Road maintenance decision support system based on digital twinning

Abstract

The invention relates to the technical field of road maintenance, and discloses a road maintenance decision support system based on digital twinning, which comprises a data acquisition module, a digital twinning module, a maintenance decision module, an intelligent monitoring module and a user interface module, wherein the data acquisition module is used for acquiring various data of a road in real time, including road surface conditions, traffic flow and environmental factors; wherein the digital twin module is used for establishing a road virtual model, performing simulation analysis and providing accurate data support for maintenance decision making; wherein the maintenance decision module is used for formulating a maintenance plan and strategy by utilizing an optimization algorithm and a data analysis technology based on the output of the digital twin module. According to the road maintenance decision support system based on the digital twinning, the digital twinning model of the road is constructed, and the real-time monitoring data and the advanced algorithm are combined, so that the intelligent support of the road maintenance decision is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of highway maintenance, and in particular to a highway maintenance decision support system based on digital twins. Background Art

[0002] The current highway maintenance decision-making process mostly relies on manual inspections and the experience accumulation of maintenance personnel. This traditional model is not only inefficient, but also difficult to guarantee accuracy, especially when faced with large-scale, complex and changeable maintenance needs. However, with the vigorous development of high-tech technologies such as the Internet of Things, big data, and artificial intelligence, the application of digital twin technology in the field of highway maintenance is increasingly attracting widespread attention from the industry.

[0003] Although the application of digital twin technology in the field of highway maintenance has begun to show its potential, it still faces many challenges in actual operation. Most digital twin applications are mainly focused on highway status monitoring and data analysis at the macro level, but they are unable to convert these macro data into specific maintenance decision support. Specifically, existing technologies can often only provide an overview of the overall operating status of the highway, but lack in-depth and refined analysis of specific maintenance issues such as pavement cracks and bridge structure damage. In addition, existing technologies are also insufficient in predicting maintenance needs, evaluating maintenance effects, and optimizing maintenance plans, making it difficult to provide comprehensive and accurate decision support. This defect has led to maintenance decisions still relying too much on manual judgment and experience accumulation, which is not only inefficient but also difficult to ensure accuracy. Summary of the invention

[0004] The purpose of this invention is to realize intelligent support for highway maintenance decision-making by constructing a digital twin model of the highway, combining real-time monitoring data and advanced algorithms, and propose a highway maintenance decision support system based on digital twins.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] A highway maintenance decision support system based on digital twins, comprising: a data acquisition module, a digital twin module, a maintenance decision module, an intelligent monitoring module and a user interface module;

[0007] The data acquisition module is used to collect various highway data in real time, including road conditions, traffic flow, and environmental factors;

[0008] The digital twin module is used to build a virtual model of the highway, conduct simulation analysis, and provide accurate data support for maintenance decisions;

[0009] The maintenance decision module formulates maintenance plans and strategies based on the output of the digital twin module using optimization algorithms and data analysis technology;

[0010] The intelligent monitoring module can monitor the road conditions in real time, detect potential problems in time, and send out alerts to users through the early warning system;

[0011] The user interface module provides an intuitive visual interface, which facilitates users to view system output and make decisions.

[0012] Based on the above technical solution, the present invention can also be improved as follows.

[0013] Furthermore, the data acquisition module also includes a pavement structure information acquisition unit, which uses laser scanning technology to obtain a three-dimensional model of the pavement and understands the structural integrity of the pavement by analyzing the model. At the same time, the data acquisition module also uses non-destructive testing technology, including rebound modulus testing, spectral analysis and seismic wave velocity testing, to obtain information on the thickness of the pavement, the interlayer bonding state and whether there are defects in the internal structure.

[0014] Furthermore, the data acquisition module also includes a traffic flow data acquisition unit and an environmental factor data acquisition unit. The traffic flow data acquisition unit records the number, speed and type of vehicles, as well as traffic congestion in real time through traffic flow sensors installed on the roadside. The environmental factor data acquisition unit uses meteorological sensors and environmental monitoring equipment to collect environmental factor data such as temperature, humidity and rainfall in real time in order to evaluate the performance and maintenance needs of the highway.

