Engine control method and device, storage medium, electronic equipment and vehicle

Abstract

The invention discloses an engine control method and device, a storage medium, electronic equipment and a vehicle. Comprising the steps that if it is detected that a surge occurrence probability exists in an engine of a target vehicle, predicted torque information, including a predicted slow torque parameter and a predicted fast torque parameter, of the engine at the next moment is predicted through a torque pre-control model on the basis of torque information at the current moment and historical torque information; correcting the torque information at the current moment according to the predicted fast torque parameter and the required torque of the engine; and selecting a target control strategy from the candidate control strategies according to the predicted fast torque parameter and the maximum torque of the engine, and controlling the engine based on the predicted torque information by adopting the target control strategy. According to the technical scheme, the torque information of the next moment can be predicted, the appropriate target control strategy is selected to control the engine, surge energy elimination and compatible energy recovery are achieved, surge is effectively avoided, and meanwhile it is ensured that power of the whole vehicle is smooth.

Description

Technical Field

[0001] This application belongs to the field of vehicle control technology, and in particular relates to an engine control method, device, storage medium, electronic equipment and vehicle. Background Technology

[0002] When a vehicle is in motion, if the throttle valve of a turbocharged engine suddenly closes, such as when shifting gears or releasing the accelerator, the high-pressure air in the intake manifold will be blocked by the throttle valve, forming a gas pressure wave that rebounds and causes turbo surge.

[0003] Currently, the conventional control method involves opening the pressure relief valve to release the gas flowing towards the throttle valve to the turbocharger compressor inlet, thereby quickly releasing excess pressure and preventing damage to components such as the turbocharger impeller due to overpressure. However, even with this conventional control method, NVH (Noise, Vibration, and Harshness) issues still exist due to the pressure relief valve line throttling. Summary of the Invention

[0004] The embodiments of this application provide an engine control method, device, storage medium, electronic device, and vehicle, which can control the engine based on predicted fast and slow torque parameters to eliminate surge energy, be compatible with energy recovery, effectively avoid surge, and ensure smooth power delivery of the entire vehicle.

[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0006] According to a first aspect of the embodiments of this application, an engine control method is provided, comprising:

[0007] If a surge probability is detected in the engine of the target vehicle, the torque prediction model is used to predict the engine's torque information at the next moment based on the torque information at the current moment and the historical torque information. The predicted torque information includes predicted slow torque parameters and predicted fast torque parameters.

[0008] The torque information at the current moment is corrected based on the predicted fast torque parameters and the engine's required torque.

[0009] Based on the predicted fast torque parameters and the engine's maximum torque, a target control strategy is selected from the candidate control strategies and then adopted to control the engine based on the predicted torque information.

[0010] In some embodiments of this application, based on the foregoing scheme, the torque pre-control model includes a slow torque pre-control model. Using this model, based on the current torque information and historical torque information, the predicted torque information of the engine at the next moment is predicted, including:

[0011] Obtain the engine's slow torque related parameters; among which, the slow torque related parameters include historical slow torque parameters, current slow torque parameters, and first related parameters, the first related parameters include the current throttle opening, wheel-side torque demand, compressor pressure ratio, intake air flow, ambient pressure, and ambient temperature;

[0012] Input the slow torque-related parameters into the slow torque pre-control model to obtain the predicted slow torque parameters for the next moment output by the slow torque pre-control model.

[0013] In some embodiments of this application, based on the foregoing scheme, the torque pre-control model includes a fast torque pre-control model. Using this model, based on the current torque information and historical torque information, the predicted torque information of the engine at the next moment is predicted, including:

[0014] Obtain the engine's fast torque related parameters; among which, the fast torque related parameters include historical fast torque parameters, current fast torque parameters, and second related parameters, the second related parameters include the engine's maximum torque at the current moment, battery-related parameters, vehicle deceleration, and energy recovery power;

[0015] Input the fast torque-related parameters into the fast torque pre-control model to obtain the predicted fast torque parameters for the next moment output by the fast torque pre-control model.

[0016] In some embodiments of this application, based on the foregoing scheme, a target control strategy is selected from candidate control strategies according to the predicted torque information and the engine's maximum torque, including:

[0017] If the predicted fast torque parameter is greater than the engine's maximum torque, then based on the predicted fast torque parameter and the current minimum torque, the corresponding fast and slow torque separation strategy is selected from the candidate control strategies as the target control strategy.

[0018] If the predicted fast torque parameter is not greater than the engine's maximum torque, then the fast and slow torque output strategy is selected from the candidate control strategies as the target control strategy.

[0019] In some embodiments of this application, based on the aforementioned scheme, a corresponding fast and slow torque separation strategy is selected from candidate control strategies as the target control strategy according to the predicted fast torque parameters and the current minimum torque of the gas volume, including:

[0020] If the predicted fast torque parameter is greater than the current minimum torque, the corresponding fast and slow torque separation strategy includes determining the change in fast torque parameter based on the predicted fast torque parameter and the fast torque parameter at the current moment, determining the corresponding ignition efficiency based on the change in fast torque parameter, and controlling the engine to reduce the ignition advance angle based on the ignition efficiency.

[0021] If the predicted fast torque parameter is not greater than the current minimum torque, the corresponding fast and slow torque separation strategy includes controlling the engine fuel cut-off.

[0022] In some embodiments of this application, based on the foregoing scheme, a target control strategy is adopted to control the engine based on predicted torque information, including:

[0023] Based on the predicted torque information, the target throttle opening and target ignition advance angle of the engine are determined;

[0024] The engine is controlled to operate based on the target throttle opening and target ignition advance angle.

