Iterative intelligent traffic facility inspection method and system

Abstract

The invention discloses an iterative intelligent traffic facility inspection method and system, and the method comprises the following steps: obtaining an inspection map, and setting a plurality of inspection points on the inspection map; setting an initial weight for each inspection point; setting an inspection route according to the initial weight of each inspection point; performing inspection operation through the unmanned aerial vehicle according to the inspection route, and shooting an inspection image; judging whether each inspection point is abnormal or not based on the inspection image; according to the abnormal condition frequency of each inspection point, adjusting the initial weight of the inspection point to obtain a dynamic weight; iteration is carried out on the inspection route based on the dynamic weight, so that the inspection points with high-frequency anomalies can obtain more inspection opportunities, and the inspection points with low-frequency anomalies can obtain less inspection opportunities; according to the method, the inspection efficiency, quality and response speed of the intelligent traffic facility can be improved through intelligentization and iterative optimization, and the technical problems of resource waste, low efficiency and response lag in a traditional inspection method are solved.

Description

Technical Field

[0001] The present invention relates to an iterative inspection method and system for intelligent transportation facilities. Background Art

[0002] With the rapid development of intelligent transportation systems, the maintenance and management of transportation facilities have become a key link to ensure road safety and smoothness. Traditional inspection methods for transportation facilities usually rely on manual inspections or fixed inspection routes, and these methods have the following defects:

[0003] Traditional inspection methods are usually based on fixed schedules or inspection plans, and the inspection frequencies of all inspection points are basically the same, lacking pertinence. Regardless of the actual importance or failure risk of the inspection points, each inspection point is arranged with the same inspection frequency. This method fails to fully consider the different needs of each inspection point, resulting in a waste of inspection resources, over-inspection of low-risk facilities, and problems of high-risk facilities may not be discovered in time due to too low inspection frequencies.

[0004] Traditional inspection methods rely on manual judgment and regular inspections, and cannot dynamically adjust inspection strategies in a timely manner according to inspection results. The inspection process is usually carried out according to a predetermined plan, without real-time feedback and analysis of inspection data, and it is difficult to make timely adjustments according to the state changes of facilities. Areas or facilities with high failure frequencies may not receive more attention, while low-frequency abnormal points may not be inspected in time, resulting in failure problems not being discovered and solved in the first time.

[0005] Due to the fixed inspection plan and dependence on manual operations, omissions or inefficiencies may occur during the inspection process. Some facilities do not receive enough attention, resulting in problems not being discovered and repaired in time, further affecting the normal operation and safety of the transportation system. Manual operations in the inspection work are also easily affected by human factors, and the stability of inspection quality is difficult to guarantee.

[0006] Currently, many inspection methods for transportation facilities still rely on traditional manual methods, or simply rely on drones to collect inspection images, lacking systematic intelligent analysis and dynamic feedback mechanisms. Most inspection data cannot be intelligently processed and deeply analyzed, and the intelligent and automated management of the inspection process cannot be realized, resulting in low inspection efficiency and easy to overlook some important details and potential problems. Summary of the Invention

[0007] Aiming at the deficiencies in the prior art, the present invention provides an iterative inspection method and system for intelligent transportation facilities, which can improve the inspection efficiency, quality and response speed of intelligent transportation facilities through intelligentization and iterative optimization, and solve the technical problems of resource waste, low efficiency and response lag in traditional inspection methods.

[0008] The technical solution adopted by the present invention to solve its technical problems is as follows:

[0009] An iterable inspection method for intelligent transportation facilities, comprising the following steps:

[0010] Obtain an inspection map and set a number of inspection points on the inspection map;

[0011] Set an initial weight for each inspection point;

[0012] Set an inspection route according to the initial weights of each inspection point, ensuring that high-weight inspection points are inspected multiple times and low-weight inspection points are inspected fewer times;

[0013] Carry out inspection operations along the inspection route by means of an unmanned aerial vehicle and capture inspection images;

[0014] Based on the inspection images, determine whether there are any abnormalities at each inspection point;

[0015] According to the frequency of abnormalities at each inspection point, adjust the initial weight of the inspection point to obtain a dynamic weight;

[0016] Iterate the inspection route based on the dynamic weight, ensuring that inspection points with high-frequency abnormalities get more inspection opportunities and inspection points with low-frequency abnormalities get fewer inspection opportunities.