[0015] Furthermore, the digital twin module includes a data preprocessing unit, a geometric modeling unit and a physical modeling unit. The data preprocessing unit cleans, calibrates and fuses the raw data collected from various sensors and monitoring equipment to ensure the accuracy, consistency and integrity of the data. The geometric modeling unit uses a three-dimensional GIS platform and BIM software for geometric modeling, and establishes a three-dimensional geometric model of the highway according to design drawings and satellite remote sensing data. During the geometric modeling process, it is necessary to collect a variety of data such as ground terrain measurement data, satellite elevation data, road horizontal and vertical information, and texture material data, and use these data to provide the model with basic information on terrain, elevation, routes and visual effects.

[0016] Furthermore, the physical modeling unit constructs a complete digital twin model based on the established highway geometric model by adding comprehensive and accurate physical properties. The physical properties specifically include but are not limited to: Material properties: detailed recording of key parameters such as material type, material strength, material toughness, material thermal expansion coefficient, etc. of each component of the highway such as pavement layer, base layer, and slope; Mechanical properties: Comprehensive consideration of mechanical performance parameters such as stress distribution, deformation characteristics, fatigue life, etc. of the highway under traffic load, temperature change, humidity change and other conditions; Environmental factors: Comprehensive consideration of meteorological conditions such as rainfall, temperature, humidity, wind speed, wind direction, as well as geological factors such as geological conditions, soil type, and groundwater level.

[0017] Furthermore, the maintenance decision module uses a machine learning algorithm to conduct in-depth analysis of historical data and real-time data based on the output results of the digital twin module to predict the degree of road damage and traffic congestion.

[0018] Furthermore, the maintenance decision module needs to consider multiple factors, including road conditions, traffic patterns, financial constraints, and environmental impacts, and use optimization techniques such as linear programming, nonlinear programming, and heuristic algorithms to determine the most cost-effective maintenance method;

[0019] Objective function:

[0020]

[0021] minC is the total cost, is the cost of the ci-th maintenance method, xi is the selection variable of the ci-th maintenance method;

[0022] Constraints:

[0023]

[0024] During this process, the module will evaluate and compare multiple maintenance plans based on the preset objective function and constraints. The objective function is expressed as the minimization of the total cost, that is, selecting the combination of maintenance methods with the lowest cost, while the constraints ensure that the selected plan can meet the expected maintenance effect.

[0025] Furthermore, in the objective function, the maintenance decision module calculates the total cost based on the cost of each maintenance method and the selection variable, where the selection variable is 1, indicating that the maintenance method is selected, and 0, indicating that it is not selected. By solving the objective function, the module can find the combination of maintenance methods with the lowest cost. At the same time, in the constraints, the module sets the requirements for maintenance effects and considers the relationship between the effect of each maintenance method and the expected maintenance effect. Only when the sum of the maintenance effects of the selected schemes meets or exceeds the expected value will the scheme be accepted by the system. Finally, based on the optimization results, the maintenance decision module generates a detailed maintenance plan, including information such as the type, time and cost of maintenance activities, to provide clear and specific guidance for highway maintenance personnel.

[0026] Furthermore, in terms of real-time monitoring, the intelligent monitoring module uses Internet of Things sensor technology to monitor key parameters of the road surface, such as temperature, humidity, cracks, potholes, etc. These sensors are deployed at various key locations on the highway and can collect and transmit data to the monitoring center in real time. Big data analysis technology is used to predict and evaluate potential risks. By comparing historical data and real-time monitoring data, the system can identify abnormal data or trends and issue early warning signals accordingly. These early warning signals can include text messages, emails, APP push and other forms to ensure that users can receive early warning information in a timely manner and take corresponding countermeasures.

[0027] Furthermore, in the user interface module, the real-time and historical data of highway maintenance are clearly presented to the user through intuitive forms of expression such as charts and reports. These charts and reports include but are not limited to line charts, bar charts, pie charts, scatter plots, etc. They can intuitively display various key indicators of highway maintenance, such as the degree of road damage, traffic flow, maintenance cost, etc. At the same time, users can set maintenance goals, select maintenance methods, adjust maintenance plans, etc. according to their own needs and preferences. The system will calculate and display the effects and costs of the maintenance plans in real time based on the user's input, helping users make the best decision. The user interface module also supports multiple devices and platforms, such as computers, mobile phones, tablets, etc., so that users can view system outputs and make decisions anytime, anywhere.

