Highway passing method, device and equipment in rainfall weather and storage medium

Abstract

The invention discloses an expressway passing method and device in rainfall weather, equipment and a storage medium, and relates to the field of electric digital data processing, the method divides an expressway into a plurality of cells for separate management, the rainfall condition of each cell is known in advance through the rainfall prediction data, and the rainfall condition of each cell is determined according to the rainfall prediction data. The traffic speed of each cell is limited through the weight coefficient, so that the larger the precipitation is, the lower the traffic speed is, and finally, the corresponding traffic parameters are obtained by detecting the cell where the vehicle is located through the radar, so that the one-step closed management of the highway is effectively prevented, and the travel convenience is ensured.

Description

Technical Field

[0001] The present application relates to the field of electronic digital data processing technology, and in particular to a method, device, equipment and storage medium for traveling on a highway in precipitation weather. Background Art

[0002] As an important means of cross-regional transportation, expressways play a vital role in my country's economic development.

[0003] On highways, traffic accidents caused by bad weather account for a large proportion of the total number of accidents. Among them, heavy rain makes the road surface slippery, the visibility is poor, the braking distance becomes longer, and the response is not timely, which easily induces traffic accidents. Therefore, it is of great significance to improve the traffic safety level of heavy rain sections of highways and reduce the probability of traffic accidents.

[0004] Bad weather can easily cause serious traffic accidents and large-scale traffic jams on highways, reducing the overall resilience of highways and seriously affecting road traffic operations and economic and social development. Under the influence of bad weather such as snow, rainstorms, and fog, it is a common practice for countries around the world to take control measures such as closing and restricting highways.

[0005] At present, in order to effectively prevent serious road traffic accidents in bad weather and ensure the safety of drivers and passengers on highways, industry authorities and highway operation and management companies often adopt a fully closed road closure control mode. For example, when a highway encounters heavy fog, it is usually closed, and sections without heavy fog are also closed or restricted, which affects the demand for highway traffic in sections without fog and restricts public transportation. Summary of the invention

[0006] The main purpose of the present application is to provide a method, device, equipment and storage medium for highway travel in precipitation weather, so as to solve the problem that the redundant closure of the fully enclosed road closure control mode in the prior art affects the demand for highway travel in non-fog areas and restricts public transportation.

[0007] To achieve the above objectives, this application provides the following technical solutions:

[0008] A method for passing a highway in precipitation weather, the method for passing a highway is applied to a highway that is about to be precipitated, and vehicles traveling on the highway, the highway is provided with a radar monitoring component and a broadcast display component at each preset interval, and the method for passing a highway comprises:

[0009] Step S1, obtaining a number of future precipitation data based on a preset number of prediction steps in the area where the expressway is located;

[0010] Step S2: Divide the highway into several continuous driving areas along the radial center line of the highway. Each driving area includes a radar monitoring device and a broadcast display device.

[0011] Step S3: Construct a future precipitation interval with zero as the minimum value of the precipitation interval and the maximum value of all future precipitation data as the maximum value of the precipitation interval.

[0012] Step S4: Divide the future precipitation interval into several future precipitation sub - intervals.

[0013] Step S5: Define a weight coefficient based on each future precipitation sub - interval. The magnitudes of all weight coefficients increase as the precipitation values of all future precipitation sub - intervals increase.

[0014] Step S6: Based on several future precipitation data, obtain several future precipitation sub - data for each driving area based on the preset prediction steps.

[0015] Step S7: Classify all future precipitation sub - data into all future precipitation sub - intervals, and obtain a weight coefficient based on one future precipitation sub - data.

[0016] Step S8: Obtain the quotient of the maximum speed limit of the current driving area and the weight coefficient to get the recommended driving speed of the current driving area.

[0017] Step S9: When the future precipitation in the current driving area arrives, use the radar monitoring device to detect whether there is a vehicle. When there is a vehicle, use the broadcast display device to broadcast and display the recommended driving speed of the current driving area.

[0018] As a further improvement of this application, all vehicles are equipped with a navigation device. In step S9, when the future precipitation in the current driving area arrives, use the radar monitoring device to detect whether there is a vehicle. When there is a vehicle, use the broadcast display device to broadcast and display the recommended driving speed of the current driving area. After that, it includes:

[0019] Step S10: Use the navigation device of the current vehicle to obtain the driving area where the current vehicle is located and the recommended driving speed corresponding to the driving area.

[0020] Step S20: Use the navigation device of the current vehicle to broadcast the corresponding recommended driving speed.

[0021] Step S30: Based on a preset detection interval, use the navigation device of the current vehicle to repeatedly detect the real - time driving speed of the current vehicle.

[0022] Step S40: Determine whether the real-time driving speed of the current vehicle is less than or equal to the recommended driving speed of the current driving area. If not, execute Step S50;

[0023] Step S50: Generate a precipitation environment speeding reminder signal;

[0024] Step S60: Broadcast the precipitation environment speeding reminder signal once based on each preset detection interval;

[0025] Step S70: Repeat Steps S10 to S60 until the real-time driving speed of the current vehicle is less than or equal to the recommended driving speed of the current driving area, then stop broadcasting.

[0026] As a further improvement of this application, in Step S1, obtain several future precipitation data of the area where the highway is located based on a preset prediction step number, including:

[0027] Step S11: Obtain several historical precipitation data of the area where the highway is located based on a preset time period;

[0028] Step S12: Perform standard normalization processing on all historical precipitation data to obtain a normalized data set;

[0029] Step S13: Divide the normalized data set into a training set and a validation set according to a preset ratio;

[0030] Step S14: Define a neural network model with signal connections in sequence of an input layer, a hidden layer, and an output layer;

[0031] Step S15: Input the training set into the input layer and perform several trainings through the neural network model;

[0032] Step S16: Obtain the root mean square error between the validation set and the current training result respectively based on each training;

[0033] Step S17: Obtain the minimum error among all root mean square errors;

[0034] Step S18: Obtain the training result corresponding to the minimum error as the precipitation prediction model;

[0035] Step S19: Predict several future precipitation data based on the preset prediction step number through the precipitation prediction model.

[0036] As a further improvement of this application, in Step S5, define a weight coefficient based on each future precipitation sub-interval, and the magnitudes of all weight coefficients increase as the precipitation values of all future precipitation sub-intervals increase, including:

[0037] Step S51: Define all future precipitation sub - intervals as small precipitation intervals, medium precipitation intervals, large precipitation intervals, and heavy precipitation intervals in ascending order according to precipitation values.

[0038] Step S52: Assign increasing first weight coefficient, second weight coefficient, third weight coefficient, and fourth weight coefficient to the small precipitation interval, the medium precipitation interval, the large precipitation interval, and the heavy precipitation interval in sequence.

[0039] As a further improvement of this application, in step S9, when the future precipitation in the current driving area arrives, use the radar monitoring component to detect whether there are vehicles. When there are vehicles, use the broadcast and display component to broadcast and display the recommended driving speed in the current driving area. After that, it includes:

[0040] Step S100: Calculate the braking distances of the vehicle in small precipitation, medium precipitation, large precipitation, and heavy precipitation based on the recommended driving speed in the current driving area respectively according to the braking distance calculation formula.

[0041] Step S200: Assign the braking distance corresponding to small precipitation to the small precipitation interval.

[0042] Step S300: Assign the braking distance corresponding to medium precipitation to the medium precipitation interval.

[0043] Step S400: Assign the braking distance corresponding to large precipitation to the large precipitation interval.

[0044] Step S500: Assign the braking distance corresponding to heavy precipitation to the heavy precipitation interval.

[0045] Step S600: Use the radar monitoring component in the current driving area to obtain the driving distance between adjacent vehicles.

[0046] Step S700: Judge whether the driving distance is greater than or equal to the corresponding braking distance. If not, execute step S800.

[0047] Step S800: Generate a warning signal for too short vehicle distance.

[0048] Step S900: Send the warning signal for too short vehicle distance to the navigation component of the vehicle located behind.

