A tunnel dynamic dimming method and system based on the Internet of Things

Abstract

This invention discloses a tunnel dynamic dimming method and system based on the Internet of Things (IoT), belonging to the field of dynamic dimming. The method comprises: an edge gateway receives sensor data in the tunnel and processes the sensor data using a multi-source heterogeneous sensing algorithm built into the edge gateway; the edge gateway transmits the received sensor data and the dimming illumination requirements calculated by the multi-source heterogeneous sensing algorithm to the cloud; an adaptive dimming algorithm generates a dimming strategy based on the sensor data and the dimming illumination requirements; and the dimming strategy generated by the adaptive dimming algorithm is distributed to a dimming control module in the tunnel. This invention can dynamically adjust the lighting according to the real-time environment in the tunnel, avoiding energy waste or insufficient lighting.

Description

Technical Field

[0001] The present invention relates to the field of dynamic dimming, and in particular to a tunnel dynamic dimming method and system based on the Internet of Things. Background Art

[0002] With the development of society, the number of highway tunnels continues to increase. Tunnel lighting systems play a vital role in tunnel traffic safety. Existing tunnel lighting control systems have several problems. They cannot dynamically adjust lighting according to real-time environmental changes, resulting in energy waste or insufficient lighting. They cannot simultaneously meet energy consumption, safety, and visual comfort requirements, and lack adaptability to complex environments such as haze. Summary of the Invention

[0003] One of the purposes of the present invention is to provide a tunnel dynamic dimming method based on the Internet of Things to solve the problem that the existing technology cannot simultaneously meet the energy consumption, safety and visual comfort requirements and the lighting control lacks comprehensiveness.

[0004] The present invention is implemented through the following technical solution, a tunnel dynamic dimming method based on the Internet of Things, including the following steps: S100, the edge gateway receives sensor data in the tunnel, and processes the sensor data through a multi-source heterogeneous perception algorithm built into the edge gateway; S200, the edge gateway sends the received sensor data and the dimming illumination requirements calculated by the multi-source heterogeneous perception algorithm to the cloud, and the adaptive dimming algorithm in the cloud generates a dimming strategy based on the sensor data and the dimming illumination requirements; the adaptive dimming algorithm includes a dynamic scene classification mechanism, an energy efficiency priority model, and a safety priority model; the dynamic scene classification mechanism performs scene classification, selects different priority modules according to different scenes, and different priority models generate different dimming strategies; S300, the dimming strategy generated by the adaptive dimming algorithm is sent to the dimming control module in the tunnel, and the dimming control module adjusts the tunnel lamps according to the dimming strategy.

[0005] Furthermore, the sensors in the tunnel include core sensors and auxiliary sensors. The core sensor is a distributed fiber optic light intensity sensor; the auxiliary sensors include: millimeter wave radar array, thermal imaging sensor, temperature / humidity sensor, light sensor and image sensor.

[0006] Furthermore, the multi-source heterogeneous perception algorithm includes: S110, extracting and integrating the input data of the sensor to obtain measured light illuminance data, visual demand illuminance data and haze attenuation factor; S120, defining a dynamic weight parameter based on the measured light illuminance data, visual demand illuminance data and haze attenuation factor, the dynamic weight parameter being a parameter group Ω=(α, β, γ) composed of multiple dynamic weights, and the role of each parameter is as follows: α determines the importance of the measured light illuminance data in the final dimming illuminance, β is used to adjust the importance of the visual demand illuminance in the final dimming, and γ is used to adjust the importance of the attenuation factor of the influence of haze on illumination; S130, combining the measured light illuminance data, visual demand illuminance data, haze attenuation factor and dynamic weight parameter into a final dimming illuminance requirement by weighted summation, and the dimming illuminance requirement is expressed by the following formula:

[0007] ,

[0008] ,

[0009] in, is the measured illuminance data, is the visual requirement illumination data, is the haze attenuation factor, is the attenuation factor, which is used to characterize the impact of haze contrast. z is the haze transmittance attenuation weight coefficient.

[0010] Furthermore, the measured illuminance data is calculated according to the following formula:

[0011] ,in, is the sum of all light sensors, For a single light sensor, is the raw data of the i-th sensor, is the sensor noise reduction residual, is the geometric attenuation weight; the visual required illumination data is calculated according to the following formula:

[0012] ,in, is the contrast sensitivity factor, is the average vehicle speed, is the road speed limit, is the exponential weight of the relationship between speed and visual required illumination; the haze attenuation factor is calculated according to the following formula:

[0013] ,in, is the regression coefficient obtained by training based on foggy image data, is the grayscale distribution of the thermal imaging image, is the humidity ratio.

