utilizing generalized priority relationships, various maintenance tasks can be abstracted into a general sequence of procedures, and time constraints can be established. Any maintenance task can be decomposed into an entry traffic control period, a core operation period, a process waiting period, and a withdrawal and opening traffic period. For operations that do not require process waiting, such as cleaning, the process waiting period is 0.

[0030] In calculating the estimated total construction period, this invention establishes a dynamic correlation mechanism between ambient temperature and material curing time. By constructing a curing material property matrix and introducing standard process waiting time and environmental sensitivity coefficient, the curing and drying rate of the material can be corrected according to the real-time ambient temperature at the construction site. This overcomes the shortcomings of traditional methods that rely solely on fixed construction period estimates under ideal experimental conditions, ensuring that the calculated estimated total construction period conforms to physical and chemical laws. It effectively avoids potential engineering quality hazards caused by insufficient estimation in low-temperature environments or waste of traffic resources caused by excessive enclosure in high-temperature environments.

[0031] Step S4, the process of obtaining the optimal maintenance time quota plan, specifically includes: For maintenance nodes in the maintenance plan, a maintenance time quota scheme with a preset population size (50 in this embodiment) is randomly generated as the initial population. The maintenance time quota scheme includes the allowable traffic interruption time allocated to each maintenance node. The upper limit of the range of the allowable traffic interruption time allocated to each maintenance node is the maximum allowable traffic interruption time corresponding to that maintenance node. For each maintenance node in the plan, the maintenance operation resource library is traversed to obtain all feasible resource combinations that fit the maintenance node, and the minimum expected total duration among them is defined as the minimum total resource duration of the maintenance node. For each maintenance time quota scheme, a comprehensive fitness score is calculated. The comprehensive fitness score aims to minimize the weighted road network interruption time while satisfying dual constraints. The mathematical expression for the comprehensive fitness score is: ; in, For the plan The overall fitness score, The number of maintenance nodes, The maintenance time quota allocated to maintenance nodes in the maintenance time quota scheme Permissible traffic disruption duration, For maintenance nodes Importance weight, To prevent extremely small positive numbers with a denominator of zero (e.g.) ); The preset penalty coefficient (preferred in this embodiment) ), used to impose a strong penalty on solutions that violate the constraints. The preset penalty coefficient should be high enough to make the fitness of solutions that violate the constraints much lower than that of feasible solutions. For the plan The constraint violation penalty term is expressed mathematically as follows: ; in, For maintenance nodes The minimum total resource duration among all feasible resource combinations. For maintenance nodes Maximum permissible traffic disruption duration; The overall fitness score indicates the duration of the allocated time. Less than minimum resource duration or greater than the maximum allowed duration At that time, penalty items Rapidly increasing, leading to fitness Approaching zero, thus automatically eliminating infeasible solutions during the evolutionary process, when the condition is met. At that time, the algorithm focuses on optimizing the weighted blocking duration. .

[0032] This invention constructs a comprehensive fitness scoring function, transforming multiple constraints into the driving force for optimization. By introducing a constraint violation penalty term, the comprehensive fitness scoring function can automatically identify schemes with an allocation time shorter than the minimum resource duration or longer than the maximum allowable duration, i.e., physically infeasible and traffic-infeasible schemes. Through a strong penalty coefficient, its fitness is brought close to zero, thereby automatically eliminating inferior solutions during the evolution process. At the same time, for feasible solutions, the algorithm strives to minimize the weighted blocking time. This means that, under the premise of satisfying constraints, priority is given to quota schemes that can significantly reduce the overall traffic impact of the road network, thus achieving the unity of constraint satisfaction and objective optimization.

