A light rail night driving lighting system for preventing glare interference

Abstract

The present invention discloses a light rail night driving lighting system for preventing glare interference, which relates to the technical field of light rail lighting. The system includes: an environmental data acquisition module, a data preprocessing module, an intelligent analysis and decision-making module, a lighting adjustment execution module, and a feedback monitoring module; through the collaborative work of the environmental data acquisition module, the data preprocessing module, the intelligent analysis and decision-making module, the lighting adjustment execution module, and the feedback monitoring module, the present invention realizes the comprehensive perception and intelligent adjustment of the light rail night driving environment. Especially in terms of glare interference, the system can accurately identify the glare area and automatically adjust the brightness, color temperature, and light color of the lighting system, effectively avoiding the interference of glare on the driver's vision and reducing the risk of traffic accidents. At the same time, the system can also flexibly adjust the lighting strategy according to different weather conditions and driving sections to ensure that the light rail can maintain a good lighting effect in different environments, improving the safety of night driving.

Description

Technical Field

[0001] The present invention relates to the technical field of light rail lighting, and specifically provides a light rail night driving lighting system that prevents glare interference. Background Art

[0002] With the acceleration of the urbanization process and the continuous improvement of the transportation network, light rail, as an efficient and environmentally friendly public transportation mode, plays an increasingly important role in the urban transportation system. Especially during night driving, the lighting system of the light rail is of great significance for ensuring driving safety and enhancing the passenger experience. However, due to the complexity of the night driving environment, such as glare, weather changes, and road section differences, higher requirements are imposed on the light rail lighting system. Therefore, developing a light rail night driving lighting system that can adapt to complex environments and achieve intelligent adjustment has become an urgent technical problem to be solved.

[0003] Traditional technologies have some deficiencies in light rail night lighting. On the one hand, traditional lighting systems often adopt fixed lighting modes and brightness levels and cannot be adjusted in real time according to environmental changes, resulting in poor lighting effects in some cases and even potential safety hazards such as glare. On the other hand, traditional systems lack intelligent analysis and decision-making capabilities and cannot comprehensively and accurately perceive and judge complex night driving environments, thus unable to provide the optimal lighting solution. These deficiencies not only affect the safety and comfort of light rail night driving but also limit the overall efficiency and user experience of the light rail transportation system.

[0004] Therefore, developing a light rail night driving lighting system that prevents glare interference will strongly promote the intelligent development of light rail night driving lighting technology and provide strong support for the optimization and upgrading of the urban transportation system. Summary of the Invention

[0005] The purpose of the present invention is to make up for the deficiencies of the existing technology and provide a light rail night driving lighting system that prevents glare interference. By integrating multiple intelligent modules, it realizes the comprehensive perception and precise adjustment of the light rail night driving environment. This system can analyze the information of ambient light, glare areas, weather conditions, and driving road sections in real time and generate the optimal lighting adjustment instructions based on this information, thus effectively avoiding glare interference and improving driving safety and comfort.

[0006] To solve the above technical problems, the present invention provides the following technical solution: A light rail night driving lighting system that prevents glare interference, which includes: an environmental data acquisition module, a data preprocessing module, an intelligent analysis and decision-making module, a lighting adjustment execution module, and a feedback monitoring module;

[0007] The environmental data acquisition module: Environmental light sensors are arranged on the front of the light rail vehicle, on the roof, and on both sides of the vehicle body to collect light data. At the same time, a high-definition camera is installed at the front of the vehicle to collect image data of the front environment, and the data is synchronously transmitted to the data preprocessing module;

[0008] The data preprocessing module: Receives the light and image data transmitted by the environmental data acquisition module, uses a filtering algorithm to remove interference signals from the light data, converts the image data into a grayscale image through a grayscale formula, removes noise using a noise reduction formula, and transmits the processed data to the intelligent analysis and decision-making module;

[0009] The intelligent analysis and decision-making module: Receives the data from the data preprocessing module, analyzes the glare area in the image recognition using a vision-environment fusion perception algorithm, determines the type and distribution of surrounding light sources with the help of a convolutional neural network, and generates adjustment instructions for the brightness, color temperature, and light color of the lighting system by integrating light, glare, weather, and road section information;

[0010] The lighting adjustment execution module: Receives the instructions from the intelligent analysis and decision-making module, adjusts the power of the power supply to change the brightness according to the instructions, controls the mixing ratio of light sources to adjust the color temperature, and drives the corresponding light sources to switch the light color;

[0011] The feedback monitoring module: Collects the ambient light conditions after lighting adjustment through the visual monitoring equipment inside the light rail vehicle, obtains the driver's visual perception through the driver feedback channel, analyzes it through the feedback data evaluation algorithm, and optimizes the system according to the analysis results.

