Control Method, Device, Hybrid Vehicle and Medium of Range-Extended Engine

Abstract

This application belongs to the technical field of engine control for hybrid electric vehicles, and relates to a control method, device, hybrid vehicle, and medium for an extended-range engine, including: if the state of charge of the battery is less than or equal to a preset charge percentage, obtaining a plurality of control parameters, a plurality of preset performance parameters, operating state parameters, and average performance parameters corresponding to the pulse map; if the operating state parameters meet the preset stability condition and the update interval time of the pulse map meets the preset interval condition, determining whether each average performance parameter meets the preset deviation condition; if each average performance parameter deviates, updating each control parameter through a trained neural network model based on the control parameters and the average performance parameters until the thermal efficiency meets the preset thermal efficiency condition; controlling the engine to provide power to the generator based on each updated control parameter and each operating state parameter until the generator stops running; reducing the various costs of calibrating each control parameter when the pulse map deviates.

Description

Technical Field

[0001] This application belongs to the technical field of engine control for hybrid electric vehicles, and particularly relates to a control method, device, hybrid vehicle and medium for an extended-range engine. Background Art

[0002] Currently, the engine control method for hybrid electric vehicles mainly adopts the "bench calibration - look-up table control" mode, that is, first calibrate the performance of the engine on a dynamometer bench, formulate a map, and directly call the control parameters on the map during the actual operation of the engine.

[0003] At the same time, for an engine that has been used for a long time, the actual performance of the engine is not fixed. For example, component wear caused by daily use, changes in the state of different engine oils, environmental factors such as temperature, humidity and air pressure, and manufacturing errors. These factors will cause the actual performance of the engine to deviate from the pre-calibrated map, thereby leading to a decline in the economy of the engine.

[0004] If the existing extended-range engine uses the traditional engine control method to re-calibrate for the changes of various factors, on the one hand, it depends on the experience of the calibration personnel, and on the other hand, a large number of bench test experiments need to be carried out. The whole process is time-consuming, laborious and costly.

[0005] The prior art has the problem that it is time-consuming, laborious and costly to calibrate the control parameters in the calibration map. Summary of the Invention

[0006] This application provides a control method, device, hybrid vehicle and medium for an extended-range engine, which can solve the problem that it is time-consuming, laborious and costly to calibrate the control parameters in the calibration map.

[0007] In the first aspect, this application provides a control method for an extended-range engine. The control method is applied to a controller of the engine. The extended-range engine is used to provide power for a generator, and the generator is used to charge a power battery. The method includes:

[0008] If the state of charge of the power battery is less than or equal to a preset charge percentage, obtain a plurality of control parameters corresponding to the map of the engine, a plurality of preset performance parameters in the map, the working state parameters of the engine, and the average performance parameters output from the generator;

[0009] If the working state parameters meet the preset stability condition and the update interval time of the map meets the preset interval condition, determine whether each of the average performance parameters meets the preset deviation condition compared with the corresponding preset performance parameter;

[0010] If any of the average performance parameters deviate, based on the control parameters and the average performance parameters, update each of the control parameters through the trained neural network model until the thermal efficiency of the engine meets the preset thermal efficiency condition;

[0011] Based on each updated control parameter and the working state parameter corresponding to each updated control parameter, control the engine to provide power for the generator until the generator stops running.

[0012] In one embodiment, the working state parameters include oil temperature, oil pressure, crankcase temperature, crankcase pressure, intake air temperature, and exhaust gas temperature;

[0013] The preset stability condition is: collect each of the working state parameters within a preset stable duration at a preset frequency, and the coefficient of variation of each of the working state parameters is less than or equal to a preset variation percentage. Wherein, the value range of the preset frequency is less than or equal to 1 Hz, the value range of the preset stable duration is less than or equal to 60 s, and the value range of the preset variation percentage is less than or equal to 2%.

[0014] In one embodiment, the average performance parameters include average output power, average fuel consumption, and average knock rate; the preset performance parameters include preset output power, preset fuel consumption, and preset knock rate;

[0015] The preset deviation condition is at least one of the following situations:

[0016] The percentage obtained by dividing the absolute value of the difference between the average output power and the preset output power by the preset output power is greater than or equal to a preset threshold percentage;

[0017] The percentage obtained by dividing the absolute value of the difference between the average fuel consumption and the preset fuel consumption by the preset fuel consumption is greater than or equal to the preset threshold percentage;

[0018] The percentage obtained by dividing the absolute value of the difference between the average knock rate and the preset knock rate by the preset knock rate is greater than or equal to the preset threshold percentage;

[0019] Wherein, the value range of the preset threshold percentage is less than or equal to 2%;

[0020] The average performance parameter is the average value of the performance parameters within a preset control state duration, and the value range of the preset control state duration is less than or equal to 30 s.