[0033] The process of obtaining the optimal maintenance time quota plan also includes: Based on the comprehensive fitness score of each maintenance time quota scheme, offspring schemes are generated through roulette wheel selection and cross-selection. During the mutation phase, each maintenance node in the offspring plan is examined. If the allocated allowable traffic interruption duration is less than its corresponding minimum total resource duration, it is identified as a schedule conflict node. Schedule conflict nodes are then subject to tiered processing, which includes: If the minimum total resource duration of a project conflict node is greater than the maximum allowable traffic disruption duration, it means that even with the most efficient resource combination, the project cannot be completed within the specified traffic restrictions, which is a physically infeasible state. The overall fitness score of the solution will be forcibly set to 0. If the minimum total resource duration of a conflicting node is less than or equal to the maximum allowable traffic interruption duration, it indicates that a feasible construction time window exists. In this case, the original allowable traffic interruption duration that does not meet the conditions is discarded, and a new allowable traffic interruption duration with random reset is generated within the feasible interval between the minimum total resource duration and the maximum allowable traffic interruption duration to overwrite the old allowable traffic interruption duration. The mathematical expression for random reset is: ; in, This indicates that after the repair operation, the first The maintenance plan is assigned to the first New permitted traffic disruption durations at each maintenance node A random number between 0 and 1 For the first The minimum total resource duration among all feasible resource combinations for a maintenance node. For the first The maximum allowable traffic interruption time for each maintenance node; this step eliminates the conflict of insufficient construction period by randomly selecting values ​​between the upper and lower limits of physical feasibility, and avoids the search stagnation caused by fixing the duration to a single value. For non-conflict nodes, in order to further improve the overall traffic flow of the road network, maintenance nodes with lower importance weights are selected with a preset probability (0.15~0.30 in this embodiment) to perform compression operations. This approximates the allowable traffic interruption time of the maintenance node with its minimum total resource duration, forcing the node to match a more efficient resource combination. The mathematical expression for the compression operation is:

[0034] in, To indicate that after compression, the first New permitted traffic disruption durations at each maintenance node For the first The minimum total resource duration among all feasible resource combinations for a maintenance node. The compression factor is 0.9 to 0.95 in this embodiment. For maintenance nodes Permissible traffic disruption duration, For the first The maximum permissible traffic disruption duration for each maintenance node; After the above random reset, correction and compression operations, iterative optimization is performed until the preset maximum number of iterations is reached (200 times in this embodiment). The individual with the highest comprehensive fitness score in the population after the iteration is completed is selected as the optimal maintenance time quota scheme.

[0035] This invention introduces random reset correction and compression operations into the genetic algorithm, which significantly improves the optimization efficiency and solution quality of the algorithm. Random reset correction is implemented for nodes with conflicting construction periods. By re-evaluating the values ​​within the upper and lower limits of physical feasibility, invalid solutions are eliminated and search stagnation caused by a single value is avoided, thus maintaining the diversity of the population. The compression operation implemented for non-conflicting nodes forces the allowable duration of non-critical nodes to approach their minimum resource construction period with a preset probability, actively guiding the system to match more efficient resource combinations. These two operations make the algorithm no longer a passive selection but an active evolution, ensuring that the final solution compresses the road occupancy time to the greatest extent while strictly adhering to traffic red lines.

[0036] Step S5, the process of generating the maintenance plan, specifically includes: Analyze the optimal maintenance time quota scheme and obtain the allowable traffic interruption duration allocated to each maintenance node; For each maintenance node, the resource combination that satisfies the allowable traffic interruption duration constraint and minimizes the total resource duration is locked in the maintenance operation resource library; A construction time window is generated based on the allowed traffic disruption duration, and the construction time window is combined with the locked resources and packaged into a work order; Work orders are sent to the maintenance operation terminal to guide the completion of maintenance operations using resource combinations within the construction time window.

