An intelligent light-sensing system for high-speed train headlights that adapts to changing line of sight distance

Abstract

This invention relates to the field of vehicle lighting technology, specifically to an intelligent light-sensing system for adaptively switching visibility distance in high-speed train headlights. In this embodiment, the dynamic visibility distance calculation module calculates the target visibility distance in real time based on collected environmental and train operating status parameters. This allows the system to flexibly adjust the headlight illumination range according to actual conditions, effectively avoiding safety risks caused by insufficient visibility. The fuzzy control module utilizes a fuzzy logic algorithm, combined with target visibility distance and environmental parameters, to output headlight control commands, precisely adjusting the headlight's illumination angle, color temperature, and light intensity level. Compared to traditional fixed parameter settings or simple adjustment methods, the fuzzy logic algorithm can handle the fuzziness and uncertainty of environmental factors, achieving refined and adaptive adjustment of headlight illumination parameters.

Description

Technical Field

[0001] This invention relates to the field of vehicle lighting technology, specifically to an intelligent light-sensing system for high-speed train headlights that adaptively switches viewing distance. Background Technology

[0002] In the rail transit sector, the performance of the lighting system for high-speed trains during nighttime or inclement weather is crucial to operational safety. With the rapid development of high-speed rail technology and the continuous increase in train speeds, higher demands are placed on the intelligence and adaptive capabilities of headlight lighting systems.

[0003] Traditional high-speed train headlight systems often employ fixed lighting parameter settings or rely solely on simple adjustments based on a single environmental factor (such as ambient light intensity), making it difficult to fully adapt to complex and changing environmental conditions. For example, in severe weather conditions such as heavy fog, heavy rain, and heavy snow, ambient visibility changes significantly, and train speed also affects the driver's required safe visibility distance. If the headlight beam angle, color temperature, and light intensity level cannot be precisely matched to the actual environment and driving conditions, it may lead to insufficient visibility or light scattering that interferes with the driver's vision, increasing driving safety hazards. Furthermore, existing technologies have weak multi-sensor data fusion processing capabilities, making it difficult to fully explore the correlation between environmental parameters and train operating status parameters, and thus unable to achieve refined and dynamic adjustment of headlight lighting parameters.

[0004] Therefore, designing a system that can perceive environmental parameters and train operating status in real time, accurately calculate target sight distance through intelligent algorithms, and adaptively adjust headlight lighting parameters accordingly has become a key technical issue for improving the safety performance of high-speed trains. Summary of the Invention

[0005] To address the aforementioned problems, this invention discloses an intelligent light-sensing system for train headlights that adaptively switches line of sight, comprising:

[0006] A multi-sensor fusion module is used to collect environmental parameter data, including light intensity, fog, rainfall, snowfall, and train operation status parameters.

[0007] The dynamic line-of-sight calculation module is used to calculate the target line-of-sight in real time based on the environmental parameters and train operation status parameters.

[0008] The fuzzy control module is used to output headlight control commands based on the target viewing distance and environmental parameters, using a fuzzy logic algorithm, to adjust the headlight's illumination angle, color temperature, and light intensity level.

[0009] The execution module is used to receive and execute the control commands to dynamically adjust the lighting parameters of the headlights.

[0010] In the above scheme, the multi-sensor fusion module includes: a light intensity sensor for detecting ambient light intensity; a fog sensor for detecting fog value; a rain sensor for detecting rain intensity; a snowfall sensor for detecting snowfall; and a speed sensor for acquiring the real-time speed of the train.

[0011] The dynamic line-of-sight calculation module includes:

[0012] The optical parameter calculation unit calculates the optical line of sight corresponding to environmental parameters based on the light intensity attenuation formula and the weather scattering coefficient.

[0013] The safe sight distance calculation unit calculates the safe sight distance based on train speed, braking time, and friction coefficient.

[0014] The judgment unit is used to take the smaller value between the optical line of sight and the safe line of sight as the target line of sight.

[0015] The fuzzy control module includes:

[0016] The fuzzy processing unit is used to map the relationship between input variables and output variables according to fuzzy processing rules. The input variables include ambient light intensity level, fog level, rainfall level and train speed level, and the output variables include headlight illumination angle, color temperature and light intensity level.