[0014] Furthermore, the parameter group Ω=(α,β,γ) is calculated according to the following formula:

[0015] ,

[0016] in, is the weight adjustment based on the change of energy consumption gradient, is a natural constant, To adjust the rate, is the energy consumption gradient change, is the gradient change weight parameter based on visual requirements and environmental interference, is the gradient of visual illumination requirement, is the gradient of the haze attenuation factor, is the quality constraint in the form of Sigmoid activation function, SQI is the sensor signal quality index, Fault flag, 1 if the sensor fails, 0 otherwise.

[0017] Furthermore, the scene feature vector modeling is expressed as follows:

[0018] ,in, is the fog concentration change rate, which reflects the changing trend of environmental visibility; is the total kinetic energy of the vehicle within 100 meters is the required curvature of illumination along the longitudinal direction of the tunnel, is the image clarity index of the image sensor.

[0019] Furthermore, the fog concentration change rate can be calculated by the following formula:

[0020] ,in, is the fog density at time t, t is the current time, The interval is usually a fixed short time. During the scene determination process, if the fog concentration change rate exceeds a certain threshold, it means that the fog concentration is changing rapidly and the lighting brightness needs to be quickly increased or decreased to adapt to the change in visibility.

[0021] Furthermore, the total kinetic energy of the vehicle within 100 meters can be calculated using the following formula:

[0022] , where M is the total number of vehicles within a hundred-meter range, is the estimated mass of the i-th vehicle, is the speed of the i-th vehicle. During scene assessment, if the total kinetic energy of vehicles within a 100-meter radius exceeds a certain threshold, it indicates that many vehicles are traveling at high speeds. In this case, the lighting brightness should be increased to ensure a clear view for the driver and reduce the possibility of accidents. If the total kinetic energy of vehicles within a 100-meter radius is lower than a certain threshold, it indicates that the vehicles are traveling slowly, possibly due to traffic congestion or other reasons. In this case, the lighting brightness can be appropriately reduced to save energy.

[0023] Furthermore, the required curvature of the longitudinal illumination along the tunnel can be calculated by the following formula:

[0024] ,in, is the illumination requirement at position x, where x is the longitudinal position of the tunnel. During scene determination, if the curvature of the illumination requirement changes significantly, it indicates that the illumination requirements at different locations within the tunnel are changing rapidly. For example, at a sudden tunnel exit or entrance, the light changes significantly, requiring rapid adjustment of the lighting brightness. If the curvature of change is small, it indicates that the illumination requirement within the tunnel is relatively stable, and the current lighting brightness can be maintained.

[0025] Furthermore, the image clarity index can be calculated by the following formula:

[0026] , is the Laplace transform value at pixel (x, y), which represents the high-frequency component of the image; =The total number of pixels in the image. During scene determination, if the image clarity index is low, it indicates that the image quality captured by the camera is poor, possibly due to haze or other factors affecting the field of view. In this case, it is necessary to increase the lighting brightness to improve the field of view. If the image clarity index is high, the current lighting conditions are good and the current lighting brightness can be maintained or appropriately reduced to save energy.

[0027] Furthermore, the energy efficiency priority model is defined by an objective function and constraints. The objective function aims to minimize energy consumption while meeting the required illumination, which can be expressed as follows:

[0028] , where u k is the control input, k is a single moment, K is the sum of the moments k, is the actual illumination value at the kth moment, is the illumination value required at the kth moment, is the weight parameter, is the control input u at the kth moment k The corresponding energy consumption; the constraints ensure that the system complies with a series of physical and operational limitations while satisfying the objective function. The constraints include: Longitudinal gradient constraint: This constraint limits the rate of change of illumination along the longitudinal direction of the tunnel to ensure that the illumination does not change too much. The maximum allowable change rate is 15 lux per meter; transient jump constraint: , which limits the control input u k The rate of change ensures that the lighting system is adjusted smoothly without sudden and drastic changes. The maximum allowable rate of change is 10% per second; there is no glare constraint: , this constraint ensures that the illuminance ratio between the brightest and darkest areas of the lighting system at any location does not exceed 5 times to avoid glare problems.