[0021] In one embodiment, the preset thermal efficiency condition is at least one of the following situations:

[0022] The percentage obtained by dividing the absolute value of the difference between the average output power and the preset output power by the preset output power is greater than or equal to the preset threshold percentage;

[0023] The percentage obtained by dividing the absolute value of the difference between the average fuel consumption and the preset fuel consumption by the preset fuel consumption is greater than or equal to the preset threshold percentage;

[0024] The percentage obtained by dividing the absolute value of the difference between the average knock rate and the preset knock rate by the preset knock rate is greater than or equal to the preset threshold percentage.

[0025] In one embodiment, the neural network model includes a policy network model and an evaluation network model, and the neural network model is a fully connected neural network model;

[0026] Updating each of the control parameters through the neural network model based on the control parameters and the average performance parameters until the thermal efficiency of the engine satisfies a preset thermal efficiency condition, including:

[0027] Based on each of the control parameters and each of the average performance parameters, the evaluation network model outputs a reward feedback value by using a first forward inference;

[0028] Based on the reward feedback value and each of the control parameters, the policy network model determines each updated control parameter by using a second forward inference;

[0029] If the thermal efficiency of the engine corresponding to each updated control parameter satisfies the preset thermal efficiency condition, the policy network model outputs each updated control parameter;

[0030] Wherein, the control parameters include engine speed, fuel injection pulse width, fuel injection timing, ignition timing, throttle angle, exhaust gas recirculation valve opening, variable valve timing oil valve opening.

[0031] In one embodiment, the process expression of the first forward inference is:

[0032]

[0033]

[0034] The process expression of the second forward inference is:

[0035]

[0036]

[0037] Wherein, is the reward feedback value after activation of the m1-th layer in the evaluation network model;

[0038] is the weighted sum value output by the m1-th layer in the evaluation network model;

[0039] is the reward feedback value activated by the (m1 - 1)-th layer in the evaluation network model;

[0040] is the first weight parameter; is the first bias parameter;

[0041] is the updated control parameter value activated by the m2-th layer in the policy network model;

[0042] is the weighted sum value of the control parameters output by the m2-th layer in the policy network model;

[0043] is the updated control parameter value activated by the (m2 - 1)-th layer in the policy network model;

[0044] is the second weight parameter; is the second bias parameter;

[0045] Both m1 and m2 are positive integers, and m1 ≤ 10, m2 ≤ 10.

[0046] In one embodiment, based on each updated control parameter and the working state parameter corresponding to each updated control parameter, controlling the engine to provide power for the generator until after the generator stops running, further includes:

[0047] Uploading each updated control parameter and the performance parameter corresponding to each updated control parameter to the cloud server;

[0048] The cloud server continues to train the neural network model based on each updated control parameter and the performance parameter corresponding to each updated control parameter until the number of training times is greater than or equal to a preset training threshold, or until the change amplitudes of the performance parameter and the control parameter output by the neural network model are both less than a preset threshold percentage;

[0049] The cloud server updates the neural network model at the vehicle end where the engine is located through over-the-air (OTA) update.

[0050] In a second aspect, the present application provides a control device for an extended-range engine, which is applied to a controller of the engine. The extended-range engine is used to provide power for a generator, and the generator is used to charge a power battery, and includes:

[0051] An acquisition module, configured to acquire a plurality of control parameters corresponding to the engine map, a plurality of preset performance parameters in the map, the working state parameters of the engine, and the average performance parameters output from the generator if the state of charge of the power battery is less than or equal to a preset state of charge percentage;

[0052] A judgment module, configured to judge whether each of the average performance parameters meets a preset deviation condition compared with the corresponding preset performance parameter if the working state parameters meet a preset stability condition and the update interval time of the map meets a preset interval condition;

[0053] An optimization module, configured to update each of the control parameters based on the control parameters and the average performance parameters through a trained neural network model until the thermal efficiency of the engine meets a preset thermal efficiency condition if each of the average performance parameters deviates;

[0054] A control module, configured to control the engine to provide power for the generator based on each updated control parameter and the working state parameter corresponding to each updated control parameter until the generator stops running.

[0055] In a third aspect, the present application provides a hybrid vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method according to any one of the above-mentioned first aspect is implemented.

[0056] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the method according to any one of the above-mentioned first aspect is implemented.

[0057] In a fifth aspect, the present application provides a computer program product, and when the computer program product runs on an electronic device, the electronic device is caused to execute the method according to any one of the above-mentioned first aspect.