[0012] Furthermore, the environmental light sensor in the environmental data acquisition module is a multi-spectral array sensor, which is composed of multiple sensing units with different spectral response ranges. The sensing units can collect light information in the ultraviolet, visible, and infrared bands respectively; when the light rail is running at a normal constant speed in a stable environment, the collection frequency is 50 times per second; when the light rail is accelerating, decelerating, or turning, the collection frequency is 100 times per second; under special weather conditions, the sensor collection frequency is 200 times per second.

[0013] Even further, the filtering algorithm used in the data preprocessing module to remove interference signals from the light data has the formula: , where, is the filtered light information value, is the number of samples participating in the filtering calculation, is the radius of the filtering window, represents the set of light samples within a window centered on the th light sample with a radius of .

[0014] Even further, the processing of image data in the data preprocessing module: Grayscale processing: The formula is: , where is the grayscale value of the pixel point with coordinates after grayscale conversion, and are the red, green, and blue primary color values of the pixel point with coordinates in the image, ranging from 0 to 255, obtained by the color sensing of the light by the image sensor of the camera and after analog-to-digital conversion; Noise reduction processing: The formula is: , where is the grayscale value of the pixel point after noise reduction, is the noise reduction coefficient, with a value range of 0.1 to 0.5, is the grayscale variance of the local area where the pixel point is located,

[0015] Furthermore, the intelligent analysis and decision-making module uses a vision-environment fusion perception algorithm to analyze the preprocessed image to identify the glare area. The formula is: , where represents whether the pixel point with coordinates is in the glare area. 1 means yes, and 0 means no, is the light intensity value of this pixel point, and are the glare judgment thresholds, respectively used to detect sudden changes in light and intensity thresholds, represents the light intensity value with respect to and the second-order mixed partial derivative of represents the partial differential symbol.

[0016] Furthermore, in the intelligent analysis and decision-making module, a convolutional neural network is used to judge the type and distribution of surrounding light sources:

[0017] Collect data on light intensity, color, and spectrum in various scenarios with a light sensor, record the corresponding light source types and distribution, clean and normalize the data, divide the data into training set, validation set, and test set, construct a convolutional neural network model including an input layer matching the data feature dimensions, a convolutional layer using convolutional kernels to extract features, a pooling layer for downsampling the data to reduce data dimensions, a fully connected layer for fusing features, and an output layer with a structure determined by the task, define the corresponding loss function, select the stochastic gradient descent optimization algorithm to train the model, input the training set data into the model, update the parameters through forward propagation, loss calculation, and backpropagation, adjust the hyperparameters according to the validation set results, evaluate the model using the test set, if not up to standard, return for retraining, and when the model training reaches the standard, deploy the model to the actual environment, obtain and preprocess the light data in real time and input it into the model, and output the light source types and distribution in the current environment by the model.

[0018] Furthermore, the specific steps for generating the lighting adjustment instruction by combining the weather condition and the driving section data in the intelligent analysis and decision-making module are as follows:

[0019] (1) Rely on the in-vehicle GPS to obtain the geographical location information and determine the current driving section type through electronic map matching;

[0020] (2) According to the section type, combine the light, glare, and weather information to retrieve the applicable strategies in the preset strategy database;

[0021] (3) According to the retrieved strategies, generate the corresponding adjustment instructions for the brightness, color temperature, and light color of the lighting system;

[0022] (4) Summarize the generated instructions, verify their integrity and rationality, convert them into a specific format, and send them to the lighting adjustment execution module through the high-speed line.

