Unmanned aerial vehicle and intelligent lamp post integrated intelligent illumination detection system

Abstract

According to the intelligent illumination detection system integrating the unmanned aerial vehicle and the intelligent lamp post, the integration of the unmanned aerial vehicle base station and the sensor on the intelligent lamp post is realized through the integration module, the installation space and cost of independent equipment are saved, and centralized management and maintenance are facilitated; the data interaction module can more comprehensively and accurately determine street lamp fault information by fusing sensor environment data and unmanned aerial vehicle detection data, errors caused by a single data source are reduced, the accuracy and efficiency of fault judgment are improved, the intelligent scheduling module schedules the unmanned aerial vehicle based on the actual fault condition, street lamp distribution and real-time requirements, and the system is convenient to use. The system can optimize a detection path and resource distribution, improves the pertinence and timeliness of detection, can achieve the quick response especially in an emergency situation, can achieve the energy-saving operation of a street lamp, can preferentially process faults in a key region, guarantees the high-efficiency and stable operation of a lighting system, and improves the safety and reliability of the system, and the control module regulates and controls the brightness and determines a repair sequence according to a detection result. And the urban lighting management level is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent lighting and unmanned aerial vehicle application, in particular to an intelligent lighting detection system integrating unmanned aerial vehicle and smart lamp pole. BACKGROUND

[0002] In the current urban lighting management, traditional street light detection relies on manual inspection, which is not only inefficient, but also has the problem of incomplete detection. Although unmanned aerial vehicle detection has been applied, its endurance is limited, and the communication stability with ground equipment is insufficient. Although smart lamp poles have certain sensing functions, they cannot be effectively combined with unmanned aerial vehicles, making it difficult to achieve efficient collaborative detection.

[0003] In the prior art, when unmanned aerial vehicles perform lighting detection tasks alone, due to endurance limitations, the coverage of a single task is small, and in complex urban environments, communication with the ground control center is easily disturbed. At the same time, the environmental data collected by smart lamp poles cannot fully support unmanned aerial vehicle detection, the data processing and fault diagnosis efficiency is not high, and there is a lack of effective means for intelligent regulation of street lights based on detection results.

[0004] To solve the above problems, the present application provides an intelligent lighting detection system integrating unmanned aerial vehicles and smart lamp poles, which realizes complementary advantages by deeply integrating unmanned aerial vehicles and smart lamp poles, and improves the intelligent level of street light detection and management. SUMMARY

[0005] The present application provides an intelligent lighting detection system integrating unmanned aerial vehicles and smart lamp poles to solve the problems raised in the background art.

[0006] An intelligent lighting detection system integrating unmanned aerial vehicles and smart lamp poles, comprising:

[0007] An integration module for integrating an unmanned aerial vehicle base station on a smart lamp pole and integrating a sensor on the smart lamp pole;

[0008] A data interaction module for data interaction based on surrounding environment data collected by the sensor and detection data obtained by the unmanned aerial vehicle detection task, and determining street light fault information according to the interaction result;

[0009] An intelligent scheduling module for intelligent scheduling detection of the unmanned aerial vehicle based on the street light fault information, in combination with street light distribution and real-time demand, to obtain a detection result;

[0010] A control module for determining the brightness control and fault repair sequence of the street light based on the detection result.

[0011] Preferably, the integration module comprises:

[0012] A base station integration unit is arranged at the top of the smart lamp pole to install a base station integration platform, and charging devices, communication relay devices and unmanned aerial vehicle storage cabins are installed and integrated on the base station integration platform.

[0013] A sensor integration unit is arranged at a specific position of the smart lamp pole to integrate various sensors and integrate sensor communication devices to transmit data of the various sensors.

[0014] Preferably, the data interaction module comprises:

[0015] A region division unit is arranged to divide the detection regions according to detection difficulty based on the surrounding environment data collected by the sensors to obtain a plurality of detection regions.

[0016] A path planning unit is arranged to set a flight path of the unmanned aerial vehicle based on the unmanned aerial vehicle detection task and the detection difficulty of the detection regions.

[0017] A region detection unit is arranged to detect the detection regions according to the flight path of the unmanned aerial vehicle to obtain detection data.

[0018] An extraction unit is arranged to extract first time sequence features and first region features of the surrounding environment data and extract second time sequence features and second region features of the detection data.

[0019] An integration unit is arranged to integrate the first time sequence features, the first region features, the second time sequence features and the second region features to obtain the street lamp fault information.

[0020] Preferably, the integration unit comprises:

[0021] A standardization unit is arranged to standardize the first time sequence features, the first region features, the second time sequence features and the second region features to obtain standard time sequence features and standard region features.

[0022] A matrix establishment unit is arranged to establish a time sequence-region association matrix based on the standard time sequence features and the standard region features based on the association relationship between the time sequence and the region, and to assign weights to the features in the time sequence-region association matrix through an attention mechanism to obtain a weighted time sequence-region association matrix.

[0023] A vector establishment unit is arranged to extract and splice features of the weighted time sequence-region association matrix to obtain a fusion feature vector, and to extract abnormal features in the fusion feature vector.

[0024] A fault determination unit is arranged to match the abnormal features with a fault type database, and to determine the street lamp fault information according to a matching result.