[0029] Furthermore, the safety priority model monitors environmental conditions in real time and dynamically adjusts the RGB of tunnel lamps according to the monitored fog concentration. mix The light color ratio is used to generate a compensating light spot through the inverse Monte Carlo ray tracing algorithm to improve the illumination of the target area and compensate for the light loss caused by haze; and the illumination is forcibly increased to 1.5 times the standard value within 20 meters of the tunnel entrance section to ensure that drivers have sufficient illumination transition when entering the tunnel, avoiding discomfort and safety hazards caused by sudden illumination changes.

[0030] Further, adjust the RGB of the tunnel lamps mix The light color ratio is determined by the following formula:

[0031] , where RGB mix is the color mixing ratio of light, C f is the density of fog. f <0.3, use the first set of ratios, blue light accounts for 70%, green light accounts for 20%, and red light accounts for 10%. When the fog concentration C f When ≥0.3, the second set of ratios is used, with blue light accounting for 60%, green light accounting for 15%, and red light accounting for 25%. The adjustment strategy for the compensation spot is determined by the following formula:

[0032] ,in, is the compensation illumination at position (x, y), D is the number of samples that need to compensate illumination, is the luminous intensity distribution function of the lamp, which indicates the direction of the lamp in the tunnel The luminous intensity, is the scattering coefficient of haze, is the distance light travels in the fog.

[0033] On the other hand, the present invention provides a tunnel dynamic dimming system for the Internet of Things, which includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the tunnel dynamic dimming method for the Internet of Things as described above is implemented.

[0034] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0035] 1. The present invention can dynamically adjust the lighting according to the real-time environment, traffic flow and lighting conditions in the tunnel, avoiding the problems of energy waste or insufficient lighting.

[0036] 2. The present invention integrates multi-dimensional information such as environment, traffic flow, and illumination through a multi-source heterogeneous perception algorithm, and introduces haze attenuation factors and dynamic weight parameters, thereby improving the system's adaptability to complex environments such as haze.

[0037] 3. The present invention combines an adaptive dimming algorithm to simultaneously meet energy consumption, safety, and visual comfort requirements. By sensing traffic information such as vehicle flow and speed, it can optimize lighting according to traffic conditions and improve the safety of people driving in tunnels. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0039] Figure 1 This is a flowchart of the overall steps provided in Example 1 of the present invention.

[0040] Figure 2 This is a timing diagram of the overall steps provided in Example 1 of the present invention.

[0041] Figure 3 This is a flowchart of the multi-source heterogeneous perception algorithm provided in Example 1 of the present invention.

[0042] Figure 4 This is a timing diagram of the multi-source heterogeneous perception algorithm provided in Example 1 of the present invention.

[0043] Figure 5 This is a timing diagram of the adaptive dimming algorithm provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0045] Example 1

[0046] Existing technologies are unable to dynamically adjust lighting based on real-time environmental changes within tunnels, resulting in energy waste or insufficient lighting. They also fail to simultaneously meet energy consumption, safety, and visual comfort requirements. Lighting control systems lack comprehensiveness and adaptability to complex environments like smog, making it impossible to adjust lighting parameters based on environmental changes. Furthermore, lighting control systems lack the ability to perceive traffic information such as vehicle flow and speed, making it impossible to optimize lighting based on traffic conditions. To address these issues, this embodiment discloses an IoT-based tunnel dynamic dimming method that dynamically adjusts lighting based on the tunnel's real-time environment, vehicle flow, and lighting conditions. This solution deploys multiple types of high-precision sensors within the tunnel to collect multi-dimensional information such as the tunnel's environment, vehicle flow, and lighting. This information is then integrated and processed using a multi-source, heterogeneous sensing algorithm to determine the dimming illumination requirement. Furthermore, an adaptive dimming algorithm deployed in the cloud converts the dimming illumination requirement into an execution policy that meets energy consumption, safety, and light quality requirements. This policy is then distributed to the tunnel's dimming control module, enabling intelligent lighting control.

[0047] The method disclosed in this embodiment can dynamically adjust tunnel lighting according to the real-time environment, traffic flow and lighting conditions in the tunnel, which can not only meet the requirements of driving safety and visual comfort, but also maximize energy conservation and improve energy utilization efficiency, thereby solving the problems existing in the existing technology.

