Hybrid transmission gear shifting control method and vehicle

Abstract

The invention discloses a hybrid transmission gear shifting control method and a vehicle. The method comprises the steps that environment data, road condition data and vehicle running state data of a target vehicle at the first moment are obtained; the environment data, the road condition data and the vehicle running state data are input into the gear shifting boundary prediction model, gear shifting boundary prediction vehicle speeds of the target vehicle at the second moment are output, the gear shifting boundary prediction vehicle speeds comprise the first prediction vehicle speed and the second prediction vehicle speed, and the first prediction vehicle speed is the boundary vehicle speed value between the series gear and the power dividing gear; the second predicted vehicle speed is a boundary vehicle speed value between the power split gear and the direct drive gear; and the first predicted vehicle speed and the second predicted vehicle speed are sent to the vehicle end controller so that the vehicle end controller can conduct gear shifting control on the hybrid transmission at the second moment according to the first predicted vehicle speed and / or the second predicted vehicle speed. According to the method and the device, the gear shifting control of the gear shifting gearbox can better conform to the actual working condition of the target vehicle, so that the user experience is improved.

Description

Technical Field

[0001] This application belongs to the field of shift control technology, and particularly relates to a shift control method for a hybrid transmission and a vehicle. Background Technology

[0002] To enable hybrid vehicles to operate in different modes, hybrid transmissions can offer various gears, such as EV (pure electric) gears, power-split VT (ECVT) gears, and direct-drive gears. Different gears can be matched with different power source combinations. Currently, hybrid transmissions typically use fixed shift boundaries, such as shifting when the vehicle speed reaches a certain threshold, which results in a poor user experience. Summary of the Invention

[0003] The embodiments of this application provide a hybrid transmission shift control method and a vehicle, which at least to a certain extent enables the shift control of the transmission to better match the actual operating conditions of the target vehicle, thereby improving the user experience.

[0004] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0005] The first aspect of this application provides a hybrid transmission shift control method, wherein the hybrid transmission includes a series gear, a power-split gear, and a direct-drive gear, and the method includes:

[0006] The shift reference data of the target vehicle at the first moment is obtained. The shift reference data includes environmental data, road condition data and vehicle operating status data. The target vehicle includes a vehicle-side controller.

[0007] The environmental data, road condition data, and vehicle operating status data are input into the shift boundary prediction model to output the shift boundary predicted speed of the target vehicle at a second time point, wherein the second time point is later than the first time point. The shift boundary predicted speed includes a first predicted speed and a second predicted speed. The first predicted speed is the boundary speed value between the series gear and the power split gear, and the second predicted speed is the boundary speed value between the power split gear and the direct drive gear. The shift boundary prediction model is obtained by training the network to be trained based on historical samples. The historical samples include historical environmental data, historical road condition data, historical vehicle operating status data, and corresponding historical actual shift boundary speeds.

[0008] The first predicted vehicle speed and the second predicted vehicle speed are sent to the vehicle-side controller so that the vehicle-side controller can perform shift control on the hybrid transmission at the second time based on the first predicted vehicle speed and / or the second predicted vehicle speed.

[0009] Optionally, obtaining the shift reference data of the target vehicle at the first moment includes:

[0010] The average environmental data, average road condition data, and average vehicle operating status data of the target vehicle are obtained during a first time period, which includes the first moment.

[0011] Optionally, after acquiring the shift reference data of the target vehicle at the first moment, the method further includes:

[0012] Obtain a preset quantization rule, wherein the quantization rule divides the data range of each type of data in the shift reference data into multiple data intervals, and each data interval corresponds to a quantization value;

[0013] For each type of data—environmental data, road condition data, and vehicle operating status data—a corresponding target quantization value is matched based on the quantization rules.

[0014] Optionally, the network to be trained includes a gated recurrent unit network (GRU), which includes an input layer, a hidden layer, and an output layer. The hidden layer includes a first sub-network and a second sub-network. The training process of the shift boundary prediction model includes:

[0015] The historical environmental data, historical road condition data, historical vehicle operating status data, and historical actual shift boundary vehicle speed are input into the input layer so that the input layer outputs the first feature.

[0016] The first feature is input into the first sub-network layer to output a first hidden feature of a preset dimension;

[0017] The first hidden feature is input into the second sub-network so that the second sub-network combines contextual information, dynamically allocates weights at different time steps based on the multi-head attention mechanism, and outputs the second hidden feature.

[0018] The second hidden feature is input into the output layer to output a first trained predicted vehicle speed and a second trained predicted vehicle speed. Optionally, at least one of the following must be satisfied:

[0019] The environmental data includes one or more of the following: weather type data, altitude data, and slope data.

[0020] The traffic data includes one or more of the following: congestion data and traffic light data.

[0021] The vehicle operating status data includes one or more of the following: power demand data, vehicle speed data, and battery charge data. Optionally, the method further includes:

[0022] Each of the shift reference data and the first predicted vehicle speed and the second predicted vehicle speed corresponding to each shift reference data are sent to the vehicle-side controller, so that the vehicle-side controller stores the first predicted vehicle speed and the second predicted vehicle speed corresponding to each shift reference data.

[0023] A second aspect of this application provides a hybrid transmission shift control device, the hybrid transmission including a series gear, a power-split gear, and a direct-drive gear, the device comprising:

[0024] The first acquisition unit is used to acquire the shift reference data of the target vehicle at a first moment. The shift reference data includes environmental data, road condition data and vehicle operating status data. The target vehicle includes a vehicle-side controller.

[0025] An input unit is used to input the environmental data, road condition data, and vehicle operating status data into a shift boundary prediction model to output the shift boundary predicted speed of the target vehicle at a second time point, wherein the second time point is later than the first time point. The shift boundary predicted speed includes a first predicted speed and a second predicted speed. The first predicted speed is the boundary speed value between the serial gear and the power split gear, and the second predicted speed is the boundary speed value between the power split gear and the direct drive gear. The shift boundary prediction model is obtained by training the network to be trained based on historical samples. The historical samples include historical environmental data, historical road condition data, historical vehicle operating status data, and corresponding historical actual shift boundary speeds.

[0026] The first transmitting unit is configured to transmit the first predicted vehicle speed and the second predicted vehicle speed to the vehicle-end controller, so that the vehicle-end controller can perform shift control on the hybrid transmission at the second time based on the first predicted vehicle speed and / or the second predicted vehicle speed.

[0027] Optionally, when acquiring the shift reference data of the target vehicle at the first moment, the first acquisition unit is used to:

[0028] The average environmental data, average road condition data, and average vehicle operating status data of the target vehicle are obtained during a first time period, which includes the first moment.