[0058] It can be understood that the beneficial effects of the above-mentioned second aspect to fifth aspect can refer to the relevant descriptions in the above-mentioned first aspect, and will not be elaborated here.

[0059] The beneficial effects of the present application compared with the prior art are:

[0060] A control method for a range - extender engine of the present application is applied to the controller of the engine. Compared with the prior art, the present application first determines whether the state of charge of the battery, the operating state parameters of the engine, and the update interval time of the map meet the requirements, and then determines whether the average performance parameters corresponding to the map deviate. When the average performance parameters deviate, the trained neural network model is used to update the control parameters of each engine until the thermal efficiency of the engine meets the preset thermal efficiency condition; then, based on the updated control parameters and the operating state parameters corresponding to the updated control parameters, the engine is controlled to provide power to the generator until the generator stops running. The present application can adaptively and real - time adjust each control parameter of the map through the trained neural network model according to the conditions of the vehicle - end battery and the engine, so as to control the range - extender engine to operate in a high - thermal - efficiency condition and maintain it in the working range of the best fuel consumption, thereby reducing the costs of calibrating each control parameter in the map when the map deviates, improving the working efficiency of correcting each control parameter in the map, and further improving the user's riding experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following - described drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0062] Figure 1 is a flowchart of the control method for a range - extender engine provided by an embodiment of the present application;

[0063] Figure 2 is a general flowchart of a control method for a range - extender engine provided by an embodiment of the present application;

[0064] Figure 3 is a flowchart of optimizing each control parameter by a neural network model including an evaluation network model and a policy network model provided by another embodiment of the present application;

[0065] Figure 4 is a structural schematic diagram of a control device for a range - extender engine provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] In the following description, specific details such as specific system architectures and technologies are presented for purposes of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0067] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0068] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0069] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0070] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0071] Currently, the engine control method of hybrid vehicles mainly adopts the "bench calibration - look-up table control" mode, that is, first calibrate the performance of the engine on a dynamometer bench, formulate a map, and directly call the control parameters on the map during the actual operation of the engine.

[0072] At the same time, for an engine that has been used for a long time, the actual performance of the engine is not fixed. For example, component wear caused by daily use, changes in environmental factors such as different oil states, temperature, humidity, and air pressure, as well as manufacturing errors, these factors will all cause the actual performance of the engine to deviate from the pre-calibrated map, thereby resulting in a decline in the fuel economy of the engine.

[0073] If the extended-range engine in the prior art recalibrates for changes in various factors using traditional engine control methods, on the one hand, it depends on the experience of the calibration personnel, and on the other hand, a large number of bench test experiments need to be carried out. The whole process is time-consuming, laborious and costly.

[0074] The extended-range engine does not directly drive the wheels and is decoupled from the vehicle speed at the vehicle end. It is only used to provide power for the generator to generate electricity. Therefore, the engine needs to operate at a high thermal efficiency operating point, and the generator is used to charge the power battery.

[0075] To overcome the above technical problems, the present application provides a control method for an extended-range engine, which is applied to the controller of the engine and includes: if the state of charge of the power battery is less than or equal to a preset charge percentage, obtaining a plurality of control parameters corresponding to the engine's pulse map, a plurality of preset performance parameters in the pulse map, the working state parameters of the engine, and the average performance parameters from the output of the generator; if the working state parameters meet the preset stability conditions and the update interval time of the pulse map meets the preset interval conditions, determining whether each average performance parameter meets the preset deviation condition compared with the corresponding preset performance parameter; if each average performance parameter deviates, updating each control parameter based on the control parameters and the average performance parameters through a trained neural network model until the thermal efficiency of the engine meets the preset thermal efficiency condition; controlling the engine to provide power for the generator based on each updated control parameter and the working state parameter corresponding to each updated control parameter until the generator stops running.

[0076] The control method for an extended-range engine provided by the present application, which is applied to the controller of the engine, compared with the prior art, the present application first determines whether the state of charge of the battery, the working state parameters of the engine, and the update interval time of the pulse map meet the requirements, and then determines whether each average performance parameter corresponding to the pulse map deviates. When each average performance parameter deviates, each control parameter of the engine is updated through a trained neural network model until the thermal efficiency of the engine meets the preset thermal efficiency condition; then, based on each updated control parameter and the working state parameter corresponding to each updated control parameter, the engine is controlled to provide power for the generator until the generator stops running; the present application can adaptively and real-time adjust each control parameter of the pulse map through a trained neural network model according to the conditions of the vehicle-end battery and the engine, so as to control the extended-range engine to operate at a high thermal efficiency condition and maintain it in the working range of the best fuel consumption, thereby reducing the costs of calibrating each control parameter in the pulse map when the pulse map deviates, improving the working efficiency of correcting each control parameter in the pulse map, and further improving the user's riding experience.