[0048] Figure 1 A flowchart showing the overall steps in this embodiment is shown. Figure 2 The timing diagram of the overall steps of this embodiment is shown. It can be seen from the diagram that this embodiment includes the following steps:

[0049] Step 1: Deploy various types of high-precision sensors in the tunnel to collect various information in the tunnel and transmit the data collected by the sensors to the edge gateway through the wireless Internet of Things.

[0050] The edge gateway has a built-in FPGA-based multi-source data processing module, which processes the data collected by sensors arranged in the tunnel through a multi-source heterogeneous perception algorithm. The multi-source heterogeneous perception algorithm realizes the perception of multi-dimensional information of the environment, traffic flow and light field through sensor processing and redundant networks.

[0051] It should be noted that in this embodiment, the deployment of multiple types of high-precision sensors includes dividing different types of sensors into core sensors and auxiliary sensors. The core sensors are distributed fiber optic light intensity sensors, installed at intervals of 2 meters in the tunnel; the auxiliary sensors include a millimeter-wave radar array for sensing vehicle information in the tunnel, a thermal imaging sensor for sensing fog concentration, and a temperature / humidity sensor, light sensor, and image sensor for environmental sensing. The data collected by the sensors is first sent to the edge gateway, which preprocesses the data. Because the sensors may be affected by noise and other interference, some preprocessing is required before processing. This can include: using wavelet transform to denoise the data to remove errors caused by environmental noise or the sensor itself. At the same time, to remove high-frequency fluctuations during the measurement process, a low-pass filter can be used to smooth the sensor data. Ultimately, the denoised sensor data value is obtained.

[0052] Figure 3 FIG. 4 shows a flowchart of the multi-source heterogeneous perception algorithm in this embodiment. Figure 4 The timing diagram of the multi-source heterogeneous perception algorithm in this embodiment is shown. As can be seen from the diagram, the multi-source heterogeneous perception algorithm includes the following steps:

[0053] 1) Extract input data related to dimming illumination requirements. These input data usually come from multiple sensors and environmental monitoring equipment. Integrate the input data to obtain measured illumination data, visual required illumination data, and haze attenuation factors.

[0054] Among them, the measured illuminance data L opt , which is the real-time light level measured directly by the sensor.

[0055] In this embodiment, it can be calculated by the following formula:

[0056] ,

[0057] in, is the sum of all light sensors, For a single light sensor, is the raw data of the i-th sensor, is the sensor noise reduction residual, is the geometric attenuation weight, which can be calculated based on the position of the lighting fixtures in the tunnel. This formula averages all sensor data and takes the geometric attenuation weight into account to obtain a comprehensive light measurement value.

[0058] Visual required illumination data L vd , which is an illuminance calculation based on visual comfort and demand. This value can determine the required illuminance based on the passing speed of vehicles in the tunnel, road conditions and speed limit.

[0059] In this embodiment, the visual required illumination data L vd It can be calculated by the following formula:

[0060] ,

[0061] in, is the contrast sensitivity factor, which can be obtained by looking up the table according to the lighting rules in the Guide to Lighting for Tunnels and Underground Passages (standard CIE 88-2004); is the average vehicle speed, is the road speed limit, is the exponential weight of the relationship between speed and visual required illuminance, which determines how changes in average vehicle speed relative to the safe speed affect visual required illuminance. When δ > 1, higher average speeds result in greater visual required illuminance. In other words, the faster the speed, the higher the driver or pedestrian's lighting demand. When δ < 1, changes in speed have little effect on visual required illuminance, and even if speed increases, the lighting demand does not increase significantly. When δ = 1, visual required illuminance has a linear relationship with speed.

[0062] Haze attenuation factor C fog Since haze can cause a strong attenuation of light, it is necessary to model this factor. The haze concentration index can be inverted through thermal imaging technology or other image processing methods to obtain a haze attenuation value calculated based on environmental conditions (such as humidity, wind speed, etc.).

[0063] In this embodiment, the haze attenuation factor C fog It can be calculated by the following formula:

[0064] ,

[0065] in, is the regression coefficient obtained by training based on foggy image data, is the grayscale distribution of the thermal imaging image, is the humidity ratio, is the second-order mixed partial derivative of the grayscale value of the thermal imaging image, which represents the rate of change of the image in the x and y directions. Used for normalized water vapor concentration to quantify the effect of water vapor on light attenuation.