[0029] Optionally, the device further includes:

[0030] The second acquisition unit is used to acquire a preset quantization rule. The quantization rule is divided into multiple data intervals according to the data range of each type of data in the shift reference data, and each data interval corresponds to a quantization value.

[0031] The matching unit is used to match a corresponding target quantization value for each type of data, including the environmental data, the road condition data, and the vehicle operating status data, based on the quantization rules.

[0032] Optionally, the network to be trained includes a gated recurrent unit network (GRU), which includes an input layer, a hidden layer, and an output layer. The hidden layer includes a first sub-network and a second sub-network. The training process of the shift boundary prediction model includes:

[0033] The historical environmental data, historical road condition data, historical vehicle operating status data, and historical actual shift boundary vehicle speed are input into the input layer so that the input layer outputs the first feature.

[0034] The first feature is input into the first sub-network layer to output a first hidden feature of a preset dimension;

[0035] The first hidden feature is input into the second sub-network so that the second sub-network combines contextual information, dynamically allocates weights at different time steps based on the multi-head attention mechanism, and outputs the second hidden feature.

[0036] The second hidden feature is input into the output layer to output a first trained predicted vehicle speed and a second trained predicted vehicle speed. Optionally, at least one of the following must be satisfied:

[0037] The environmental data includes one or more of the following: weather type data, altitude data, and slope data.

[0038] The traffic data includes one or more of the following: congestion data and traffic light data.

[0039] The vehicle operating status data includes one or more of the following: power demand data, vehicle speed data, and battery charge data. Optionally, the device further includes:

[0040] The second transmitting unit is used to transmit each of the shift reference data and the first predicted vehicle speed and the second predicted vehicle speed corresponding to each of the shift reference data to the vehicle-end controller, so that the vehicle-end controller stores the first predicted vehicle speed and the second predicted vehicle speed corresponding to each of the shift reference data.

[0041] A third aspect of this application provides a hybrid transmission shift control method, wherein the hybrid transmission includes a series gear, a power-split gear, and a direct-drive gear, and the method includes:

[0042] The target vehicle's operating status data at a first moment is uploaded to a cloud server. The cloud server also acquires the target vehicle's environmental and road condition data at the first moment. The environmental data, road condition data, and vehicle operating status data constitute shift reference data. The cloud server inputs the environmental data, road condition data, and vehicle operating status data into a shift boundary prediction model to output the target vehicle's shift boundary predicted speed at a second moment, where the second moment is later than the first moment. The shift boundary predicted speed includes a first predicted speed and a second predicted speed. The first predicted speed is the boundary speed value between the serial gear and the power-split gear, and the second predicted speed is the boundary speed value between the power-split gear and the direct-drive gear. The shift boundary prediction model is obtained by training the network based on historical samples, including historical environmental data, historical road condition data, historical vehicle operating status data, and historical actual shift boundary speeds.

[0043] The system receives the first predicted vehicle speed and the second predicted vehicle speed sent by the cloud server, and at the second moment, performs shift control on the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed.

[0044] Optionally, the step of controlling the shift of the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed includes:

[0045] Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0046] When the first actual vehicle speed is less than the first predicted vehicle speed, if the hybrid transmission is in the power split gear, then the hybrid transmission is controlled to switch to the series gear; if the hybrid transmission is in the direct drive gear, then the hybrid transmission is controlled to switch to the power split gear.

[0047] Optionally, after controlling the hybrid transmission to switch to the power split gear, the method further includes: obtaining the second actual vehicle speed of the target vehicle at a third moment, wherein the third moment is later than the second moment;

[0048] When the second actual vehicle speed is less than the first predicted vehicle speed, the hybrid transmission is controlled to switch from the power split gear to the series gear.

[0049] Optionally, the step of controlling the shift of the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed includes:

[0050] Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0051] When the first actual vehicle speed is greater than or equal to the first predicted vehicle speed and less than the second predicted vehicle speed, if the hybrid transmission is in the series gear position, the hybrid transmission is controlled to switch to the power split gear position; if the hybrid transmission is in the direct drive gear position, the hybrid transmission is controlled to switch to the power split gear position.

[0052] Optionally, the step of controlling the shift of the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed includes:

[0053] Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0054] When the target vehicle speed is greater than or equal to the second predicted vehicle speed, if the hybrid transmission is in the series gear position, the hybrid transmission is controlled to switch to the power split gear position; if the hybrid transmission is in the power split gear position, the hybrid transmission is controlled to switch to the direct drive gear position.

[0055] Optionally, after controlling the hybrid transmission to switch to the power split gear, the method further includes: obtaining the second actual vehicle speed of the target vehicle at a third moment, wherein the third moment is later than the second moment;

[0056] When the second actual vehicle speed is greater than or equal to the second predicted vehicle speed, the hybrid transmission is controlled to switch from the power split gear to the direct drive gear.

[0057] Optionally, the method further includes:

[0058] In the event of a communication interruption between the target vehicle and the cloud server, the target shift reference data with the highest similarity to the current shift reference data of the target vehicle is obtained from a plurality of pre-stored shift reference data, along with the first target predicted vehicle speed and the second target predicted vehicle speed corresponding to the target shift reference data.

[0059] The hybrid transmission is shift-controlled based on the predicted vehicle speed of the first target and / or the predicted vehicle speed of the second target. A fourth aspect of this application provides a hybrid transmission shift-control device, the hybrid transmission including a series gear, a power-split gear, and a direct-drive gear, the device comprising:

[0060] An upload unit is used to upload the vehicle operating status data of the target vehicle at a first moment to a cloud server. The cloud server also acquires the environmental data and road condition data of the target vehicle at the first moment. The environmental data, road condition data, and vehicle operating status data constitute shift reference data. The cloud server inputs the environmental data, road condition data, and vehicle operating status data into a shift boundary prediction model to output the shift boundary predicted speed of the target vehicle at a second moment, where the second moment is later than the first moment. The shift boundary predicted speed includes a first predicted speed and a second predicted speed. The first predicted speed is the boundary speed value between the serial gear and the power-split gear, and the second predicted speed is the boundary speed value between the power-split gear and the direct-drive gear. The shift boundary prediction model is obtained by training the network to be trained based on historical samples, including historical environmental data, historical road condition data, historical vehicle operating status data, and historical actual shift boundary speeds.

[0061] The first control unit is configured to receive the first predicted vehicle speed and the second predicted vehicle speed sent by the cloud server, and at the second moment, perform shift control on the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed.

[0062] Optionally, when performing shift control on the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed, the first shift control unit is used to:

[0063] Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0064] When the first actual vehicle speed is less than the first predicted vehicle speed, if the hybrid transmission is in the power split gear, then the hybrid transmission is controlled to switch to the series gear; if the hybrid transmission is in the direct drive gear, then the hybrid transmission is controlled to switch to the power split gear.

