Smart Street Lighting Adaptive Control System
Through the smart street light lighting adaptive control system, geological and anglers data near the dam water body are collected and analyzed in real time, and the brightness and angle of street lights are dynamically adjusted, which solves the problem of traditional systems failing to effectively deal with landslides and drowning risks and surface reflection interference, improving the problem of the traditional system's failure to effectively deal with landslides and drowning risks and water surface reflection interference. Lighting effect and safety.
Patent Information
- Application Number
- CN202411098191.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-08-12
AI Technical Summary
Traditional smart street light systems failed to effectively consider landslide and drowning risks in areas near the dam water body, lacked geological monitoring and risk assessment functions, could not provide real-time warnings or adjust lighting strategies, and failed to dynamically handle reflective interference on the water surface, resulting in uneven lighting effects and Reduced safety.
A smart street light lighting adaptive control system was designed. By monitoring the partition configuration unit, acquisition unit, risk analysis unit, light analysis unit and adaptive adjustment unit, geological slope and angler activity data are collected in real time, and landslide and drowning risk indicators are constructed. , dynamically adjust the brightness and angle of street lights to optimize the lighting effect.
Timely early warning and emergency response to landslide and drowning risks are achieved, hidden dangers of drowning events are reduced, lighting effects are optimized, regional safety and lighting intelligence and adaptability are improved, and unnecessary waste of resources is avoided.
Smart Images

Figure CN118660367B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart street lamp control, and in particular to a smart street lamp lighting adaptive control system. Background Art
[0002] In many cities, water bodies such as lakes, reservoirs, and dam areas are often incorporated into urban planning. These water bodies not only play an important role in ecological and environmental protection, but also provide valuable leisure and entertainment space for citizens. Therefore, cities often build various public facilities around these water bodies, such as parks, trails, and fishing areas. These areas not only attract a large number of residents to play, walk, and fish, but also become part of the city's leisure and social places.
[0003] In traditional smart street light systems, the main focus is on basic lighting functions, energy saving and automatic control. However, in areas near dam water bodies, traditional smart street light systems fail to effectively consider the landslide risk in areas near dam water bodies. The geological structure and environmental conditions in these areas may affect the occurrence of landslides, but traditional systems often do not integrate relevant geological monitoring and risk assessment functions. Therefore, when the risk of landslides increases, the smart street light system cannot provide real-time warnings or automatically adjust the lighting strategy to deal with this risk. Drowning is a potential safety hazard near water bodies where fishing is available. Traditional smart street light systems fail to take into account the depth, flow rate of the water body, and the activities of anglers. Such systems usually lack the function of monitoring the location and activities of anglers, and have no mechanism to detect and respond to drowning risks. Therefore, when a drowning incident occurs, traditional systems cannot provide timely alarms or take appropriate lighting adjustments to help rescue. Reflections on the surface of water bodies can significantly affect the lighting effect at night, making the light distribution in the area uneven or causing glare. Traditional smart street light systems often do not make adjustments for water surface reflections, nor do they dynamically monitor and correct the lighting interference caused by water surface reflections. The result may be that the lighting effect is affected, resulting in the light being unable to effectively cover the target area, reducing the actual effect and safety of the lighting. Summary of the invention
[0004] In view of the deficiencies of the prior art, the present invention provides a smart street lamp adaptive control system to solve the problems mentioned in the background technology.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a smart street lamp lighting adaptive control system, including a monitoring partition configuration unit, a first acquisition unit, a second acquisition unit, a risk analysis unit, a light analysis unit and an adaptive adjustment unit;
[0006] The monitoring partition configuration unit is used to collect several street lamp positions, and pre-select the area beside the dam water body where the street lamp position is located, and divide the area beside the dam water body into several monitoring partitions, ensuring that each monitoring partition includes at least one street lamp, and setting monitoring points in several monitoring partitions;
[0007] The first acquisition unit is used to collect geological slope information and angler activity data beside the water body in several monitoring zones to establish a first data set; the second acquisition unit is used to monitor environmental information and related lighting information in the corresponding monitoring zones to establish a second data set;
[0008] The risk analysis unit is used to construct a landslide risk ratio Hpb and a drowning risk index Nsfx through a trained risk prediction model based on the geological slope information next to the water body collected by the first collection unit and the angler activity data, and associate the landslide risk ratio Hpb with the drowning risk index Nsfx, obtain a risk alarm index YJbj, evaluate the risk alarm index YJbj, obtain a corresponding risk level, and generate a corresponding street lamp emergency flashing mode according to the corresponding risk level;
[0009] The light analysis unit is used to extract the environmental information and related lighting information features in the second data set through the trained light prediction model, so as to obtain the basic brightness of the street lamp Ld, the water surface reflection value Sfg, the road surface water film thickness smhd, the average water level rise value Swz and the farthest distance of the angler zyh, and deeply calculate and obtain the first light attenuation index SJzs; and perform feature extraction on the related lighting information in the second data set to respectively obtain the total number of anglers Cdzs, the average brightness of personal lighting equipment PJld and the average range value of personal lighting Zmfw in the corresponding monitoring area, and calculate and obtain the second light interference index Grzs; and associate the first light attenuation index SJzs with the second light interference index Grzs in the same monitoring area, and fit and obtain the light adjustment index Tszs in the corresponding monitoring area;
[0010] The adaptive adjustment unit is used to compare and analyze the light adjustment index Tszs in the corresponding monitoring zone with the preset adjustment threshold A to obtain the corresponding adjustment level, so as to generate the light brightness and angle adjustment management strategy in the corresponding monitoring zone.
[0011] Preferably, the monitoring partition configuration unit includes a street lamp position acquisition module and a marking module;
[0012] The street light location acquisition module is used to use GPS positioning technology to collect the latitude and longitude coordinates of each street light, and collect the street light installation height, angle and illumination range information, draw a three-dimensional model of the street light network through SAD modeling, add roads, dams, water bodies, green vegetation and slope facilities, and assign a unique number to each street light through the marking module, and mark them as: D1, D2,..., Dn, where n represents the number of street lights.
[0013] Preferably, the first data set includes: the slope value S from the dam to the water body, the real-time precipitation JsL, the soil density Trmd, the vegetation coverage rate V, the straight-line distance D between the angler and the edge of the water body, and the number of safety facilities AQss;
[0014] The second data set includes: water depth W, water flow velocity SlSD, basic brightness of street lamps Ld, water surface reflection value Sfg, road surface water film thickness smhd, average water level rise value Swz, farthest distance of anglers zyh, total number of anglers Cdzs, average brightness of personal lighting equipment PJld and average range value of personal lighting Zmfw.
