Method, device and equipment for synchronously adjusting global illumination brightness of train and medium

Abstract

The invention relates to a method, a device and equipment for synchronously adjusting global illumination brightness of a train and a medium. The method comprises the following steps: acquiring a plurality of illumination data of a first train and a tail train of the train; performing data verification on the illumination data to remove corresponding abnormal data, and calculating the illumination data after the abnormal data is removed through dynamic weighting to obtain a current average illumination value; based on the current average illumination value, obtaining an illumination change trend in a preset time period through a preset illumination prediction model; generating an illumination adjustment instruction according to the illumination change trend, and synchronously issuing the illumination adjustment instruction to each compartment through a ring topology network; and calling a local dynamic gradient dimming algorithm to generate dimming control parameters based on the illumination adjustment instruction, and further controlling the illumination equipment to execute brightness adjustment operation. The method has the effect of reducing the brightness difference of the train carriages.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent lighting for rail transit, and in particular to a method, device, equipment and medium for synchronously adjusting the global lighting brightness of a train. Background Art

[0002] At present, train lighting systems are widely used in rail transit scenarios such as high-speed railways, subways and intercity railways. They are mainly used to provide passengers with a stable and comfortable lighting environment, and adjust the brightness inside the car according to changes in the external environment to enhance the riding experience.

[0003] Existing train lighting systems typically adopt a single-carriage independent control mode, that is, each car is separately equipped with a light sensor, dimming controller and lighting driver module, and the brightness is adjusted according to the ambient light data collected by each car. However, this method has the following problems during application: the brightness adjustment of each car is inconsistent due to factors such as differences in perception position, local environmental interference, and asynchronous acquisition delays. In addition, the response time of each car varies in scenarios with sudden changes in lighting, such as when entering and exiting tunnels or bridges, which can easily cause a sense of visual fragmentation and affect the passenger experience.

[0004] The above-mentioned existing technical solutions have the following defects: the existing train lighting control method is difficult to synchronously adjust the brightness within the entire carriage range, resulting in large differences in brightness between different carriages, so there is room for improvement. Summary of the Invention

[0005] In order to reduce the brightness difference among train compartments, the present application provides a method, device, equipment and medium for synchronously adjusting the global lighting brightness of a train.

[0006] The above-mentioned invention objective of this application is achieved through the following technical solutions: A method for synchronously adjusting the brightness of global lighting on a train, comprising: Obtain some lighting data of the first and last cars of the train; Performing data verification on the illumination data to eliminate corresponding abnormal data, and calculating the illumination data after eliminating the abnormalities through dynamic weighting to obtain a current average illumination value; Based on the current average light value, obtaining a light change trend within a preset time period through a preset light prediction model; generating a lighting adjustment instruction according to the lighting change trend, and synchronously sending the lighting adjustment instruction to each carriage through a ring topology network; Based on the lighting adjustment instruction, a local dynamic gradient dimming algorithm is called to generate dimming control parameters, thereby controlling the lighting device to perform a brightness adjustment operation.

[0007] By adopting the above technical solution, by obtaining a number of lighting data from the first and last cars of the train, it is possible to perceive the changes in ambient light at both ends of the train in real time, thereby improving the response speed and accuracy to changes in the overall external light level; by performing data verification on the lighting data and dynamically weighted calculation of the current average lighting value, it is possible to effectively eliminate abnormal fluctuating data and adaptively adjust the lighting perception weight based on the operating status, thereby improving the stability and reliability of environmental perception; by using the lighting prediction model based on the current average lighting value to obtain future lighting change trends, it is possible to predict the dynamics of ambient light changes in advance, thereby optimizing the dimming strategy and improving the foresight of lighting control; by generating lighting adjustment instructions based on the lighting change trend and simultaneously issuing them to each car, it is possible to ensure the consistency and synchronization of the lighting adjustment actions in each car, thereby avoiding visual discomfort to passengers caused by sudden changes in lighting between cars and improving overall riding comfort.

[0008] In one example, the present application may be further configured as follows: performing data verification on the illumination data to eliminate corresponding abnormal data, and calculating the illumination data after eliminating the abnormalities by dynamic weighting to obtain a current average illumination value, specifically including: When any of the illumination data deviates from the floating range of the average illumination data on the same side, the illumination data deviating from the range is determined to be abnormal data, and the abnormal data is eliminated to obtain the illumination data of the first vehicle and the illumination data of the last vehicle; The current average illumination value E_avg is calculated according to the preset dynamic weighted formula E_avg=α×E_front+β×E_rear, wherein E_front is the illumination data of the first train, E_rear is the illumination data of the last train, α and β are the weight values of the corresponding data respectively, α+β=1, and the weight value is dynamically adjusted according to the train driving conditions.

[0009] By adopting the above technical solution, abnormal data is eliminated when the illumination data deviates from the floating range of the average illumination data on the same side. Abnormal fluctuating data caused by factors such as occlusion and instantaneous sensor failure can be accurately eliminated, thereby improving the accuracy and reliability of the overall illumination perception data; by calculating the current average illumination value according to the dynamic weighted formula and dynamically adjusting the illumination data weights of the first and last trains in combination with the train driving conditions, it is possible to adapt to the sensitivity requirements of different operating scenarios to illumination changes, thereby improving the accuracy of the illumination perception data in reflecting the actual changes in the train environment, and further supporting the accurate implementation of subsequent predictions and dimming actions.

