Plateau area LED integrated lighting system based on low-light photovoltaic driving

Abstract

The invention discloses a plateau area LED integrated lighting system based on low-light photovoltaic driving, and relates to the technical field of intelligent lighting. The plateau area LED integrated lighting system based on low-light photovoltaic driving comprises a data acquisition and preprocessing module for preprocessing environment energy data and target sensing data; the intelligent environment perception and energy-saving scheduling module is used for performing suppression type harmonic product evaluation on the environment energy data, and performing adaptive adjustment of lighting output, energy distribution and charging management; the target type distinguishing and business shunting module is used for dynamically identifying the target type and pushing and judging whether to enter the intelligent lighting range and brightness regulation and control module in real time; and the intelligent illumination range and brightness regulation and control module is used for dynamically optimizing illumination space distribution, brightness output and a continuous strategy. The problem that an LED lighting system in a plateau area cannot realize intelligent self-adaptive regulation and control and efficient energy management under complex environment and variable load conditions is solved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of intelligent lighting, in particular to a highland LED integrated lighting system based on micro-light photovoltaic driving. BACKGROUND

[0002] With the popularization of smart cities and green energy concepts, LED lighting systems based on solar photovoltaic driving are increasingly popular in public places such as roads, squares, scenic spots, etc. Due to the unique geographical location, the highland area is rich in sunshine resources, and micro-light photovoltaic technology can efficiently utilize solar energy under low-illumination conditions, providing a solid energy foundation for local green lighting. At the same time, LED light sources, with their high brightness, low energy consumption and long service life, have become the mainstream choice in the outdoor lighting field. In recent years, integrated intelligent lighting systems have been continuously developed, integrating efficient photovoltaic components, intelligent controllers, energy storage batteries and multiple types of sensors, which can realize integrated operation of lighting, energy supply, energy consumption monitoring and intelligent scheduling, meeting the lighting needs of the highland area in terms of variable climate, complex terrain and distributed scenes. Technical progress has continuously improved the reliability, energy efficiency and intelligent management of lighting systems, providing a sustainable and low-carbon new path for public lighting in highlands and remote areas.

[0003] For example, the patent for invention with the announcement number CN110831306B discloses an intelligent lighting system and its safety design method, which includes a central management server, a lighting controller, a mobile control terminal, a router and a plurality of lighting nodes. The lighting nodes form a lighting network, the mobile control terminal and the lighting controller are connected with the central management server and the router respectively for data exchange, and the lighting controller is provided with a UDP server, supporting Web login and APP operation. The network link includes wired Ethernet and wireless communication, and the central management server has user management, data management, control management, monitoring management, fault management, report management and log management function modules.

[0004] For example, the patent for invention with the publication number CN106028581A discloses a lighting system and its control method, which includes a processor and a controller. The controller is used to monitor the light output power of a plurality of lighting sources within a period of time, sequentially correct a subset of lighting sources to obtain a corrected light output, and control the lighting sources to maintain a predetermined light output power. It can detect defective lighting sources and dynamically allocate non-defective lighting sources for compensation. The lighting sources include actinic lighting sources and non-actinic lighting sources, and support multiple exposure wavelengths. The method also includes a compensation mechanism for lighting source decay, which increases the current or increases the number of active lighting sources to maintain the light output, supports dynamic switching of lighting source grouping, and can predict system life based on parameters and implement regular maintenance.

[0005] The existing intelligent lighting system mostly adopts centralized control, single communication mode or fixed logic management mode to realize node control and security protection, and some schemes only support basic remote control and timing task scheduling, lacking flexible data interaction and hierarchical security evaluation capability. In network communication, some traditional systems are limited to single wired or wireless protocol, and are difficult to adapt to heterogeneous access demand in complex environment. For abnormal detection and state compensation of lighting nodes, the existing scheme often relies on periodic inspection or single-point redundant switching, and it is difficult to realize intelligent collaborative response and real-time compensation for multi-lighting source failure. In terms of security management and risk assessment, the traditional method is mainly based on static permission configuration, manual statistics or simple level division, and it is difficult to realize multi-dimensional quantitative indicators and automatic risk rating, affecting the overall security and intelligent control ability.

[0006] Therefore, in view of the above problems, there is an urgent need for a high-altitude region LED integrated lighting system based on micro-light photovoltaic driving. SUMMARY

[0007] Technical problems solved In view of the deficiencies of the prior art, the present application provides a high-altitude region LED integrated lighting system based on micro-light photovoltaic driving, which solves the problem that the high-altitude region LED lighting system cannot realize intelligent adaptive regulation and efficient energy management under complex environment and variable load conditions.

[0008] Technical scheme To achieve the above purpose, the present application is implemented by the following technical scheme: a high-altitude region LED integrated lighting system based on micro-light photovoltaic driving, comprising a data acquisition and preprocessing module for acquiring environmental energy data and target perception data, and preprocessing the environmental energy data and target perception data; an intelligent environment perception and energy-saving scheduling module for performing suppressive harmonic product evaluation on the environmental energy data, and performing adaptive adjustment of lighting output, energy distribution and charging management according to the suppressive harmonic product evaluation result; a target type discrimination and service shunting module for performing feature interaction fusion analysis on the target perception data, and dynamically identifying the target type and real-time pushing to determine whether to enter the intelligent lighting range and brightness control module according to the feature interaction fusion analysis result; an intelligent lighting range and brightness control module for performing state enhancement fusion analysis on the environmental energy data and target perception data, and performing dynamic optimization of lighting space distribution, brightness output and continuous strategy according to the state enhancement fusion analysis result.

[0009] Further, the specific process of collecting environmental energy data and target perception data is: collecting environmental energy data and target perception data in real time; the environmental energy data includes: current light intensity, maximum light intensity, current battery remaining capacity, historical battery capacity data, battery remaining energy ratio, environmental temperature, photovoltaic output power, and historical environmental temperature; the target perception data includes: target real-time speed, target real-time size value, target real-time reflection intensity, target continuous real-time speed, target relative distance, azimuth angle, and sensor absolute coordinates, and video monitoring image data.

[0010] Further, the specific process of preprocessing the environmental energy data and the target perception data is: performing noise suppression on the environmental energy data by using an adaptive mean filtering and median filtering algorithm to reduce instantaneous fluctuations caused by sensor drift, environmental disturbance, and measurement error; performing physical consistency verification on the target perception data by using a motion anomaly recognition and trajectory continuity analysis algorithm to eliminate data records with broken motion trajectories, abrupt points, and inconsistent physical laws; performing noise suppression on the target perception data by using a Kalman filter and a multi-level time series smoothing algorithm to improve the accuracy and stability of motion feature acquisition; and performing scale unification and interval mapping on the environmental energy data and the target perception data by using a distribution standardization and linear normalization algorithm to perform standardization and normalization processing.