[0028] Compared with the prior art, the technical solution of this application has the following beneficial technical effects:

[0029] Through the data acquisition module, the present invention can collect various highway data in real time and comprehensively, including but not limited to road conditions, traffic flow, environmental factors, etc. This feature greatly enriches the information sources required for maintenance decisions. Compared with the traditional manual inspection mode, it not only improves the efficiency and accuracy of data acquisition, but also enables maintenance decisions to be made based on more comprehensive and real data. Secondly, the establishment of the digital twin module provides accurate data support for highway maintenance decisions. By constructing a virtual model of the highway and conducting simulation analysis, the module can deeply explore the inherent laws of the highway operation status and provide a scientific basis for maintenance decisions. This feature overcomes the defects of existing digital twin technologies that mostly remain at the macro-level monitoring and data analysis, and realizes in-depth and refined analysis of specific maintenance issues. Furthermore, the maintenance decision-making module uses optimization algorithms and data analysis technology to formulate maintenance plans and strategies based on the output of the digital twin module. This module can not only make maintenance plans based on actual The intelligent monitoring module can dynamically adjust the maintenance plan based on real-time data, and can also help users choose the optimal maintenance strategy by comparing the costs and benefits of different maintenance plans. This not only improves the scientificity and accuracy of maintenance decisions, but also significantly reduces maintenance costs. In addition, the intelligent monitoring module can detect potential problems in a timely manner by monitoring the road conditions in real time, and send alarms to users through the early warning system. This feature enables maintenance personnel to carry out preventive maintenance before problems occur, avoiding greater losses caused by the deterioration of problems. At the same time, the intelligent monitoring module can also improve the pertinence and efficiency of maintenance work, so that maintenance resources can be more reasonably allocated. Finally, the user interface module provides an intuitive visual interface for users to view system output and make decisions. This feature not only lowers the technical threshold for maintenance decisions, but also improves the user experience. Through the visual interface, users can intuitively understand the current status and trends of highway maintenance, providing strong support for the formulation of scientific maintenance plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a system block diagram of a highway maintenance decision support system based on digital twins in the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Combination Figure 1As shown, a highway maintenance decision support system based on digital twins of the present invention includes: a data acquisition module, a digital twin module, a maintenance decision module, an intelligent monitoring module and a user interface module;

[0033] The data acquisition module is used to collect various highway data in real time, including road conditions, traffic flow, and environmental factors;

[0034] The digital twin module is used to build a virtual model of the highway and conduct simulation analysis to provide accurate data support for maintenance decisions;

[0035] The maintenance decision module formulates maintenance plans and strategies based on the output of the digital twin module using optimization algorithms and data analysis technology;

[0036] The intelligent monitoring module monitors the road conditions in real time, detects potential problems in time, and issues alerts to users through the early warning system;

[0037] The user interface module provides an intuitive visual interface, which makes it easy for users to view system output and make decisions.

[0038] In a preferred embodiment of the present invention, the data acquisition module further includes a pavement structure information acquisition unit, which uses laser scanning technology to acquire a three-dimensional model of the pavement, and understands the structural integrity of the pavement by analyzing the model. At the same time, the data acquisition module also uses non-destructive testing technology, including rebound modulus test, spectral analysis method and seismic wave velocity test, to obtain information on the thickness of the pavement, the interlayer bonding state and whether there are defects in the internal structure. The data acquisition module has been further refined and enhanced, especially the introduction of the pavement structure information acquisition unit. The addition of this unit significantly improves the system's monitoring ability of the structural integrity and internal state of the highway pavement. By acquiring a three-dimensional model of the pavement through laser scanning technology, the system can accurately depict the geometric shape of the pavement, and then analyze the structural integrity of the pavement, and timely discover potential cracks, potholes and other defects. At the same time, combined with non-destructive testing technologies such as rebound modulus test, spectral analysis method and seismic wave velocity test, the system can further obtain detailed information on the thickness of the pavement, the interlayer bonding state and whether there are defects in the internal structure. The comprehensive application of these technologies provides more comprehensive and accurate data support for maintenance decisions, greatly improving the pertinence and scientificity of maintenance decisions.