[0065] Optionally, the device further includes:

[0066] The third acquisition unit is used to acquire the second actual vehicle speed of the target vehicle at a third moment, wherein the third moment is later than the second moment.

[0067] The second control unit is used to control the hybrid transmission to switch from the power split gear to the series gear when the second actual vehicle speed is less than the first predicted vehicle speed.

[0068] Optionally, when performing shift control on the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed, the first shift control unit is used to:

[0069] Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0070] When the first actual vehicle speed is greater than or equal to the first predicted vehicle speed and less than the second predicted vehicle speed, if the hybrid transmission is in the series gear position, the hybrid transmission is controlled to switch to the power split gear position; if the hybrid transmission is in the direct drive gear position, the hybrid transmission is controlled to switch to the power split gear position.

[0071] Optionally, when performing shift control on the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed, the first shift control unit is used to:

[0072] Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0073] When the target vehicle speed is greater than or equal to the second predicted vehicle speed, if the hybrid transmission is in the series gear position, the hybrid transmission is controlled to switch to the power split gear position; if the hybrid transmission is in the power split gear position, the hybrid transmission is controlled to switch to the direct drive gear position.

[0074] Optionally, the device further includes:

[0075] The fourth acquisition unit is used to acquire the second actual vehicle speed of the target vehicle at a third moment, wherein the third moment is later than the second moment;

[0076] The third control unit is used to control the hybrid transmission to switch from the power split gear to the direct drive gear when the second actual vehicle speed is greater than or equal to the second predicted vehicle speed.

[0077] Optionally, the device further includes:

[0078] The fifth acquisition unit is used to, in the event of a communication interruption between the target vehicle and the cloud server, acquire, from a plurality of pre-stored shift reference data, the target shift reference data that has the highest similarity to the current shift reference data of the target vehicle, as well as the first target predicted vehicle speed and the second target predicted vehicle speed corresponding to the target shift reference data.

[0079] The fourth control unit is used to perform shift control on the hybrid transmission based on the first target predicted vehicle speed and / or the second target predicted vehicle speed.

[0080] A fifth aspect of this application provides a vehicle including one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, the at least one piece of program code being loaded and executed by the one or more processors to perform the operations performed as described in any of the methods in the third aspect.

[0081] A sixth aspect of this application provides a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to perform the operation as described in any of the methods in the first aspect or any of the methods in the second aspect.

[0082] The embodiments of the present invention provide one or more technical solutions that achieve at least the following technical effects or advantages:

[0083] The hybrid transmission shift control method provided in this application includes a hybrid transmission with series gears, power-split gears, and direct-drive gears. The method includes: acquiring shift reference data of a target vehicle at a first moment, the shift reference data including environmental data, road condition data, and vehicle operating status data; the target vehicle including a vehicle-side controller; inputting the environmental data, road condition data, and vehicle operating status data into a shift boundary prediction model to output the shift boundary predicted vehicle speed of the target vehicle at a second moment, wherein the second moment is later than the first moment, and the shift boundary predicted vehicle speed includes a first predicted vehicle speed and a second predicted vehicle speed. The vehicle speed is predicted in two ways: a first predicted speed, which is the boundary speed between the series gear and the power-split gear; and a second predicted speed, which is the boundary speed between the power-split gear and the direct-drive gear. The shift boundary prediction model is trained on the network based on historical samples, including historical environmental data, historical road condition data, historical vehicle operating status data, and corresponding historical actual shift boundary speeds. The first and second predicted speeds are sent to the vehicle-side controller, enabling the controller to perform shift control on the hybrid transmission based on the first and / or second predicted speeds at a second moment. Therefore, this embodiment integrates environmental data, road condition data, and vehicle operating status data of the target vehicle, and predicts the shift boundaries of the hybrid transmission based on the shift boundary prediction model. This makes the shift control of the transmission more consistent with the actual operating conditions of the target vehicle, thereby improving the user experience.

[0084] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0085] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0086] Figure 1 A flowchart of a hybrid transmission shift control method according to an embodiment of this application is shown;

[0087] Figure 2 The network architecture diagram of the network to be trained according to an embodiment of this application is shown;

[0088] Figure 3 A schematic diagram of the hidden layer mechanism of the network to be trained is shown;

[0089] Figure 4 A structural block diagram of a hybrid transmission shift control device according to an embodiment of this application is shown;

[0090] Figure 5 A flowchart of a hybrid transmission shift control method according to an embodiment of this application is shown;

[0091] Figure 6 A structural block diagram of a hybrid transmission shift control device according to an embodiment of this application is shown;

[0092] Figure 7 A schematic diagram of the structure of a computer system suitable for implementing embodiments of the present application is shown. Detailed Implementation

[0093] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0094] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0095] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different models and / or processor devices and / or microcontroller devices.

[0096] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0097] It should also be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such uses of these terms can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described.

[0098] Hybrid vehicles typically consist of a drive motor, a generator, and an engine. These three power sources can be combined according to different operating conditions, outputting torque at the wheels to drive the vehicle. The power source combination methods include pure electric mode (EV (Electric Vehicle) mode, ECVT (Electric Continuously Variable Transmission, which uses planetary gear sets to distribute engine power), and direct drive mode. Specifically, when the battery's state of charge is high or the vehicle's torque demand is low, in pure electric mode, the battery provides electricity to the drive motor, and the wheel torque is provided by the drive motor. In this mode, the generator stops operating and does not participate in driving. In direct drive mode, the engine and drive motor together generate wheel torque to drive the vehicle, or the engine alone generates wheel torque. For scenarios with multiple direct-drive gears, an ECVT mode is introduced to achieve speed transitions between different direct-drive gears. After the engine starts, the power of the engine is split through the planetary gear set. A portion of the engine torque is used to maintain the torque balance of the planetary carrier. The speed ratios of the motor, engine, and ring gear need to be maintained, and the lever torque balance is maintained through torque closed-loop control. The other part of the engine output is sent to the wheel ends to drive the vehicle, thus achieving power splitting.

[0099] To enable hybrid vehicles to operate in the different modes described above, the hybrid transmission of a hybrid vehicle can provide multiple gears, each matching a different power source combination. For example, the hybrid transmission in this embodiment includes multiple gears, specifically, the positions corresponding to each gear from smallest to largest are defined as positions 2 to 10. Positions 2, 4, 8, and 10 are direct-drive gears; positions 3, 5, 7, and 9 are ECVT gears (power split gears); and position 6 is an EV gear (pure electric gear). Positions 2, 4, 8, and 10 correspond to the respective direct-drive gears, defined as gear 1, gear 2, gear 3, and gear 4, where the wheels are driven jointly by the engine and the drive motor, or the engine drives the wheels independently. At workstations 3, 5, 7, and 9, after the engine starts, a portion of the engine's torque is used to maintain the torque balance of the planetary carrier. The generator speed, engine speed, and gear ring speed need to maintain a fixed speed ratio relationship. Through torque closed-loop control, the lever torque balance can be maintained, achieving smooth speed adjustment transition of gears. Another portion of the engine's torque is output to the wheel ends to drive the vehicle, thereby achieving power splitting.

