Wind-solar complementary intelligent monitoring unmanned plane cruising system

Abstract

This invention discloses a wind-solar hybrid intelligent monitoring drone patrol system, specifically relating to the field of unmanned inspection. It includes a wind-solar hybrid power supply module, a ground intelligent monitoring module, a drone automatic patrol module, and an intelligent scheduling and control module. The wind-solar hybrid power supply module provides energy to the system, enabling load monitoring, predictive evaluation, and adaptive power balance control of the wind-solar hybrid units. The ground intelligent monitoring module collects multi-source environmental monitoring data in field scenarios. The drone automatic patrol module performs dynamic patrols, automatic charging, and differentiated inspections based on risk and power supply status. The intelligent scheduling and control module coordinates data fusion, task scheduling, energy allocation, and anomaly warning. This invention achieves long-term stable operation, comprehensive monitoring without blind spots, efficient intelligent collaborative operation, and accurate real-time early warning in field scenarios without mains power.

Description

Technical Field

[0001] This invention relates to the field of unmanned inspection, and more specifically, to a wind-solar hybrid intelligent monitoring drone patrol system. Background Technology

[0002] Currently, when carrying out intelligent monitoring and safety inspection work in areas without mains power coverage, such as river channels, mountainous areas, and forests, we still face several technical bottlenecks that urgently need to be overcome, which seriously restrict the monitoring efficiency and reliability.

[0003] 1. Traditional monitoring equipment either relies on mains power, requiring the laying of long-distance power cables in complex terrain, resulting in high construction costs and susceptibility to damage from natural disasters; or it uses short-duration batteries, requiring frequent manual replacement, which not only incurs high maintenance costs but also fails to meet the requirements for long-term unattended continuous operation, often leading to the loss of monitoring data due to power outages.

[0004] 2. Existing monitoring mainly relies on fixed ground-based points. Due to natural conditions such as undulating terrain, vegetation obstruction, and meandering river channels, the monitoring field of view is limited, making it difficult to achieve full coverage of a large area and accurate investigation of potential hazards, which can easily lead to missed detection of abnormal situations.

[0005] 3. Existing drone inspections mostly perform preset tasks independently, without forming an effective linkage with ground monitoring systems and being unable to share energy supply (e.g., drones cannot automatically replenish energy using ground monitoring stations), resulting in fragmented ground and aerial monitoring data and a low overall level of intelligence and collaboration.

[0006] 4. In the absence of operator base station coverage in the wild, traditional wireless communication methods are susceptible to electromagnetic interference and terrain obstruction, which can lead to frequent interruptions and packet loss in the transmission of monitoring data and drone inspection images and videos. This makes it impossible to guarantee stable data transmission and real-time early warning of abnormal situations, thus delaying the opportunity for emergency response.

[0007] Although independent wind-solar hybrid power supply systems and drone inspection solutions have emerged in existing technologies, the two lack organic integration and have failed to solve core issues such as intelligent energy dispatch optimization, deep integration of multi-source monitoring data, and intelligent dynamic scheduling of inspection tasks. As a result, they are difficult to meet the actual needs of full-coverage, long-term stability, and efficient collaborative monitoring and inspection in complex field environments.

[0008] To address the aforementioned problems, a technical solution is provided. Summary of the Invention

[0009] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a wind-solar hybrid intelligent monitoring drone patrol system to solve the problems mentioned in the background art.

[0010] To achieve the above objectives, the present invention provides the following technical solution:

[0011] A wind-solar hybrid intelligent monitoring drone patrol system includes a wind-solar hybrid power supply module, a ground intelligent monitoring module, a drone automatic patrol module, and an intelligent dispatch and control module;

[0012] The wind-solar hybrid power supply module is used to provide energy supply to the system and realize load monitoring, prediction and evaluation and adaptive power balance control of the wind-solar hybrid unit;

[0013] The ground-based intelligent monitoring module is used to collect multi-source environmental monitoring data in field scenarios;

[0014] The drone automatic patrol module performs dynamic patrol, automatic charging, and differentiated inspection based on risk and power supply status.