[0025] Preferably, the intelligent scheduling module comprises:

[0026] The information analysis unit is configured to acquire a fault type, a fault severity, and a fault position from the street lamp fault information, determine a detection priority based on the fault type, the fault severity, and the fault position, and determine a target detection parameter based on the fault type;

[0027] The policy determination unit is configured to acquire a base station position, a load, and a remaining endurance of the UAV, match the base station position, the load, and the remaining endurance with the target detection parameter based on a preset resource matching rule to determine a resource adaptation degree, and determine an initial scheduling policy for the UAV based on the detection priority and the resource adaptation degree;

[0028] The path determination unit is configured to design a flight path of the UAV based on the UAV position and the street lamp position in combination with the target detection parameter, including an efficiency path and a precision path, and establish a path switching rule based on real-time requirements;

[0029] The policy judgment and adjustment unit is configured to determine actual detection parameters and actual resource consumption of the UAV under the initial scheduling policy based on the efficiency path, the precision path, and the path switching rule, determine a detection evaluation value under the initial scheduling policy based on a parameter precision deviation between the target detection parameter and the actual detection parameter and a resource difference between the actual resource consumption and a theoretical resource consumption under the resource adaptation degree, and determine the detection evaluation value.

[0030] The detection evaluation value is determined to be greater than a preset evaluation value;

[0031] If yes, the detection of the street lamp fault information is completed according to the initial scheduling policy, and detection data is obtained;

[0032] Otherwise, a weighted weight of the target detection parameter is set based on the parameter precision deviation, a weighted detection parameter is obtained, a preset resource matching rule is weighted processed based on the resource difference, a weighted resource matching rule is obtained, the base station position, the load, and the remaining endurance are matched with the target detection parameter based on the weighted resource matching rule to re-determine the resource adaptation degree, a latest scheduling policy is further determined, the detection of the street lamp fault information is completed according to the latest scheduling policy, and the detection data is obtained.

[0033] The result determination unit is configured to determine specific fault parameter information and personnel activity influence information from the detection data as a detection result.

[0034] Preferably, the information analysis unit comprises:

[0035] The influence determination unit is configured to determine a lighting influence value and a safety influence value based on the fault type, the fault severity, and the fault position;

[0036] The priority determination unit is configured to determine the detection priority based on a sum of the lighting influence value and the safety influence value;

[0037] The filtering unit is used to retrieve reference detection parameters related to the fault type from historical data, and filter the reference detection parameters based on real-time requirements to obtain the target detection parameters.

[0038] Preferably, the path determination unit includes:

[0039] The path generation evaluation unit is used to generate multiple initial flight paths based on the location of the UAV and the location of the street lamp, combined with detection parameters, and to evaluate the multiple initial flight paths based on the efficiency evaluation model and the accuracy evaluation model, and select the efficient path and the accurate path.

[0040] The rule-building unit is used to match keywords with efficiency and accuracy selections based on real-time requirements, and to build path switching rules based on the matching results.

[0041] Preferably, the control module includes:

[0042] The illumination loss determination unit is used to determine the fault point and fault type based on the detection results, determine the standard illumination value based on the historical illumination data of the fault point, and determine the illumination loss value based on the fault type.

[0043] The illumination compensation degree determination unit is used to obtain the street light illumination type and distance from the fault point based on the street light distribution information around the fault point, and to determine the illumination compensation degree of the surrounding street lights for the current fault point area based on the street light illumination type and distance from the fault point.

[0044] The brightness determination unit is used to determine the brightness of the streetlights around the fault point based on the light loss value and the light compensation degree, and to determine the comprehensive light compensation value for the fault point.

[0045] The repair coefficient determination unit is used to determine the basic repair coefficient based on the difference between the light deficiency value and the comprehensive light compensation value, obtain the impact information of personnel activities from the detection results, determine the safety impact value and the convenience impact value based on the impact information of personnel activities, determine the main repair coefficient based on the safety impact value, determine the secondary repair coefficient based on the convenience impact value, and determine the additional repair coefficient based on the main repair coefficient and the secondary repair coefficient.

[0046] The maintenance cost determination unit is used to obtain specific fault parameter information from the test results, determine the maintenance resources required to repair the specific fault parameter information based on historical repair data, and determine the resource cost coefficient based on the maintenance resources and their scheduling.

[0047] The repair sequence determination unit is used to generate a repair sequence for streetlights based on the basic repair coefficient, additional repair coefficient, and resource cost coefficient.

[0048] Preferably, the repair order determination unit includes:

[0049] The coefficient processing unit is used to determine the repair weight of the fault repair base coefficient based on the additional repair coefficient, and to perform weighted processing on the fault repair base coefficient based on the repair weight to obtain the target fault repair coefficient.

[0050] The sequence determination unit is used to establish a fault repair sequence based on the difference between the target fault repair coefficient and the resource cost coefficient as a fault repair score, in descending order of the fault repair scores.

[0051] Preferably, the brightness determination unit includes:

[0052] Based on the distance between the streetlights around the fault point and the fault point, a compensation brightness difference sequence is set. Based on the compensation brightness difference sequence and combined with the illumination loss value, the streetlight illumination compensation value is determined.