[0066] 2) Define a dynamic weight parameter Ω for the measured illuminance data, the visual required illuminance data, and the haze attenuation factor. The dynamic weight parameter Ω = (α, β, γ) is a parameter group consisting of multiple dynamic weights. The function of each parameter is as follows:

[0067] α determines the importance of the measured illuminance data in the final dimming illuminance. It is usually a dynamic value and may be adjusted according to changes in energy consumption, lighting conditions, etc.

[0068] β is used to adjust the importance of visual demand illuminance in the final dimming, and its value may vary depending on traffic conditions, road type, or driver needs.

[0069] γ is used to adjust the importance of the attenuation factor of the effect of haze on illumination. Its value may depend on the signal quality of the sensor or environmental conditions, such as humidity and haze concentration.

[0070] These weights are dynamic, meaning they adjust in real time based on environmental conditions, sensor signal quality, and other factors. These dynamically changing weight parameters ensure the flexibility and adaptability of the entire system, enabling it to operate efficiently in complex and changing IoT environments.

[0071] Specifically, in this implementation, the dynamic weight parameter Ω can be calculated according to the following formula:

[0072] ,

[0073] in, is the weight adjustment based on the change of energy consumption gradient, is a natural constant, To adjust the rate, is the energy consumption gradient change, is the gradient change weight parameter based on visual requirements and environmental interference, is the gradient of visual required illumination, used to express the function The rate of change in each direction,

[0074] Is the norm of the illumination gradient, indicating the size of the gradient vector, quantizing The overall rate of change or intensity of change in space; is the gradient of the haze attenuation factor, is the norm of the haze attenuation factor gradient, which quantifies the total change rate or change intensity of the haze attenuation factor in space; is the weight parameter based on the sensor signal quality index and fault mark, is the quality constraint in the form of Sigmoid activation function, SQI is the sensor signal quality index, Fault flag, 1 if the sensor fails, 0 otherwise.

[0075] 3) According to the measured illuminance data, visual required illuminance data, haze attenuation factor and dynamic weight parameters, they are combined into the final dimming illuminance requirement L through weighted summation. req, the dimming illumination requirement can be expressed by the following formula:

[0076] ,

[0077] ,

[0078] in, is the attenuation factor, which is used to characterize the impact of haze contrast. z is the haze transmittance attenuation weight coefficient.

[0079] Step 2: After receiving the sensor data and dimming illumination requirements sent by the edge gateway, the cloud data center uses the adaptive dimming algorithm deployed on the cloud to combine the sensor data and convert the dimming illumination requirements into a dimming execution strategy that can meet energy consumption, safety and light quality.

[0080] Specifically, the adaptive dimming algorithm includes a dynamic scene classification mechanism, an energy efficiency priority model, and a safety priority model. The dynamic scene classification mechanism first classifies scenes, selects different priority modules based on different scenarios, and generates different dimming execution strategies based on the rules of different priority models. Figure 5 FIG. 4 shows a timing diagram of the adaptive dimming algorithm of this embodiment.

[0081] In this embodiment, the scene feature vector modeling is expressed by the following formula:

[0082] ,

[0083] in, is the fog concentration change rate, which reflects the changing trend of environmental visibility; is the total kinetic energy of vehicles within 100 meters, reflecting the comprehensive situation of traffic flow and vehicle speed; The curvature of the illumination demand along the longitudinal direction of the tunnel, that is, the second-order derivative of the illumination demand along the longitudinal direction of the tunnel, reflects the degree of change of the illumination demand and is used to judge the drastic change of the lighting demand in the tunnel; It is the image clarity index of the image sensor, reflecting the current visibility and image quality.

[0084] In this embodiment, the fog concentration change rate can be calculated by the following formula:

[0085] ,

[0086] in, is the fog density at time t, t is the current time, The interval is usually a fixed short time. During the scene determination process, if the fog concentration change rate exceeds a certain threshold, it means that the fog concentration is changing rapidly and the lighting brightness needs to be quickly increased or decreased to adapt to the change in visibility.

[0087] The total kinetic energy of the vehicle within 100 meters can be calculated using the following formula:

[0088] ,

[0089] Where M is the total number of vehicles within a hundred-meter range, is the estimated mass of the i-th vehicle, is the speed of the i-th vehicle. During scene assessment, if the total kinetic energy of vehicles within a 100-meter radius exceeds a certain threshold, it indicates that many vehicles are traveling at high speeds. In this case, the lighting brightness should be increased to ensure a clear view for the driver and reduce the possibility of accidents. If the total kinetic energy of vehicles within a 100-meter radius is lower than a certain threshold, it indicates that the vehicles are traveling slowly, possibly due to traffic congestion or other reasons. In this case, the lighting brightness can be appropriately reduced to save energy.