[0017] Preferably, the method for obtaining an inspection map and setting a number of inspection points on the inspection map is as follows:

[0018] Obtain map data by means of a geographic information system platform, satellite images or unmanned aerial vehicle aerial images;

[0019] Load or import the map data in the GIS platform;

[0020] Perform map calibration and docking to align the data collected by the unmanned aerial vehicle with the map;

[0021] Based on the importance, usage frequency and potential risk factors of the transportation facilities, select a number of key inspection points, including traffic lights, road signs, traffic cameras and road surface facilities;

[0022] Use the point marking tool in the GIS platform to mark the position of each inspection point on the map;

[0023] For each inspection point, assign relevant attributes, including inspection point number and facility type;

[0024] Enter the information of the inspection points into the inspection management system or database.

[0025] Preferably, the method for setting an initial weight for each inspection point is as follows:

[0026] Obtain the traffic flow of each inspection point through traffic monitoring devices;

[0027] Calculate the initial weight based on the standardized usage frequency value of each inspection point, and the standardized usage frequency value is calculated by the following formula:

[0028] Standardized frequency = (actual usage frequency - minimum usage frequency) / (maximum usage frequency - minimum usage frequency)

[0029] Among them, the minimum usage frequency and the maximum usage frequency are respectively the lowest and highest usage frequency values among all inspection points.

[0030] Preferably, the method for setting the inspection route according to the initial weights of each inspection point is as follows:

[0031] Calculate the inspection times of each inspection point according to the initial weights of each inspection point, and the inspection times are proportional to the initial weights of the inspection points;

[0032] Construct an adjusted distance matrix of inspection points, considering the distance between inspection points and the weight difference of inspection points. The adjusted distance matrix adjusts the distance according to the weight difference of inspection points to preferentially select high-weight inspection points;

[0033] Use the optimization algorithm of the traveling salesman problem to select the shortest path and generate the optimal inspection route to ensure that high-weight inspection points are inspected more frequently.

[0034] Preferably, the adjusted distance matrix of inspection points is calculated by the following formula:

[0035] D′ ij = D ij ×(1 + α × |W i - W j |)

[0036] Among them, D′ ij is the adjusted distance, D ij is the original distance, W i and W j are the weights of inspection point i and inspection point j respectively, and α is the adjustment factor.

[0037] Preferably, the method for adjusting the initial weight of the inspection point according to the abnormal situation frequency of each inspection point to obtain the dynamic weight is as follows:

[0038] For each inspection point, according to the historical inspection data or the real-time inspection result, count the frequency of abnormalities occurring at each inspection point. The abnormal frequency can be calculated in the following way:

[0039] Count the number of abnormal occurrences at a certain inspection point within a certain time range;

[0040] Calculate the abnormal occurrence ratio of each inspection point, that is, the number of abnormal occurrences / the number of inspections. Assume that the abnormal occurrence frequency of inspection point i is f i , then:

[0041]

[0042] Directly adjust the weight of the inspection point according to the abnormal occurrence frequency. When the abnormal frequency of a certain inspection point is high, it indicates that there is a greater potential risk at this point, and a higher weight is assigned to it. The formula is as follows:

[0043] w i (t) = w i (0) × (1 + λ × f i (t))

[0044] Among them, w i (t) is the dynamic weight of inspection point i at time t, w i (0) is the initial weight of inspection point i, λ is a coefficient that controls the influence degree of the abnormal frequency on the weight, and f i (t) is the abnormal frequency of inspection point i at time t.

[0045] Preferably, the method for iterating the inspection route based on the dynamic weight is:

[0046] Calculate the inspection priority of each inspection point according to the dynamically adjusted weight. The inspection priority formula is:

[0047] P i (t) = w i (t) × C i

[0048] Among them, P i (t) is the inspection priority of inspection point i, and C i is the criticality coefficient of inspection point i;

[0049] Based on the calculated inspection priority, optimize the inspection route, and preferentially arrange the inspection points with higher weights for inspection.

[0050] Another technical problem to be solved by the present invention is to provide an iterable intelligent transportation facility inspection system, including:

[0051] An inspection map acquisition module, which is used to acquire the inspection map of urban transportation facilities and set inspection points;

[0052] A weight setting module, which is used to set the initial weight for each inspection point;

[0053] A route planning module, which is used to set the inspection route according to the initial weight of the inspection point;

[0054] The UAV inspection module is used to control the UAV to perform inspection operations and capture inspection images according to the inspection route;

[0055] The anomaly detection module is used to determine whether there is an anomaly at the inspection point based on the inspection image;

[0056] The dynamic weight adjustment module is used to adjust the weight value of the inspection point according to the anomaly frequency of the inspection point and reset the inspection route;

[0057] The system iterative optimization module is used to optimize the inspection route and inspection strategy according to the results of each inspection.