[0049] As a further improvement of this application, in step S900, after sending the warning signal for too short vehicle distance to the navigation component of the vehicle located behind, it includes:

[0050] Step S1000: Repeatedly obtain the driving distance between adjacent vehicles through the radar monitoring component in the current driving area based on the preset detection interval.

[0051] Step S2000, determine whether the inter-vehicle distance is greater than or equal to the corresponding braking distance. If not, execute Step S3000;

[0052] Step S3000, broadcast the warning signal of too short vehicle distance once every preset detection interval;

[0053] Step S4000, repeat Step S1000 to Step S3000 until the inter-vehicle distance between the vehicle behind and the vehicle in front is greater than or equal to the corresponding braking distance, then stop broadcasting.

[0054] As a further improvement of the present application, in Step S7, classify all future precipitation sub-data into all future precipitation sub-intervals, and obtain a weight coefficient based on one future precipitation sub-data, including:

[0055] Step S71, integrate all future precipitation sub-data to form a set of signals to be classified;

[0056] Step S72, define a set of categories according to all future precipitation sub-intervals;

[0057] Step S73, calculate the conditional probabilities of the set of signals to be classified under each of all future precipitation sub-intervals;

[0058] Step S74, classify each future precipitation sub-data into the all future precipitation sub-interval with the highest conditional probability of its own respectively;

[0059] Step S75, assign the classified future precipitation sub-data in the current future precipitation sub-interval the weight coefficient of the current future precipitation sub-interval.

[0060] To achieve the above object, the present application also provides the following technical solutions:

[0061] A highway passing device for precipitation weather, the highway passing device is applied to the highway passing method as described above, and the highway passing device includes:

[0062] A future precipitation data acquisition module, configured to acquire a plurality of future precipitation data of the area where the highway is located based on a preset prediction step;

[0063] A driving area division module, configured to equally divide the highway into a plurality of continuous driving areas along the driving radial center line of the highway, and each driving area includes a radar monitoring component and a broadcast display component;

[0064] A future precipitation interval construction module, configured to construct a future precipitation interval with zero value as the minimum value of the precipitation interval and the maximum value of all future precipitation data as the maximum value of the precipitation interval;

[0065] A future precipitation quantum interval division module for equally dividing the future precipitation interval into a plurality of future precipitation sub - intervals;

[0066] A weight coefficient definition module for defining a weight coefficient based on each future precipitation sub - interval, and the magnitudes of all weight coefficients increase as the precipitation values of all future precipitation sub - intervals increase;

[0067] A future precipitation sub - data acquisition module for respectively acquiring a plurality of future precipitation sub - data for each driving area based on a plurality of future precipitation data according to the preset prediction steps;

[0068] A future precipitation sub - data classification module for classifying all future precipitation sub - data into all future precipitation sub - intervals and obtaining a weight coefficient based on one future precipitation sub - data;

[0069] A recommended driving speed acquisition module for the driving area, which is used to obtain the quotient of the maximum speed limit of the current driving area and the weight coefficient to obtain the recommended driving speed of the current driving area;

[0070] A recommended driving speed broadcast module for, when the future precipitation in the current driving area arrives, detecting whether there is a vehicle through the radar monitoring component, and when there is a vehicle, broadcasting and displaying the recommended driving speed of the current driving area through the broadcast display component.

[0071] To achieve the above object, the present application also provides the following technical solutions:

[0072] An electronic device includes a processor and a memory coupled to the processor, and the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the highway passing method as described above.

[0073] To achieve the above object, the present application also provides the following technical solutions:

[0074] A storage medium stores program instructions, and when the program instructions are executed by a processor, they can implement the highway passing method as described above.

[0075] This application obtains several future precipitation data of the area where the highway is located based on a preset prediction step; divides the highway into several continuous driving areas along the driving radial center line of the highway, and each driving area includes a radar monitoring device and a broadcast display device; constructs a future precipitation interval with zero as the minimum value of the precipitation interval and the maximum value of all future precipitation data as the maximum value of the precipitation interval; divides the future precipitation interval into several future precipitation sub-intervals; defines a weight coefficient based on each future precipitation sub-interval, and the magnitudes of all weight coefficients increase as the precipitation values of all future precipitation sub-intervals increase; obtains several future precipitation sub-data of each driving area based on a preset prediction step based on several future precipitation data; classifies all future precipitation sub-data into all future precipitation sub-intervals, and obtains a weight coefficient based on one future precipitation sub-data; obtains the quotient of the maximum speed limit of the current driving area and the weight coefficient to obtain the recommended driving speed of the current driving area; when the future precipitation in the current driving area arrives, detects whether there is a vehicle through the radar monitoring device, and broadcasts and displays the recommended driving speed of the current driving area through the broadcast display device when there is a vehicle. This application divides the highway into multiple small intervals for separate management, learns about the precipitation conditions of each small interval in advance through the predicted precipitation data, and restricts the passing speed of each small interval through the weight coefficient, so that the greater the precipitation, the lower the passing speed. Finally, the corresponding passing parameters are obtained by detecting the small interval where the vehicle is located by radar, effectively preventing the one-size-fits-all closed management of the highway and ensuring travel convenience. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 It is a schematic flowchart of the steps of an embodiment of the method for passing a highway in rainy weather according to this application;

[0077] Figure 2 It is a schematic diagram of the functional modules of an embodiment of the device for passing a highway in rainy weather according to this application;

[0078] Figure 3 It is a schematic structural diagram of an embodiment of the electronic device according to this application;

[0079] Figure 4 It is a schematic structural diagram of an embodiment of the storage medium according to this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0080] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0081] The terms "first", "second", and "third" in this application are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of this application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined. In the embodiments of this application, all directional indications (such as up, down, left, right, front, back...) are only used to explain the relative positional relationship, movement conditions, etc. between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indication will also change accordingly. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0082] Referring to "embodiments" herein means that specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of this application. The phrase appearing in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0083] As Figure 1 shown, this example provides an embodiment of a highway traffic method for precipitation weather. In this embodiment, the highway traffic method is applied to a highway about to experience precipitation and vehicles traveling on the highway. A radar monitoring component and a broadcast display component are provided at preset intervals on the highway.

[0084] Preferably, the radar monitoring component can be set as a millimeter-wave radar, and the broadcast display component can be set as an LED large display screen.

[0085] Among them, the core functions of the millimeter-wave radar include ranging, speed measurement, azimuth angle measurement, micro-motion detection, and 4D imaging, etc. In the automotive field, millimeter-wave radars are mainly used for functions such as obstacle avoidance, active collision avoidance, pre-collision systems, automatic emergency braking systems, adaptive cruise systems, blind spot detection, front anti-rear-end collision warning, and lane change assistance. These functions transmit and receive millimeter-wave signals to accurately measure the distance, angle, and relative speed between the vehicle and other objects, providing solid technical support for driving safety.

[0086] In addition, millimeter-wave radar also plays an important role in the low-altitude economy. For example, in the field of drones, it is used for obstacle avoidance and altitude determination to ensure the safe operation of plant protection drones in complex environments. In the field of urban air traffic, millimeter-wave radar can achieve low-altitude precise perception applications such as trajectory recognition and intrusion monitoring. In the aspect of integrated communication and sensing, it is integrated with communication technologies such as 5G to provide a wider coverage range and save spectrum resources.

[0087] The working principle of millimeter-wave radar is to transmit and receive radio waves to accurately measure the distance, angle, and relative speed between vehicles. This technology enables drivers to better master the driving distance, thus effectively avoiding collision risks during high-speed driving or in complex road conditions and enhancing driving safety.

[0088] Among them, the LED large display screen based on highways is an information release system that provides real-time traffic information and relevant public service information to drivers and pedestrians through the LED electronic display screen. This system is widely used on highways to improve traffic safety and convenience.

[0089] The main functions of highway display screens include:

[0090] Real-time display of traffic conditions: Display road conditions, accidents, construction information, etc., to help drivers timely understand the road situation and adjust their driving plans.