[0011] Further, the specific process of performing suppressive harmonic product evaluation on the environmental energy data is: The current light intensity, maximum light intensity, current battery remaining capacity, historical battery capacity data, environmental temperature, photovoltaic output power, and historical environmental temperature are obtained; the maximum battery capacity is obtained by performing statistical and outlier elimination algorithms on the historical battery capacity data; the optimal environmental temperature is obtained by performing a fitting energy efficiency temperature curve algorithm on the photovoltaic output power and the historical environmental temperature; the temperature deviation allowable value is obtained by performing an adaptive interval optimization algorithm on the photovoltaic output power and the historical environmental temperature; the environmental data evaluation value is obtained by comprehensively analyzing the current light intensity, maximum light intensity, current battery remaining capacity, battery maximum capacity, environmental temperature, optimal environmental temperature, and temperature deviation allowable value; and the specific analysis method of the environmental data evaluation value is: multiplying the ratio of the current light intensity to the historical maximum light intensity by the ratio of the current battery remaining capacity to the battery maximum capacity to obtain an energy-light fusion term, calculating the absolute deviation value of the current environmental temperature and the optimal environmental temperature, using the ratio of the absolute deviation value to the temperature deviation allowable value to obtain a temperature correction value, multiplying the energy-light fusion term and the temperature correction value to obtain the environmental data evaluation value.

[0012] Further, the specific process of self-adaptive adjusting the lighting output, energy distribution and charging management according to the evaluation result of the inhibition type harmonic product is: comparing the environment data with the first evaluation threshold, the second evaluation threshold and the environment data evaluation value in real time: when the environment data evaluation value is greater than or equal to the first evaluation threshold of the environment data, all lighting units are output, the charging rate is increased to supplement the battery unit with energy, all auxiliary loads are turned on, the current environment parameters and device performance are recorded, and the battery health is checked regularly; when the environment data evaluation value is less than the first evaluation threshold of the environment data and greater than or equal to the second evaluation threshold of the environment data, only the main road and key area lighting is performed, the edge area lighting brightness is reduced, the current charging rate is maintained, the non-core load is reduced in frequency, and the battery discharge depth is reduced; when the environment data evaluation value is less than the second evaluation threshold of the environment data, only the necessary area is illuminated, the illumination brightness is reduced, the charging rate is reduced, all unnecessary loads are turned off, and the battery low power and extreme environment warning are pushed.

[0013] Further, the specific process for feature interaction fusion analysis of target perception data is: obtaining target real-time speed, target real-time size value, target real-time reflection intensity, target continuous real-time speed, target relative distance, azimuth angle and sensor absolute coordinates; performing a speed difference algorithm on the target continuous real-time speed to obtain a target real-time acceleration; performing a residual normalization algorithm on the target spatial coordinate data to obtain a motion trajectory linearity value; comprehensively analyzing the target real-time speed, the target real-time size value, the target real-time reflection intensity, the target real-time acceleration and the motion trajectory linearity value to obtain a target recognition fusion value; the specific analysis method of the target recognition fusion value is: performing an exponential operation on the absolute value of the target real-time speed with the motion trajectory linearity value as the index to obtain a speed trajectory dynamic feature item; performing an exponential operation on the absolute value of the target real-time size value with the target real-time acceleration as the index to obtain a size acceleration structure feature item; performing an exponential operation on the target real-time reflection intensity with a natural constant as the base to obtain a reflection intensity enhancement item; multiplying the speed trajectory dynamic feature item, the size acceleration structure feature item and the reflection intensity enhancement item to obtain a feature fusion numerator item of the target recognition fusion value formula, multiplying the target real-time acceleration and the motion trajectory linearity value and taking the absolute value, and adding one to obtain a dynamic normalization denominator item, and dividing the feature fusion numerator item by the dynamic normalization denominator item to obtain the target recognition fusion value.

[0014] Further, the specific process of residual normalization algorithm on target space coordinate data to obtain motion trajectory linear value is: obtaining target relative distance, azimuth angle and sensor absolute coordinate data, combining target relative distance and azimuth angle data with known absolute coordinate data, using Cartesian coordinate transformation algorithm to convert distance and azimuth angle information in polar coordinates into space coordinates in Cartesian coordinate system, so as to calculate the spatial position of the target in the global coordinate system; at the same time, when observing the same target, further using multi-point positioning and data fusion algorithm to improve the accuracy of space coordinate calculation, and the output target space coordinate data is the absolute position of the target in the current scene global coordinate system, which is used to calculate the motion trajectory linear value.

[0015] Further, the specific process of dynamically identifying target type according to feature interaction fusion analysis result and pushing the discrimination result in real time into the intelligent lighting range and brightness control module is: comparing the target recognition fusion threshold and the target recognition fusion value in real time: when the target recognition fusion value is greater than or equal to the target recognition fusion threshold, it is determined that the current is a key target, and the discrimination result is pushed to the intelligent lighting range and brightness control module; when the target recognition fusion value is less than the target recognition fusion threshold, it is determined as other small targets and abnormal state, ignoring the lighting adjustment, keeping the current lighting state unchanged.

[0016] Further, the specific process of using state enhancement fusion analysis on environmental energy data and target perception data is: obtaining environmental data evaluation value, target recognition fusion value, historical battery power data, battery remaining energy ratio, video monitoring image data; obtaining environmental visibility by computer vision and intelligent perception algorithm on video monitoring image data; obtaining comprehensive lighting response value by comprehensive analysis of environmental data evaluation value, target recognition fusion value, environmental visibility, battery remaining energy ratio and battery remaining energy amplification factor; the specific analysis method of the comprehensive lighting response value is: square root of the sum of the environmental data evaluation value and the target recognition fusion value plus one, then multiplied by the environmental data evaluation value, forming an enhanced fusion term, calculating the absolute value of the difference between the environmental visibility and one, forming a visibility adjustment term, dividing the enhanced fusion term by the visibility adjustment term, then multiplying by the product of one plus the battery remaining energy amplification factor and the battery remaining energy ratio, to obtain the comprehensive lighting response value.