[0058] Another technical problem to be solved by the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the iterable intelligent transportation facility inspection method described in any one of the above is implemented.

[0059] Another technical problem to be solved by the present invention is to provide a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the iterable intelligent transportation facility inspection method described in any one of the above is implemented.

[0060] The beneficial effects of the present invention are:

[0061] By dynamically adjusting the weight of the inspection point according to the anomaly frequency of the inspection point, the intelligent allocation of resources is realized, so that more inspection points with higher failure risks can get more inspection opportunities, while the inspection frequency of low-frequency anomaly points is reduced, maximizing the use of inspection resources; using UAVs for inspection, combined with dynamic weight adjustment, can optimize the inspection route according to the specific conditions of each inspection point, thereby improving the efficiency of inspection operations. This avoids over-inspection of low-risk facilities and ensures that high-risk facilities receive timely attention and handling.

[0062] By using the inspection image to judge anomalies and adjusting the weight of the inspection point according to the anomaly situation, the system can autonomously learn and adapt to changes in the facility conditions, gradually optimize the inspection strategy, reduce the need for manual intervention, and thus improve the intelligence level of inspection; through the dynamic adjustment of the weight of the inspection point and the iteration of the inspection route, it is ensured that the inspection operation can be adjusted in real time according to the actual maintenance needs of the facility, enhancing the pertinence and timeliness of inspection. Specific implementation method

[0064] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention. The present invention will be described more specifically by way of example in the following paragraphs. The advantages and features of the present invention will be clearer according to the following description and claims.

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs. The terms used in the specification of this invention are for the purpose of describing specific embodiments only and are not intended to limit the invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. Embodiment

[0066] An iterative inspection method for intelligent transportation facilities, comprising the following steps:

[0067] Obtain an inspection map and set a number of inspection points on the inspection map;

[0068] Set an initial weight for each inspection point;

[0069] Set an inspection route according to the initial weights of each inspection point, ensuring that high-weight inspection points are inspected multiple times and low-weight inspection points are inspected fewer times;

[0070] Perform inspection operations along the inspection route by a drone and capture inspection images;

[0071] Based on the inspection images, determine whether there are any abnormalities at each inspection point;

[0072] Adjust the initial weights of the inspection points according to the abnormal situation frequencies of each inspection point to obtain dynamic weights;

[0073] Iterate the inspection route based on the dynamic weights, ensuring that inspection points with high-frequency abnormalities have more inspection opportunities and inspection points with low-frequency abnormalities have fewer inspection opportunities.

[0074] By assigning dynamic weights to different inspection points, this method can intelligently adjust the inspection route according to the abnormal frequency and importance of each inspection point. This ensures that facilities with high-frequency abnormalities can obtain more inspection opportunities, while facilities with fewer abnormalities have reduced inspection frequencies. This method avoids the traditional average inspection method and improves resource utilization; traditional inspection methods often set the same inspection frequency for all facilities and cannot effectively allocate limited inspection resources. Through this method, the inspection frequency can be adjusted according to the actual situation of each inspection point to ensure that important facilities receive sufficient attention, thereby improving the efficiency of resource use and reducing unnecessary inspection work.

[0075] This method combines drone inspection and image analysis technologies to achieve the intelligence and automation of the inspection process. Drones can efficiently cover the inspection area and capture high-quality inspection images. The anomaly judgment and dynamic weight adjustment based on image analysis can automatically optimize the inspection plan, reduce manual intervention, and improve the inspection quality and accuracy. By collecting inspection images in real time and judging anomalies, the system can continuously adjust the weights and inspection strategies according to the actual anomaly situations. This can timely respond to the changes in the facility conditions, ensure that high-risk facilities receive more attention, and thus reduce the risk of potential failures.

[0076] This method supports the dynamic adjustment and iterative update of the inspection strategy, enabling the inspection plan to be continuously optimized according to the actual operation situation. As the amount of data increases, the system can gradually learn and improve, so as to achieve higher inspection efficiency and quality in the long term.

[0077] Data collection and inspection map establishment:

[0078] Through Geographic Information System (GIS) technology, an accurate inspection map of traffic facilities is established, and the positions of each inspection point are marked on the map. These inspection points can be traffic lights, street lights, traffic signs, road facilities, etc.

[0079] Initial weight setting:

[0080] An initial weight is set for each inspection point. This weight can be set according to factors such as the importance of the facility, historical failure records, and equipment age. The initial weight can also be configured based on expert experience or historical data to ensure that high-risk facilities have higher weights.