[0010] In one example, the present application may be further configured as follows: the weight value is dynamically adjusted according to the train running conditions, specifically including: Obtaining the train speed, and when the train speed reaches a preset high-speed threshold, increasing the first train illumination weight α according to a preset speed-weight curve to improve the response speed to changes in ambient light ahead of the train; The external environment brightness is obtained, and the variation range of the external environment brightness is calculated. When the variation range exceeds a preset brightness variation threshold, the first vehicle illumination weight α is increased using a preset environment-weight curve.

[0011] By adopting the above technical solution, by obtaining the train speed and adjusting the lighting weight of the first car according to the speed-weight curve when the high-speed threshold is reached, it is possible to prioritize the perception of forward environmental changes in high-speed driving environments, thereby improving the timeliness of lighting response in drastic changes such as tunnel entrances and bridge entrances and exits; by obtaining the brightness change range of the external environment and increasing the lighting weight of the first car according to the environment-weight curve when the change range exceeds the preset threshold, it is possible to dynamically improve the prediction foresight in the case of sudden changes in external lighting, thereby improving the sensitivity and adaptability of the overall lighting adjustment strategy, and ensuring that the train maintains good lighting continuity and comfort in complex environmental changes.

[0012] In one example, the present application may be further configured as follows: the construction of the illumination prediction model specifically includes: Obtaining historical lighting data of the train under different operating environments, and classifying the historical lighting data according to the train operating scenes and lighting change characteristics to obtain a training data set; The preset long short-term memory neural network model is trained based on the training data set, and the illumination change trend within a preset time period is predicted according to the correlation law between the ambient illumination change and the illumination trend, thereby obtaining the illumination prediction model.

[0013] By adopting the above technical solution, by obtaining historical lighting data of trains under different operating environments and classifying them to establish training data sets, it is possible to build a sample base of lighting changes covering a variety of typical operating scenarios, thereby improving the lighting prediction model's learning accuracy of actual environmental changes; by training a long-short-term memory neural network model based on the training data set and establishing lighting trend prediction capabilities, the model can grasp the inherent correlation between environmental changes and lighting changes, thereby achieving accurate prediction of future short-term lighting trends in actual operation, optimizing lighting control decisions in advance, and improving the intelligence and initiative level of train lighting adjustment.

[0014] In one example, the present application may be further configured as follows: synchronously sending the lighting adjustment instruction to each carriage via a ring topology network specifically includes: Building a train network architecture based on the TRDP communication protocol, interconnecting the car nodes in a ring manner, thereby obtaining the ring topology network; A unified command effective time is set for the lighting adjustment instruction and a timestamp is added, and the timestamp and the lighting adjustment instruction are sent through the ring topology network.

[0015] By adopting the above technical solution and building a train network architecture in which each car node is interconnected in a ring manner based on the TRDP communication protocol, it is possible to ensure that lighting adjustment instructions are transmitted stably and at high speed between the cars of the train, and that the issuance of instructions is uninterrupted even in the event of a single point failure, thereby improving the reliability of lighting control communication for the entire train; by setting a unified command effective time for the lighting adjustment instructions and attaching a timestamp mark, it is possible to achieve synchronous execution of lighting adjustment actions by each car node according to a unified time point, thereby effectively avoiding the visual fragmentation caused by the asynchronous lighting brightness change time between cars, and further enhancing the overall visual experience of passengers.

[0016] In one example, the present application may be further configured as follows: based on the lighting adjustment instruction, calling a local dynamic gradient dimming algorithm to generate dimming control parameters, and then controlling the lighting device to perform a brightness adjustment operation, specifically including: Parsing the lighting adjustment instruction and the timestamp mark, extracting the target brightness value and the timestamp information, obtaining the actual brightness value of the current lighting device, and calculating the brightness difference between the actual brightness value and the target brightness; Based on a dynamic gradient dimming algorithm, a continuously changing brightness adjustment amplitude is calculated according to the brightness difference and a preset adjustment time period, and an adjustment start time is generated according to the timestamp information; The dimming control parameter is generated according to the brightness adjustment amplitude and the adjustment start time, and the brightness adjustment operation is performed according to the dimming control parameter.

[0017] By adopting the above technical solution, by parsing the lighting adjustment instructions and timestamp information to extract the target brightness value and the current actual brightness and calculate the brightness difference, it is possible to provide an accurate difference basis for subsequent dimming actions, thereby ensuring that the dimming process is precise and controllable; by calculating the continuous brightness adjustment amplitude according to the brightness difference and the preset adjustment time period based on the dynamic gradient dimming algorithm, and generating a specific dimming start time, it is possible to achieve a smooth gradual change in brightness, avoiding abrupt perception by passengers due to large jumps; by generating dimming control parameters based on the brightness adjustment amplitude and adjustment start time and executing the brightness adjustment operation, it is possible to achieve a uniform and natural brightness transition within the set time, thereby improving the comfort and transition continuity of the train lighting environment changes.

[0018] The second object of the present invention is achieved through the following technical solutions: A device for synchronously adjusting the brightness of global lighting on a train, comprising: Lighting data acquisition module, used to obtain some lighting data of the first and last cars of the train; an illumination data processing module for performing data verification on the illumination data to eliminate corresponding abnormal data, and calculating the illumination data after eliminating abnormalities by dynamic weighting to obtain a current average illumination value; A lighting trend prediction module, configured to obtain a lighting change trend within a preset time period based on the current average lighting value using a preset lighting prediction model; A lighting instruction generation module is used to generate a lighting adjustment instruction according to the lighting change trend, and synchronously send the lighting adjustment instruction to each carriage through a ring topology network; The dynamic gradient dimming module is used to call a local dynamic gradient dimming algorithm to generate dimming control parameters based on the lighting adjustment instruction, and then control the lighting device to perform a brightness adjustment operation.

