Streetlight inspection vehicle system with automated inspection process

Abstract

This invention provides a street light inspection vehicle system with an automated inspection process. By precisely designing the driving speed, parking position, and inspection action sequence based on the street light inspection route and distribution, it significantly improves the continuity and smoothness of large-scale street light inspection. By adding resistance detection and combining it with the original image acquisition and brightness detection, it can acquire more comprehensive street light operation data, providing a high-quality data foundation for street light inspection and analysis. Through in-depth analysis of multi-dimensional data, it can accurately identify street light faults, predict potential faults, and address issues such as lighting brightness. Based on lighting problems, it determines fault warning and distribution optimization strategies, which can not only promptly detect existing faults but also provide early warnings of potential faults. Through distribution optimization strategies, the lighting layout can be rationally adjusted according to the street light operation status. Ultimately, this improves the response speed and efficiency of urban management and better meets the needs of modern urban efficient management.

Description

Technical Field

[0001] This invention relates to the field of street light inspection technology, and in particular to a street light inspection vehicle system with an automated inspection process. Background Technology

[0002] In urban road lighting management, the normal operation of streetlights is crucial. Traditional streetlight inspection relies mainly on manual labor, requiring inspectors to check the brightness, appearance, and other aspects of each streetlight on-site. This method not only requires a large workforce but also involves a complex inspection process, and inspectors are prone to omissions and misidentifications due to fatigue or other factors. In large-scale streetlight acceptance projects, this is especially time-consuming and resource-intensive, severely impacting the efficiency of urban management and failing to meet the demands of rapid urban development.

[0003] With the continuous expansion of urban areas, the number of streetlights has increased dramatically. Traditional inspection methods are far from meeting the needs of efficient management in modern cities. Therefore, there is an urgent need for equipment that can automate the inspection process to improve the accuracy and efficiency of streetlight inspection. Summary of the Invention

[0004] This invention provides a street light inspection vehicle system with an automated inspection process to solve the problems mentioned in the background art.

[0005] A street light inspection vehicle system with an automated inspection process includes:

[0006] The vehicle control module is used to design the driving speed, parking position, and detection sequence of the detection vehicle based on the street light detection route and street light distribution.

[0007] The street light detection module is used to acquire images, detect brightness, and detect resistance of street lights in the order of detection actions to obtain street light detection data.

[0008] The data analysis module is used to perform in-depth analysis of street light detection data to identify lighting problems of the street lights;

[0009] The fault warning module is used to determine fault warning and distribution optimization strategies for streetlights based on lighting problems.

[0010] Preferably, the vehicle control module includes:

[0011] The speed determination unit is used to perform road condition analysis on the street light detection route based on the city road map to obtain road condition data, determine the detection point area based on the street light distribution, determine the initial speed of the detection vehicle based on the road condition data, and perform weighted processing on the initial speed based on the distance between the detection vehicle and the detection point area, according to the rule that the smaller the distance, the smaller the weight, to obtain the driving speed of the detection vehicle.

[0012] The location determination unit is used to determine the optimal parking location based on the street light distribution, combined with the street light spacing and real-time traffic conditions.

[0013] The action determination unit is used to determine the extension angle of the detection arm, image acquisition parameters, brightness detection parameters, and resistance detection clamp movement parameters of the detection vehicle based on the relative position of the parking position and the street light, thereby determining the sequence of detection actions.

[0014] Preferably, the position determination unit includes:

[0015] The distance determination unit is used to determine the installation height and pole diameter of the streetlights based on the streetlight distribution, determine the farthest relative distance between the streetlights and the inspection vehicle when the inspection requirements are met based on the inspection arm length of the inspection vehicle, and determine the maximum number of inspections at one time based on the relationship between the streetlight spacing and the farthest relative distance.

[0016] The street light segmentation unit is used to determine congested road sections based on real-time traffic conditions, and to segment the street lights based on the positional relationship between the congested road sections and the street lights, resulting in first street lights that are not affected by traffic and second street lights that are affected by traffic.

[0017] The determining unit is used to determine the position of the first street light according to the maximum number of detections at one time, obtain the initial detection position, determine whether the initial detection position is a no-stopping area, if so, adjust the initial detection position to ensure that the maximum number of detections at one time is met, and obtain the target detection position; otherwise, the initial detection position is used as the target detection position.

[0018] The determining unit is also used to determine the detectable area of ​​the second street light based on real-time traffic conditions, and to establish a position recognition model based on the distribution of the second street light and the characteristics of the detection device of the detection vehicle to maximize the number of detections at one time. Based on the position recognition model, multiple initial positions are obtained, and an optional initial position in the detectable area is selected.