[0017] Further, the specific process of dynamically optimizing the lighting space distribution, brightness output and duration strategy according to the state enhancement fusion analysis result is: through the response value mapping algorithm and the linkage control technology, the comprehensive lighting response value is converted into the regulation and control instructions of the lighting range, brightness output, duration and battery energy: lighting range intelligent adjustment: based on the regulation and control instructions of the lighting range, the lighting area is adjusted in real time; when the comprehensive lighting response value increases, the lighting range is actively expanded, and the surrounding coverage area is increased; when the comprehensive lighting response value decreases, the lighting range is shortened, and only the target area and its direct access are covered; brightness output dynamic adjustment: based on the regulation and control instructions of the brightness output, the street lamp brightness is dynamically adjusted in real time; when the comprehensive lighting response value increases, the lighting brightness is increased, and when the comprehensive lighting response value decreases, the lighting brightness is decreased, and only the basic safety lighting is maintained; duration control: based on the regulation and control instructions of the duration, the lighting duration is controlled in real time; when the comprehensive lighting response value increases, the duration of the lighting is prolonged; when the comprehensive lighting response value decreases, the lighting duration is shortened; battery energy distribution: based on the regulation and control instructions of the battery energy, the battery output power is distributed in real time; when the comprehensive lighting response value increases, the power output is increased; when the comprehensive lighting response value decreases, the battery output power is simultaneously reduced.

[0018] Advantages The present application has the following advantages: (1) The present application can continuously and stably collect environmental energy data and target perception data in extreme climates such as highlands and variable environmental conditions, effectively improve data quality and consistency through real-time synchronization, noise suppression, scale unification and feature fusion processing of multi-source heterogeneous data, and provide reliable data support for subsequent lighting response analysis and intelligent control decision-making.

[0019] (2) The present application can jointly map multi-source environmental and target feature results into a comprehensive lighting response value, realize dynamic linkage and optimal control of multiple parameters such as lighting space distribution, brightness output, duration and energy distribution, and intelligently adjust each lighting behavior according to the comprehensive state to accurately adapt to actual field requirements.

[0020] (3) The present application has the intelligent lighting area dynamic optimization capability based on the target space coordinates and the spatial relationship of the street lamp network, adjusts the range and boundary of the lighting area in real time according to the target position, motion trajectory and road network structure, realizes accurate expansion and convergence of lighting coverage, and effectively reduces invalid lighting and energy waste.

[0021] (4) The present application intelligently allocates the battery energy output power according to the real-time comprehensive lighting response value, dynamically increases or decreases the output level according to the field requirements, meets the large-range high-brightness lighting requirements, ensures the convergence of the output in energy shortage or low demand, and improves the endurance and overall energy efficiency.

[0022] Of course, implementing any of the products of the application does not necessarily require that all of the advantages described above be achieved simultaneously. BRIEF DESCRIPTION OF DRAWINGS

[0023] Fig. 1 A structural diagram of a highland LED integrated lighting system based on micro-light photovoltaic driving according to the present application; Fig. 2 Q, F, and V of the present application e Multi-source parameter and S comprehensive lighting response value three-dimensional bubble chart. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0025] Please refer to Figs. 1-2 The embodiments of the present application provide a technical solution: a highland LED integrated lighting system based on micro-light photovoltaic driving, comprising a data acquisition and preprocessing module, which is used to acquire environmental energy data and target perception data, and preprocess the environmental energy data and the target perception data; an intelligent environment perception and energy-saving scheduling module, which is used to perform inhibitory harmonic product evaluation on the environmental energy data, and perform adaptive adjustment of lighting output, energy distribution, and charging management according to the inhibitory harmonic product evaluation result; a target type discrimination and service shunting module, which is used to perform feature interaction fusion analysis on the target perception data, dynamically identify the target type according to the feature interaction fusion analysis result, and push the result to the intelligent lighting range and brightness control module in real time to determine whether to enter the intelligent lighting range; and the intelligent lighting range and brightness control module, which is used to perform state enhancement fusion analysis on the environmental energy data and the target perception data, and perform dynamic optimization of lighting space distribution, brightness output, and continuous strategy according to the state enhancement fusion analysis result.

[0026] Specifically, the specific process of collecting environmental energy data and target perception data is: real-time collection of environmental energy data and target perception data to provide data support for intelligent lighting scheduling and energy efficiency optimization. The environmental energy data includes: current light intensity and maximum light intensity, reflecting the change of environmental illumination; current battery remaining power, historical battery power data and battery remaining energy ratio, reflecting the energy state in real time; environmental temperature, historical environmental temperature and photovoltaic output power, providing the basis for energy management and adaptive adjustment. The target perception data is mainly collected by deploying advanced sensing devices such as high-sensitivity radar microwave sensors, including: target real-time speed, target real-time size value, target real-time reflection intensity, target continuous real-time speed, fully depicting the dynamic characteristics of the target; target relative distance and azimuth angle are directly obtained by radar microwave sensor with high precision, and sensor absolute coordinates are used as positioning reference to provide data basis for spatial positioning and subsequent lighting range adjustment; video monitoring image data is collected by camera in real time, which enhances the multi-modal perception ability of target recognition and environmental perception. The deployment of high-performance radar microwave sensors significantly improves the accuracy of target detection and the adaptability in complex environments, reflecting the innovation and advancement of the scheme in the field of intelligent sensing.

[0027] In the embodiment, the real-time collection of environmental energy data and target perception data can continuously perceive the on-site light, energy reserve, temperature change, target motion and space state, and fuse video image information to realize comprehensive dynamic perception of the on-site environment and target. Based on these high-quality, multi-dimensional data support, the lighting range, brightness, time length and energy allocation can be intelligently adjusted according to the actual environment and target state, realizing adaptive optimization of lighting strategy and continuous improvement of energy efficiency management. This step ensures the accurate response and flexible regulation of lighting in complex highland environment and variable scene, significantly improves the intelligent level, environmental adaptability and energy efficiency of the overall operation, and provides a strong guarantee for stable operation and long-term reliability.

[0028] Specifically, the specific process of preprocessing the environmental energy data and the target perception data is: noise suppression of the environmental energy data by adaptive mean filtering and median filtering algorithm, effectively reducing the influence of drift, external environmental disturbance and instantaneous measurement error on the accuracy of the data during the long-term use of the sensor, ensuring that the collected light, temperature, power and other data more truly reflect the actual working conditions. The physical consistency of the target perception data is checked by the motion anomaly recognition and trajectory continuity analysis algorithm, and the broken, mutation points and data records that do not conform to the actual physical law in the target trajectory are timely eliminated to prevent abnormal data from affecting target recognition, classification and subsequent lighting strategy optimization. The target perception data is suppressed by Kalman filtering and multi-level time series smoothing algorithm, effectively filtering the random fluctuations caused by sensor noise, sampling error and environmental interference during the motion process, significantly improving the collection accuracy and continuity of the target motion characteristics, and more accurately reflecting the real motion state of the target. The scale of the environmental energy data and the target perception data is unified and the interval is mapped by the distribution standardization and linear normalization algorithm, which converts data of different dimensions and different distributions to a standard interval, effectively solving the scale inconsistency problem between multi-source data.

