Whole-vehicle driving control system of amphibious transport vehicle based on mode recognition

Abstract

The invention relates to the technical field of multifunctional hybrid power transport vehicle driving, and particularly discloses an amphibious transport vehicle whole vehicle driving control system based on mode recognition, and the system comprises a working mode recognition module which is used for predicting future required power by analyzing historical data of a vehicle; in combination with the current required power, the battery charge state and the vehicle mode on-off state, selecting an optimal working mode based on a logic gate threshold value judgment rule; the driving control management module is used for calculating initial required torque according to driver input information and vehicle state information, designing a torque coordination filtering adaptive function, performing torque filtering by adopting an adaptive torque change factor, converting the current required torque into required power through a power torque conversion formula, and assisting in selecting an optimal working mode; and the power is reasonably distributed based on the working mode. The adaptive capacity of the amphibious vehicle in various complex operation scenes of'variable environment-cross medium 'can be effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of multifunctional hybrid power transport vehicle driving, in particular to an amphibious transport vehicle whole vehicle driving control system based on pattern recognition. Background Art

[0002] With the diversification of modern transportation needs, amphibious vehicles have gradually become an important tool for coping with complex terrain transportation tasks, and are widely used in emergency rescue, military deployment, disaster management and engineering operations. At the same time, the increasingly severe global energy shortage and environmental pollution problems have further promoted the innovation of transportation technology. The hybrid system, relying on the complementary advantages of internal combustion engines and electric motors, not only significantly improves energy utilization efficiency, but also greatly extends the vehicle's cruising range. It has become a key technical direction for the development of amphibious heavy-duty transport vehicles.

[0003] As a special-purpose vehicle, amphibious heavy-duty transport vehicles need to perform efficient and stable transportation tasks in complex land and water environments. Therefore, working mode recognition methods for various complex operating scenarios and stable, reliable and adaptable drive control technologies are particularly important. Summary of the invention

[0004] The purpose of the present invention is to provide a whole vehicle drive control system for an amphibious transport vehicle based on pattern recognition to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: Terminology explanation: ISG motor (Integrated Starter Generator): is a motor that integrates starting and generating functions.

[0006] WHVC (World Harmonized Vehicle Cycle): Standardized test conditions for heavy vehicles (such as commercial trucks, buses, etc.).

[0007] RDE condition (Real Driving Emissions): real driving emissions test.

[0008] A whole vehicle drive control system for an amphibious transport vehicle based on pattern recognition, the drive control system comprising: The working mode recognition module predicts the power requirements at N moments in the future by analyzing the collected historical vehicle data, and calculates the average power requirements at these moments. By combining the current power requirements, the battery state of charge and the vehicle mode switch state, the optimal working mode most suitable for the current moment is selected based on the logic gate threshold judgment, wherein the vehicle historical data includes historical vehicle speed, historical power requirements, historical accelerator pedal opening, historical brake pedal switch signal and historical working mode; The drive control management module first calculates the vehicle's initial required torque based on the driver's input information and the vehicle status information; then, it limits the initial required torque through the maximum allowable power, the maximum allowable vehicle speed, and the maximum driving performance of the motor and the injection pump; next, it filters the drive torque to avoid excessive torque fluctuations and ensure the smoothness of the vehicle's driving; finally, it converts the current required torque into required power through the power-torque conversion formula and inputs it into the working mode recognition module to assist in selecting the current optimal working mode, and based on this working mode, reasonably allocates the required power to the engine and power battery.

[0009] As a further technical solution of the present invention, in the working mode recognition module, the present invention adopts a feedforward neural network to predict the power demand at N moments in the future. The parameter update of the feedforward neural network includes two stages: offline optimization and online fine-tuning. First, the parameters of the feedforward neural network are preliminarily learned using standard driving conditions. The network model after learning is installed in the controller. The parameters of the feedforward neural network are updated online by collecting the actual operating data of the amphibious transport vehicle, so that it is more suitable for the actual driving condition requirements of the amphibious transport vehicle. The online fine-tuning loss function is defined as follows: ; ; in, For the The loss value at that moment is for The total loss value at this moment is It is The actual power demand value at a moment, It is The power demand value is predicted at each moment. is the number of data samples, The number of data samples selected to update the threshold is used to prevent the model from changing drastically and destroying the model's predictive ability. , that is, whenever the amphibious transport vehicle collects The parameters of the feedforward neural network are updated once every sample, and the fine-tuned model is used to predict the next The power demand at all times is repeated in this way, and the model is continuously updated and optimized online.