[0081] Set the inspection route:

[0082] According to the initial weights, algorithms (such as weighted graph algorithms, greedy algorithms, etc.) are used to generate the inspection route. Facilities with high weights will be arranged more inspection opportunities, while facilities with low weights will be arranged fewer inspection frequencies. At this time, the arrangement of the inspection route should not only consider the weights of the facilities but also optimize the inspection efficiency and reduce unnecessary paths and time waste.

[0083] Drone inspection and image collection:

[0084] The drone flies according to the set inspection route and captures inspection images. The drone needs to be equipped with high-definition imaging equipment, and even multiple means such as infrared imaging technology can be used to ensure the quality and comprehensiveness of the inspection images. The automated flight and image collection of the drone can greatly improve the inspection speed and reduce the time and cost of manual inspection.

[0085] Anomaly judgment based on image analysis:

[0086] The inspection images are analyzed through image processing techniques, and machine learning, computer vision and other technologies are used to automatically identify abnormal phenomena. For example, problems such as damaged traffic signs, malfunctioning traffic lights, and road surface cracks can be identified through images. By training the model, the accuracy and reliability of anomaly detection are improved.

[0087] Feedback on abnormal situations and dynamic weight adjustment:

[0088] According to the abnormal situations found in the inspection images, the abnormal frequency of each inspection point is counted. If abnormal situations frequently occur at a certain inspection point, the system will automatically increase the weight of this point to ensure that this point can obtain more inspection opportunities in subsequent inspections. Conversely, the weight of points with fewer abnormalities will be reduced.

[0089] Iterative optimization of the inspection route:

[0090] With the feedback on abnormal situations and the adjustment of weights, the inspection route will be optimized iteratively according to the dynamic weights. This means that after each inspection, the system will analyze the data and recalculate the optimal inspection route, so that facilities with high-frequency abnormalities receive more attention.

[0091] Continuous learning and adaptability:

[0092] By continuously collecting inspection data, the system can gradually learn the abnormal patterns of each inspection point and continuously adjust the inspection frequency and inspection route according to historical data. After long-term operation, the system can achieve adaptive optimization, which not only improves the inspection efficiency but also reduces the probability of equipment failures.

[0093] The method for obtaining the inspection map and setting several inspection points on the inspection map is as follows:

[0094] Obtain map data through a geographic information system platform, satellite images or drone aerial images;

[0095] Load or import the map data in the GIS platform;

[0096] Perform map calibration and docking to align the data collected by the drone with the map;

[0097] Based on the importance, usage frequency and potential risk factors of traffic facilities, select several key inspection points, including traffic lights, road signs, traffic cameras and road surface facilities;

[0098] Use the point marking tool in the GIS platform to mark the position of each inspection point on the map;

[0099] For each inspection point, assign relevant attributes, including the inspection point number and facility type;

[0100] Enter the information of the inspection points into the inspection management system or database.

[0101] Obtain the inspection map through the Geographic Information System (GIS) platform, satellite images or drone aerial images and conduct data docking, which can ensure the highly accurate location of the inspection points. Such precise geographical information can make the inspection work more efficient, reducing errors and omissions in manual inspections. At the same time, the GIS platform can integrate, visualize and manage the inspection point information, facilitating comprehensive management and tracking by the inspection team.

[0102] Selecting key inspection points based on the importance, usage frequency and potential risk factors of traffic facilities can ensure that high-risk and important facilities receive priority attention. This data-driven inspection strategy can optimize the inspection route through intelligent analysis and dynamic adjustment, thereby improving the accuracy and efficiency of inspections. Combined with the GIS platform, real-time monitoring and feedback of the facility status can also be achieved to ensure that problems can be discovered and handled in a timely manner.

[0103] Entering the information of each inspection point into the inspection management system or database can establish a detailed facility file for easy future query and analysis. Through systematic recording, not only can the historical inspection data of each inspection point be traced, but also risk assessment and prediction can be carried out based on the historical data to assist decision-makers in formulating more reasonable inspection plans.

[0104] The method for setting the initial weight for each inspection point is as follows:

[0105] Obtain the traffic flow of each inspection point through traffic monitoring devices;

[0106] Calculate the initial weight based on the standardized usage frequency value of each inspection point, and the standardized usage frequency value is calculated by the following formula:

[0107] Standardized frequency = (Actual usage frequency - Minimum usage frequency) / (Maximum usage frequency - Minimum usage frequency)

[0108] Wherein, the minimum usage frequency and the maximum usage frequency are respectively the lowest and highest usage frequency values among all inspection points.