[0091] Weather forecast: Provide current and future weather conditions, remind drivers to pay attention to meteorological changes, and ensure safe driving.

[0092] Traffic safety tips: Release information such as speeding, fatigue driving, and seat belt reminders to enhance drivers' safety awareness.

[0093] Traffic management assistance: Release traffic control, road closure, temporary parking tips, etc., to improve traffic management efficiency.

[0094] Specifically, the highway passing method includes the following steps:

[0095] Step S1, obtain several future precipitation data based on a preset prediction step in the area where the highway is located.

[0096] Preferably, a preset prediction step can be set to one of ten minutes, half an hour, and one hour.

[0097] Preferably, local weather forecasts can be used, or a neural network in the following text can be used for accurate prediction in a small area.

[0098] Step S2, equally divide the highway into several continuous driving areas along the driving radial center line of the highway. Each driving area includes a radar monitoring component and a broadcast display component.

[0099] Preferably, since the mileage of the highway is long, and a radar monitoring device and a broadcast display device are generally installed every one kilometer to every several kilometers, a driving area can be set according to the installation positions of the radar monitoring device and the broadcast display device, and the radar monitoring device and the broadcast display device can be placed at the midpoint of a driving area.

[0100] Preferably, more refined division can be achieved by installing additional radar monitoring devices and broadcast display devices.

[0101] Step S3: Construct a future precipitation interval with zero as the minimum value of the precipitation interval and the maximum value of all future precipitation data as the maximum value of the precipitation interval.

[0102] Step S4: Divide the future precipitation interval equally into several future precipitation sub - intervals.

[0103] Step S5: Define a weight coefficient based on each future precipitation sub - interval, and the magnitudes of all weight coefficients increase as the precipitation values of all future precipitation sub - intervals increase.

[0104] Preferably, if the small precipitation interval, medium precipitation interval, large precipitation interval, and heavy precipitation interval in the following text are adopted, the specific values of the weight coefficients can be calculated inversely according to the speed limit standards of national highways in this embodiment.

[0105] Specifically, the speed limit standards for highways are as follows:

[0106] Small passenger cars: The maximum speed shall not exceed 120 kilometers per hour.

[0107] Other motor vehicles: The maximum speed shall not exceed 100 kilometers per hour.

[0108] Motorcycles: The maximum speed shall not exceed 80 kilometers per hour.

[0109] Highly toxic chemical transport vehicles: The maximum speed shall not exceed 90 kilometers per hour.

[0110] School buses and dangerous goods transport vehicles: The maximum speed shall not exceed 80 kilometers per hour.

[0111] Specific speed limit standards for different lanes:

[0112] When there are two lanes in the same direction, the minimum speed of the left - hand lane is 100 kilometers per hour and the maximum speed is 120 kilometers per hour.

[0113] When there are three or more lanes in the same direction, the minimum speed of the left - most lane is 110 kilometers per hour and the maximum speed is 120 kilometers per hour; the minimum speed of the middle lane is 90 kilometers per hour.

[0114] Speed ​​limits under special weather conditions:

[0115] In low visibility weather conditions such as fog, rain, snow, hail, etc., when visibility is less than 200 meters, the vehicle speed shall not exceed 60 kilometers per hour, and a distance of more than 100 meters shall be maintained from the vehicle in front in the same lane; when visibility is less than 100 meters, the vehicle speed shall not exceed 40 kilometers per hour, and a distance of more than 50 meters shall be maintained from the vehicle in front in the same lane; when visibility is less than 50 meters, the vehicle speed shall not exceed 20 kilometers per hour, and exit the expressway as soon as possible from the nearest exit.

[0116] From the above, we can know that when the visibility is less than 200 meters, the vehicle speed shall not exceed 60km / h. Taking the maximum speed of a small passenger car as an example, when the visibility is less than 200 meters, it is defined as a small precipitation interval, and the weight coefficient of the small precipitation interval is 2 using 120 / 60; when the visibility is less than 100 meters, the vehicle speed shall not exceed 40 kilometers per hour, and the visibility is less than 100 meters. It is defined as a medium precipitation interval, and the weight coefficient of the small precipitation interval is 3 using 120 / 40; when the visibility is less than 50 meters, the vehicle speed shall not exceed 20 kilometers per hour, and the visibility is less than 50 meters. It is defined as a medium precipitation interval, and the weight coefficient of the small precipitation interval is 6 using 120 / 20; for driving safety, the weight coefficient of the heavy precipitation interval can be defined as a large number, so that the speed limit in the heavy precipitation interval is close to zero, so as to indicate to the vehicle to leave the highway as soon as possible through the display screen and navigation components.

[0117] Step S6, based on the plurality of future precipitation data, respectively obtain a plurality of future precipitation sub-data based on a preset prediction step number for each driving area.

[0118] Preferably, the driving area and the future precipitation data are both regional, and the future precipitation sub-data between cells can be obtained by matching the geographical locations.

[0119] Step S7: classify all future precipitation sub-data into all future precipitation quantum intervals, and obtain a weight coefficient based on one future precipitation sub-data.

[0120] In simple terms, each future precipitation sub-data receives a number plate in the corresponding future precipitation quantum interval.

[0121] Step S8, obtaining the quotient of the maximum speed limit of the current driving area and the weight coefficient to obtain the recommended driving speed of the current driving area.

[0122] Preferably, referring to the above example, the dividend is divided by the divisor to obtain the quotient.

[0123] Step S9, when the future precipitation in the current driving area arrives, use the radar monitoring device to detect whether there is a vehicle. When there is a vehicle, use the broadcast display device to broadcast and display the recommended driving speed in the current driving area.

[0124] Preferably, to prevent precipitation weather from affecting the vehicle's acquisition of the recommended driving speed, the navigation device of the vehicle can be used for synchronous broadcast.

[0125] Further, all vehicles are equipped with navigation devices. In step S9, when the future precipitation in the current driving area arrives, use the radar monitoring device to detect whether there is a vehicle. When there is a vehicle, use the broadcast display device to broadcast and display the recommended driving speed in the current driving area. After that, it includes:

[0126] Step S10, use the navigation device of the current vehicle to obtain the driving area where the current vehicle is located and the corresponding recommended driving speed of the driving area.

[0127] Preferably, the recommended driving speed and the geographical coordinates of the driving area can be sent to the navigation satellite, and then forwarded by the navigation satellite to the navigation device of the vehicle.

[0128] Step S20, use the navigation device of the current vehicle to broadcast the corresponding recommended driving speed.

[0129] Step S30, based on a preset detection interval, use the navigation device of the current vehicle to repeatedly detect the real-time driving speed of the current vehicle.

[0130] Preferably, the preset detection interval can be set to 5 seconds.

[0131] Step S40, determine whether the real-time driving speed of the current vehicle is less than or equal to the recommended driving speed of the current driving area. If not, execute step S50.

[0132] Step S50, generate an overspeed reminder signal in the precipitation environment.

[0133] Step S60, broadcast the overspeed reminder signal in the precipitation environment once every preset detection interval.

[0134] Step S70, repeat steps S10 to S60 until the real-time driving speed of the current vehicle is less than or equal to the recommended driving speed of the current driving area, then stop broadcasting.

[0135] Further, in step S1, obtain several future precipitation data of the area where the highway is located based on a preset prediction step number, including:

[0136] Step S11, obtain several historical precipitation data of the area where the highway is located based on a preset time period.

[0137] Preferably, the step size of the preset time period can be the same as the step size of the preset prediction steps described above.

[0138] Step S12: Perform standard normalization on all historical precipitation data to obtain a normalized data set.

[0139] Preferably, in this embodiment, a zero-mean normalization (Z-score normalization) method is preferably used. This method normalizes the data based on the mean and standard deviation of the original data, and the processed data conforms to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. For the normalization method, batch normalization can also be used in this embodiment. Compared with simple normalization, in the training of neural networks in the past, only the data of the input layer was normalized, but not in the intermediate layer. Although the data set of the input nodes was normalized, the data distribution after matrix multiplication of the input data was very likely to change greatly, and as the number of network layers in the hidden layer deepened, the change in data distribution would become larger and larger. Therefore, batch normalization performs normalization in the intermediate layer of the neural network, resulting in better training effects.