[0077] The technical solution of the present application will be described below through specific embodiments.

[0078] In the first aspect, as Figure 1As shown in the figure, the present application provides a control method for a range-extended engine, which is applied to the controller of the engine and includes:

[0079] S100, if the state of charge of the power battery is less than or equal to the preset charge percentage, obtain multiple control parameters corresponding to the engine's map, multiple preset performance parameters in the map, the working state parameters of the engine, and the average performance parameters from the output of the generator.

[0080] In this embodiment, the battery management system (BMS, Battery Management System) of the range-extended electric vehicle monitors the state of charge (SOC, State of Charge) of the power battery. If the state of charge of the power battery is less than or equal to the preset charge percentage, after the controller of the engine is powered on and initialized, according to the power supply demand of the electric vehicle, multiple control parameters corresponding to the engine's map are obtained, and at the same time, the controller reads multiple preset performance parameters in the map. Among them, the value range of the preset charge percentage is less than or equal to 30%, and the control parameters include engine speed, injection pulse width, injection timing, ignition timing, throttle angle, exhaust gas recirculation valve opening (EGR, Exhaust Gas Recirculation), and variable valve timing oil valve opening. Since the precondition for starting the range-extended engine is set, it can be started only when the user needs it, avoiding frequent engine starts, reducing energy consumption, and improving the user experience.

[0081] S200, if the working state parameters meet the preset stability condition and the update interval time of the map meets the preset interval condition, determine whether each average performance parameter meets the preset deviation condition compared with the corresponding preset performance parameter.

[0082] In this embodiment, two preconditions are set, that is, the working state parameters meet the preset stability condition and the update interval time of the map meets the preset interval condition. Only when these two preconditions are met simultaneously will it be determined whether the average performance parameter deviates. If these two preconditions are not met, no action will be taken, reducing the number of times of frequently starting to correct the deviation of the average performance parameter, reducing energy consumption and computing resources, improving the accuracy of starting to correct the deviation of the average performance parameter, and improving the user experience.

[0083] In one embodiment, for step S200, if the working state parameters meet the preset stability condition and the update interval time of the map meets the preset interval condition, determine whether each average performance parameter meets the preset deviation condition compared with the corresponding preset performance parameter, including:

[0084] Determine whether the working state parameters meet the preset stability condition;

[0085] If the operating state parameters meet the preset stability conditions, determine whether the update interval time of the pulse spectrum diagram meets the preset interval conditions;

[0086] If the update interval time of the pulse spectrum diagram also meets the preset interval conditions, determine whether each average performance parameter meets the preset deviation conditions compared with the corresponding preset performance parameter.

[0087] In one embodiment, the operating state parameters of the engine include oil temperature, oil pressure, crankcase temperature, crankcase pressure, intake air temperature, and exhaust gas temperature, and the operating state parameters are obtained through various temperature sensors and pressure sensors; the preset stability conditions are: collect each operating state parameter within a preset stable duration at a preset frequency, and the coefficient of variation of each operating state parameter is less than or equal to a preset variation percentage, where the value range of the preset frequency is less than or equal to 1 Hz, the value range of the preset stable duration is less than or equal to 60 s, and the value range of the preset variation percentage is less than or equal to 2%. After setting the range of the coefficient of variation, the control parameters of the engine will not be affected by other external factors, and the control parameters can be improved.

[0088] In one embodiment, the calculation formula of the coefficient of variation is:

[0089]

[0090] Wherein, is the coefficient of variation, is any operating state parameter, is the average value of any operating state parameter obtained within a preset stable duration at a preset frequency, is the preset stable duration.

[0091] In one embodiment, the preset interval condition is that the time between two adjacent updates of the pulse spectrum diagram is greater than or equal to an interval time threshold, and the value range of the interval time threshold is greater than or equal to 72 hours. For example, the interval time threshold is 96 hours.

[0092] In one embodiment, after the operating state parameters meet the preset stability conditions, maintain the engine in the current operating state for a preset maintenance duration, and the generator controller of the range extender outputs the average performance parameters of each performance parameter within the preset maintenance duration, and the generator controller synchronously transmits them to the engine controller through the Controller Area Network (CAN) bus. The average performance parameters include average output power, average fuel consumption, and average knock rate; the preset performance parameters include preset output power, preset fuel consumption, and preset knock rate; where the value range of the preset maintenance duration is less than or equal to 30 s. For example, the preset maintenance duration is 15 s.