[0109] Suppose there are three inspection points (A, B, C) corresponding to traffic flows respectively, and the flow data is as follows:

[0110] Inspection point A: Traffic flow is 1500 vehicles per hour

[0111] Inspection point B: Traffic flow is 3000 vehicles per hour

[0112] Inspection point C: Traffic flow is 500 vehicles per hour

[0113] If we set the maximum traffic flow to 3,000 vehicles per hour and the minimum traffic flow to 500 vehicles per hour, the calculation of the normalized frequency is as follows:

[0114] A: (1500 - 500) / (3000 - 500) = 0.5(1500 - 500) / (3000 - 500) = 0.5

[0115] B: (3000 - 500) / (3000 - 500) = 1.0(3000 - 500) / (3000 - 500) = 1.0

[0116] C: (500 - 500) / (3000 - 500) = 0.0(500 - 500) / (3000 - 500) = 0.0

[0117] Based on these normalized frequencies, the initial weights are respectively:

[0118] A: 0.5

[0119] B: 1.0

[0120] C: 0.0

[0121] By obtaining the traffic flow of each inspection point through traffic monitoring devices and calculating the normalized frequency according to the actual usage frequency, it ensures that the calculation of the inspection point weight is based on actual traffic data. This data-driven method can avoid human subjective judgment, making the priority allocation of the inspection work more scientific and objective, thus improving the inspection efficiency.

[0122] The calculation method of the normalized usage frequency can dynamically adjust the initial weights of the inspection points according to the actual traffic flow changes. With the fluctuation of the traffic flow, the weights of some inspection points may change, and the system can automatically adjust the inspection priorities according to these changes. This enables the inspection plan to respond to the traffic conditions in real time, ensuring more reasonable and effective resource allocation.

[0123] By normalizing the usage frequency, it can avoid the over-concentration of inspection tasks due to too high weights for some frequently used inspection points, resulting in waste of resources. The normalization process enables reasonable weight allocation for inspection points with different usage frequencies, balancing the workload of the inspection work and contributing to the realization of comprehensive and efficient inspection management.

[0124] The method of setting the inspection route according to the initial weights of each inspection point is as follows:

[0125] Calculate the inspection times of each inspection point according to its initial weight, and the inspection times are proportional to the initial weight of the inspection point;

[0126] Construct an adjusted inspection point distance matrix, considering the distances between inspection points and the weight differences of inspection points. The adjusted distance matrix adjusts the distances according to the weight differences of inspection points to preferentially select inspection points with high weights;

[0127] Use an optimization algorithm for the traveling salesman problem to select the shortest path and generate an optimal inspection route to ensure that inspection points with high weights are inspected more frequently.

[0128] By setting the number of inspections according to the initial weights of the inspection points, it can be ensured that inspection points with high weights receive more attention and inspections, thereby increasing the supervision frequency of important areas. This optimization method is based on a comprehensive consideration of weights and distances, making the inspection process more targeted, avoiding excessive attention to low-priority inspection points, and improving the inspection efficiency.

[0129] When constructing the adjusted inspection point distance matrix, the distances and weight differences between inspection points are considered. This means that the inspection route will be able to balance the importance and physical distance of inspection points, thereby optimizing the route planning and reducing ineffective inspection paths. This method reduces the time and cost required for inspections and improves the overall efficiency and coverage of inspections.

[0130] By using an optimization algorithm for the traveling salesman problem (TSP), the shortest inspection route can be generated to ensure that the execution of inspection tasks is both efficient and minimizes time and cost. The TSP algorithm can find the optimal inspection route that meets the weight and distance requirements, making the inspection process both logical and efficient, ensuring that inspection points with high weights receive more attention, and at the same time reducing the complexity of the overall inspection process.

[0131] The adjusted inspection point distance matrix mentioned above is calculated by the following formula:

[0132] D′ ij =D ij ×(1+α×|W i -W j |)

[0133] where D′ ij is the adjusted distance, D ij is the original distance, W i and W j are the weights of inspection point i and inspection point j respectively, and α is the adjustment factor.

[0134] Through the adjusted distance matrix, adjusting the original distance according to the weight differences of inspection points can ensure that inspection points with high weights receive more attention when generating the inspection route. This method enables the system to preferentially select important inspection points, increases the inspection frequency of key areas, and thus better allocates resources to ensure that high-priority tasks are fully executed.

[0135] By introducing an adjustment factor, the planning of the inspection route is optimized, so that the inspection path not only considers the distance factor, but also incorporates the importance of the inspection points. Inspection points with higher weights will be preferentially selected. Even if the physical distance of these points may be slightly farther, they can occupy more positions in the inspection route. This helps to reduce the frequent inspections of low-priority points and improve the overall inspection efficiency.