[0025] In some embodiments of this application, based on the aforementioned scheme, the torque information at the current moment is corrected according to the predicted fast torque parameters and the engine's required torque, including:

[0026] Determine the torque deviation based on the predicted fast torque parameters and the engine's required torque;

[0027] The required torque of the drive motor is corrected based on the deviation of the required torque.

[0028] In some embodiments of this application, based on the foregoing scheme, detecting the probability of engine surge in the target vehicle includes:

[0029] Based on the current operating condition information of the target vehicle's engine, determine the probability of engine surge; where the current operating condition information includes the compressor pressure ratio and intake air flow at the current moment.

[0030] In some embodiments of this application, based on the foregoing scheme, the probability of engine surge is determined according to the current operating condition information of the target vehicle's engine, including:

[0031] The compressor pressure ratio and intake flow rate at the current moment are substituted into the prediction function for calculation to obtain the corresponding function value; the prediction function is obtained by fitting the calibration results based on the engine surge test.

[0032] If the function value satisfies the target condition, then the probability of engine surge is determined.

[0033] According to a second aspect of the embodiments of this application, an engine control device is provided, comprising:

[0034] The torque prediction module is used to predict the engine's torque information at the next moment based on the current torque information and historical torque information if the probability of engine surge in the target vehicle is detected. The predicted torque information includes predicted slow torque parameters and predicted fast torque parameters.

[0035] The torque correction module is used to correct the torque information at the current moment based on the predicted fast torque parameters and the engine's required torque.

[0036] The engine control module is used to select a target control strategy from candidate control strategies based on the predicted fast torque parameters and the engine's maximum torque, and then use the target control strategy to control the engine based on the predicted torque information.

[0037] According to a third aspect of the embodiments of this application, a computer-readable storage medium is provided, which stores computer program instructions that, when loaded and executed by a processor, implement the steps of the method as described in any of the first aspects above.

[0038] According to a fourth aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the method as described in any of the first aspects above.

[0039] According to a fifth aspect of the embodiments of this application, a vehicle is provided, including an engine, wherein when the engine is controlled, the steps of the method as described in any of the first aspects above are implemented.

[0040] According to a sixth aspect of the embodiments of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method as described in any of the first aspects above.

[0041] In this application, if a surge probability is detected in the engine of a target vehicle, a torque pre-control model is used to predict the engine's torque information for the next moment based on the current torque information and historical torque information. The predicted torque information includes predicted slow torque parameters and predicted fast torque parameters. The torque information for the current moment is corrected based on the predicted fast torque parameters and the engine's required torque. A target control strategy is selected from candidate control strategies based on the predicted fast torque parameters and the engine's maximum torque, and this target control strategy is used to control the engine based on the predicted torque information. The technical solution provided in this application can predict the engine's fast and slow torque parameters for the next moment when a surge probability exists in the target vehicle's engine, thereby selecting a suitable target control strategy and controlling the engine based on the predicted fast and slow torque parameters. This eliminates surge energy, is compatible with energy recovery, effectively avoids surge, and performs closed-loop correction on the current torque information to prevent the target control strategy from affecting the total required torque, ensuring smooth vehicle power delivery.

[0042] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0043] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0044] Figure 1 A schematic diagram of a scenario in which the engine control method of the embodiments of this application can be applied is shown;

[0045] Figure 2 A flowchart of the engine control method in an embodiment of this application is shown;

[0046] Figure 3 A flowchart illustrating the determination of predicted slow torque parameters in an embodiment of this application is shown;

[0047] Figure 4 A schematic diagram of the neural network architecture of the slow torque pre-control model in the embodiments of this application is shown;

[0048] Figure 5 A flowchart illustrating the determination of predicted fast torque parameters in an embodiment of this application is shown;

[0049] Figure 6 A schematic diagram of the neural network architecture of the fast torque pre-control model in the embodiments of this application is shown;

[0050] Figure 7 An engine torque state diagram is shown in an embodiment of this application;

[0051] Figure 8 Another engine torque state diagram is shown in an embodiment of this application;

[0052] Figure 9 Another engine torque state diagram is shown in an embodiment of this application;

[0053] Figure 10 A flowchart illustrating the determination of surge occurrence probability in an embodiment of this application is shown;

[0054] Figure 11 Another flowchart of the engine control method in an embodiment of this application is shown;

[0055] Figure 12 A block diagram of an engine control device according to an embodiment of this application is shown;

[0056] Figure 13 A schematic diagram of the structure of an electronic device according to an embodiment of this application is shown. Detailed Implementation

[0057] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0058] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0059] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0060] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0061] To enable those skilled in the art to better understand this application, firstly, in conjunction with Figure 1 A brief description of the application scenarios involved in this application is provided.

[0062] See Figure 1 The diagram illustrates a scenario where the engine control method of the present application embodiments can be applied.

[0063] The target vehicle is an intelligent driving vehicle, which can be a hybrid model. The vehicle-side controller of the target vehicle has a certain data processing capability, which can analyze the relevant information transmitted by various sensors, and then precisely control the engine of the target vehicle.

[0064] During vehicle operation, when sensors detect engine-related information, they transmit this information in real time to the vehicle-side controller. This allows the controller to assess the probability of engine surge. If surge is present, the vehicle-side controller can use a torque pre-control model, based on the current torque information from the sensors and stored historical torque data, to predict the engine's torque for the next moment. This prediction includes both slow-speed and fast-speed torque parameters.