[0017] The execution module includes:

[0018] The driver module is used to adjust the output power of the laser diode via a PWM signal;

[0019] Optical modulation device, used to adjust the headlight's beam angle and color temperature;

[0020] The fault self-test unit is used to monitor the system's operating status and trigger a degraded operating mode.

[0021] In one embodiment, the intelligent light-sensing system for train headlights also includes an energy-saving control module, which is used to automatically switch to a low-power standby mode during the day or in tunnels; and dynamically adjust the PWM duty cycle of the laser diode according to the target line of sight to reduce energy consumption.

[0022] The intelligent light-sensing system for high-speed train headlights also includes a random perturbation generator, which is communicatively connected to the fuzzy control module. The random perturbation generator includes a command pre-perturbation unit, which dynamically preprocesses the control command based on the headlight control command type output by the fuzzy control module and current environmental parameters. When the control command is a light intensity level adjustment command, the command pre-perturbation unit superimposes a dynamically changing perturbation value on the target light intensity level. When the control command is an illumination angle adjustment command, the command pre-perturbation unit generates an angle adjustment amount with random offset based on the train's running speed and curve curvature parameters.

[0023] The random perturbation generator also includes a feedback adjustment unit, which is communicatively connected to the fault self-test unit and optical modulation device of the execution module. It is used to receive monitoring data of light source temperature, light decay, and lighting effect. The feedback adjustment unit adaptively adjusts the perturbation parameters according to the real-time monitoring data. When the light source temperature exceeds a preset threshold, it automatically reduces the light intensity perturbation amplitude and increases the fluctuation frequency. When a blind spot is detected, it dynamically increases the random offset of the illumination angle, forming a closed-loop adjustment mechanism.

[0024] The random perturbation generator and the fuzzy control module interact via a hybrid coding communication unit. This hybrid coding communication unit includes an coding module that dynamically adjusts the coding strategy based on the real-time transmission requirements of the data type. Specifically, control commands with high real-time requirements are encoded using fixed-length fast coding and an independent synchronization identifier is set. Periodically changing environmental parameters are encoded using differential coding, transmitting only the difference data from the previous frame. Perturbation parameters containing random characteristics are encrypted. The fuzzy control commands, random perturbation parameters, environmental parameters, and train operation status parameters are uniformly encoded to generate a composite data frame.

[0025] The composite data frame contains at least four data segments, each consisting of an identifier bit and data bits, wherein:

[0026] The first data segment stores the control command type identifier and the corresponding command data; the second data segment stores the perturbation parameter type identifier and the perturbation parameter value.

[0027] The third data segment stores the environment parameter type identifier and corresponding parameter set;

[0028] The fourth data segment stores the train operation status identifier and status data.

[0029] The dynamic sight distance calculation module in this embodiment calculates the target sight distance in real time based on collected environmental and train operating status parameters. This allows the system to flexibly adjust the headlight illumination range according to actual conditions, effectively avoiding safety risks caused by insufficient sight distance.

[0030] The fuzzy control module calculates the target viewing distance and environmental parameters to output headlight control commands, precisely adjusting the headlight's illumination angle, color temperature, and light intensity level. Compared to traditional fixed parameter settings or simple adjustments, the fuzzy control module can handle the fuzziness and uncertainty of environmental factors, achieving refined and adaptive adjustment of headlight lighting parameters. Attached Figure Description

[0031] Figure 1 This is an architectural diagram of an intelligent light-sensing system for adaptive switching of line of sight in a high-speed train headlight, as described in an embodiment of this application.

[0032] Figure 2 This is an architectural diagram of another adaptive switching line-of-sight intelligent light-sensing system for train headlights in this application embodiment.

[0033] Figure 3 This is a flowchart of the sensor data processing method in the embodiments of this application;

[0034] Figure 4 This is a flowchart of the control process of the fuzzy control module in the embodiments of this application. Detailed Implementation

[0035] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention. The principles and features of this invention are described below with reference to the accompanying drawings. The examples given are only for explaining this invention and are not intended to limit the scope of this invention.

[0036] The term "comprising" and other similar expressions used in the specification, claims, and accompanying drawings of this invention are intended to cover a non-exclusive inclusion, such as a process, method, system, or apparatus that includes a series of steps or units but is not limited to the steps or units listed.

