A method for adaptively adjusting the illumination intensity of solar street lights

Abstract

The invention discloses a method for adaptively adjusting the illumination intensity of a solar street lamp, and specifically relates to the technical field of solar street lamps. A discharge depth nonlinear index is calculated according to nonlinear characteristics of a discharge rate drop coefficient, an internal resistance increment coefficient, and a temperature distribution difference coefficient, so as to timely capture the nonlinear characteristics of a battery voltage fluctuation as the discharge depth increases, evaluate the battery power status and the degree of nonlinear discharge fluctuation of the battery, and simultaneously calculate a solar street lamp hidden danger assessment index according to a light source attenuation coefficient, a metal corrosion coefficient, and an insulation layer damage coefficient, so as to timely identify the potential failure risk of the street lamp after long-term use, and appropriately adjust the brightness according to the degree of hidden danger, so as to ensure the safe and stable operation of the street lamp system. When the battery is in a low power state, the brightness curve is corrected according to the discharge depth nonlinear index and the solar street lamp hidden danger assessment index, so that the system can adapt to the complex characteristics of battery discharge and the aging effect of the street lamp.

Description

Technical Field

[0001] The present invention relates to the technical field of solar street lamps, and more specifically, to a method for adaptively adjusting the illumination intensity of solar street lamps. Background Art

[0002] As a green and environmentally friendly lighting solution, solar street lights are widely used in urban streets, parks, roads and other places. They mainly rely on solar panels to convert daytime sunlight into electrical energy, which is stored in batteries for use at night. The discharge process of the battery is a nonlinear process. Especially when the battery power is low, the battery voltage drops faster, making the relationship between the battery power and the actual power provided more complicated. Specifically, as the depth of battery discharge increases, the terminal voltage of the battery will drop rapidly, resulting in an increase in the fluctuation of the battery voltage. This fluctuation not only affects the discharge efficiency of the battery, but also increases the fluctuation of the street light illumination intensity, making it impossible to effectively guarantee the stability of street light illumination. In addition, as the battery capacity is gradually exhausted, the self-discharge rate of the battery increases, and the internal resistance increases, further exacerbating the voltage fluctuation and the instability of power output. Therefore, in the low power state, the traditional linear model-based control algorithm cannot effectively cope with these nonlinear changes, resulting in large errors in the system during the adjustment process, which in turn affects the lighting quality of the street light. At the same time, the solar street light itself is also affected by the service life and operating status. Especially after long-term use, the light source attenuation, metal corrosion, insulation layer damage and other problems of the street light will affect its normal operation. When the light intensity of street lamps is affected by both battery discharge characteristics and aging effects, simple linear adjustment methods are difficult to balance system stability and energy saving, often resulting in failure of the adjustment strategy. Therefore, there is an urgent need for a more intelligent and adaptive adjustment method that can comprehensively consider battery discharge characteristics, load requirements, and street lamp operating status to achieve precise adjustment of solar street lamp light intensity. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method for adaptively adjusting the illumination intensity of a solar street lamp to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A method for adaptively adjusting the illumination intensity of a solar street light comprises the following steps:

[0006] Step S1, real-time monitoring of the remaining power of the battery. When the battery is in a low power state, the discharge voltage, battery temperature and internal resistance change data of the battery are collected according to a high-precision sensor, and the collected data are pre-processed to extract the nonlinear characteristics of the discharge depth of the battery;

[0007] Step S2, constructing a nonlinear prediction model of the depth of discharge according to the nonlinear characteristics of the depth of discharge of the battery, outputting a nonlinear index of the depth of discharge, and evaluating the degree of nonlinear discharge fluctuation caused by the increase of the depth of discharge when the battery is in a low power state;

[0008] Step S3, obtaining the light source attenuation information, metal corrosion information and insulation layer damage information of the solar street lamp, and constructing a solar street lamp hidden danger assessment model according to the light source attenuation information, metal corrosion information and insulation layer damage information, outputting a solar street lamp hidden danger assessment index, and assessing the degree of potential hidden dangers in the operation state of the solar street lamp as the use time increases;

[0009] Step S4, judging whether the solar street light needs to be turned on according to the real-time light intensity data provided by the ambient light sensor, and if turned on, adjusting the brightness of the light source according to a preset brightness curve;

[0010] Step S5, when the solar street light needs to be turned on and the battery is in a low power state, the preset brightness curve is corrected according to the nonlinear discharge fluctuation degree of the battery in the low power state and the potential hidden danger degree of the solar street light operation state.

[0011] In a preferred embodiment, the nonlinear characteristics of the battery's depth of discharge include a discharge rate drop coefficient , internal resistance increment coefficient , Temperature distribution difference coefficient .

[0012] In a preferred embodiment, the logic for obtaining the discharge rate reduction coefficient is as follows:

[0013] Calculate the discharge current based on the discharge voltage and battery internal resistance collected at different times , the expression is as follows ,in represents the discharge current at time t, represents the discharge voltage at time t, Indicates the internal resistance of the battery at time t; calculates the discharge rate , the expression is as follows ,in Indicates the remaining battery capacity of the battery; compares the discharge rate at different times t with the preset discharge rate threshold, records the discharge time when the discharge rate is less than the discharge rate threshold, and accumulates the discharge time when the discharge rate is less than the discharge rate threshold to obtain the discharge rate reduction time period; records the discharge time when the discharge rate is greater than or equal to the discharge rate threshold, and accumulates the discharge time when the discharge rate is greater than or equal to the discharge rate threshold to obtain the discharge rate high efficiency time period; when the discharge rate reduction time period is greater than the discharge rate high efficiency time period, calculates the discharge rate reduction coefficient , the expression is as follows ,in Indicates the time period of decreasing discharge rate, Indicates the high efficiency time period of the discharge rate, represents the discharge time when the i-th discharge rate is less than the discharge rate threshold, , represents the discharge time when the jth discharge rate is greater than or equal to the discharge rate threshold, ;

[0014] The logic for obtaining the internal resistance increment coefficient is as follows:

[0015] Create a data set containing timestamp and battery internal resistance value based on the collected battery internal resistance data: ,in Indicates the timestamp, Indicated in The internal resistance of the battery at the time, ;

[0016] According to the preset time sliding window T, calculate the sliding average increment of the resistance value change at each moment , the expression is as follows ,in Indicated in The internal resistance of the battery at the time, Indicated in The internal resistance value of the battery at the moment, m is used to represent the time point in the time sliding window T, and its value range is arrive ; Calculate the internal resistance increment coefficient , the expression is as follows ;