[0093] In one embodiment, the preset deviation condition is at least one of the following cases:

[0094] The percentage obtained by dividing the absolute value of the difference between the average output power and the preset output power by the preset output power is greater than or equal to the preset threshold percentage;

[0095] The percentage obtained by dividing the absolute value of the difference between the average fuel consumption and the preset fuel consumption by the preset fuel consumption is greater than or equal to the preset threshold percentage;

[0096] The percentage obtained by dividing the absolute value of the difference between the average knock rate and the preset knock rate by the preset knock rate is greater than or equal to the preset threshold percentage;

[0097] Wherein, the value range of the preset threshold percentage is less than or equal to 2%;

[0098] The average performance parameter is the average of the performance parameters within the preset control state duration, and the value range of the preset control state duration is less than or equal to 30 s.

[0099] In one embodiment, the expression of the preset deviation condition is:

[0100]

[0101] In the formula, i represents the label of any performance parameter of the engine, represents the current average performance parameter of the engine, represents the preset performance parameter in the pulse spectrum diagram.

[0102] S300, if each average performance parameter deviates, based on the control parameters and the average performance parameters, update each control parameter through the trained neural network model until the thermal efficiency of the engine meets the preset thermal efficiency condition.

[0103] In this embodiment, by setting the precondition for each average performance parameter to deviate, the control parameters are updated through the neural network model, reducing the number of times of frequently starting to adjust the deviation of the performance parameters in the pulse spectrum diagram, reducing energy consumption and computing resources, improving the accuracy of calibrating each control parameter, and improving the user experience.

[0104] In one embodiment, the neural network model includes a policy network model and an evaluation network model. The neural network model is a fully connected neural network model (FCNN, Full Connect Neural Network), that is, each hidden layer of each fully connected layer includes a linear layer and an activation layer. Among them, the linear layer calculates the linear weighted sum value, and the activation layer is used to output the activated reward feedback value or the updated control parameters.

[0105] In one embodiment, in step S300, based on the control parameters and the average performance parameters, each control parameter is updated through a neural network model until the thermal efficiency of the engine meets the preset thermal efficiency condition, including:

[0106] Based on each control parameter and each average performance parameter, the evaluation network model uses the first forward inference to output a reward feedback value;

[0107] Based on the reward feedback value and each control parameter, the policy network model uses the second forward inference to determine each updated control parameter;

[0108] If the thermal efficiency of the engine corresponding to each updated control parameter meets the preset thermal efficiency condition, the policy network model outputs each updated control parameter.

[0109] In one embodiment, each control parameter input to the evaluation network model is the average control parameter of each control parameter within a preset maintenance duration. Using the average control parameter helps to prevent control parameters that are mutated due to external factors from entering the evaluation network model, improves the accuracy of the reward feedback value output by the evaluation network model, and further improves the accuracy of each updated control parameter output by the policy network model, thereby improving the user experience. The average control parameters include the average engine speed, the average fuel injection pulse width, the average fuel injection timing, the average ignition timing, the average throttle angle, the average exhaust gas recirculation valve opening, and the average variable valve timing oil valve opening.

[0110] In one embodiment, the number of cycles for the neural network model to update each control parameter is less than or equal to a preset number of cycles. The value range of the preset number of cycles is less than or equal to 100 times. For example, the preset number of cycles is 5 times or 50 times, which can reduce the computing resources at the vehicle end.

[0111] In one embodiment, the process expression of the first forward inference is:

[0112]

[0113]

[0114] The process expression of the second forward inference is:

[0115]

[0116]

[0117] Wherein, is the reward feedback value after activation of the m1-th layer in the evaluation network model;

[0118] is the weighted sum value output by the m1-th layer in the evaluation network model;

[0119] To evaluate the reward feedback value after activation of the (m1 - 1)-th layer in the network model;

[0120] is the first weight parameter; is the first bias parameter;

[0121] is the updated control parameter value after activation of the m2-th layer in the policy network model;

[0122] is the weighted sum value of the control parameters output by the m2-th layer in the policy network model;

[0123] is the updated control parameter value after activation of the (m2 - 1)-th layer in the policy network model;

[0124] is the second weight parameter; is the second bias parameter;

[0125] Both m1 and m2 are positive integers, and m1 ≤ 10, m2 ≤ 10.

