Vehicle thermal management control method and device, electronic equipment, storage medium and vehicle

Abstract

The application provides a vehicle thermal management control method and device, electronic equipment, storage medium and vehicle. The method comprises the following steps: obtaining the running condition of the vehicle; determining the control target, the target state and the current state of the control target according to the running condition; iteratively selecting the control quantity according to a predetermined algorithm; determining the predicted state of the control target by using a pre-constructed model predictive controller according to the current state of the control target and the selected control quantity; and taking the corresponding control quantity as the target control quantity of the current control time domain when the predicted state reaches the target state. The application is based on the pre-established model predictive controller suitable for the thermal management system, and the target control quantity of the system is determined by using the model predictive controller, so that the operation efficiency of the thermal management system can be ensured, and the thermal management demand under different conditions can be met.

Description

Technical Field

[0001] This application relates to the field of new energy vehicle technology, and in particular to a vehicle thermal management control method, device, electronic equipment, storage medium, and vehicle. Background Technology

[0002] In the field of new energy vehicles, the performance of the vehicle's thermal management system directly affects the vehicle's range and overall operating performance. Existing vehicle thermal management systems generally design separate thermal management subsystems for each heat-generating subsystem, with these subsystems coupled through heat exchangers. PID (proportional integration differentiation) feedback control is used to control these subsystems. However, because the thermal management system is a highly nonlinear thermodynamic system, there are thermodynamic coupling relationships between the various heat-generating subsystems. The PID control of each subsystem also needs to coordinate with each other. A single PID control parameter is insufficient to effectively control the entire thermal management system, easily leading to oscillations and control instability. Furthermore, composite PID control methods make system control exceptionally complex. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a vehicle thermal management control method, device, electronic device, storage medium and vehicle.

[0004] To achieve the above objectives, this application provides a vehicle thermal management control method, comprising:

[0005] Obtain the vehicle's operating status;

[0006] Based on the operating conditions, determine the control target and the target state and current state of the control target;

[0007] The control quantity is iteratively selected according to a predetermined algorithm. Based on the current state of the control target and the control quantity selected this time, the predicted state of the control target is determined by a pre-built model predictive controller.

[0008] When the predicted state reaches the target state, the corresponding control quantity is used as the target control quantity in the current control time domain.

[0009] Optionally, there may be multiple control objectives, each with a different priority;

[0010] Based on the current state of the control objective and the selected control variable, the predicted state of the control objective is determined using a pre-built model predictive controller, including:

[0011] Based on the current state of the high-priority control objective and the selected control variable, the model predictive controller determines the predicted state of the high-priority control objective.

[0012] Optionally, there are multiple high-priority control targets, and each control target has a different weight value;

[0013] When the predicted state reaches the target state, the corresponding control quantity is used as the target control quantity in the current control time domain, including:

[0014] When the predicted state of each high-priority control objective reaches the target state, the corresponding control quantity is used as the reference control quantity for the corresponding control objective in the current control time domain.

[0015] The target control quantity is determined based on the reference control quantity and corresponding weight value of each high-priority control objective.

[0016] Optionally, after determining the control target and its target state and current state, the method further includes:

[0017] In response to the difference between the current state and the target state being greater than a preset adjustment threshold, multiple control time domains required to adjust the current state to the target state, and the target state of each control time domain, are determined based on the difference.

[0018] Based on the current state and the target state of each control time domain, a state change curve for each control time domain is determined according to a preset state change rate; the state change curve is a curve formed by the state at each time point within the control time domain.

[0019] The control variable is iteratively selected according to a predetermined algorithm. Based on the current state of the control target and the selected control variable, the predicted state of the control target is determined using a pre-built model predictive controller, including:

[0020] Based on the target state of each control time domain, for each control time domain, a control quantity is iteratively selected according to a predetermined algorithm. Based on the current state of the control target and the selected control quantity, the predicted state of the control target is determined using the model predictive controller.

[0021] When the predicted state reaches the target state, the corresponding control quantity is used as the target control quantity in the current control time domain, including:

[0022] When the predicted state matches the state change curve, the corresponding control quantity is used as the target control quantity in the corresponding control time domain.

[0023] Optionally, when the predicted state matches the state change curve, the corresponding control quantity is used as the target control quantity in the corresponding control time domain, including:

[0024] Calculate the state difference between the predicted state at each time point in the control time domain and the state at the corresponding time point on the state change curve;

[0025] The control quantity corresponding to the minimum sum of state differences at each time point is taken as the target control quantity.

[0026] Optionally, after setting the corresponding control quantity as the target control quantity in the current control time domain when the predicted state reaches the target state, the method further includes:

[0027] After outputting the target control quantity to the thermal management system, the actual state fed back by the thermal management system is obtained; the actual state is the actual state after the thermal management system executes according to the target control quantity.

[0028] Based on the actual state, determine the feedback adjustment amount;

[0029] Based on the feedback adjustment, the target control quantity of the model predictive controller is corrected in the next control time domain.

[0030] Optionally, there are multiple sets of target control quantities in the current control time domain; after taking the corresponding control quantity as the target control quantity in the current control time domain when the predicted state reaches the target state, the system further includes:

[0031] At each preset time interval, a set of target control variables is output to the thermal management system from multiple sets of target control variables;

[0032] Based on the computation time and the output time required to output multiple sets of target control quantities to the thermal management system, the calling time for obtaining multiple sets of target control quantities in the next control time domain is determined; the computation time is the time required for the model predictive controller to determine the predicted state based on the current state and the control quantities selected in the iteration, and to determine multiple sets of target control quantities based on the predicted state and the target state.