[0010] As a further technical solution of the present invention, in the working mode recognition module, the step of selecting the best working mode most suitable for the current moment based on the logic gate threshold judgment includes: When the vehicle enters the drivable state, first select the three working modes of land, water and beaching according to the mode switch pressed by the driver. There is an interlocking relationship between the three working modes. Once a working mode is entered, it can only be switched to other modes after exiting the mode. If two or more switches are turned on at the same time, the mode selection is carried out in sequence. Only after the first switch is turned off can another working mode be entered. After determining that the vehicle is in a certain working mode, the corresponding working mode selection is carried out; There are six land working modes: hybrid driving mode 1, hybrid driving mode 2, pure electric driving mode, power generation driving mode, energy recovery mode and mechanical braking mode. When the required power is greater than 0, first determine whether the difference between the current required power and the previous required power is greater than the calibration value a. If the difference is greater than a, enter hybrid driving mode 1 to meet the driver's instantaneous high power demand. If the difference is less than a, determine whether the current required power is greater than the predicted average required power. If it is greater than the average required power, enter hybrid driving mode 2 to make the engine work in the high-efficiency area. If it is less than the average required power, determine whether the current battery state of charge is lower than the charging threshold. If it is lower than the charging threshold, enter the power generation driving mode, the engine works in the high-efficiency area, and use the excess power to charge the power battery. If it is higher than the charging threshold, enter the pure electric driving mode to avoid the engine running in the low-efficiency area to reduce fuel consumption. When the required power is less than 0, first determine whether the current battery state of charge is lower than the maximum state of charge threshold. If it is lower, enter the energy recovery mode. If it is higher, enter the conventional mechanical braking mode.

[0011] As a further technical solution of the present invention, the water working modes include four types: hybrid navigation mode 1, hybrid navigation mode 2, pure electric navigation mode, and power generation navigation mode; when the required power is greater than 0, first determine whether the difference between the current power demand and the previous power demand is greater than the calibration value b; if the difference is greater than b, enter hybrid navigation mode 1 to meet the driver's instantaneous high power demand; if the difference is less than b, determine whether the current power demand is greater than the predicted average power demand. If it is greater than the average power demand, enter hybrid navigation mode 2 to make the engine work in a high-efficiency area; if it is less than the average power demand, determine whether the current battery charge state is lower than the charging threshold. If it is lower than the charging threshold, enter the power generation navigation mode, and the engine works in the high-efficiency area, using excess power to charge the power battery; if it is higher than the charging threshold, enter the pure electric navigation mode to avoid the engine running in the low-efficiency area to reduce fuel consumption.

[0012] As a further technical solution of the present invention, the up and down beach ship working modes include three types: hybrid up and down beach mode 1, hybrid up and down beach mode 2, and pure electric up and down beach mode; first, it is determined whether the difference between the power demand at the current moment and the power demand at the previous moment is greater than the calibration quantity c; if the difference is greater than c, the hybrid up and down beach mode 1 is entered to meet the driver's instantaneous high power demand; if the difference is less than c, it is determined whether the current power demand is greater than the predicted average power demand, if it is greater than the average power demand, the hybrid up and down beach mode 2 is entered to make the engine work in the high efficiency area; if it is less than the average power demand, the pure electric up and down beach mode is entered to avoid the engine running in the low efficiency area to reduce fuel consumption.

[0013] As a further technical solution of the present invention, a torque coordination filter adaptive function is designed in the drive control management module, and an adaptive torque change factor is used for torque coordination filtering. Under the premise of ensuring acceleration performance, drastic changes in torque are avoided to ensure the smoothness of vehicle driving; the torque change factor will be adaptively adjusted in real time according to the actual torque value and the required torque value, and the strategy is as follows: First, an initial value of the initial torque change factor is determined according to the torque interval where the current actual torque value is located. The torque interval can be divided using a conventional S-shaped distribution, and each interval corresponds to an initial value of the initial torque change factor. Secondly, according to the difference between the actual torque value and the target torque value, a torque change factor coefficient is determined through an adaptive function. Finally, the initial value of the torque change factor is multiplied by the torque change factor coefficient to obtain the final torque change factor, and the torque change factor is used to adjust the actual torque value. The filtered required torque can be converted into the current required power by the following formula: ; in, is the current required power, is the current required torque, The speed of the drive motor, wheel hub motor and jet pump, The working efficiency of the motor; The calculated current required power is input into the working mode recognition module to assist in identifying the current optimal working mode, and according to the power distribution plan of the working mode, the required power is reasonably distributed to the engine and the power battery.