[0019] The determination unit is also used to determine the participation weights of detection efficiency, detection safety and traffic impact based on detection needs and traffic needs. Based on detection efficiency, detection safety, traffic impact and participation weights, the unit comprehensively evaluates the possible initial locations and selects the one with the largest evaluation value as the target detection location.

[0020] The judgment unit is used to generate a global detection position distribution map based on the target detection positions of the first street light and the second street light, perform vehicle posture and orientation detection on adjacent detection positions in the global detection position distribution map, and determine whether the difference in vehicle posture and orientation between adjacent detection positions is within a preset range.

[0021] If so, the optimal parking location is determined based on the target detection location;

[0022] Otherwise, the vehicle's posture and orientation at the target detection location are optimized to obtain the optimal parking position.

[0023] Preferably, the street light detection module includes:

[0024] The image acquisition unit is used to acquire images of the streetlights based on the image acquisition device according to the detection action sequence, and obtain image acquisition data.

[0025] The brightness detection unit is used to detect the brightness of the street light based on the brightness sensor according to the detection action sequence, and obtain brightness detection data.

[0026] The resistance detection unit is used to perform resistance detection on the street light based on the resistance detection clip according to the detection action sequence, and obtain resistance detection data.

[0027] The preprocessing unit is used to preprocess the image acquisition data, brightness detection data, and resistance detection data to obtain street light detection data.

[0028] Preferably, the image acquisition unit includes:

[0029] The compensation unit is used to perform brightness compensation on the streetlights before the image acquisition device detects them, so as to obtain a brightness compensation environment.

[0030] The acquisition unit is used to acquire images of streetlights based on an image acquisition device under a brightness compensation environment, and obtain image acquisition data.

[0031] Preferably, the data analysis module includes:

[0032] The synchronization judgment unit is used to extract abnormal brightness data and abnormal resistance data from street light detection data, perform time alignment on the abnormal brightness data and abnormal resistance data, and determine whether the abnormal brightness and abnormal resistance are synchronized based on the alignment result.

[0033] If so, the problem with the streetlights is determined to be abnormal brightness caused by line loss;

[0034] Otherwise, the lighting problem with the streetlights is determined to be due to a potential circuit fault;

[0035] The association determination unit is used to identify defects in image acquisition data based on a defect recognition model when brightness abnormalities and resistance abnormalities are out of sync, obtain defect features, and match the defect features with brightness abnormalities based on preset association rules to obtain the association matching degree.

[0036] The matching judgment unit is used to determine the lighting problem of the street lamp based on the defect characteristics when the correlation matching degree is greater than the preset matching degree, and to compare the street lamp data with the reference street lamp of the same type when the correlation matching degree is not greater than the preset matching degree. If the brightness deviation is greater than the preset deviation, the lighting problem of the street lamp is determined to be individual performance degradation.

[0037] The change comparison unit is used to obtain the brightness value and resistance value of the street lamp in a preset historical time period from the street lamp detection data, obtain the brightness change rate and resistance change rate, and obtain the environmental data corresponding to the street lamp detection data, and determine the standard brightness change rate and standard resistance change rate that meet the environment based on the environmental data.

[0038] The problem identification unit is used to compare the rate of change of brightness and the rate of change of resistance with the standard rate of change of brightness and the standard rate of change of resistance. If the comparison result is not within the preset range, it is determined that the lighting strategy has not been adjusted in a timely manner according to the environment, which is a lighting problem of the street light.

[0039] Preferably, the data analysis module further includes:

[0040] The integration unit is used to analyze all detected lighting problems of streetlights and generate an analysis report containing streetlight ID, streetlight location, problem type, and judgment criteria.

[0041] Preferably, the fault early warning module includes:

[0042] The early warning unit is used to provide early warning information based on the analysis report corresponding to the street light lighting problem, to determine the early warning level based on the urgency of the street light lighting problem, and to provide fault early warning based on the early warning information and the early warning level.

[0043] The optimization unit is used to determine the optimal distribution strategy for streetlights in the strategy problem of streetlight-based lighting problems.

[0044] Preferably, the optimization unit includes:

[0045] The problem acquisition unit is used to acquire strategy problems from the street lighting problem;

[0046] The strategy generation unit is used to obtain historical lighting strategies with the same characteristics as the street lighting environment from the historical strategy library, and generate a distribution optimization strategy for the street lights based on the historical lighting strategies and the lighting requirements of the street lights.

[0047] Preferably, it also includes: a transmission module for transmitting street light detection data to the data analysis module and fault early warning module in the data center.