[0090] The required curvature of the longitudinal illumination along the tunnel can be calculated using the following formula:

[0091] ,

[0092] in, is the illumination requirement at position x, where x is the longitudinal position of the tunnel. During scene determination, if the curvature of the illumination requirement changes significantly, it indicates that the illumination requirements at different locations within the tunnel are changing rapidly. For example, at a sudden tunnel exit or entrance, the light changes significantly, requiring rapid adjustment of the lighting brightness. If the curvature of change is small, it indicates that the illumination requirement within the tunnel is relatively stable, and the current lighting brightness can be maintained.

[0093] The image clarity index can be calculated using the following formula:

[0094] ,

[0095] is the Laplace transform value at pixel (x, y), which represents the high-frequency component of the image; =The total number of pixels in the image. During scene determination, if the image clarity index is low, it indicates that the image quality captured by the camera is poor, possibly due to haze or other factors affecting the field of view. In this case, it is necessary to increase the lighting brightness to improve the field of view. If the image clarity index is high, the current lighting conditions are good and the current lighting brightness can be maintained or appropriately reduced to save energy.

[0096] It should be noted that the rules for determining by vector features can be:

[0097] High fog concentration variation + high total vehicle kinetic energy + high illumination demand variation + low image clarity:

[0098] The lighting brightness needs to be increased quickly to ensure that the driver can see clearly ahead.

[0099] Low fog concentration variation + low total vehicle kinetic energy + low illumination requirement variation + high image clarity:

[0100] Lighting levels can be maintained at current levels or reduced to save energy.

[0101] Moderate fog density change + moderate vehicle total kinetic energy + moderate illumination requirement change + moderate image clarity:

[0102] Depending on the circumstances, minor adjustments may be necessary to ensure that lighting conditions meet current traffic and environmental needs.

[0103] In this embodiment, the energy efficiency priority model can be defined by an objective function and constraint conditions.

[0104] The purpose of the objective function is to minimize energy consumption while meeting the required illumination, which can be expressed as follows:

[0105] ,

[0106] Among them, u k is the control input, which can be the setting of the lighting system (such as switch status, brightness adjustment, etc.), k is a single moment, K is the sum of the moments k, is the actual illumination value at the kth moment, is the illumination value required at the kth moment, is a weight parameter used to balance the weight between tracking accuracy and energy consumption. The value means more attention to energy consumption, smaller The value means more emphasis on control accuracy. is the control input u at the kth moment k The corresponding energy consumption, This item is the square of the difference between the actual illuminance value and the required illuminance value, which represents the control accuracy. The square form means that the greater the deviation, the greater the penalty, thereby prompting the system to try to make the actual illuminance value close to the required illuminance value.

[0107] Constraints ensure that the system adheres to a set of physical and operational limitations while satisfying the objective function. In this embodiment, the constraints include:

[0108] Longitudinal gradient constraint:

[0109] This constraint limits the rate of change of illuminance along the longitudinal direction of the tunnel, ensuring that the illuminance does not change too much and avoid discomfort to the driver. The maximum allowable change rate is 15 lux per meter.

[0110] Transient jump constraints:

[0111] , which limits the control input u k The change rate ensures that the lighting system is adjusted smoothly without sudden and drastic changes to avoid causing dizziness or discomfort to the driver. The maximum allowable change rate is 10% per second.

[0112] No glare constraints:

[0113] This constraint ensures that the illumination ratio between the brightest and darkest areas of the lighting system at any location does not exceed 5 times to avoid glare problems and ensure the comfort and safety of the driver's vision.

[0114] In this embodiment, the safety priority model dynamically adjusts the light wavelength ratio by monitoring the environmental conditions in real time, and adjusts the light wavelength ratio according to the fog concentration C f Dynamically adjust tunnel lighting RGB mix At the same time, compensation light spots are generated through inverse Monte Carlo ray tracing to improve the illumination of specific areas and compensate for the light loss caused by haze; and the illumination within 20 meters of the tunnel entrance is forcibly increased to 1.5 times the standard value to ensure that drivers have sufficient illumination transition when entering the tunnel, avoiding discomfort and safety hazards caused by sudden illumination changes.