[0037] Example 1: See Figure 1-2 An intelligent light-sensing system for high-speed train headlights that adaptively switches sight distances includes:

[0038] The multi-sensor fusion module is used to collect environmental parameter data, including light intensity, fog, rainfall, snowfall, and train operation status parameters.

[0039] In one embodiment, the multi-sensor fusion module includes the following sensors:

[0040] A light intensity sensor is used to detect ambient light intensity; a fog sensor is used to detect fog levels; a rain sensor is used to detect rain intensity; a snowfall sensor is used to detect snowfall; and a speed sensor is used to obtain the real-time speed of the train.

[0041] See Figure 3 Sensor data is processed through the following steps:

[0042] S01: Filter and normalize the raw sensor signal to eliminate noise interference; for example, the voltage value output by the haze sensor needs to be converted into a standardized haze level.

[0043] S02: Extract key feature parameters from the preprocessed data, such as ambient light intensity (I), haze value (H), and rainfall intensity (R);

[0044] S03: Using a weighting and thresholding method, the characteristic parameters of different sensors are integrated into a unified optical attenuation coefficient β. During the integration process, corresponding processing methods are determined for different weather types. For example, the scattering coefficient in foggy weather can be determined through the correlation between experimental calibration coefficients and fog concentration parameters; the attenuation coefficient in rainy weather increases accordingly with increasing rain intensity. After integrating the optical attenuation coefficient β, environmental parameters are standardized and preprocessed to convert them into a unified set of environmental characteristic parameters. Then, a pre-stored light intensity attenuation formula (calibrated through environmental simulation experiments) is called. Finally, the standardized parameters and the optical attenuation coefficient are substituted into the formula for iterative calculation, outputting the optical line of sight that reflects the upper limit of the actual detection capability of the visual monitoring system.

[0045] The dynamic line-of-sight calculation module is used to calculate the target line-of-sight in real time based on environmental parameters and train operating status parameters;

[0046] In one embodiment, the dynamic line-of-sight calculation module includes:

[0047] The optical parameter calculation unit calculates the optical line of sight corresponding to environmental parameters based on the light intensity attenuation formula and the weather scattering coefficient.

[0048] The safe sight distance calculation unit calculates the safe sight distance based on train speed, braking time, and friction coefficient.

[0049] The judgment unit is used to take the smaller value between the optical line of sight and the safe line of sight as the target line of sight.

[0050] In one embodiment, the optical parameter calculation unit acquires real-time environmental parameters such as visibility level, precipitation intensity, airborne particulate matter concentration, and light intensity by connecting to a train external environment monitoring sensor group. In data processing, the environmental parameters are first standardized and preprocessed to convert them into a unified set of environmental characteristic parameters. Then, a pre-stored light intensity attenuation formula (calibrated through environmental simulation experiments) is called, and the weather scattering coefficient is matched to the characteristic parameters using a scattering coefficient mapping table based on the environmental parameters. Finally, the standardized parameters and scattering coefficient are substituted into the formula for iterative calculation, outputting the optical line of sight that reflects the upper limit of the actual detection capability of the visual monitoring system.

[0051] The safe line-of-sight calculation unit interacts in real time with the train's onboard control system to obtain key parameters such as current speed, braking system response time, and friction coefficient between the rail surface and wheels. During the calculation, the train speed unit is first converted from km / h to m / s; then the braking process is broken down, calculating the uniform travel distance (speed × response time) within the braking response time and the deceleration braking distance after braking takes effect; the safe line-of-sight is the sum of these two, ensuring the train can come to a complete stop in front of the target object.

[0052] The judgment unit receives two line-of-sight data in real time and compares the values ​​through built-in comparison logic: when the optical line-of-sight is greater than or equal to the safe line-of-sight, the safe line-of-sight is used as the target line-of-sight to ensure braking reaction distance; when the optical line-of-sight is less than the safe line-of-sight, the optical line-of-sight is used as the target line-of-sight to avoid the risk of collision due to insufficient line-of-sight.

[0053] The fuzzy control module is used to output headlight control commands based on the target viewing distance and environmental parameters, using fuzzy logic algorithms to adjust the headlight's illumination angle, color temperature, and light intensity level.