[0065] Furthermore, the vehicle-side controller can determine whether the engine's fast and slow torques are consistent based on the predicted fast torque parameters and the engine's maximum torque, and then determine whether to perform fast and slow torque separation control. This allows for the selection of an appropriate target control strategy to precisely control the engine, eliminate surge energy based on the predicted slow torque parameters, and integrate energy recovery based on the predicted fast torque parameters, effectively preventing surge from occurring.

[0066] In addition, the vehicle-side controller can also perform closed-loop correction of the torque information at the current moment based on the predicted fast torque parameters and the engine's required torque. Specifically, it corrects the P3 / 4 required torque to avoid using a target control strategy to control the engine and affect the total required torque, ultimately ensuring the smooth power delivery of the entire vehicle.

[0067] In one exemplary embodiment, refer to Figure 2 The flowchart of the engine control method in the embodiments of this application is shown below, and is described in detail below:

[0068] Step 201: If a surge probability is detected in the engine of the target vehicle, the torque prediction model is used to predict the engine's torque information at the next moment based on the torque information at the current moment and the historical torque information.

[0069] The vehicle-side controller of the target vehicle can periodically execute the engine control method in this application embodiment. For example, at the beginning of each new cycle, the vehicle-side controller detects whether there is a probability of engine surge in the current cycle. If so, it continues to execute the steps of the subsequent control method; if not, no additional operation is performed, and the engine operates normally.

[0070] Specifically, the vehicle-side controller can obtain relevant engine information from various sensors at the current moment, such as engine speed, compressor pressure ratio, and intake airflow. It then combines this information to determine the probability of engine surge occurring within the current cycle. The probability of surge refers to the possibility of surge occurring or the impossibility of surge. As long as the probability of surge exists, regardless of its magnitude, subsequent control steps must be executed.

[0071] The vehicle-side controller runs a torque pre-control model, taking the current torque information and historical torque information as inputs to obtain the predicted torque information for the next moment. The historical torque information includes torque data from multiple historical moments, comprising slow torque parameters and fast torque parameters; that is, the predicted torque information includes predicted slow torque parameters and predicted fast torque parameters.

[0072] For example, an initial torque pre-control model is constructed, and then iteratively trained based on engine sample data (including torque information) until the training termination condition is met, resulting in the torque pre-control model provided in this embodiment. Optionally, the initial torque pre-control model can be created based on MLP (Multi-layer Perceptron), LSTM (Long Short-Term Memory), or GRU (Gate Recurrent Unit), which can extract the correlation features of engine sample data in the time dimension and obtain more accurate prediction results. The torque pre-control model can also be composed of multiple sub-models.

[0073] Step 202: Correct the torque information at the current moment based on the predicted fast torque parameters and the engine's required torque.

[0074] It should be noted that since the predicted torque information includes both predicted slow torque and predicted fast torque parameters, the engine's fast and slow torque may not be consistent when the engine is subsequently controlled based on the predicted torque information. For example, if surge energy is eliminated based on the predicted slow torque parameters, or energy recovery is compatible based on the predicted fast torque parameters, various constraints may lead to inconsistencies between the fast and slow torques. Consequently, the slow torque of the engine will gradually decrease, affecting wheel-end power, while the engine's fast torque will also decrease accordingly. Therefore, before controlling the engine based on the predicted torque information, it is necessary to promptly correct the engine's actual torque to ensure that the total torque demand of the engine or wheel-end power remains unchanged, meeting the actual needs of the driver.

[0075] Based on the predicted fast torque parameters and the engine's required torque, the fast torque in the torque information at the current moment is corrected.

[0076] Optionally, the required torque deviation is determined based on the predicted fast torque parameters and the engine's required torque; the required torque of the drive motor is then corrected based on this deviation. Specifically, the difference between the predicted fast torque parameters and the engine's required torque is used as the required torque deviation, and a closed-loop correction is performed on the current required torque of the drive motor based on this deviation. Here, the required torque of the drive motor specifically refers to the required torque of the P3 / P4 drive motors.

[0077] Step 203: Based on the predicted fast torque parameters and the engine's maximum torque, select the target control strategy from the candidate control strategies and adopt the target control strategy to control the engine based on the predicted torque information.

[0078] The candidate control strategies are preset engine control strategies required under different driving conditions, including at least a fast / slow torque separation strategy and a fast / slow torque output strategy. The specific control methods for the engine differ under different control strategies. Specifically, when the engine's fast and slow torques are the same, the fast and slow torques decrease slowly, eliminating the need for fast / slow torque separation, and the fast / slow torque output strategy can be directly adopted. When the engine's fast and slow torques are inconsistent, the fast torque decreases rapidly while the slow torque decreases slowly, requiring fast / slow torque separation, and thus employing a fast / slow torque separation strategy.

[0079] Specifically, based on the predicted fast torque parameters and the engine's maximum torque, it is determined whether the fast and slow torques are consistent, and then the corresponding target control strategy is selected to precisely control the engine in the current cycle until the next cycle begins. At this point, the probability of surge is re-detected, and the engine control method in this embodiment is repeated.

[0080] Optionally, based on the predicted torque information, the target throttle opening and target ignition advance angle of the engine are determined; the engine is controlled to operate based on the target throttle opening and target ignition advance angle.

[0081] For example, the target throttle opening of the engine required to eliminate surge is determined based on the predicted slow torque parameters, and the target ignition advance angle of the engine required to meet power demand is determined based on the predicted fast torque parameters. Then, the throttle opening of the engine is controlled to the target throttle opening and the ignition advance angle is controlled to the target ignition advance angle in the current cycle, thereby completing the precise control of the engine in the current cycle.