[0019] By adopting the above technical solution, by obtaining a number of lighting data from the first and last cars of the train, it is possible to perceive the changes in ambient light at both ends of the train in real time, thereby improving the response speed and accuracy to changes in the overall external light level; by performing data verification on the lighting data and dynamically weighted calculation of the current average lighting value, it is possible to effectively eliminate abnormal fluctuating data and adaptively adjust the lighting perception weight based on the operating status, thereby improving the stability and reliability of environmental perception; by using the lighting prediction model based on the current average lighting value to obtain future lighting change trends, it is possible to predict the dynamics of ambient light changes in advance, thereby optimizing the dimming strategy and improving the foresight of lighting control; by generating lighting adjustment instructions based on the lighting change trend and simultaneously issuing them to each car, it is possible to ensure the consistency and synchronization of the lighting adjustment actions in each car, thereby avoiding visual discomfort to passengers caused by sudden changes in lighting between cars and improving overall riding comfort.

[0020] The third objective of this application is achieved through the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for synchronously adjusting the global illumination brightness of a train are implemented.

[0021] The fourth objective of this application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for synchronously adjusting the global illumination brightness of a train.

[0022] In summary, this application has the following beneficial technical effects: 1. By acquiring lighting data from the first and last cars of a train, it is possible to perceive changes in ambient light at both ends of the train in real time, thereby improving the speed and accuracy of responding to changes in the overall external light level. By verifying the lighting data and dynamically weighting the current average lighting value, it is possible to effectively eliminate abnormal fluctuations and adaptively adjust the lighting perception weight based on the operating status, thereby improving the stability and reliability of environmental perception. By using the lighting prediction model based on the current average lighting value to determine future lighting change trends, it is possible to predict the dynamics of ambient light changes in advance, thereby optimizing the dimming strategy and improving the foresight of lighting control. By generating lighting adjustment instructions based on the lighting change trends and simultaneously issuing them to each car, it is possible to ensure the consistency and synchronization of lighting adjustment actions in each car, thereby avoiding visual discomfort for passengers caused by sudden changes in lighting between cars and improving overall riding comfort. 2. By eliminating abnormal data when it deviates from the floating range of the average illumination data on the same side, it can accurately eliminate abnormal fluctuations caused by factors such as occlusion and instantaneous sensor failure, thereby improving the accuracy and reliability of the overall illumination perception data. By calculating the current average illumination value according to a dynamic weighting formula and dynamically adjusting the illumination data weights of the first and last trains based on the train's driving conditions, it can adapt to the sensitivity of different operating scenarios to illumination changes, thereby improving the accuracy of illumination perception data in reflecting actual changes in the train environment, further supporting the accurate implementation of subsequent predictions and dimming actions. 3. By obtaining the train speed and adjusting the lighting weight of the first car according to the speed-weight curve when the high-speed threshold is reached, it is possible to prioritize the perception of forward environmental changes in high-speed driving environments, thereby improving the timeliness of lighting response in drastic changes such as tunnel entrances and bridge entrances and exits; by obtaining the range of changes in external environmental brightness and increasing the lighting weight of the first car according to the environment-weight curve when the range of changes exceeds the preset threshold, it is possible to dynamically improve the prediction foresight in the event of sudden changes in external lighting, thereby improving the sensitivity and adaptability of the overall lighting adjustment strategy, ensuring that the train maintains good lighting continuity and comfort in complex environmental changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a method for synchronously adjusting the global illumination brightness of a train in one embodiment of the present application; Figure 2 This is the architecture diagram of the train lighting synchronization control system of this application; Figure 3 This is a flowchart for implementing step S20 in the method for synchronously adjusting the global illumination brightness of a train in one embodiment of the present application; Figure 4 This is a flowchart for implementing step S22 in the method for synchronously adjusting the global illumination brightness of a train in one embodiment of the present application; Figure 5This is a flowchart for implementing step S30 in the method for synchronously adjusting the global illumination brightness of a train in one embodiment of the present application; Figure 6 This is a flowchart for implementing step S40 in the method for synchronously adjusting the global illumination brightness of a train in one embodiment of the present application; Figure 7 This is a flowchart for implementing step S50 in the method for synchronously adjusting the global illumination brightness of a train in one embodiment of the present application; Figure 8 This is a principle block diagram of a device for synchronously adjusting the global illumination brightness of a train in one embodiment of the present application; Figure 9 It is a schematic diagram of a device in one embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below with reference to the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a method for synchronously adjusting the global illumination brightness of a train, which specifically includes the following steps: S10: Obtain some lighting data of the first and last cars of the train.

[0026] Specifically, if Figure 2 As shown in the architecture diagram of the train lighting synchronization control system, multiple light sensors ALS are installed in the first and last cars of the train. The lighting data of the light sensors are obtained by the lighting controller and transmitted to the central control system via Ethernet. By setting a unified sampling period, for example, synchronous collection every 50ms, the light data of the first and last cars are ensured to have strict consistency and time series comparability. At the same time, preliminary filtering is performed during the collection process to remove obvious noise data, thereby obtaining some light data of the first and last cars.