[0039] In a preferred embodiment of the present invention, the data collection module may further include a traffic flow data collection unit and an environmental factor data collection unit. The traffic flow data collection unit records the number, speed and type of vehicles, as well as traffic congestion in real time through traffic flow sensors installed on the roadside. The environmental factor data collection unit uses meteorological sensors and environmental monitoring equipment to collect environmental factor data such as temperature, humidity and rainfall in real time in order to evaluate the performance and maintenance needs of the highway. The addition of the traffic flow data collection unit and the environmental factor data collection unit significantly enhances the comprehensiveness and accuracy of the system's evaluation of the performance and maintenance needs of the highway. The traffic data collection unit can record the number, speed, type and traffic congestion of vehicles in real time through traffic flow sensors installed on the roadside, providing important data support for analyzing the characteristics of highway traffic flow and predicting traffic development trends. At the same time, the environmental factor data collection unit uses meteorological sensors and environmental monitoring equipment to collect real-time data on environmental factors such as temperature, humidity and rainfall. These data are of great significance for evaluating the aging rate of highway materials, the degree of road damage and the urgency of maintenance needs. Therefore, the addition of these two units enables the system to have a more comprehensive understanding of the usage status and maintenance needs of the highway, providing a strong guarantee for the formulation of scientific and reasonable maintenance plans.

[0040] In a preferred embodiment, the present invention can be further configured as follows: the digital twin module includes a data preprocessing unit, a geometric modeling unit and a physical modeling unit. The data preprocessing unit cleans, calibrates and fuses the raw data collected from various sensors and monitoring equipment to ensure the accuracy, consistency and integrity of the data. The geometric modeling unit uses a three-dimensional GIS platform and BIM software for geometric modeling, and establishes a three-dimensional geometric model of the highway according to design drawings and satellite remote sensing data. During the geometric modeling process, it is necessary to collect a variety of data such as ground terrain measurement data, satellite elevation data, road horizontal and vertical information, and texture material data, and use these data to provide the model with basic information on terrain, elevation, routes and visual effects. The data preprocessing unit, geometric modeling unit and physical modeling unit, this refinement not only improves the functionality and practicality of the digital twin module , and ensures the data accuracy and model precision of the highway maintenance decision support system. The data preprocessing unit, as the cornerstone of the digital twin module, effectively eliminates data errors by cleaning, calibrating and fusing the raw data collected from various sensors and monitoring equipment, ensuring the accuracy, consistency and integrity of the data, which provides reliable data support for subsequent modeling and simulation analysis. The geometric modeling unit uses advanced 3D GIS platform and BIM software to construct a 3D geometric model of the highway according to design drawings and satellite remote sensing data. This model not only accurately restores the geometric shape of the highway, but also collects a variety of information such as ground terrain measurement data, satellite elevation data, road horizontal and vertical information, and texture material data. It provides the model with basic information such as terrain, elevation, lines and visual effects, greatly enhancing the realism and practicality of the model.

[0041] In a preferred embodiment of the present invention, the physical modeling unit can be further configured as follows: on the basis of the established highway geometric model, the physical modeling unit constructs a complete digital twin model by adding comprehensive and accurate physical properties. The physical properties specifically include but are not limited to: material properties: detailed recording of key parameters such as material type, material strength, material toughness, material thermal expansion coefficient, etc. of each component of the highway such as the pavement layer, base layer, and slope; mechanical properties: comprehensive consideration of mechanical performance parameters such as stress distribution, deformation characteristics, fatigue life, etc. of the highway under conditions such as traffic load, temperature change, and humidity change; environmental factors: comprehensive consideration of meteorological conditions such as rainfall, temperature, humidity, wind speed, and wind direction, as well as geological conditions, soil type, groundwater level, and other geological factors. The physical modeling unit successfully constructs a complete digital twin model by adding comprehensive and accurate physical properties on the basis of the established highway geometric model. This measure significantly improves the digital twin model. Functionality and practicality provide more accurate and comprehensive data support for the highway maintenance decision support system. Specifically, the physical modeling unit records in detail the material properties of each component of the highway, such as the material type, material strength, material toughness, material thermal expansion coefficient and other key parameters of the pavement layer, base layer and slope. These parameters are crucial for evaluating the durability and service life of the highway. At the same time, the physical modeling unit also comprehensively considers the mechanical performance parameters of the highway under traffic loads, temperature changes, humidity changes and other conditions, such as stress distribution, deformation characteristics, fatigue life, etc. These parameters can reflect the actual performance of the highway under different working conditions and provide a scientific basis for maintenance decisions. In addition, the physical modeling unit also comprehensively considers meteorological conditions such as rainfall, temperature, humidity, wind speed, wind direction, as well as geological factors such as geological conditions, soil type, and groundwater level. These environmental factors are of great significance for evaluating the safety and stability of the highway.