[0048] Compared with the prior art, the present invention has achieved the following beneficial effects:

[0049] By precisely designing driving speed, parking position, and detection action sequence based on street light detection routes and distribution, human intervention is eliminated, significantly reducing human error. This allows the detection vehicle to efficiently complete detection tasks along the optimal path and at the optimal pace, significantly improving the continuity and smoothness of large-scale street light detection. The addition of resistance detection, combined with existing image acquisition and brightness detection, enables more comprehensive acquisition of street light operation data, providing a high-quality data foundation for street light detection and analysis. In-depth analysis of multi-dimensional data can accurately identify street light faults, predict potential faults, and address issues such as lighting brightness. Compared to single-dimensional detection, this approach provides a more accurate grasp of the actual operating status of street lights, offering a more reliable basis for subsequent processing. Based on lighting issues, fault warning and distribution optimization strategies are determined, enabling timely detection of existing faults and early warning of potential faults. This allows management to schedule maintenance in advance, reducing street light downtime. Furthermore, distribution optimization strategies allow for reasonable adjustments to the lighting layout based on street light operating conditions, improving the overall rationality and economy of urban lighting. Ultimately, the highly automated process reduces reliance on manual operation and lowers labor costs. The inspection vehicle travels along a pre-set efficient route and pace, avoiding unnecessary stops and detours. In large-scale street light inspection projects, it can significantly shorten inspection time, improve the response speed and efficiency of urban management, and better meet the needs of modern urban efficient management.

[0050] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0051] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0052] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0053] Figure 1 This is a structural diagram of a street light inspection vehicle system with an automated inspection process according to an embodiment of the present invention;

[0054] Figure 2 This is a structural diagram of the vehicle control module described in an embodiment of the present invention;

[0055] Figure 3 This is a structural diagram of the fault early warning module described in an embodiment of the present invention. Detailed Implementation

[0056] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0057] Example 1:

[0058] This invention provides a street light inspection vehicle system with an automated inspection process, such as... Figure 1 As shown, it includes:

[0059] The vehicle control module is used to design the driving speed, parking position, and detection sequence of the detection vehicle based on the street light detection route and street light distribution.

[0060] The street light detection module is used to acquire images, detect brightness, and detect resistance of street lights in the order of detection actions to obtain street light detection data.

[0061] The data analysis module is used to perform in-depth analysis of street light detection data to identify lighting problems of the street lights;

[0062] The fault warning module is used to determine fault warning and distribution optimization strategies for streetlights based on lighting problems.

[0063] In this embodiment, based on the street light detection route and street light distribution, the system designs the driving speed, parking position, and detection action sequence of the detection vehicle. For example, when the detection vehicle approaches a street light, the system automatically controls the vehicle to decelerate and stop smoothly, triggering the detection arm to move. After the detection is completed, the system controls the detection arm to retract, and the vehicle accelerates to the next street light. The entire detection process is highly automated, reducing human error.

[0064] In this embodiment, the lighting problems of streetlights include streetlight malfunctions, predicted streetlight malfunctions, and lighting brightness conditions.

[0065] In this embodiment, image acquisition involves capturing the appearance of the streetlights.

[0066] The beneficial effects of the above design scheme are as follows: By accurately designing the driving speed, parking position, and sequence of detection actions based on the street light detection route and distribution, no manual intervention is required, significantly reducing human error. This allows the detection vehicle to efficiently complete the detection task according to the optimal path and rhythm, significantly improving the continuity and smoothness of large-scale street light detection. By adding resistance detection, combined with the original image acquisition and brightness detection, more comprehensive street light operation data can be obtained, providing a high-quality data foundation for street light detection and analysis. Through in-depth analysis of multi-dimensional data, street light faults, potential faults, and lighting brightness issues can be accurately identified. Compared with a single detection dimension, the actual operating status of street lights can be grasped more accurately, providing a more reliable basis for subsequent processing. Based on lighting issues, fault warning and distribution optimization strategies can be determined, which can not only detect existing faults in a timely manner but also provide early warnings of potential faults, facilitating management departments to arrange maintenance in advance and reducing street light downtime. At the same time, through distribution optimization strategies, the lighting layout can be reasonably adjusted according to the operating status of street lights, improving the overall rationality and economy of urban lighting. Finally, the highly automated process reduces reliance on manual operation and lowers labor costs. The inspection vehicle travels along a pre-set efficient route and pace, avoiding unnecessary stops and detours. In large-scale street light inspection projects, it can significantly shorten inspection time, improve the response speed and efficiency of urban management, and better meet the needs of modern urban efficient management.