[0015] Preferably, the risk analysis unit includes a risk model building module, a first calculation module, an association module, a first evaluation module and a first strategy module;
[0016] The risk model building module is used to collect historical event data, including landslides and drowning events, and to label the historical event data with binary classification labels; after extracting features from the first data set, neural network and deep learning network technologies are selected to build a risk prediction model, and after training, the risk prediction model is deployed into the system;
[0017] The first calculation module is used to perform in-depth analysis based on the first data set to calculate and obtain the landslide risk ratio Hpb and the drowning risk index Nsfx;
[0018] The associated module is used to generate the risk alarm index YJbj by using the following associated formula to convert the corresponding monitoring area landslide risk ratio Hpb and drowning risk index Nsfx:
[0019] YJbj=Hpb*α+Nsfx*β;
[0020] Wherein, α and β represent weight coefficients, and α+β=1.
[0021] Preferably, the steps for obtaining the landslide risk ratio Hpb and the drowning risk index Nsfx are as follows:
[0022] S11, extract the slope value S from the dam to the water body, the real-time precipitation JsL, the soil density Trmd and the vegetation coverage rate V of each monitoring area in the first data set, and perform dimensionless processing;
[0023] S12. The landslide risk ratio Hpb is calculated by the following formula:
[0024]
[0025] Where Hpb i represents the landslide risk ratio of the ith monitoring area, S i is the slope value from the dam to the water body in the i-th monitoring area, JsL i It is expressed as the real-time precipitation of the ith monitoring area, Trmd i It is expressed as the soil density in the i-th monitoring area, V i It is expressed as the vegetation coverage rate in the i-th monitoring area, a1, a2, a3 and a4 are all weight coefficients, and C1 is expressed as the first correction constant;
[0026] S13, extracting the behavior characteristics of the angler and the location and quantity characteristics of the safety facilities from the video image in the first data set to obtain: the straight-line distance D between the angler and the edge of the water body and the number of safety facilities AQss;
[0027] Extract water depth and water flow velocity characteristics from the second data set to obtain: water depth W and water flow velocity SlSD; and perform dimensionless processing on the above data;
[0028] S14. The drowning risk index Nsfx is calculated using the following formula:
[0029]
[0030] Where Nsfx i represents the drowning risk index of the ith monitoring area, D ij is the straight-line distance between the jth angler in the ith monitoring area and the edge of the water body, W ij represents the water depth within the 10-meter diameter area where the jth angler in the ith monitoring area is located, SlSD ij AQss represents the water flow velocity within the 10-meter diameter area where the jth angler in the ith monitoring zone is located. ij It indicates the number of safety facilities within a 10-meter diameter area where the j-th angler in the ith monitoring zone is located; safety facilities include guardrails, life-saving equipment, rescue equipment, warning signs and anti-slip facilities; a5, a6, a7 and a8 are all weight coefficients, and C2 is represented as the second correction constant.
[0031] Preferably, the first assessment module is used to preset a first risk threshold value X1 and a second risk threshold value X2, the first risk threshold value X1 < the second risk threshold value X2, and compare and evaluate the risk alarm index YJbj with the first risk threshold value X1 and the second risk threshold value X2 to obtain the following corresponding risk levels, including:
[0032] When the risk alarm index YJbj is less than the first risk threshold X1, it means that the current monitoring area has no risk and the first safety level is generated;
[0033] When the first risk threshold X1≤risk alarm index YJbj≤second risk threshold X2, it indicates that there is a landslide risk in the current monitoring area, and the second risk level is generated;
[0034] When the risk alarm index YJbj> the second risk threshold X2, it means that there is a drowning risk in the current monitoring area, and the third risk level is generated;
[0035] The first strategy module is used to generate corresponding emergency strategies according to corresponding risk levels, including:
[0036] Receiving a first security level, generating a first strategy: maintaining normal lighting of current street lamps;
[0037] A second risk level is received and a second strategy is generated: the street light flashes slowly in white, once per second, and a warning sound is added to remind anglers to pay attention to ramp safety;
[0038] The third risk level is received and the third strategy is generated: the street light flashes red quickly, once every half a second, and the emergency broadcast is triggered to broadcast the high-risk area, notifying anglers to evacuate immediately.
[0039] Preferably, the light analysis unit includes a water level prediction module, a second calculation module and a third calculation module;
[0040] The water level prediction module is used to collect and obtain several groups of water level values through water level sensors, sort them, and obtain the real-time water level value SW at the previous moment based on the linear regression method. N+1 The predicted water level value SW at the next moment is obtained by using the typical water level change curve N-1 ;
[0041] The real-time water level value SW of the previous moment N+1 And the predicted water level value SW at the next moment N-1 The water level rise prediction value ΔSw is obtained by the following formula:
[0042] ΔS=SW N+1 -SW N-1 ;
[0043] By analyzing historical data, the correction factor F is determined, and the water level rise prediction value is corrected by the correction factor F. The average water level rise value Swz is obtained through the following correction formula;
[0044]
[0045] Where N represents the total data points at a given moment.
[0046] Preferably, the second calculation module is used to select neural network and deep learning network technology, and after the light prediction model is established and trained and evaluated as qualified, the light prediction model is deployed into the system; and the basic brightness of the street lamp Ld, the water surface reflection value Sfg, the road surface water film thickness smhd, the average water level rise value Swz and the farthest distance of the angler zyh in the second data set are extracted.
[0047] After dimensionless processing, the first light attenuation index SJzs is calculated using the following formula:
[0048]
[0049] Wherein, b1, b2, b3, b4 and b5 are weight coefficients of the basic brightness of street lamp Ld, the water surface reflection value Sfg, the road surface water film thickness smhd, the average water level rise value Swz and the farthest distance of the angler zyh, respectively, and C3 is represented as the third correction constant;
[0050] The third calculation module is used to extract the total number of fishermen Cdzs, the average brightness of personal lighting equipment PJld and the average range value of personal lighting Zmfw in the corresponding monitoring area in the second data set, and after dimensionless processing, calculate the second light interference index Grzs through the following formula:
[0051]
[0052] Wherein, b6, b7 and b8 are weight coefficients of the total number of anglers Cdzs, the average brightness of personal lighting equipment PJld and the average range value of personal lighting Zmfw, respectively, and C4 is represented as the fourth correction constant;
[0053] The first light attenuation index SJzs and the second light interference index Grzs in the same monitoring zone are associated with each other through the following formula to obtain the light adjustment index Tszs in the corresponding monitoring zone:
[0054] Tszs=SJzs*γ+Grzs*δ;
[0055] Wherein, γ and δ represent weight coefficients, and γ+δ=1.