[0015] The intelligent scheduling and control module is used to coordinate data fusion, task scheduling, energy allocation, and anomaly early warning.

[0016] In a preferred embodiment, the operation of the wind-solar hybrid power supply module specifically includes the following:

[0017] Collect real-time load monitoring data of the target wind-solar hybrid power generation unit, which includes wind power generation modules and photovoltaic power generation modules;

[0018] A load assessment model is introduced to analyze the load monitoring data and obtain the predicted power generation load results;

[0019] If the predicted power generation load exceeds the preset load threshold, an adaptive control command is generated.

[0020] In a preferred embodiment, the full real-time operation monitoring data of the target wind-solar hybrid power generation unit is collected based on adaptive control commands and used as the data source for the multi-input power generation prediction model.

[0021] The real-time operation monitoring data is segmented by features to extract real-time meteorological factors, wind power generation component operation status data and photovoltaic power generation component operation status data;

[0022] Real-time meteorological information and wind power generation component operation data are input into the wind power prediction channel to obtain the predicted output power of the wind power generation components;

[0023] Real-time meteorological information and photovoltaic power generation module operation data are input into the photovoltaic power generation prediction channel to obtain the predicted output power of the photovoltaic power generation module;

[0024] The predicted output power of the wind power generation module and the photovoltaic power generation module are summed to obtain the overall predicted power generation of the power generation unit.

[0025] In a preferred embodiment, the operation of the ground-based intelligent monitoring module specifically includes the following:

[0026] Collect real-time monitoring data on meteorology, hydrology, soil, geology, and the ecological environment;

[0027] If the predicted power generation of the wind-solar hybrid power supply module exceeds the preset power threshold, priority will be given to ensuring the power supply of the ground intelligent monitoring module and the UAV automatic patrol module.

[0028] In a preferred embodiment, a power smoother is activated based on an adaptive control command to obtain the predicted output power of wind power and photovoltaic modules and compare the difference.

[0029] If the wind power generation unit is predicted to have a higher output power, it will be selected as the target control unit.

[0030] If the photovoltaic power generation module is predicted to have a higher output power, it will be selected as the target control unit.

[0031] In a preferred embodiment, the operation of the UAV automatic patrol module specifically includes the following:

[0032] Based on the spatial distribution of each point within the monitoring area, the distance between points is calculated, isolated monitoring points and concentrated monitoring areas are divided, and two types of core inspection points are determined.

[0033] Based on the effective risk level of each inspection point, a differentiated search radius is matched for different points, and isolated points are mapped to circular inspection areas and concentrated areas are mapped to polygonal inspection areas to generate a dynamic patrol map.

[0034] Generate an executable drone flight path based on the updated patrol map.

[0035] In a preferred embodiment, data on triggering conditions such as meteorological and hydrological rhythms, environmental disturbances, and emergencies are collected, and multiple operation periods are divided according to thresholds.

[0036] Analyze the overlapping intervals and number of overlaps in each operation period, and generate drone operation instructions based on preset triggering rules;

[0037] The system analyzes operational instructions and dynamically adjusts patrol routes and monitoring mission parameters, including increasing or decreasing the number of flights, adjusting the frequency of photo taking, increasing the frequency of patrols in high-risk areas, and simplifying patrols in low-risk areas.

[0038] In a preferred embodiment, the intelligent scheduling control module operates specifically including the following:

[0039] Analyze the time-series images generated by continuous monitoring, assess the effective risk level of each point based on changes in water body characteristics, and determine the final effective level based on two consecutive consistent risk levels.

[0040] Eliminate low-risk areas, strengthen the inspection priority of high-risk areas, and update the power allocation strategy of wind-solar hybrid power supply modules in a timely manner to ensure energy supply during inspection periods in high-risk areas.