[0017] The logic for obtaining the temperature distribution difference coefficient is as follows:

[0018] Create a battery temperature data set containing battery temperature values ​​and locations based on the collected battery temperature data ,in represents the position coordinates of the hth battery temperature data point, Indicated in Battery temperature value at the location coordinates, ; Based on the K-means clustering algorithm, the temperature distribution on the battery pack surface is clustered and analyzed and the temperature distribution difference coefficient is calculated as follows:

[0019] Step A1, using the elbow rule to determine the initial cluster number K, randomly selecting K battery temperature data points from the battery temperature data set as the initial cluster clusters, and the data in the battery temperature data points are used as the cluster center coordinates of the initial cluster clusters;

[0020] Step A2, using the Euclidean distance calculation method to calculate the distance between each battery temperature data point in the battery temperature data set and the cluster center of each cluster, and assigning it to the cluster with the smallest distance;

[0021] Step A3, calculating the average value of the battery temperature data points in each cluster, and using it as the cluster center coordinate of the cluster;

[0022] Step A4, repeating steps A2 and A3 until the cluster center coordinates no longer change, then the clustering process ends and the final temperature distribution cluster is obtained;

[0023] Calculate the standard deviation of the battery temperature values ​​in each temperature distribution cluster , the expression is as follows ,in Represents the battery temperature value of the dth battery temperature data point in the temperature distribution cluster, Represents the average value of battery temperature in the temperature distribution cluster;

[0024] Calculate the temperature distribution coefficient of variation , the expression is as follows ,in represents the standard deviation of the battery temperature value of the fth temperature distribution cluster, represents the average value of the battery temperature value of the fth temperature distribution cluster, Represents the average value of the battery temperature values ​​in the battery temperature dataset.

[0025] In a preferred embodiment, a nonlinear prediction model for the depth of discharge is constructed based on the discharge rate drop coefficient, the internal resistance increment coefficient, and the temperature distribution difference coefficient, and a nonlinear index of the depth of discharge is output. The model is based on the following formula , where represent the preset proportional coefficients of the discharge rate reduction coefficient, the internal resistance increment coefficient, and the temperature distribution difference coefficient, respectively, and Both are greater than 0.

[0026] In a preferred embodiment, the light source attenuation information includes the light source attenuation coefficient , metal corrosion information including metal corrosion coefficient , insulation damage information includes insulation damage coefficient .

[0027] In a preferred embodiment, the logic for obtaining the light source attenuation coefficient is as follows:

[0028] Use light sensors to collect light intensity data of solar street lights at different time points ,in Indicates the light intensity of the solar street lamp at the bth sampling time point; calculates the light source attenuation coefficient , the expression is as follows ,in Indicates the light intensity when the solar street light is put into use. Indicates the specific moment of the b-th adopted time point;

[0029] The logic for obtaining the metal corrosion coefficient is as follows:

[0030] Use high-precision sensors to collect environmental data including temperature in the environment where the solar street light is located ,humidity , concentration of corrosive gases in the air , atmospheric pressure ; Calculate corrosion density , the expression is as follows ,in Respectively represent the preset proportional coefficients of temperature, humidity, air corrosive gas concentration, and atmospheric pressure, and All are greater than 0;

[0031] Calculate metal corrosion coefficient , the expression is as follows ,in Indicates the time when the solar street light is put into use. represents the molar mass of the metal, represents the chemical equivalent number of the metal, is the Faraday constant, Represents the metal surface area;

[0032] The logic for obtaining the insulation layer damage coefficient is as follows:

[0033] The insulation layer images of cables and electrical equipment in solar street lights are collected by high-definition cameras. The collected insulation layer images are preprocessed, including grayscale, noise removal, and histogram equalization. The Canny edge detection algorithm is used to detect the edges in the insulation layer images, identify the boundaries of cracks and wear, and the Otsu algorithm is used to segment the insulation layer images into crack wear areas and non-damaged areas: ,in represents the segmented insulation layer image, Indicates the crack wear area, Indicates the non-damaged area, represents the insulation layer image before segmentation, Represents the segmentation threshold of pixels; calculates the crack wear ratio , the expression is as follows ,in express The image is marked as The pixel accumulation value, express The image is marked as The pixel accumulation value;

[0034] Analyze each pair of adjacent pixels in the crack wear area in the insulation layer image, count the grayscale values ​​of each pair of adjacent pixels, and convert the grayscale values ​​of each pair of adjacent pixels into a single value according to the preset distance and direction. Scan the insulation layer image as an index and count the grayscale values ​​of each pair of adjacent pixels The number of occurrences; and the number of occurrences of the grayscale values ​​of each pair of adjacent pixels is used as a matrix element to construct a grayscale co-occurrence matrix; calculate the crack wear contrast , the expression is as follows ,in represents the difference in grayscale values ​​between the gth pair of adjacent pixels, is the element of the gray-level co-occurrence matrix, representing the gray value and The co-occurrence probability of; Calculate the insulation layer damage coefficient , the expression is as follows ,in represent the preset proportional coefficients of crack wear ratio and crack wear contrast, respectively, and Both are greater than 0.

[0035] In a preferred embodiment, a solar street light hidden danger assessment model is constructed based on the light source attenuation coefficient, metal corrosion coefficient, and insulation layer damage coefficient, and a solar street light hidden danger assessment index is output. The model is based on the following formula , where Respectively represent the preset proportional coefficients of the light source attenuation coefficient, metal corrosion coefficient, and insulation layer damage coefficient, and Both are greater than 0.

[0036] In a preferred embodiment, in step S5, when the solar street light needs to be turned on and the battery is in a low power state, the preset brightness curve is corrected according to the nonlinear discharge fluctuation degree of the battery in the low power state and the potential hidden danger degree of the solar street light operation state, as follows:

[0037] The preset brightness curve is corrected according to the discharge depth nonlinear index and the solar street light hidden danger assessment index. The correction formula is as follows: ,in Indicates the brightness value of the preset brightness curve. Represents the corrected brightness value, , Respectively represent the preset proportional coefficients of the discharge depth nonlinear index and the solar street light hidden danger assessment index; and , Both are greater than 0.