[0082] In this application, if a surge probability is detected in the engine of a target vehicle, a torque pre-control model is used to predict the engine's torque information for the next moment based on the current torque information and historical torque information. The predicted torque information includes predicted slow torque parameters and predicted fast torque parameters. The torque information for the current moment is corrected based on the predicted fast torque parameters and the engine's required torque. A target control strategy is selected from candidate control strategies based on the predicted fast torque parameters and the engine's maximum torque, and this target control strategy is used to control the engine based on the predicted torque information. The technical solution provided in this application can predict the engine's fast and slow torque parameters for the next moment when a surge probability exists in the target vehicle's engine, thereby selecting a suitable target control strategy and controlling the engine based on the predicted fast and slow torque parameters. This eliminates surge energy, is compatible with energy recovery, effectively avoids surge, and performs closed-loop correction on the current torque information to prevent the target control strategy from affecting the total required torque, ensuring smooth vehicle power delivery.

[0083] Based on the above embodiments, in an exemplary embodiment, the torque pre-control model includes a slow torque pre-control model, see [link to example]. Figure 3 This illustrates the method for determining the predicted slow torque parameters in embodiments of this application, specifically including:

[0084] Step 301: Obtain the engine's slow torque-related parameters.

[0085] Among them, the slow torque related parameters include historical slow torque parameters, current slow torque parameters, and first related parameters. The first related parameters include the current throttle opening, wheel-side torque demand, compressor pressure ratio, intake air flow, ambient pressure, and ambient temperature.

[0086] Step 302: Input the slow torque related parameters into the slow torque pre-control model to obtain the predicted slow torque parameters for the next moment output by the slow torque pre-control model.

[0087] For example, such as Figure 4 The neural network architecture of the slow-torsion pre-control model is shown, which is implemented based on GRU. Where T... slow (tm), T slow (t-m+1), ..., until the implicit T slow (t-1), forming the historical slow torque parameters, which include the slow torque parameters of the first m historical moments, i.e., the slow torque; T slow (t) represents the slow torque parameter at the current moment; R throttle (t) represents the throttle opening at the current moment; T req (t) represents the wheel-side torque demand at the current moment; R compression (t) represents the compressor pressure ratio at the current moment; QEngIntake (t) represents the intake airflow rate at the current moment; P ambient T represents the environmental pressure at the current moment. ambient (t) represents the ambient temperature at the current moment; T slow (t+1) represents the slow torque parameter at the next moment, i.e., the predicted slow torque parameter.

[0088] The input layer of the slow-torsion pre-control model reads the normalized data and passes it to the hidden layer. The calculation results of each neuron in the hidden layer are represented as follows:

[0089]

[0090] Among them, g Hid Let x be the activation function of the hidden layer. in and y Hid These represent the outputs of each neuron in the input layer and the hidden layer, respectively. in That is, the q principal components of the input slow torque pre-control model, w Hid and b Hid The network weights of the hidden layer, 0 ≤ w Hid ≤1 and 0≤b Hid ≤1, where q is the number of neurons in the input layer.

[0091] Furthermore, the computational relationship from the hidden layer to the output layer can be represented as follows:

[0092]

[0093] Among them, g Out y is the activation function of the output layer. Out For the output of the output layer neurons, w Out and b Out The network weights of the hidden layer, 0 ≤ w Out ≤1 and 0≤b Out ≤1, where m is the number of neurons in the hidden layer.

[0094] The slow-torsion pre-control model based on GRU has hidden layer neurons with special gating structures, including update gates and reset gates. The update gate z∈[0,1] controls the balance between input and forgetting. Specifically:

[0095] z(t)=σ(w z y In (t)+u z y Hid (t-1)+b z );

[0096] Among them, w z u z and b zTo update the network weights of the gates in the hidden layer neurons, y Hid Characterizes the state of hidden layer neurons and stores nonlinear output information; when z = 0, y Hid (t) and y Hid (t-1) represents a nonlinear functional relationship; when z = 1, y Hid (t) and y Hid (t-1) represents a linear function relationship. That is, the closer the value of z is to 1, the stronger the y function. Hid (t) and y Hid The higher the degree of linear correlation between (t-1), the better.

[0097] Correspondingly, the reset gate r∈[0,1] controls the candidate state. Whether it depends on the state of the previous moment, specifically:

[0098] r(t)=σ(w r y In (t)+u r y Hid (t-1)+b r );

[0099]

[0100] Here, wr, ur, br and wh, uh, bh respectively define the network weights for resetting gates and updating candidate states in the hidden layer neurons. When r = 0, the state of the hidden layer neuron at the current time depends only on the current input and is independent of historical states. When r = 1, the state of the hidden layer neuron at the current time depends on both the current input and the state at the previous time. That is, the closer r is to 1, the higher the correlation between the state of the hidden layer neuron at the current time and historical states.

[0101] The state update method hidden as a neuron is as follows:

[0102]

[0103] Where y(t) is the state of the hidden layer neuron at the current time, z(t) is the input at the current time, and y(t-1) is the state of the hidden layer neuron at the previous time. This represents the candidate states of the hidden layer neurons at the current moment.

[0104] In this application, the accuracy of the predicted slow torque parameters at the next moment can be improved by using a slow torque pre-control model. Based on these predicted slow torque parameters, demand-based slow torque control can be achieved, which can eliminate surge by gradually closing the throttle. Specifically, by dynamically limiting the opening and closing speed of the throttle, the engine's slow torque is controlled, avoiding drastic changes in intake pressure and flow, thereby effectively preventing engine surge.