[0067] Example 2:

[0068] Based on Embodiment 1, this embodiment of the invention provides a street light inspection vehicle system with an automated inspection process, such as... Figure 2 As shown, the vehicle control module includes:

[0069] The speed determination unit is used to perform road condition analysis on the street light detection route based on the city road map to obtain road condition data, determine the detection point area based on the street light distribution, determine the initial speed of the detection vehicle based on the road condition data, and perform weighted processing on the initial speed based on the distance between the detection vehicle and the detection point area, according to the rule that the smaller the distance, the smaller the weight, to obtain the driving speed of the detection vehicle.

[0070] The location determination unit is used to determine the optimal parking location based on the street light distribution, combined with the street light spacing and real-time traffic conditions.

[0071] The action determination unit is used to determine the extension angle of the detection arm, image acquisition parameters, brightness detection parameters, and resistance detection clamp movement parameters of the detection vehicle based on the relative position of the parking position and the street light, thereby determining the sequence of detection actions.

[0072] In this embodiment, the road condition data includes data such as road curvature, number of lanes, and speed limit signs.

[0073] In this embodiment, the initial speed is weighted at (0, 1). The weight is 1 when the distance between the detection vehicle and the detection point area is greater than a preset distance, and the weight gradually decreases when the distance is less than the preset distance.

[0074] The beneficial effects of the above design scheme are as follows: Through a three-level logic of road condition analysis, initial speed setting, and distance-weighted adjustment, dynamic optimization of driving speed is achieved. Road condition analysis based on urban road maps fully considers fundamental characteristics such as road grade, curvature, and speed limits, providing a scientific basis for the initial speed. Weighted processing based on the distance between the testing vehicle and the testing point area allows the speed to decrease smoothly as the vehicle approaches the testing point, avoiding the impact of sudden deceleration on the vehicle's stability. It also ensures that the vehicle speed has decreased to a suitable range for stopping and starting testing upon reaching the testing point. Furthermore, by using streetlight distribution as the core, combined with streetlight spacing and real-time... Determining parking locations based on traffic conditions minimizes traffic disruption while meeting inspection needs. By accurately calculating key parameters such as the extension angle of the inspection arm and image acquisition parameters based on the relative position of the parking location and the streetlight, the sequence of inspection actions is determined, achieving seamless integration of the inspection process. This upgrades the inspection actions from mechanical execution to intelligent collaboration, significantly improving the inspection efficiency of a single streetlight. Especially in large-scale streetlight acceptance projects, the cumulative time cost savings are considerable. Ultimately, this enhances the system's automation level and inspection accuracy, better meeting the needs of modern urban efficient management for streetlight inspection equipment.

[0075] Example 3:

[0076] Based on Embodiment 2, this embodiment of the invention provides a street light inspection vehicle system with an automated detection process, wherein the position determination unit includes:

[0077] The distance determination unit is used to determine the installation height and pole diameter of the streetlights based on the streetlight distribution, determine the farthest relative distance between the streetlights and the inspection vehicle when the inspection requirements are met based on the inspection arm length of the inspection vehicle, and determine the maximum number of inspections at one time based on the relationship between the streetlight spacing and the farthest relative distance.

[0078] The street light segmentation unit is used to determine congested road sections based on real-time traffic conditions, and to segment the street lights based on the positional relationship between the congested road sections and the street lights, resulting in first street lights that are not affected by traffic and second street lights that are affected by traffic.

[0079] The determining unit is used to determine the position of the first street light according to the maximum number of detections at one time, obtain the initial detection position, determine whether the initial detection position is a no-stopping area, if so, adjust the initial detection position to ensure that the maximum number of detections at one time is met, and obtain the target detection position; otherwise, the initial detection position is used as the target detection position.

[0080] The determining unit is also used to determine the detectable area of ​​the second street light based on real-time traffic conditions, and to establish a position recognition model based on the distribution of the second street light and the characteristics of the detection device of the detection vehicle to maximize the number of detections at one time. Based on the position recognition model, multiple initial positions are obtained, and an optional initial position in the detectable area is selected.

[0081] The determination unit is also used to determine the participation weights of detection efficiency, detection safety and traffic impact based on detection needs and traffic needs. Based on detection efficiency, detection safety, traffic impact and participation weights, the unit comprehensively evaluates the possible initial locations and selects the one with the largest evaluation value as the target detection location.

[0082] The judgment unit is used to generate a global detection position distribution map based on the target detection positions of the first street light and the second street light, perform vehicle posture and orientation detection on adjacent detection positions in the global detection position distribution map, and determine whether the difference in vehicle posture and orientation between adjacent detection positions is within a preset range.