[0056] Preferably, the adaptive adjustment unit includes a second evaluation module and a second strategy module;
[0057] The second evaluation module is used to preset the adjustment threshold A, and compare and analyze the light adjustment index Tszs in the corresponding monitoring zone with the preset adjustment threshold A to obtain the corresponding adjustment level, including:
[0058] When the light adjustment index Tszs is less than the preset adjustment threshold A, it means that there is no interference in the current monitoring zone and there are no anglers in the monitoring zone, and the first adjustment level is generated;
[0059] When the preset adjustment threshold A≤light adjustment index Tszs≤preset adjustment threshold A*130%, it indicates that the interference of the current monitoring partition is in the first abnormal state, and the second adjustment level is generated;
[0060] When the light adjustment index Tszs>the preset adjustment threshold A*130%, it indicates that the current monitoring partition is in the second abnormal state, and the third adjustment level is generated.
[0061] Preferably, the second strategy module is used to generate a light brightness and angle adjustment management strategy in a corresponding monitoring zone according to the corresponding adjustment level, including:
[0062] Generate a first adjustment strategy according to the first adjustment level: including adjusting the current light brightness and angle to an energy-saving mode, including reducing the current basic lighting to 500 lumens, and tilting the light upward by 5-10 degrees from the basic angle;
[0063] Generate a second adjustment strategy according to the second adjustment level: including adjusting the current light brightness and angle to an anti-glare mode, including increasing the brightness of the current basic lighting to 1000 lumens, tilting the light downward by 5-10 degrees from the basic angle, and installing a diffuse lampshade;
[0064] A third adjustment strategy is generated according to the third adjustment level: including adjusting the current light brightness and angle to the anti-reflective mode, including increasing the brightness of the current basic lighting to 1500 lumens, tilting the light 5-10 degrees sideways from the basic angle, and installing a reflector directly above the street light.
[0065] The present invention provides a smart street lamp adaptive control system, which has the following beneficial effects:
[0066] (1) The intelligent street lighting adaptive control system can collect geological slope information in the area near the dam water body in real time through the monitoring partition configuration unit and the first acquisition unit. This enables the system to accurately assess the landslide risk. The risk analysis unit uses the trained risk prediction model to construct the landslide risk ratio Hpb. This can timely warn of potential landslide risks and trigger the street light emergency flashing mode, thereby improving the safety of the area.
[0067] (2) The smart street lighting adaptive control system can monitor the location and activity data of anglers and identify possible drowning risks. This function can help to timely discover potential safety hazards. The risk analysis unit analyzes the drowning risk index Nsfx and generates a risk alarm index YJbj. When a drowning risk is detected, the system can trigger corresponding alarms and lighting adjustments to help rescuers respond to emergencies more quickly.
[0068] (3) In the intelligent street lighting adaptive control system, the light analysis unit calculates the first light attenuation index SJzs and the second light interference index Grzs. This enables the system to dynamically adjust the lighting to compensate for the interference caused by the reflection of the water surface. By calculating the light adjustment index Tszs, the system can optimize the brightness and angle of the light, reduce the problem of uneven light distribution or glare, and thus improve the overall lighting effect and the safety of the area. The adaptive adjustment unit compares and analyzes the light adjustment index Tszs with the preset adjustment threshold A, and automatically adjusts the brightness and angle of the light. This adaptive control capability can adjust the lighting strategy according to the actual environmental changes, thereby improving the intelligence and adaptability of the system. The system generates different adjustment levels according to the different levels of the light adjustment index Tszs, thereby achieving a dynamic response to light interference and ensuring more flexible and efficient lighting management. By setting different adjustment levels and strategies, the system can accurately adjust the lighting settings according to the actual situation, improve the lighting quality, and avoid unnecessary waste of resources. When the interference is small or there are no anglers in the monitoring area, by reducing the brightness and adjusting the angle to energy-saving mode, energy can be effectively saved while maintaining sufficient lighting effects. In the case of abnormal interference, by increasing the brightness, adjusting the angle and installing a diffuse lampshade, glare can be effectively reduced, visual comfort can be improved, and eyesight can be protected. In the case of large interference or abnormal conditions, by increasing the brightness, adjusting the angle and installing a reflector, the reflection problem of light can be effectively reduced to ensure the stability and comfort of the lighting effect. Through appropriate lighting adjustment strategies, the system can ensure the safety of the night environment and avoid safety hazards caused by light problems, such as preventing light from interfering with anglers or causing blind spots. In the case of less interference, reduce the lighting brightness and adjust the angle to energy-saving mode to effectively reduce energy consumption. On the contrary, in the case of large interference, ensure sufficient lighting by increasing the brightness to achieve the purpose of optimizing energy use. BRIEF DESCRIPTION OF THE DRAWINGS
[0069] Figure 1 This is a schematic diagram of the block diagram process structure of the intelligent street lamp adaptive control system of the present invention. DETAILED DESCRIPTION
[0070] 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.