[0054] In one specific implementation, the fuzzy control module adopts an ECU module, specifically including:

[0055] The fuzzy processing unit is used to map the relationship between input variables and output variables according to fuzzy processing rules. The input variables include ambient light intensity level, fog level, rainfall level and train speed level, and the output variables include headlight illumination angle, color temperature and light intensity level.

[0056] For example, the fuzzing rules include:

[0057] If the light intensity is low and the haze is heavy, then the color temperature is yellow, the illumination angle is small, and the light intensity setting is 5.

[0058] If heavy rainfall AND high speed, then visibility is reduced, light intensity level 4

[0059] If snowfall is moderate AND light intensity is moderate, then the color temperature is green, the angle of illumination is moderate, and the light intensity setting is 3.

[0060] Quantize and partition the input variables into intervals:

[0061] Light intensity: Low (0-500cd), Medium (500-1500cd), High (1500-3000cd)

[0062] Haze levels: Light (0%–20%), Medium (20%–50%), Heavy (50%–100%)

[0063] Rainfall: None (0.1 mm / min), Light (13 mm / min), Moderate (36 mm / min), Heavy (610 mm / min)

[0064] Speed: Low speed (0-100km / h), medium speed (100-160km / h), high speed (160-350km / h);

[0065] See Figure 4 The control process includes the following steps:

[0066] S21: Convert the raw sensor data into membership function values; for example, when the light intensity is 800 cd, the membership function is "low": 0.2, "medium": 0.8, "high": 0.0;

[0067] S22: Reasoning is performed based on the fuzzy rule base to generate fuzzy control output; the Zadeh approximate reasoning method is used to take the minimum value between the condition and the conclusion as the output;

[0068] S23: Convert fuzzy output into specific control commands using the centroid method or the maximum membership method. For example, when the fuzzy output is "short viewing distance", it is mapped to an illumination angle of 15°, a yellow color temperature, and a light intensity level of 5.

[0069] In this embodiment, the fuzzy processing unit maps the relationship between input and output variables according to fuzzy processing rules. This fuzzy logic processes some vague and uncertain information without requiring precise mathematical models, making it particularly suitable for factors like environmental conditions that are difficult to quantify precisely. For example, light intensity, fog, and rainfall can be processed using interval partitioning and membership functions. Even if the actual data are not precise numerical values, their fuzzy level can be accurately determined, thus better aligning with human perception and processing of the environment.

[0070] Through fuzzy control algorithms, the headlights can adaptively adjust based on real-time environmental conditions and train status. For example, when ambient light is low and fog is heavy, the color temperature is adjusted to yellow, the beam angle is reduced, and the beam intensity level is set to 5. This adjustment provides better illumination in adverse conditions, enhances driver visibility, and improves driving safety. Similarly, when there is heavy rain and high train speed, visibility is reduced, and the beam intensity level is adjusted accordingly to ensure adequate illumination under these conditions.

[0071] Furthermore, the fuzzy control algorithm has low computational complexity, approximately 50 μs, which meets the real-time requirements of the high-speed rail ECU (Electronic Control Unit). During high-speed rail operation, the headlights can quickly adjust according to changes in the environment and train status, responding promptly to various situations and ensuring the effectiveness and reliability of the lighting system.

[0072] By converting raw sensor data into membership function values, performing inference based on a fuzzy rule base, and using the centroid method or maximum membership method to convert fuzzy outputs into specific control commands, the entire control process exhibits a certain degree of standardization and systematicity. The method in this embodiment simplifies the conversion process from raw data to final control commands, facilitating system implementation and maintenance.

[0073] The execution module is used to receive and execute control commands to dynamically adjust the lighting parameters of the headlights.

[0074] In one embodiment, the execution module includes:

[0075] The driver module is used to adjust the output power of the laser diode via a PWM signal;

[0076] An optical modulation device is used to adjust the illumination angle and color temperature of the headlight; in one specific embodiment, the optical modulation device may be a microelectromechanical system (MEMS) modulator.

[0077] The fault self-diagnostic unit monitors the system's operating status and triggers a degraded operating mode. Specifically, it monitors the ECU's operating status; if the status is not refreshed within a preset time (500ms), the system is forcibly restarted. The ECU continuously monitors the status of each sensor and actuator module; when a fault is detected, it is immediately recorded and uploaded to the train control system. In the event of partial sensor failure, the system can switch to a single-sensor mode or a preset safety mode.