[0037] In one specific embodiment of the present invention, based on the optimal maintenance time quota scheme, the resource combination with the minimum total resource duration in the last iteration of the optimal maintenance time quota scheme is selected; Specifically, the optimal maintenance time quota scheme determines the allowable traffic interruption time for each maintenance node in the entire road network while taking into account both traffic efficiency and physical feasibility. Based on this time limit as a rigid boundary, the maintenance operation resource library is traversed again. From all feasible resource combinations that can be completed within this time limit, the combination with the shortest total project duration is selected as the execution standard to ensure that the construction process has the maximum safety margin. Build digital work orders, which specifically include: The precise entry and exit times (i.e., construction time windows) are obtained by converting the allowed traffic interruption duration. Detailed parameters of the specified resource combination, including specific types of maintenance materials, types of construction machinery and equipment, and process parameters; Digital work orders are pushed to the maintenance operation terminal of the on-site construction manager in real time via wireless network. After receiving the instructions, the maintenance operation terminal locks the specified resource combination and monitors the on-site construction progress to ensure that the maintenance work is completed and traffic is opened strictly within the specified construction time window.

[0038] This invention analyzes the optimal maintenance time quota scheme, which can automatically lock in the best resource combination that minimizes the total project duration and generate a precise construction time window accordingly. This information is packaged into digital work orders and pushed to the maintenance operation terminal in real time, giving on-site construction clear time limits and resource allocation standards. This not only eliminates the arbitrariness of on-site execution and ensures that the construction process strictly leaves a safety margin, but also ensures that the optimization results of complex mathematical models can be truly transformed into standardized on-site operation behavior, effectively improving the execution efficiency and compliance of maintenance projects.

[0039] The road and bridge maintenance intelligent management system based on big data includes a data collection module, a traffic flow prediction module, a maintenance plan generation module, an optimization module, and a maintenance module. The data acquisition module is used to obtain basic data, which includes maintenance tasks, location data, static data, and historical traffic flow data within the target maintenance area. The traffic flow prediction module is used to calculate the maximum permissible traffic disruption duration for each maintenance node based on basic data. The maintenance plan generation module is used to construct maintenance plans based on the maintenance task type and calculate the estimated total duration of the maintenance plan. The optimization module is used to construct an initial population with the maximum allowable traffic interruption time as the upper limit and the allowable traffic interruption time allocated to the maintenance nodes as the population individuals. The genetic algorithm is used to iteratively optimize the population individuals to obtain the optimal maintenance time quota scheme. The genetic algorithm includes random reset correction and compression operations. The maintenance module is used to generate maintenance plans based on the optimal maintenance time quota scheme.

[0040] This invention constructs a traffic saturation term by introducing a confidence level coefficient and the standard deviation of traffic flow, which can quantify and cover the risk of random fluctuations in traffic flow during the planned construction period, significantly improving the robustness of quota calculation in the face of sudden traffic peaks. This invention also constructs a nonlinear penalty mechanism by combining the comprehensive importance weight of road network nodes. As the importance of maintenance nodes increases, the allowable traffic interruption time decreases exponentially, thereby ensuring that the intensity of construction control at key hub nodes matches their status in the road network and avoiding regional traffic paralysis caused by excessive occupation of core nodes. In the calculation of the maintenance plan's construction period, a dynamic correlation mechanism between the environmental sensitivity coefficient and the waiting time of the material standard process was introduced. By constructing a maintenance material attribute matrix, the curing and drying rates of materials such as asphalt and coatings can be corrected according to the real-time ambient temperature at the construction site. The total expected construction period, including the entire process of entry, core operations and withdrawal, can be accurately calculated. This calculation method overcomes the shortcomings of traditional methods that rely solely on experience estimates, ensuring that the construction plan conforms to physical and chemical laws and effectively avoiding construction delays caused by environmental factors or potential engineering quality hazards caused by premature opening of traffic. This invention utilizes a genetic algorithm with repair and compression operations to achieve intelligent optimization of maintenance time quotas. By incorporating constraint violation penalties in the fitness scoring function, it can automatically identify and eliminate physically infeasible solutions during the evolutionary process. In particular, the random reset correction implemented for conflicting nodes and the compression operation implemented for non-conflicting nodes not only effectively resolve the contradiction between the maximum allowable traffic interruption time and the minimum total resource duration, but also force the system to actively match more efficient resource combinations. This allows the final maintenance plan to minimize road occupancy time while strictly adhering to traffic congestion control limits, achieving the best balance between road maintenance efficiency and urban traffic flow.