[0038] Technical effects and advantages of the present invention:

[0039] 1. The present invention collects nonlinear data of discharge depth when the battery is in a low-power state and extracts the nonlinear characteristics of the discharge rate drop coefficient, the internal resistance increment coefficient, and the temperature distribution difference coefficient to calculate the nonlinear index of discharge depth, so as to timely capture the nonlinear characteristics of the voltage fluctuation of the battery as the discharge depth increases, evaluate the power status of the battery and the degree of nonlinear discharge fluctuation of the battery, and dynamically adjust the brightness of the light source, so as to maximize the service life of the battery while ensuring the lighting quality. At the same time, the solar street light hidden danger assessment index is calculated according to the light source attenuation coefficient, the metal corrosion coefficient, and the insulation layer damage coefficient, so as to timely identify the potential failure risk of the street light after long-term use, and appropriately adjust the brightness according to the degree of hidden danger to ensure the safe and stable operation of the street light system. When the battery is in a low-power state, the brightness curve is corrected according to the nonlinear index of discharge depth and the hidden danger assessment index of the solar street light, so that the system can adapt to the complex characteristics of battery discharge and the aging effect of the street light. This adaptive correction mechanism not only improves the accuracy of light source brightness adjustment, but also effectively reduces the energy waste of the system, while avoiding battery loss and equipment failure caused by excessive adjustment, and ensuring the stable operation of the solar street light under low power, aging or high load conditions.

[0040] 2. The present invention dynamically adjusts the brightness of the light source based on the above method, and accurately responds to the complex nonlinear changes and aging problems in the solar street light system, thereby achieving multiple technical advantages of high efficiency and energy saving, extending equipment life, and improving system stability and reliability. It can not only effectively extend the service life of solar street lights, but also reduce maintenance costs, while providing more reliable technical guarantees for green lighting in smart cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0042] Figure 1 The figure is a flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Example: Figure 1 The present invention provides a method for adaptively adjusting the illumination intensity of a solar street light, comprising the following steps:

[0045] Step S1, real-time monitoring of the remaining power of the battery. When the battery is in a low power state, the discharge voltage, battery temperature and internal resistance change data of the battery are collected according to a high-precision sensor, and the collected data are pre-processed to extract the nonlinear characteristics of the discharge depth of the battery;

[0046] Step S2, constructing a nonlinear prediction model of the depth of discharge according to the nonlinear characteristics of the depth of discharge of the battery, outputting a nonlinear index of the depth of discharge, and evaluating the degree of nonlinear discharge fluctuation caused by the increase of the depth of discharge when the battery is in a low power state;

[0047] Step S3, obtaining the light source attenuation information, metal corrosion information and insulation layer damage information of the solar street lamp, and constructing a solar street lamp hidden danger assessment model according to the light source attenuation information, metal corrosion information and insulation layer damage information, outputting a solar street lamp hidden danger assessment index, and assessing the degree of potential hidden dangers in the operation state of the solar street lamp as the use time increases;

[0048] Step S4, judging whether the solar street light needs to be turned on according to the real-time light intensity data provided by the ambient light sensor, and if turned on, adjusting the brightness of the light source according to a preset brightness curve;

[0049] Step S5, when the solar street light needs to be turned on and the battery is in a low power state, the preset brightness curve is corrected according to the nonlinear discharge fluctuation degree of the battery in the low power state and the potential hidden danger degree of the solar street light operation state;

[0050] In step S1, the remaining power of the battery is monitored in real time through the battery management system. When the battery is in a low power state, the discharge voltage change of the battery is monitored in real time through a high-precision voltage sensor. The data acquisition frequency should meet the real-time control requirements of the system; a temperature sensor (such as a thermocouple or NTC thermistor) is installed to monitor the operating temperature of the battery, because the temperature will significantly affect the discharge characteristics of the battery; the internal resistance change of the battery is collected using a battery management system (BMS) or a special battery internal resistance tester. The increase in internal resistance usually indicates battery aging or a decrease in discharge performance;

[0051] Clean the collected discharge voltage, battery temperature and internal resistance change data, remove noise data, and apply filtering algorithms (such as Kalman filtering, low-pass filtering, etc.) to smooth the fluctuations of voltage, battery temperature and internal resistance; normalize the collected data so that various data sources can be compared and analyzed on the same scale; extract the nonlinear characteristics of the battery's discharge depth based on the battery's discharge characteristics at low power;

[0052] The nonlinear characteristics of the battery's depth of discharge include a discharge rate drop coefficient , internal resistance increment coefficient , Temperature distribution difference coefficient ;

[0053] The discharge rate drop coefficient is a key indicator used to measure the decrease in the discharge rate of a battery as the depth of discharge increases when the battery is in a low-power state. When the battery is close to exhaustion, the discharge rate will gradually decrease. The discharge rate drop coefficient is used to describe the nonlinear relationship between the voltage drop rate of the battery during the discharge process and the remaining battery power. Specifically, as the battery power gradually decreases, the battery voltage drop rate during the discharge process usually accelerates, resulting in more drastic fluctuations in the battery voltage. This fluctuation makes the power output of the battery more unstable, which directly affects the lighting intensity of the solar street light. When the remaining power of the battery is at a low level, the discharge rate drop coefficient increases, and the voltage change during the battery discharge process accelerates, resulting in the battery being unable to stably provide sufficient voltage and power. At this time, if it is not adjusted, the brightness of the street light may fluctuate violently, or even insufficient lighting may occur. By real-time monitoring and calculating the discharge rate drop coefficient, the system can accurately evaluate the discharge state of the battery and identify the area where the battery may produce large voltage fluctuations, thereby predicting the lighting instability problem that the street light may face at this stage. By calculating the discharge rate reduction coefficient, not only can potential problems in low-battery conditions be identified in advance, but also the contradiction between the nonlinear discharge characteristics of the battery and the lighting needs of street lamps can be balanced through intelligent adjustment strategies, ensuring that street lamps can maintain relatively stable and efficient lighting effects under different battery conditions.