[0126] In one embodiment, the preset thermal efficiency condition is: the change in the average performance parameter and the preset performance parameter is less than or equal to the preset threshold percentage; the preset thermal efficiency condition is specifically at least one of the following situations:

[0127] The percentage obtained by dividing the absolute value of the difference between the average output power and the preset output power by the preset output power is greater than or equal to the preset threshold percentage;

[0128] The percentage obtained by dividing the absolute value of the difference between the average fuel consumption and the preset fuel consumption by the preset fuel consumption is greater than or equal to the preset threshold percentage;

[0129] The percentage obtained by dividing the absolute value of the difference between the average knock rate and the preset knock rate by the preset knock rate is greater than or equal to the preset threshold percentage;

[0130] Among them, the value range of the preset threshold percentage is less than or equal to 2%.

[0131] In another embodiment, the preset thermal efficiency condition is: the change in the average performance parameter and the preset performance parameter is less than or equal to the preset threshold percentage, and / or, the change in the average control parameter and the control parameter is less than or equal to the preset threshold percentage, where the control parameter is the control parameter before the preset maintenance duration.

[0132] In another embodiment, the preset thermal efficiency condition is at least one of the following situations:

[0133] The percentage obtained by dividing the absolute value of the difference between the average output power and the preset output power by the preset output power is greater than or equal to the preset threshold percentage;

[0134] The percentage obtained by dividing the absolute value of the difference between the average fuel consumption and the preset fuel consumption by the preset fuel consumption is greater than or equal to the preset threshold percentage;

[0135] The percentage obtained by dividing the absolute value of the difference between the average knock rate and the preset knock rate by the preset knock rate is greater than or equal to the preset threshold percentage;

[0136] The percentage obtained by dividing the absolute value of the difference between the average engine speed and the engine speed by the engine speed is greater than or equal to the preset threshold percentage;

[0137] The percentage obtained by dividing the absolute value of the difference between the average fuel injection pulse width and the fuel injection pulse width by the fuel injection pulse width is greater than or equal to the preset threshold percentage;

[0138] The percentage obtained by dividing the absolute value of the difference between the average fuel injection timing and the fuel injection timing by the fuel injection timing is greater than or equal to the preset threshold percentage;

[0139] The percentage obtained by dividing the absolute value of the difference between the average ignition timing and the ignition timing by the ignition timing is greater than or equal to the preset threshold percentage;

[0140] The percentage obtained by dividing the absolute value of the difference between the average throttle angle and the throttle angle by the throttle angle is greater than or equal to the preset threshold percentage;

[0141] The percentage obtained by dividing the absolute value of the difference between the average exhaust gas recirculation valve opening and the exhaust gas recirculation valve opening by the exhaust gas recirculation valve opening is greater than or equal to the preset threshold percentage;

[0142] The percentage obtained by dividing the absolute value of the difference between the average variable valve timing oil valve opening and the variable valve timing oil valve opening by the variable valve timing oil valve opening is greater than or equal to the preset threshold percentage;

[0143] Wherein, the value range of the preset threshold percentage is less than or equal to 2%.

[0144] S400, based on each updated control parameter and the working state parameter corresponding to each updated control parameter, controls the engine to provide power for the generator until the generator stops running.

[0145] In this embodiment, based on each updated control parameter and the operating state parameter corresponding to each updated control parameter, the engine is controlled to provide power to the generator, which can keep the control of the range extender engine in a high thermal efficiency working condition and maintain it in the working range of the best fuel consumption, thereby reducing the costs of each control parameter in the calibrated map when the pulse map deviates, improving the working efficiency of correcting each control parameter in the pulse map, and further improving the user's riding experience.

[0146] In one embodiment, after controlling the engine to provide power to the generator based on each updated control parameter and the operating state parameter corresponding to each updated control parameter until the generator stops running, it further includes:

[0147] Upload each updated control parameter and the performance parameter corresponding to each updated control parameter to the cloud server;

[0148] The cloud server continues to train the neural network model based on each updated control parameter and the performance parameter corresponding to each updated control parameter until the number of training times is greater than or equal to the preset training threshold, or until the change amplitudes of the performance parameter and the control parameter output by the neural network model are both less than the preset threshold percentage;

[0149] The cloud server updates the neural network model on the vehicle side where the engine is located through the over-the-air (OTA) method.

[0150] It should be noted that each updated control parameter and each performance parameter are stored in the on-board diagnostic system (OBD), and the on-board diagnostic system uploads them to the cloud server. The cloud server continues to train the neural network model based on each updated control parameter and the performance parameter corresponding to each updated control parameter using batch training and backpropagation gradient descent until the number of training times is greater than or equal to the preset training threshold (for example, the preset training threshold ≥ 500 times), or until the change amplitudes of the performance parameter and the control parameter output by the neural network model are both less than the preset threshold percentage (for example, the preset threshold percentage ≤ 2%), and updates the weight parameter and bias parameter of the neural network model. The cloud server performs local deployment of the updated neural network model through the over-the-air (OTA) method.