[0115] It's important to note that the safety-first model adaptively adjusts the light wavelength by adjusting the color mixing ratio based on fog concentration to reduce scattering and improve visibility. It also uses inverse Monte Carlo ray tracing to calculate compensatory illumination to overcome the scattering and absorption of light by haze. Finally, it enforces increased illumination in key areas (such as tunnel entrances) and enables rapid response via a high-speed communication bus. These combined methods ensure adequate lighting and safety even in harsh environments.

[0116] The specific strategy for adjusting the light color ratio of tunnel lamps can be determined by the following formula:

[0117] ,

[0118] Among them, RGB mix is the color mixing ratio of light, C f is the density of fog. fWhen the fog density C is less than 0.3, the first set of ratios (0.2, 0.7, 0.1) is used, that is, blue light accounts for 70%, green light accounts for 20%, and red light accounts for 10%. This combination helps provide better visibility in low-density fog conditions. f When ≥0.3, the second set of ratios (0.15, 0.6, 0.25) is used, that is, blue light accounts for 60%, green light accounts for 15%, and red light accounts for 25%. This combination provides better visibility in high-concentration fog conditions.

[0119] The specific compensation spot adjustment strategy can be determined by the following formula:

[0120] ,

[0121] in, is the compensation illumination at position (x, y), D is the number of samples that need to compensate illumination, is the luminous intensity distribution function of the lamp, which indicates the direction of the lamp in the tunnel The luminous intensity, is the scattering coefficient of haze, is the distance light travels in the fog.

[0122] Step 3: The cloud data center sends the dimming execution strategy generated by the adaptive dimming algorithm to the dimming control module in the tunnel. The dimming control module adjusts the brightness of the tunnel lamps according to the dimming execution strategy.

[0123] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A tunnel dynamic dimming method based on the Internet of Things, characterized in that: The dynamic dimming method includes: S100, the edge gateway receives sensor data in the tunnel and processes the sensor data through the multi-source heterogeneous perception algorithm built into the edge gateway; S200 and the edge gateway send the received sensor data and the dimming illumination requirements calculated by the multi-source heterogeneous perception algorithm to the cloud. The cloud-based adaptive dimming algorithm generates a dimming strategy based on sensor data and dimming illumination requirements; The adaptive dimming algorithm includes a dynamic scene classification mechanism, an energy efficiency priority model, and a safety priority model; Dynamic scene classification mechanism performs scene classification, selects different priority modules according to different scenes, and generates different dimming strategies based on different priority models; S300: Send the dimming strategy generated by the adaptive dimming algorithm to the dimming control module in the tunnel. The dimming control module adjusts the tunnel lamps according to the dimming strategy; The multi-source heterogeneous perception algorithm includes: S110, extracting and integrating sensor input data to obtain measured light illuminance data, visual required illuminance data, and haze attenuation factor; S120: defining dynamic weight parameters according to the measured illuminance data, the visual required illuminance data, and the haze attenuation factor. The dynamic weight parameter is a parameter group Ω=(α,β,γ) composed of multiple dynamic weights. The function of each parameter is as follows: α determines the importance of the measured illuminance data in the final dimming illuminance. β is used to adjust the importance of visual demand illuminance in the final dimming. γ is used to adjust the importance of the attenuation factor of the effect of haze on illumination; S130: Combine the measured illuminance data, the visual required illuminance data, the haze attenuation factor, and the dynamic weight parameter into the final dimming illuminance requirement through weighted summation. The dimming illumination requirement is expressed by the following formula: ， ， in, is the measured illuminance data, is the visual requirement illumination data, is the haze attenuation factor, is the attenuation factor, which is used to characterize the impact of haze contrast, and z is the haze transmittance attenuation weight coefficient; The parameter set Ω=(α, β, γ) is calculated according to the following formula: ， in, is the weight adjustment based on the change of energy consumption gradient, is a natural constant, To adjust the rate, is the energy consumption gradient change, is the gradient change weight parameter based on visual requirements and environmental interference, is the gradient of visual illumination requirement, is the gradient of the haze attenuation factor, is the quality constraint in the form of Sigmoid activation function, SQI is the sensor signal quality index, is the fault flag, which is 1 if the sensor fails, otherwise it is 0; t is the current time; The measured illuminance data is calculated according to the following formula: ， in, is the sum of all light sensors, For a single light sensor, is the raw data of the i-th sensor, is the sensor noise reduction residual, is the geometric attenuation weight; The visual required illumination data is calculated according to the following formula: ， in, is the contrast sensitivity factor, is the average vehicle speed, is the road speed limit, is the exponential weight of the relationship between speed and visual required illumination; The haze attenuation factor is calculated according to the following formula: ， in, is the regression coefficient obtained by training based on foggy image data, is the grayscale distribution of the thermal imaging image, is the humidity ratio.