[0027] S20: performing data verification on the illumination data to eliminate corresponding abnormal data, and calculating the illumination data after eliminating the abnormalities through dynamic weighting to obtain the current average illumination value.

[0028] Specifically, based on the synchronously collected lighting data of the first and last trains, the mean is first calculated for each data set, and a floating detection threshold is set as the elimination criterion. When the deviation of any lighting data from the lighting mean on the same side exceeds the set floating range, for example, ±10%, the data can be judged as abnormal data and eliminated. After elimination, the lighting mean of the first train and the lighting mean of the last train are recalculated based on the valid data set, and then the effective mean values of the first and last trains are combined through dynamic weighting to obtain the average lighting value of the current train as a whole. In the dynamic weighting process, the weights of the first and last trains are dynamically adjusted according to the real-time train operation status to improve the overall perception accuracy.

[0029] S30: Based on the current average illumination value, obtain an illumination change trend within a preset time period through a preset illumination prediction model.

[0030] Specifically, the currently calculated average illumination value is used as input data and input into a pre-trained illumination prediction model. The time series analysis module within the model is called to perform trend analysis on the input illumination value. The long short-term memory network is used to learn and infer the illumination change characteristics at consecutive moments, and the short-term trend prediction of illumination change is completed within the model. The prediction time period can be set to 1 second in the future. According to the model output, the direction and amplitude trend of the ambient illumination change of the train within the preset time period are obtained to guide the generation of subsequent lighting control strategies.

[0031] S40: Generate lighting adjustment instructions according to the lighting change trend, and synchronously send the lighting adjustment instructions to each carriage through the ring topology network.

[0032] Specifically, based on the predicted lighting change trend information and combined with the current operating conditions of the train, the target lighting brightness value is generated, the target brightness value is encapsulated into a standardized adjustment instruction data packet, and the command effective timestamp is attached to the data packet to mark the timing of synchronous execution. The generated lighting adjustment instruction is broadcast to each car node through the ring communication network built based on the TRDP protocol inside the train. After receiving the instruction, each node caches the instruction to be executed according to the timestamp information and synchronously waits for the command to take effect, so as to ensure that the dimming operation is started at the same time in all cars of the train, and the passengers' perception of the light environment is continuous and consistent.

[0033] S50: Based on the lighting adjustment instruction, call the local dynamic gradient dimming algorithm to generate dimming control parameters, and then control the lighting device to perform a brightness adjustment operation.

[0034] Specifically, after the carriage node receives the lighting adjustment instruction and completes the timestamp cache, it parses the target brightness value and dimming time parameters in the instruction, reads the actual output brightness of the current lighting device, determines the dimming span by calculating the difference between the target brightness and the current brightness, and calls the local dynamic gradient dimming algorithm to generate a continuously changing brightness adjustment curve based on the difference and the set dimming duration, such as 2 seconds. The brightness adjustment curve is subdivided into multiple small step amplitudes, for example, the brightness value is adjusted every 100ms to form a smooth gradual transition. At the same time, the dimming execution is started at the set time point according to the timestamp information in the instruction, and the lighting output is gradually adjusted according to the generated dimming parameters through the control module, and finally the brightness change is smoothly completed within the target time.

[0035] In one embodiment, if Figure 2As shown, in step S20, the illumination data is verified to remove the corresponding abnormal data, and the illumination data after the abnormality is removed is calculated by dynamic weighting to obtain the current average illumination value, which specifically includes: S21: When any illumination data deviates from the floating range of the average illumination data on the same side, the illumination data deviating from the range is determined to be abnormal data, and the abnormal data is eliminated to obtain the illumination data of the first vehicle and the illumination data of the last vehicle.

[0036] Specifically, after receiving the sets of illumination data collected synchronously by the first and last vehicles, the average values of the illumination data of the first vehicle and the illumination data of the last vehicle are calculated respectively first, and a preset floating range is set based on their respective average values as the elimination criteria. When it is detected that the deviation amplitude of a certain illumination data from its average value on the same side exceeds the set floating range, it is judged that the illumination data is abnormal. Abnormal data usually includes extreme fluctuation values caused by instantaneous strong light, interference from obstructions or sensor abnormalities. For example, the floating range is set to ±10%. If the average illumination of the first vehicle is 1000lx, the judgment interval is between 900lx and 1100lx. When the value reported by a sensor is 1200lx, it is judged as abnormal data and eliminated. After the elimination is completed, the remaining valid illumination data of the first vehicle and the illumination data of the last vehicle are reorganized as the input source for subsequent dynamic weighting.

[0037] S22: Calculate the current average illumination value E_avg according to the preset dynamic weighted formula E_avg=α×E_front+β×E_rear, where E_front is the illumination data of the first train, E_rear is the illumination data of the last train, α and β are the weight values of the corresponding data, α+β=1, and the weight value is dynamically adjusted according to the train running conditions.

[0038] Specifically, after obtaining the first car illumination data E_front and the last car illumination data E_rear after eliminating anomalies, the two sets of data are weighted and fused according to the preset dynamic weighted calculation logic, and the dynamic weighted formula is applied to calculate the average value. The initial weights are set to α=0.7 and β=0.3 to maintain the balance of perception of the first and last cars. The core of dynamic weighting is the ability to adjust the ratio of α and β in real time according to the train operation status. When the train operation environment changes or the speed changes significantly, the weighting parameters are dynamically adjusted to enhance the front perception ability or overall stability, thereby ensuring that the current average illumination value E_avg can more accurately reflect the actual illumination change trend of the train operation environment.