[0042] In a preferred embodiment, the present invention can be further configured as follows: the maintenance decision module uses a machine learning algorithm to conduct an in-depth analysis of historical data and real-time data based on the output results of the digital twin module to predict the degree of road damage and traffic congestion. The maintenance decision module can use the comprehensive and accurate road surface information (such as material properties, mechanical properties, environmental factors, etc.) and traffic flow data provided by the digital twin module, combined with historical maintenance records and real-time monitoring data, to establish a prediction model through a machine learning algorithm. The model can accurately predict the degree of road damage, such as the development trends of common diseases such as cracks, potholes, and ruts, and provide maintenance personnel with timely early warning information. At the same time, the maintenance decision module can also predict traffic congestion, help traffic management departments formulate response measures in advance, and effectively alleviate traffic pressure. This function not only improves the efficiency of highway use, but also significantly improves the public's travel experience.

[0043] In a preferred embodiment, the present invention can be further configured as follows: the maintenance decision module needs to consider multiple factors, including road conditions, traffic patterns, financial constraints, and environmental impacts, and use optimization techniques such as linear programming, nonlinear programming, and heuristic algorithms to determine the most cost-effective maintenance method;

[0044] Objective function:

[0045]

[0046] minC is the total cost, is the cost of the ci-th maintenance method, xi is the selection variable of the ci-th maintenance method;

[0047] Constraints:

[0048]

[0049] During this process, the module will evaluate and compare multiple maintenance plans based on the preset objective function and constraints. The objective function is expressed as the minimization of the total cost, that is, selecting the combination of maintenance methods with the lowest cost, while the constraints ensure that the selected plan can meet the expected maintenance effect. On the basis of considering multiple factors (including road conditions, traffic patterns, financial constraints and environmental impacts, etc.), optimization techniques such as linear programming, nonlinear programming and heuristic algorithms are used to determine the most cost-effective maintenance method. This design not only reflects the high attention paid to the scientificity and rationality of maintenance decisions, but also brings significant beneficial effects in practical applications. Specifically, by comprehensively considering multiple factors, the maintenance decision-making module can more comprehensively evaluate the advantages and disadvantages of different maintenance plans, thereby ensuring that the selected plan can not only meet the expected maintenance effect, but also minimize the total cost. This not only helps to improve the economic benefits of highway maintenance, but also reduces the burden on public finances and achieves the optimal allocation of maintenance resources.

[0050] In a preferred embodiment of the present invention, the maintenance decision module can be further configured as follows: in the objective function, the maintenance decision module calculates the total cost according to the cost of each maintenance method and the selection variable, wherein the selection variable is 1 to indicate that the maintenance method is selected, and 0 to indicate that the maintenance method is not selected. By solving the objective function, the module can find the maintenance method combination with the lowest cost. At the same time, in the constraint conditions, the module sets the maintenance effect requirements and considers the relationship between the effect of each maintenance method and the expected maintenance effect. Only when the total maintenance effect of the selected scheme meets or exceeds the expected value will the scheme be accepted by the system. Finally, according to the optimization results, the maintenance decision module generates a detailed maintenance plan, including the type, time and cost of the maintenance activities, to provide clear and specific guidance for highway maintenance personnel. The module calculates the maintenance effect according to the cost of each maintenance method and the selection variable (1 This design enables the module to automatically search and find the combination of maintenance methods with the lowest cost. At the same time, in the constraints, the module sets the requirements for maintenance effects and considers the relationship between the effect of each maintenance method and the expected maintenance effect. Only when the sum of the maintenance effects of the selected schemes meets or exceeds the expected value will the scheme be accepted by the system. This dual mechanism not only ensures the economy of maintenance decisions, but also ensures the effectiveness of maintenance effects. Finally, based on the optimization results, the maintenance decision module can generate a detailed maintenance plan, including information such as the type, time and cost of maintenance activities, providing clear and specific guidance for highway maintenance personnel. This beneficial effect not only improves the scientificity and accuracy of maintenance decisions, but also greatly reduces the workload of maintenance personnel and improves the overall efficiency of maintenance work.