[0029] In the embodiment, the data processing step effectively improves the quality and reliability of the collected data, so that various environmental energy data and target perception data can more truly, stably and continuously reflect the actual working conditions and target dynamics. Through noise suppression, abnormality elimination and scale unification, the influence of environmental interference and measurement error on the accuracy of the data is reduced, providing a solid data foundation for the subsequent intelligent optimization of lighting range, brightness, duration and energy allocation. This step effectively improves the accuracy and flexibility of lighting scheduling, which helps to achieve high-level intelligent management and operational reliability in complex environmental and dynamic target scenarios.

[0030] Specifically, the specific process of suppressing the environmental energy data is: The current light intensity, the maximum light intensity, the current battery remaining capacity, the historical battery capacity data, the environment temperature, the photovoltaic output power and the historical environment temperature are acquired to provide a comprehensive information base for subsequent data analysis and state evaluation; the battery maximum capacity is obtained by statistical analysis and abnormal value elimination algorithm on the historical battery capacity data, which can effectively filter out abnormal fluctuations and invalid data, and improve the evaluation accuracy of the battery maximum capacity; the optimal environment temperature is obtained by fitting the energy efficiency temperature curve algorithm on the photovoltaic output power and the historical environment temperature, which scientifically extracts the optimal operating point of the photovoltaic module at different temperatures, and determines the optimal environment temperature as an important reference for energy efficiency regulation; the adaptive interval optimization algorithm is used on the photovoltaic output power and the historical environment temperature to reasonably define the effective interval of the influence of temperature fluctuation on the performance of photovoltaic and battery, so as to obtain the temperature deviation allowable value; the environment data evaluation value is obtained by comprehensive analysis of the current light intensity, the maximum light intensity, the current battery remaining capacity, the battery maximum capacity, the environment temperature, the optimal environment temperature and the temperature deviation allowable value; the specific analysis method of the environment data evaluation value is that the ratio of the current light intensity to the historical maximum light intensity is multiplied by the ratio of the current battery remaining capacity to the battery maximum capacity to obtain an energy-light fusion term, the absolute deviation value of the current environment temperature and the optimal environment temperature is calculated, the ratio of the absolute deviation value to the temperature deviation allowable value is subtracted to obtain a temperature correction value, the energy-light fusion term and the temperature correction value are multiplied and then the cubic root is taken to obtain the environment data evaluation value, which is used for dynamic evaluation of the comprehensive state of the current site environment, and provides a key basis for adaptive adjustment of lighting strategy, energy efficiency optimization and subsequent intelligent decision-making.

[0031] The specific formula of the environment data evaluation value is: ; In the formula, represents the environment data evaluation value, which evaluates the comprehensive state of the current site environment; represents the current light intensity, which reflects the instantaneous light level in the environment; represents the maximum light intensity, which is used to refer to the relative position of the current light state in the whole cycle; represents the current battery remaining capacity, which reflects the current energy reserve situation; represents the battery maximum capacity, which is an important benchmark for measuring the proportion of remaining capacity and energy efficiency evaluation; represents the environment temperature, which is used to describe the real-time temperature state of the lighting site; represents the optimal environment temperature, which is the core reference parameter for energy efficiency correction and state adjustment; represents the temperature deviation allowable value, which is used to limit the actual influence range of environment temperature fluctuation on energy efficiency.

[0032] In this embodiment, through the collection and analysis of multi-dimensional environmental energy data, comprehensive statistics, algorithm optimization and fusion calculation, the accuracy and comprehensiveness of the on-site environmental state perception are effectively improved. The environmental data evaluation value, as the core index dynamically reflecting the comprehensive state of the current lighting scene, can sensitively respond to the changes of key parameters such as illumination, energy and temperature. With the help of scientific data elimination, fitting and optimization algorithm, the evaluation result is more real and stable, effectively avoiding the interference of abnormal fluctuations and extreme cases on the subsequent strategy judgment. The environmental data evaluation value provides a solid quantitative basis for the adaptive adjustment of lighting strategy, energy efficiency management and intelligent decision-making, significantly improves the intelligent level and energy efficiency optimization ability of lighting management, and ensures efficient and accurate operation in a changing environment.

[0033] Specifically, the specific process of adaptive adjustment of lighting output, energy distribution and charging management according to the suppression type harmonic product evaluation result is as follows: Real-time comparison of environmental data first-level evaluation threshold, environmental data second-level evaluation threshold and environmental data evaluation value: When the environmental data evaluation value is greater than or equal to the environmental data first-level evaluation threshold, all lighting units output lighting capacity synchronously, realizing high-brightness coverage of the whole area, improving the charging rate through intelligent energy scheduling strategy, continuously supplementing the energy of the battery unit, and ensuring that the overall performance of the lighting system is fully played out when the energy is sufficient and the environment is good. Turn on all auxiliary loads, including remote communication, data acquisition and environmental monitoring, etc. additional functions, enhance the comprehensive service ability. Record the current environmental parameters and equipment performance indicators to provide detailed historical data for subsequent state tracking and maintenance management. When the environmental data evaluation value is lower than the first-level evaluation threshold but higher than or equal to the second-level evaluation threshold, the lighting scheduling strategy is changed to focus on guaranteeing the lighting demand of main roads and core areas, ensuring that the key area illumination intensity meets the standard; for the edge area, the lighting brightness is intelligently lowered to realize zoned and graded energy consumption control. Maintain the current charging rate to maintain the battery endurance and prevent overcharging risk. For non-core loads, reduce energy consumption by reducing frequency or limiting power consumption, further reduce battery discharge depth, improve energy utilization efficiency, and ensure that the lighting function can still run continuously when energy resources are limited. When the environmental data evaluation value is less than the environmental data second-level evaluation threshold, the lighting only covers the necessary area to guarantee the basic safety lighting, and the lighting brightness is reduced to reduce the energy consumption, and the charging rate is also lowered to prioritize battery safety and remaining energy preservation. All unnecessary loads will be turned off to minimize energy consumption. Actively push the battery low power and extreme environment alarm information, remind the maintenance personnel to take maintenance measures in time through the intelligent alarm mechanism, prevent interruption and safety risks caused by abnormal conditions.