[0039] In one embodiment, if Figure 3 As shown, in step S22, the weight value is dynamically adjusted according to the train running situation, specifically including: S221: Obtain the train speed. When the train speed reaches a preset high-speed threshold, increase the first train illumination weight α through a preset speed-weight curve to improve the response speed to changes in the ambient light in front of the train.

[0040] Specifically, the train speed information is monitored in real time during the operation of the train, and the current speed of the train is obtained through the communication module or local interface call, and the speed value is compared with the preset high-speed threshold. When the train speed exceeds the high-speed threshold, such as 120km / h, the weight α of the first car's lighting data is dynamically increased according to the speed-weight relationship curve. For example, under high-speed operation, α is adjusted from 0.7 to 0.9, and the weight β of the tail car's lighting data is reduced to 0.1 accordingly. This ensures that the changes in the environment ahead of the train have a dominant weight on the overall lighting perception, thereby improving the train's perception and response speed to scenes with rapid lighting changes such as tunnels, bridges, entrances and exits ahead.

[0041] Furthermore, the speed-weight curve is derived through a comprehensive analysis of the environmental lighting change response data collected by the train at different speeds. By collecting statistical data on the response speed and accuracy of the lighting data of the first and last trains to environmental changes at different train speed stages in an actual operating environment, it is found that as the train speed increases, the impact of changes in the front environment on the overall lighting environment of the train increases significantly. In particular, when passing through drastic changes such as tunnels, bridges, and entrances and exits at high speed, the lighting change signal collected by the first train appears before that of the last train. Therefore, in order to enhance the overall dimming system's ability to respond to forward-changing scenarios, when the train speed exceeds a specific high-speed threshold, such as 120km / h, a correlation curve between speed and the lighting weight of the first train is formed by fitting a large amount of actual sampling data. Specifically, as the speed increases, the weight α of the lighting data of the first train gradually increases, and the weight β of the lighting data of the last train decreases accordingly. Therefore, under high-speed operation, the overall lighting state is dynamically adjusted with reference to the changes in the front environment, ensuring that the train lighting environment quickly synchronizes with the forward change trend.

[0042] S222: Obtain the external environment brightness and calculate the variation range of the external environment brightness. When the variation range exceeds a preset brightness variation threshold, increase the first vehicle illumination weight α using a preset environment-weight curve.

[0043] Specifically, the external environment light intensity data is continuously collected and the change amplitude per unit time is calculated. The illumination change between consecutive sampling points is detected to determine whether the current environment is in a state of drastic change. When the ambient brightness change amplitude exceeds the set change threshold, such as 500lx, it is identified as a drastic change scene. The weighted ratio α of the first car's illumination data is dynamically increased according to the environment-weight adjustment curve. For example, when the environment changes drastically, α is adjusted to 0.85 to enhance the train's forward perception ability of sudden illumination changes. At the same time, the weight β of the tail car's illumination data is reduced. In this way, the first car data is prioritized to guide the overall illumination prediction and dimming decision in sudden environmental changes, ensuring that the illumination transition in the passenger area of the train is smoother and more natural.

[0044] Furthermore, the environment-weight curve is obtained by collecting statistics on the lighting change characteristics of the train under different external natural lighting change environments. By continuously monitoring the amplitude and speed of changes in ambient light intensity when the train passes through different weather conditions, tunnel entrances and exits, building shadow areas and other scenarios, a corresponding relationship between the environmental change rate and the accuracy of lighting perception is established. After training and analysis of a large amount of sample data, it is found that when the external environmental lighting change rate exceeds a certain threshold, such as a change of more than 500lx per second, the first car lighting data is significantly better than the last car data in indicating the overall environmental change trend. Therefore, a segmented weight adjustment strategy is set according to the amplitude and rate of external environmental lighting changes, and a relationship curve between the environmental change rate and the first car lighting weight α is fitted. Specifically, the more drastic the environmental change, the gradually higher the weight α of the first car lighting data, and the synchronously lowering of the tail car lighting weight β. This enables the train to adjust the overall lighting status in a timely and accurate manner when responding to sudden external lighting changes, thereby improving passengers' visual comfort and adaptability to the light environment.

[0045] In one embodiment, if Figure 4 As shown, in step S30, i.e., the construction of the illumination prediction model, specifically includes: S31: Obtain historical lighting data of the train under different operating environments, and classify the historical lighting data according to the train operating scenes and lighting change characteristics to obtain a training data set.

[0046] Specifically, during the long-term operation of the train, the ambient lighting data of the first and last cars are continuously collected, and each set of lighting data is labeled according to the collection time, geographical location and train operation status, for example, labeled as tunnel entry section, tunnel exit section, bridge section, open area section or platform section. Further classification is performed according to the lighting change rate and pattern in each operation scene. When the lighting in a certain interval changes dramatically and drops rapidly, it can be classified as a tunnel entrance scene. When the lighting gradually becomes brighter and rises slowly, it can be classified as a tunnel exit scene. Through this refined classification, the lighting data collected under different operating environments are combined into a training data set with clear labels, providing an accurate and rich sample basis for the subsequent lighting prediction model training.