[0078] In one specific implementation, the dynamic line-of-sight calculation module can be an ECU processor.

[0079] The drive module is a laser drive module, such as a PWM constant current drive module containing an FP7125 drive chip; the fog and rain sensors are connected to the ECU via an ADC module.

[0080] Example 2: In one embodiment, the intelligent light-sensing system for train headlights further includes an energy-saving control module, which is used to automatically switch to a low-power standby mode during the day or in a tunnel; and dynamically adjust the PWM duty cycle of the laser diode according to the target line of sight to reduce energy consumption.

[0081] The laser diode current can be adjusted via PWM according to the line-of-sight setting; lower settings reduce the duty cycle to save energy. For example:

[0082] Short viewing distance setting (500m): PWM duty cycle 40%, light intensity setting 3

[0083] Medium viewing distance (1000m): PWM duty cycle 60%, light intensity setting 4

[0084] Long viewing distance setting (2000m): PWM duty cycle 90%, light intensity setting 5.

[0085] The intelligent light-sensing system for high-speed train headlights also includes a random perturbation generator, which is communicatively connected to the fuzzy control module. The random perturbation generator includes a command pre-perturbation unit, which is used to dynamically preprocess the control command based on the type of headlight control command output by the fuzzy control module and the current environmental parameters. When the control command is a light intensity level adjustment command, the command pre-perturbation unit superimposes a dynamically changing perturbation value on the target light intensity level. When the control command is an illumination angle adjustment command, the command pre-perturbation unit generates an angle adjustment amount with random offset based on the train's running speed and curve curvature parameters.

[0086] The random perturbation generator also includes a feedback adjustment unit, which is communicatively connected to the fault self-test unit and optical modulation device of the execution module. It is used to receive monitoring data on light source temperature, light decay, and lighting effect. The feedback adjustment unit adaptively adjusts the perturbation parameters based on real-time monitoring data. When the light source temperature exceeds a preset threshold, it automatically reduces the light intensity perturbation amplitude and increases the fluctuation frequency. When a blind spot is detected, it dynamically increases the random offset of the illumination angle, forming a closed-loop adjustment mechanism.

[0087] The random perturbation generator and the fuzzy control module interact via a hybrid coding communication unit. This unit includes an coding module that dynamically adjusts the coding strategy based on the real-time transmission requirements of the data type. Specifically, it employs fixed-length fast coding for control commands with high real-time requirements and sets an independent synchronization identifier; differential coding is used for periodically changing environmental parameters, transmitting only the difference data from the previous frame; and encrypted coding is used for perturbation parameters containing random characteristics. The fuzzy control commands, random perturbation parameters, environmental parameters, and train operation status parameters are uniformly encoded to generate a composite data frame.

[0088] The composite data frame contains at least four data segments, each consisting of an identifier bit and data bits, wherein:

[0089] The first data segment stores the control command type identifier and the corresponding command data; the second data segment stores the perturbation parameter type identifier and the perturbation parameter value.

[0090] The third data segment stores the environment parameter type identifier and corresponding parameter set;

[0091] The fourth data segment stores the train operation status identifier and status data.

[0092] The headlight control commands (including illumination angle, color temperature, and light intensity level) output by the fuzzy control module are first sent to the command pre-perturbation unit of the random perturbation generator before being transmitted to the execution module. This unit performs targeted preprocessing of the commands based on their type and current environmental parameters.

[0093] When the fuzzy control module outputs a high-brightness light intensity setting command, the pre-perturbation unit superimposes a perturbation value that dynamically changes over time onto the command to prevent the light source from overheating due to prolonged operation at a fixed high power. For example, when the light intensity setting is at its highest level, a random fluctuation with an amplitude within ±5% and a frequency of 0.5Hz is introduced to both ensure illumination intensity and reduce the rate of light decay.

[0094] For illumination angle adjustment commands, the pre-perturbation unit combines train speed and curve curvature information to generate an angle adjustment amount with random offset. For example, when traveling on a curve, in addition to executing the fixed angle adjustment value calculated by the fuzzy control module, an additional ±0.2° random oscillation is added to make the beam coverage more flexible and effectively reduce illumination blind spots.