[0051] In a preferred embodiment of the present invention, the intelligent monitoring module can be further configured as follows: In terms of real-time monitoring, the intelligent monitoring module uses the Internet of Things sensor technology to monitor key parameters such as temperature, humidity, cracks, potholes, etc. of the road surface in real time. These sensors are deployed at various key locations on the road, and can collect and transmit data to the monitoring center in real time, and use big data analysis technology to predict and evaluate potential risks. By comparing historical data and real-time monitoring data, the system can identify abnormal data or trends and issue early warning signals accordingly. These early warning signals can include text messages, emails, APP push and other forms to ensure that users can receive early warning information in a timely manner and take corresponding countermeasures. Through the Internet of Things sensor technology, the intelligent monitoring module can The key parameters of the road surface, such as temperature, humidity, cracks, potholes, etc., are collected in real time and the data is transmitted to the monitoring center. This real-time monitoring method greatly improves the accuracy and timeliness of the data, enabling the monitoring center to quickly grasp the actual condition of the road surface. Secondly, using big data analysis technology, the intelligent monitoring module can compare historical data and real-time monitoring data, identify abnormal data or trends, and thus issue early warning signals in a timely manner. These early warning signals are presented in various forms such as text messages, emails, and APP push notifications, ensuring that users can quickly receive early warning information and take corresponding response measures. This function not only improves the timeliness and accuracy of highway maintenance, but also effectively reduces the risk of traffic accidents caused by highway damage, and protects the lives and property of the public.

[0052] In a preferred embodiment of the present invention, the present invention can be further configured as follows: in the user interface module, the real-time data and historical data of highway maintenance are clearly presented to the user through intuitive forms of expression such as charts and reports. These charts and reports include but are not limited to line charts, bar charts, pie charts, scatter charts, etc. They can intuitively display various key indicators of highway maintenance, such as the degree of road damage, traffic flow, maintenance cost, etc. At the same time, users can set maintenance goals, select maintenance methods, adjust maintenance plans, etc. according to their own needs and preferences. The system will calculate and display the effect and cost of the maintenance plan in real time based on the user's input, helping the user to make the best decision. The user interface module also supports a variety of devices and platforms, such as computers, mobile phones, tablets, etc., so that users can access the system at any time. View system output and make decisions anywhere. The intuitiveness of charts and reports enables users to quickly understand key indicators of highway maintenance, such as the degree of road damage, traffic flow, maintenance costs, etc., which is crucial for users to make timely and accurate decisions. Secondly, the user interface module allows users to set maintenance goals, select maintenance methods, adjust maintenance plans, etc. according to their own needs and preferences. The system can calculate and display the effects and costs of maintenance plans in real time, which provides users with great flexibility and convenience and helps users make the best decisions. In addition, the user interface module also supports a variety of devices and platforms, such as computers, mobile phones, tablets, etc., which enables users to view system output and make decisions anytime, anywhere, further improving work efficiency and decision-making quality.