[0047] S32: Training a preset long short-term memory neural network model based on the training data set, predicting the illumination change trend within a preset time period according to the correlation between the ambient illumination change and the illumination trend, and thereby obtaining an illumination prediction model.

[0048] Specifically, the constructed training dataset is used as input, and the historical lighting time series data is input into a long short-term memory neural network model with a preset structure. The time window length of each batch of input data is set, for example, 1 second or 2 seconds. During the training process, the model continuously adjusts the network weights according to the correspondence between the historical illumination change trajectory and the subsequent actual change trend. The model optimization is completed by minimizing the error between the predicted value and the true value. After multiple rounds of iterative training, the model is finally able to capture the deep correlation between the ambient lighting changes and the train driving scene. In actual application, the direction and amplitude of the lighting changes in the future preset time period are predicted according to the current average lighting value and the historical change trend, forming the output of the lighting prediction model.

[0049] In one embodiment, if Figure 5 As shown, in step S40, the lighting adjustment instruction is synchronously sent to each carriage through the ring topology network, specifically including: S41: Build a train network architecture based on the TRDP communication protocol, interconnect the car nodes in a ring manner, and then obtain a ring topology network.

[0050] Specifically, during the overall network deployment of the train, hardware equipment and interface specifications that comply with the TRDP communication protocol are used to configure communication nodes in each carriage, and adjacent carriage nodes are connected through redundant bidirectional physical links to form a complete ring communication topology structure that is connected end to end. This topology has natural redundancy and high reliability, and can maintain uninterrupted network communication even in the event of a single point failure in the link, thereby ensuring that lighting adjustment commands can be transmitted quickly and reliably between carriages, providing basic communication support for achieving synchronous dimming of the entire train.

[0051] S42: Setting a unified command effective time for the lighting adjustment instruction and adding a timestamp, and sending the timestamp and the lighting adjustment instruction through the ring topology network.

[0052] Specifically, when the central control node generates a lighting adjustment instruction, a uniformly set command effectiveness time is attached to each instruction, for example, it is set to take effect uniformly 500 milliseconds in the future. At the same time, timestamp information accurate to the millisecond level is added to the instruction data packet to mark the instruction generation time. Each car node receives the instruction and reads the timestamp field therein to synchronize with the local clock for comparison. It caches the instructions to be executed locally and controls the delay in executing the dimming operation according to the timestamp and the unified effectiveness time. In this way, even if there is a very small network delay, each car can still start the lighting adjustment at almost the same time, effectively avoiding the problem of asynchronous brightness changes between different cars.

[0053] In one embodiment, if Figure 6 As shown, in step S50, based on the lighting adjustment instruction, the local dynamic gradient dimming algorithm is called to generate dimming control parameters, and then the lighting device is controlled to perform the brightness adjustment operation, which specifically includes: S51: Parse the lighting adjustment instruction and the timestamp mark, extract the target brightness value and timestamp information, obtain the actual brightness value of the current lighting device, and calculate the brightness difference between the actual brightness value and the target brightness.

[0054] Specifically, after the car node receives the lighting adjustment instruction, it first parses the data packet content, extracts the target brightness setting value and the attached effective timestamp information, obtains the actual brightness value by reading the output parameters of the current lighting driver, and calculates the numerical difference between the actual brightness and the target brightness by direct comparison. For example, if the current brightness is 80% and the target brightness is 30%, the brightness difference is 50%. This brightness difference serves as the basis for subsequent dynamic gradient dimming processing and guides the calculation of the dimming amplitude and change rhythm.

[0055] S52: Based on the dynamic gradient dimming algorithm, the continuously changing brightness adjustment amplitude is calculated according to the brightness difference and the preset adjustment time period, and the adjustment start time is generated according to the timestamp information.

[0056] Specifically, based on the brightness difference obtained by analysis and the preset dimming transition time period, for example, 2 seconds, the local dynamic gradient dimming algorithm is called to divide the overall brightness change into multiple small step changes, and the brightness adjustment is set every 100ms. The brightness adjustment amplitude of each step is calculated according to the total change and the number of steps. For example, if the difference is 50% and the number of steps is 20, then the adjustment is 2.5% per step. At the same time, the effective timestamp information in the received instruction is aligned with the local clock to determine the specific dimming start time point, ensuring that each dimming action is started strictly according to the unified time base.

[0057] S53: Generate a dimming control parameter according to the brightness adjustment amplitude and the adjustment start time, and perform a brightness adjustment operation according to the dimming control parameter.

[0058] Specifically, the calculated brightness adjustment amplitude and dimming start time of each step are used as input to generate a complete set of dimming control parameters, including the brightness increase or decrease of each small step adjustment, the adjustment cycle and the trigger time point. The dimming execution program is automatically started when the set dimming start time is reached, and the output brightness value of the lighting equipment is adjusted in sequence according to the preset step strategy until the actual brightness reaches the target brightness, thereby achieving a smooth, uniform and synchronous lighting brightness transition process for the entire vehicle, ensuring that passengers have a continuous and comfortable visual experience during lighting changes.