[0014] Compared with the prior art, the present invention has the following beneficial effects: (1) A working mode recognition method suitable for amphibious heavy-duty transport vehicles is proposed, which improves the working mode recognition accuracy of the vehicle in various complex operating scenarios on land and water.

[0015] (2) A drive control management method suitable for amphibious heavy-duty transport vehicles is proposed. Based on the results of pattern recognition, the power distribution scheme of the vehicle in different operating scenarios can be adjusted in real time, thereby improving the vehicle's adaptability in various complex operating scenarios on land and water.

[0016] (3) A torque coordination filter adaptive function is designed, and an adaptive torque change factor is used for torque coordination filtering. Under the premise of ensuring acceleration performance, drastic changes in torque are avoided, thus ensuring the smoothness of vehicle driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0018] Figure 1 This is the structural diagram of the power system of an amphibious heavy-duty transport vehicle.

[0019] Figure 2 This is a diagram of the driving control system of an amphibious heavy-duty transport vehicle based on pattern recognition.

[0020] Figure 3 Identify the flow chart for onshore working mode.

[0021] Figure 4 Identify the flow chart for water working mode.

[0022] Figure 5 This is the flow chart for identifying the working mode of the ship going up and down the beach. DETAILED DESCRIPTION

[0023] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0024] like Figure 1 As shown, the power system of the amphibious heavy-duty transport vehicle adopts an extended-range hybrid power system, which is mainly composed of components such as an engine, a power battery, an ISG motor, a drive motor, a hub motor, a jet pump propeller, a clutch, a transfer case and a transmission. The amphibious heavy-duty transport vehicle drive control technology based on pattern recognition disclosed in the present invention is intended to select the best working mode according to the different power requirements of the vehicle in various complex operating scenarios on land and water, and reasonably allocate the vehicle power requirements to optimize the power output between the engine and the power battery.

[0025] See also Figure 2 The embodiment of the present invention provides a whole vehicle driving control system of an amphibious transport vehicle based on pattern recognition, and the driving control system includes: The working mode recognition module predicts the power requirements at N moments in the future by analyzing the collected historical vehicle data, and calculates the average power requirements at these moments. By combining the current power requirements, the battery state of charge and the vehicle mode switch state, the optimal working mode most suitable for the current moment is selected based on the logic gate threshold judgment, wherein the vehicle historical data includes historical vehicle speed, historical power requirements, historical accelerator pedal opening, historical brake pedal switch signal and historical working mode; In the working mode recognition module, the present invention adopts a feedforward neural network to predict the power demand at N moments in the future, and uses the powerful fitting and feature learning capabilities of the neural network to achieve accurate prediction of the future power demand; the parameter update of the feedforward neural network includes two stages: offline optimization and online fine-tuning. First, the parameters of the feedforward neural network are preliminarily learned using standard driving conditions (such as WHVC, RDE, etc.). The network model after learning is installed in the controller. The parameters of the feedforward neural network are updated online by collecting the actual operating data of the amphibious transport vehicle, so that it is more suitable for the actual driving condition requirements of the amphibious transport vehicle. The actual operating data includes the actual vehicle speed, the actual power output, the actual accelerator pedal opening, the actual brake pedal switch and the actual working mode; The online fine-tuning loss function is defined as follows: ; ; in, For the The loss value at that moment is for The total loss value at this moment is It is The actual power demand value at a moment, It is The power demand value is predicted at each moment. is the number of data samples, In order to update the threshold value to prevent the model from changing dramatically and destroying the model's predictive ability, the loss function is used for back propagation calculation to achieve online fine-tuning and parameter update. In the present invention, the number of selected data samples is , that is, whenever the amphibious transport vehicle collects The parameters of the feedforward neural network are updated once every sample, and the fine-tuned model is used to predict the next The power demand at all times is repeated in this way, and the model is continuously updated and optimized online.