[0071] Example 1: The present invention provides a smart street lighting adaptive control system. Figure 1 , including a monitoring partition configuration unit, a first acquisition unit, a second acquisition unit, a risk analysis unit, a light analysis unit and an adaptive adjustment unit;
[0072] The monitoring partition configuration unit is used to collect several street lamp positions, and pre-select the area beside the dam water body where the street lamp position is located, and divide the area beside the dam water body into several monitoring partitions, ensuring that each monitoring partition includes at least one street lamp, and setting monitoring points in several monitoring partitions;
[0073] The first acquisition unit is used to collect geological slope information and angler activity data beside the water body in several monitoring zones to establish a first data set; the second acquisition unit is used to monitor environmental information and related lighting information in the corresponding monitoring zones to establish a second data set;
[0074] The risk analysis unit is used to construct a landslide risk ratio Hpb and a drowning risk index Nsfx through a trained risk prediction model based on the geological slope information next to the water body collected by the first collection unit and the angler activity data, and associate the landslide risk ratio Hpb with the drowning risk index Nsfx, obtain a risk alarm index YJbj, evaluate the risk alarm index YJbj, obtain a corresponding risk level, and generate a corresponding street lamp emergency flashing mode according to the corresponding risk level;
[0075] The light analysis unit is used to extract the environmental information and related lighting information features in the second data set through the trained light prediction model, so as to obtain the basic brightness of the street lamp Ld, the water surface reflection value Sfg, the road surface water film thickness smhd, the average water level rise value Swz and the farthest distance of the angler zyh, and deeply calculate and obtain the first light attenuation index SJzs; and perform feature extraction on the related lighting information in the second data set to respectively obtain the total number of anglers Cdzs, the average brightness of personal lighting equipment PJld and the average range value of personal lighting Zmfw in the corresponding monitoring area, and calculate and obtain the second light interference index Grzs; and associate the first light attenuation index SJzs with the second light interference index Grzs in the same monitoring area, and fit and obtain the light adjustment index Tszs in the corresponding monitoring area;
[0076] The adaptive adjustment unit is used to compare and analyze the light adjustment index Tszs in the corresponding monitoring zone with the preset adjustment threshold A to obtain the corresponding adjustment level, so as to generate the light brightness and angle adjustment management strategy in the corresponding monitoring zone.
[0077] In this embodiment, by monitoring the partition configuration unit and the first acquisition unit, the system can collect geological slope information in the area near the dam water body in real time. This enables the system to accurately assess the landslide risk. The risk analysis unit uses the trained risk prediction model to construct the landslide risk ratio Hpb. This can timely warn of potential landslide risks and trigger the emergency flashing mode of street lights, thereby improving the safety of the area.
[0078] The system can monitor the angler's location and activity data to identify possible drowning risks. This function can help to promptly identify potential safety hazards. The risk analysis unit analyzes the drowning risk index Nsfx and generates a risk alarm index YJbj. When a drowning risk is detected, the system can trigger corresponding alarms and lighting adjustments to help rescuers respond to emergencies more quickly.
[0079] The light analysis unit calculates the first light attenuation index SJzs and the second light interference index Grzs. This enables the system to dynamically adjust the lighting to compensate for the interference caused by the reflection of the water surface. By calculating the light adjustment index Tszs, the system can optimize the brightness and angle of the light, reduce the problem of uneven light distribution or glare, thereby improving the overall lighting effect and the safety of the area. The adaptive adjustment unit compares and analyzes the light adjustment index Tszs with the preset adjustment threshold A, and automatically adjusts the brightness and angle of the light. This adaptive control capability can adjust the lighting strategy according to actual environmental changes, improving the intelligence and adaptability of the system.
[0080] Example 2: This example is a detailed explanation of Example 1. Figure 1 ,The monitoring partition configuration unit includes a street lamp location acquisition module and a marking module;
[0081] The street light location acquisition module is used to use GPS positioning technology to collect the latitude and longitude coordinates of each street light, and collect the street light installation height, angle and illumination range information, draw a three-dimensional model of the street light network through SAD modeling, add roads, dams, water bodies, green vegetation and slope facilities, and assign a unique number to each street light through the marking module, and mark them as: D1, D2,..., Dn, where n represents the number of street lights.
[0082] In this embodiment, the installation height and illumination range information of the street lamps are collected at the same time, so that the system can fully understand the actual working conditions of each street lamp, so as to more accurately adjust the lighting and assess the risks. Through the SAD modeling technology, the system can establish a three-dimensional model of the street lamp network including roads, dams, water bodies, green vegetation and slope facilities. This comprehensive three-dimensional modeling can better simulate the various elements and relationships in the actual environment, and provide a three-dimensional perspective for risk assessment and lighting adjustment. The marking module assigns a unique number to each street lamp (such as D1, D2, ..., Dn), which enables each street lamp to be clearly identified in the system. The unique number not only facilitates subsequent data management and analysis, but also helps to quickly locate and deal with problems when they arise.
[0083] Example 3: This example is a detailed explanation of Example 1. Figure 1 ,The first data set includes: the slope value S from the dam to the water body, the real-time precipitation JsL, the soil density Trmd, the vegetation coverage V, the straight-line distance D between the angler and the edge of the water body, and the number of safety facilities AQss;
[0084] The second data set includes: water depth W, water flow velocity SlSD, basic brightness of street lamps Ld, water surface reflection value Sfg, road surface water film thickness smhd, average water level rise value Swz, farthest distance of anglers zyh, total number of anglers Cdzs, average brightness of personal lighting equipment PJld and average range value of personal lighting Zmfw.
[0085] The slope value S from the dam to the water body is obtained by collecting the terrain slope through the tilt sensor; the real-time precipitation JsL is obtained by collecting the rain gauge installed on the street lamp; the soil density Trmd is obtained by collecting the soil density meter; the vegetation coverage rate V is obtained by installing a video monitor on the street lamp, shooting the video and identifying the vegetation coverage area of the monitoring area through image recognition technology; the straight-line distance D between the angler and the edge of the water body is obtained by installing a video monitor on the street lamp, shooting the video and identifying the straight-line distance characteristics between each angler and the edge of the water body in the monitoring area through image recognition technology and tracking the position changes of each angler to calculate and obtain; the number of safety facilities AQss is obtained by collecting and recording the number of safety facilities in each monitoring area;
[0086] The water depth W is collected and obtained by installing an ultrasonic water depth sensor at the edge of the water body; the water flow velocity SlSD is measured and obtained by installing a water flow velocity sensor in the water body; the basic brightness of the street lamp Ld is measured and obtained by installing it on the street lamp pole; the water surface reflection value Sfg is measured and obtained by a light reflection sensor; the road surface water film thickness smhd is measured and obtained by a road surface slipperiness sensor; the average water level rise value Swz is measured and obtained by a water level sensor; the farthest distance of the angler zyh is obtained by installing a video monitor on the street lamp, shooting the video and using image recognition technology to identify the straight-line distance characteristics between each angler in the monitoring area and the edge of the water body and track the position changes of each angler, and identify the distance between the position of the farthest angler and the current street lamp; the total number of anglers Cdzs is obtained by shooting the fishing area with a video monitor and using image recognition technology to count the total number of anglers in the monitoring area; the average brightness of personal lighting equipment PJld and the average range value of personal lighting Zmfw are both collected and obtained by light sensors and distance sensors.