[0105] Based on the above embodiments, in an exemplary embodiment, the torque pre-control model includes a fast torque pre-control model, see [link to example]. Figure 5 This illustrates the method for determining the predicted fast torsion parameters in an embodiment of this application, specifically including:

[0106] Step 501: Obtain the engine's high-torque parameters.

[0107] Among them, the fast torque related parameters include historical fast torque parameters, current fast torque parameters, and second related parameters. The second related parameters include the current engine maximum torque, battery-related parameters, vehicle deceleration, and energy recovery power.

[0108] Step 502: Input the fast torque-related parameters into the fast torque pre-control model to obtain the predicted fast torque parameters for the next moment output by the fast torque pre-control model.

[0109] For example, such as Figure 6 The neural network architecture of the fast torque pre-control model is shown, which is implemented based on GRU. Where T... quick (tm), T quick (t-m+1), ..., until the implicit T quick (t-1), forming the historical fast torque parameters, which include the fast torque parameters of the first m historical moments, i.e., the fast torque; T quick (t) represents the fast torsion parameter at the current moment; T engLimit (t) represents the maximum engine torque at the current moment, i.e., the engine torque limit; SOCDiff(t) represents the current battery charge-related parameters, i.e., the difference between the actual SOC and the target SOC; a(t) represents the vehicle deceleration at the current moment; P recycle (t) represents the energy recovery power at the current moment; T quick (t+1) represents the fast torsion parameter at the next moment, i.e., the predicted fast torsion parameter.

[0110] The power generation corresponding to the current fast torque parameters needs to meet the power generation needs when the battery is too low, especially the need to prevent the battery from being overcharged and over-discharged when the battery is too low. These vehicle safety requirements constitute the constraints on the engine's fast torque, that is, the engine's power generation power < the battery's maximum recharge power - the drive motor's recharge power. The generator and engine are generally mechanically connected with a fixed speed ratio.

[0111]

[0112] Among them, T engLimit T is the engine's maximum torque. MCULimit P is the maximum torque of the generator. MCULimit P is the maximum charging power of the generator. battmax For the maximum power of battery recharge, P GCUmax For the energy recovery power of the drive motor, n MCU and n eng These are the rotational speeds of the generator and the engine, respectively, in μ. MCU This refers to the efficiency of the generator.

[0113] In this application, the accuracy of the predicted fast torque parameters can be improved by using a fast torque pre-control model to predict the parameters at the next moment. This allows for demand-based fast torque control, enabling energy recovery and power generation during braking or coasting. Specifically, if a driver suddenly increases the throttle before braking or coasting has fully ended, the throttle opening and closing speed, controlled based on predicted slow torque parameters to avoid engine surge, cannot simultaneously respond to the user's acceleration demand. However, the predicted fast torque parameters can quickly respond to the power demand; that is, slow torque eliminates surge energy, while fast torque accommodates energy recovery, power generation, and wheel-side power demands for coasting re-acceleration.

[0114] Based on the above embodiments, in an exemplary embodiment, if the predicted fast torque parameter is greater than the engine's maximum torque, then according to the predicted fast torque parameter and the current minimum torque, the corresponding fast and slow torque separation strategy is selected from the candidate control strategies as the target control strategy; if the predicted fast torque parameter is not greater than the engine's maximum torque, then the fast and slow torque output strategy is selected from the candidate control strategies as the target control strategy.

[0115] like Figure 7 The engine torque state diagram shown indicates that when the predicted fast torque parameter is not greater than the engine's maximum torque, the engine's fast and slow torques are consistent. At this time, the fast and slow torques are only limited by surge energy. The fast and slow torque output strategy is selected as the target control strategy, and the fast and slow torques decrease synchronously and slowly, directly controlling the engine's throttle opening and ignition advance angle.

[0116] When the predicted fast torque parameter is greater than the engine's maximum torque, the engine's fast and slow torques are inconsistent. In this case, fast and slow torque separation is required. A fast and slow torque separation strategy is selected as the target control strategy, where the slow torque decreases slowly and the fast torque decreases rapidly, thereby controlling the engine's throttle opening and ignition advance angle. This fast and slow torque separation strategy includes at least two different strategies. The applicable fast and slow torque separation strategy will differ depending on the inconsistency between the predicted fast torque parameter and the current minimum air-fuel ratio torque. The current minimum air-fuel ratio torque refers to the torque at the minimum ignition angle under the current air-fuel ratio. When the actual torque is lower than the current minimum air-fuel ratio torque, the engine cannot maintain normal combustion and fuel cut-off is necessary.

[0117] Optionally, if the predicted fast torque parameter is greater than the current minimum torque, the corresponding fast and slow torque separation strategy includes determining the change in fast torque parameter based on the predicted fast torque parameter and the fast torque parameter at the current moment, determining the corresponding ignition efficiency based on the change in fast torque parameter, and controlling the engine to reduce the ignition advance angle based on the ignition efficiency; if the predicted fast torque parameter is not greater than the current minimum torque, the corresponding fast and slow torque separation strategy includes controlling the engine to cut off fuel.

[0118] like Figure 8 The engine torque state diagram shown indicates that when the predicted fast torque parameter is greater than the current minimum torque, the engine can maintain normal combustion. The corresponding fast and slow torque separation strategy includes determining the change in fast torque parameter based on the predicted fast torque parameter and the fast torque parameter at the current moment, then determining the corresponding ignition efficiency based on the change in fast torque parameter, and finally controlling the engine to reduce the ignition advance angle corresponding to the ignition efficiency.