[0034] In this embodiment, the implementation of the hierarchical regulation strategy ensures that the lighting unit can dynamically adjust the output state and energy allocation according to the environmental data evaluation value, realizes full global highlight coverage and maximum function when the energy is sufficient and the environment is good, fully meets various lighting and auxiliary needs. When the energy or environmental conditions decrease, the main roads and key areas are intelligently prioritized, the brightness of the edge area and the power consumption of the non-core load are flexibly adjusted, the energy utilization efficiency is optimized, and the service life of the battery is effectively prolonged. In extreme cases, by converging the lighting range, reducing the charging rate and turning off all unnecessary loads, the energy consumption is minimized, while timely issuing a low battery and extreme environment warning, significantly improving the safety and early warning capability of the equipment. Overall, the hierarchical regulation measures significantly improve the intelligent level, resilience and energy efficiency management capability of lighting management, ensuring that the lighting system always operates efficiently, reliably and sustainably in complex environments such as highlands.

[0035] Specifically, the specific process for feature interaction fusion analysis of target perception data is: Obtain target real-time speed, target real-time size value, target real-time reflectivity, target continuous real-time speed, target relative distance, azimuth angle and sensor absolute coordinates to ensure comprehensive perception of target motion state and spatial distribution; perform speed difference algorithm on the target continuous real-time speed to obtain target real-time acceleration, which facilitates the capture of target behavior mutations or dynamic adjustments; perform residual normalization algorithm on the target spatial coordinate data to obtain motion trajectory linearity value, which measures the coherence and linearity of the target motion trajectory, and finally obtains the motion trajectory linearity value; Obtain target recognition fusion value by comprehensively analyzing target real-time speed, target real-time size value, target real-time reflectivity, target real-time acceleration and motion trajectory linearity value; the specific analysis method of the target recognition fusion value is: power operation of the absolute value of the target real-time speed with the motion trajectory linearity value as the exponent to obtain the speed trajectory dynamic feature term, which reflects the cooperative effect of target motion speed and path characteristics; power operation of the absolute value of the target real-time size value with the target real-time acceleration as the exponent to obtain the size acceleration structure feature term, which depicts the composite properties of target body shape and motion change; exponential operation of the target real-time reflectivity with a natural constant as the base to obtain the reflectivity enhancement term, which emphasizes the sensitivity improvement of the reflection characteristic; multiply the speed trajectory dynamic feature term, the size acceleration structure feature term and the reflectivity enhancement term to obtain the feature fusion numerator term of the target recognition fusion value formula, multiply the target real-time acceleration and the motion trajectory linearity value and take the absolute value, and add one as the dynamic normalization denominator term, divide the feature fusion numerator term by the dynamic normalization denominator term to obtain the target recognition fusion value, realize adaptive fusion discrimination of target multi-dimensional features, and provide a quantitative basis for subsequent accurate perception and response.

[0036] wherein the specific formula of the target recognition fusion value is: ; In the formula, represents a target recognition fusion value, which is used to comprehensively evaluate the multi-dimensional characteristics of the target, so as to realize accurate discrimination of the target type and state; represents a target real-time speed, which reflects the motion rate of the target at the current time; represents a target real-time size value, which describes the spatial scale of the target in the observation direction, and provides a basis for body type classification and anomaly detection; represents a target real-time reflection intensity, which embodies the echo characteristics of the target to the microwave signal or laser; represents a target real-time acceleration, which describes the instantaneous change trend of the target speed, and can assist in judging the behavior pattern and dynamic stability of the target; represents a motion trajectory linearity value, which is used to measure the straightness and continuity of the target motion path.

[0037] In the embodiment, the fine level and discrimination robustness of the target recognition process are improved, so that the lighting scene can continuously maintain a high recognition rate and a low misjudgment rate when facing various motion modes, complex body types and targets of different materials. Through the dynamic application of the target recognition fusion value, abnormal behavior, abnormal motion trajectory and emergencies can be accurately recognized and tracked, key targets in the case of multi-target interaction and occlusion can be effectively distinguished, and preferential response and differentiated lighting strategies for key targets are realized. The analysis results directly support intelligent dynamic adjustment of the lighting area, brightness and time length, make the lighting resources more efficient, and enhance the overall adaptive ability and operation safety in complex environments such as highlands and dynamic scenes.

[0038] Specifically, the specific process of obtaining the motion trajectory linearity value by residual normalization algorithm on the target spatial coordinate data is as follows: The target relative distance, azimuth and sensor absolute coordinate data are obtained, which lays a foundation for subsequent spatial positioning and trajectory analysis. The target relative distance and azimuth data are combined with the known sensor absolute coordinates, and the distance and azimuth information in polar coordinates are accurately converted into spatial coordinates in the Cartesian coordinate system through the Cartesian coordinate transformation algorithm, so as to realize accurate calculation of the target spatial position in the global coordinate system. This method can effectively eliminate the spatial ambiguity caused by single measurement angle, and improve the consistency and accuracy of spatial positioning. When multiple sensors observe the same target at the same time, a multi-point positioning and data fusion algorithm can be further used to fully integrate information from different directions and distances, and the least square method and multi-lateral measurement means are used for collaborative calibration, so as to further improve the accuracy of target spatial coordinate calculation. The output target spatial coordinate data is the absolute spatial position of the target in the global coordinate system of the current scene, which provides key data support for accurate calculation of the motion trajectory linearity value and target behavior analysis and intelligent lighting linkage decision.

[0039] In this embodiment, this step significantly improves the spatial resolution of target positioning and scene restoration, so that the target can be accurately mapped to the global coordinate system regardless of the change of the moving path in the complex environment, and the intuitive control of the target distribution and regional relationship is realized. The acquisition of high-precision spatial coordinates helps to dynamically adjust the lighting distribution, accurately distinguish the target density in the region and the key activity area, so as to optimize the lighting coverage strategy, improve the utilization rate of lighting resources, and lay a technical foundation for multi-target linkage and scene partition management.

[0040] Specifically, according to the feature interaction fusion analysis result, the target type is dynamically identified and the discrimination result is pushed in real time, and the specific process of entering the intelligent lighting range and brightness control module is as follows: The target recognition fusion value is compared with the target recognition fusion threshold in real time, and the dynamic screening and judgment of the importance of the target are realized. When the target recognition fusion value is greater than or equal to the target recognition fusion threshold, it is judged that the current target is a key target, which has a higher response priority, and the discrimination result is immediately pushed to the intelligent lighting range and brightness control module to drive the lighting system to actively expand the coverage range, improve the brightness or prolong the lighting time, and ensure the safety and visibility of the key target area. When the target recognition fusion value is lower than the target recognition fusion threshold, the target is determined to be a general small target or an abnormal state, and the lighting strategy adjustment is not triggered, and the current lighting level is maintained, which avoids the waste of resources on non-key targets, improves the refinement of the lighting strategy and the energy efficiency, and ensures that the resources are focused on the targets and areas that really need them.