[0026] In the working mode recognition module, based on the logic gate threshold judgment, the steps of selecting the best working mode most suitable for the current moment include: When the vehicle enters the drivable state (Ready), first select the three working modes of land, water and beaching according to the mode switch pressed by the driver. There is an interlocking relationship between the three working modes. Once a working mode is entered, it can only be switched to other modes after exiting the mode. If two or more switches are turned on at the same time, the mode selection is carried out in sequence. Only after the first switch is turned off can another working mode be entered. After determining that the vehicle is in a certain working mode, the corresponding working mode selection is carried out; like Figure 3As shown, there are six land working modes: hybrid driving mode 1 (mainly driven by power battery to meet the vehicle's instantaneous response capability), hybrid driving mode 2 (mainly driven by engine, the engine works in the high-efficiency area), pure electric driving mode (the motor drives alone to reduce engine fuel consumption), power generation driving mode (the engine works in the high-efficiency area, and the excess power is used to charge the power battery), energy recovery mode and mechanical braking mode; when the required power is greater than 0, first determine whether the difference between the required power at the current moment and the required power at the previous moment is greater than the calibration value a; if the difference is greater than a, enter hybrid driving mode 1 to meet the driver's instantaneous high power demand; if the difference is less than a, determine Whether the current power demand is greater than the predicted average power demand. If so, the hybrid driving mode 2 is entered to make the engine work in the high-efficiency area. If less than the average power demand, whether the current battery state of charge is lower than the charging threshold is determined. If so, the power generation driving mode is entered, and the engine works in the high-efficiency area, using excess power to charge the power battery. If higher than the charging threshold, the pure electric driving mode is entered to avoid the engine running in the low-efficiency area to reduce fuel consumption. When the power demand is less than 0, first determine whether the current battery state of charge is lower than the maximum state of charge threshold. If so, the energy recovery mode is entered; if higher, the conventional mechanical braking mode is entered.

[0027] like Figure 4 As shown, there are four water working modes: hybrid navigation mode 1 (mainly driven by power batteries to meet the vehicle's instantaneous response capability), hybrid navigation mode 2 (mainly driven by the engine, the engine works in the high-efficiency area), pure electric navigation mode (motor driven alone to reduce engine fuel consumption), power generation navigation mode (the engine works in the high-efficiency area, and the excess power is used to charge the power battery); when the required power is greater than 0, first determine whether the difference between the current required power and the previous required power is greater than the calibration quantity b; if the difference is greater than b, enter hybrid navigation mode 1 to meet the driver's instantaneous high power demand; if the difference is less than b, determine whether the current required power is greater than the predicted average required power. If it is greater than the average required power, enter hybrid navigation mode 2 to make the engine work in the high-efficiency area; if it is less than the average required power, determine whether the current battery charge state is lower than the charging threshold. If it is lower than the charging threshold, enter the power generation navigation mode, the engine works in the high-efficiency area, and uses the excess power to charge the power battery; if it is higher than the charging threshold, enter the pure electric navigation mode to avoid the engine running in the low-efficiency area to reduce fuel consumption.

[0028] like Figure 5As shown, there are three working modes of the up and down beach ship: hybrid up and down beach mode 1 (mainly driven by power batteries to meet the vehicle's instantaneous response capability), hybrid up and down beach mode 2 (mainly driven by the engine, the engine works in the high-efficiency area), and pure electric up and down beach mode (the motor is driven alone to reduce the engine fuel consumption); first, it is determined whether the difference between the current power demand and the previous power demand is greater than the calibration quantity c; if the difference is greater than c, the hybrid up and down beach mode 1 is entered to meet the driver's instantaneous high power demand; if the difference is less than c, it is determined whether the current power demand is greater than the predicted average power demand. If it is greater than the average power demand, the hybrid up and down beach mode 2 is entered to make the engine work in the high-efficiency area; if it is less than the average power demand, the pure electric up and down beach mode is entered to avoid the engine running in the low-efficiency area to reduce fuel consumption; The drive control management module first calculates the initial required torque of the vehicle based on the driver's input information (such as the accelerator pedal, brake pedal, gear position, etc.) and the vehicle status information (such as vehicle speed, motor speed, injection pump speed, battery charge state, etc.); then, the initial required torque is limited by the maximum allowable power, the maximum allowable vehicle speed, and the maximum driving performance of the motor and injection pump; then, the drive torque is filtered to avoid excessive torque fluctuations and ensure the smoothness of the vehicle's driving; finally, the current required torque is converted into required power through the power-torque conversion formula and input into the working mode recognition module to assist in selecting the current optimal working mode, and based on this working mode, the required power is reasonably allocated to the engine and power battery; In the drive control management module, a torque coordination filter adaptive function is designed, and an adaptive torque change factor is used for torque coordination filtering. Under the premise of ensuring acceleration performance, drastic changes in torque are avoided to ensure the smoothness of vehicle driving; the torque change factor will be adaptively adjusted in real time according to the actual torque value and the required torque value. The strategy is as follows: First, an initial value of the initial torque change factor is determined according to the torque interval where the current actual torque value is located. The torque interval can be divided using a conventional S-shaped distribution, and each interval corresponds to an initial value of the initial torque change factor. Secondly, according to the difference between the actual torque value and the target torque value, a torque change factor coefficient is determined through an adaptive function. Finally, the initial value of the torque change factor is multiplied by the torque change factor coefficient to obtain the final torque change factor, and the torque change factor is used to adjust the actual torque value. ; Wherein, x represents the torque variation factor coefficient, and y represents the difference between the actual torque and the target torque. In actual use, the torque difference y at that moment is used to check the above adaptive function to determine the x value at that moment, i.e., the torque variation factor coefficient. It should be noted that the value of x is between 1 and 2. The filtered required torque can be converted into the current required power by the following formula: ; in, is the current required power, is the current required torque, The speed of the drive motor, wheel hub motor and jet pump, The working efficiency of the motor; The calculated current required power is input into the working mode recognition module to assist in identifying the current optimal working mode, and according to the power distribution plan of the working mode, the required power is reasonably distributed to the engine and the power battery.