[0119] like Figure 9 The engine torque state diagram shown indicates that when the predicted fast torque parameter is not greater than the current minimum torque, the engine cannot maintain normal combustion. The corresponding fast and slow torque separation strategy includes first controlling the engine to cut off fuel until the fast torque is greater than the current minimum torque, then determining the change in the fast torque parameter, and then determining the corresponding ignition efficiency based on the change in the fast torque parameter, and finally controlling the engine to reduce the ignition advance angle corresponding to the ignition efficiency.

[0120] This application provides a strategy for precise engine control that can achieve a balanced control requirement where slow torque is responsible for addressing surge and fast torque is responsible for energy management. Through integrated control of power splitting and energy management, hybrid vehicles equipped with turbocharged engines can eliminate the pressure relief valve, thereby achieving cost reduction and efficiency improvement.

[0121] Based on the above embodiments, in an exemplary embodiment, the method for detecting the probability of surge specifically includes: determining the probability of engine surge based on the current operating condition information of the engine of the target vehicle; wherein, the current operating condition information includes the compressor pressure ratio and intake air flow at the current moment.

[0122] Optionally, a large amount of sample data from the engine is acquired, and the operating condition information under both surge and non-surge scenarios is statistically analyzed, recording the corresponding compressor pressure ratio and intake air flow rate. Surge probability information is then generated through correction analysis. This surge probability information can be stored in tabular form. Furthermore, when it is necessary to detect whether the engine has a surge probability in the current cycle, the compressor pressure ratio and intake air flow rate at the current moment can be retrieved from the surge probability information, and the corresponding results in the surge probability information are used as the result of whether the engine has a surge probability.

[0123] Optional, see Figure 10 This illustrates a method for determining the probability of surge occurrence in embodiments of this application, specifically including:

[0124] Step 1001: Substitute the compressor pressure ratio and intake flow rate at the current moment into the prediction function for calculation to obtain the corresponding function value.

[0125] The prediction function is obtained by fitting the calibration results based on the engine surge test.

[0126] It is understandable that there may not be a compressor pressure ratio and intake flow rate that perfectly match historical operating conditions. Based on surge tests, calibration is performed based on engine performance, and then a prediction function is obtained by fitting the calibration results. The prediction function is expressed as:

[0127] B surge =f(R) compression Q EngIntake );

[0128] Among them, B surge R is the function value. compression Q is the compressor pressure ratio. EngIntake This refers to the intake airflow.

[0129] Step 1002: If the function value satisfies the target condition, then determine the probability of engine surge.

[0130] For example, the prediction function has a value of 0 or 1, where a value of 0 indicates that there is no probability of engine surge, and a value of 1 indicates that there is a probability of engine surge. The target condition is a function value of 1.

[0131] Optionally, the range of the predictive function value is [0,1], and the target condition is that the function value reaches the preset target value. That is, the subsequent control method steps are only executed when the function value reaches the preset target value, including determining the predicted torque information for the next moment through the torque pre-control model.

[0132] In this application, the probability of engine surge is detected based on the engine's current operating condition information. It is possible to determine whether to adopt a target control strategy before surge occurs, thereby optimizing the engine control process.

[0133] To enable those skilled in the art to better understand this application as a whole, the application process of the solution in this application will be briefly described below with a specific embodiment:

[0134] See Figure 11 The diagram shows another flowchart of the engine control method in the embodiments of this application, which specifically includes a fast and slow torque prediction model (i.e., a torque pre-control model) based on a neural network and a fast and slow torque separation model.

[0135] Among them, the vehicle power constraint is determined based on the battery power constraint, motor power constraint and engine power constraint, and the vehicle power is obtained by combining the driver's required torque. Energy management power is then performed, namely the PI (engine and generator) required torque and the P3 / P4 drive motor required torque.

[0136] Based on the PI (engine and generator) torque demand, engine intake airflow, engine speed, and engine pressure ratio are obtained to predict engine surge. If no surge is predicted, the engine operates normally, outputting the engine throttle opening and ignition angle. If surge is predicted, slow torque is predicted using a neural network (slow torque pre-control model), and fast torque is predicted using a neural network (fast torque pre-control model). The fast torque prediction also requires determining the engine's allowable power based on vehicle constraints (battery allowable power and current motor power).

[0137] Combining the estimated slow torque and estimated fast torque results, a fast / slow torque determination is performed. This involves identifying the corrected fast torque, then performing a closed-loop correction on the torque demand of the P3 / P4 drive motors, and determining whether fast / slow torque separation is necessary. Specifically, if fast / slow torque separation is performed, the slow torque decreases slowly, while the fast torque decreases rapidly, with the fast torque corresponding to the engine's ignition de-angle or fuel cut-off slow torque output. If fast / slow torque separation is not performed, the fast and slow torque decrease slowly, and both are output simultaneously. The final output determines the engine throttle opening and ignition angle.

[0138] In this application, when the engine of the target vehicle has a probability of surge, the torque pre-control model predicts the engine's fast and slow torque parameters at the next moment, and then selects an appropriate target control strategy. Based on the predicted fast and slow torque parameters, the engine is controlled to eliminate surge energy, integrate energy recovery, effectively avoid surge, and perform closed-loop correction on the current torque information to avoid the target control strategy affecting the total torque demand, thus ensuring smooth power delivery of the entire vehicle.

[0139] The following describes an embodiment of the apparatus described in this application, which can be used to execute the engine control method described in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the engine control method described above.