[0100] Having introduced the operating modes of hybrid vehicles and the gear settings of hybrid transmissions, the shift transmission control method of this application embodiment will now be described.

[0101] Figure 1 A flowchart of a hybrid transmission shift control method according to an embodiment of this application is shown.

[0102] The first aspect of this application provides a hybrid transmission shift control method, wherein the hybrid transmission includes a series gear, a power-split gear, and a direct-drive gear. The method can be executed on a cloud server, and the method includes, but is not limited to, steps S101-S103:

[0103] Step S101. Obtain the shift reference data of the target vehicle at the first moment. The shift reference data includes environmental data, road condition data and vehicle operating status data. The target vehicle includes a vehicle-side controller.

[0104] In some embodiments, at least one of the following is satisfied: the environmental data includes one or more of weather type data, altitude data, and slope data; the road condition data includes one or more of congestion data and traffic light data; and the vehicle operating status data includes one or more of power demand data, vehicle speed data, and battery charge data (SOC, State of Health).

[0105] For example, weather type data can be sunny, cloudy, overcast, foggy, hazy, rainy, snowy, heavy rain, heavy snow, etc.

[0106] Among them, the congestion status data can be characterized according to the average vehicle speed of the surrounding vehicles of the target vehicle; the traffic light data can include the distance data between the vehicle and the traffic light intersection, the traffic light status data, the remaining time data of the traffic light, etc.

[0107] In some embodiments, the obtaining of the shift reference data of the target vehicle at the first moment includes:

[0108] Obtaining the average environmental data, average road condition data, and average vehicle operation state data of the target vehicle within the first period, where the first period includes the first moment.

[0109] It can be understood that the first period can be a previous period ending at the first moment. Using the data within the first period as a micro - travel segment can avoid the inaccuracy of data such as the vehicle speed or SOC at a single point (the first moment).

[0110] It can be understood that the vehicle - end controller can be a vehicle control unit (VCU).

[0111] In some embodiments, after obtaining the shift reference data of the target vehicle at the first moment, the method further includes: Step S1011. Obtaining a preset quantization rule. The quantization rule divides multiple data intervals according to the data range of each type of data in the shift reference data, and each data interval corresponds to a quantization value.

[0112] For example: Table 1 shows the quantization rule of weather type data. The cloud server can obtain the weather type from a third - party platform, such as an environmental science data platform, and correspond to different quantization values P. Each quantization value is used to characterize the influence degree of this type of weather on vehicle driving, where P1 < P2 < P3 < P4 < P5 < P6.

[0113] Table 1

[0114] Weather type sunny Cloudy / Overcast Fog / Haze Rain / Snow Heavy rain / blizzard Quantitative indicators P1 P2 P3 P4 P5

[0115] For example: Table 2 shows the quantization rule of congestion status data. The cloud server can obtain the average vehicle speed Vsurround of the surrounding vehicles of the target vehicle based on the satellite map. Different average vehicle speeds correspond to different quantization values Q. Thus, based on the quantization value, the congestion situation of the current road where the target vehicle is located and the influence degree on vehicle driving can be judged, where Q1 < Q2 < Q3 < Q4, and the division boundaries V1, V2, V3 can be calibrated.

[0116] Table 2

[0117]

[0118] For example, Table 3 shows the quantification rules for traffic light data. The cloud server can obtain the distance X between the vehicle and the traffic light intersection, the status of the traffic light, and the remaining time t of the traffic light based on satellite maps, and comprehensively determine whether the vehicle can successfully pass through the current intersection. In the quantification index Ilight (calibrable), 0 indicates that the vehicle can successfully pass through the current intersection, and 1 indicates that it needs to wait for the traffic light to change. The boundaries X1, t1, and t2 are calibrable.

[0119] Table 3

[0120]

[0121] It is understandable that the process of quantifying data is also a process of data preprocessing. After the data is preprocessed, it is stored in a cloud server to facilitate parameter training and data retrieval for the multi-mode gear shifting boundary prediction model.

[0122] Step S1012. For each type of data, including the environmental data, the road condition data, and the vehicle operating status data, match the corresponding target quantization value for that type of data based on the quantization rules.

[0123] Step S102. Input the environmental data, road condition data, and vehicle operating status data into the shift boundary prediction model to output the shift boundary prediction speed of the target vehicle at the second time point, wherein the second time point is later than the first time point, the shift boundary prediction speed includes a first prediction speed and a second prediction speed, the first prediction speed is the boundary speed value between the series gear and the power split gear, the second prediction speed is the boundary speed value between the power split gear and the direct drive gear, and the shift boundary prediction model is obtained by training the network to be trained based on historical samples, the historical samples include historical environmental data, historical road condition data, historical vehicle operating status data, and corresponding historical actual shift boundary speeds;

[0124] Figure 2 A network architecture diagram of the network to be trained according to an embodiment of this application is shown. Figure 3 A schematic diagram of the hidden layer mechanism of the network to be trained is shown.

[0125] like Figure 2 As shown, the network to be trained includes a gated recurrent unit (GRU) network, which comprises an input layer, a hidden layer, and an output layer. The input layer receives the feature data input to the neural network and passes it to the hidden layer.

[0126] The input layer receives the feature data input to the neural network and passes it to the hidden layers. It's important to note that the data needs to be normalized before entering the input layer to eliminate the impact of different units of measurement on the processing speed and performance of the neural network.

[0127]

[0128] Where x represents the feature data input to the neural network (weather type data Iweather, altitude data HASL, slope data Hstope, congestion data ITPI, traffic light data Ilight, vehicle speed data Vmean, and battery charge data SOCmean), xmax is the maximum value in the original data sequence, xmin is the minimum value in the original data sequence, and xnor is the normalized data, i.e., the input parameters of the input layer.

[0129] like Figure 3 As shown, the hidden layer neurons of the GRU neural network are gated recurrent structures, introducing a gating mechanism to control the way information is updated. Its gating structure includes update gates and reset gates, selectively memorizing key information from earlier parts of the sequence, thus improving the efficiency of big data processing.