[0054] The logic for obtaining the discharge rate reduction coefficient is as follows:

[0055] Calculate the discharge current based on the discharge voltage and battery internal resistance collected at different times , the expression is as follows ,in represents the discharge current at time t, represents the discharge voltage at time t, Indicates the internal resistance of the battery at time t; calculates the discharge rate , the expression is as follows ,in Indicates the remaining battery capacity of the battery; compares the discharge rate at different times t with the preset discharge rate threshold, records the discharge time when the discharge rate is less than the discharge rate threshold, and accumulates the discharge time when the discharge rate is less than the discharge rate threshold to obtain the discharge rate reduction time period; records the discharge time when the discharge rate is greater than or equal to the discharge rate threshold, and accumulates the discharge time when the discharge rate is greater than or equal to the discharge rate threshold to obtain the discharge rate high efficiency time period; when the discharge rate reduction time period is greater than the discharge rate high efficiency time period, calculates the discharge rate reduction coefficient , the expression is as follows ,in Indicates the time period of decreasing discharge rate, Indicates the high efficiency time period of the discharge rate, represents the discharge time when the i-th discharge rate is less than the discharge rate threshold, , represents the discharge time when the jth discharge rate is greater than or equal to the discharge rate threshold, ;

[0056] The internal resistance increment coefficient is used to measure the increase in the internal resistance of the battery as the depth of discharge increases. The increase in internal resistance will affect the discharge efficiency of the battery, especially in the low-power state. The increase in the internal resistance of the battery will significantly reduce the output power of the battery. Based on the internal resistance increment coefficient, the evaluation of the nonlinear discharge fluctuations of the battery in the low-power state as the depth of discharge increases can effectively help the solar street light system predict and adjust the impact of battery performance changes on the stability of lighting intensity. The internal resistance increment coefficient measures the degree of change in the internal resistance of the battery as the depth of discharge increases. This change not only affects the charging and discharging efficiency of the battery, but also aggravates the voltage fluctuation of the battery. When the internal resistance increment coefficient of the battery is large, it means that the voltage drop of the battery during the discharge process increases, and the battery's response to the load is weakened. This change will directly cause the discharge characteristics of the battery in the low-power state to become more unstable, further aggravating the fluctuation of the street light illumination intensity. Through the evaluation based on the internal resistance increment coefficient, the system can monitor the internal resistance changes in the battery discharge process in real time, identify the trend of battery performance degradation, and then predict the possible unstable period of battery discharge. In this way, the street light system can take countermeasures in advance to ensure the stability of lighting intensity and avoid lighting instability caused by the increase of battery internal resistance. Therefore, the internal resistance increment coefficient can provide a very valuable adjustment basis for the solar street light system when evaluating the low-power discharge characteristics of the battery. By monitoring the changes in internal resistance, the system can better understand the nonlinear discharge fluctuations of the battery and avoid voltage fluctuations caused by excessive internal resistance, thereby ensuring the continuous stability of street lighting and optimizing energy efficiency.

[0057] The logic for obtaining the internal resistance increment coefficient is as follows:

[0058] Create a data set containing timestamp and battery internal resistance value based on the collected battery internal resistance data: ,in Indicates the timestamp, Indicated in The internal resistance of the battery at the time, ;

[0059] According to the preset time sliding window T, calculate the sliding average increment of the resistance value change at each moment , the expression is as follows ,in Indicated in The internal resistance of the battery at the time, Indicated in The internal resistance value of the battery at the moment, m is used to represent the time point in the time sliding window T, and its value range is arrive ; Calculate the internal resistance increment coefficient , the expression is as follows ;

[0060] The temperature distribution difference coefficient is used to measure the degree of temperature difference between different areas on the surface of the battery pack. As the battery discharge depth increases, the temperature distribution inside the battery will become more uneven, and the temperature difference will increase. This increase in temperature difference directly affects the discharge performance and stability of the battery. Through the calculation of the temperature distribution difference coefficient, it can be reflected that when the battery is in a low-power state, especially at a high discharge depth, the temperature difference between different areas of the battery is aggravated due to increased internal resistance and uneven chemical reactions, which further aggravates the nonlinear fluctuations in the battery discharge process. Specifically, as the battery discharge depth increases, the temperature inside the battery gradually rises, especially the high-power load area inside the battery (such as the positive electrode and the negative electrode) may experience local overheating. At this time, the difference in temperature distribution reflects the unevenness of the battery discharge process, especially the expansion of the temperature difference means that the discharge efficiency and stability of the battery may fluctuate violently when the battery is in a low-power state. The relationship between this temperature difference fluctuation and the battery discharge depth provides a quantitative basis for further understanding and evaluating the nonlinear discharge characteristics of the battery.

[0061] Therefore, through the temperature distribution difference coefficient, the discharge condition of the battery in a low-power state can be dynamically monitored, and the risk of nonlinear discharge fluctuation faced by the battery as the depth of discharge increases can be evaluated in real time, thereby providing an effective reference for optimizing the battery control strategy.

[0062] The logic for obtaining the temperature distribution difference coefficient is as follows:

[0063] Create a battery temperature data set containing battery temperature values ​​and locations based on the collected battery temperature data ,in represents the position coordinates of the hth battery temperature data point, Indicated in Battery temperature value at the location coordinates, ; Based on the K-means clustering algorithm, the temperature distribution on the battery pack surface is clustered and analyzed and the temperature distribution difference coefficient is calculated as follows:

[0064] Step A1, using the elbow rule to determine the initial cluster number K, randomly selecting K battery temperature data points from the battery temperature data set as the initial cluster clusters, and the data in the battery temperature data points are used as the cluster center coordinates of the initial cluster clusters;

[0065] Step A2, using the Euclidean distance calculation method to calculate the distance between each battery temperature data point in the battery temperature data set and the cluster center of each cluster, and assigning it to the cluster with the smallest distance;

[0066] Step A3, calculating the average value of the battery temperature data points in each cluster, and using it as the cluster center coordinate of the cluster;

[0067] Step A4, repeating steps A2 and A3 until the cluster center coordinates no longer change, then the clustering process ends and the final temperature distribution cluster is obtained;

[0068] Calculate the standard deviation of the battery temperature values ​​in each temperature distribution cluster , the expression is as follows ,in Represents the battery temperature value of the dth battery temperature data point in the temperature distribution cluster, Represents the average value of battery temperature in the temperature distribution cluster;

[0069] Calculate the temperature distribution coefficient of variation , the expression is as follows ,in represents the standard deviation of the battery temperature value of the fth temperature distribution cluster, represents the average value of the battery temperature value of the fth temperature distribution cluster, Represents the average value of the battery temperature values ​​in the battery temperature data set;

[0070] Step S2, constructing a nonlinear prediction model of the depth of discharge according to the nonlinear characteristics of the depth of discharge of the battery, outputting a nonlinear index of the depth of discharge, and evaluating the degree of nonlinear discharge fluctuation caused by the increase of the depth of discharge when the battery is in a low power state;