[0087] Example 4: This example is a detailed explanation of Example 1. Figure 1 , the risk analysis unit includes a risk model building module, a first calculation module, an association module, a first evaluation module and a first strategy module;
[0088] The risk model building module is used to collect historical event data, including landslides and drowning events, and to label the historical event data with binary classification labels; after extracting features from the first data set, neural network and deep learning network technologies are selected to build a risk prediction model, and after training, the risk prediction model is deployed into the system;
[0089] The first calculation module is used to perform in-depth analysis based on the first data set to calculate and obtain the landslide risk ratio Hpb and the drowning risk index Nsfx;
[0090] The associated module is used to generate the risk alarm index YJbj by using the following associated formula to convert the corresponding monitoring area landslide risk ratio Hpb and drowning risk index Nsfx:
[0091] YJbj=Hpb*α+Xsfx*β;
[0092] Wherein, α and β represent weight coefficients, which are adjusted and set by the user, 0<α<1, 0<β<1, and α+β=1.
[0093] The steps for obtaining the landslide risk ratio Hpb and drowning risk index Nsfx are as follows:
[0094] S11, extract the slope value S from the dam to the water body, the real-time precipitation JsL, the soil density Trmd and the vegetation coverage rate V of each monitoring area in the first data set, and perform dimensionless processing;
[0095] S12. The landslide risk ratio Hpb is calculated by the following formula:
[0096]
[0097] Where Hpb i represents the landslide risk ratio of the ith monitoring area, S i is the slope value from the dam to the water body in the i-th monitoring area, JsL i It is expressed as the real-time precipitation of the ith monitoring area, Trmd i It is expressed as the soil density in the i-th monitoring area, V i It is expressed as the vegetation coverage rate in the i-th monitoring area, a1, a2, a3 and a4 are weight coefficients, which are adjusted and set by the user, 0<a1<, 0<a2<1, 0<a3<1, 0<a4<1, and a1+a2+a3+a4=1, C1 is expressed as the first correction constant;
[0098] S13, extracting the behavior characteristics of the angler and the location and quantity characteristics of the safety facilities from the video image in the first data set to obtain: the straight-line distance D between the angler and the edge of the water body and the number of safety facilities AQss;
[0099] Extract water depth and water flow velocity characteristics from the second data set to obtain: water depth W and water flow velocity SlSD; and perform dimensionless processing on the above data;
[0100] S14. The drowning risk index Nsfx is calculated using the following formula:
[0101]
[0102] Where Nsfx i represents the drowning risk index of the ith monitoring area, D ij is the straight-line distance between the jth angler in the ith monitoring area and the edge of the water body, W ij represents the water depth within the 10-meter diameter area where the jth angler in the ith monitoring area is located, SlSD ij AQss represents the water flow velocity within the 10-meter diameter area where the jth angler in the ith monitoring zone is located. ij It indicates the number of safety facilities within a 10-meter diameter area where the j-th angler in the ith monitoring zone is located; safety facilities include guardrails, life-saving equipment, rescue equipment, warning signs and anti-slip facilities; a5, a6, a7 and a8 are all weight coefficients, which are adjusted and set by the user, 0<a5<1, 0<a6<1, 0<a7<1, 0<a8<1, and a5+a6+a7+a8=1, C2 is represented as the second correction constant.
[0103] In this embodiment, by dimensionlessly processing the slope value from the dam to the water body, the real-time precipitation, the soil density and the vegetation coverage, and combining the weight coefficient and the correction constant, the landslide risk ratio Hpb can provide an accurate landslide risk assessment. This accurate risk prediction helps to identify potential landslide areas in advance, take preventive measures in time, and reduce the safety hazards caused by landslides.
[0104] By extracting data such as angler behavior characteristics, the straight-line distance between anglers and the edge of the water body, the number of safety facilities, water depth and water flow speed, and combining weight coefficients and correction constants, the drowning risk index Nsfx can effectively assess the drowning risk. This assessment helps to monitor the safety of anglers in real time, issue alarms in time, and reduce the occurrence of drowning incidents.
[0105] Example 5: This example is a specific explanation of Example 4. Please refer to Figure 1 The first assessment module is used to preset a first risk threshold value X1 and a second risk threshold value X2, the first risk threshold value X1 < the second risk threshold value X2, and compare and evaluate the risk alarm index YJbj with the first risk threshold value X1 and the second risk threshold value X2 to obtain the following corresponding risk levels, including:
[0106] When the risk alarm index YJbj is less than the first risk threshold X1, it means that the current monitoring area has no risk and the first safety level is generated;
[0107] When the first risk threshold X1≤risk alarm index YJbj≤second risk threshold X2, it indicates that there is a landslide risk in the current monitoring area, and the second risk level is generated;
[0108] When the risk alarm index YJbj> the second risk threshold X2, it means that there is a drowning risk in the current monitoring area, and the third risk level is generated;
[0109] The first strategy module is used to generate corresponding emergency strategies according to corresponding risk levels, including:
[0110] Receiving a first security level, generating a first strategy: maintaining normal lighting of current street lamps;
[0111] A second risk level is received and a second strategy is generated: the street light flashes slowly in white, once per second, and a warning sound is added to remind anglers to pay attention to ramp safety;
[0112] The third risk level is received and the third strategy is generated: the street light flashes red quickly, once every half a second, and the emergency broadcast is triggered to broadcast the high-risk area, notifying anglers to evacuate immediately.
[0113] In this embodiment, the system can automatically adjust the emergency strategy according to different risk levels. This dynamic management mechanism ensures that when various risk situations occur, the system can quickly adapt and take corresponding lighting and alarm measures, thereby improving the management efficiency of environmental safety. By adjusting the flashing mode and color of street lights in real time, the system can effectively enhance the risk awareness of anglers and other residents. Rapid red flashing and alarm broadcasts can quickly attract attention and reduce the probability of accidents. When there is no obvious risk in the monitoring area, the system maintains normal lighting to ensure that residents' daily activities are not affected. This reasonable lighting management improves the user's comfort and sense of security.