[0130] The update gate zt∈[0,1] controls the balance between input and forgetting:

[0131]

[0132] Where W, U, and b represent the training coefficients of the neurons. Let zt represent the input of the hidden layer neuron at time t, ht-1 represent the state of the hidden layer neuron at time t-1, and σ represent the sigmoid function. When zt = 0, the relationship between the current hidden layer neuron state ht and the previous state ht-1 is a non-linear function; when zt = 1, the relationship between ht and ht-1 is a linear function. In a gated recurrent structure, the hidden layer candidate states... Defined as:

[0133]

[0134] Here, ⊙ represents the XOR operation, and the reset gate rt∈[0,1] controls the candidate state. Does it depend on the state ht-1 from the previous time step?

[0135] When rt = 0 Only depends on It is independent of ht-1; when rt = 1, depending on And HT-1.

[0136] In summary, the state update method for the gated loop structure is as follows:

[0137]

[0138] Here, ht represents not only the state of the hidden layer neurons at time t, but also the output signal of the hidden layer neurons. The output layer receives the output signal of the hidden layer and finally outputs the prediction result of the GRU neural network, including the first training predicted vehicle speed Vboundary① and the second training predicted vehicle speed Vboundary②.

[0139] In some embodiments, the hidden layer includes: a first sub-network and a second sub-network, and the training process of the shift boundary prediction model includes:

[0140] Step S1021. Input the historical environmental data, historical road condition data, historical vehicle operating status data, and historical actual shift boundary vehicle speed into the input layer so that the input layer outputs the first feature;

[0141] Step S1022. Input the first feature into the first sub-network layer to output a first hidden feature of a preset dimension; Step S1023. Input the first hidden feature into the second sub-network layer to enable the second sub-network layer to combine contextual information, dynamically allocate weights at different time steps based on a multi-head attention mechanism, and output a second hidden feature.

[0142] Understandably, the first sub-network can be used to process the first feature and output the first hidden feature in 256 dimensions. The second sub-network can receive the first hidden feature and integrate static context information (such as weather type quantification value and congestion status quantification value). Through a multi-head attention mechanism, the weights of different time steps are dynamically allocated, focusing on key event windows such as sudden slope changes and rapid acceleration.

[0143] Step S1024. Input the second hidden feature into the output layer to output the first trained predicted vehicle speed and the second trained predicted vehicle speed.

[0144] In some embodiments, the output layer can adopt a multi-branch structure. The main branch outputs the predicted values ​​of VBoundary① and VBoundary② through a fully connected layer; the auxiliary branch introduces a self-supervised learning task to predict the demand power change trend over a future period, and promotes the GRU to learn a more generalized temporal representation through a multi-task loss function. To enhance the interpretability of the model, an interpretability module is added after the last GRU unit. SHAP (SHapley Additive explanations) is used to analyze the degree of influence of each feature on the switching boundary. For example, it can quantify the marginal effect of every 100-meter increase in altitude on the ECVT-direct drive switching speed.

[0145] In some embodiments, the training strategy for the network to be trained combines phased curriculum learning with a physical constraint loss function.

[0146] For example, in the initial stage, only stable cruise data (such as highway segments) is used to train the basic GRU model. Subsequently, complex conditions (such as urban congestion combined with steep slopes) are gradually introduced. The model's convergence stability is improved by dynamically adjusting the learning rate (cosine annealing scheduler) and batch sample difficulty (ranked based on power demand volatility). The loss function is designed as a composite of weighted mean square error (MSE) and physical rule penalty term: the MSE term calculates the error between the predicted boundary and the true label; the physical rule term forces a constraint that VBoundary② is greater than VBoundary①, and the difference between the two conforms to the mechanical speed ratio range of the transmission (such as ΔV≥15km / h). The constraint is transformed into a differentiable optimization objective using the Lagrange multiplier method. To address the high cost of real vehicle data acquisition, a transfer learning strategy is adopted: the GRU is first pre-trained on virtual data generated by a high-fidelity simulation platform, and then the feature extractor is fine-tuned using a small amount of labeled data from actual vehicles through domain adaptation technology, significantly reducing the dependence on real labeled data. After training, Bayesian optimization is used to automatically search for the optimal sequence length and dropout rate, achieving a balance between inference speed and prediction accuracy.

[0147] It is understood that, with the use of the vehicle, the shift boundary prediction model of this embodiment can be in a continuous self-learning process, thereby continuously optimizing the model parameters and improving the accuracy of predicting the shift boundaries of the hybrid transmission. Step S103. Send the first predicted vehicle speed and the second predicted vehicle speed to the vehicle-side controller, so that the vehicle-side controller performs shift control on the hybrid transmission at the second time based on the first predicted vehicle speed and / or the second predicted vehicle speed.

[0148] It is understandable that the second moment is later than the first moment, but the second moment is relatively close to the first moment. Therefore, the environmental conditions of the target vehicle are basically unchanged. Thus, the environmental conditions of the target vehicle at the first moment can be used as the model input to predict the shift boundaries of the hybrid transmission, which is more in line with the actual operating conditions of the target vehicle and improves the user experience. For ease of understanding, the shift control process of the hybrid transmission in this embodiment is summarized in Table 4 below.

[0149] Table 4

[0150]

[0151] Vreal represents the actual vehicle speed.

[0152] In some embodiments, the method further includes:

[0153] Each of the shift reference data and the first predicted vehicle speed and the second predicted vehicle speed corresponding to each shift reference data are sent to the vehicle-side controller, so that the vehicle-side controller stores the first predicted vehicle speed and the second predicted vehicle speed corresponding to each shift reference data.

[0154] In other words, for each multi-mode gear shift, the cloud server actively memorizes different environmental conditions and driving conditions, and dynamically stores the offline shift boundary values ​​within the range of different environmental conditions and driving conditions into the vehicle controller. As a result, the vehicle controller can still use the corresponding shift boundary values ​​according to the different driving conditions of the vehicle even when offline, further improving the user experience.

[0155] Figure 4 A structural block diagram of a hybrid transmission shift control device according to an embodiment of this application is shown.

[0156] A second aspect of this application provides a hybrid transmission shift control device 200, the hybrid transmission including a series gear, a power split gear, and a direct drive gear, the device 200 including:

[0157] The first acquisition unit 201 is used to acquire the shift reference data of the target vehicle at a first moment. The shift reference data includes environmental data, road condition data and vehicle operating status data. The target vehicle includes a vehicle-side controller.

[0158] Input unit 202 is used to input the environmental data, the road condition data, and the vehicle operating status data into the shift boundary prediction model to output the shift boundary predicted speed of the target vehicle at a second time, wherein the second time is later than the first time, the shift boundary predicted speed includes a first predicted speed and a second predicted speed, the first predicted speed is the boundary speed value between the serial gear and the power split gear, and the second predicted speed is the boundary speed value between the power split gear and the direct drive gear, the shift boundary prediction model is obtained by training the network to be trained based on historical samples, the historical samples include historical environmental data, historical road condition data, historical vehicle operating status data, and corresponding historical actual shift boundary speeds;

[0159] The first transmitting unit 203 is used to transmit the first predicted vehicle speed and the second predicted vehicle speed to the vehicle-end controller, so that the vehicle-end controller can perform shift control on the hybrid transmission at the second time according to the first predicted vehicle speed and / or the second predicted vehicle speed.