[0041] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0042] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the protection scope of the present invention.

Claims

1. A road and bridge maintenance intelligent management method based on big data, characterized in that, Includes the following steps: Step S1: Obtain basic data, which includes maintenance tasks, location data, static data, and historical traffic flow data within the target maintenance area; Step S2: Based on the aforementioned basic data, calculate the maximum permissible traffic disruption duration for each maintenance node; Step S3: Based on the maintenance task type, construct a maintenance plan and calculate the estimated total duration of the maintenance plan; Step S4: Using the maximum allowable traffic interruption time as the upper limit, and the allowable traffic interruption time allocated to the maintenance node as the population individuals, an initial population is constructed, and the population individuals are iteratively optimized using a genetic algorithm to obtain the optimal maintenance time quota scheme. The genetic algorithm includes random reset correction and compression operations. Step S5: Generate a maintenance plan based on the optimal maintenance time quota scheme.

2. The intelligent management method for road and bridge maintenance based on big data as described in claim 1, characterized in that, In step S1, the maintenance task includes maintenance nodes, maintenance task types for maintenance nodes, number of lanes to be closed, and planned construction period. The location data includes the ID, spatial coordinates, and physical distance between each road and bridge maintenance node within the target maintenance area; The static data includes the design traffic capacity of the maintenance nodes, lane number configuration information, the specified physical construction time window, and ambient temperature. The historical traffic flow data includes the average daily traffic flow, daily traffic flow, and time-specific traffic flow at each maintenance node in the target maintenance area within a preset historical period.

3. The intelligent management method for road and bridge maintenance based on big data as described in claim 2, characterized in that, In step S2, the process of calculating the maximum permissible traffic disruption duration includes: With the goal of maximizing the overall traffic efficiency of the road network, a function for the maximum permissible traffic interruption duration is constructed. The mathematical expression for the maximum permissible traffic interruption duration is as follows: The mathematical expression for the maximum permissible traffic disruption duration is: ； in, For maintenance nodes Maximum permissible traffic disruption duration This is the largest physically available time window for construction. The confidence level coefficient is... To determine the average traffic flow during the construction period, To determine the standard deviation of traffic flow during the construction period, To maintain the design traffic capacity of the nodes, This is the lane reduction factor. As an adjustment constant, The importance weight of maintenance node i.

4. The intelligent management method for road and bridge maintenance based on big data as described in claim 3, characterized in that, The process of calculating the overall importance weight of maintenance nodes specifically includes: The road network topology is constructed by combining the connection relationships of maintenance nodes; The betweenness centrality of all nodes in the road network topology is calculated using the Brandes algorithm. The reciprocal of the sum of the distances from the maintenance node to all other maintenance nodes in the road network topology is used as the compactness. The average daily traffic flow is extracted from historical traffic flow data. The betweenness centrality, compactness, and average daily traffic flow are normalized using the extreme value method. The normalized betweenness centrality, compactness, and average daily traffic volume are used as evaluation indicators to calculate the first weight. The process of calculating the first weight specifically includes: Calculate the feature weight of any maintenance node under any evaluation index. The feature weight is the value of the maintenance node under the evaluation index divided by the sum of the values ​​of the evaluation index of all maintenance nodes. Calculate the information entropy based on the feature weight, and then calculate the first weight of the evaluation index based on the information entropy. The mathematical expression for the first weight is: ； in, For the first The first weight of each evaluation indicator For the first Information entropy of each indicator For the first Information entropy of each indicator; An evaluation matrix is ​​constructed based on the normalized betweenness centrality, compactness, and average daily traffic flow. The rows of the evaluation matrix represent maintenance nodes, and the columns represent the normalized evaluation indicators. Based on the evaluation matrix, the comprehensive information content of the evaluation indicators is calculated, and the mathematical expression for the comprehensive information content is: ； in, For the first The standard deviation of each evaluation indicator For the first The Pearson correlation coefficient between the k-th evaluation index and the k-th evaluation index Characteristic indicators Conflicts with other indicators; The comprehensive information content is normalized to obtain the second weight; The first and second weights are merged using a linear weighting method to obtain the combined weights of each evaluation index. The combined weights of the three indices are then concatenated into a column vector to obtain the combined weight vector. The product of the evaluation matrix and the combined weight vector is used as the importance weight vector, and each element in the importance weight vector is the importance weight of the corresponding target maintenance node.