[0041] By integrating ground monitoring data with drone inspection data, early warnings are triggered for abnormal locations.

[0042] The technical effects and advantages of the wind-solar hybrid intelligent monitoring drone patrol system of the present invention are as follows:

[0043] 1. Through real-time load monitoring, multi-dimensional power prediction and adaptive power balance control of the wind-solar hybrid power supply module, the utilization of solar and wind energy resources can be maximized to achieve energy complementarity day and night and all seasons; with a large-capacity energy storage unit, even under severe weather conditions such as continuous rain and no wind, the system can still ensure a continuous and stable power supply for 7-15 days, completely freeing it from the constraints of the mains power supply, meeting the needs of long-term unattended operation in the field, and significantly reducing the construction and maintenance costs of cable laying and battery replacement;

[0044] 2. The ground-based intelligent monitoring module collects multi-dimensional basic data such as meteorology, hydrology, soil, and geology. The UAV automatic patrol module plans differentiated inspection paths based on the spatial distribution and risk level of monitoring points to achieve full coverage without blind spots. At the same time, by dynamically adjusting the patrol parameters, it intensifies inspections in high-risk areas and simplifies inspections in low-risk areas, thus making up for the limited field of view of ground-based fixed monitoring.

[0045] 3. The intelligent scheduling and control module enables deep fusion and analysis of ground sensor data and UAV inspection data, and achieves task feedback through data exchange; at the same time, the UAV can use the wind and solar complementary energy of the ground monitoring station to achieve automatic take-off, landing and charging.

[0046] 4. Improve the accuracy of risk level determination through continuous verification of time-series images, and achieve accurate identification of abnormal situations by combining multi-source data for complementary verification; once an anomaly is detected, a graded early warning is immediately triggered, and energy power allocation and inspection resource scheduling are optimized simultaneously to prioritize energy supply for inspection and emergency response in high-risk areas, thereby improving emergency response speed and handling efficiency. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the structure of a wind-solar hybrid intelligent monitoring drone patrol system according to the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0049] Example 1

[0050] Figure 1 The present invention provides a wind-solar hybrid intelligent monitoring drone patrol system, comprising a wind-solar hybrid power supply module, a ground intelligent monitoring module, a drone automatic patrol module, and an intelligent scheduling and control module;

[0051] The wind-solar hybrid power supply module is used to provide energy supply to the system and realize load monitoring, prediction and evaluation and adaptive power balance control of the wind-solar hybrid unit;

[0052] The ground-based intelligent monitoring module is used to collect multi-source environmental monitoring data in field scenarios;

[0053] The drone automatic patrol module performs dynamic patrol, automatic charging, and differentiated inspection based on risk and power supply status.

[0054] The intelligent scheduling and control module is used to coordinate data fusion, task scheduling, energy allocation, and anomaly early warning.

[0055] The operation of the wind-solar hybrid power supply module includes the following:

[0056] Collect real-time load monitoring data of the target wind-solar hybrid power generation unit, which includes wind power generation modules and photovoltaic power generation modules;

[0057] A load assessment model is introduced to analyze the load monitoring data and obtain the predicted power generation load results;

[0058] If the predicted power generation load exceeds the preset load threshold, an adaptive control command is generated.

[0059] Based on adaptive control commands, the full real-time operation monitoring data of the target wind-solar hybrid power generation unit is collected and used as the data source for the multi-input power generation prediction model.

[0060] The real-time operation monitoring data is segmented by features to extract real-time meteorological factors, wind power generation component operation status data and photovoltaic power generation component operation status data;

[0061] Real-time meteorological information and wind power generation component operation data are input into the wind power prediction channel to obtain the predicted output power of the wind power generation components;

[0062] Real-time meteorological information and photovoltaic power generation module operation data are input into the photovoltaic power generation prediction channel to obtain the predicted output power of the photovoltaic power generation module;

[0063] The predicted output power of the wind power generation module and the photovoltaic power generation module are summed to obtain the overall predicted power generation of the power generation unit.