[0140] See Figure 12 The diagram shows a block diagram of the engine control device 1200 in an embodiment of this application, which specifically includes:

[0141] The torque prediction module 1201 is used to predict the engine's torque information at the next moment based on the current torque information and historical torque information if the probability of engine surge in the target vehicle is detected. The predicted torque information includes predicted slow torque parameters and predicted fast torque parameters.

[0142] The torque correction module 1202 is used to correct the torque information at the current moment based on the predicted fast torque parameters and the engine's required torque.

[0143] The engine control module 1203 is used to select a target control strategy from candidate control strategies based on the predicted fast torque parameters and the engine's maximum torque, and to use the target control strategy to control the engine based on the predicted torque information.

[0144] In an exemplary embodiment, based on the above embodiments, the torque prediction model includes a slow torque prediction model, and the torque prediction module 1201 includes:

[0145] The slow torque parameter acquisition unit is used to acquire the engine's slow torque related parameters; among which, the slow torque related parameters include historical slow torque parameters, current slow torque parameters, and first related parameters, the first related parameters include the current throttle opening, wheel-side torque demand, compressor pressure ratio, intake air flow, ambient pressure, and ambient temperature;

[0146] The slow torque prediction unit is used to input slow torque-related parameters into the slow torque pre-control model to obtain the predicted slow torque parameters for the next moment output by the slow torque pre-control model.

[0147] In an exemplary embodiment, based on the above embodiments, the torque prediction model includes a fast torque prediction model, and the torque prediction module 1201 includes:

[0148] The fast torque parameter acquisition unit is used to acquire the fast torque related parameters of the engine; among which, the fast torque related parameters include historical fast torque parameters, the fast torque parameters at the current moment, and second related parameters. The second related parameters include the engine's maximum torque at the current moment, battery-related parameters, vehicle deceleration, and energy recovery power.

[0149] The fast torque prediction unit is used to input fast torque-related parameters into the fast torque pre-control model to obtain the predicted fast torque parameters for the next moment output by the fast torque pre-control model.

[0150] In one exemplary embodiment, based on the above embodiments, the engine control module 1203 includes:

[0151] The separation strategy determination unit is used to select the corresponding fast and slow torque separation strategy from the candidate control strategies as the target control strategy if the predicted fast torque parameter is greater than the engine's maximum torque, based on the predicted fast torque parameter and the current minimum torque of the gas volume.

[0152] The output strategy determination unit is used to select the fast and slow torque output strategy from the candidate control strategies as the target control strategy if the predicted fast torque parameter is not greater than the engine's maximum torque.

[0153] In an exemplary embodiment, based on the above embodiments, the separation strategy determination unit includes:

[0154] The first separation strategy determines the sub-unit, which is used to determine the change in fast torque parameters based on the predicted fast torque parameters and the fast torque parameters at the current time, determine the corresponding ignition efficiency based on the change in fast torque parameters, and control the engine to reduce the ignition advance angle based on the ignition efficiency if the predicted fast torque parameters are greater than the current minimum torque.

[0155] The second separation strategy determines the sub-unit, which is used to determine the fast and slow torque separation strategy if the predicted fast torque parameter is not greater than the current minimum torque. This strategy includes controlling the engine fuel cut-off.

[0156] In one exemplary embodiment, based on the above embodiments, the engine control module 1203 includes:

[0157] The control quantity determination unit is used to determine the target throttle opening and target ignition advance angle of the engine based on the predicted torque information.

[0158] The engine control unit is used to control the engine to operate based on the target throttle opening and target ignition advance angle.

[0159] In an exemplary embodiment, based on the above embodiments, the torque correction module 1202 includes:

[0160] The deviation determination unit is used to determine the deviation of the required torque based on the predicted fast torque parameters and the engine's required torque.

[0161] The torque correction unit is used to correct the required torque of the drive motor based on the deviation of the required torque.

[0162] In one exemplary embodiment, based on the above embodiments, the engine control device 1200 further includes:

[0163] The surge prediction module is used to determine the probability of engine surge based on the current operating condition information of the target vehicle's engine; the current operating condition information includes the compressor pressure ratio and intake air flow at the current moment.

[0164] In an exemplary embodiment, based on the above embodiments, the surge prediction module includes:

[0165] The function value determination unit is used to substitute the compressor pressure ratio and intake flow rate at the current moment into the prediction function for calculation to obtain the corresponding function value; wherein, the prediction function is obtained by fitting the calibration results based on the engine surge test.

[0166] The surge prediction unit is used to determine the probability of engine surge if the function value meets the target condition.

[0167] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing computer program instructions. When the computer program instructions are loaded and executed by a processor, they implement the steps of the engine control method described above.

[0168] Based on the same inventive concept, this application provides an electronic device, see [link to relevant documentation]. Figure 13 The diagram shows a schematic of the structure of an electronic device in an embodiment of this application. The electronic device includes one or more memories 1304, one or more processors 1302, and at least one computer program stored in the memory 1304 and executable on the processor 1302. When the processor 1302 executes the computer program, it implements the steps of the engine control method described above.

[0169] The bus architecture (represented by bus 1300) may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 1302 and memory represented by memory 1304. Bus 1300 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 1305 provides an interface between bus 1300 and receiver 1301 and transmitter 1303. Receiver 1301 and transmitter 1303 may be the same element, a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 1302 is responsible for managing bus 1300 and general processing, while memory 1304 can be used to store data used by processor 1302 during operation.