[0053] When the sum of the street light illumination compensation values ​​is less than or equal to the illumination loss value, the street light brightness is determined based on the street light illumination compensation values.

[0054] Otherwise, based on the assumption that the street light illumination compensation value is the same as the illumination loss value, the street light illumination compensation value is reduced according to the compensation brightness difference sequence to obtain the target street light illumination compensation value, and the street light brightness is determined based on the target street light illumination compensation value.

[0055] Compared with the prior art, the present invention has achieved the following beneficial effects:

[0056] The integrated module integrates the drone base station and sensors on the smart light pole, saving installation space and costs associated with independent equipment and facilitating centralized management and maintenance. It also allows sensors to collect environmental data locally, providing fundamental support for subsequent detection. The data interaction module, by fusing sensor environmental data and drone detection data, can more comprehensively and accurately determine street light obstruction information, reducing errors from single data sources and improving the accuracy and efficiency of fault diagnosis. The intelligent scheduling module schedules drones based on actual fault conditions, street light distribution, and real-time needs, optimizing detection paths and resource allocation, improving the targeting and timeliness of detection, and enabling rapid response, especially in emergencies. The control module adjusts brightness and determines the repair sequence based on detection results, achieving energy-saving operation of street lights while prioritizing critical area faults, ensuring the efficient and stable operation of the lighting system and improving urban lighting management.

[0057] 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.

[0058] 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

[0059] 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:

[0060] Figure 1 This is a structural diagram of an intelligent lighting detection system integrating a drone and a smart light pole, according to an embodiment of the present invention.

[0061] Figure 2 This is a structural diagram of the integrated module described in an embodiment of the present invention;

[0062] Figure 3 This is a structural diagram of the intelligent scheduling module described in an embodiment of the present invention. Detailed Implementation

[0063] 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.

[0064] Example 1:

[0065] This invention provides an intelligent lighting detection system integrating a drone and a smart light pole, such as... Figure 1 As shown, it includes:

[0066] An integrated module for integrating drone base stations and sensors onto smart light poles;

[0067] The data interaction module is used to interact with the surrounding environment data collected by the sensors and the detection data obtained by the UAV detection mission, and to determine the street light fault information based on the interaction results.

[0068] The intelligent scheduling module is used to intelligently schedule and detect drones based on street light fault information, combined with street light distribution and real-time demand, and obtain detection results;

[0069] The control module is used to determine the brightness control of streetlights and the order of fault repair based on the detection results.

[0070] In this embodiment, the drone base station is equipped with an automatic charging device, a drone storage compartment, and communication relay equipment. After completing its testing mission, the drone can automatically fly back to the base station to dock and recharge, solving the battery life problem. The communication relay equipment enhances the communication stability between the drone and the ground control center and expands the signal coverage area.

[0071] In this embodiment, the sensors include light sensors, temperature and humidity sensors, cameras, etc.

[0072] In this embodiment, intelligent scheduling and detection of drones can be used, for example, to launch drones at any time to inspect streetlights in a specific area, or to quickly arrange comprehensive inspections in an emergency.

[0073] In this embodiment, the detection data obtained by the UAV detection task is routine detection, while the UAV is intelligently scheduled for detection, and the detection result is specifically for detecting street light fault information.

[0074] The beneficial effects of the above design scheme are as follows: The integrated module realizes the integrated integration of drone base station and sensor on smart light pole, saving the installation space and cost of independent equipment, and facilitating centralized management and maintenance. At the same time, it allows the sensor to collect environmental data nearby, providing basic support for subsequent detection. The data interaction module, by fusing sensor environmental data and drone detection data, can more comprehensively and accurately determine street light obstruction information, reduce the error of a single data source, and improve the accuracy and efficiency of fault diagnosis. The intelligent scheduling module schedules drones based on actual fault conditions, street light distribution, and real-time needs, which can optimize detection paths and resource allocation, improve the targeting and timeliness of detection, and enable rapid response, especially in emergency situations. The control module adjusts brightness and determines the repair sequence based on the detection results, which can not only achieve energy-saving operation of street lights, but also prioritize the handling of faults in key areas, ensure the efficient and stable operation of the lighting system, and improve the level of urban lighting management.

[0075] Example 2:

[0076] Based on Embodiment 1, this embodiment of the invention provides an intelligent lighting detection system integrating a drone and a smart light pole, such as... Figure 2 As shown, the integrated module includes:

[0077] The base station integration unit is used to set up a base station integration platform on the top of the smart light pole, and to install and integrate charging devices, communication relay equipment, and drone storage compartments on the base station integration platform.

[0078] The sensor integration unit is used to integrate various sensors at specific locations on the smart light pole, and integrates a sensor communication device to transmit data between the various sensors.

[0079] The beneficial effects of the above design scheme are as follows: In the base station integration unit, the close integration of the charging device, communication relay equipment, and drone storage compartment significantly shortens the signal transmission distance between devices. When a drone leaves the storage compartment to perform a mission, the communication relay equipment can instantly establish a stable connection, and the charging device can quickly start the charging process after the drone returns. The connection time for a single mission is shortened. The sensor integration unit achieves centralized data transmission and distribution through the sensor communication device, enabling various sensor data to be aggregated to the smart light pole control module in real time. When sensors detect abnormal conditions such as street light malfunctions, the drone scheduling mechanism of the base station integration unit can be quickly triggered through the internal high-speed communication link. The response time of the drone from receiving the command to takeoff is shortened, and the accuracy of fault detection is improved.