[0023] Furthermore, the preset strategy database in the intelligent analysis and decision-making module is as follows:

[0024] Adjustment strategy based on the glare area: Identify that a large area and high-intensity glare area is concentrated in the front, reduce the brightness of the lighting fixtures in that direction, and adjust the light angle; when the glare area is small and scattered, slightly adjust the local lighting color temperature;

[0025] Adjustment strategy based on the type and distribution of surrounding light sources: When the surrounding main light source is high-brightness natural light and is evenly distributed, reduce the overall brightness of the light rail lighting system, and at the same time adjust the color temperature to a higher value to simulate the natural light color; when the surrounding light sources are of low color temperature and are distributed on both sides of the road, adjust the light rail lighting color temperature to a similar range and increase the brightness at the same time;

[0026] Adjustment strategies based on weather conditions: In foggy weather, switch the illumination light color to yellow light and increase the overall brightness; in rainy weather, reduce the illumination brightness and adjust the light angle to make it more downward.

[0027] Adjustment strategies based on the driving section: When the light rail is running in the tunnel, maintain a stable and relatively high illumination brightness; when running on the open track and the surrounding environmental light is sufficient, reduce the illumination brightness and fine-tune its own color temperature according to the color temperature of the environmental light; on special sections of the bridge, fine-tune the power output of the power supply to maintain the relative stability of the illumination brightness.

[0028] Furthermore, the adjustment of the brightness, color temperature, and light color of the illumination system in the illumination adjustment execution module;

[0029] Adjustment of brightness: The microprocessor receives the brightness adjustment instruction, analyzes the adjustment amplitude in the instruction, and according to the requirement of the adjustment amplitude, changes the duty cycle of the pulse width modulation signal to adjust the magnitude of the output current or voltage.

[0030] Adjustment of color temperature: Receive the color temperature adjustment instruction, extract the target color temperature value in the instruction. For an illumination system using a multi-light source combination, calculate the mixing ratio of light sources with different color temperatures according to the target color temperature, and adjust the luminous intensity of light sources with different color temperatures by controlling the drive current of various light sources.

[0031] Adjustment of light color: Receive the light color adjustment instruction, and adjust the light color by adjusting the excitation ratio of the internal phosphor or controlling the luminous intensity of different color chips according to the instruction.

[0032] Furthermore, in the feedback monitoring module, analyze the secondary monitoring data of the environmental light and the feedback data of the driver's visual perception through the feedback data evaluation algorithm. The formula is: , where is the quantization value of the driver's visual perception feedback, is the comprehensive feedback evaluation value, and are the weight coefficients, and , is the value related to the environmental light brightness before adjustment, is the value related to the environmental light brightness after adjustment.

[0033] Compared with the prior art, the anti-glare interference night driving illumination system for light rail has the following beneficial effects:

[0034] 1. Through the collaborative work of the environmental data collection module, data preprocessing module, intelligent analysis and decision-making module, lighting adjustment execution module, and feedback monitoring module, the present invention realizes the comprehensive perception and intelligent adjustment of the light rail's night driving environment. Especially in terms of glare interference, the system can accurately identify the glare area and automatically adjust the brightness, color temperature, and light color of the lighting system, effectively avoiding the interference of glare on the driver's vision and reducing the risk of traffic accidents. At the same time, the system can also flexibly adjust the lighting strategy according to different weather conditions and driving sections to ensure that the light rail can maintain good lighting effects in different environments, improving the comfort and safety of night driving.

[0035] 2. By introducing the intelligent analysis and decision-making module and convolutional neural network technology, the present invention realizes the precise adjustment of the lighting system. The system can analyze the information of environmental light, glare area, weather conditions, and driving sections in real time and generate the optimal lighting adjustment instructions based on this information. This intelligent adjustment method not only improves the energy efficiency of the lighting system but also greatly enhances its adaptability and flexibility. In addition, the present invention also uses the feedback monitoring module to monitor and evaluate the lighting effect in real time, providing strong support for the continuous optimization of the system. It not only provides a safer and more comfortable lighting environment for the light rail's night driving but also provides new ideas and methods for the lighting system design in other traffic fields.

[0036] Other advantages, objectives, and features of the present invention will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0038] Figure 1 It is a flowchart of a lighting system for light rail night driving to prevent glare interference;

[0039] Figure 2 It is a framework diagram of a lighting system for light rail night driving to prevent glare interference. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0040] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention objective, the following will, in conjunction with the accompanying drawings and preferred embodiments, detail the specific implementation manners, structures, features, and their effects of the present invention as follows.

[0041] Example 1:

[0042] Night-time tunnel driving scenario.

[0043] Late at night on a working day, a light rail full of late-returning passengers is slowly approaching a tunnel. At this time, each module of the light rail lighting system starts to cooperate closely, such as Figure 1 , showing the complete process of the system from data collection to feedback optimization, including the data flow between modules.