5. The intelligent management method for road and bridge maintenance based on big data as described in claim 3, characterized in that, The process of obtaining the mean traffic flow and the standard deviation of the traffic flow during the planned construction period specifically includes: The planned construction period is divided into time slices according to the preset time window to construct a traffic flow matrix; The values ​​of the elements in the traffic flow matrix represent the actual traffic flow for the corresponding day and time. The mean of all elements in the traffic flow matrix is ​​the mean of the traffic flow during the planned construction period, and the standard deviation of all elements in the traffic flow matrix is ​​the standard deviation of the traffic flow during the planned construction period.

6. The intelligent management method for road and bridge maintenance based on big data as described in claim 3, characterized in that, In step S3, the specific process of calculating the expected total construction period for each maintenance plan includes: Based on the maintenance plan, identify the current target maintenance task type, and for the identified task type, extract suitable operation resources from the maintenance operation resource library, including a variety of optional maintenance materials and a variety of optional maintenance equipment combinations; Construct a curing material attribute matrix, wherein the curing material attribute matrix is ​​a behavior curing material, and the standard process waiting time and environmental sensitivity coefficient are listed for each material. The environmental sensitivity coefficient represents the correction ratio of the material curing rate to the unit change in ambient temperature. Construct a construction equipment efficiency matrix, where the matrix consists of construction equipment and lists the time spent on traffic control upon entry, the time spent on core operations, and the time spent opening the site for traffic for each equipment combination. The maintenance material set and the construction equipment set are combined in all possible arrangements to generate a maintenance plan; The mathematical expression for the estimated total construction period corresponding to each maintenance operation plan is as follows: ； in, The time spent on traffic control at the entrance The core task takes time, Traffic disruptions caused by the closure and reopening of the venue Standard processing time for materials. The environmental sensitivity coefficient of the material. The current ambient temperature at the construction site. This is the standard laboratory temperature.

7. The intelligent management method for road and bridge maintenance based on big data as described in claim 6, characterized in that, The process of obtaining the optimal maintenance time quota scheme in step S4 specifically includes: For maintenance nodes in the maintenance plan, a maintenance time quota scheme with a preset population size is randomly generated as the initial population. The maintenance time quota scheme includes the allowable traffic interruption time allocated to each maintenance node. The upper limit of the range of allowable traffic interruption time allocated to each maintenance node is the maximum allowable traffic interruption time corresponding to that maintenance node. For each maintenance node in the scheme, the maintenance operation resource library is traversed to obtain all feasible resource combinations that fit the maintenance node, and the minimum expected total duration among them is defined as the minimum total resource duration of the maintenance node. For each maintenance time quota scheme, a comprehensive fitness score is calculated. This comprehensive fitness score aims to minimize the weighted road network interruption duration while satisfying dual constraints. The mathematical expression for the comprehensive fitness score is: ； in, For the plan The overall fitness score, The number of maintenance nodes, The maintenance time quota allocated to maintenance nodes in the maintenance time quota scheme Permissible traffic disruption duration, For maintenance nodes Importance weight, To prevent extremely small positive numbers with a denominator of zero, This is the preset penalty coefficient; For the plan The constraint violation penalty term is expressed mathematically as follows: ； in, For maintenance nodes The minimum total resource duration among all feasible resource combinations. For maintenance nodes The maximum permissible duration of traffic disruption.