[0080] Example 3:

[0081] Based on Embodiment 1, this embodiment of the invention provides an intelligent lighting detection system integrating a drone and a smart light pole, wherein the data interaction module includes:

[0082] The region division unit is used to divide the detection area according to the detection difficulty based on the surrounding environment data collected by the sensor, resulting in multiple detection areas;

[0083] The path planning unit is used to set the flight path of the UAV based on the UAV detection task and the detection difficulty of the detection area;

[0084] The area detection unit is used by the UAV to detect the detection area according to the flight path and obtain detection data;

[0085] The extraction unit is used to extract the first temporal features and the first regional features of the surrounding environmental data, and to extract the second temporal features and the second regional features of the detection data.

[0086] The integration unit is used to integrate the first time-series feature, the first regional feature, the second time-series feature, and the second regional feature to obtain street light fault information.

[0087] In this embodiment, temporal features include, for example, temperature trends, brightness conditions, and crowd flow conditions over a continuous time period. In this embodiment, regional features include, for example, brightness distribution and crowd flow distribution within a streetlight illumination area.

[0088] In this embodiment, the more difficult the detection, the denser the corresponding flight paths, and these are given priority.

[0089] The beneficial effects of the above design scheme are as follows: By classifying the detection area according to difficulty based on the surrounding environmental data collected by sensors, the UAV can prioritize processing high-difficulty areas, avoiding repeated detections or missed detections caused by blind flight. Temporal features, such as the changing trend of light intensity over time and the fluctuation period of street light current, and regional features, such as the average occlusion rate and street light distribution density of a specific area, are extracted from both environmental and detection data, achieving a structured representation of multi-dimensional data. The time granularity of the first and second temporal features is aligned, and the first and second regional features use a unified spatial grid encoding, laying the foundation for subsequent integration. Multiple features are fused through feature splicing and attention mechanisms, with a focus on strengthening highly correlated feature combinations. This provides accurate basis for subsequent maintenance resource scheduling, enabling more comprehensive and accurate determination of street light fault information, reducing errors from single data sources, and improving the accuracy and efficiency of fault diagnosis.

[0090] Example 4:

[0091] Based on Embodiment 3, this embodiment of the invention provides an intelligent lighting detection system integrating a drone and a smart light pole, wherein the integrated unit includes:

[0092] The standardization unit is used to standardize the first time-series feature, the first regional feature, the second time-series feature, and the second regional feature to obtain the standard time-series feature and the standard regional feature.

[0093] The matrix building unit is used to construct a time-series-region correlation matrix based on the correlation between time series and region, based on standard time series features and standard region features, and to assign weights to the features in the time-series-region correlation matrix through an attention mechanism to obtain a weighted time-series-region correlation matrix;

[0094] The vector building unit is used to extract and concatenate features from the weighted time-series-regional correlation matrix to obtain a fused feature vector, and to extract abnormal features from the fused feature vector.

[0095] The fault determination unit is used to match abnormal features with the fault type database and determine the street light fault information based on the matching results.

[0096] The beneficial effects of the above design scheme are as follows: By unifying data processing rules, the differences in dimensions and format conflicts among the four types of features are eliminated, making features from different sources comparable; by constructing a time-series-regional correlation matrix, the originally scattered time-series and regional features are incorporated into a unified correlation framework; by quantifying the spatiotemporal correlation strength between the two, the limitation of the separation of time and region in traditional feature processing is broken; through feature extraction and concatenation, the high-dimensional weighted time-series-regional correlation matrix is ​​compressed into a compact fused feature vector; and the targeted extraction of anomalous features avoids the waste of resources in full feature analysis. This improves the speed of fault identification. At the same time, by concatenating features, the spatiotemporal correlation information of abnormal features is preserved, providing rich contextual information for subsequent fault matching. Abnormal features are matched in a structured manner with a fault type database containing feature templates of common street light faults, such as abnormal current, light source damage, severe light decay, and lamp flickering. The matching degree is calculated using a cosine similarity algorithm. When the matching degree is ≥90%, the fault information is directly output, enabling a more comprehensive and accurate determination of street light obstruction information, reducing errors from a single data source, and improving the accuracy and efficiency of fault judgment.

[0097] Example 5:

[0098] Based on Embodiment 1, this embodiment of the invention provides an intelligent lighting detection system integrating a drone and a smart light pole, such as... Figure 3 As shown, the intelligent scheduling module includes:

[0099] The information analysis unit is used to obtain the fault type, fault severity and fault location from the street light fault information, determine the detection priority based on the fault type, fault severity and fault location, and determine the target detection parameters based on the fault type.

[0100] The strategy determination unit is used to obtain the base station location, payload and remaining endurance of the UAV, match the base station location, payload and remaining endurance with the target detection parameters based on the preset resource matching rules to determine the resource suitability, and determine the initial scheduling strategy for the UAV based on the detection priority and resource suitability.