[0095] When communicating between the random perturbation generator and the fuzzy control module, fuzzy control commands, random perturbation parameters, environmental parameters (light intensity, fog, etc.), and train operation status parameters are uniformly encoded and packaged into composite data frames. For example, the data frame format is "[control command identifier + command data][perturbation parameter identifier + parameter value][environmental parameter identifier + parameter set][operation status identifier + status data]", thereby reducing the number of communication operations and improving data transmission efficiency.

[0096] Example 3: In order to address scenarios that traditional solutions cannot handle, such as "sensor failure", "sudden light source failure" and "extreme weather (such as blizzards and sandstorms)", the random perturbation generator also includes a fault-adaptive perturbation unit.

[0097] When the "haze sensor fails" (can only detect light intensity data), the change in reflected light after light intensity perturbation (e.g., when the light intensity perturbation is ±5%, if the change in reflected light is >10%, it is determined to be dense fog) is reversed to determine the fog level, and then the corresponding perturbation strategy is matched (e.g., if the change in reflected light is large, the perturbation amplitude is reduced).

[0098] When "single headlight source suddenly loses light (>50%)": the fault adaptation micro-perturbation unit starts "compensation micro-perturbation" for the "normal side headlight", the light intensity micro-perturbation amplitude is increased to 1.5 times the original amplitude, and the illumination angle micro-perturbation is shifted to the "fault side" by 1-2°. The micro-perturbation covers the lighting blind spot of the fault side, avoiding visual imbalance caused by instantaneous single-sided lighting failure.

[0099] When a "sandstorm weather (visibility < 50m)" is detected: the fault adaptation perturbation unit starts "pulse perturbation", outputting a perturbation mode of "strong light pulse (instantaneous increase of light intensity by 30%) + weak light transition (light intensity returns to normal)" at a frequency of "0.5 seconds / time". The pulsed strong light breaks through the sand and dust obstruction, while the weak light transition avoids visual fatigue.

[0100] The technical means disclosed in this invention are not limited to those disclosed in the above embodiments, but also include technical solutions composed of any combination of the above technical features. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this invention, and these improvements and modifications are also considered within the scope of protection of this invention.

Claims

1. A self-adaptive switching range light motorcar headlight intelligent photosensitive system, characterized in that, include: A multi-sensor fusion module is used to collect environmental parameter data, including light intensity, fog, rainfall, snowfall, and train operation status parameters. The dynamic line-of-sight calculation module is used to calculate the target line-of-sight in real time based on the environmental parameters and train operation status parameters. The fuzzy control module is used to output headlight control commands based on the target viewing distance and environmental parameters, using a fuzzy logic algorithm, to adjust the headlight's illumination angle, color temperature, and light intensity level. An execution module is used to receive and execute the control commands to dynamically adjust the lighting parameters of the headlights; The intelligent light-sensing system for high-speed train headlights also includes a random perturbation generator, which is communicatively connected to the fuzzy control module. The random perturbation generator includes a command pre-perturbation unit, which dynamically preprocesses the control command based on the headlight control command type output by the fuzzy control module and current environmental parameters. When the control command is a light intensity level adjustment command, the command pre-perturbation unit superimposes a dynamically changing perturbation value on the target light intensity level. When the control command is an illumination angle adjustment command, the command pre-perturbation unit generates an angle adjustment amount with random offset based on the train's running speed and curve curvature parameters.

2. The intelligent light-sensing system for train headlights according to claim 1, characterized in that, The random perturbation generator and the fuzzy control module interact via a hybrid coding communication unit. This hybrid coding communication unit includes an coding module that dynamically adjusts the coding strategy based on the real-time transmission requirements of the data type. Specifically, control commands with high real-time requirements are encoded using fixed-length fast coding and an independent synchronization identifier is set. Periodically changing environmental parameters are encoded using differential coding, transmitting only the difference data from the previous frame. Perturbation parameters containing random characteristics are encrypted. The fuzzy control commands, random perturbation parameters, environmental parameters, and train operation status parameters are uniformly encoded to generate a composite data frame.

3. The intelligent light-sensing system for train headlights according to claim 2, characterized in that, The composite data frame contains at least four data segments, each consisting of an identifier bit and data bits, wherein: The first data segment stores the control command type identifier and the corresponding command data; the second data segment stores the perturbation parameter type identifier and the perturbation parameter value. The third data segment stores the environment parameter type identifier and corresponding parameter set; The fourth data segment stores the train operation status identifier and status data.