[0160] In some embodiments, when acquiring the shift reference data of the target vehicle at a first moment, the first acquisition unit is configured to: acquire the average environmental data, average road condition data, and average vehicle operating status data of the target vehicle within a first time period, wherein the first time period includes the first moment.

[0161] In some embodiments, the apparatus further includes:

[0162] The second acquisition unit is used to acquire a preset quantization rule. The quantization rule is divided into multiple data intervals according to the data range of each type of data in the shift reference data, and each data interval corresponds to a quantization value.

[0163] The matching unit is used to match a corresponding target quantization value for each type of data, including the environmental data, the road condition data, and the vehicle operating status data, based on the quantization rules.

[0164] In some embodiments, the network to be trained includes a gated recurrent unit network (GRU), which includes an input layer, a hidden layer, and an output layer. The hidden layer includes a first sub-network and a second sub-network. The training process of the shift boundary prediction model includes:

[0165] The historical environmental data, historical road condition data, historical vehicle operating status data, and historical actual shift boundary vehicle speed are input into the input layer so that the input layer outputs the first feature.

[0166] The first feature is input into the first sub-network layer to output a first hidden feature of a preset dimension;

[0167] The first hidden feature is input into the second sub-network so that the second sub-network combines contextual information, dynamically allocates weights at different time steps based on the multi-head attention mechanism, and outputs the second hidden feature.

[0168] The second hidden feature is input into the output layer to output a first trained predicted vehicle speed and a second trained predicted vehicle speed. In some embodiments, at least one of the following is satisfied:

[0169] The environmental data includes one or more of the following: weather type data, altitude data, and slope data.

[0170] The traffic data includes one or more of the following: congestion data and traffic light data.

[0171] The vehicle operating status data includes one or more of the following: power demand data, vehicle speed data, and battery charge data. In some embodiments, the device further includes:

[0172] The second transmitting unit is used to transmit each of the shift reference data and the first predicted vehicle speed and the second predicted vehicle speed corresponding to each of the shift reference data to the vehicle-end controller, so that the vehicle-end controller stores the first predicted vehicle speed and the second predicted vehicle speed corresponding to each of the shift reference data.

[0173] Figure 5 A flowchart of a hybrid transmission shift control method according to an embodiment of this application is shown.

[0174] A third aspect of this application provides a hybrid transmission shift control method, wherein the hybrid transmission includes a series gear, a power-split gear, and a direct-drive gear, and the method can be executed on a vehicle-side controller, including but not limited to steps S301-S302:

[0175] Step S301. Upload the vehicle operating status data of the target vehicle at the first moment to the cloud server. The cloud server also obtains the environmental data and road condition data of the target vehicle at the first moment. The environmental data, road condition data, and vehicle operating status data constitute shift reference data. The cloud server inputs the environmental data, road condition data, and vehicle operating status data into the shift boundary prediction model to output the shift boundary predicted speed of the target vehicle at the second moment. The second moment is later than the first moment. The shift boundary predicted speed includes a first predicted speed and a second predicted speed. The first predicted speed is the boundary speed value between the serial gear and the power split gear. The second predicted speed is the boundary speed value between the power split gear and the direct drive gear. The shift boundary prediction model is obtained by training the network to be trained based on historical samples. The historical samples include historical environmental data, historical road condition data, historical vehicle operating status data, and historical actual shift boundary speeds.

[0176] Step S302. Receive the first predicted vehicle speed and the second predicted vehicle speed sent by the cloud server, and at the second moment, perform shift control on the hybrid transmission according to the first predicted vehicle speed and / or the second predicted vehicle speed.

[0177] In some embodiments, the step of shifting the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed includes:

[0178] Step S302A1. Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0179] Step S302A2. When the first actual vehicle speed is less than the first predicted vehicle speed, if the hybrid transmission is in the power split gear, then control the hybrid transmission to switch to the series gear; if the hybrid transmission is in the direct drive gear, then control the hybrid transmission to switch to the power split gear.

[0180] In some embodiments, after controlling the hybrid transmission to switch to the power split gear, the method further includes:

[0181] Step S302A3. Obtain the second actual vehicle speed of the target vehicle at a third moment, wherein the third moment is later than the second moment;

[0182] Step S302A4. When the second actual vehicle speed is less than the first predicted vehicle speed, control the hybrid transmission to switch from the power split gear to the series gear.

[0183] Understandably, for power-split vehicles, the EV mode and direct drive mode cannot be directly switched. Therefore, when the vehicle is currently in direct drive mode and the second actual vehicle speed is less than the first predicted vehicle speed, the current mode can be switched to ECVT mode first, and then switched to EV mode at the next moment.

[0184] In some embodiments, the step of shifting the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed includes:

[0185] Step S302B1. Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0186] Step S302B2. When the first actual vehicle speed is greater than or equal to the first predicted vehicle speed and less than the second predicted vehicle speed, if the hybrid transmission is in the series gear position, then control the hybrid transmission to switch to the power split gear position; if the hybrid transmission is in the direct drive gear position, then control the hybrid transmission to switch to the power split gear position.

[0187] In some embodiments, the step of shifting the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed includes:

[0188] Step S302C1. Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0189] Step S302C2. When the target vehicle speed is greater than or equal to the second predicted vehicle speed, if the hybrid transmission is in the series gear position, control the hybrid transmission to switch to the power split gear position; if the hybrid transmission is in the power split gear position, control the hybrid transmission to switch to the direct drive gear position.

[0190] In some embodiments, after controlling the hybrid transmission to switch to the power split gear, the method further includes:

[0191] Step S302C3. Obtain the second actual vehicle speed of the target vehicle at a third moment, wherein the third moment is later than the second moment;

[0192] Step S302C4. When the second actual vehicle speed is greater than or equal to the second predicted vehicle speed, control the hybrid transmission to switch from the power split gear to the direct drive gear.

[0193] Understandably, for power-split models, the EV mode and direct drive mode cannot be switched directly.

[0194] When the vehicle is currently in EV mode and the second actual vehicle speed is greater than or equal to the second predicted vehicle speed, the current gear can be switched to ECVT mode first, and then switched to direct drive mode at the next moment.