[0136] Through the adjustment factor, the relative distance between inspection points can be flexibly adjusted, enabling the system to dynamically adjust the inspection path according to specific requirements (such as weights, priorities). This adjustment mechanism makes the inspection plan not only flexible but also optimized according to the actual situation, thus better coping with various changes and enhancing the responsiveness and execution ability of the inspection work.

[0137] The method for obtaining the dynamic weight by adjusting the initial weight of the inspection point according to the frequency of abnormal situations at each inspection point is as follows:

[0138] For each inspection point, according to historical inspection data or real-time inspection results, count the frequency of abnormalities occurring at each inspection point. The abnormal frequency can be calculated in the following ways:

[0139] Count the number of abnormal occurrences at a certain inspection point within a certain time range;

[0140] Calculate the abnormal occurrence ratio of each inspection point, that is, the number of abnormal occurrences / the number of inspections. Assume that the abnormal occurrence frequency of inspection point i is f i , then:

[0141]

[0142] Directly adjust the weight of the inspection point according to the abnormal occurrence frequency. When the abnormal frequency of a certain inspection point is high, it indicates that there is a greater potential risk at this point, and a higher weight is assigned to it. The formula is as follows:

[0143] w i (t) = w i (0) × (1 + λ × f i (t))

[0144] Where, w i (t) is the dynamic weight of inspection point i at time t, w i (0) is the initial weight of inspection point i, λ is a coefficient that controls the influence degree of the abnormal frequency on the weight, f i (t) is the abnormal frequency of inspection point i at time t.

[0145] By dynamically adjusting the weights of inspection points according to the anomaly frequency, the system can identify potential risk points in real time and adjust the inspection strategy in a timely manner. Inspection points with a higher anomaly frequency will be assigned higher weights, thus receiving more inspection resources and attention preferentially. This dynamic adjustment mechanism ensures that the inspection work can adapt to the changing risk environment and avoids over - attention to low - risk points.

[0146] Adjusting the weights of inspection points according to the anomaly frequency helps to accurately identify inspection points with relatively high potential risks. Inspection points with a high anomaly frequency may indicate potential faults or problems. By increasing the weights of these points, more frequent inspections can be carried out on high - risk points during inspections, thus effectively preventing potential accidents and improving the overall safety and stability of the system.

[0147] This solution uses historical data or real - time data as an important basis for inspection decision - making, making inspection decisions more data - driven rather than relying solely on manual experience. By calculating the anomaly occurrence frequency, the system can make adjustments based on the actual situation, avoiding a fixed inspection strategy and improving the intelligence and efficiency of the inspection work.

[0148] The method of iterating the inspection route based on dynamic weights is as follows:

[0149] Calculate the inspection priority of each inspection point according to the dynamically adjusted weights. The inspection priority formula is:

[0150] P i (t)=w i (t)×C i

[0151] Where, P i (t) is the inspection priority of inspection point i, and C i is the criticality coefficient of inspection point i;

[0152] Based on the calculated inspection priorities, optimize the inspection route and preferentially arrange inspections for inspection points with higher weights.

[0153] By calculating the inspection priorities and preferentially arranging high - weight inspection points, the inspection resources are allocated more reasonably and efficiently. This can ensure that key areas and high - risk areas are inspected preferentially, avoiding low - risk inspection points from occupying too much time and resources, thus improving the overall inspection efficiency; the introduction of dynamic weights makes the inspection route better reflect the real - time risk situation. Dynamically adjusting the priorities according to the anomaly frequency and criticality coefficient of inspection points can quickly respond to potential risks and preferentially inspect inspection points with relatively high potential faults. This improves the risk management ability of the inspection system and reduces the probability of system failures.

[0154] After calculating and adjusting the inspection priorities, the inspection routes can be optimized according to the priorities, reducing unnecessary detours. By prioritizing the inspection of high-weight inspection points, the system can ensure that important inspection tasks are completed in the shortest possible time, improving the comprehensiveness and timeliness of inspections. This method has strong adaptability and can dynamically adjust the inspection priorities according to changes in inspection data. As the data is updated during the inspection process, the priorities of the inspection points and the inspection routes will be adjusted accordingly, being able to reflect the current work priorities and potential risks in real time, ensuring that the inspection work always targets the most important issues.

[0155] This solution uses historical data and real-time data to drive the optimization decision of the inspection routes, avoiding the limitations of traditional reliance on manual experience. The data-driven optimization process makes the planning of inspection routes more scientific and accurate, ensuring that inspection tasks are carried out in the most effective way. Through the adjustment of dynamic weights and priorities, the inspection routes are continuously optimized, ensuring that high-risk and high-importance areas are promptly attended to. This not only improves the effectiveness of inspections but also enhances the quality of inspection work, helping the system to detect problems earlier and take measures.