4. The intelligent light-sensing system for train headlights according to claim 2, characterized in that, The random perturbation generator also includes a fault-adaptive perturbation unit, which is used to generate risk-hedging perturbation strategies for sensor failure, sudden light source failure and extreme weather scenarios, so as to ensure the basic lighting function of the lighting system under fault or extreme conditions. The specific working logic of the fault adaptation perturbation unit includes at least one of the following: (1) When the fog sensor fails and only ambient light intensity data can be acquired, the light intensity perturbation command with a preset amplitude is output to the execution module, and the reflected light change data after the light intensity perturbation is collected and analyzed. If the reflected light change amplitude is >10%, the current environment is determined to be a dense fog scene, and the light intensity perturbation amplitude is reduced accordingly; if the reflected light change amplitude is ≤10%, the perturbation strategy under the normal fog scene is matched. (2) When the fault self-test unit detects that the light decay of the headlight source on one side is greater than 50%, the light intensity perturbation amplitude of the normal side headlight is increased to 1.5 times the original light intensity perturbation amplitude, and at the same time, the illumination angle perturbation command is output to the optical modulation device to make the illumination angle of the normal side headlight shift 1-2° to the fault side, so as to cover the illumination blind spot of the fault side headlight through perturbation adjustment. (3) When the multi-sensor fusion module detects that the current environment is a sandstorm and the visibility is <50m, it generates a periodic light intensity perturbation command at a frequency of 0.5 seconds / time. The light intensity perturbation command includes a strong light pulse segment and a weak light transition segment. The instantaneous light intensity value of the strong light pulse segment is 30% higher than the current target light intensity, and the light intensity value of the weak light transition segment drops back to the current target light intensity. The strong light pulse breaks through the sandstorm obstruction, while the weak light transition avoids driver visual fatigue.

5. The intelligent light-sensing system for train headlights according to claim 1, characterized in that, The random perturbation generator also includes a feedback adjustment unit, which is communicatively connected to the fault self-test unit and optical modulation device of the execution module, and is used to receive monitoring data of light source temperature, light decay degree and lighting effect. The feedback adjustment unit adaptively adjusts the perturbation parameters based on real-time monitoring data. When the light source temperature exceeds a preset threshold, it automatically reduces the light intensity perturbation amplitude and increases the fluctuation frequency. When a blind spot is detected, it dynamically increases the random offset of the illumination angle, forming a closed-loop adjustment mechanism.

6. The intelligent light-sensing system for train headlights according to claim 1, characterized in that, The multi-sensor fusion module includes: a light intensity sensor for detecting ambient light intensity; a fog sensor for detecting fog intensity; a rain sensor for detecting rain intensity; a snowfall sensor for detecting snowfall; and a speed sensor for acquiring the real-time speed of the train.

7. The intelligent light-sensing system for train headlights according to claim 1, characterized in that, The dynamic line-of-sight calculation module includes: The optical parameter calculation unit calculates the optical line of sight corresponding to environmental parameters based on the light intensity attenuation formula and the weather scattering coefficient. The safe sight distance calculation unit calculates the safe sight distance based on train speed, braking time, and friction coefficient. The judgment unit is used to take the smaller value between the optical line of sight and the safe line of sight as the target line of sight.

8. The intelligent light-sensing system for train headlights according to claim 1, characterized in that, The fuzzy control module includes: The fuzzy processing unit is used to map the relationship between input variables and output variables according to fuzzy processing rules. The input variables include ambient light intensity level, fog level, rainfall level and train speed level, and the output variables include headlight illumination angle, color temperature and light intensity level.

9. The intelligent light-sensing system for train headlights according to claim 1, characterized in that, The execution module includes: The driver module is used to adjust the output power of the laser diode via a PWM signal; Optical modulation device, used to adjust the headlight's beam angle and color temperature; The fault self-test unit is used to monitor the system's operating status and trigger a degraded operating mode.

10. The intelligent light-sensing system for train headlights according to claim 1, characterized in that, The intelligent light-sensing system for high-speed train headlights also includes an energy-saving control module, which is used to automatically switch to a low-power standby mode during the day or in tunnels; and dynamically adjust the PWM duty cycle of the laser diode according to the target line of sight to reduce energy consumption.

Images