[0140] Step S13: Divide the normalized data set into a training set and a validation set according to a preset ratio.

[0141] Preferably, the preset ratio can be set to 8:2 to divide the normalized data set into a training set and a sample set in a ratio of 8:2.

[0142] Preferably, in the actual application process, a certain proportion of the validation set is also required to verify the accuracy of the model, that is, it needs to be verified after training, and only after successful verification can the sample set be used for prediction. Usually, the image data is divided into a training set, a validation set, and a sample set in a ratio of 70%:15%:15%, that is, 70% of the data is the training set, 15% of the data is the validation set, and 15% of the data is the sample set.

[0143] Step S14: Define a neural network model with the input layer, hidden layer, and output layer connected in sequence by signals.

[0144] The neural network model is represented by the following formula:

[0145]

[0146] where y is the neural network model; x n is the nth input node of the input layer, and each input node corresponds to a normalized data set in the training set. is the weight from the mth input node of the input layer to the nth input node of the hidden layer. is the bias of the nth input node connected to the hidden layer; is the bias of the output layer; tansig(·) is the activation function; the number in the parentheses of the symbol subscript is the layer number, the subscript (1) is the first layer, i.e., the input layer, and the subscript (1, 2) is from the first layer to the second layer, i.e., from the input layer to the hidden layer.

[0147] It should be noted that the symbol meanings described in the above principle explanation are not interoperable with the meanings of other symbols in the context.

[0148] Step S15, input the training set input values into the input layer and perform several trainings through the neural network model.

[0149] Step S16, respectively obtain the root mean square error between the validation set and the current training result for each training.

[0150] Step S17, obtain the minimum error among all the root mean square errors.

[0151] Step S18, obtain the training result corresponding to the minimum error as the precipitation prediction model.

[0152] Preferably, training a neural network model usually requires providing a large amount of data, that is, a data set; the data set is generally divided into three categories, namely the above-mentioned training set (training set), validation set (validation set), and test set (test set).

[0153] Among them, one epoch is equal to the process of training once using all the samples in the training set. The so-called training once means performing one forward pass and one back pass; when the number of samples in one epoch (i.e., the training set) is too large, performing one training may consume too much time, and it is not entirely necessary to use all the data in the training set for each training. Therefore, the entire training set needs to be divided into multiple small pieces, that is, divided into multiple batches for training; one epoch consists of one or more batches. A batch is a part of the training set, and only a part of the data, that is, one batch, is used in each training process. The process of training one batch is one iteration.

[0154] Preferably, neural network training specifically includes the Perceptron. The Perceptron consists of two layers of neurons. The input layer receives external input signals and then transmits them to the output layer. The output layer is an M-P neuron, and the step function is y j = f(Σ i w i ·x i -θi )。

[0155] Preferably, given a training data set, the weights w i (i = 1, 2, ..., n) and the training bias θ i can be obtained through learning, and θ i can be understood as the weight w corresponding to a fixed value with fixed inputs of -1 and 0 i+1 。

[0156] It should be noted that the step function here does not have the same symbol meaning as other formulas in the embodiments. This step function is only for illustrative purposes and does not participate in the calculations of other formulas.

[0157] Preferably, the number of neural network training times in this embodiment can be set to 10,000 times.

[0158] Preferably, the learning rate for the 1st to 5000th epochs can be set to 0.01, the learning rate for the 5001st to 7500th epochs can be set to 0.001, and the learning rate for the 7501st to 10000th epochs can be set to 0.0001.

[0159] It can be understood that the neural network training in this embodiment mainly includes the following ideas:

[0160] ① Initialize the weights and bias terms in the network.

[0161] Initializing the parameter values (the weights and bias terms of the output units, and the weights and bias terms of the hidden units are all parameters of the model) is to activate the forward propagation, obtain the output values of each layer of elements, and thus obtain the value of the loss function.

[0162] ② Activate the forward propagation to obtain the output values of each layer and the expected values of the loss functions of each layer.

[0163] ③ Calculate the error terms of the output units and the error terms of the hidden units according to the loss function.

[0164] Calculate each error term, calculate the gradient of the parameter with respect to the loss function or calculate the partial derivative according to the chain rule of calculus. For the partial derivative of a vector or matrix in a composite function, the partial derivative of the inner function of the composite function is always chosen to be left-multiplied; for the partial derivative of a scalar in a composite function, the partial derivative of the inner function of the composite function can be chosen to be left-multiplied or right-multiplied.

[0165] ④ Update the weights and bias terms in the neural network.

[0166] ⑤ Repeat steps ② to ④ until the loss function is less than the preset bias or the number of iterations is used up, and output the parameters at this time as the current optimal parameters.

[0167] Step S19: Predict a number of future precipitation data based on a precipitation prediction model for a preset number of prediction steps.

[0168] Further, in step S5, define a weight coefficient based on each future precipitation sub-interval, and the magnitudes of all weight coefficients increase as the precipitation values in all future precipitation sub-intervals increase, including:

[0169] Step S51: Define all future precipitation sub-intervals as small precipitation intervals, medium precipitation intervals, large precipitation intervals, and heavy precipitation intervals in ascending order of precipitation values.

[0170] Preferably, the classification criteria for light rain, moderate rain, heavy rain, and rainstorm are as follows:

[0171] Light rain: The rainfall in 24 hours is less than 10 mm, or the rainfall in 12 hours is less than 5 mm. The raindrops are clearly distinguishable, and when they fall on the roof tiles and hard ground, they do not splash. The sound of the rain is gentle and pattering.

[0172] Moderate rain: The rainfall in 24 hours is between 10 and 25 mm, or the rainfall in 12 hours is between 5 and 15 mm. The rain falls in a line, and the raindrops are not easily distinguishable. When they fall on the roof tiles and hard ground, they splash slightly, and water puddles form relatively quickly.

[0173] Heavy rain: The rainfall in 24 hours is between 25 and 50 mm, or the rainfall in 12 hours is between 15 and 30 mm. The rain pours down like a deluge, blurring into a sheet. When the raindrops fall on the roof tiles and hard ground, they can splash up to several inches, and water pools form extremely quickly.

[0174] Rainstorm: The rainfall in 24 hours exceeds 50 mm and can be divided into three grades according to the intensity:

[0175] Rainstorm: The rainfall in 24 hours is between 50 and 100 mm.

[0176] Heavy rainstorm: The rainfall in 24 hours is between 100 and 250 mm.

[0177] Extra heavy rainstorm: The rainfall in 24 hours exceeds 250 mm.

[0178] Preferably, the classification criteria for light snow, moderate snow, heavy snow, and blizzard are as follows:

[0179] Light snow:

[0180] Precipitation in 24 hours: 0.1 to 2.4 mm.

[0181] Precipitation in 12 hours: 0.1 to 0.9 mm.

[0182] Visibility: The horizontal visibility distance is equal to or greater than 1000 m.

[0183] Depth of ground snow cover: Below 3 cm.

[0184] Moderate snow:

[0185] Precipitation in 24 hours: 2.5 to 4.9 mm.

[0186] Precipitation in 12 hours: 1.0 to 2.9 mm.

[0187] Visibility: Horizontal visibility distance is between 500 and 1000 meters.

[0188] Depth of ground snow cover: 3 to 5 cm.

[0189] Heavy snow:

[0190] Precipitation in 24 hours: 5.0 to 9.9 mm.

[0191] Precipitation in 12 hours: 3.0 to 5.9 mm.

[0192] Visibility: Horizontal visibility distance is less than 500 meters.

[0193] Depth of ground snow cover: Equal to or greater than 5 cm. 2

[0194] Blizzard:

[0195] Precipitation in 24 hours: 10.0 to 19.9 mm.

[0196] Precipitation in 12 hours: 6.0 to 9.9 mm.