[0170] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this application and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0171] Based on the same inventive concept, this application provides a vehicle including an engine, wherein the steps of the engine control method described above are implemented when the engine is controlled.

[0172] Based on the same inventive concept, this application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the engine control method described above.

[0173] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0174] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0175] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing computer program instructions, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0176] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An engine control method, characterized in that, The method includes: If a surge probability is detected in the engine of the target vehicle, the torque prediction model is used to predict the engine's torque information at the next moment based on the current torque information and historical torque information; wherein, the predicted torque information includes predicted slow torque parameters and predicted fast torque parameters. Based on the predicted fast torque parameters and the engine's required torque, the torque information at the current moment is corrected; Based on the predicted fast torque parameters and the engine's maximum torque, a target control strategy is selected from the candidate control strategies, and the target control strategy is adopted to control the engine based on the predicted torque information.

2. The method according to claim 1, characterized in that, The torque pre-control model includes a slow torque pre-control model. The method of predicting the engine's torque information at the next moment based on the current torque information and historical torque information using the torque pre-control model includes: Obtain the slow torque related parameters of the engine; wherein, the slow torque related parameters include historical slow torque parameters, current slow torque parameters and first related parameters, the first related parameters including the current throttle opening, wheel-side torque demand, compressor pressure ratio, intake air flow, ambient pressure and ambient temperature; The slow torque-related parameters are input into the slow torque pre-control model to obtain the predicted slow torque parameters for the next moment output by the slow torque pre-control model.

3. The method according to claim 1, characterized in that, The torque pre-control model includes a fast torque pre-control model. The process of predicting the engine's torque information for the next moment based on the current torque information and historical torque information using the torque pre-control model includes: Obtain the fast torque related parameters of the engine; wherein, the fast torque related parameters include historical fast torque parameters, current fast torque parameters, and a second related parameter, the second related parameter including the current engine maximum torque, battery-related parameters, vehicle deceleration, and energy recovery power; The fast torque-related parameters are input into the fast torque pre-control model to obtain the predicted fast torque parameters for the next moment output by the fast torque pre-control model.

4. The method according to claim 1, characterized in that, The step of selecting a target control strategy from candidate control strategies based on the predicted torque information and the engine's maximum torque includes: If the predicted fast torque parameter is greater than the engine's maximum torque, then based on the predicted fast torque parameter and the current minimum torque, the corresponding fast and slow torque separation strategy is selected from the candidate control strategies as the target control strategy. If the predicted fast torque parameter is not greater than the engine's maximum torque, then the fast and slow torque output strategy is selected from the candidate control strategies as the target control strategy.

5. The method according to claim 4, characterized in that, The step of selecting a corresponding fast / slow torque separation strategy from candidate control strategies as the target control strategy based on the predicted fast torque parameters and the current minimum torque of the gas volume includes: If the predicted fast torque parameter is greater than the current minimum torque, the corresponding fast and slow torque separation strategy includes determining the change in fast torque parameter based on the predicted fast torque parameter and the fast torque parameter at the current moment, determining the corresponding ignition efficiency based on the change in fast torque parameter, and controlling the engine to reduce the ignition advance angle based on the ignition efficiency. If the predicted fast torque parameter is not greater than the current minimum torque, the corresponding fast and slow torque separation strategy includes controlling the engine to cut off fuel.

6. The method according to claim 4 or 5, characterized in that, The step of using the target control strategy to control the engine based on the predicted torque information includes: Based on the predicted torque information, the target throttle opening and target ignition advance angle of the engine are determined; The engine is controlled to operate based on the target throttle opening and the target ignition advance angle.

7. The method according to claim 1 or 5, characterized in that, The step of correcting the torque information at the current moment based on the predicted fast torque parameters and the engine's required torque includes: Based on the predicted fast torque parameters and the engine's required torque, the required torque deviation is determined; The required torque of the drive motor is corrected based on the required torque deviation.

8. The method according to claim 1, characterized in that, The detected probability of engine surge in the target vehicle includes: Based on the current operating condition information of the target vehicle's engine, the probability of surge in the engine is determined; wherein, the current operating condition information includes the compressor pressure ratio and intake air flow rate at the current moment.

9. The method according to claim 8, characterized in that, The step of determining the probability of engine surge based on the current operating condition information of the target vehicle's engine includes: The compressor pressure ratio and intake flow rate at the current moment are substituted into the prediction function for calculation to obtain the corresponding function value; wherein, the prediction function is obtained by fitting the calibration results of the engine surge test; If the function value satisfies the target condition, then it is determined that there is a probability of surge occurring in the engine.

10. An engine control device, characterized in that, The device includes: The torque prediction module is used to predict the engine's torque information at the next moment based on the current torque information and historical torque information if a surge probability is detected in the target vehicle's engine. The predicted torque information includes predicted slow torque parameters and predicted fast torque parameters. The torque correction module is used to correct the torque information at the current moment based on the predicted fast torque parameters and the engine's required torque. An engine control module is used to select a target control strategy from candidate control strategies based on the predicted fast torque parameters and the engine's maximum torque, and to control the engine based on the predicted torque information using the target control strategy.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which are loaded and executed by a processor to perform the operations performed by the method as described in any one of claims 1 to 9.

12. An electronic device comprising a processor and a memory, characterized in that, The memory stores computer program instructions that can be executed by the processor, and when the processor executes the computer program instructions, it implements the instructions of the method as described in any one of claims 1 to 9.

13. A vehicle, comprising an engine, characterized in that, When controlling the engine, the method described in any one of claims 1 to 9 is employed.

Images