[0044] The environmental data collection module starts first. The multi-spectral array environmental light sensors installed on the front of the light rail, the roof, and both sides of the body quickly collect light data at a high frequency of 200 times per second, accurately capturing the subtle changes in light inside and outside the tunnel. At the same time, the high-definition camera at the front of the train is also working synchronously, continuously shooting the environmental image data inside the tunnel ahead at a speed of 30 frames per second. The collected light and image data are quickly transmitted to the data preprocessing module through a high-speed data transmission line, such as Figure 2 , showing the hardware framework of the system, including the connection relationships of sensors, processors, and actuators.

[0045] After receiving the data, the data preprocessing module immediately starts working. For the light data, advanced filtering algorithms are used to remove various external interference signals. The formula is: , where is the filtered light information value, is the number of samples participating in the filtering calculation, is the filtering window radius, represents the set of light samples within a window centered on the th light sample with a radius of to ensure the accuracy of the light data; for the image data, first, the color image is converted to a grayscale image through grayscale processing,

[0046] The formula is: , where is the grayscale value of the pixel at coordinates after grayscale processing, are the red, green, and blue primary color values of the pixel at coordinates in the image, obtained by the color sensing of the light by the image sensor of the camera and after analog-to-digital conversion, making the image data easier to analyze and process subsequently. Then, a noise reduction algorithm is used to remove the noise in the image. The formula is: , where is the grayscale value of the pixel after noise reduction, is the noise reduction coefficient, with a value range of 0.1 to 0.5, is the pixel The gray variance of the local area is the gray mean of the local area to enhance the image clarity. The processed data is then transmitted to the intelligent analysis and decision-making module.

[0047] After receiving the data, the intelligent analysis and decision-making module starts in-depth analysis. It uses an advanced vision-environment fusion perception algorithm to analyze the preprocessed image, combines the light data, and determines that there is no glare area in the tunnel. The formula is: , where represents whether the pixel point with coordinates is in the glare area. 1 means yes, and 0 means no. is the light intensity value of this pixel point. and are the glare judgment thresholds, which are used to detect sudden changes in light and intensity thresholds respectively. represents the light intensity value with respect to and second-order mixed partial derivative. represents the partial differential symbol. At the same time, the accurate geographical location information of the light rail is obtained through the vehicle-mounted GPS, and then with the help of electronic map matching, it is accurately determined that the current light rail is in the tunnel driving section, and it is known that the current weather condition is sunny. Based on this information, the intelligent analysis and decision-making module quickly retrieves applicable strategies in the preset strategy database, and finally determines that when driving in the tunnel, it is necessary to maintain a stable and relatively high lighting brightness to ensure that the driver can clearly observe the road conditions ahead and ensure driving safety. Therefore, it generates a corresponding lighting adjustment instruction, and the instruction content is to increase the brightness of the lighting system while maintaining the current color temperature and light color unchanged.

[0048] After receiving the instruction, the lighting adjustment execution module responds quickly. The microprocessor accurately analyzes the adjustment amplitude in the instruction, and by changing the duty cycle of the pulse width modulation signal, it cleverly increases the magnitude of the output current or voltage to accurately control the brightness of the lighting system. As the current or voltage increases, the lighting fixtures gradually brighten, and the light rail carriage and the tunnel ahead are instantly illuminated by bright light, creating a safe and comfortable riding environment for passengers and providing a clear field of vision for the driver.

[0049] The feedback monitoring module is also continuously working. It collects the ambient light conditions after lighting adjustment in all directions through multiple visual monitoring devices installed in the light rail, monitors the light uniformity and brightness changes from different angles. At the same time, it also collects the driver's visual feelings through a dedicated driver feedback channel. The driver can simply click a button or enter text through the feedback terminal in the vehicle to describe their feelings about the lighting effect, such as whether they feel glare or whether there are lighting dead spots. After the feedback monitoring module collects this data, it uses a feedback data evaluation algorithm for in-depth analysis. The formula is: , where is the quantified value of the driver's visual feeling feedback, is the comprehensive feedback evaluation value, and are weight coefficients, and , is the ambient light brightness related value before adjustment, is the ambient light brightness related value after adjustment. If the analysis result shows that the lighting effect is good and the driver's visual feeling is comfortable, the system will continue to maintain the current lighting state; if it is found that the lighting effect is not good, such as the brightness is too bright or too dark, the system will optimize the subsequent lighting adjustment according to the analysis result to ensure that the lighting system is always in the best working state.