[0114] Example 6: This example is a specific explanation of Example 1. Please refer to Figure 1 , the light analysis unit includes a water level prediction module, a second calculation module and a third calculation module;
[0115] The water level prediction module is used to collect and obtain several groups of water level values through water level sensors, sort them, and obtain the real-time water level value SW at the previous moment based on the linear regression method. N+1 The predicted water level value SW at the next moment is obtained by using the typical water level change curve N-1 ;
[0116] The real-time water level value SW of the previous moment N+1 And the predicted water level value SW at the next moment N-1 The water level rise prediction value ΔSw is obtained by the following formula:
[0117] ΔSw=SW N+1 -SW N-1 ;
[0118] By analyzing historical data, the correction factor F is determined, and the water level rise prediction value is corrected by the correction factor F. The average water level rise value Swz is obtained through the following correction formula;
[0119]
[0120] Where N represents the total data points at a given moment.
[0121] In this embodiment, the correction factor F in the correction formula is used to smooth the predicted data, making the average water level rise value Swz more representative and reliable. This smoothing process helps to reduce fluctuations in the prediction and improve the stability of the data. The accurate average water level rise value Swz can provide a reliable data basis for the light analysis unit, thereby optimizing the brightness adjustment of the street lamp. Especially in the case where the water level rise may affect the reflection of light, this optimization can ensure the stability and effectiveness of the lighting effect.
[0122] Please refer to Figure 1The second calculation module is used to select neural network and deep learning network technology, and after the light prediction model is established and trained and evaluated, the light prediction model is deployed into the system; and the basic brightness of the street lamp Ld, the water surface reflection value Sfg, the road surface water film thickness smhd, the average water level rise value Swz and the farthest distance of the angler zyh in the second data set are extracted, and after dimensionless processing, the first light attenuation index SJzs is calculated by the following formula:
[0123]
[0124] Wherein, b1, b2, b3, b4 and b5 are weight coefficients of the basic brightness of street lamp Ld, the water surface reflection value Sfg, the road surface water film thickness smhd, the average water level rise value Swz and the farthest distance of the angler zyh, respectively, which are adjusted and set by the user, 0<b1<1, 0<b2<1, 0<b3<1, 0<b4<1, 0<b5<1, and b1+b2+b3+b4+b5=1, C3 is represented as the third correction constant;
[0125] The third calculation module is used to extract the total number of fishermen Cdzs, the average brightness of personal lighting equipment PJld and the average range value of personal lighting Zmfw in the corresponding monitoring area in the second data set, and after dimensionless processing, calculate the second light interference index Grzs through the following formula:
[0126]
[0127] Wherein, b6, b7 and b8 are weight coefficients of the total number of anglers Cdzs, the average brightness of personal lighting equipment PJld and the average range value of personal lighting Zmfw, respectively, which are adjusted and set by the user, 0<b6<1, 0<b7<1, 0<b8<1, and b6+b7+b8=1, and C4 is represented as the fourth correction constant;
[0128] The first light attenuation index SJzs and the second light interference index Grzs in the same monitoring zone are associated with each other through the following formula to obtain the light adjustment index Tszs in the corresponding monitoring zone:
[0129] Tszs=SJzs*γ+Grzs*δ;
[0130] Wherein, γ and δ represent weight coefficients, which are adjusted and set by the user, 0<γ<1, 0<δ<1, and γ+δ=1.
[0131] In this embodiment, by considering the basic brightness of the street lamp Ld, the water surface reflection value Sfg, the road surface water film thickness smhd, the average water level rise value Swz and the farthest distance of the angler zyh, the calculated first light attenuation index SJzs can accurately evaluate the impact of the environment on the light, thereby ensuring the effectiveness of the lighting effect. Effectively identify and reduce the interference of water surface reflection and water film thickness on light, thereby reducing light loss and ensuring that the light can cover the target area more effectively. Considering the total number of anglers Cdzs, the average brightness of personal lighting equipment PJld and the average range value of personal lighting in the corresponding monitoring area, the calculated second light interference index Grzs can accurately evaluate the interference from personal lighting equipment and effectively manage the interference factors of light in the area. The first light attenuation index SJzs and the second light interference index Grzs are associated, and the calculated light adjustment index Tszs can provide a comprehensive lighting adjustment strategy to ensure that the lighting system can operate effectively under various environmental conditions.
[0132] Example 7: This example is a detailed explanation of Example 1. Figure 1 , the adaptive adjustment unit includes a second evaluation module and a second strategy module;
[0133] The second evaluation module is used to preset the adjustment threshold A, and compare and analyze the light adjustment index Tszs in the corresponding monitoring zone with the preset adjustment threshold A to obtain the corresponding adjustment level, including:
[0134] When the light adjustment index Tszs is less than the preset adjustment threshold A, it means that there is no interference in the current monitoring zone and there are no anglers in the monitoring zone, and the first adjustment level is generated;
[0135] When the preset adjustment threshold A≤light adjustment index Tszs≤preset adjustment threshold A*130%, it indicates that the interference of the current monitoring partition is in the first abnormal state, and the second adjustment level is generated;
[0136] When the light adjustment index Tszs>the preset adjustment threshold A*130%, it indicates that the current monitoring partition is in the second abnormal state, and the third adjustment level is generated.
[0137] The second strategy module is used to generate a light brightness and angle adjustment management strategy in the corresponding monitoring zone according to the corresponding adjustment level, including: generating a first adjustment strategy according to the first adjustment level: including adjusting the current light brightness and angle to an energy-saving mode, including reducing the current light basic lighting to 500 lumens, and tilting the light upward from the basic angle by 5-10 degrees;
[0138] Generate a second adjustment strategy according to the second adjustment level: including adjusting the current light brightness and angle to an anti-glare mode, including increasing the brightness of the current basic lighting to 1000 lumens, tilting the light downward by 5-10 degrees from the basic angle, and installing a diffuse lampshade;
[0139] A third adjustment strategy is generated according to the third adjustment level: including adjusting the current light brightness and angle to the anti-reflective mode, including increasing the brightness of the current basic lighting to 1500 lumens, tilting the light 5-10 degrees sideways from the basic angle, and installing a reflector directly above the street light.