[0064] Real-time acquisition of load data from wind and solar power modules, combined with a load assessment model, accurately predicts future load fluctuations, proactively mitigating risks such as equipment overload and overcharging / over-discharging of energy storage batteries caused by overload exceeding limits, ensuring long-term stable system operation. When the predicted load exceeds a preset threshold, the adaptive control command's active triggering mechanism transforms from passive response to proactive prediction, significantly improving the system's ability to cope with complex weather conditions in the field (such as continuous rain and windless periods), effectively extending the lifespan of energy storage batteries and power generation modules. The acquisition of full real-time operational data and the application of multi-input prediction models... This system comprehensively covers multi-dimensional information on meteorology and unit operation, avoiding prediction bias caused by data gaps. By breaking down the data into meteorological factors and unit operation status data and constructing independent prediction channels for wind power and photovoltaics, it can specifically capture the power generation patterns of different energy sources, significantly improving the accuracy of power generation prediction. Finally, the overall predicted power generation obtained by summing is combined with the dynamic control of the power smoother to achieve a balanced distribution of wind and solar energy, ensuring that the system can maintain continuous power supply for 7-15 days in cloudy, rainy, and windless weather, completely eliminating dependence on grid power and meeting the energy needs of long-term unattended monitoring in the field.

[0065] The operation of the ground-based intelligent monitoring module specifically includes the following:

[0066] Collect real-time monitoring data on meteorology, hydrology, soil, geology, and the ecological environment;

[0067] If the predicted power generation of the wind-solar hybrid power supply module exceeds the preset power threshold, priority will be given to ensuring the power supply of the ground intelligent monitoring module and the UAV automatic patrol module.

[0068] The power smoother is activated based on the adaptive control command, and the predicted output power of wind power and photovoltaic modules is obtained and the difference is compared.

[0069] If the wind power generation unit is predicted to have a higher output power, it will be selected as the target control unit.

[0070] If the photovoltaic power generation module is predicted to have a higher output power, it will be selected as the target control unit.

[0071] It comprehensively collects real-time data from multiple dimensions, including meteorology, hydrology, soil, geology, and the ecological environment, enabling the construction of a basic environmental data system covering the monitoring area. This provides complete data support for comprehensive monitoring and analysis and anomaly identification. By real-time linkage with the predicted power generation of the wind-solar hybrid power supply module, it prioritizes power supply to itself and the UAV automatic patrol module when the power exceeds a preset threshold. This ensures that core monitoring tasks are not affected by energy fluctuations, maintains the continuity and stability of monitoring work, and avoids data loss due to power outages. Based on adaptive control commands, it activates a power smoother and selects the target control unit by comparing the predicted output power of wind and solar modules. This allows for targeted dynamic adjustment of power generation, achieving balanced distribution and efficient utilization of wind and solar energy. It avoids overload operation of a single energy component, maximizes the power supply advantages of wind-solar hybrid systems, and ensures the reliability of energy supply under complex weather conditions in the field.

[0072] The operation of the drone automatic patrol module specifically includes the following:

[0073] Based on the spatial distribution of each point within the monitoring area, the distance between points is calculated, isolated monitoring points and concentrated monitoring areas are divided, and two types of core inspection points are determined.

[0074] Based on the effective risk level of each inspection point, a differentiated search radius is matched for different points, and isolated points are mapped to circular inspection areas and concentrated areas are mapped to polygonal inspection areas to generate a dynamic patrol map.

[0075] Generate an executable drone flight path based on the updated patrol map.

[0076] Collect data on triggering conditions such as meteorological and hydrological rhythms, environmental disturbances, and emergencies, and divide the operation into multiple time periods according to thresholds;

[0077] Analyze the overlapping intervals and number of overlaps in each operation period, and generate drone operation instructions based on preset triggering rules;

[0078] The system analyzes operational instructions and dynamically adjusts patrol routes and monitoring mission parameters, including increasing or decreasing the number of flights, adjusting the frequency of photo taking, increasing the frequency of patrols in high-risk areas, and simplifying patrols in low-risk areas.