[0059] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0060] In one embodiment, a device for synchronously adjusting the brightness of global lighting on a train is provided, and the device for synchronously adjusting the brightness of global lighting on a train corresponds one-to-one to the method for synchronously adjusting the brightness of global lighting on a train in the above embodiment. Figure 7 As shown, the train global lighting brightness synchronous adjustment device includes a lighting data acquisition module, a lighting data processing module, a lighting trend prediction module, a lighting instruction generation module, and a dynamic gradient dimming module. The functional modules are described in detail as follows: Lighting data acquisition module, used to obtain some lighting data of the first and last cars of the train; The illumination data processing module is used to verify the illumination data to eliminate the corresponding abnormal data, and calculate the illumination data after eliminating the abnormalities through dynamic weighting to obtain the current average illumination value; The illumination trend prediction module is used to obtain the illumination change trend within a preset time period based on the current average illumination value through a preset illumination prediction model; The lighting instruction generation module is used to generate lighting adjustment instructions based on the lighting change trend and synchronously send the lighting adjustment instructions to each carriage through the ring topology network; The dynamic gradient dimming module is used to call the local dynamic gradient dimming algorithm to generate dimming control parameters based on the lighting adjustment instruction, and then control the lighting device to perform brightness adjustment operations.

[0061] Optionally, the illumination data processing module specifically includes: The abnormal data elimination submodule is used to determine that any illumination data deviates from the floating range of the average illumination data on the same side is abnormal data, and eliminate the abnormal data to obtain the illumination data of the first vehicle and the illumination data of the last vehicle; The dynamic weighted calculation submodule is used to calculate the current average illumination value E_avg according to the preset dynamic weighted formula E_avg=α×E_front+β×E_rear, where E_front is the illumination data of the first train, E_rear is the illumination data of the last train, α and β are the weight values of the corresponding data, α+β=1, and the weight value is dynamically adjusted according to the train's travel conditions.

[0062] Optionally, the dynamic weighted calculation submodule specifically includes: The speed weight adjustment unit is used to obtain the train speed. When the train speed reaches a preset high-speed threshold, the light weight α of the first train is increased according to the preset speed-weight curve to improve the response speed to the changes in the ambient light in front of the train. The environment weight adjustment unit is used to obtain the external environment brightness and calculate the variation range of the external environment brightness. When the variation range exceeds the preset brightness variation threshold, the first vehicle lighting weight α is increased through the preset environment-weight curve.

[0063] Optional, construction of a lighting prediction model, specifically including: The historical data collection submodule is used to obtain historical lighting data of the train under different operating environments, and classify the historical lighting data according to the train operation scene and lighting change characteristics to obtain a training data set; The illumination model training submodule is used to train the preset long-short-term memory neural network model based on the training data set, and predict the illumination change trend within a preset time period according to the correlation between ambient illumination changes and illumination trends, thereby obtaining an illumination prediction model.

[0064] Optionally, the lighting instruction generation module specifically includes: The network architecture construction submodule is used to build the train network architecture based on the TRDP communication protocol, interconnecting the car nodes in a ring manner to obtain a ring topology network; The instruction synchronization sending submodule is used to set a unified command effective time for the lighting adjustment instruction and attach a timestamp mark, and send the timestamp mark and the lighting adjustment instruction through the ring topology network.

[0065] Optionally, the dynamic gradient dimming module specifically includes: The instruction parsing submodule is used to parse the lighting adjustment instruction and the timestamp mark, extract the target brightness value and timestamp information, obtain the actual brightness value of the current lighting device, and calculate the brightness difference between the actual brightness value and the target brightness; A gradient dimming calculation submodule is used to calculate the continuously changing brightness adjustment amplitude according to the brightness difference and the preset adjustment time period based on the dynamic gradient dimming algorithm, and generate the adjustment start time according to the timestamp information; The dimming control submodule is used to generate dimming control parameters according to the brightness adjustment amplitude and the adjustment start time, and perform brightness adjustment operations according to the dimming control parameters.

[0066] The specific definitions of the train global lighting brightness synchronous adjustment device can be found in the definitions of the train global lighting brightness synchronous adjustment method above and will not be repeated here. Each module in the aforementioned train global lighting brightness synchronous adjustment device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of these modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0067] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When executed by the processor, the computer program implements a method for synchronously adjusting the brightness of global lighting on a train.

[0068] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed: Obtain some lighting data of the first and last cars of the train; Perform data verification on the illumination data to eliminate the corresponding abnormal data, and calculate the illumination data after eliminating the abnormalities through dynamic weighting to obtain the current average illumination value; Based on the current average light value, the light change trend within the preset time period is obtained through the preset light prediction model; Generate lighting adjustment instructions based on lighting change trends and send them synchronously to each carriage through a ring topology network; Based on the lighting adjustment instruction, the local dynamic gradient dimming algorithm is called to generate dimming control parameters, thereby controlling the lighting device to perform brightness adjustment operations.

[0069] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: Obtain some lighting data of the first and last cars of the train; Perform data verification on the illumination data to eliminate the corresponding abnormal data, and calculate the illumination data after eliminating the abnormalities through dynamic weighting to obtain the current average illumination value; Based on the current average light value, the light change trend within the preset time period is obtained through the preset light prediction model; Generate lighting adjustment instructions based on lighting change trends and send them synchronously to each carriage through a ring topology network; Based on the lighting adjustment instruction, the local dynamic gradient dimming algorithm is called to generate dimming control parameters, thereby controlling the lighting device to perform brightness adjustment operations.