[0197] Depth of ground snow cover: No specific standard.

[0198] Preferably, hailstones can be divided into small hailstones, medium hailstones and large hailstones according to the diameter size, and the classification criteria are as follows:

[0199] Small hailstone: Diameter is less than 5 mm.

[0200] Medium hailstone: Diameter is between 5 mm and 20 mm.

[0201] Large hailstone: Diameter is between 20 mm and 50 mm.

[0202] Extra-large hailstone: Diameter is greater than or equal to 50 mm.

[0203] In addition, according to the severity of hailstones, they can also be divided into light hail, medium hail and heavy hail:

[0204] Light hail: Most of the hailstones have a diameter not exceeding 0.5 cm, the cumulative hail time does not exceed 10 minutes, and the ground hail thickness does not exceed 2 cm.

[0205] Medium hail: Most of the hailstones have a diameter between 0.5 cm and 2 cm, the cumulative hail time is 10 to 30 minutes, and the ground hail thickness is 2 to 5 cm.

[0206] Heavy hail: The diameter of most hailstones is more than 2 cm, the cumulative hail - falling time reaches more than 30 minutes, and the thickness of the accumulated hail on the ground reaches more than 5 cm.

[0207] Step S52: Assign increasing first, second, third, and fourth weight coefficients to the small - precipitation interval, medium - precipitation interval, large - precipitation interval, and heavy - precipitation interval in sequence.

[0208] Preferably, if according to the national standard, the weight coefficients in the above text can be adopted; if customization is required, the first, second, third, and fourth weight coefficients can be defined as 1, 2, 3, and 4 in sequence.

[0209] Further, in step S9, when the future precipitation in the current driving area arrives, use the radar monitoring component to detect whether there is a vehicle. When there is a vehicle, use the broadcast display component to broadcast and display the recommended driving speed in the current driving area. After that, it includes:

[0210] Step S100: Calculate the braking distances of the vehicle in small precipitation, medium precipitation, large precipitation, and heavy precipitation based on the recommended driving speed in the current driving area respectively according to the braking - distance calculation formula.

[0211] Preferably, the braking distance can be calculated according to the braking - distance formula:

[0212]

[0213] Among them, S is the braking distance, in meters; V is the vehicle speed, in meters per second; g is the acceleration due to gravity, generally taken as 9.8 m / s 2 (or taken as 9.81 m / s according to specific circumstances 2 )

[0214] Since precipitation causes the change of the road - surface friction coefficient, the friction coefficient needs to be considered:

[0215]

[0216] Among them, μ is the friction coefficient.

[0217] Since there may be slopes on highway sections, then:

[0218]

[0219] Among them, i is the slope, expressed in decimal form. A positive sign indicates an uphill slope, and a negative sign indicates a downhill slope.

[0220] Step S200: Assign the braking distance corresponding to small precipitation to the small - precipitation interval.

[0221] Preferably, the friction coefficient when it is light rain on the highway is generally 0.3.

[0222] Step S300, assign the braking distance corresponding to moderate precipitation to the moderate precipitation interval.

[0223] Preferably, the friction coefficient when it is moderate rain on the highway is generally 0.25.

[0224] Step S400, assign the braking distance corresponding to heavy precipitation to the heavy precipitation interval.

[0225] Preferably, the friction coefficient when it is heavy rain on the highway is generally 0.2.

[0226] Step S500, assign the braking distance corresponding to extreme precipitation to the extreme precipitation interval.

[0227] Preferably, the friction coefficient when it is rainstorm on the highway is generally 0.15.

[0228] Preferably, the friction coefficient of the asphalt pavement is negatively correlated with the rainfall, that is, as the rainfall increases, the friction coefficient will decrease.

[0229] Specifically, rainwater will make the asphalt on the road surface slippery, thus reducing the friction coefficient. Especially at the beginning of the rain, due to more pollutants on the road surface, it is easy to form a lubricating film after mixing with rainwater, further reducing the friction coefficient of the road surface and increasing the risk of skidding. In addition, studies have shown that as the thickness of the water film increases, the friction process between the tire and the road surface will go through different lubrication stages, and there is a logarithmic relationship between the friction coefficient and the water film thickness in the mixed lubrication stage, which also illustrates the influence of rainfall (i.e., water film thickness) on the friction coefficient.

[0230] Step S600, obtain the driving distance between adjacent vehicles through the radar monitoring component in the current driving area.

[0231] Step S700, determine whether the driving distance is greater than or equal to the corresponding braking distance. If not, execute Step S800.

[0232] Step S800, generate a warning signal for too short vehicle distance.

[0233] Step S900, send the warning signal for too short vehicle distance to the navigation component of the vehicle located behind.

[0234] Further, in Step S900, after sending the warning signal for too short vehicle distance to the navigation component of the vehicle located behind, it includes:

[0235] Step S1000, repeatedly obtain the driving distance between adjacent vehicles through the radar monitoring component in the current driving area based on a preset detection interval.

[0236] Step S2000: Determine whether the inter-vehicle distance is greater than or equal to the corresponding braking distance. If not, execute Step S3000.

[0237] Step S3000: Broadcast a warning signal for too short a vehicle distance once every preset detection interval.

[0238] Step S4000: Repeat Step S1000 to Step S3000 until the inter-vehicle distance between the vehicle behind and the vehicle in front is greater than or equal to the corresponding braking distance, then stop broadcasting.

[0239] Further, in Step S7, classify all future precipitation sub-data into all future precipitation sub-intervals, and obtain a weight coefficient based on one future precipitation sub-data, including:

[0240] Step S71: Integrate all future precipitation sub-data to form a set of signals to be classified.

[0241] Preferably, the set of signals to be classified can be defined as X = {x 1 , x 2 , …, x j , …, x m}, where x j is the j-th future precipitation sub-data, and m is the number of all future precipitation sub-data.

[0242] Step S72: Define a set of categories according to all future precipitation sub-intervals.

[0243] Preferably, the set of categories can be defined as C = {y 1 , y 2 , …, y k , …, y n}, where y k is the k-th future precipitation sub-interval in the set of categories C, and n is the number of all future precipitation sub-intervals.

[0244] Step S73: Calculate the conditional probabilities of the set of signals to be classified under each of all future precipitation sub-intervals.

[0245] Preferably, the conditional probability can be calculated by the following formula:

[0246]

[0247] where P(Xy k ) is the conditional probability of all future precipitation sub-data in the k-th future precipitation sub-interval; P(y k ) is the marginal probability of the k-th future precipitation sub-interval; P(x j y k) is the conditional probability of the j-th future precipitation sub-data in the k-th future precipitation quantum interval.

[0248] Step S74: Classify each future precipitation sub-data into all the future precipitation quantum intervals with the highest conditional probability for each.

[0249] Step S75: Assign the weighted coefficient of the current future precipitation quantum interval to the classified future precipitation sub-data in the current future precipitation quantum interval.

[0250] Preferably, the classification algorithm in this embodiment preferably uses the Naive Bayes classification.

[0251] Preferably, the definition of Naive Bayes is as follows:

[0252] ① Let x = {a 1 , a 2 , a 3 , ……, a n} be an item to be classified, and each a is a feature of x.

[0253] ② There is a class set c = {y 1 , y 2 , y 3 , ……, y m}.

[0254] ③ Calculate P(y 1 |x), P(y 2 |x), ……, P(y m |x).

[0255] ④ If P(y k |x) = max{P(y 1 |x), P(y 2 |x), ……, P(y m |x)}, then x ∈ y k .

[0256] Then calculate each conditional probability in step ③ through the following steps:

[0257] 1. Find a set of items to be classified with known classifications, and this set is called the training sample set.

[0258] 2. Statistically obtain the conditional probability estimates of each feature attribute under each category. That is:

[0259] P(a 1 |y 1 ), P(a 2 |y 1 ), ……, P(a n |y 1 )

[0260] P(a 1 |y 2 ), P(a 2 |y 2 ), ……, P(a n |y 2 );

[0261] ……

[0262] P(a 1 |y m ), P(a 2 |y m ), ……, P(a n |y m );

[0263] 3. Assume that each feature attribute is conditionally independent. Then, according to Bayes' theorem:

[0264] P(y i |x) = P(x|y i )P(y i ) / P(x).