[0156] An iterative intelligent transportation facility inspection system, comprising:

[0157] An inspection map acquisition module, used to acquire the inspection map of urban transportation facilities and set inspection points;

[0158] A weight setting module, used to set initial weights for each inspection point;

[0159] A route planning module, used to set inspection routes according to the initial weights of the inspection points;

[0160] A drone inspection module, used to control the drone to perform inspection operations according to the inspection route and capture inspection images;

[0161] An anomaly detection module, used to judge whether there are anomalies at the inspection points based on the inspection images;

[0162] A dynamic weight adjustment module, used to adjust the weight values of the inspection points according to the anomaly frequencies of the inspection points and reset the inspection routes;

[0163] A system iterative optimization module, used to optimize the inspection routes and inspection strategies according to the results of each inspection.

[0164] The system conducts automated inspections through drones, avoiding the time and space limitations of manual inspections. Drones can quickly cover inspection points and capture high-definition images simultaneously, greatly improving the inspection efficiency. Through the initial weight and route planning module, the system can reasonably arrange inspection tasks to ensure that important inspection points are covered first, reducing unnecessary time waste. The anomaly detection module determines whether there are problems with facilities based on inspection images and can automatically identify potential anomalies such as damage and wear of traffic facilities using image recognition technology. Compared with manual inspections, intelligent anomaly detection not only improves accuracy but also reduces human errors and enhances the quality of inspections.

[0165] The dynamic weight adjustment module adjusts the weights according to the anomaly frequency of inspection points, enabling dynamic optimization of the inspection strategy based on actual situations. Inspection points with higher anomaly frequencies will be assigned higher weights and will be inspected first. This adaptive mechanism ensures that the system always focuses on the areas that most need to be inspected, avoiding waste of resources and improving the timeliness of problem discovery. The system iterative optimization module continuously optimizes the inspection route and strategy through the feedback of each inspection result. This means that as the system runs for a longer time, the inspection route and strategy will be continuously adjusted according to actual situations, forming a more efficient and intelligent inspection mode, thereby further improving the inspection quality and work efficiency.

[0166] The system can comprehensively collect inspection images and analyze the situations of all inspection points, which can ensure better coverage of each key area and timely problem discovery compared to traditional manual inspections. The inspections by drones are not restricted by weather, environment, etc., and are especially suitable for high-risk or inaccessible areas, ensuring the comprehensiveness and accuracy of inspections. Automated inspections and dynamic weight adjustment reduce the dependence on manual inspectors, lowering labor costs and the time required for inspections. Drones can quickly complete a large number of inspection tasks without the need for rest, further enhancing the efficiency of resource utilization. In addition, the system can continuously optimize the inspection route based on data, further reducing unnecessary inspection repetitions and saving inspection costs. The system makes inspection decisions more data-driven by collecting and analyzing data from each inspection. The accumulation of data can help decision-makers make more scientific and accurate judgments, improving the management level of traffic facility maintenance.

[0167] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the iterable intelligent traffic facility inspection method as described above.

[0168] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the iterable intelligent traffic facility inspection method as described above.

[0169] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0170] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0171] The above embodiments of the present invention do not limit the protection scope of the present invention. The embodiments of the present invention are not limited thereto. All such modifications, substitutions, or changes made to the above structure of the present invention in various other forms according to the above content of the present invention, in accordance with the common general knowledge and customary means in the art, without departing from the above basic technical idea of the present invention, shall fall within the protection scope of the present invention.

Claims

1. An iterable inspection method for intelligent transportation facilities, characterized in that, It includes the following steps: Obtain an inspection map and set several inspection points on the inspection map; Set an initial weight for each inspection point; Set an inspection route according to the initial weights of each inspection point, ensuring that high-weight inspection points are inspected multiple times and low-weight inspection points are inspected fewer times; Conduct inspection operations along the inspection route by an unmanned aerial vehicle and capture inspection images; Based on the inspection images, determine whether there are abnormalities at each inspection point; Adjust the initial weights of the inspection points according to the abnormality frequency of each inspection point to obtain dynamic weights; Iterate the inspection route based on the dynamic weights, ensuring that inspection points with high-frequency abnormalities get more inspection opportunities and inspection points with low-frequency abnormalities get fewer inspection opportunities.