[0083] If so, the optimal parking location is determined based on the target detection location;

[0084] Otherwise, the vehicle's posture and orientation at the target detection location are optimized to obtain the optimal parking position.

[0085] In this embodiment, for example, when the detection arm is 8 meters long and the street light is installed at a height of 5 meters, the maximum relative distance can be calculated to be 6 meters. If the spacing between street lights is 5 meters, then two adjacent street lights can be detected at once. This quantitative range definition avoids the problem of missing detections or invalid data due to detections exceeding the range. While ensuring detection quality, it maximizes the detection coverage of a single parking session, especially in densely lit street light areas, which can significantly reduce the number of parking sessions and reduce time costs.

[0086] In this embodiment, no-stopping areas include, for example, bus stops and fire lanes.

[0087] In this embodiment, for example, if the initial location happens to be a fire lane, the system will replan a location within a 3-meter radius to meet the required number of detections, without violating traffic rules or reducing detection efficiency.

[0088] In this embodiment, if the difference in vehicle steering angle between two adjacent parking spots exceeds 30 degrees, the system will automatically optimize the orientation, such as uniformly adjusting to parking on the right side, reducing the time wasted by frequent turning of the detection vehicle; if there is a slope difference in the vehicle posture, such as the front being lower and the rear being higher, the position will be finely adjusted to ensure a smooth parking, avoiding detection arm shaking and data errors caused by unstable posture; this global perspective optimization allows each parking spot to form a coherent and efficient detection chain, rather than isolated single points, further improving the overall detection efficiency and data consistency.

[0089] The beneficial effects of the above design scheme are as follows: By determining the maximum relative distance based on the street light installation height, pole diameter, and detection arm length, and then combining this with the street light spacing to determine the maximum number of lights that can be detected at once, a scientific basis for batch detection is provided. The first and second street lights are distinguished according to real-time traffic conditions, achieving differentiated allocation of detection resources. For the first street lights, detection can be carried out efficiently at a regular pace; for the second street lights, a targeted strategy can be adjusted. This division avoids detection stagnation caused by traffic congestion. For the first street lights, the initial position is determined based on the maximum number of lights that can be detected at once, and adjustments are made through no-stopping zone verification. To ensure that the location is legal and efficient, for the second street light, the location recognition model maximizes the number of detections per time, and combines the weights of detection efficiency, safety and traffic impact to select the optimal location. This dynamic weighting mechanism enables flexible switching between efficiency priority and safety priority, taking into account both detection needs and public interests. By generating a global detection location distribution map, the differences in vehicle posture and orientation between adjacent locations are verified, avoiding the problem of local optima but global inefficiency. The optimization of the global perspective allows each parking point to form a coherent and efficient detection chain, rather than isolated single points, further improving the overall detection efficiency and data consistency.

[0090] Example 4:

[0091] Based on Embodiment 1, this embodiment of the invention provides a street light inspection vehicle system with an automated inspection process. The street light inspection module includes:

[0092] The image acquisition unit is used to acquire images of the streetlights based on the image acquisition device according to the detection action sequence, and obtain image acquisition data.

[0093] The brightness detection unit is used to detect the brightness of the street light based on the brightness sensor according to the detection action sequence, and obtain brightness detection data.

[0094] The resistance detection unit is used to perform resistance detection on the street light based on the resistance detection clip according to the detection action sequence, and obtain resistance detection data.

[0095] The preprocessing unit is used to preprocess the image acquisition data, brightness detection data, and resistance detection data to obtain street light detection data.

[0096] In this embodiment, preprocessing includes data cleaning, data anomaly removal, and data standardization.

[0097] The beneficial effects of the above design scheme are: by adding resistance detection, combined with the original image acquisition and brightness detection, more comprehensive street light operation data can be obtained, providing a high-quality data foundation for street light detection and analysis.

[0098] Example 5:

[0099] Based on Embodiment 4, this embodiment of the invention provides a street light inspection vehicle system with an automated inspection process, wherein the image acquisition unit includes:

[0100] The compensation unit is used to perform brightness compensation on the streetlights before the image acquisition device detects them, so as to obtain a brightness compensation environment.

[0101] The acquisition unit is used to acquire images of streetlights based on an image acquisition device under a brightness compensation environment, and obtain image acquisition data.

[0102] The beneficial effects of the above design scheme are: by performing brightness compensation on the streetlights before the image acquisition device detects them, a brightness compensation environment is obtained, providing a high-quality detection environment for image acquisition and ensuring the accuracy of image detection.