[0265] Since the denominator is a constant for all classes, it is only necessary to maximize the numerator. Also, because each feature attribute is conditionally independent, then:

[0266] P(x|y i )P(y i ) = P(a 1 |y i )P(a 2 |y i )... P(a n |y i )P(y i ).

[0267] It should be noted that the above preferred content is also an explanation of the principle, and its symbol meanings are not interoperable with those of other formulas in this embodiment.

[0268] In this embodiment, several future precipitation data of the area where the highway is located are obtained based on a preset prediction step; the highway is equally divided into several continuous driving areas along the driving radial center line of the highway, and each driving area includes a radar monitoring component and a broadcast display component; a future precipitation interval is constructed with zero as the minimum value of the precipitation interval and the maximum value of all future precipitation data as the maximum value of the precipitation interval; the future precipitation interval is equally divided into several future precipitation sub-intervals; a weight coefficient is defined based on each future precipitation sub-interval, and the magnitudes of all weight coefficients increase as the precipitation values of all future precipitation sub-intervals increase; several future precipitation sub-data of each driving area based on a preset prediction step are obtained respectively based on several future precipitation data; all future precipitation sub-data are classified into all future precipitation sub-intervals, and a weight coefficient is obtained based on one future precipitation sub-data; the quotient of the maximum speed limit of the current driving area and the weight coefficient is obtained to get the recommended driving speed of the current driving area; when the future precipitation in the current driving area arrives, it is detected whether there is a vehicle through the radar monitoring component, and when there is a vehicle, the recommended driving speed of the current driving area is broadcast and displayed through the broadcast display component. In this embodiment, the highway is divided into multiple small intervals for separate management, the precipitation conditions of each small interval are known in advance through the predicted precipitation data, and the passing speed of each small interval is restricted through the weight coefficient, so that the greater the precipitation, the lower the passing speed. Finally, the passing parameters corresponding to the small interval where the vehicle is located are obtained by radar detecting the small interval where the vehicle is located, effectively preventing the one-size-fits-all closed management of the highway and ensuring travel convenience.

[0269] As Figure 2 shown, this embodiment provides an embodiment of a highway passing device in rainy weather. In this embodiment, the highway passing device is applied to the highway passing method in the above embodiment.

[0270] Specifically, the highway passing device includes a future precipitation data acquisition module 1, a driving area division module 2, a future precipitation interval construction module 3, a future precipitation sub-interval division module 4, a weight coefficient definition module 5, a future precipitation sub-data acquisition module 6, a future precipitation sub-data classification module 7, a driving area recommended driving speed acquisition module 8, and a recommended driving speed broadcast module 9, which are electrically connected in sequence.

[0271] Among them, the future precipitation data acquisition module 1 is used to acquire a plurality of future precipitation data of the area where the highway is located based on a preset number of prediction steps; the driving area division module 2 is used to equally divide the highway into a plurality of continuous driving areas along the driving radial center line of the highway, and each driving area includes a radar monitoring component and a broadcast display component; the future precipitation interval construction module 3 is used to construct a future precipitation interval with zero as the minimum value of the precipitation interval and the maximum value of all future precipitation data as the maximum value of the precipitation interval; the future precipitation sub-interval division module 4 is used to equally divide the future precipitation interval into a plurality of future precipitation sub-intervals; the weight coefficient definition module 5 is used to define a weight coefficient based on each future precipitation sub-interval, and the magnitudes of all weight coefficients increase as the precipitation values of all future precipitation sub-intervals increase; the future precipitation sub-data acquisition module 6 is used to respectively acquire a plurality of future precipitation sub-data of each driving area based on a preset number of prediction steps based on a plurality of future precipitation data; the future precipitation sub-data classification module 7 is used to classify all future precipitation sub-data into all future precipitation sub-intervals, and obtain a weight coefficient based on one future precipitation sub-data; the recommended driving speed acquisition module 8 for the driving area is used to obtain the quotient of the maximum speed limit of the current driving area and the weight coefficient to obtain the recommended driving speed of the current driving area; the recommended driving speed broadcast module 9 is used to detect whether there is a vehicle through the radar monitoring component when the future precipitation in the current driving area arrives, and broadcast and display the recommended driving speed of the current driving area through the broadcast display component when there is a vehicle.

[0272] Further, the highway passing device further includes a recommended driving speed acquisition module, a recommended driving speed broadcast module, a real-time driving speed repeated detection module, a real-time driving speed judgment module, a precipitation environment speeding reminder signal generation module, a precipitation environment speeding reminder signal repeated broadcast module, and a first repeated execution module that are electrically connected in sequence; the recommended driving speed acquisition module is electrically connected to the recommended driving speed broadcast module 9, and the first repeated execution module is electrically connected to the recommended driving speed acquisition module.

[0273] Among them, the recommended driving speed acquisition module is used to obtain the driving area where the current vehicle is located and the recommended driving speed corresponding to the driving area through the navigation device of the current vehicle; the recommended driving speed broadcast module is used to broadcast the corresponding recommended driving speed through the navigation device of the current vehicle; the real-time driving speed repeated detection module is used to repeatedly detect the real-time driving speed of the current vehicle through the navigation device of the current vehicle based on a preset detection interval; the real-time driving speed judgment module is used to judge whether the real-time driving speed of the current vehicle is less than or equal to the recommended driving speed of the current driving area; the precipitation environment speeding reminder signal generation module is used to generate a precipitation environment speeding reminder signal if it is not less than or equal to the recommended driving speed of the current driving area; the precipitation environment speeding reminder signal repeated broadcast module is used to broadcast a precipitation environment speeding reminder signal once based on each preset detection interval; the first repeated execution module is used to repeatedly execute the recommended driving speed acquisition module to the precipitation environment speeding reminder signal repeated broadcast module until the real-time driving speed of the current vehicle is less than or equal to the recommended driving speed of the current driving area, and then stop broadcasting.

[0274] Further, the future precipitation data acquisition module 1 specifically includes a first future precipitation data acquisition sub-module, a second future precipitation data acquisition sub-module, a third future precipitation data acquisition sub-module, a fourth future precipitation data acquisition sub-module, a fifth future precipitation data acquisition sub-module, a sixth future precipitation data acquisition sub-module, a seventh future precipitation data acquisition sub-module, an eighth future precipitation data acquisition sub-module, and a ninth future precipitation data acquisition sub-module that are electrically connected in sequence; the ninth future precipitation data acquisition sub-module is electrically connected to the driving area division module 2.

[0275] Among them, the first future precipitation data acquisition sub-module is used to obtain a plurality of historical precipitation data of the area where the highway is located based on a preset time period; the second future precipitation data acquisition sub-module is used to perform standard normalization processing on all historical precipitation data to obtain a normalized data set; the third future precipitation data acquisition sub-module is used to divide the normalized data set into a training set and a validation set according to a preset ratio; the fourth future precipitation data acquisition sub-module is used to define a neural network model in which the input layer, the hidden layer, and the output layer are sequentially connected by signals; the fifth future precipitation data acquisition sub-module is used to input the training set input value into the input layer and perform several trainings through the neural network model; the sixth future precipitation data acquisition sub-module is used to obtain the root mean square error between the validation set and the current training result respectively based on each training; the seventh future precipitation data acquisition sub-module is used to obtain the minimum error among all root mean square errors; the eighth future precipitation data acquisition sub-module is used to obtain the training result corresponding to the minimum error as the precipitation prediction model; the ninth future precipitation data acquisition sub-module is used to predict a plurality of future precipitation data based on the precipitation prediction model based on a preset prediction step.