[0101] The path determination unit is used to design and determine the flight path of the UAV based on the location of the UAV and the location of the street lamp, combined with the target detection parameters. This includes efficient paths and accuracy paths, and establishes path switching rules based on real-time requirements.

[0102] The strategy judgment and adjustment unit is used to determine the actual detection parameters and actual resource consumption of the UAV under the initial scheduling strategy based on the efficiency path, accuracy path and path switching rules. Based on the parameter accuracy deviation between the target detection parameters and the actual detection parameters, as well as the resource difference between the actual resource consumption and the theoretical resource consumption under the resource adaptation, the detection evaluation value under the initial scheduling strategy is determined.

[0103] Determine whether the detected evaluation value is greater than a preset evaluation value;

[0104] If so, the detection of street light fault information is completed according to the initial scheduling strategy, and the detection data is obtained;

[0105] Otherwise, the weighted detection parameters are set based on the parameter accuracy deviation to obtain the weighted detection parameters. The preset resource matching rules are weighted based on resource differences to obtain the weighted resource matching rules. Based on the weighted resource matching rules, the base station location, load and remaining battery life are matched with the target detection parameters to redetermine the resource adaptability. The latest scheduling strategy is further determined. The detection of street light fault information is completed according to the latest scheduling strategy to obtain the detection data.

[0106] The result determination unit is used to determine specific fault parameter information and personnel activity impact information from the detection data as the detection result.

[0107] In this embodiment, for example, when the fault type is cable sag, reference parameters are retrieved from historical data: shooting distance 5m, 360° surround angle, and 4K resolution. After combining the real-time requirements for nighttime detection and filtering, the target detection parameters are: infrared camera is turned on to identify abnormal cable temperature; the shooting frame rate is increased to 30fps to capture the sag amplitude in a light breeze; and the lidar scanning accuracy is 0.1m to measure the sag height.

[0108] In this embodiment, the specific fault parameter information is the fault detail data obtained through drone detection, which is used to clarify the fault degree and repair plan. For example, for the fault of billboard obstructing street light, the specific parameters parsed from the detection data are: obstruction size: 2m×1.5m (width×height); obstruction area ratio: 75% (affecting the street light illumination range); billboard material: plastic (lightweight, easily blown by the wind, aggravating obstruction); installation position: 1.2m away from the street light head (repair requires high-altitude operation).

[0109] In this embodiment, the impact information on personnel activities is based on the fault location, severity, and surrounding environment, assessing the impact of the fault on the safety and convenience of personnel activities. For the fault of the street light flickering at the school gate, the impact information on personnel activities is as follows: Impact range: 20m radius centered on the street light (covering the school gate and sidewalk); Time period risk: 7:00-8:00 am and 5:00-6:00 pm (peak hours for students going to and from school, risk coefficient 1.8); Activity type: children walking and parents picking up and dropping off (high requirement for light stability); Recommended measures: temporarily set up mobile lighting equipment and complete the repair within 2 hours.

[0110] The beneficial effects of the above design scheme are as follows: Quantitative calculation of lighting and safety impact values ​​determines detection priorities, ensuring high-speed response to high-risk faults; matching rules between UAV base station location, payload, and endurance with target detection parameters improves the adaptability of UAVs to the detection content and increases resource utilization; the coexistence of efficiency paths (shortest distance and few turns) and accuracy paths (multi-dimensional surround shooting), combined with real-time demand switching rules, allows for flexible response to scene changes; dynamic correction of the initial strategy by comparing detection evaluation values ​​with preset thresholds solves the problem of deviation between theoretical scheduling and actual execution, improving detection accuracy; and outputting specific fault parameters and personnel activity impact information provides a complete basis for maintenance scheduling and safety early warning, optimizing detection paths and resource allocation, enhancing the targeting and timeliness of detection, and enabling rapid response, especially in emergency situations.

[0111] Example 6:

[0112] Based on Embodiment 5, this embodiment of the invention provides an intelligent lighting detection system integrating a drone and a smart light pole, including an information analysis unit comprising:

[0113] The impact determination unit is used to determine the lighting impact value and the safety impact value based on the fault type, fault severity and fault location;

[0114] A priority determination unit is used to determine the detection priority based on the sum of the lighting impact value and the safety impact value;

[0115] The filtering unit is used to retrieve reference detection parameters related to the fault type from historical data, and filter the reference detection parameters based on real-time requirements to obtain the target detection parameters.

[0116] In this embodiment, for example, a short circuit fault on the main road, with a lighting impact value of 80, a safety impact value of 90, and a priority of 170, will take precedence over a light decay fault on the auxiliary road of the community, with a lighting impact value of 30, a safety impact value of 20, and a priority of 50.

[0117] The beneficial effects of the above design scheme are: by quantitatively calculating the impact values ​​of lighting and safety, the detection priority is determined, ensuring a high-speed response to high-risk faults.