[0050] In summary, in the specific scenario of driving in a tunnel at night, the lighting system of the present invention fully demonstrates its advantages. The environmental data acquisition module timely and accurately obtains light and image data, providing a reliable basis for subsequent processing. The data preprocessing module effectively removes interference and optimizes images, making the information more valuable for analysis. The intelligent analysis and decision-making module quickly matches a suitable lighting strategy based on various information and generates reasonable instructions. The lighting adjustment execution module accurately executes the instructions, improves the lighting brightness, and ensures clear vision. The feedback monitoring module continuously optimizes the system by comprehensively evaluating the ambient light and the driver's feelings. Each module cooperates closely, not only meeting the lighting requirements for tunnel driving, but also improving driving safety and passenger comfort, effectively verifying the scientificity and practicality of the present invention.

[0051] Embodiment 2:

[0052] Driving scenario on an open-air track at night in rainy weather.

[0053] On a rainy night with heavy rain, the city streets are shrouded in rain, and a light rail is struggling to drive on the open-air track. At this time, the lighting system of the light rail faces severe challenges, but it calmly copes with the complex environment with its intelligent functions.

[0054] The multi-spectral array ambient light sensor of the environmental data acquisition module collects light data at a frequency of 100 times per second. In rainy weather, the high acquisition frequency can promptly capture the light changes caused by raindrop scattering and reflection, providing an accurate basis for subsequent data analysis. At the same time, the high-definition front camera is equipped with a wiper device to continuously remove raindrops on the lens surface to ensure the acquisition quality of the front environmental image data. The collected data is transmitted to the data preprocessing module through a high-speed line.

[0055] After receiving the data, the data preprocessing module immediately processes the light data using a filtering algorithm. The formula is: to remove the interference introduced by raindrop-scattered light and restore the real environmental illumination data. For the image data, it is first grayscaled.

[0056] The formula is: Then, a noise reduction algorithm is applied. The formula is: to eliminate the image noise generated by rainwater and low light conditions and improve the image clarity. The processed light and image data are transmitted to the intelligent analysis and decision-making module.

[0057] After receiving the data, the intelligent analysis and decision-making module starts complex analysis work. It uses a vision-environment fusion perception algorithm to analyze the image and combines the light data to determine that there is no obvious glare area at this time. The formula is: It obtains the position information of the light rail through vehicle-mounted GPS, uses electronic map matching to determine that the light rail is on an open track section, and at the same time combines the current heavy rain weather information to retrieve the applicable strategy for driving on an open track in rainy days in the preset strategy database. According to the strategy, it is necessary to reduce the lighting brightness to avoid excessive reflection of light on the rain curtain and affect the driver's vision, and at the same time adjust the light angle to make it more downward to enhance the lighting effect on the track and road surface. Therefore, the intelligent analysis and decision-making module generates corresponding lighting adjustment instructions.

[0058] After receiving the instruction, the lighting adjustment execution module's microprocessor parses the brightness adjustment instruction and reduces the output current or voltage by changing the duty cycle of the pulse width modulation signal to achieve lighting brightness adjustment. At the same time, it controls the motor drive device to adjust the angle of the lighting fixture so that its irradiation direction is downward to enhance the lighting effect on the track and road surface and reduce the interference of rain reflection.

[0059] The feedback monitoring module collects the ambient light data after lighting adjustment through the visual monitoring equipment in the light rail, analyzes the propagation effect of light in the rain curtain and the lighting uniformity inside the car and around the track. At the same time, it collects visual perception data through the driver feedback channel. It comprehensively analyzes the two types of data using the feedback data evaluation algorithm. The formula is: , if the analysis result shows that the lighting effect does not meet the driving requirements in rainy days, the system will further optimize the lighting adjustment parameters (such as brightness, light angle or light color) according to the analysis result to ensure the safety and comfort of driving at night in rainy days.