[0276] Furthermore, the weight coefficient definition module 5 specifically includes a first weight coefficient definition sub-module and a second weight coefficient definition sub-module that are electrically connected in sequence; the first weight coefficient definition sub-module is electrically connected to the future precipitation sub-interval division module 4, and the second weight coefficient definition sub-module is electrically connected to the future precipitation sub-data acquisition module 6.

[0277] Among them, the first weight coefficient definition sub-module is used to define all future precipitation sub-intervals as small precipitation intervals, medium precipitation intervals, large precipitation intervals, and heavy precipitation intervals in ascending order according to the precipitation values; the second weight coefficient definition sub-module is used to assign increasing first weight coefficients, second weight coefficients, third weight coefficients, and fourth weight coefficients to the small precipitation interval, medium precipitation interval, large precipitation interval, and heavy precipitation interval in sequence.

[0278] Furthermore, the highway passing device further includes a braking distance calculation module, a small precipitation interval assignment module, a medium precipitation interval assignment module, a large precipitation interval assignment module, a heavy precipitation interval assignment module, a driving distance acquisition module, a driving distance judgment module, a vehicle distance too short warning signal generation module, and a vehicle distance too short warning signal sending module that are electrically connected in sequence; the braking distance calculation module is electrically connected to the recommended driving speed broadcast module 9.

[0279] Among them, the braking distance calculation module is used to calculate the braking distances of the vehicle during small precipitation, medium precipitation, large precipitation, and heavy precipitation based on the recommended driving speed in the current driving area according to the braking distance calculation formula; the small precipitation interval assignment module is used to assign the braking distance corresponding to small precipitation to the small precipitation interval; the medium precipitation interval assignment module is used to assign the braking distance corresponding to medium precipitation to the medium precipitation interval; the large precipitation interval assignment module is used to assign the braking distance corresponding to large precipitation to the large precipitation interval; the heavy precipitation interval assignment module is used to assign the braking distance corresponding to heavy precipitation to the heavy precipitation interval; the driving distance acquisition module is used to obtain the driving distance between adjacent vehicles through the radar monitoring component in the current driving area; the driving distance judgment module is used to judge whether the driving distance is greater than or equal to the corresponding braking distance; the vehicle distance too short warning signal generation module is used to generate a vehicle distance too short warning signal if it is not greater than or equal to the corresponding braking distance; the vehicle distance too short warning signal sending module is used to send the vehicle distance too short warning signal to the navigation device of the vehicle located behind.

[0280] Furthermore, the highway passing device further includes a driving distance repeated acquisition module, a driving distance repeated judgment module, a vehicle distance too short warning signal repeated broadcast module, and a second repeated execution module that are electrically connected in sequence; the driving distance repeated acquisition module is electrically connected to the vehicle distance too short warning signal sending module.

[0281] Among them, the driving distance repeated acquisition module is used to repeatedly acquire the driving distance between adjacent vehicles through the radar monitoring component in the current driving area based on a preset detection interval; the driving distance repeated judgment module is used to judge whether the driving distance is greater than or equal to the corresponding braking distance; the short vehicle distance warning signal repeated broadcast module is used to, if it is not greater than or equal to the corresponding braking distance, broadcast a short vehicle distance warning signal once based on each preset detection interval; the second repeated execution module is used to repeatedly execute the driving distance repeated acquisition module to the short vehicle distance warning signal repeated broadcast module until the driving distance between the vehicle behind and the vehicle in front is greater than or equal to the corresponding braking distance, and then stop broadcasting.

[0282] Further, the future precipitation sub-data classification module 7 specifically includes a first future precipitation sub-data classification sub-module, a second future precipitation sub-data classification sub-module, a third future precipitation sub-data classification sub-module, a fourth future precipitation sub-data classification sub-module, and a fifth future precipitation sub-data classification sub-module that are electrically connected in sequence; the first future precipitation sub-data classification sub-module is electrically connected to the future precipitation sub-data acquisition module 6, and the fifth future precipitation sub-data classification sub-module is electrically connected to the driving area recommended driving speed acquisition module 8.

[0283] Among them, the first future precipitation sub-data classification sub-module is used to integrate all future precipitation sub-data to form a set of signals to be classified; the second future precipitation sub-data classification sub-module is used to define a set of categories according to all future precipitation sub-intervals; the third future precipitation sub-data classification sub-module is used to calculate the conditional probabilities of the set of signals to be classified under each of all future precipitation sub-intervals; the fourth future precipitation sub-data classification sub-module is used to classify each future precipitation sub-data into the all future precipitation sub-intervals with the highest conditional probability respectively; the fifth future precipitation sub-data classification sub-module is used to assign the weighted coefficient of the current future precipitation sub-interval to the classified future precipitation sub-data in the current future precipitation sub-interval.

[0284] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. For the preferred, extended, limited, exemplified, and principle description parts of this embodiment, please refer to the above embodiment, and this embodiment will not be elaborated here.

[0285] In this embodiment, several future precipitation data of the area where the highway is located are obtained based on a preset prediction step; the highway is equally divided into several continuous driving areas along the radial center line of the highway driving direction, and each driving area includes a radar monitoring component and a broadcast display component; a future precipitation range is constructed with zero as the minimum value of the precipitation range and the maximum value of all future precipitation data as the maximum value of the precipitation range; the future precipitation range is equally divided into several future precipitation sub-ranges; a weight coefficient is defined based on each future precipitation sub-range, and the magnitudes of all weight coefficients increase as the precipitation values of all future precipitation sub-ranges increase; several future precipitation sub-data of each driving area based on a preset prediction step are obtained respectively based on several future precipitation data; all future precipitation sub-data are classified into all future precipitation sub-ranges, and a weight coefficient is obtained based on one future precipitation sub-data; the quotient of the maximum speed limit of the current driving area and the weight coefficient is obtained to get the recommended driving speed of the current driving area; when the future precipitation in the current driving area arrives, it is detected whether there is a vehicle through the radar monitoring component, and when there is a vehicle, the recommended driving speed of the current driving area is broadcast and displayed through the broadcast display component. In this embodiment, the highway is divided into multiple small intervals for separate management, the precipitation conditions of each small interval are obtained in advance through the predicted precipitation data, and the passing speed of each small interval is restricted through the weight coefficient, so that the greater the precipitation, the lower the passing speed. Finally, the passing parameters corresponding to the small interval where the vehicle is located are obtained by radar detecting the small interval where the vehicle is located, effectively preventing the one-size-fits-all closed management of the highway and ensuring travel convenience.

[0286] Figure 3 An embodiment of the electronic device of the present application is shown. Refer to Figure 3 , the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0287] The memory 102 stores program instructions for implementing the highway passing method in rainy weather in any of the above embodiments.

[0288] The processor 101 is configured to execute the program instructions stored in the memory 102 to perform highway passing in rainy weather.

[0289] Among them, the processor 101 can also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip with signal processing capabilities. The processor 101 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0290] Furthermore, Figure 4 is a schematic structural diagram of a storage medium according to an embodiment of the present application. Refer to Figure 4 , the storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods. Among them, the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0291] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling, direct coupling, or communication connection can be through some interfaces. The indirect coupling or communication connection of devices or units can be in an electrical, mechanical, or other form.

[0292] In addition, in each embodiment of the present application, each functional unit may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. The above is only the implementation mode of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be included in the patent protection scope of the present application by the same token.

[0293] The specific implementation modes of the application have been described in detail above, but they are only examples, and the present application is not limited to the specific implementation modes described above. For those skilled in the art, any equivalent modification or substitution to the application is also within the scope of the present application. Therefore, all equal transformations, modifications, improvements, etc. made without departing from the spirit and principles of the present application should be covered by the scope of the present application.