[0071] A nonlinear prediction model for discharge depth is constructed based on the discharge rate drop coefficient, internal resistance increment coefficient, and temperature distribution difference coefficient, and a nonlinear index of discharge depth is output. The model is based on the following formula , where represent the preset proportional coefficients of the discharge rate reduction coefficient, the internal resistance increment coefficient, and the temperature distribution difference coefficient, respectively, and All are greater than 0;

[0072] It should be noted that before constructing the nonlinear prediction model of discharge depth, it is necessary to ensure that the discharge rate drop coefficient, internal resistance increment coefficient, and temperature distribution difference coefficient are all normalized. Commonly used normalization methods include Min-Max normalization and Z-Score normalization. Set it according to the actual situation. For example, adopt the expert empowerment method, that is, invite experts in related fields to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0073] It can be seen from the above calculation expression that the larger the discharge rate decrease coefficient, the larger the internal resistance increment coefficient, and the larger the temperature distribution difference coefficient, the larger the discharge depth nonlinear index, which means that when the battery is in a low power state, as the discharge depth increases, its nonlinear characteristics become more obvious, and the battery's discharge performance may be greatly affected. On the contrary, the smaller the discharge rate decrease coefficient, the smaller the internal resistance increment coefficient, and the smaller the temperature distribution difference coefficient, the smaller the discharge depth nonlinear index, which means that the battery's discharge process is more linear, the battery's discharge fluctuation is smaller in a low power state, the battery's discharge performance is more stable, the battery can maintain a high discharge efficiency, and the management system can more accurately adjust the energy to ensure the lighting stability of systems such as solar street lights, while extending the battery life;

[0074] Step S3, obtaining the light source attenuation information, metal corrosion information and insulation layer damage information of the solar street lamp, and constructing a solar street lamp hidden danger assessment model according to the light source attenuation information, metal corrosion information and insulation layer damage information, outputting a solar street lamp hidden danger assessment index, and assessing the degree of potential hidden dangers in the operation state of the solar street lamp as the use time increases;

[0075] The light source attenuation information includes the light source attenuation coefficient , metal corrosion information including metal corrosion coefficient , insulation damage information includes insulation damage coefficient ;

[0076] The light source attenuation coefficient is used to measure the attenuation of the light intensity of solar street lights as their service life increases. As the use time of solar street lights increases, the light source attenuation coefficient gradually increases, which means that the brightness of the street light source gradually decreases. This attenuation will directly affect the lighting effect of the street light, resulting in insufficient lighting intensity, especially at night. As an important indicator for evaluating the health of street lights, the light source attenuation coefficient can reveal the severity of light source attenuation, thereby reflecting the potential performance degradation of street lights during their service life. When the light source attenuation coefficient is large, it indicates that the light intensity of the street light is already far lower than the initial design requirements, and there is a risk of insufficient lighting, which not only affects the basic functions of the street light (such as road lighting), but may also cause safety hazards, especially in areas with heavy traffic at night. In addition, the increase in the light source attenuation coefficient is usually accompanied by the aging and loss of the light source itself. If the light source is not replaced or maintained in time, it may cause the street light to fail completely, causing greater social and economic losses.

[0077] By monitoring and evaluating the light source attenuation coefficient, the potential hidden dangers of solar street lights can be predicted in advance and appropriate maintenance or replacement measures can be taken.

[0078] Therefore, evaluating the operating status of solar street lights as their service life increases based on the light source attenuation coefficient not only helps to identify potential lighting problems, but also provides data support for maintenance strategies, extends the service life of solar street lights, and ensures their stable operation, avoiding safety hazards caused by light source decay.

[0079] The logic for obtaining the light source attenuation coefficient is as follows:

[0080] Use light sensors to collect light intensity data of solar street lights at different time points ,in Indicates the light intensity of the solar street lamp at the bth sampling time point; calculates the light source attenuation coefficient , the expression is as follows ,in Indicates the light intensity when the solar street light is put into use. Indicates the specific moment of the b-th adopted time point;

[0081] The metal corrosion coefficient is used to measure the degree of corrosion of the metal parts (such as brackets, cable connectors, etc.) of solar street lights due to long-term exposure to corrosive substances such as moisture, salt, oxygen, etc. in the environment as the service life increases. Metal corrosion will affect the structural safety of street lights, and in severe cases may cause mechanical failure or circuit disconnection; a large metal corrosion coefficient means that the surface of the metal parts has been severely corroded, which may cause problems such as poor contact, line failure, or even bracket breakage, which in turn affects the lighting stability and service life of the street lights. By monitoring the metal corrosion coefficient, the control system can adjust the operation strategy in time to avoid the risk of failure caused by corrosion, such as adjusting the brightness of the street lights, optimizing the battery charge and discharge cycle, or increasing the maintenance frequency in a highly corrosive environment. This potential risk assessment based on the metal corrosion coefficient helps to improve the reliability and safety of the system and ensure the normal operation of solar street lights in harsh environments.

[0082] Therefore, evaluating the potential hazards of solar street lights based on the metal corrosion coefficient can not only provide a basis for later maintenance, but also extend the service life of solar street lights and improve their long-term operation safety and stability, thereby reducing the failure rate caused by corrosion problems and improving the economic benefits of the overall system.

[0083] The logic for obtaining the metal corrosion coefficient is as follows:

[0084] Use high-precision sensors to collect environmental data including temperature in the environment where the solar street light is located ,humidity , concentration of corrosive gases in the air , atmospheric pressure ; Calculate corrosion density , the expression is as follows ,in Respectively represent the preset proportional coefficients of temperature, humidity, air corrosive gas concentration, and atmospheric pressure, and All are greater than 0;

[0085] It should be noted that before calculating the corrosion density, it is necessary to ensure that the temperature, humidity, concentration of corrosive gases in the air, and atmospheric pressure are all normalized; Set according to actual conditions, for example, adopt the expert empowerment method, that is, invite experts in relevant fields to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0086] Calculate metal corrosion coefficient , the expression is as follows ,in Indicates the time when the solar street light is put into use. represents the molar mass of the metal, represents the chemical equivalent number of the metal, is the Faraday constant, Represents the metal surface area;