2. The iterable intelligent transportation facility inspection method according to claim 1, characterized in that, The method for obtaining an inspection map and setting several inspection points on the inspection map is as follows: Obtain map data through a geographic information system platform, satellite images, or unmanned aerial vehicle aerial images; Load or import the map data in the GIS platform; Perform map calibration and docking to align the data collected by the unmanned aerial vehicle with the map; Based on the importance, usage frequency, and potential risk factors of traffic facilities, select several key inspection points, including traffic lights, road signs, traffic cameras, and road surface facilities; Use the point marking tool in the GIS platform to mark the location of each inspection point on the map; For each inspection point, assign relevant attributes, including the inspection point number and facility type; Enter the information of the inspection points into the inspection management system or database.

3. The iterable intelligent transportation facility inspection method according to claim 1 or 2, characterized in that, The method for setting an initial weight for each inspection point is as follows: Obtain the traffic flow of each inspection point through traffic monitoring devices; Calculate the initial weight according to the standardized usage frequency value of each inspection point, and the standardized usage frequency value is calculated by the following formula: Standardized frequency = (actual usage frequency - minimum usage frequency) / (maximum usage frequency - minimum usage frequency) Wherein, the minimum usage frequency and the maximum usage frequency are respectively the lowest and highest usage frequency values among all inspection points.

4. The iterable intelligent transportation facility inspection method according to claim 3, wherein, The method for setting an inspection route according to the initial weights of each inspection point is as follows: Calculate the inspection times of each inspection point according to the initial weights of each inspection point, and the inspection times are proportional to the initial weights of the inspection points; Construct an adjusted inspection point distance matrix, considering the distance between inspection points and the weight difference of inspection points. The adjusted distance matrix adjusts the distance according to the weight difference of inspection points to preferentially select high-weight inspection points; Use the optimization algorithm of the traveling salesman problem to select the shortest path and generate the optimal inspection route to ensure that high-weight inspection points are inspected more.

5. The iterative intelligent transportation facility inspection method according to claim 4, characterized in that: The adjusted inspection point distance matrix is calculated by the following formula: D′ ij = D ij × (1 + α × |W i - W j |) Among them, D′ ij is the adjusted distance, D ij is the original distance, W i and W j are the weights of inspection point i and inspection point j respectively, and α is the adjustment factor.

6. The iterable intelligent transportation facility inspection method according to claim 1, characterized in that The method for adjusting the initial weights of the inspection points according to the abnormality frequency of each inspection point to obtain dynamic weights is as follows: For each inspection point, according to historical inspection data or real-time inspection results, count the frequency of abnormalities occurring at each inspection point. The abnormality frequency can be calculated in the following way: Count the number of abnormality occurrences at a certain inspection point within a certain time range; Calculate the abnormality occurrence ratio of each inspection point, that is, the number of abnormal occurrences / number of inspections. Assume that the abnormality occurrence frequency of inspection point i is f i ,but: Directly adjust the weight of the inspection point according to the abnormality occurrence frequency. When the abnormality frequency of a certain inspection point is high, it indicates that there is a greater potential risk at this point, and a higher weight is assigned to it. The formula is as follows: w i w(t) = i w(0)×(1 + λ×f i (t)) Among them, w i (t) is the dynamic weight of inspection point i at time t, w i (0) is the initial weight of inspection point i, λ is a coefficient that controls the influence of abnormal frequency on the weight, and f i (t) is the abnormal frequency of inspection point i at time t.

7. The iterative intelligent transportation facility inspection method according to claim 6, characterized in that: The method of iterating the inspection route based on dynamic weights is as follows: Calculate the inspection priority of each inspection point according to the dynamically adjusted weights. The inspection priority formula is: P i (t)=w i (t)×C i Among them, P i (t) is the inspection priority of inspection point i, C i is the criticality coefficient of inspection point i; Based on the calculated inspection priority, optimize the inspection route and give priority to arranging the inspection points with higher weights for inspection.

8. An iterable intelligent transportation facility inspection system, characterized in that, It includes: An inspection map acquisition module for acquiring the inspection map of urban traffic facilities and setting inspection points; A weight setting module for setting initial weights for each inspection point; A route planning module for setting the inspection route according to the initial weights of the inspection points; A drone inspection module for controlling the drone to perform inspection operations and capture inspection images according to the inspection route; An anomaly detection module for judging whether there is an anomaly at the inspection point based on the inspection images; A dynamic weight adjustment module for adjusting the weight values of the inspection points according to the anomaly frequency of the inspection points and resetting the inspection route; A system iterative optimization module for optimizing the inspection route and inspection strategy according to the results of each inspection.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the iterable intelligent transportation facility inspection method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the iterable intelligent transportation facility inspection method according to any one of claims 1-7.

Images