[0041] In this embodiment, the fine identification and hierarchical response of various target states are realized, which significantly improves the pertinence of lighting resource allocation and the overall perception decision-making ability. The immediate identification and priority pushing of key targets effectively guarantee the lighting needs of key areas and key targets, and enhance the regional safety and scene adaptive ability. For general small targets and abnormal states, the lighting adjustment is ignored by judgment, which ensures that the lighting energy is always focused on the most valuable targets and areas, reduces unnecessary energy consumption and interference, helps to prolong the battery life and optimize the overall operating cost. This process strengthens the intelligent level and dynamic response ability of lighting control, and provides a technical foundation for efficient, accurate and sustainable lighting management in complex environments.

[0042] Specifically, the specific process for state-enhanced fusion analysis of environmental energy data and target perception data is as follows: The environment data evaluation value, the target recognition fusion value, the historical battery power data, the battery residual energy ratio and the video monitoring image data are acquired to provide a multi-source heterogeneous information basis for subsequent comprehensive lighting response decision-making; the video monitoring image data is subjected to computer vision and intelligent perception algorithm, obstacles, weather and illumination changes and other factors in the scene are dynamically identified, the environmental visibility parameter is obtained in real time, and the perception ability for complex environmental changes is further improved; The comprehensive lighting response value is obtained by comprehensively analyzing the environment data evaluation value, the target recognition fusion value, the environmental visibility, the battery residual energy ratio and the battery residual energy amplification factor; the specific analysis method of the comprehensive lighting response value is: square root of the sum of the environment data evaluation value and the target recognition fusion value, then multiplied by the environment data evaluation value to form an enhanced fusion term, highlighting the coupling effect of environment and target, calculating the absolute value of the difference between the environmental visibility and one to form a visibility adjustment term to realize adaptive correction of the lighting response intensity in different scenes, dividing the enhanced fusion term by the visibility adjustment term, then multiplying by the product of one plus the battery residual energy amplification factor and the battery residual energy ratio to obtain the comprehensive lighting response value.

[0043] The calculation formula of the comprehensive lighting response value is: ; In the formula, represents the comprehensive lighting response value, measuring the current lighting demand and energy efficiency allocation state; represents the environment data evaluation value, comprehensively reflecting the overall state of multi-dimensional environmental factors such as field illumination, energy and temperature, providing environmental basis for lighting scheduling; represents the target recognition fusion value, quantifying the importance and dynamic characteristics of the target; represents the environmental visibility, embodying the visual accessibility in the current scene, having a direct impact on the dynamic regulation of lighting intensity and range; represents the battery residual energy ratio, reflecting the current battery state and energy reserve; represents the battery residual energy amplification factor, collecting the historical battery power data of the battery management unit, dynamically determining the battery residual energy amplification factor through adaptive optimization algorithm, and used for gain adjustment of the influence of the battery residual energy.

[0044] The change trend of the comprehensive lighting response value under different environment data evaluation values, target recognition fusion values and environmental visibility value conditions is compared and analyzed, the battery residual energy ratio and the battery residual energy amplification factor are fixed, and the Q, F and V eTypical representative values ​​were selected for combined sampling, and the integrated lighting response values ​​under different scenarios were calculated and summarized. This intuitively demonstrates the actual impact of environmental conditions, target characteristics, and visibility on the integrated lighting response mechanism, providing a quantitative analysis basis for multi-source data-driven adaptive lighting control and energy efficiency optimization, as shown in Table 1 (Q, F, V). e The mapping table between multi-source parameters and integrated lighting response values ​​is shown.

[0045] Table 1 Q, F, V e Multi-source parameter mapping table to integrated lighting response value

[0046] like Fig. 2 As shown, Q, F, and V represent the integrated LED lighting system for plateau regions based on low-light photovoltaic driving provided in this application embodiment. e Three-dimensional bubble diagram of multi-source parameters and S-type integrated lighting response value. See Table 1 and... Fig. 2 It can be seen that when Q, F, V e When all three parameters are at a high level, the S-value also reaches a high level, enabling it to actively output maximum lighting capacity and meet the safety lighting requirements of critical scenarios and high-demand targets; while when Q, F, and V are at a high level, the S-value also reaches a high level. e When any one of the following is low, the S value decreases significantly, indicating the entry into an energy-saving operation mode with controlled energy consumption and reduced lighting. An increase in Q significantly drives an increase in S, demonstrating that a favorable environment and energy state provide a fundamental guarantee for a strong response. An increase in F reflects the priority response capability when key targets are accurately identified, but if energy or the environment is limited, the increase in S will still be suppressed. e As a denominator adjustment factor, the lower the visibility, the more obvious the suppression effect on S, reflecting the adaptive characteristics of actively reducing lighting output and avoiding ineffective energy consumption in harsh environments.

[0047] This implementation scheme significantly improves the sensitivity and accuracy of the comprehensive lighting response value to the on-site environment, target characteristics, and battery energy status through real-time acquisition and fusion calculation of multi-source heterogeneous data. It dynamically reflects the synergistic effects of multiple influencing factors such as illumination, energy, target, and visibility, enabling quantitative identification of actual lighting needs and effectively strengthening the intelligent response capability to changes in complex environments and key targets. Thanks to the dynamic extraction of visibility using computer vision and intelligent sensing algorithms, as well as the joint analysis of environment, target, and energy status, the spatial distribution, brightness intensity, and energy allocation of lighting output can achieve high-precision adaptive adjustment, greatly improving overall energy efficiency and on-site adaptability. Ultimately, this mechanism provides a solid data foundation and technical support for lighting strategy optimization, energy consumption control, and safety assurance in key areas.

[0048] Specifically, the specific process of dynamically optimizing the lighting space distribution, brightness output and duration strategy according to the state enhancement fusion analysis result is as follows: through the response value mapping algorithm and the linkage control technology, the comprehensive lighting response value is efficiently converted into multi-dimensional regulation and control instructions such as lighting range, brightness output, duration and battery energy distribution, which can flexibly adapt to changes in the field demand and realize full-process closed-loop optimization. Lighting range intelligent adjustment: based on the regulation and control instruction of the lighting range, combined with the target position and scene space distribution, the lighting area is adjusted in real time and accurately. When the comprehensive lighting response value increases, the lighting range is expanded, the surrounding coverage area is increased, and the overall visibility and safety protection capability of the site are improved; when the comprehensive lighting response value decreases, the lighting range is intelligently converged, the basic lighting of the target area and its direct access is reserved, and the invalid energy consumption is effectively reduced. Brightness output dynamic adjustment: based on the regulation and control instruction of the brightness output, according to the change trend of the comprehensive lighting response value, the brightness level of each lamp is adjusted in real time and dynamically. When the comprehensive lighting response value increases, the brightness of the lamp is increased to provide stronger lighting support for the high demand area; when the response value decreases, the brightness is lowered accordingly to maintain the basic safety lighting, realizing the dual goals of energy saving and safety protection. Duration control: based on the regulation and control instruction of the duration, combined with the target activity mode and the real-time state of the environment, the duration of each lighting is flexibly controlled. When the comprehensive lighting response value increases, the duration of the lighting is extended accordingly to meet the long-time lighting demand of the key target and high-traffic period; when the response value decreases, the lighting duration is shortened to reduce unnecessary energy consumption and equipment wear and tear, and the overall operation efficiency is improved. Battery energy distribution: based on the regulation and control instruction of the battery energy, the battery output power distribution is optimized in real time. When the comprehensive lighting response value increases, the output power is increased to prioritize the lighting demand of the key area and high brightness; when the response value decreases, the battery output power is simultaneously reduced to prioritize the energy to cope with subsequent key loads, prolong the battery endurance and ensure long-term stable operation.