[0070] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0071] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0072] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for synchronously adjusting the global illumination brightness of a train, characterized in that: The method for synchronously adjusting the global illumination brightness of a train comprises: Obtain some lighting data of the first and last cars of the train; Performing data verification on the illumination data to eliminate corresponding abnormal data, and calculating the illumination data after eliminating the abnormalities through dynamic weighting to obtain a current average illumination value; Based on the current average light value, obtaining a light change trend within a preset time period through a preset light prediction model; generating a lighting adjustment instruction according to the lighting change trend, and synchronously sending the lighting adjustment instruction to each carriage through a ring topology network; Based on the lighting adjustment instruction, a local dynamic gradient dimming algorithm is called to generate dimming control parameters, thereby controlling the lighting device to perform a brightness adjustment operation.

2. The method for synchronously adjusting the global illumination brightness of a train according to claim 1, characterized in that: The data verification of the illumination data to eliminate corresponding abnormal data, and calculating the illumination data after the abnormalities are eliminated by dynamic weighting to obtain the current average illumination value, specifically includes: When any of the illumination data deviates from the floating range of the average illumination data on the same side, the illumination data deviating from the range is determined to be abnormal data, and the abnormal data is eliminated to obtain the illumination data of the first vehicle and the illumination data of the last vehicle; The current average illumination value E_avg is calculated according to the preset dynamic weighted formula E_avg=α×E_front+β×E_rear, wherein E_front is the illumination data of the first train, E_rear is the illumination data of the last train, α and β are the weight values of the corresponding data respectively, α+β=1, and the weight value is dynamically adjusted according to the train driving conditions.

3. The method for synchronously adjusting the global illumination brightness of a train according to claim 2, characterized in that: The weight value is dynamically adjusted according to the train running conditions, specifically including: Obtaining the train speed, and when the train speed reaches a preset high-speed threshold, increasing the first train illumination weight α according to a preset speed-weight curve to improve the response speed to changes in ambient light ahead of the train; The external environment brightness is obtained, and the variation range of the external environment brightness is calculated. When the variation range exceeds a preset brightness variation threshold, the first vehicle illumination weight α is increased using a preset environment-weight curve.

4. The method for synchronously adjusting the global illumination brightness of a train according to claim 1, characterized in that: The construction of the illumination prediction model specifically includes: Obtaining historical lighting data of the train under different operating environments, and classifying the historical lighting data according to the train operating scenes and lighting change characteristics to obtain a training data set; The preset long short-term memory neural network model is trained based on the training data set, and the illumination change trend within a preset time period is predicted according to the correlation law between the ambient illumination change and the illumination trend, thereby obtaining the illumination prediction model.

5. The method for synchronously adjusting the global illumination brightness of a train according to claim 1, characterized in that: The step of synchronously sending the lighting adjustment instruction to each carriage via the ring topology network specifically includes: Building a train network architecture based on the TRDP communication protocol, interconnecting the car nodes in a ring manner, thereby obtaining the ring topology network; A unified command effective time is set for the lighting adjustment instruction and a timestamp is added, and the timestamp and the lighting adjustment instruction are sent through the ring topology network.

6. The method for synchronously adjusting the global illumination brightness of a train according to claim 5, characterized in that: The step of calling a local dynamic gradient dimming algorithm based on the lighting adjustment instruction to generate dimming control parameters, and then controlling the lighting device to perform a brightness adjustment operation, specifically includes: Parsing the lighting adjustment instruction and the timestamp mark, extracting the target brightness value and the timestamp information, obtaining the actual brightness value of the current lighting device, and calculating the brightness difference between the actual brightness value and the target brightness; Based on a dynamic gradient dimming algorithm, a continuously changing brightness adjustment amplitude is calculated according to the brightness difference and a preset adjustment time period, and an adjustment start time is generated according to the timestamp information; The dimming control parameter is generated according to the brightness adjustment amplitude and the adjustment start time, and the brightness adjustment operation is performed according to the dimming control parameter.

7. A device for synchronously adjusting the global lighting brightness of a train, characterized in that: The device comprises: Lighting data acquisition module, used to obtain some lighting data of the first and last cars of the train; an illumination data processing module for performing data verification on the illumination data to eliminate corresponding abnormal data, and calculating the illumination data after eliminating abnormalities by dynamic weighting to obtain a current average illumination value; A lighting trend prediction module, configured to obtain a lighting change trend within a preset time period based on the current average lighting value using a preset lighting prediction model; A lighting instruction generation module is used to generate a lighting adjustment instruction according to the lighting change trend, and synchronously send the lighting adjustment instruction to each carriage through a ring topology network; The dynamic gradient dimming module is used to call a local dynamic gradient dimming algorithm to generate dimming control parameters based on the lighting adjustment instruction, and then control the lighting device to perform a brightness adjustment operation.

8. The train global lighting brightness synchronous adjustment device according to claim 7, characterized in that: The illumination data processing module specifically includes: An abnormal data elimination submodule is used to determine that when any of the illumination data deviates from the floating range of the average illumination data on the same side, the illumination data that deviates from the range is abnormal data, and eliminate the abnormal data to obtain the illumination data of the first vehicle and the illumination data of the last vehicle; The dynamic weighted calculation submodule is used to calculate the current average illumination value E_avg according to the preset dynamic weighted formula E_avg=α×E_front+β×E_rear, wherein E_front is the illumination data of the first car, E_rear is the illumination data of the last car, α and β are the weight values of the corresponding data respectively, α+β=1, and the weight value is dynamically adjusted according to the train driving conditions.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for synchronously adjusting the global illumination brightness of a train as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for synchronously adjusting the global illumination brightness of a train as claimed in any one of claims 1 to 6 are implemented.

Images