[0151] It can be understood that Figure 2 is a schematic diagram of the overall process of a control method for a range extender engine, Figure 3 is a schematic diagram of the process of optimizing each control parameter by a neural network model (i.e., a reinforcement learning model) including an evaluation network model and a policy network model. For the specific process, please refer to the content of the above embodiments.

[0152] In the second aspect, as Figure 4As shown in the figure, the present application provides a control device 100 for an extended-range engine, which is applied to the controller of the engine. The extended-range engine is used to provide power for the generator, and the generator is used to charge the power battery, including:

[0153] An acquisition module 110, configured to obtain a plurality of control parameters corresponding to the engine's map, a plurality of preset performance parameters in the map, the engine's working state parameters, and the average performance parameters from the generator output if the state of charge of the power battery is less than or equal to a preset charge percentage;

[0154] A judgment module 120, configured to judge whether each average performance parameter meets a preset deviation condition compared with the corresponding preset performance parameter if the working state parameters meet the preset stability condition and the update interval time of the map meets the preset interval condition;

[0155] An optimization module 130, configured to update each control parameter based on the control parameters and the average performance parameters through a trained neural network model until the thermal efficiency of the engine meets the preset thermal efficiency condition if each average performance parameter deviates;

[0156] A control module 140, configured to control the engine to provide power for the generator based on each updated control parameter and the working state parameter corresponding to each updated control parameter until the generator stops running.

[0157] It should be noted that for the information interaction, execution process, etc. between the above modules, since they are based on the same concept as the method embodiment of the present application, their specific functions and the technical effects brought can be specifically referred to the method embodiment part, and will not be elaborated here.

[0158] Those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0159] In a third aspect, an embodiment of the present application provides a hybrid vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in any one of the above first aspects is implemented.

[0160] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the method described in any one of the above first aspects.

[0161] In a fifth aspect, an embodiment of the present application provides a computer program product, which when running on an electronic device causes the electronic device to execute the method described in any one of the above first aspects.

[0162] It can be understood that the beneficial effects of the above second to fifth aspects can refer to the relevant descriptions in the above first aspect and will not be elaborated here.

[0163] If the integrated unit is implemented in the form of 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, to implement all or part of the processes in the above embodiment methods of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc.

[0164] The computer-readable medium can at least include: any entity or device capable of carrying the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0165] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0166] Those of ordinary skill in the art will realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0167] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be electrical, mechanical or other forms.

[0168] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included in the protection scope of this application.

Claims

1. A control method for a range-extended engine, characterized in that, The control method is applied to a controller of an engine. The range-extended engine is used to provide power for a generator, and the generator is used to charge a power battery, and the method includes: If the state of charge of the power battery is less than or equal to a preset charge percentage, obtain a plurality of control parameters corresponding to the engine's map, a plurality of preset performance parameters in the map, the engine's operating state parameters, and the average performance parameters output from the generator; If the operating state parameters meet the preset stability condition and the update interval time of the map meets the preset interval condition, determine whether each of the average performance parameters meets the preset deviation condition compared with the corresponding preset performance parameter; If any of the average performance parameters deviate, update each of the control parameters based on the control parameters and the average performance parameters through a trained neural network model until the engine's thermal efficiency meets the preset thermal efficiency condition; Based on each updated control parameter and the operating state parameter corresponding to each updated control parameter, control the engine to provide power for the generator until the generator stops operating; Wherein, the operating state parameters include oil temperature, oil pressure, crankcase temperature, crankcase pressure, intake air temperature, and exhaust gas temperature; The preset stability condition is: collect each of the operating state parameters within a preset stable duration at a preset frequency, and the coefficient of variation of each of the operating state parameters is less than or equal to a preset variation percentage. Wherein, the value range of the preset frequency is less than or equal to 1 Hz, the value range of the preset stable duration is less than or equal to 60 s, and the value range of the preset variation percentage is less than or equal to 2%; 2. The method according to claim 1, characterized in that, The average performance parameters include average output power, average fuel consumption, and average knock rate; the preset performance parameters include preset output power, preset fuel consumption, and preset knock rate; The preset deviation condition is at least one of the following situations: The percentage obtained by dividing the absolute value of the difference between the average output power and the preset output power by the preset output power is greater than or equal to a preset threshold percentage; The percentage obtained by dividing the absolute value of the difference between the average fuel consumption and the preset fuel consumption by the preset fuel consumption is greater than or equal to the preset threshold percentage; The percentage obtained by dividing the absolute value of the difference between the average knock rate and the preset knock rate by the preset knock rate is greater than or equal to the preset threshold percentage; Wherein, the value range of the preset threshold percentage is less than or equal to 2%; The average performance parameter is the average value of the performance parameters within a preset control state duration, and the value range of the preset control state duration is less than or equal to 30 s.