[0118] Example 7:

[0119] Based on Embodiment 5, this embodiment of the invention provides an intelligent lighting detection system integrating a drone and a smart light pole, comprising a path determination unit, including:

[0120] The path generation evaluation unit is used to generate multiple initial flight paths based on the location of the UAV and the location of the street lamp, combined with detection parameters, and to evaluate the multiple initial flight paths based on the efficiency evaluation model and the accuracy evaluation model, and select the efficient path and the accurate path.

[0121] The rule-building unit is used to match keywords with efficiency and accuracy selections based on real-time requirements, and to build path switching rules based on the matching results.

[0122] The beneficial effects of the above design scheme are: by combining the efficiency path, which is specifically the shortest distance and few turns, with the accuracy path, which is specifically multi-dimensional surround shooting, and by combining the switching rules of real-time needs, it can flexibly respond to scene changes.

[0123] Example 8:

[0124] Based on Embodiment 1, this embodiment of the invention provides an intelligent lighting detection system integrating a drone and a smart light pole, wherein the control module includes:

[0125] The illumination loss determination unit is used to determine the fault point and fault type based on the detection results, determine the standard illumination value based on the historical illumination data of the fault point, and determine the illumination loss value based on the fault type.

[0126] The illumination compensation degree determination unit is used to obtain the street light illumination type and distance from the fault point based on the street light distribution information around the fault point, and to determine the illumination compensation degree of the surrounding street lights for the current fault point area based on the street light illumination type and distance from the fault point.

[0127] The brightness determination unit is used to determine the brightness of the streetlights around the fault point based on the light loss value and the light compensation degree, and to determine the comprehensive light compensation value for the fault point.

[0128] The repair coefficient determination unit is used to determine the basic repair coefficient based on the difference between the light deficiency value and the comprehensive light compensation value, obtain the impact information of personnel activities from the detection results, determine the safety impact value and the convenience impact value based on the impact information of personnel activities, determine the main repair coefficient based on the safety impact value, determine the secondary repair coefficient based on the convenience impact value, and determine the additional repair coefficient based on the main repair coefficient and the secondary repair coefficient.

[0129] The maintenance cost determination unit is used to obtain specific fault parameter information from the test results, determine the maintenance resources required to repair the specific fault parameter information based on historical repair data, and determine the resource cost coefficient based on the maintenance resources and their scheduling.

[0130] The repair sequence determination unit is used to generate a repair sequence for streetlights based on the basic repair coefficient, additional repair coefficient, and resource cost coefficient.

[0131] In this embodiment, the additional repair coefficient is mainly determined based on the primary repair coefficient, and the secondary repair coefficient is fine-tuned for it.

[0132] In this embodiment, the greater the resources required for maintenance and the more complex the scheduling, the higher the corresponding resource cost coefficient.

[0133] The beneficial effects of the above design scheme are as follows: The illumination loss determination unit quantifies the illumination loss value through historical illumination data. Combined with the illumination compensation determination unit's analysis of the type and distance of surrounding streetlights, it can accurately calculate the required illumination compensation amount for the fault point, avoiding energy waste caused by blindly increasing the brightness of surrounding streetlights; the brightness determination unit further adjusts the brightness of surrounding streetlights according to actual needs, ensuring basic illumination in the fault area while achieving efficient utilization of lighting resources and balancing energy saving and lighting effect; the repair coefficient determination unit combines the urgency of the illumination loss itself with a basic coefficient, the safety impact of personnel activities with a primary repair coefficient, and the convenience impact with a secondary repair coefficient, prioritizing safety factors, which conforms to the core principle of safety first in urban management. The design of the secondary repair coefficient, with the primary coefficient dominating and the secondary coefficient being fine-tuned, ensures both... This approach ensures both the rigidity of safety as a priority and the convenience of practical use, making the determination of repair priorities more aligned with actual scenario needs. The maintenance cost determination unit analyzes maintenance resource requirements and scheduling complexity, introducing a resource cost coefficient to avoid resource misallocation that may result from formulating repair plans solely based on urgency. For example, it prioritizes repairing low-urgency faults that require a large amount of scarce resources. The higher the resource cost coefficient, the more appropriate it will be in the repair order, ensuring that the repair plan is executed efficiently under the premise of resource accessibility and cost controllability, thereby improving overall repair efficiency. From quantifying and compensating for light loss to calculating repair coefficients and generating repair order, the logic of each unit is coherent, forming a complete closed loop. It can dynamically respond to the actual impact of faults and resource conditions, making fault handling more targeted and operable, ultimately improving the stability and emergency response capabilities of urban lighting systems.

[0134] Example 9:

[0135] Based on Embodiment 8, this embodiment of the invention provides an intelligent lighting detection system integrating a drone and a smart light pole, wherein the repair sequence determination unit includes:

[0136] The coefficient processing unit is used to determine the repair weight of the fault repair base coefficient based on the additional repair coefficient, and to perform weighted processing on the fault repair base coefficient based on the repair weight to obtain the target fault repair coefficient.

[0137] The sequence determination unit is used to establish a fault repair sequence based on the difference between the target fault repair coefficient and the resource cost coefficient as a fault repair score, in descending order of the fault repair scores.

[0138] In this embodiment, the target fault repair coefficient is always greater than the resource cost coefficient.