[0079] By integrating spatial point division, risk level adaptation, dynamic patrol flight planning, and multi-condition intelligent triggering, the efficiency of all-area inspection can be significantly improved. First, isolated points and concentrated areas are distinguished according to the spatial distribution of monitoring points. Then, differentiated inspection ranges are matched according to the risk level of different points. Isolated points are set as circular inspection areas and concentrated areas are set as polygonal inspection areas, and dynamic patrol flight maps are generated. This makes the UAV inspection path more in line with the actual terrain and monitoring needs, avoiding ineffective flights and monitoring blind spots. At the same time, multi-dimensional trigger data such as meteorological, hydrological rhythms, environmental disturbances, and emergencies are collected, and operation time periods are divided and overlapping intervals are counted. Based on this, operation instructions are intelligently generated, which can flexibly adjust the patrol flight path, number of flights, and photo frequency. The inspection is intensified in high-risk areas and simplified in low-risk areas, which improves the speed of abnormal event detection and emergency response capabilities. It can reasonably save energy consumption, extend the UAV's endurance and the overall system runtime, making the inspection operation more targeted, economical, and intelligent, and perfectly adapting to the long-term automatic patrol flight needs in the field without mains power.

[0080] The intelligent scheduling and control module operates by including the following:

[0081] Analyze the time-series images generated by continuous monitoring, assess the effective risk level of each point based on changes in water body characteristics, and determine the final effective level based on two consecutive consistent risk levels.

[0082] Eliminate low-risk areas, strengthen the inspection priority of high-risk areas, and update the power allocation strategy of wind-solar hybrid power supply modules in a timely manner to ensure energy supply during inspection periods in high-risk areas.

[0083] By integrating ground monitoring data with drone inspection data, early warnings are triggered for abnormal locations.

[0084] Deep analysis of time-series images generated by continuous monitoring, assessment of risk levels at each location based on changes in water body characteristics, and using two consecutive consistent results as the final valid level effectively filters out random errors from single monitoring, ensuring the accuracy and reliability of risk level determination and avoiding misjudgments or omissions. By eliminating low-risk areas and prioritizing inspections of high-risk areas, while simultaneously adjusting the power allocation strategy of the wind-solar hybrid power supply module to prioritize energy supply during inspection periods in high-risk areas, precise matching of inspection resources and energy supply is achieved, improving the efficiency of detecting anomalies and hidden dangers in high-risk areas, avoiding energy waste, and ensuring the efficient advancement of core monitoring tasks. Furthermore, the integration of multi-dimensional ground monitoring data with images and environmental data from UAV inspections, through complementary verification and correlation analysis of multi-source data, significantly improves the accuracy of anomaly identification, promptly triggers early warnings, and provides comprehensive and reliable data support for emergency response. This completely solves the problems of data fragmentation and delayed response in traditional monitoring, significantly improving the intelligence level and emergency response capabilities of full-domain monitoring, and providing a solid guarantee for safe and stable monitoring in long-term unattended field scenarios.

[0085] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0086] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A wind-solar complementary intelligent monitoring unmanned aerial vehicle patrol system, characterized in that, It includes a wind-solar hybrid power supply module, a ground intelligent monitoring module, an unmanned aerial vehicle (UAV) automatic patrol flight module, and an intelligent dispatch and control module; The wind-solar hybrid power supply module is used to provide energy supply to the system and realize load monitoring, prediction and evaluation and adaptive power balance control of the wind-solar hybrid unit; The ground-based intelligent monitoring module is used to collect multi-source environmental monitoring data in field scenarios; The drone automatic patrol module performs dynamic patrol, automatic charging, and differentiated inspection based on risk and power supply status. The intelligent scheduling and control module is used to coordinate data fusion, task scheduling, energy allocation, and anomaly early warning.