2. The method for dynamic tunnel lighting control based on the Internet of Things according to claim 1, characterized in that: The sensors in the tunnel include core sensors and auxiliary sensors. The core sensor is a distributed optical fiber light intensity sensor; The auxiliary sensors include: a millimeter-wave radar array, a thermal imaging sensor, a temperature / humidity sensor, a light sensor, and an image sensor.

3. The tunnel dynamic dimming method based on the Internet of Things according to claim 1, characterized in that: The dynamic scene classification mechanism includes: scene feature vector modeling, The scene feature vector modeling is expressed by the following formula: ， in, is the fog concentration change rate, which reflects the changing trend of environmental visibility; is the total kinetic energy of the vehicle within 100 meters; is the required curvature of illumination along the longitudinal direction of the tunnel, is the required illumination value; is the image clarity index of the image sensor.

4. The method for dynamic tunnel lighting control based on the Internet of Things according to claim 1, characterized in that: The energy efficiency priority model is defined by the objective function and constraints. The purpose of the objective function is to minimize energy consumption while meeting the required illumination, which can be expressed as follows: ， Among them, u k is the control input, k is a single moment, K is the sum of the moments k, is the actual illumination value at the kth moment, is the illumination value required at the kth moment, is the weight parameter, is the control input u at the kth moment k The corresponding energy consumption, is the actual illumination value; Constraints ensure that the system adheres to a set of physical and operational limitations while satisfying the objective function. Constraints include: Longitudinal gradient constraint: ， This constraint limits the rate of change of illuminance along the longitudinal direction of the tunnel to ensure that the illuminance does not change too much. The maximum allowable change rate is 15 lux per meter. Transient jump constraints: ， This constraint limits the control input u k The rate of change ensures that the lighting system is adjusted smoothly without sudden and large changes. The maximum allowable rate of change is 10% per second. No glare constraints: ， is the maximum illuminance value, is the minimum illuminance value; this constraint ensures that the illuminance ratio between the brightest and darkest areas of the lighting system at any location does not exceed 5 times to avoid glare problems.

5. The tunnel dynamic dimming method based on the Internet of Things according to claim 1, characterized in that: The safety priority model monitors environmental conditions in real time and dynamically adjusts the RGB of tunnel lamps according to the monitored fog concentration. mix The ratio of light color; Generate compensation light spots through inverse Monte Carlo ray tracing to improve the illumination of the target area and compensate for the light loss caused by haze; The illumination within 20 meters of the tunnel entrance is forcibly increased to 1.5 times the standard value to ensure that drivers have sufficient illumination transition when entering the tunnel, avoiding discomfort and safety hazards caused by sudden changes in illumination.

6. The method for dynamic tunnel lighting control based on the Internet of Things according to claim 5, characterized in that: Adjusting the RGB of tunnel lamps mix The light color ratio is determined by the following formula: ， Among them, RGB mix is the color mixing ratio of light, C f is the concentration of fog; when the concentration of fog C f <0.3, use the first set of ratios, blue light accounts for 70%, green light accounts for 20%, and red light accounts for 10%. When the fog concentration C f When ≥0.3, the second group ratio is used, with blue light accounting for 60%, green light accounting for 15%, and red light accounting for 25%; The adjustment strategy of the compensation spot is determined by the following formula: ， in, is the compensation illumination at position (x, y), D is the number of samples that need to compensate illumination, is the luminous intensity distribution function of the lamp, which indicates the direction of the lamp in the tunnel The luminous intensity, is the scattering coefficient of haze, is the distance light travels in the fog.

7. A tunnel dynamic dimming system based on the Internet of Things, characterized in that: The dynamic dimming system includes: processor; A memory storing a computer program, which, when executed by a processor, implements the tunnel dynamic dimming method based on the Internet of Things as described in any one of claims 1 to 6.

Images