[0060] In summary, in the scenario of driving on an open-air track at night in rainy days, the lighting system of the present invention has demonstrated good adaptability and adjustment ability. The environmental data acquisition module stably acquires data in the complex rainy-day environment, the data preprocessing module processes the data to reduce the influence of external interference, the intelligent analysis and decision-making module combines the characteristics of rainy days and open-air track driving to quickly formulate appropriate lighting strategies, the lighting adjustment execution module reduces the brightness and adjusts the light angle according to the instructions to reduce the interference of light reflection, and the feedback monitoring module collects and analyzes the feedback data to optimize the lighting effect in a timely manner. The entire system operates in coordination, effectively overcoming the lighting problems in rainy-night driving, providing strong support for the safe driving of light rails, and highlighting the application value of the present invention in complex weather and road conditions.

[0061] The above are only the preferred embodiments of the present invention and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the equivalent embodiments by using the disclosed technical content within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A light rail night driving lighting system for preventing glare interference, characterized in that, The system includes: environmental data acquisition module, data preprocessing module, intelligent analysis and decision module, lighting adjustment execution module and feedback monitoring module; The environmental data acquisition module: arranges ambient light sensors on the front, roof and both sides of the light rail vehicle to collect light data. At the same time, installs a high-definition camera on the front to collect front environmental image data and synchronously transmits it to the data preprocessing module; The said data preprocessing module: receives the light and image data transmitted by the environmental data acquisition module, applies a filtering algorithm to the light data to remove interference signals, and the formula is: where L ′ is the light information value after filtering, m is the number of samples participating in the filtering calculation, k is the radius of the filtering window, and L j-k:j+k represents the set of light samples within a window with a radius of k centered on the j-th light sample. The image data is converted into a grayscale image through the grayscale formula, and the formula is: where G x,y is the grayscale value of the pixel at coordinates (x, y) after grayscale conversion, r x,y , g x,y , b x,y are the red, green, and blue primary color values of the pixel at coordinates (x, y) in the image, with a range of 0 - 255, obtained by the color sensing of the light by the image sensor of the camera and after analog-to-digital conversion. The noise is removed using the noise reduction formula, and the formula is: where is the grayscale value of the pixel after noise reduction, δ is the noise reduction coefficient, with a value range of 0.1 to 0.5, σ x,y is the grayscale variance of the local area where the pixel (x, y) is located, and μ x,y is the grayscale mean of this local area, and the processed data is transmitted to the intelligent analysis and decision-making module; The intelligent analysis and decision-making module: receives the data from the data preprocessing module, and uses the vision-environment fusion perception algorithm to analyze the image to identify the glare area. The formula is as follows: where D x,y indicates whether the pixel point with coordinates (x, y) is in the glare area, 1 means yes, 0 means no, and I x,y is the illumination intensity value of this pixel point. ∈1 and ∈2 are glare judgment thresholds, which are used to detect sudden illumination changes and intensity thresholds respectively. represents the illumination intensity value I x,y is the second-order mixed partial derivative of x and y, represents the partial differential symbol. With the help of a convolutional neural network, it judges the type and distribution of surrounding light sources, and comprehensively considers information such as light, glare, weather, and road sections to generate adjustment instructions for the brightness, color temperature, and light color of the lighting system. The lighting adjustment execution module receives instructions from the intelligent analysis and decision-making module, adjusts the power supply to change the brightness, controls the light source mixing ratio to adjust the color temperature, and drives the corresponding light source to switch the light color according to the instructions; The feedback monitoring module collects the ambient light conditions after lighting adjustment through the visual monitoring equipment in the light rail, the driver's visual experience obtained through the driver feedback channel, analyzes it through the feedback data evaluation algorithm, and optimizes the system according to the analysis results.

2. The anti-glare interference light rail night driving lighting system according to claim 1, characterized in that, The ambient light sensor in the environmental data acquisition module is a multi-spectral array sensor, which is composed of a plurality of sensing units with different spectral response ranges. The sensing units can respectively collect light information in the ultraviolet, visible light and infrared bands. When the light rail is traveling at a normal and uniform speed in a stable environment, the collection frequency is 50 times per second; when the light rail is accelerating, decelerating or traveling on a curve, the collection frequency is 100 times per second; under special weather conditions, the sensor collection frequency is 200 times per second.