[0049] In this embodiment, based on the multi-dimensional linkage regulation and control of the comprehensive lighting response value, the adaptive dynamic coordination of the lighting range, brightness output, duration and battery energy distribution and other multi-parameters is realized, so that the lighting management has high intelligentization and fine regulation and control capability in terms of space coverage, light intensity, time extension and energy utilization, the sensitivity and response rate of the lighting system to the field target and environmental state are significantly improved, and the invalid energy consumption and resource waste are effectively inhibited through real-time closed-loop optimization. The lighting resources can be dynamically allocated to the key areas and high-risk scenes according to the actual demand to ensure that the safety and visibility are always in the best state; the energy efficiency and battery endurance are greatly improved, effectively reducing the operation pressure and long-term operation cost in complex environments such as highlands, greatly enhancing the environmental adaptability, scene adaptation flexibility and operation lean level, and providing high-standard technical support for the deep integration of intelligent lighting and energy management.

[0050] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting; it is not intended to exclude myriad other embodiments of the present application that other presenters can develop. It is also possible, however, that only a single element can be present. It is further noted that such a term as "comprising" is intended to mean that the embodiments include the recited elements, but not excluding other elements. "Consisting essentially of when used herein in relation to a composition, means that the composition includes the recited elements, and can include additional elements, so long as the additional elements do not materially alter the basic and novel properties of the claimed composition. "Consisting of" when used herein in relation to a composition means that the composition includes the recited elements and nothing more.

[0051] The preferred embodiments of the application disclosed above are only to help explain the principles of the present application. The preferred embodiments do not limit the present application to only the specific embodiments described. It is apparent that many modifications and variations of this application are possible in light of this disclosure. The preferred embodiments are chosen and described in order to best explain the principles of the application and the practical application, to thereby enable others skilled in the art to best utilize the application. The present application is limited only by the claims and their full scope and equivalents.

Claims

1. A high-altitude integrated LED lighting system based on low-light photovoltaic drive, characterized in that, include: The data acquisition and preprocessing module is used to acquire environmental energy data and target perception data, and to preprocess the environmental energy data and target perception data. The intelligent environmental sensing and energy-saving scheduling module is used to perform suppression harmonic product evaluation on environmental energy data, and adaptively adjust lighting output, energy distribution and charging management based on the suppression harmonic product evaluation results; The target type identification and business diversion module is used to perform feature interaction fusion analysis on target perception data, dynamically identify the target type based on the feature interaction fusion analysis results and push the determination of whether it enters the smart lighting range and brightness control module in real time. The intelligent lighting range and brightness control module is used to perform state-enhanced fusion analysis on environmental energy data and target perception data, and to dynamically optimize the spatial distribution of lighting, brightness output and continuous strategies based on the results of the state-enhanced fusion analysis.

2. The integrated LED lighting system for plateau regions based on low-light photovoltaic driving according to claim 1, characterized in that: The specific process for collecting environmental energy data and target perception data is as follows: Real-time acquisition of environmental energy data and target perception data: Environmental energy data includes: current light intensity, maximum light intensity, current remaining battery power, historical battery power data, remaining battery energy percentage, ambient temperature, photovoltaic output power, and historical ambient temperature. Target perception data includes: target real-time velocity, target real-time size, target real-time reflection intensity, target continuous real-time velocity, target relative distance, azimuth angle and sensor absolute coordinates, and video surveillance image data.

3. The integrated LED lighting system for plateau regions based on low-light photovoltaic driving according to claim 1, characterized in that: The specific process for preprocessing environmental energy data and target perception data is as follows: Noise suppression is achieved through adaptive mean filtering and median filtering algorithms for environmental energy data, reducing instantaneous fluctuations caused by sensor drift, environmental disturbances, and measurement errors. Physical consistency verification of target perception data is performed using motion anomaly identification and trajectory continuity analysis algorithms, eliminating data records with broken motion trajectories, abrupt changes, and inconsistencies with actual physical laws. Noise suppression of target perception data is further enhanced through Kalman filtering and multi-level temporal smoothing algorithms, improving the accuracy and stability of motion feature acquisition. Finally, scale unification and interval mapping are performed on environmental energy data and target perception data using distribution standardization and linear normalization algorithms, achieving standardization and normalization.

4. The integrated LED lighting system for plateau regions based on low-light photovoltaic driving according to claim 1, characterized in that: The specific process for evaluating the suppressed harmonic product of environmental energy data is as follows: The algorithm acquires current light intensity, maximum light intensity, current remaining battery power, historical battery power data, ambient temperature, photovoltaic output power, and historical ambient temperature. It then uses statistical analysis and outlier removal algorithms on the historical battery power data to obtain the maximum battery power. Finally, it uses an energy efficiency temperature curve fitting algorithm to combine the photovoltaic output power and historical ambient temperature to obtain the optimal ambient temperature. Finally, it uses an adaptive interval optimization algorithm to combine the photovoltaic output power and historical ambient temperature to obtain the allowable temperature deviation. An environmental data assessment value is obtained through comprehensive analysis of current light intensity, maximum light intensity, current remaining battery power, maximum battery power, ambient temperature, optimal ambient temperature, and allowable temperature deviation. The specific analysis method for this environmental data assessment value is as follows: Multiply the ratio of the current light intensity to the historical maximum light intensity by the ratio of the current remaining battery power to the maximum battery power to obtain the energy-light fusion term. Calculate the absolute deviation of the current ambient temperature from the optimal ambient temperature. Subtract the ratio of the absolute deviation to the allowable temperature deviation to obtain the temperature correction value. Multiply the energy-light fusion term and the temperature correction value and take the cube root to obtain the environmental data assessment value.