[0087] The insulation damage factor is used to measure whether the insulation layer of cables and electrical equipment in solar street lights is damaged or aged after long-term use. Damage to the insulation layer may cause safety hazards such as circuit short circuit and leakage. Based on the insulation damage factor, the degree of potential hidden dangers in the operation of solar street lights as the use time increases can be evaluated, which can effectively improve the safety and reliability of the street light system. With the long-term use of solar street lights, external environmental factors, material aging, physical damage and other factors will gradually lead to the damage of the insulation layer, which directly affects the electrical safety of the street lights, the risk of short circuit and the stability of the entire system. By evaluating the degree of damage to the insulation layer, potential hidden dangers can be identified in time to avoid serious electrical failures and fire risks. Specifically, the introduction of the insulation damage factor has the following key beneficial effects:

[0088] Early identification of hidden dangers and prevention of electrical failures: Damage to the insulation layer can lead to electrical short circuits, leakage, and even fires. By evaluating the damage to the insulation layer, potential electrical hazards can be discovered in advance and timely maintenance or replacement can be performed. This can effectively reduce the occurrence of electrical failures and reduce the failure rate and maintenance costs of the street light system.

[0089] Improve operational safety: As the insulation damage factor increases, the electrical isolation of the street light weakens, the leakage current increases, and the equipment is exposed to potential electrical hazards. By monitoring and evaluating this factor, electrical accidents can be prevented and the solar street light can still operate safely and stably in harsh environments.

[0090] Extend the service life of equipment: Regular inspection and evaluation of the degree of insulation damage can be used to repair or replace insulation early, avoiding electrical damage caused by excessive damage, thereby extending the service life of the solar street light system. Through scientific evaluation, the maintenance and replacement cycle can be reasonably arranged to reduce unnecessary downtime and maintenance costs.

[0091] Optimize maintenance plan and reduce maintenance cost: By accurately assessing the degree of insulation damage, the maintenance and overhaul plan can be optimized according to actual needs to avoid premature or late repairs. Reasonable maintenance arrangements can not only improve the working efficiency of the equipment, but also effectively reduce the overall maintenance cost and improve the return on investment.

[0092] Improve environmental adaptability: Under different environmental conditions (such as humidity, pollution, temperature changes, etc.), the insulation layer of solar street lights may accelerate aging or damage. By regularly evaluating the damage coefficient of the insulation layer, the design and use strategy of street lights can be adjusted according to environmental changes, improving the adaptability of the equipment in complex environments.

[0093] Enhanced intelligent management of the system: By combining with intelligent sensors and monitoring systems, evaluating the insulation damage coefficient can monitor the operating status of street lights in real time, warn of potential safety hazards in advance, and help managers make more accurate decisions. This intelligent management method can significantly improve the efficiency and response speed of equipment management.

[0094] In summary, the evaluation based on the insulation damage coefficient can not only improve the operating safety and extend the service life of solar street lights, but also help reduce maintenance costs and optimize equipment management. Through accurate evaluation and prediction, it can effectively reduce the occurrence of faults and potential risks, and improve the overall reliability and performance of the street light system.

[0095] The logic for obtaining the insulation layer damage coefficient is as follows:

[0096] The insulation layer images of cables and electrical equipment in solar street lights are collected by high-definition cameras. The collected insulation layer images are preprocessed, including grayscale, noise removal, and histogram equalization. The Canny edge detection algorithm is used to detect the edges in the insulation layer images, identify the boundaries of cracks and wear, and the Otsu algorithm is used to segment the insulation layer images into crack wear areas and non-damaged areas: ,in represents the segmented insulation layer image, Indicates the crack wear area, Indicates the non-damaged area, represents the insulation layer image before segmentation, Represents the segmentation threshold of pixels; calculates the crack wear ratio , the expression is as follows ,in express The image is marked as The pixel accumulation value, express The image is marked as The pixel accumulation value;

[0097] Analyze each pair of adjacent pixels in the crack wear area in the insulation layer image, count the grayscale values ​​of each pair of adjacent pixels, and convert the grayscale values ​​of each pair of adjacent pixels into a single value according to the preset distance and direction. Scan the insulation layer image as an index and count the grayscale values ​​of each pair of adjacent pixels The number of occurrences; and the number of occurrences of the grayscale values ​​of each pair of adjacent pixels is used as a matrix element to construct a grayscale co-occurrence matrix; calculate the crack wear contrast , the expression is as follows ,in represents the difference in grayscale values ​​between the gth pair of adjacent pixels, is the element of the gray-level co-occurrence matrix, representing the gray value and The co-occurrence probability of; Calculate the insulation layer damage coefficient , the expression is as follows ,in represent the preset proportional coefficients of crack wear ratio and crack wear contrast, respectively, and All are greater than 0;

[0098] It should be noted that before calculating the insulation layer damage coefficient, it is necessary to ensure that the crack wear ratio and crack wear contrast are normalized; Set according to actual conditions, for example, adopt the expert empowerment method, that is, invite experts in relevant fields to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0099] According to the light source attenuation coefficient, metal corrosion coefficient and insulation layer damage coefficient, a solar street light hidden danger assessment model is constructed to output the solar street light hidden danger assessment index The model is based on the following formula , where Respectively represent the preset proportional coefficients of the light source attenuation coefficient, metal corrosion coefficient, and insulation layer damage coefficient, and All are greater than 0;

[0100] It should be noted that before constructing the solar street light hidden danger assessment model, it is necessary to ensure that the light source attenuation coefficient, metal corrosion coefficient, and insulation layer damage coefficient are all normalized; Set according to actual conditions, for example, adopt the expert empowerment method, that is, invite experts in relevant fields to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0101] From the above calculation expression, it can be seen that the greater the light source attenuation coefficient, metal corrosion coefficient, and insulation layer damage coefficient, the greater the solar street light hidden danger assessment index, which means that the solar street light may have greater hidden dangers and the greater the impact on the solar street light lighting. On the contrary, the smaller the light source attenuation coefficient, metal corrosion coefficient, and insulation layer damage coefficient, the smaller the solar street light hidden danger assessment index, which means that the solar street light is in good operating condition, has fewer hidden dangers, and has less impact on the solar street light lighting.