[0195] In some embodiments, the method further includes:

[0196] In the event of a communication interruption between the target vehicle and the cloud server, the target shift reference data with the highest similarity to the current shift reference data of the target vehicle is obtained from a plurality of pre-stored shift reference data, along with the first target predicted vehicle speed and the second target predicted vehicle speed corresponding to the target shift reference data.

[0197] The hybrid transmission performs shift control based on the predicted vehicle speed of the first target and / or the predicted vehicle speed of the second target. It is understood that in the event of a communication interruption between the target vehicle and the cloud server, when the vehicle is offline (e.g., in tunnels, mountainous areas, or other road conditions), the transmission signal to the cloud server may be weak or fail. In this case, the predicted shift speed can be queried based on the environmental conditions and driving conditions at the vehicle's closest online moment, and the shift demand can be determined based on the current vehicle speed collected in real-time by the vehicle controller. This effectively avoids the impact of communication failures on multi-mode shift control, improving vehicle reliability and stability.

[0198] Figure 6 A structural block diagram of a hybrid transmission shift control device according to an embodiment of this application is shown.

[0199] A fourth aspect of this application provides a hybrid transmission shift control device 400, the hybrid transmission including a series gear, a power split gear, and a direct drive gear, the device 400 including:

[0200] Upload unit 401 is used to upload the vehicle operating status data of the target vehicle at a first moment to a cloud server. The cloud server also obtains the environmental data and road condition data of the target vehicle at the first moment. The environmental data, road condition data, and vehicle operating status data constitute shift reference data. The cloud server inputs the environmental data, road condition data, and vehicle operating status data into a shift boundary prediction model to output the shift boundary predicted speed of the target vehicle at a second moment, where the second moment is later than the first moment. The shift boundary predicted speed includes a first predicted speed and a second predicted speed. The first predicted speed is the boundary speed value between the serial gear and the power split gear, and the second predicted speed is the boundary speed value between the power split gear and the direct drive gear. The shift boundary prediction model is obtained by training the network to be trained based on historical samples. The historical samples include historical environmental data, historical road condition data, historical vehicle operating status data, and historical actual shift boundary speeds.

[0201] The first control unit 402 is used to receive the first predicted vehicle speed and the second predicted vehicle speed sent by the cloud server, and at the second moment, to perform shift control on the hybrid transmission according to the first predicted vehicle speed and / or the second predicted vehicle speed.

[0202] In some embodiments, when shifting the hybrid transmission according to the first predicted vehicle speed and / or the second predicted vehicle speed, the first shift control unit is configured to:

[0203] Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0204] When the first actual vehicle speed is less than the first predicted vehicle speed, if the hybrid transmission is in the power split gear, then the hybrid transmission is controlled to switch to the series gear; if the hybrid transmission is in the direct drive gear, then the hybrid transmission is controlled to switch to the power split gear.

[0205] In some embodiments, the apparatus further includes:

[0206] The third acquisition unit is used to acquire the second actual vehicle speed of the target vehicle at a third moment, wherein the third moment is later than the second moment.

[0207] The second control unit is used to control the hybrid transmission to switch from the power split gear to the series gear when the second actual vehicle speed is less than the first predicted vehicle speed.

[0208] In some embodiments, when shifting the hybrid transmission according to the first predicted vehicle speed and / or the second predicted vehicle speed, the first shift control unit is configured to:

[0209] Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0210] When the first actual vehicle speed is greater than or equal to the first predicted vehicle speed and less than the second predicted vehicle speed, if the hybrid transmission is in the series gear position, the hybrid transmission is controlled to switch to the power split gear position; if the hybrid transmission is in the direct drive gear position, the hybrid transmission is controlled to switch to the power split gear position.

[0211] In some embodiments, when shifting the hybrid transmission according to the first predicted vehicle speed and / or the second predicted vehicle speed, the first shift control unit is configured to:

[0212] Obtain the first actual vehicle speed of the target vehicle at the second moment;

[0213] When the target vehicle speed is greater than or equal to the second predicted vehicle speed, if the hybrid transmission is in the series gear position, the hybrid transmission is controlled to switch to the power split gear position; if the hybrid transmission is in the power split gear position, the hybrid transmission is controlled to switch to the direct drive gear position.

[0214] In some embodiments, the apparatus further includes:

[0215] The fourth acquisition unit is used to acquire the second actual vehicle speed of the target vehicle at a third moment, wherein the third moment is later than the second moment;

[0216] The third control unit is used to control the hybrid transmission to switch from the power split gear to the direct drive gear when the second actual vehicle speed is greater than or equal to the second predicted vehicle speed.

[0217] In some embodiments, the apparatus further includes:

[0218] The fifth acquisition unit is used to, in the event of a communication interruption between the target vehicle and the cloud server, acquire, from a plurality of pre-stored shift reference data, the target shift reference data that has the highest similarity to the current shift reference data of the target vehicle, as well as the first target predicted vehicle speed and the second target predicted vehicle speed corresponding to the target shift reference data.

[0219] The fourth control unit is used to perform shift control on the hybrid transmission based on the first target predicted vehicle speed and / or the second target predicted vehicle speed.

[0220] A fifth aspect of this application provides a vehicle including one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, the at least one piece of program code being loaded and executed by the one or more processors to perform the operations performed as described in any of the methods in the third aspect.

[0221] like Figure 7 As shown, vehicle 400 is represented in the form of a general-purpose computing device. The components of vehicle 400 may include, but are not limited to: at least one processing unit 410, at least one storage unit 420, and a bus 430 connecting different system components (including storage unit 420 and processing unit 410).

[0222] The storage unit stores program code, which can be executed by the processing unit 410, causing the processing unit 410 to perform the steps described in the "Embodiment Methods" section of this specification according to various exemplary embodiments of this application. The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 421 and / or a cache 422, and may further include a read-only memory (ROM) 423.

[0223] Storage unit 420 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0224] Bus 430 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0225] Vehicle 400 can also communicate with one or more external devices 500 (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable users to interact with vehicle 400, and / or any device that enables vehicle 400 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed through I / O (input / output) interface 450, which can also be connected to display unit 440 to display the communication content. Furthermore, vehicle 400 can communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 460. As shown, network adapter 460 communicates with other modules of vehicle 400 via bus 430. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with vehicle 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0226] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0227] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0228] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0229] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk. A sixth aspect of this application provides a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to perform the operations performed by any of the methods described in the first aspect or any of the methods described in the second aspect.