[0029] It should be noted that, in this article, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0030] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A vehicle drive control system for an amphibious transport vehicle based on pattern recognition, characterized in that: The drive control system comprises: The working mode recognition module predicts the power requirements at N moments in the future by analyzing the collected historical vehicle data, and calculates the average power requirements at these moments. By combining the current power requirements, the battery state of charge and the vehicle mode switch state, the optimal working mode most suitable for the current moment is selected based on the logic gate threshold judgment, wherein the vehicle historical data includes historical vehicle speed, historical power requirements, historical accelerator pedal opening, historical brake pedal switch signal and historical working mode; The drive control management module first calculates the vehicle's initial required torque based on the driver's input information and the vehicle status information; then, it limits the initial required torque through the maximum allowable power, the maximum allowable vehicle speed, and the maximum driving performance of the motor and the injection pump; next, it filters the drive torque to avoid excessive torque fluctuations and ensure the smoothness of the vehicle's driving; finally, it converts the current required torque into required power through the power-torque conversion formula and inputs it into the working mode recognition module to assist in selecting the current optimal working mode, and based on this working mode, reasonably allocates the required power to the engine and power battery.

2. The amphibious transport vehicle driving control system based on pattern recognition according to claim 1 is characterized in that: In the working mode recognition module, a feedforward neural network is used to predict the power demand at N moments in the future. The parameter update of the feedforward neural network includes two stages: offline optimization and online fine-tuning. First, the parameters of the feedforward neural network are preliminarily learned using standard driving conditions. The network model after learning is installed in the controller. The parameters of the feedforward neural network are updated online by collecting the actual operating data of the amphibious transport vehicle to make it more suitable for the actual driving condition requirements of the amphibious transport vehicle. The online fine-tuning loss function is defined as follows: ； ； in, For the The loss value at that moment is for The total loss value at this moment is It is The actual power demand value at a moment, It is The power demand value is predicted at each moment. is the number of data samples, The number of data samples selected to update the threshold is used to prevent the model from undergoing drastic changes and destroying the model's predictive ability. , that is, whenever the amphibious transport vehicle collects The parameters of the feedforward neural network are updated once every sample, and the fine-tuned model is used to predict the next The power demand at all times is repeated in this way, and the model is continuously updated and optimized online.