8. The intelligent management method for road and bridge maintenance based on big data as described in claim 7, characterized in that, The process of obtaining the optimal maintenance time quota plan also includes: Based on the comprehensive fitness score of each maintenance time quota scheme, offspring schemes are generated through roulette wheel selection and cross-selection. During the mutation phase, each maintenance node in the offspring plan is examined. If the allocated allowable traffic interruption duration is less than its corresponding minimum total resource duration, it is identified as a schedule conflict node. Schedule conflict nodes are then subjected to tiered processing, which includes: If the minimum total resource duration of a project conflict node is greater than the maximum allowable traffic disruption duration, the overall fitness score of the solution will be forcibly set to 0. If the minimum total resource duration of a conflicting node is less than or equal to the maximum allowable traffic disruption duration, a random reset correction is applied to the allowable traffic disruption duration in the plan. The mathematical expression for the random reset correction is: ； in, This indicates that after the repair operation, the first The maintenance plan is assigned to the first New permitted traffic disruption durations at each maintenance node A random number between 0 and 1 For the first The minimum total resource duration among all feasible resource combinations for a maintenance node. For the first The maximum permissible traffic disruption duration for each maintenance node; For non-conflict nodes, maintenance nodes with lower importance weights are selected with a preset probability to perform compression operations. The mathematical expression for the compression operation is: in, To indicate that after compression, the first New permitted traffic disruption durations at each maintenance node For the first The minimum total resource duration among all feasible resource combinations for a maintenance node. As the compression factor, For maintenance nodes Permissible traffic disruption duration; For the first The maximum permissible traffic disruption duration for each maintenance node; After the above random reset, correction and compression operations, iterative optimization is carried out until the preset maximum number of iterations is reached. The individual with the highest comprehensive fitness score in the population after the iteration ends is selected as the optimal maintenance time quota scheme.

9. The intelligent management method for road and bridge maintenance based on big data as described in claim 8, characterized in that, The process of generating the maintenance plan in step S5 specifically includes: The optimal maintenance time quota scheme is analyzed to obtain the allowable traffic interruption duration allocated to each maintenance node; For each maintenance node, the resource combination that satisfies the allowable traffic interruption duration constraint and has the minimum total resource duration is locked in the maintenance operation resource library; A construction time window is generated based on the allowed traffic disruption duration, and the construction time window is combined with the locked resources and encapsulated into a work order; The work order is sent to the maintenance operation terminal to complete the maintenance operation.

10. A road and bridge maintenance intelligent management system based on big data, applied in the road and bridge maintenance intelligent management method based on big data as described in any one of claims 1-9, characterized in that, It includes a data collection module, a traffic flow prediction module, a maintenance plan generation module, an optimization module, and a maintenance module; The acquisition module is used to acquire basic data, which includes maintenance tasks, location data, static data and historical traffic flow data within the target maintenance area. The traffic flow prediction module is used to calculate the maximum allowable traffic interruption time for each maintenance node based on the basic data. The maintenance plan generation module is used to construct a maintenance plan based on the maintenance task type and calculate the estimated total duration of the maintenance plan. The optimization module is used to construct an initial population with the maximum allowable traffic interruption time as the upper limit and the allowable traffic interruption time allocated to the maintenance nodes as the population individuals, and to use a genetic algorithm to iteratively optimize the population individuals to obtain the optimal maintenance time quota scheme. The genetic algorithm includes random reset correction and compression operations. The maintenance module is used to generate a maintenance plan based on the optimal maintenance time quota scheme.

Images