3. The method according to claim 2, wherein The preset thermal efficiency condition is at least one of the following situations: The percentage obtained by dividing the absolute value of the difference between the average output power and the preset output power by the preset output power is less than or equal to the preset threshold percentage; The percentage obtained by dividing the absolute value of the difference between the average fuel consumption and the preset fuel consumption by the preset fuel consumption is less than or equal to the preset threshold percentage; The percentage obtained by dividing the absolute value of the difference between the average knocking rate and the preset knocking rate by the preset knocking rate is less than or equal to the preset threshold percentage.

4. The method according to claim 1, characterized in that, The neural network model includes a policy network model and a value network model, and the neural network model is a fully connected neural network model; Based on the control parameters and the average performance parameters, updating each of the control parameters through the neural network model until the thermal efficiency of the engine meets the preset thermal efficiency condition, including: Based on each of the control parameters and each of the average performance parameters, the value network model uses a first forward inference to output a reward feedback value; Based on the reward feedback value and each of the control parameters, the policy network model uses a second forward inference to determine each of the updated control parameters; If the thermal efficiency of the engine corresponding to each of the updated control parameters meets the preset thermal efficiency condition, the policy network model outputs each of the updated control parameters; Wherein, the control parameters include engine speed, injection pulse width, injection timing, ignition timing, throttle angle, exhaust gas recirculation valve opening, variable valve timing oil valve opening.

5. The method according to claim 4, characterized in that, The process expression of the first forward inference is: The process expression of the second forward inference is: Among them, is the reward feedback value after activation of the m first layer in the evaluation network model; is the weighted sum value output by the m first layer in the evaluation network model; For the reward feedback value after activation of the m 1 - first layer in the evaluation network model; is the first weight parameter; is the first bias parameter; The updated control parameter value after activation of the second layer in the policy network model; m 2-layer activation is the weighted sum value of the control parameters output by the m second layer in the policy network model; The updated control parameter value after activation of the m2- first layer in the policy network model; is the second weight parameter; is the second bias parameter; m 1. m Both 1 and 2 are positive integers, and m 1 ≤ 10, m 2 ≤ 10.

6. The method according to claim 1, wherein Based on each of the updated control parameters and the working state parameters corresponding to each of the updated control parameters, controlling the engine to provide power for the generator until after the generator stops running, further including: Uploading each of the updated control parameters and the performance parameters corresponding to each of the updated control parameters to a cloud server; The cloud server continues to train the neural network model based on each of the updated control parameters and the performance parameters corresponding to each of the updated control parameters until the number of training times is greater than or equal to a preset training threshold, or until the change amplitudes of the performance parameters and the control parameters output by the neural network model are both less than the preset threshold percentage; The cloud server updates the neural network model at the vehicle end where the engine is located through over-the-air (OTA) technology.

7. A control device for a range extender engine, characterized in that A controller applied to an engine, the range extender engine is used to provide power for a generator, and the generator is used to charge a power battery, including: An acquisition module, configured to, if the state of charge of the power battery is less than or equal to a preset charge percentage, acquire a plurality of control parameters corresponding to the map of the engine, a plurality of preset performance parameters in the map, the working state parameters of the engine, and the average performance parameters output from the generator; A judgment module, configured to, if the working state parameters meet the preset stability condition and the update interval time of the map meets the preset interval condition, judge whether each of the average performance parameters meets a preset deviation condition compared with the corresponding preset performance parameter; An optimization module, configured to, if each of the average performance parameters deviates, update each of the control parameters through a trained neural network model based on the control parameters and the average performance parameters until the thermal efficiency of the engine meets the preset thermal efficiency condition; A control module, configured to control the engine to provide power to the generator based on each updated control parameter and the operating state parameter corresponding to each of the updated control parameters until the generator stops running; Wherein, the operating state parameters include oil temperature, oil pressure, crankcase temperature, crankcase pressure, intake air temperature, and exhaust gas temperature; The preset stability condition is: collecting each of the operating state parameters within a preset stable duration at a preset frequency, and the coefficient of variation of each of the operating state parameters is less than or equal to a preset variation percentage, wherein the value range of the preset frequency is less than or equal to 1 Hz, the value range of the preset stable duration is less than or equal to 60 s, and the value range of the preset variation percentage is less than or equal to 2%.

8. A hybrid vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the method according to any one of claims 1 to 6 is implemented.

Images