[0103] Example 6:

[0104] Based on Embodiment 1, this embodiment of the invention provides a street light inspection vehicle system with an automated inspection process, wherein the data analysis module includes:

[0105] The synchronization judgment unit is used to extract abnormal brightness data and abnormal resistance data from street light detection data, perform time alignment on the abnormal brightness data and abnormal resistance data, and determine whether the abnormal brightness and abnormal resistance are synchronized based on the alignment result.

[0106] If so, the problem with the streetlights is determined to be abnormal brightness caused by line loss;

[0107] Otherwise, the lighting problem with the streetlights is determined to be due to a potential circuit fault;

[0108] The association determination unit is used to identify defects in image acquisition data based on a defect recognition model when brightness abnormalities and resistance abnormalities are out of sync, obtain defect features, and match the defect features with brightness abnormalities based on preset association rules to obtain the association matching degree.

[0109] The matching judgment unit is used to determine the lighting problem of the street lamp based on the defect characteristics when the correlation matching degree is greater than the preset matching degree, and to compare the street lamp data with the reference street lamp of the same type when the correlation matching degree is not greater than the preset matching degree. If the brightness deviation is greater than the preset deviation, the lighting problem of the street lamp is determined to be individual performance degradation.

[0110] The change comparison unit is used to obtain the brightness value and resistance value of the street lamp in a preset historical time period from the street lamp detection data, obtain the brightness change rate and resistance change rate, and obtain the environmental data corresponding to the street lamp detection data, and determine the standard brightness change rate and standard resistance change rate that meet the environment based on the environmental data.

[0111] The problem identification unit is used to compare the rate of change of brightness and the rate of change of resistance with the standard rate of change of brightness and the standard rate of change of resistance. If the comparison result is not within the preset range, it is determined that the lighting strategy has not been adjusted in a timely manner according to the environment, which is a lighting problem of the street light.

[0112] In this embodiment, defect features include, for example, a broken lampshade, a tilted lamp, or dust accumulation. If the image shows a broken lampshade and the brightness value is less than 70% of the rated value, it is determined that the lampshade is broken, resulting in a loss of brightness. If the image shows a lamp tilt greater than 30 degrees and the brightness value is within the normal range but the brightness of adjacent areas is uneven, it is determined that the installation angle deviation causes an abnormal lighting range.

[0113] In this embodiment, the defect identification model is pre-trained based on deep learning.

[0114] The beneficial effect of the above design scheme is that by aligning the abnormal brightness data and abnormal resistance data in a timely manner, it can be determined whether the two are synchronized, and the abnormal brightness caused by line loss and potential line faults can be quickly distinguished. When the two are synchronized, the abnormal brightness is directly identified as a result of line loss. This is because line loss affects both current transmission and brightness output, causing the abnormal changes in resistance and brightness to be consistent. When the two are not synchronized, it indicates that the abnormal resistance has not yet significantly affected the brightness, thus identifying a potential line fault. This time-synchronization-based judgment method avoids misjudging the fault type based on a single parameter, providing a precise direction for subsequent maintenance and reducing ineffective maintenance operations. When the abnormal brightness and abnormal resistance are not synchronized, a defect identification model is used to analyze image data, extract defect features, and match them with the abnormal brightness. The correlation matching degree is used to determine whether the defect is the cause of the abnormal brightness. When the correlation matching degree is high, the lighting problem is determined based on the defect features, breaking through the limitations of a single data dimension and enabling a more comprehensive tracing of the root cause of the abnormal brightness. Especially for non-line causes, such as aging of the lamp itself or appearance defects, the accuracy of the judgment is greatly improved. By obtaining the rate of change of brightness and resistance within a preset historical time period and combining it with environmental data to determine the standard rate of change, a quantitative basis is provided for judging whether the lighting strategy is adapted to environmental changes. The problem identification unit compares the actual rate of change with the standard rate of change. If it exceeds the preset range, it is determined that the lighting strategy has not been adjusted in a timely manner according to the environment. This design takes into account the impact of the environment, such as season, weather and time of day, on the street lighting demand. Compared with the traditional analysis method that only focuses on the fault of the equipment itself, this design expands the dimensions of problem analysis and helps to achieve smarter and more energy-efficient street lighting management.

[0115] Example 7:

[0116] Based on Embodiment 6, this embodiment of the invention provides a street light inspection vehicle system with an automated inspection process, wherein the data analysis module further includes:

[0117] The integration unit is used to analyze all detected lighting problems of streetlights and generate an analysis report containing streetlight ID, streetlight location, problem type, and judgment criteria.