[0102] In step S4, the light intensity data of the current environment is obtained from the ambient light sensor, and the light intensity of the environment is compared with a preset light threshold. If the light intensity of the environment is less than the light threshold, the solar street light is turned on and the brightness of the light source is adjusted according to a preset brightness curve; if the light intensity of the environment is greater than or equal to the light threshold, the solar street light does not need to be turned on;

[0103] In step S5, when the solar street light needs to be turned on and the battery is in a low power state, the preset brightness curve is corrected according to the nonlinear discharge fluctuation degree of the battery in the low power state and the potential hidden danger degree of the solar street light operation state, as follows:

[0104] The preset brightness curve is corrected according to the discharge depth nonlinear index and the solar street light hidden danger assessment index. The correction formula is as follows: ,in Indicates the brightness value of the preset brightness curve. Represents the corrected brightness value, , Respectively represent the preset proportional coefficients of the discharge depth nonlinear index and the solar street light hidden danger assessment index; and , All are greater than 0;

[0105] It should be noted that , Set according to actual conditions, for example, adopt the expert empowerment method, that is, invite experts in relevant fields to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0106] It should be noted that the significance of the above correction formula is to adjust the brightness when the battery power is low. The greater the depth of discharge, the greater the brightness correction, indicating that the brightness needs to be reduced to save power. It is used to adjust the brightness when the potential risk of street lamp failure is high. The greater the potential risk assessment index, the more likely it is that the brightness needs to be reduced or power needs to be used conservatively in other ways.

[0107] The present invention collects discharge depth nonlinear data when the battery is in a low power state and extracts the nonlinear characteristics of the discharge rate drop coefficient, the internal resistance increment coefficient, and the temperature distribution difference coefficient to calculate the discharge depth nonlinear index, so as to timely capture the nonlinear characteristics of the voltage fluctuation of the battery as the discharge depth increases, evaluate the battery power status and the nonlinear discharge fluctuation degree of the battery, and dynamically adjust the light source brightness, so as to maximize the battery life while ensuring the lighting quality. At the same time, the solar street lamp hidden danger assessment index is calculated according to the light source attenuation coefficient, the metal corrosion coefficient, and the insulation layer damage coefficient, so as to timely identify the potential failure risk of the street lamp after long-term use, and appropriately adjust the brightness according to the hidden danger degree, so as to ensure the safe and stable operation of the street lamp system. When the battery is in a low power state, the brightness curve is corrected according to the discharge depth nonlinear index and the solar street lamp hidden danger assessment index, so that the system can adapt to the complex characteristics of battery discharge and the aging effect of the street lamp. This adaptive correction mechanism not only improves the accuracy of the light source brightness adjustment, but also effectively reduces the energy waste of the system, while avoiding battery loss and equipment failure caused by excessive adjustment, and ensuring the stable operation of the solar street lamp under low power, aging or high load conditions.

[0108] The present invention dynamically adjusts the brightness of the light source based on the above method, and accurately copes with the complex nonlinear changes and aging problems in the solar street light system, thereby achieving multiple technical advantages of high efficiency energy saving, extending equipment life, and improving system stability and reliability. It can not only effectively extend the service life of solar street lights, but also reduce maintenance costs, while providing more reliable technical guarantees for the green lighting of smart cities.

[0109] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0110] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0111] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for adaptively adjusting the illumination intensity of a solar street light, characterized in that: The steps include: Step S1, real-time monitoring of the remaining power of the battery. When the battery is in a low power state, the discharge voltage, battery temperature and internal resistance change data of the battery are collected according to a high-precision sensor, and the collected data are pre-processed to extract the nonlinear characteristics of the discharge depth of the battery; Step S2, constructing a nonlinear prediction model of the depth of discharge according to the nonlinear characteristics of the depth of discharge of the battery, outputting a nonlinear index of the depth of discharge, and evaluating the degree of nonlinear discharge fluctuation caused by the increase of the depth of discharge when the battery is in a low power state; Step S3, obtaining the light source attenuation information, metal corrosion information and insulation layer damage information of the solar street lamp, and constructing a solar street lamp hidden danger assessment model according to the light source attenuation information, metal corrosion information and insulation layer damage information, outputting a solar street lamp hidden danger assessment index, and assessing the degree of potential hidden dangers in the operation state of the solar street lamp as the use time increases; Step S4, judging whether the solar street light needs to be turned on according to the real-time light intensity data provided by the ambient light sensor, and if turned on, adjusting the brightness of the light source according to a preset brightness curve; Step S5, when the solar street light needs to be turned on and the battery is in a low power state, the preset brightness curve is corrected according to the nonlinear discharge fluctuation degree of the battery in the low power state and the potential hidden danger degree of the solar street light operation state.

2. The method for adaptively adjusting illumination intensity of solar street lamps according to claim 1, characterized in that: The nonlinear characteristics of the battery's depth of discharge include a discharge rate drop coefficient , internal resistance increment coefficient , Temperature distribution difference coefficient .