[0140] In this embodiment, the system generates different adjustment levels according to different levels of the light adjustment index Tszs, thereby achieving a dynamic response to light interference and ensuring that light management is more flexible and efficient. By setting different adjustment levels and strategies, the system can accurately adjust the light settings according to the actual situation, improve the lighting quality, and avoid unnecessary waste of resources. When the interference is small or there are no anglers in the monitoring partition, by reducing the brightness and adjusting the angle to the energy-saving mode, energy can be effectively saved while maintaining sufficient lighting effects. In the case of abnormal interference, by increasing the brightness, adjusting the angle and installing a diffuse lampshade, glare can be effectively reduced, visual comfort can be improved, and eyesight can be protected. In the case of large interference or abnormal conditions, by increasing the brightness, adjusting the angle and installing a reflector, the reflection problem of light can be effectively reduced, and the stability and comfort of the lighting effect can be ensured. Through appropriate light adjustment strategies, the system can ensure the safety of the night environment and avoid safety hazards caused by light problems, such as preventing light from interfering with anglers or causing blind spots. In the case of small interference, reducing the lighting brightness and adjusting the angle to the energy-saving mode can effectively reduce energy consumption. On the contrary, in the case of large interference, sufficient lighting is ensured by increasing the brightness to achieve the purpose of optimizing energy use.
[0141] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.
[0142] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above are only preferred specific implementations of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.
Claims
1. Intelligent street lighting adaptive control system, characterized by: It includes a monitoring partition configuration unit, a first collection unit, a second collection unit, a risk analysis unit, a light analysis unit and an adaptive adjustment unit; The monitoring partition configuration unit is used to collect several street lamp positions, and pre-select the area beside the dam water body where the street lamp position is located, and divide the area beside the dam water body into several monitoring partitions, ensuring that each monitoring partition includes at least one street lamp, and setting monitoring points in several monitoring partitions; The first acquisition unit is used to collect geological slope information and angler activity data beside the water body in several monitoring zones to establish a first data set; the second acquisition unit is used to monitor environmental information and related lighting information in the corresponding monitoring zones to establish a second data set; The risk analysis unit is used to construct a landslide risk ratio Hpb and a drowning risk index Nsfx through a trained risk prediction model based on the geological slope information next to the water body collected by the first collection unit and the angler activity data, and associate the landslide risk ratio Hpb with the drowning risk index Nsfx, obtain a risk alarm index YJbj, evaluate the risk alarm index YJbj, obtain a corresponding risk level, and generate a corresponding street lamp emergency flashing mode according to the corresponding risk level; The light analysis unit is used to extract the environmental information and related lighting information features in the second data set through the trained light prediction model to obtain the basic brightness of the street lamp Ld, the water surface reflection value Sfg, the road surface water film thickness smhd, the average water level rise value Swz and the farthest distance of the angler zyh, and deeply calculate to obtain the first light attenuation index SJzs; and extract the features of the related lighting information in the second data set to respectively obtain the total number of anglers Cdzs, the average brightness of personal lighting equipment PJld and the average range value of personal lighting Zmfw in the corresponding monitoring area, and calculate to obtain the second light interference index Grzs; and associate the first light attenuation index SJzs with the second light interference index Grzs in the same monitoring area, and fit to obtain the light adjustment index Tszs in the corresponding monitoring area; The adaptive adjustment unit is used to compare and analyze the light adjustment index Tszs in the corresponding monitoring zone with the preset adjustment threshold A to obtain the corresponding adjustment level, so as to generate the light brightness and angle adjustment management strategy in the corresponding monitoring zone.
2. The intelligent street lighting adaptive control system according to claim 1 is characterized in that: The monitoring partition configuration unit includes a street lamp position acquisition module and a marking module; The street lamp position acquisition module is used to use GPS positioning technology to collect the latitude and longitude coordinates of each street lamp, and collect the installation height, angle and illumination range information of the street lamp, draw a three-dimensional model of the street lamp network through SAD modeling, add roads, dams, water bodies, green vegetation and slope facilities, and assign a unique number to each street lamp through the marking module, and mark them as: D1, D2,..., Dn, where n represents the number of street lamps.
3. The intelligent street lighting adaptive control system according to claim 1 is characterized in that: The first data set includes: the slope value S from the dam to the water body, the real-time precipitation JsL, the soil density Trmd, the vegetation coverage rate V, the straight-line distance D between the angler and the edge of the water body, and the number of safety facilities AQss; The second data set includes: water depth W, water flow velocity SlSD, basic brightness of street lamps Ld, water surface reflection value Sfg, road surface water film thickness smhd, average water level rise value Swz, farthest distance of anglers zyh, total number of anglers Cdzs, average brightness of personal lighting equipment PJld and average range value of personal lighting Zmfw.
4. The intelligent street lighting adaptive control system according to claim 1 is characterized in that: The risk analysis unit includes a risk model building module, a first calculation module, an association module, a first evaluation module and a first strategy module; The risk model building module is used to collect historical event data, including landslide events and drowning events, and to label the historical event data with binary classification labels; and after extracting features from the first data set, a neural network and deep learning network technology are selected to establish a risk prediction model and after training, the risk prediction model is deployed into the system; The first calculation module is used to perform in-depth analysis based on the first data set to calculate and obtain the landslide risk ratio Hpb and the drowning risk index Nsfx; The association module is used to generate a risk alarm index YJbj by using the following association formula to calculate the landslide risk ratio Hpb and drowning risk index Nsfx of the corresponding monitoring area: YJbj=Hpb*α+Nsfx*β; Wherein, α and β represent weight coefficients, and α+β=1.
5. The intelligent street lighting adaptive control system according to claim 1 is characterized in that: The steps for obtaining the landslide risk ratio Hpb and the drowning risk index Nsfx are as follows: S11, extract the slope value S from the dam to the water body, the real-time precipitation JsL, the soil density Trmd and the vegetation coverage rate V of each monitoring area in the first data set, and perform dimensionless processing; S12. The landslide risk ratio Hpb is calculated by the following formula: Where Hpb i represents the landslide risk ratio of the ith monitoring area, S i is the slope value from the dam to the water body in the i-th monitoring area, JsL i It is expressed as the real-time precipitation of the ith monitoring area, Trmd i It is expressed as the soil density in the i-th monitoring area, V i It is expressed as the vegetation coverage rate in the i-th monitoring area, a1, a2, a3 and a4 are all weight coefficients, and C1 is expressed as the first correction constant; S13, extracting the behavior characteristics of the angler and the location and quantity characteristics of the safety facilities from the video image in the first data set to obtain: the straight-line distance D between the angler and the edge of the water body and the number of safety facilities AQss; Extract water depth and water flow velocity characteristics from the second data set to obtain: water depth W and water flow velocity SlSD; and perform dimensionless processing on the above data; S14. The drowning risk index Nsfx is calculated by the following formula: Where Nsfx i represents the drowning risk index of the ith monitoring area, D ij is the straight-line distance between the jth angler in the ith monitoring area and the edge of the water body, W ij represents the water depth within the 10-meter diameter area where the jth angler in the ith monitoring area is located, SlSD ij AQss represents the water flow velocity within the 10-meter diameter area where the jth angler in the ith monitoring zone is located. ij It indicates the number of safety facilities within a 10-meter diameter area where the j-th angler in the ith monitoring zone is located; safety facilities include guardrails, life-saving equipment, rescue equipment, warning signs and anti-slip facilities; a5, a6, a7 and a8 are all weight coefficients, and C2 is represented as the second correction constant.