[0118] The beneficial effects of the above design scheme are: by analyzing the lighting problems of all detected streetlights, an analysis report is generated containing streetlight ID, streetlight location, problem type, and judgment criteria, providing accurate fault information for regulatory warnings.

[0119] Example 8:

[0120] Based on Embodiment 1, this embodiment of the invention provides a street light inspection vehicle system with an automated inspection process, such as... Figure 3 As shown, the fault early warning module includes:

[0121] The early warning unit is used to provide early warning information based on the analysis report corresponding to the street light lighting problem, to determine the early warning level based on the urgency of the street light lighting problem, and to provide fault early warning based on the early warning information and the early warning level.

[0122] The optimization unit is used to determine the optimal distribution strategy for streetlights in the strategy problem of streetlight-based lighting problems.

[0123] The beneficial effects of the above design scheme are: determining fault early warning and distribution optimization strategies based on lighting problems can not only promptly detect existing faults, but also provide early warnings of potential faults, making it easier for management departments to arrange maintenance in advance and reducing street light downtime. At the same time, through distribution optimization strategies, the lighting layout can be reasonably adjusted according to the operating status of street lights, improving the overall rationality and economy of urban lighting.

[0124] Example 9:

[0125] Based on Embodiment 8, this embodiment of the invention provides a street light inspection vehicle system with an automated inspection process, wherein the optimization unit includes:

[0126] The problem acquisition unit is used to acquire strategy problems from the street lighting problem;

[0127] The strategy generation unit is used to obtain historical lighting strategies with the same characteristics as the street lighting environment from the historical strategy library, and generate a distribution optimization strategy for the street lights based on the historical lighting strategies and the lighting requirements of the street lights.

[0128] The beneficial effects of the above design scheme are: through the distribution optimization strategy, the lighting layout can be reasonably adjusted according to the operation status of street lights, thereby improving the overall rationality and economy of urban lighting.

[0129] Example 10:

[0130] Based on Embodiment 1, this embodiment of the invention provides a street light inspection vehicle system with an automated inspection process, which further includes: a transmission module for transmitting street light inspection data to a data analysis module and a fault early warning module in a data center.

[0131] The beneficial effect of the above design scheme is that it enables real-time transmission of street light detection data through the transmission module, providing a basis for subsequent analysis and early warning.

[0132] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this application and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A street light inspection vehicle system with an automated inspection process, characterized in that, include: The vehicle control module is used to design the driving speed, parking position, and detection sequence of the detection vehicle based on the street light detection route and street light distribution. The street light detection module is used to acquire images, detect brightness, and detect resistance of street lights in the order of detection actions to obtain street light detection data. The data analysis module is used to perform in-depth analysis of street light detection data to identify lighting problems, including: The synchronization judgment unit is used to extract abnormal brightness data and abnormal resistance data from street light detection data, perform time alignment on the abnormal brightness data and abnormal resistance data, and determine whether the abnormal brightness and abnormal resistance are synchronized based on the alignment result. If so, the problem with the streetlights is determined to be abnormal brightness caused by line loss; Otherwise, the lighting problem with the streetlights is determined to be due to a potential circuit fault; The association determination unit is used to identify defects in image acquisition data based on a defect recognition model when brightness abnormalities and resistance abnormalities are out of sync, obtain defect features, and match the defect features with brightness abnormalities based on preset association rules to obtain the association matching degree. The matching judgment unit is used to determine the lighting problem of the street lamp based on the defect characteristics when the correlation matching degree is greater than the preset matching degree, and to compare the street lamp data with the reference street lamp of the same type when the correlation matching degree is not greater than the preset matching degree. If the brightness deviation is greater than the preset deviation, the lighting problem of the street lamp is determined to be individual performance degradation. The change comparison unit is used to obtain the brightness value and resistance value of the street lamp in a preset historical time period from the street lamp detection data, obtain the brightness change rate and resistance change rate, and obtain the environmental data corresponding to the street lamp detection data, and determine the standard brightness change rate and standard resistance change rate that meet the environment based on the environmental data. The problem determination unit is used to compare the rate of change of brightness and the rate of change of resistance with the standard rate of change of brightness and the standard rate of change of resistance. If the comparison result is not within the preset range, it determines that the lighting strategy has not been adjusted in a timely manner according to the environment as a lighting problem of the street light. The fault warning module is used to determine fault warning and distribution optimization strategies for streetlights based on lighting problems.