3. The method for adaptively adjusting the illumination intensity of a solar street lamp according to claim 2, characterized in that: The logic for obtaining the discharge rate reduction coefficient is as follows: Calculate the discharge current based on the discharge voltage and battery internal resistance collected at different times , the expression is as follows ,in represents the discharge current at time t, represents the discharge voltage at time t, Indicates the internal resistance of the battery at time t; calculates the discharge rate , the expression is as follows ,in Indicates the remaining battery capacity of the battery; compares the discharge rate at different times t with the preset discharge rate threshold, records the discharge time when the discharge rate is less than the discharge rate threshold, and accumulates the discharge time when the discharge rate is less than the discharge rate threshold to obtain the discharge rate reduction time period; records the discharge time when the discharge rate is greater than or equal to the discharge rate threshold, and accumulates the discharge time when the discharge rate is greater than or equal to the discharge rate threshold to obtain the discharge rate high efficiency time period; when the discharge rate reduction time period is greater than the discharge rate high efficiency time period, calculates the discharge rate reduction coefficient , the expression is as follows ,in Indicates the time period of decreasing discharge rate, Indicates the high efficiency time period of the discharge rate, represents the discharge time when the i-th discharge rate is less than the discharge rate threshold, , represents the discharge time when the jth discharge rate is greater than or equal to the discharge rate threshold, ; The logic for obtaining the internal resistance increment coefficient is as follows: Create a data set containing timestamp and battery internal resistance value based on the collected battery internal resistance data: ,in Indicates the timestamp, Indicated in The internal resistance of the battery at the time, ; According to the preset time sliding window T, calculate the sliding average increment of the resistance value change at each moment , the expression is as follows ,in Indicated in The internal resistance of the battery at the time, Indicated in The internal resistance value of the battery at the moment, m is used to represent the time point in the time sliding window T, and its value range is arrive ; Calculate the internal resistance increment factor , the expression is as follows ; The logic for obtaining the temperature distribution difference coefficient is as follows: A battery temperature data set containing battery temperature values ​​and locations is established based on the collected battery temperature data ,in represents the position coordinates of the hth battery temperature data point, Indicated in Battery temperature value at the location coordinates, ; Based on the K-means clustering algorithm, the temperature distribution on the battery pack surface is clustered and analyzed and the temperature distribution difference coefficient is calculated as follows: Step A1, using the elbow rule to determine the initial cluster number K, randomly selecting K battery temperature data points from the battery temperature data set as the initial cluster clusters, and the data in the battery temperature data points are used as the cluster center coordinates of the initial cluster clusters; Step A2, using the Euclidean distance calculation method to calculate the distance between each battery temperature data point in the battery temperature data set and the cluster center of each cluster, and assigning it to the cluster with the smallest distance; Step A3, calculating the average value of the battery temperature data points in each cluster, and using it as the cluster center coordinate of the cluster; Step A4, repeating steps A2 and A3 until the cluster center coordinates no longer change, then the clustering process ends and the final temperature distribution cluster is obtained; Calculate the standard deviation of the battery temperature values ​​in each temperature distribution cluster , the expression is as follows ,in Represents the battery temperature value of the dth battery temperature data point in the temperature distribution cluster, Represents the average value of battery temperature in the temperature distribution cluster; Calculate the temperature distribution coefficient of variation , the expression is as follows ,in represents the standard deviation of the battery temperature value of the fth temperature distribution cluster, represents the average value of the battery temperature value of the fth temperature distribution cluster, Represents the average value of the battery temperature values ​​in the battery temperature dataset.

4. The method for adaptively adjusting the illumination intensity of a solar street lamp according to claim 3 is characterized in that: A nonlinear prediction model for discharge depth is constructed based on the discharge rate drop coefficient, internal resistance increment coefficient, and temperature distribution difference coefficient, and a nonlinear index of discharge depth is output. The model is based on the following formula , where represent the preset proportional coefficients of the discharge rate reduction coefficient, the internal resistance increment coefficient, and the temperature distribution difference coefficient, respectively, and Both are greater than 0.

5. The method for adaptively adjusting the illumination intensity of a solar street lamp according to claim 4, characterized in that: The light source attenuation information includes the light source attenuation coefficient , metal corrosion information including metal corrosion coefficient , insulation damage information includes insulation damage coefficient .

6. A method for adaptively adjusting illumination intensity of solar street lamps according to claim 5, characterized in that: The logic for obtaining the light source attenuation coefficient is as follows: Use light sensors to collect light intensity data of solar street lights at different time points ,in represents the light intensity of the solar street lamp at the bth sampling time point; Calculate the light source attenuation coefficient , the expression is as follows ,in Indicates the light intensity when the solar street light is put into use. Indicates the specific moment of the b-th adopted time point; The logic for obtaining the metal corrosion coefficient is as follows: Use high-precision sensors to collect environmental data including temperature in the environment where the solar street light is located ,humidity , concentration of corrosive gases in the air , atmospheric pressure ; Calculate corrosion density , the expression is as follows ,in Respectively represent the preset proportional coefficients of temperature, humidity, air corrosive gas concentration, and atmospheric pressure, and All are greater than 0; Calculate metal corrosion coefficient , the expression is as follows ,in Indicates the time when the solar street light is put into use. represents the molar mass of the metal, represents the chemical equivalent number of the metal, is the Faraday constant, Represents the metal surface area; The logic for obtaining the insulation layer damage coefficient is as follows: The insulation layer images of cables and electrical equipment in solar street lights are collected by high-definition cameras. The collected insulation layer images are preprocessed, including grayscale, noise removal, and histogram equalization. The Canny edge detection algorithm is used to detect the edges in the insulation layer images, identify the boundaries of cracks and wear, and the Otsu algorithm is used to segment the insulation layer images into crack wear areas and non-damaged areas: ,in represents the segmented insulation layer image, Indicates the crack wear area, Indicates the non-damaged area, represents the insulation layer image before segmentation, Represents the segmentation threshold of pixels; calculates the crack wear ratio , the expression is as follows ,in express The image is marked as The pixel accumulation value, express The image is marked as The pixel accumulation value; Analyze each pair of adjacent pixels in the crack wear area in the insulation layer image, count the grayscale values ​​of each pair of adjacent pixels, and convert the grayscale values ​​of each pair of adjacent pixels into a single value according to the preset distance and direction. Scan the insulation layer image as an index and count the grayscale values ​​of each pair of adjacent pixels The number of occurrences; and the number of occurrences of the grayscale values ​​of each pair of adjacent pixels is used as a matrix element to construct a grayscale co-occurrence matrix; Calculation of crack wear contrast , the expression is as follows ,in represents the difference in grayscale values ​​between the gth pair of adjacent pixels, is the element of the gray-level co-occurrence matrix, representing the gray value and The co-occurrence probability of Calculation of insulation damage factor , the expression is as follows ,in represent the preset proportional coefficients of crack wear ratio and crack wear contrast, respectively, and Both are greater than 0.

7. A method for adaptively adjusting illumination intensity of solar street lamps according to claim 6, characterized in that: According to the light source attenuation coefficient, metal corrosion coefficient and insulation layer damage coefficient, a solar street light hidden danger assessment model is constructed to output the solar street light hidden danger assessment index The model is based on the following formula , where Respectively represent the preset proportional coefficients of the light source attenuation coefficient, metal corrosion coefficient, and insulation layer damage coefficient, and Both are greater than 0.

8. The method for adaptively adjusting illumination intensity of solar street lamps according to claim 7, characterized in that: In step S5, when the solar street light needs to be turned on and the battery is in a low power state, the preset brightness curve is corrected according to the nonlinear discharge fluctuation degree of the battery in the low power state and the potential hidden danger degree of the solar street light operation state, as follows: The preset brightness curve is corrected according to the discharge depth nonlinear index and the solar street light hidden danger assessment index. The correction formula is as follows: ,in Indicates the brightness value of the preset brightness curve. Represents the corrected brightness value, , Respectively represent the preset proportional coefficients of the discharge depth nonlinear index and the solar street light hidden danger assessment index; and , Both are greater than 0.

Images