2. The wind-solar hybrid intelligent monitoring drone patrol system according to claim 1, characterized in that: The operation of the wind-solar hybrid power supply module includes the following: Collect real-time load monitoring data of the target wind-solar hybrid power generation unit, which includes wind power generation modules and photovoltaic power generation modules; A load assessment model is introduced to analyze the load monitoring data and obtain the predicted power generation load results; If the predicted power generation load exceeds the preset load threshold, an adaptive control command is generated.

3. The wind-solar hybrid intelligent monitoring drone patrol system according to claim 2, characterized in that: Based on adaptive control commands, the full real-time operation monitoring data of the target wind-solar hybrid power generation unit is collected and used as the data source for the multi-input power generation prediction model. The real-time operation monitoring data is segmented by features to extract real-time meteorological factors, wind power generation component operation status data and photovoltaic power generation component operation status data; Real-time meteorological information and wind power generation component operation data are input into the wind power prediction channel to obtain the predicted output power of the wind power generation components; Real-time meteorological information and photovoltaic power generation module operation data are input into the photovoltaic power generation prediction channel to obtain the predicted output power of the photovoltaic power generation module; The predicted output power of the wind power generation module and the photovoltaic power generation module are summed to obtain the overall predicted power generation of the power generation unit.

4. The wind-solar hybrid intelligent monitoring drone patrol system according to claim 3, characterized in that: The operation of the ground-based intelligent monitoring module specifically includes the following: Collect real-time monitoring data on meteorology, hydrology, soil, geology, and the ecological environment; If the predicted power generation of the wind-solar hybrid power supply module exceeds the preset power threshold, priority will be given to ensuring the power supply of the ground intelligent monitoring module and the UAV automatic patrol module.

5. The wind-solar hybrid intelligent monitoring drone patrol system according to claim 4, characterized in that: The power smoother is activated based on the adaptive control command, and the predicted output power of wind power and photovoltaic modules is obtained and the difference is compared. If the wind power generation unit is predicted to have a higher output power, it will be selected as the target control unit. If the photovoltaic power generation module is predicted to have a higher output power, it will be selected as the target control unit.

6. The wind-solar hybrid intelligent monitoring drone patrol system according to claim 5, characterized in that: The operation of the drone automatic patrol module specifically includes the following: Based on the spatial distribution of each point within the monitoring area, the distance between points is calculated, isolated monitoring points and concentrated monitoring areas are divided, and two types of core inspection points are determined. Based on the effective risk level of each inspection point, a differentiated search radius is matched for different points, and isolated points are mapped to circular inspection areas and concentrated areas are mapped to polygonal inspection areas to generate a dynamic patrol map. The updated patrol map is used to generate the actual drone patrol path.

7. The wind-solar hybrid intelligent monitoring drone patrol system according to claim 6, characterized in that: Collect meteorological, hydrological rhythm, environmental disturbance and emergency triggering conditions data, and divide the operation into multiple time periods according to thresholds; Analyze the overlapping intervals and number of overlaps in each operation period, and generate drone operation instructions based on preset triggering rules; The system analyzes operational instructions and dynamically adjusts patrol routes and monitoring mission parameters, including increasing or decreasing the number of flights, adjusting the frequency of photo taking, increasing the frequency of patrols in high-risk areas, and simplifying patrols in low-risk areas.

8. The wind-solar hybrid intelligent monitoring drone patrol system according to claim 7, characterized in that: The intelligent scheduling and control module operates by including the following: Analyze the time-series images generated by continuous monitoring, assess the effective risk level of each point based on changes in water body characteristics, and determine the final effective level based on two consecutive consistent risk levels. Eliminate low-risk areas, strengthen the inspection priority of high-risk areas, and update the power allocation strategy of wind-solar hybrid power supply modules in a timely manner to ensure energy supply during inspection periods in high-risk areas. By integrating ground monitoring data with drone inspection data, early warnings are triggered for abnormal locations.

Images