6. The intelligent street lighting adaptive control system according to claim 4 is characterized in that: The first assessment module is used to preset a first risk threshold value X1 and a second risk threshold value X2, wherein the first risk threshold value X1 is less than the second risk threshold value X2, and compare and evaluate the risk alarm index YJbj with the first risk threshold value X1 and the second risk threshold value X2 to obtain the following corresponding risk levels, including: When the risk alarm index YJbj is less than the first risk threshold X1, it means that the current monitoring area has no risk and the first safety level is generated; When the first risk threshold X1≤risk alarm index YJbj≤second risk threshold X2, it indicates that there is a landslide risk in the current monitoring area, and the second risk level is generated; When the risk alarm index YJbj> the second risk threshold X2, it means that there is a drowning risk in the current monitoring area, and the third risk level is generated; The first strategy module is used to generate a corresponding emergency strategy according to the corresponding risk level, including: Receiving a first security level, generating a first strategy: maintaining normal lighting of current street lamps; A second risk level is received and a second strategy is generated: the street light flashes slowly in white, once per second, and a warning sound is added to remind anglers to pay attention to ramp safety; The third risk level is received and the third strategy is generated: the street light flashes red quickly, once every half a second, and the emergency broadcast is triggered to broadcast the high-risk area, notifying anglers to evacuate immediately.
7. The intelligent street lighting adaptive control system according to claim 1 is characterized in that: The light analysis unit includes a water level prediction module, a second calculation module and a third calculation module; The water level prediction module is used to collect and obtain several groups of water level values through the water level sensor, sort them, and obtain the real-time water level value SW at the previous moment according to the linear regression method. N+1 The predicted water level value SW at the next moment is obtained by using the typical water level change curve N-1 ; The real-time water level value SW of the previous moment N+1 And the predicted water level value SW at the next moment N-1 The water level rise prediction value ΔSw is obtained by the following formula: ΔSw=SW N+1 -SW N-1 ; By analyzing historical data, the correction factor F is determined, and the water level rise prediction value is corrected by the correction factor F. The average water level rise value Swz is obtained through the following correction formula; Where N represents the total data points at a given moment.
8. The intelligent street lighting adaptive control system according to claim 7 is characterized in that: The second computing module is used to select a neural network and a deep learning network technology, establish a light prediction model, train and evaluate it, and then deploy the light prediction model into the system; The basic brightness of street lamps Ld, water surface reflection value Sfg, road surface water film thickness smhd, average water level rise value Swz and the farthest distance of anglers zyh in the second data set are extracted and dimensionless processed to obtain the first light attenuation index SJzs by the following formula: Wherein, b1, b2, b3, b4 and b5 are weight coefficients of the basic brightness of street lamp Ld, the water surface reflection value Sfg, the road surface water film thickness smhd, the average water level rise value Swz and the farthest distance of the angler zyh, respectively, and C3 is represented as the third correction constant; The third calculation module is used to extract the total number of fishermen Cdzs, the average brightness of personal lighting equipment PJld and the average range value of personal lighting Zmfw in the corresponding monitoring area in the second data set, and after dimensionless processing, calculate the second light interference index Grzs by the following formula: Wherein, b6, b7 and b8 are weight coefficients of the total number of anglers Cdzs, the average brightness of personal lighting equipment PJld and the average range value of personal lighting Zmfw, respectively, and C4 is represented as the fourth correction constant; The first light attenuation index SJzs and the second light interference index Grzs in the same monitoring zone are associated with each other through the following formula to obtain the light adjustment index Tszs in the corresponding monitoring zone: Tszs=SJzs*γ+Grzs*δ; Wherein, γ and δ represent weight coefficients, and γ+δ=1.
9. The intelligent street lighting adaptive control system according to claim 8 is characterized in that: The adaptive adjustment unit includes a second evaluation module and a second strategy module; The second evaluation module is used to preset the adjustment threshold A, and compare and analyze the light adjustment index Tszs in the corresponding monitoring zone with the preset adjustment threshold A to obtain the corresponding adjustment level, including: When the light adjustment index Tszs is less than the preset adjustment threshold A, it means that there is no interference in the current monitoring zone and there are no anglers in the monitoring zone, and the first adjustment level is generated; When the preset adjustment threshold A≤light adjustment index Tszs≤preset adjustment threshold A*130%, it indicates that the interference of the current monitoring partition is in the first abnormal state, and the second adjustment level is generated; When the light adjustment index Tszs>the preset adjustment threshold A*130%, it indicates that the current monitoring partition is in the second abnormal state, and the third adjustment level is generated.
10. The intelligent street lighting adaptive control system according to claim 9, characterized in that: The second strategy module is used to generate a light brightness and angle adjustment management strategy in a corresponding monitoring zone according to the corresponding adjustment level, including: Generate a first adjustment strategy according to the first adjustment level: including adjusting the current light brightness and angle to an energy-saving mode, including reducing the current basic lighting to 500 lumens, and tilting the light upward by 5-10 degrees from the basic angle; Generate a second adjustment strategy according to the second adjustment level: including adjusting the current light brightness and angle to an anti-glare mode, including increasing the brightness of the current basic lighting to 1000 lumens, tilting the light downward by 5-10 degrees from the basic angle, and installing a diffuse lampshade; A third adjustment strategy is generated according to the third adjustment level: including adjusting the current light brightness and angle to the anti-reflective mode, including increasing the brightness of the current basic lighting to 1500 lumens, tilting the light 5-10 degrees sideways from the basic angle, and installing a reflector directly above the street light.