[0053] The highway maintenance decision support system based on digital twin is a highly integrated and intelligent system that aims to improve the efficiency and accuracy of highway maintenance through digital technology. The data acquisition module collects various highway data in real time through various sensors and monitoring equipment installed along the highway, including road conditions (such as cracks, potholes, etc.), traffic flow (number of vehicles, speed, type, etc.), environmental factors (temperature, humidity, rainfall, etc.) and road structure information (such as three-dimensional model, thickness, interlayer bonding state, etc.). These data provide a solid foundation for subsequent digital twin modeling and maintenance decision-making. Then, the digital twin module uses the collected data through data preprocessing, geometric modeling and physical modeling. This model not only includes the geometric shape and appearance of the highway, but also goes deep into the physical properties and mechanical properties of the highway. It can fully and accurately reflect the actual situation of the highway. Through simulation analysis, the digital twin module can provide accurate data support for maintenance decisions. Then, the maintenance decision module predicts the degree of damage and traffic congestion of the highway based on the output results of the digital twin module using machine learning algorithms and historical data. At the same time, the module will also consider various factors (such as road conditions, traffic patterns, financial constraints, environmental impacts, etc.) and use optimization techniques (such as linear programming, nonlinear programming, heuristic algorithms, etc.) to determine the most cost-effective maintenance method. By setting objective functions and constraints, the maintenance decision module can evaluate and compare multiple maintenance plans, and finally generate a detailed maintenance plan to provide clear and specific guidance for highway maintenance personnel. The intelligent monitoring module is responsible for real-time monitoring of highway conditions, collecting key parameters (such as temperature, humidity, cracks, potholes, etc.) through IoT sensor technology, and using big data analysis technology to predict and evaluate potential risks. Once abnormal data or trends are found, the module will immediately issue an early warning signal and notify users through SMS, email, APP push and other forms to ensure that users can receive early warning information in a timely manner and take corresponding countermeasures. Finally, the user interface module uses intuitive forms such as charts and reports to display information. , the real-time and historical data of highway maintenance are clearly presented to users. Users can set maintenance goals, select maintenance methods, adjust maintenance plans, etc. according to their needs and preferences. The system will calculate and display the effects and costs of the maintenance plans in real time based on the user's input, helping users make the best decision. At the same time, the user interface module also supports a variety of devices and platforms (such as computers, mobile phones, tablets, etc.), which is convenient for users to view system outputs and make decisions anytime and anywhere. In summary, the highway maintenance decision support system based on digital twins integrates multiple functional modules such as data acquisition, digital twin modeling, maintenance decision making, intelligent monitoring, and user interface interaction to achieve comprehensive and intelligent management of highway maintenance work.

[0054] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0055] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A highway maintenance decision support system based on digital twins, characterized in that: include: Data acquisition module, digital twin module, maintenance decision module, intelligent monitoring module and user interface module; The data acquisition module is used to collect various highway data in real time, including road conditions, traffic flow, and environmental factors; The digital twin module is used to build a virtual model of the highway, conduct simulation analysis, and provide accurate data support for maintenance decisions; The maintenance decision module formulates maintenance plans and strategies based on the output of the digital twin module using optimization algorithms and data analysis technology; The intelligent monitoring module can monitor the road conditions in real time, detect potential problems in time, and send out alerts to users through the early warning system; The user interface module provides an intuitive visual interface, which facilitates users to view system output and make decisions.

2. According to the highway maintenance decision support system based on digital twins according to claim 1, it is characterized in that: The data acquisition module also includes a pavement structure information acquisition unit, which uses laser scanning technology to obtain a three-dimensional model of the pavement and understands the structural integrity of the pavement by analyzing the model. At the same time, the data acquisition module also uses non-destructive testing technology, including rebound modulus testing, spectral analysis and seismic wave velocity testing, to obtain information on the thickness of the pavement, the interlayer bonding state and whether there are defects in the internal structure.

3. The highway maintenance decision support system based on digital twin according to claim 1 is characterized in that: The data acquisition module also includes a traffic flow data acquisition unit and an environmental factor data acquisition unit. The traffic flow data acquisition unit records the number, speed and type of vehicles, as well as traffic congestion in real time through traffic flow sensors installed on the roadside. The environmental factor data acquisition unit uses meteorological sensors and environmental monitoring equipment to collect environmental factor data such as temperature, humidity and rainfall in real time in order to evaluate the performance and maintenance needs of the highway.

4. The highway maintenance decision support system based on digital twin according to claim 1 is characterized in that: The digital twin module includes a data preprocessing unit, a geometric modeling unit and a physical modeling unit. The data preprocessing unit cleans, calibrates and fuses the raw data collected from various sensors and monitoring equipment to ensure the accuracy, consistency and integrity of the data. The geometric modeling unit uses a three-dimensional GIS platform and BIM software for geometric modeling, and establishes a three-dimensional geometric model of the highway based on design drawings and satellite remote sensing data. During the geometric modeling process, it is necessary to collect a variety of data such as ground terrain measurement data, satellite elevation data, road horizontal and vertical information, and texture material data, and use these data to provide the model with basic information on terrain, elevation, routes and visual effects.