[0139] The beneficial effects of the above design scheme are as follows: by using the difference between the target fault repair coefficient and the resource cost coefficient as the scoring standard, the essence is to find a balance between needing to repair and being able to repair efficiently. For faults that are highly necessary but not difficult, the score is higher and they are given priority. For faults that are highly necessary but have complex resource scheduling, the score will be appropriately lowered to avoid resource congestion or inefficiency caused by forcibly prioritizing them. This design makes the repair sequence more in line with the actual execution conditions, reduces resource waste, and improves the smoothness of the overall repair process.

[0140] Example 10:

[0141] Based on Embodiment 8, this embodiment of the invention provides an intelligent lighting detection system integrating a drone and a smart light pole, wherein the brightness determination unit includes:

[0142] Based on the distance between the streetlights around the fault point and the fault point, a compensation brightness difference sequence is set. Based on the compensation brightness difference sequence and combined with the illumination loss value, the streetlight illumination compensation value is determined.

[0143] When the sum of the street light illumination compensation values ​​is less than or equal to the illumination loss value, the street light brightness is determined based on the street light illumination compensation values.

[0144] Otherwise, based on the assumption that the street light illumination compensation value is the same as the illumination loss value, the street light illumination compensation value is reduced according to the compensation brightness difference sequence to obtain the target street light illumination compensation value, and the street light brightness is determined based on the target street light illumination compensation value.

[0145] In this embodiment, the compensation brightness difference sequence is, for example, the compensation brightness difference sequence of streetlights at distances of 50m, 100m, and 150m must satisfy [50%, 20%, 10%]. That is, when the illumination compensation of the streetlight at a distance of 50m is 50, the illumination compensation of the streetlight at 100m must be 20, and the illumination compensation of the streetlight at 150m must be 10. The purpose is to ensure brightness uniformity.

[0146] In this embodiment, when the sum of the street light illumination compensation values ​​is greater than the illumination loss value, it indicates that the illumination compensation degree exceeds the required compensation demand, so it can be reduced to save resources while ensuring the lighting effect.

[0147] The beneficial effects of the above design scheme are: by using the logic of regular proportional constraints and dynamic total control, while ensuring the uniformity and accuracy of illumination, it achieves the goal of energy saving and the improvement of system efficiency, providing a scientific and reliable solution for temporary lighting protection in fault areas.

[0148] 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. An intelligent lighting detection system integrating a drone and a smart light pole, characterized in that, include: An integrated module for integrating drone base stations and sensors onto smart light poles; The data interaction module is used to interact with the surrounding environment data collected by the sensors and the detection data obtained by the UAV detection mission, and to determine the street light fault information based on the interaction results. The intelligent scheduling module is used to intelligently schedule and detect drones based on street light fault information, combined with street light distribution and real-time demand, and obtain detection results; The control module is used to determine the brightness control of streetlights and the order of fault repair based on the detection results.

2. The intelligent lighting detection system integrating a drone and a smart light pole according to claim 1, characterized in that, The integrated module includes: The base station integration unit is used to set up a base station integration platform on the top of the smart light pole, and to install and integrate charging devices, communication relay equipment, and drone storage compartments on the base station integration platform. The sensor integration unit is used to integrate various sensors at specific locations on the smart light pole, and integrates a sensor communication device to transmit data between the various sensors.

3. The intelligent lighting detection system integrating a drone and a smart light pole according to claim 1, characterized in that, The data interaction module includes: The region division unit is used to divide the detection area according to the detection difficulty based on the surrounding environment data collected by the sensor, resulting in multiple detection areas; The path planning unit is used to set the flight path of the UAV based on the UAV detection task and the detection difficulty of the detection area; The area detection unit is used by the UAV to detect the detection area according to the flight path and obtain detection data; The extraction unit is used to extract the first temporal features and the first regional features of the surrounding environmental data, and to extract the second temporal features and the second regional features of the detection data. The integration unit is used to integrate the first time-series feature, the first regional feature, the second time-series feature, and the second regional feature to obtain street light fault information.

4. The intelligent lighting detection system integrating a drone and a smart light pole according to claim 3, characterized in that, The integration unit includes: The standardization unit is used to standardize the first time-series feature, the first regional feature, the second time-series feature, and the second regional feature to obtain the standard time-series feature and the standard regional feature. The matrix building unit is used to construct a time-series-region correlation matrix based on the correlation between time series and region, based on standard time series features and standard region features, and to assign weights to the features in the time-series-region correlation matrix through an attention mechanism to obtain a weighted time-series-region correlation matrix; The vector building unit is used to extract and concatenate features from the weighted time-series-regional correlation matrix to obtain a fused feature vector, and to extract abnormal features from the fused feature vector. The fault determination unit is used to match abnormal features with the fault type database and determine the street light fault information based on the matching results.