3. The amphibious transport vehicle driving control system based on pattern recognition according to claim 1 is characterized in that: In the working mode recognition module, based on the logic gate threshold judgment, the steps of selecting the best working mode most suitable for the current moment include: When the vehicle enters the drivable state, first select the three working modes of land, water and beaching according to the mode switch pressed by the driver. There is an interlocking relationship between the three working modes. Once a working mode is entered, it can only be switched to other modes after exiting the mode. If two or more switches are turned on at the same time, the mode selection is carried out in sequence. Only after the first switch is turned off can another working mode be entered. After determining that the vehicle is in a certain working mode, the corresponding working mode selection is carried out; There are six land working modes: hybrid driving mode 1, hybrid driving mode 2, pure electric driving mode, power generation driving mode, energy recovery mode and mechanical braking mode. When the required power is greater than 0, first determine whether the difference between the current required power and the previous required power is greater than the calibration value a. If the difference is greater than a, enter hybrid driving mode 1 to meet the driver's instantaneous high power demand. If the difference is less than a, determine whether the current required power is greater than the predicted average required power. If it is greater than the average required power, enter hybrid driving mode 2 to make the engine work in the high-efficiency area. If it is less than the average required power, determine whether the current battery state of charge is lower than the charging threshold. If it is lower than the charging threshold, enter the power generation driving mode, the engine works in the high-efficiency area, and use the excess power to charge the power battery. If it is higher than the charging threshold, enter the pure electric driving mode to avoid the engine running in the low-efficiency area to reduce fuel consumption. When the required power is less than 0, first determine whether the current battery state of charge is lower than the maximum state of charge threshold. If it is lower, enter the energy recovery mode. If it is higher, enter the conventional mechanical braking mode.

4. The amphibious transport vehicle driving control system based on pattern recognition according to claim 3 is characterized in that: There are four water working modes: hybrid sailing mode 1, hybrid sailing mode 2, pure electric sailing mode, and power generation sailing mode; When the demand power is greater than 0, first determine whether the difference between the current demand power and the previous demand power is greater than the calibration value b; if the difference is greater than b, enter hybrid navigation mode 1 to meet the driver's instantaneous high power demand; if the difference is less than b, determine whether the current demand power is greater than the predicted average demand power. If it is greater than the average demand power, enter hybrid navigation mode 2 to make the engine work in the high-efficiency area; if it is less than the average demand power, determine whether the current battery charge state is lower than the charging threshold. If it is lower than the charging threshold, enter the power generation navigation mode, the engine works in the high-efficiency area, and use excess power to charge the power battery; if it is higher than the charging threshold, enter the pure electric navigation mode to avoid the engine running in the low-efficiency area to reduce fuel consumption.

5. The amphibious transport vehicle driving control system based on pattern recognition according to claim 3 is characterized in that: There are three working modes of the up and down beach ship: hybrid up and down beach mode 1, hybrid up and down beach mode 2, and pure electric up and down beach mode. First, it is determined whether the difference between the current power demand and the previous power demand is greater than the calibration quantity c. If the difference is greater than c, the hybrid up and down beach mode 1 is entered to meet the driver's instantaneous high power demand. If the difference is less than c, it is determined whether the current power demand is greater than the predicted average power demand. If it is greater than the average power demand, the hybrid up and down beach mode 2 is entered to make the engine work in the high-efficiency area. If it is less than the average required power, the vehicle will enter the pure electric up and down beach mode to prevent the engine from running in the low-efficiency area, thereby reducing fuel consumption.

6. The amphibious transport vehicle driving control system based on pattern recognition according to claim 1 is characterized in that: In the drive control management module, a torque coordination filter adaptive function is designed, and an adaptive torque change factor is used for torque coordination filtering. Under the premise of ensuring acceleration performance, drastic changes in torque are avoided to ensure the smoothness of vehicle driving; the torque change factor will be adaptively adjusted in real time according to the actual torque value and the required torque value. The strategy is as follows: Firstly, an initial value of the initial torque change factor is determined according to the torque interval where the current actual torque value is located. The torque interval can be divided using a conventional S-shaped distribution, and each interval corresponds to an initial value of the initial torque change factor; Secondly, according to the difference between the actual torque value and the target torque value, a torque change factor coefficient is determined through an adaptive function; Finally, the initial value of the torque change factor is multiplied by the torque change factor coefficient to obtain the final torque change factor, and the torque change factor is used to adjust the actual torque value; ； Wherein, x represents the torque variation factor coefficient, and y represents the difference between the actual torque and the target torque; in actual use, the torque difference y at that moment is used to check the above adaptive function to determine the x value at that moment, i.e., the torque variation factor coefficient; The filtered required torque can be converted into the current required power by the following formula: ； in, is the current required power, is the current required torque, The speed of the drive motor, wheel hub motor and jet pump, The working efficiency of the motor; The calculated current required power is input into the working mode recognition module to assist in identifying the current optimal working mode, and according to the power distribution plan of the working mode, the required power is reasonably distributed to the engine and the power battery.

Images