2. The street light inspection vehicle system with an automated inspection process according to claim 1, characterized in that, The vehicle control module includes: The speed determination unit is used to perform road condition analysis on the street light detection route based on the city road map to obtain road condition data, determine the detection point area based on the street light distribution, determine the initial speed of the detection vehicle based on the road condition data, and perform weighted processing on the initial speed based on the distance between the detection vehicle and the detection point area, according to the rule that the smaller the distance, the smaller the weight, to obtain the driving speed of the detection vehicle. The location determination unit is used to determine the optimal parking location based on the street light distribution, combined with the street light spacing and real-time traffic conditions. The action determination unit is used to determine the extension angle of the detection arm, image acquisition parameters, brightness detection parameters, and resistance detection clamp movement parameters of the detection vehicle based on the relative position of the parking position and the street light, thereby determining the sequence of detection actions.

3. The street light inspection vehicle system with an automated inspection process according to claim 2, characterized in that, The location determination unit includes: The distance determination unit is used to determine the installation height and pole diameter of the streetlights based on the streetlight distribution, determine the farthest relative distance between the streetlights and the inspection vehicle when the inspection requirements are met based on the inspection arm length of the inspection vehicle, and determine the maximum number of inspections at one time based on the relationship between the streetlight spacing and the farthest relative distance. The street light segmentation unit is used to determine congested road sections based on real-time traffic conditions, and to segment the street lights based on the positional relationship between the congested road sections and the street lights, resulting in first street lights that are not affected by traffic and second street lights that are affected by traffic. The determining unit is used to determine the position of the first street light according to the maximum number of detections at one time, obtain the initial detection position, determine whether the initial detection position is a no-stopping area, if so, adjust the initial detection position to ensure that the maximum number of detections at one time is met, and obtain the target detection position; otherwise, the initial detection position is used as the target detection position. The determining unit is also used to determine the detectable area of ​​the second street light based on real-time traffic conditions, and to establish a position recognition model based on the distribution of the second street light and the characteristics of the detection device of the detection vehicle to maximize the number of detections at one time. Based on the position recognition model, multiple initial positions are obtained, and an optional initial position in the detectable area is selected. The determination unit is also used to determine the participation weights of detection efficiency, detection safety and traffic impact based on detection needs and traffic needs. Based on detection efficiency, detection safety, traffic impact and participation weights, the unit comprehensively evaluates the possible initial locations and selects the one with the largest evaluation value as the target detection location. The judgment unit is used to generate a global detection position distribution map based on the target detection positions of the first street light and the second street light, perform vehicle posture and orientation detection on adjacent detection positions in the global detection position distribution map, and determine whether the difference in vehicle posture and orientation between adjacent detection positions is within a preset range. If so, the optimal parking location is determined based on the target detection location; Otherwise, the vehicle's posture and orientation at the target detection location are optimized to obtain the optimal parking position.

4. The street light inspection vehicle system with an automated inspection process according to claim 1, characterized in that, The street light detection module includes: The image acquisition unit is used to acquire images of the streetlights based on the image acquisition device according to the detection action sequence, and obtain image acquisition data. The brightness detection unit is used to detect the brightness of the street light based on the brightness sensor according to the detection action sequence, and obtain brightness detection data. The resistance detection unit is used to perform resistance detection on the street light based on the resistance detection clip according to the detection action sequence, and obtain resistance detection data. The preprocessing unit is used to preprocess the image acquisition data, brightness detection data, and resistance detection data to obtain street light detection data.

5. A street light inspection vehicle system with an automated inspection process according to claim 4, characterized in that, The image acquisition unit includes: The compensation unit is used to perform brightness compensation on the streetlights before the image acquisition device detects them, so as to obtain a brightness compensation environment. The acquisition unit is used to acquire images of streetlights based on an image acquisition device under a brightness compensation environment, and obtain image acquisition data.

6. A street light inspection vehicle system with an automated inspection process according to claim 5, characterized in that, The data analysis module also includes: The integration unit is used to analyze all detected lighting problems of streetlights and generate an analysis report containing streetlight ID, streetlight location, problem type, and judgment criteria.

7. A street light inspection vehicle system with an automated inspection process according to claim 1, characterized in that, The fault early warning module includes: The early warning unit is used to provide early warning information based on the analysis report corresponding to the street light lighting problem, to determine the early warning level based on the urgency of the street light lighting problem, and to provide fault early warning based on the early warning information and the early warning level. The optimization unit is used to determine the optimal distribution strategy for streetlights in the strategy problem of streetlight-based lighting problems.

8. A street light inspection vehicle system with an automated inspection process according to claim 1, characterized in that, Also includes: The transmission module is used to transmit street light detection data to the data analysis module and fault early warning module in the data center.

Images