5. The integrated LED lighting system for plateau regions based on low-light photovoltaic driving according to claim 1, characterized in that: The specific process of adaptively adjusting lighting output, energy distribution, and charging management based on the evaluation results of the suppression-type harmonic product is as follows: Real-time comparison of primary environmental data assessment thresholds, secondary environmental data assessment thresholds, and environmental data assessment values: When the environmental data assessment value is greater than or equal to the first-level environmental data assessment threshold, all lighting units output, the charging rate is increased to replenish the battery unit, all auxiliary loads are turned on, the current environmental parameters and equipment performance are recorded, and battery health checks are performed regularly. When the environmental data assessment value is less than the first-level environmental data assessment threshold and greater than or equal to the second-level environmental data assessment threshold, only the lighting of main roads and key areas will be reduced, while the lighting brightness of edge areas will be reduced, the current charging rate will be maintained, non-core loads will be reduced, and the depth of battery discharge will be decreased. When the environmental data assessment value is less than the secondary environmental data assessment threshold, only necessary areas will be illuminated, and the lighting brightness will be reduced, the charging rate will be lowered, all unnecessary loads will be turned off, and low battery and extreme environment alarms will be pushed.

6. The integrated LED lighting system for plateau regions based on low-light photovoltaic driving according to claim 1, characterized in that: The specific process for performing feature interaction fusion analysis on target perception data is as follows: Acquire the target's real-time velocity, real-time size, real-time reflection intensity, continuous real-time velocity, relative distance, azimuth, and sensor absolute coordinates; perform a velocity difference algorithm on the continuous real-time velocity to obtain the target's real-time acceleration; The linear values ​​of the motion trajectory are obtained by performing a residual normalization algorithm on the target spatial coordinate data; The target recognition fusion value is obtained by comprehensively analyzing the target's real-time velocity, real-time size, real-time reflection intensity, real-time acceleration, and linearity of motion trajectory. The specific analysis method for the target recognition fusion value is as follows: the absolute value of the target's real-time velocity is raised to the power of the linear value of the motion trajectory to obtain the velocity trajectory dynamic feature term; the absolute value of the target's real-time size is raised to the power of the target's real-time acceleration to obtain the size acceleration structural feature term. Using the natural constant as the base, the real-time reflection intensity of the target is exponentially calculated to obtain the reflection intensity enhancement term. The dynamic feature term of velocity trajectory, the structural feature term of size acceleration, and the reflection intensity enhancement term are multiplied together to obtain the feature fusion numerator term of the target recognition fusion value formula. The real-time acceleration of the target is multiplied by the linear value of the motion trajectory and the absolute value is taken, and then added to one to obtain the dynamic normalized denominator term. The feature fusion numerator term is divided by the dynamic normalized denominator term to obtain the target recognition fusion value.

7. The integrated LED lighting system for plateau regions based on low-light photovoltaic driving according to claim 6, characterized in that: The specific process of obtaining the linear value of the motion trajectory by performing a residual normalization algorithm on the target spatial coordinate data is as follows: The system acquires the target's relative distance, azimuth, and sensor absolute coordinate data. It then combines this data with the known absolute coordinates and employs a Cartesian coordinate transformation algorithm to convert the polar coordinates into Cartesian spatial coordinates, thereby calculating the target's spatial position in the global coordinate system. Simultaneously, when the same target is observed, a multi-point positioning and data fusion algorithm is used to improve the accuracy of the spatial coordinate calculation. The output target spatial coordinate data represents the target's absolute position in the current scene's global coordinate system, used to calculate the linear value of its motion trajectory.

8. The integrated LED lighting system for plateau regions based on low-light photovoltaic driving according to claim 1, characterized in that: The specific process of dynamically identifying the target type based on the feature interaction fusion analysis results and pushing the discrimination results in real time, and then entering the intelligent lighting range and brightness control module, is as follows: Real-time comparison of target recognition fusion threshold and target recognition fusion value: When the target recognition fusion value is greater than or equal to the target recognition fusion threshold, the target is determined to be a key target, and the determination result is pushed to the intelligent lighting range and brightness control module. When the target recognition fusion value is less than the target recognition fusion threshold, it is judged as other small targets and abnormal state, the lighting adjustment is ignored, and the current lighting state remains unchanged.

9. The integrated LED lighting system for plateau regions based on low-light photovoltaic driving according to claim 1, characterized in that: The specific process for performing state-enhanced fusion analysis on environmental energy data and target perception data is as follows: Acquire environmental data assessment values, target recognition fusion values, historical battery power data, battery remaining energy percentage, and video surveillance image data; apply computer vision and intelligent perception algorithms to the video surveillance image data to obtain environmental visibility. The comprehensive lighting response value is obtained by comprehensively analyzing the environmental data assessment value, target identification fusion value, environmental visibility, battery remaining energy ratio, and battery remaining energy amplification factor. The specific analysis method of the comprehensive lighting response value is as follows: add one to the environmental data assessment value and the target identification fusion value, take the square root, and then multiply it with the environmental data assessment value to form an enhanced fusion term. Calculate the absolute value of the difference between one and the environmental visibility to form a visibility adjustment term. Divide the enhanced fusion term by the visibility adjustment term, and then multiply it by one plus the product of the battery remaining energy amplification factor and the battery remaining energy ratio to obtain the comprehensive lighting response value.

10. A plateau-area integrated LED lighting system based on low-light photovoltaic drive according to claim 1, characterized in that: The specific process of dynamically optimizing the lighting spatial distribution, brightness output, and persistence strategy based on the state-enhanced fusion analysis results is as follows: The integrated lighting response value is converted into control commands for lighting range, brightness output, duration, and battery energy through response value mapping algorithms and linkage control technology. Intelligent adjustment of lighting range: Based on the control command of the lighting range, the lighting area is adjusted in real time; when the overall lighting response value increases, the lighting range is actively expanded to increase the surrounding coverage area; When the overall lighting response value decreases, the abbreviated lighting range only covers the target area and its direct path; Dynamic brightness output adjustment: Based on the brightness output control command, the street light brightness is dynamically adjusted in real time; When the overall lighting response value increases, the lighting brightness is increased; when the overall lighting response value decreases, the lighting brightness is decreased, maintaining only basic safety lighting. Duration control: Real-time control of lighting duration based on duration control commands; When the overall lighting response value increases, the duration of continuous lighting is extended; When the overall lighting response value decreases, the lighting duration should be shortened. Battery energy distribution: Based on the battery energy control commands, the battery output power is distributed in real time; When the overall lighting response value increases, the power output is increased; When the overall lighting response value decreases, the battery output power is reduced simultaneously.

Images