Claims

1. A method for passing a highway in precipitation weather, the method for passing a highway is applied to a highway that is about to be precipitated, and vehicles traveling on the highway, wherein a radar monitoring element and a broadcast display element are provided at each preset interval on the highway, and the method is characterized in that: The expressway travel method comprises: Step S1, obtaining a number of future precipitation data based on a preset number of prediction steps in the area where the expressway is located; Step S2, dividing the expressway into a plurality of continuous driving areas along the driving radial center line of the expressway, each driving area including a radar monitoring unit and a broadcast display unit; Step S3, constructing a future precipitation interval with zero as the minimum value of the precipitation interval and the maximum value of all future precipitation data as the maximum value of the precipitation interval; Step S4, dividing the future precipitation interval into a plurality of future precipitation quantum intervals; Step S5, defining a weight coefficient based on each future precipitation quantum interval, and the magnitude of all weight coefficients increases as the precipitation values ​​of all future precipitation quantum intervals increase; Step S6, obtaining a plurality of future precipitation sub-data for each driving area based on the preset prediction steps based on a plurality of future precipitation data; Step S7, classifying all future precipitation sub-data into all future precipitation quantum intervals, and obtaining a weight coefficient based on one future precipitation sub-data; Step S8, obtaining the quotient of the maximum speed limit of the current driving area and the weight coefficient to obtain the recommended driving speed of the current driving area; Step S9, when the future precipitation in the current driving area arrives, the radar monitoring component detects whether there is a vehicle, and when there is a vehicle, the announcement and display component announces and displays the recommended driving speed of the current driving area.

2. The highway travel method according to claim 1, wherein all vehicles are equipped with navigation components, characterized in that: Step S9, when the future precipitation in the current driving area arrives, the radar monitoring component detects whether there is a vehicle, and when there is a vehicle, the announcement and display component announces and displays the recommended driving speed of the current driving area, and then includes: Step S10, obtaining the driving area where the current vehicle is located and the recommended driving speed corresponding to the driving area through the navigation component of the current vehicle; Step S20, broadcasting the corresponding recommended driving speed through the navigation component of the current vehicle; Step S30, repeatedly detecting the real-time driving speed of the current vehicle through the navigation component of the current vehicle based on a preset detection interval; Step S40, determining whether the current real-time driving speed of the vehicle is less than or equal to the recommended driving speed of the current driving area, if not, executing step S50; Step S50, generating a precipitation environment overspeed warning signal; Step S60, broadcasting the precipitation environment speeding reminder signal once based on each preset detection interval; Step S70, repeating steps S10 to S60 until the real-time driving speed of the current vehicle is less than or equal to the recommended driving speed of the current driving area, then stopping the announcement.

3. The highway passing method according to claim 1, characterized in that: Step S1, obtaining a number of future precipitation data based on a preset number of prediction steps in the area where the expressway is located, including: Step S11, obtaining a plurality of historical precipitation data based on a preset time period in the area where the expressway is located; Step S12, performing standard normalization processing on all historical precipitation data to obtain a normalized data set; Step S13, dividing the normalized data set into a training set and a validation set according to a preset ratio; Step S14, defining a neural network model in which the input layer, the hidden layer, and the output layer are sequentially connected; Step S15, inputting the training set into the input layer, and performing several trainings through the neural network model; Step S16, obtaining a root mean square error between the verification set and the current training result based on each training; Step S17, obtaining the minimum error value among all root mean square errors; Step S18, obtaining a training result corresponding to the minimum error value as a precipitation prediction model; Step S19: predicting a number of future precipitation data based on the preset prediction steps by using the precipitation prediction model.

4. The highway passing method according to claim 2, characterized in that: Step S5, defining a weight coefficient based on each future precipitation quantum interval, the magnitude of all weight coefficients increases as the precipitation values ​​of all future precipitation quantum intervals increase, including: Step S51, defining all future precipitation quantum intervals as small precipitation intervals, medium precipitation intervals, large precipitation intervals, and heavy precipitation intervals in ascending order according to precipitation values; Step S52, assigning a first weight coefficient, a second weight coefficient, a third weight coefficient, and a fourth weight coefficient in increasing order to the light precipitation interval, the medium precipitation interval, the heavy precipitation interval, and the heavy precipitation interval.

5. The highway passing method according to claim 4, characterized in that: Step S9, when the future precipitation in the current driving area arrives, the radar monitoring component detects whether there is a vehicle, and when there is a vehicle, the announcement and display component announces and displays the recommended driving speed of the current driving area, and then includes: Step S100, calculating the braking distance of the vehicle based on the recommended driving speed in the current driving area when there is light precipitation, moderate precipitation, heavy precipitation, and torrential precipitation respectively according to the braking distance calculation formula; Step S200, assigning a braking distance corresponding to light precipitation to the light precipitation interval; Step S300, assigning a braking distance corresponding to medium precipitation to the medium precipitation interval; Step S400, assigning a braking distance corresponding to heavy precipitation to the heavy precipitation interval; Step S500, assigning a braking distance corresponding to the heavy rainfall to the heavy rainfall interval; Step S600, obtaining the driving distance between adjacent vehicles through the radar monitoring device in the current driving area; Step S700, determining whether the driving distance is greater than or equal to the corresponding braking distance, if not, executing step S800; Step S800, generating a short headway warning signal; Step S900: sending the short distance warning signal to the navigation device of the vehicle behind.

6. The highway passing method according to claim 5, characterized in that: Step S900, sending the short distance warning signal to the navigation device of the vehicle behind, and then including: Step S1000, repeatedly acquiring the driving distance between adjacent vehicles through the radar monitoring element in the current driving area based on the preset detection interval; Step S2000, determining whether the driving distance is greater than or equal to the corresponding braking distance, if not, executing step S3000; Step S3000, broadcasting the short distance warning signal once based on each preset detection interval; Step S4000, repeating steps S1000 to S3000 until the distance between the vehicle at the rear and the vehicle at the front is greater than or equal to the corresponding braking distance, then stopping the broadcast.

7. The highway passing method according to claim 1, characterized in that: Step S7, classifying all future precipitation sub-data into all future precipitation quantum intervals, and obtaining a weight coefficient based on one future precipitation sub-data, including: Step S71, integrating all future precipitation sub-data to form a signal set to be classified; Step S72, defining a category set according to all future precipitation quantum intervals; Step S73, calculating the conditional probability of the signal set to be classified in each of all future precipitation quantum intervals; Step S74, classifying each future precipitation sub-data into all future precipitation quantum intervals with the highest conditional probability; Step S75 , assigning the classified future precipitation sub-data in the current future precipitation quantum interval with the weight coefficient of the current future precipitation quantum interval.

8. A highway passing device for rainy weather, the highway passing device being applied to the highway passing method according to any one of claims 1 to 7, characterized in that: The highway traffic device comprises: A future precipitation data acquisition module is used to acquire a number of future precipitation data based on a preset prediction step number in the area where the expressway is located; A driving area division module, used to divide the expressway into a plurality of continuous driving areas along the driving radial center line of the expressway, each driving area including a radar monitoring unit and a broadcast display unit; A future precipitation interval construction module is used to construct a future precipitation interval with a zero value as the minimum value of the precipitation interval and a maximum value of all future precipitation data as the maximum value of the precipitation interval; A future precipitation quantum interval division module is used to divide the future precipitation interval into a number of future precipitation quantum intervals; A weight coefficient definition module is used to define a weight coefficient based on each future precipitation quantum interval, and the size of all weight coefficients increases as the precipitation values ​​of all future precipitation quantum intervals increase; A future precipitation sub-data acquisition module is used to respectively acquire a plurality of future precipitation sub-data of each driving area based on the preset prediction steps based on a plurality of future precipitation amount data; A future precipitation sub-data classification module is used to classify all future precipitation sub-data into all future precipitation quantum intervals, and obtain a weight coefficient based on one future precipitation sub-data; The driving area recommended driving speed acquisition module is used to obtain the quotient of the maximum speed limit of the current driving area and the weight coefficient to obtain the recommended driving speed of the current driving area; The recommended driving speed broadcast module is used to detect whether there are vehicles through the radar monitoring component when future precipitation arrives in the current driving area, and to broadcast and display the recommended driving speed of the current driving area through the broadcast display component when there are vehicles.

9. An electronic device, characterized in that: It includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the highway passing method as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the highway passing method according to any one of claims 1 to 7 can be implemented.

Images