5. The intelligent lighting detection system integrating a drone and a smart light pole according to claim 1, characterized in that, The intelligent scheduling module includes: The information analysis unit is used to obtain the fault type, fault severity and fault location from the street light fault information, determine the detection priority based on the fault type, fault severity and fault location, and determine the target detection parameters based on the fault type. The strategy determination unit is used to obtain the base station location, payload and remaining endurance of the UAV, match the base station location, payload and remaining endurance with the target detection parameters based on the preset resource matching rules to determine the resource suitability, and determine the initial scheduling strategy for the UAV based on the detection priority and resource suitability. The path determination unit is used to design and determine the flight path of the UAV based on the location of the UAV and the location of the street lamp, combined with the target detection parameters. This includes efficient paths and accuracy paths, and establishes path switching rules based on real-time requirements. The strategy judgment and adjustment unit is used to determine the actual detection parameters and actual resource consumption of the UAV under the initial scheduling strategy based on the efficiency path, accuracy path and path switching rules. Based on the parameter accuracy deviation between the target detection parameters and the actual detection parameters, as well as the resource difference between the actual resource consumption and the theoretical resource consumption under the resource adaptation, the detection evaluation value under the initial scheduling strategy is determined. Determine whether the detected evaluation value is greater than a preset evaluation value; If so, the detection of street light fault information is completed according to the initial scheduling strategy, and the detection data is obtained; Otherwise, the weighted detection parameters are set based on the parameter accuracy deviation to obtain the weighted detection parameters. The preset resource matching rules are weighted based on resource differences to obtain the weighted resource matching rules. Based on the weighted resource matching rules, the base station location, load and remaining battery life are matched with the target detection parameters to redetermine the resource adaptability. The latest scheduling strategy is further determined. The detection of street light fault information is completed according to the latest scheduling strategy to obtain the detection data. The result determination unit is used to determine specific fault parameter information and personnel activity impact information from the detection data as the detection result.

6. The intelligent lighting detection system integrating a drone and a smart light pole according to claim 5, characterized in that, The information analysis unit includes: The impact determination unit is used to determine the lighting impact value and the safety impact value based on the fault type, fault severity and fault location; A priority determination unit is used to determine the detection priority based on the sum of the lighting impact value and the safety impact value; The filtering unit is used to retrieve reference detection parameters related to the fault type from historical data, and filter the reference detection parameters based on real-time requirements to obtain the target detection parameters.

7. The intelligent lighting detection system integrating a drone and a smart light pole according to claim 5, characterized in that, The path determination unit includes: The path generation evaluation unit is used to generate multiple initial flight paths based on the location of the UAV and the location of the street lamp, combined with detection parameters, and to evaluate the multiple initial flight paths based on the efficiency evaluation model and the accuracy evaluation model, and select the efficient path and the accurate path. The rule-building unit is used to match keywords with efficiency and accuracy selections based on real-time requirements, and to build path switching rules based on the matching results.

8. The intelligent lighting detection system integrating a drone and a smart light pole according to claim 1, characterized in that, The control module includes: The illumination loss determination unit is used to determine the fault point and fault type based on the detection results, determine the standard illumination value based on the historical illumination data of the fault point, and determine the illumination loss value based on the fault type. The illumination compensation degree determination unit is used to obtain the street light illumination type and distance from the fault point based on the street light distribution information around the fault point, and to determine the illumination compensation degree of the surrounding street lights for the current fault point area based on the street light illumination type and distance from the fault point. The brightness determination unit is used to determine the brightness of the streetlights around the fault point based on the light loss value and the light compensation degree, and to determine the comprehensive light compensation value for the fault point. The repair coefficient determination unit is used to determine the basic fault repair coefficient based on the difference between the light deficiency value and the comprehensive light compensation value, obtain the personnel activity impact information from the detection results, determine the safety impact value and the convenience impact value based on the personnel activity impact information, determine the main repair coefficient based on the safety impact value, determine the secondary repair coefficient based on the convenience impact value, and determine the additional repair coefficient based on the main repair coefficient and the secondary repair coefficient. The maintenance cost determination unit is used to obtain specific fault parameter information from the test results, determine the maintenance resources required to repair the specific fault parameter information based on historical repair data, and determine the resource cost coefficient based on the maintenance resources and their scheduling. The repair sequence determination unit is used to generate a repair sequence for streetlights based on the basic repair coefficient, additional repair coefficient, and resource cost coefficient.

9. The intelligent lighting detection system integrating a drone and a smart light pole according to claim 8, characterized in that, The repair order determination unit includes: The coefficient processing unit is used to determine the repair weight of the fault repair base coefficient based on the additional repair coefficient, and to perform weighted processing on the fault repair base coefficient based on the repair weight to obtain the target fault repair coefficient. The sequence determination unit is used to establish a fault repair sequence based on the difference between the target fault repair coefficient and the resource cost coefficient as a fault repair score, in descending order of the fault repair scores.

10. The intelligent lighting detection system integrating a drone and a smart light pole according to claim 8, characterized in that, The brightness determination unit includes: Based on the distance between the streetlights around the fault point and the fault point, a compensation brightness difference sequence is set. Based on the compensation brightness difference sequence and combined with the illumination loss value, the streetlight illumination compensation value is determined. When the sum of the street light illumination compensation values ​​is less than or equal to the illumination loss value, the street light brightness is determined based on the street light illumination compensation values. Otherwise, based on the assumption that the street light illumination compensation value is the same as the illumination loss value, the street light illumination compensation value is reduced according to the compensation brightness difference sequence to obtain the target street light illumination compensation value, and the street light brightness is determined based on the target street light illumination compensation value.

Images