[0230] Computer-readable storage media may be portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the computer-readable storage medium of this application is not limited thereto. In this application, the readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0231] A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0232] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0233] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for shifting control of a hybrid transmission, characterized in that, The hybrid transmission includes a series gear, a power-split gear, and a direct-drive gear; the method includes: The shift reference data of the target vehicle at the first moment is obtained. The shift reference data includes environmental data, road condition data and vehicle operating status data. The target vehicle includes a vehicle-side controller. The environmental data, road condition data, and vehicle operating status data are input into the shift boundary prediction model to output the shift boundary predicted speed of the target vehicle at a second time point, wherein the second time point is later than the first time point. The shift boundary predicted speed includes a first predicted speed and a second predicted speed. The first predicted speed is the boundary speed value between the series gear and the power split gear, and the second predicted speed is the boundary speed value between the power split gear and the direct drive gear. The shift boundary prediction model is obtained by training the network to be trained based on historical samples. The historical samples include historical environmental data, historical road condition data, historical vehicle operating status data, and corresponding historical actual shift boundary speeds. The first predicted vehicle speed and the second predicted vehicle speed are sent to the vehicle-side controller so that the vehicle-side controller can perform shift control on the hybrid transmission at the second time based on the first predicted vehicle speed and / or the second predicted vehicle speed.

2. The method according to claim 1, characterized in that, The acquisition of the target vehicle's shift reference data at the first moment includes: The average environmental data, average road condition data, and average vehicle operating status data of the target vehicle are obtained during a first time period, which includes the first moment.

3. The method according to claim 1, characterized in that, After acquiring the shift reference data of the target vehicle at the first moment, the method further includes: Obtain a preset quantization rule, wherein the quantization rule divides the data range of each type of data in the shift reference data into multiple data intervals, and each data interval corresponds to a quantization value; For each type of data—environmental data, road condition data, and vehicle operating status data—a corresponding target quantization value is matched based on the quantization rules.

4. The method according to any one of claims 1-3, characterized in that, The network to be trained includes a gated recurrent unit network, which includes an input layer, a hidden layer, and an output layer. The hidden layer includes a first sub-network and a second sub-network. The training process of the shift boundary prediction model includes inputting the historical environment data, historical road condition data, historical vehicle operating status data, and historical actual shift boundary vehicle speed into the input layer so that the input layer outputs a first feature. The first feature is input into the first sub-network layer to output a first hidden feature of a preset dimension; the first hidden feature is input into the second sub-network layer to enable the second sub-network layer to combine contextual information, dynamically allocate weights at different time steps based on a multi-head attention mechanism, and output a second hidden feature; the second hidden feature is input into the output layer to output a first trained predicted vehicle speed and a second trained predicted vehicle speed.

5. The method according to any one of claims 1-3, characterized in that, At least one of the following must be met: The environmental data includes one or more of the following: weather type data, altitude data, and slope data. The traffic data includes one or more of the following: congestion data and traffic light data. The vehicle operating status data includes one or more of the following: power demand data, vehicle speed data, and battery charge data.

6. The method according to claim 1, characterized in that, The method further includes: Each of the shift reference data and the first predicted vehicle speed and the second predicted vehicle speed corresponding to each shift reference data are sent to the vehicle-side controller, so that the vehicle-side controller stores the first predicted vehicle speed and the second predicted vehicle speed corresponding to each shift reference data.

7. A hybrid transmission shift control method, characterized in that, The hybrid transmission includes a series gear, a power-split gear, and a direct-drive gear; the method includes: The target vehicle's operating status data at a first moment is uploaded to a cloud server. The cloud server also acquires the target vehicle's environmental and road condition data at the first moment. The environmental data, road condition data, and vehicle operating status data constitute shift reference data. The cloud server inputs the environmental data, road condition data, and vehicle operating status data into a shift boundary prediction model to output the target vehicle's shift boundary predicted speed at a second moment, where the second moment is later than the first moment. The shift boundary predicted speed includes a first predicted speed and a second predicted speed. The first predicted speed is the boundary speed value between the serial gear and the power-split gear, and the second predicted speed is the boundary speed value between the power-split gear and the direct-drive gear. The shift boundary prediction model is obtained by training the network based on historical samples, including historical environmental data, historical road condition data, historical vehicle operating status data, and historical actual shift boundary speeds. The system receives the first predicted vehicle speed and the second predicted vehicle speed sent by the cloud server, and at the second moment, performs shift control on the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed.

8. The method according to claim 7, characterized in that, The step of controlling the shifting of the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed includes: Obtain the first actual vehicle speed of the target vehicle at the second moment; When the first actual vehicle speed is less than the first predicted vehicle speed, if the hybrid transmission is in the power split gear, then the hybrid transmission is controlled to switch to the series gear; if the hybrid transmission is in the direct drive gear, then the hybrid transmission is controlled to switch to the power split gear.

9. The method according to claim 8, characterized in that, After controlling the hybrid transmission to switch to the power split gear, the method further includes: The second actual vehicle speed of the target vehicle at a third moment is obtained, the third moment being later than the second moment; if the second actual vehicle speed is less than the first predicted vehicle speed, the hybrid transmission is controlled to switch from the power split gear to the series gear.

10. The method according to claim 7, characterized in that, The step of controlling the shifting of the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed includes: Obtain the first actual vehicle speed of the target vehicle at the second moment; When the first actual vehicle speed is greater than or equal to the first predicted vehicle speed and less than the second predicted vehicle speed, if the hybrid transmission is in the series gear position, the hybrid transmission is controlled to switch to the power split gear position; if the hybrid transmission is in the direct drive gear position, the hybrid transmission is controlled to switch to the power split gear position.

11. The method according to claim 7, characterized in that, The step of controlling the shifting of the hybrid transmission based on the first predicted vehicle speed and / or the second predicted vehicle speed includes: Obtain the first actual vehicle speed of the target vehicle at the second moment; When the target vehicle speed is greater than or equal to the second predicted vehicle speed, if the hybrid transmission is in the series gear position, the hybrid transmission is controlled to switch to the power split gear position; if the hybrid transmission is in the power split gear position, the hybrid transmission is controlled to switch to the direct drive gear position.

12. The method according to claim 11, characterized in that, After controlling the hybrid transmission to switch to the power split gear, the method further includes: The second actual vehicle speed of the target vehicle at a third moment is obtained, the third moment being later than the second moment; when the second actual vehicle speed is greater than or equal to the second predicted vehicle speed, the hybrid transmission is controlled to switch from the power split gear to the direct drive gear.

13. The method according to any one of claims 7-12, characterized in that, The method further includes: In the event of a communication interruption between the target vehicle and the cloud server, the target shift reference data with the highest similarity to the current shift reference data of the target vehicle is obtained from a plurality of pre-stored shift reference data, along with the first target predicted vehicle speed and the second target predicted vehicle speed corresponding to the target shift reference data. The hybrid transmission is shifted based on the predicted vehicle speed of the first target and / or the predicted vehicle speed of the second target.

14. A vehicle, characterized in that, It includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to perform the operation performed by the method as described in any one of claims 7-13.

Images