5. The highway maintenance decision support system based on digital twin according to claim 4 is characterized in that: The physical modeling unit constructs a complete digital twin model based on the established highway geometry model by adding comprehensive and accurate physical properties. The physical properties specifically include but are not limited to: Material properties: Detailed recording of key parameters such as material type, material strength, material toughness, material thermal expansion coefficient, etc. of each component of the highway such as the pavement layer, base layer, and slope; Mechanical properties: Comprehensive consideration of mechanical performance parameters such as stress distribution, deformation characteristics, fatigue life, etc. of the highway under traffic load, temperature change, humidity change, etc.; Environmental factors: Comprehensive consideration of meteorological conditions such as rainfall, temperature, humidity, wind speed, wind direction, as well as geological factors such as geological conditions, soil type, and groundwater level.

6. The highway maintenance decision support system based on digital twin according to claim 1 is characterized in that: The maintenance decision module uses machine learning algorithms to conduct in-depth analysis of historical data and real-time data based on the output results of the digital twin module to predict the degree of road damage and traffic congestion.

7. The highway maintenance decision support system based on digital twin according to claim 6 is characterized in that: The maintenance decision module needs to consider multiple factors, including road conditions, traffic patterns, financial constraints and environmental impacts, and use optimization techniques such as linear programming, nonlinear programming and heuristic algorithms to determine the most cost-effective maintenance method; Objective function: minC is the total cost, is the cost of the ci-th maintenance method, xi is the selection variable of the ci-th maintenance method; Constraints: During this process, the module will evaluate and compare multiple maintenance plans based on the preset objective function and constraints. The objective function is expressed as the minimization of the total cost, that is, selecting the combination of maintenance methods with the lowest cost, while the constraints ensure that the selected plan can meet the expected maintenance effect.

8. The highway maintenance decision support system based on digital twin according to claim 7 is characterized in that: In the objective function, the maintenance decision module calculates the total cost based on the cost of each maintenance method and the selection variable, where the selection variable is 1 to indicate that the maintenance method is selected, and 0 to indicate that it is not selected. By solving the objective function, the module can find the combination of maintenance methods with the lowest cost. At the same time, in the constraints, the module sets the requirements for maintenance effects and considers the relationship between the effect of each maintenance method and the expected maintenance effect. Only when the sum of the maintenance effects of the selected schemes meets or exceeds the expected value will the scheme be accepted by the system. Finally, based on the optimization results, the maintenance decision module generates a detailed maintenance plan, including information such as the type, time and cost of maintenance activities, to provide clear and specific guidance for highway maintenance personnel.

9. The highway maintenance decision support system based on digital twin according to claim 1 is characterized in that: In terms of real-time monitoring, the intelligent monitoring module uses Internet of Things sensor technology to monitor key parameters of the road surface, such as temperature, humidity, cracks, potholes, etc. These sensors are deployed at various key locations on the highway and can collect and transmit data to the monitoring center in real time. Big data analysis technology is used to predict and evaluate potential risks. By comparing historical data and real-time monitoring data, the system can identify abnormal data or trends and issue early warning signals accordingly. These early warning signals can include text messages, emails, APP push and other forms to ensure that users can receive early warning information in a timely manner and take corresponding countermeasures.

10. The highway maintenance decision support system based on digital twin according to claim 1, characterized in that: In the user interface module, the real-time and historical data of highway maintenance are clearly presented to the user through intuitive forms of expression such as charts and reports. These charts and reports include but are not limited to line charts, bar charts, pie charts, scatter plots, etc. They can intuitively display various key indicators of highway maintenance, such as the degree of road damage, traffic flow, maintenance cost, etc. At the same time, users can set maintenance goals, select maintenance methods, adjust maintenance plans, etc. according to their own needs and preferences. The system will calculate and display the effects and costs of the maintenance plans in real time based on the user's input, helping users make the best decision. The user interface module also supports multiple devices and platforms, such as computers, mobile phones, tablets, etc., so that users can view system outputs and make decisions anytime, anywhere.

Images