3. The anti-glare interference light rail night driving lighting system according to claim 1, characterized in that, The intelligent analysis and decision-making module uses a convolutional neural network to determine the type and distribution of surrounding light sources: With the help of light sensors, data on light intensity, color, and spectrum are collected in various scenarios, and the corresponding light source types and distribution are recorded. The data is cleaned and normalized, and divided into training set, validation set, and test set. A convolutional neural network model is constructed, which includes an input layer that matches the data feature dimension, a convolution layer that uses convolution kernels to extract features, a pooling layer that downsamples the data to reduce the data dimension, a fully connected layer that fuses features, and an output layer whose structure is determined by the task. The corresponding loss function is defined, and the stochastic gradient descent optimization algorithm is selected to train the model. The training set data is input into the model, and the parameters are updated through forward propagation, loss calculation, and back propagation. The hyperparameters are adjusted according to the validation set results. The model is evaluated using the test set. If it does not meet the standards, it is returned for retraining. After the model training meets the standards, the model is deployed to the actual environment, and the light data is input into the model in real time and preprocessed. The model outputs the types and distribution of light sources in the current environment.

4. A light rail night driving lighting system for preventing glare interference according to claim 1, characterized in that The specific steps of generating lighting adjustment instructions in the intelligent analysis and decision module by combining weather conditions and driving section data are as follows: (1) Obtain geographic location information through vehicle-mounted GPS and determine the current road type through electronic map matching; (2) Retrieve applicable strategies from the preset strategy database based on the road type, combined with light, glare, and weather information; (3) Generate corresponding adjustment instructions for the brightness, color temperature, and light color of the lighting system based on the retrieved strategy; (4) Summarize the generated instructions, verify their integrity and rationality, convert them into a specific format, and send them to the lighting control execution module via a high-speed line.

5. The anti-glare interference light rail night driving lighting system according to claim 1, characterized in that, The preset strategy database in the intelligent analysis and decision-making module is: Adjustment strategy based on the glare area: Identify that a large area with high-intensity glare areas is concentrated in the front, reduce the brightness of the lighting fixtures in that direction, and adjust the light angle; when the glare areas are small and scattered, finely adjust the local lighting color temperature; Adjustment strategy based on the type and distribution of surrounding light sources: When the main surrounding light source is high-brightness natural light and is evenly distributed, reduce the overall brightness of the light rail lighting system, and at the same time adjust the color temperature to a higher value to simulate the natural light color; when the surrounding light source has a low color temperature and is distributed on both sides of the road, adjust the light rail lighting color temperature to a similar range and increase the brightness at the same time; Adjustment strategy based on weather conditions: In foggy weather, switch the lighting color to yellow light and increase the overall brightness; in rainy weather, reduce the lighting brightness and at the same time adjust the light angle to be more downward; Adjustment strategy based on the driving section: When the light rail is running in a tunnel, maintain a stable and relatively high lighting brightness; when running on an open track and the surrounding environmental light is sufficient, reduce the lighting brightness and finely adjust its own color temperature according to the ambient light color temperature; in special bridge sections, finely adjust the power output of the power supply to maintain the relative stability of the lighting brightness.

6. The anti-glare interference light rail night driving lighting system according to claim 1, characterized in that, The adjustment of the brightness, color temperature and light color of the lighting system in the lighting adjustment execution module; For the adjustment of brightness: The microprocessor receives the brightness adjustment instruction, analyzes the adjustment amplitude in the instruction, and according to the adjustment amplitude requirement, changes the duty cycle of the pulse width modulation signal to adjust the magnitude of the output current or voltage; For the adjustment of color temperature: Receive the color temperature adjustment instruction, extract the target color temperature value in the instruction. For a lighting system using a multi-light source combination, calculate the mixing ratio of light sources with different color temperatures according to the target color temperature, and adjust the luminous intensity of light sources with different color temperatures by controlling the drive current of various light sources; For the adjustment of light color: Receive the light color adjustment instruction, and adjust the light color according to the instruction by adjusting the excitation ratio of the internal phosphor or controlling the luminous intensity of different color chips.

7. The anti-glare interference light rail night driving lighting system according to claim 1, characterized in that, In the feedback monitoring module, the ambient light secondary monitoring data and the driver visual perception feedback data are analyzed through a feedback data evaluation algorithm. The formula is as follows: Where F v is the quantified value of the driver's visual perception feedback, E is the comprehensive feedback evaluation value, ω1 and ω2 are weight coefficients, and ω1 + ω2 = 1. L′ is the ambient light brightness related value before adjustment, and L″ is the ambient light brightness related value after adjustment.

Images