[0033] Starting with the output of the first set of target control quantities from the multiple sets of target control quantities in the current control time domain to the thermal management system, the multiple sets of target control quantities in the next control time domain are obtained every time the calling time is reached.

[0034] Based on the time interval and the calculation time, determine the number of target control quantity groups output within the calculation time.

[0035] Based on the number of target control quantities output within the calculation time, determine the first set of target control quantities output to the thermal management system from the multiple sets of target control quantities in the next control time domain.

[0036] At each time interval, a set of target control variables is output to the thermal management system, starting from the first set of target control variables.

[0037] This application also provides a vehicle thermal management control device, including:

[0038] The acquisition module is used to acquire the vehicle's operating conditions;

[0039] The target determination module is used to determine the control target, the target state, and the current state of the control target based on the operating conditions.

[0040] The model prediction module is used to iteratively select control variables according to a predetermined algorithm. Based on the current state of the control target and the selected control variable, the module uses a pre-built model prediction controller to determine the predicted state of the control target. When the predicted state reaches the target state, the corresponding control variable is used as the target control variable in the current control time domain.

[0041] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the vehicle thermal management control method when executing the program.

[0042] This application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the vehicle thermal management control method.

[0043] This application also provides a vehicle including the aforementioned electronic device.

[0044] As can be seen from the above, the vehicle thermal management control method, device, electronic equipment, storage medium, and vehicle provided in this application acquire the vehicle's operating conditions, determine the control objective, target state, and current state of the control objective based on the operating conditions, and determine the predicted state of the control objective using a pre-built model predictive controller based on the current state of the control objective and the iteratively selected control quantity. When the predicted state reaches the target state, the corresponding control quantity is used as the target control quantity in the current control time domain. Since the subsystems in the vehicle's thermal management system have complex coupling relationships, this application, by establishing a model predictive controller to predict the control quantity of the thermal management system, is more suitable for nonlinear vehicle thermal management systems. Based on a pre-built model predictive controller suitable for the thermal management system, this application uses the model predictive controller to determine the system's target control quantity, ensuring the operational efficiency of the thermal management system and meeting the thermal management requirements under different operating conditions. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the method flow of an embodiment of this application;

[0046] Figure 2 This is a schematic diagram of a method flow according to another embodiment of this application;

[0047] Figure 3 This is a schematic diagram of a method for adjusting the target state into a state change curve according to an embodiment of this application;

[0048] Figure 4 This is a schematic flowchart of the feedback control method according to an embodiment of this application;

[0049] Figure 5 This is a schematic flowchart of the optimized control method according to an embodiment of this application;

[0050] Figure 6 This is a simplified block diagram of the thermal management system model of a range-extended vehicle according to an embodiment of this application;

[0051] Figure 7 This is a block diagram of the device structure of one or more embodiments of this specification;

[0052] Figure 8 This is a block diagram of an electronic device structure for one or more embodiments of this specification. Detailed Implementation

[0053] To better understand the above-mentioned objectives, features, and advantages of this application, the solution of this application will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0054] Many specific details are set forth in the following description in order to provide a full understanding of this application, but this application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some embodiments of this application, and not all embodiments.

[0055] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the term "comprising" or any other variations thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0056] In related technologies, a vehicle's thermal management system includes heating components and execution components. Through the coordinated work of these components, it provides heating or cooling to the vehicle's passenger compartment, battery, and other components, meeting the vehicle's thermal management needs and ensuring optimal vehicle performance. However, because the thermal management system is a nonlinear system with coupling relationships between its subsystems, controlling it using PID control methods is difficult to achieve satisfactory control results. Given the complex and varied operating conditions of vehicles, with different thermal management requirements and control objectives for each component under different conditions, some methods pre-configure the control quantities for each component under various operating conditions through experimental calibration. When the vehicle operates under a certain condition, the corresponding control quantity is output to the thermal management system, enabling the thermal management system to operate under that condition. However, in actual operation, influenced by various factors such as the external environment and component performance, operating the thermal management system based on pre-configured control quantities is unlikely to achieve optimal operating efficiency and performance. Furthermore, some operating conditions are difficult to simulate experimentally, making it difficult to determine the corresponding control quantities.

[0057] In view of this, embodiments of this application provide a vehicle thermal management control method. A model predictive controller is pre-built based on the thermal management system. The control objective to be adjusted and the target state of the control objective are determined according to the vehicle's operating conditions. Different control quantities are iteratively selected. The current state of the control objective and the selected control quantities are used as inputs to the model predictive controller. The model predictive controller outputs a predicted state. When the obtained predicted state reaches the target state, the corresponding control quantity is the system's target control quantity. Controlling the thermal management system according to the target control quantity enables the thermal management system to reach its optimal operating state, ensuring good vehicle performance.

[0058] like Figure 1 , 2 As shown in the figure, this application provides a vehicle thermal management control method, including:

[0059] S101: Obtain the vehicle's operating status;

[0060] In this embodiment, the vehicle's operating conditions are first obtained through the vehicle controller or sensors. For example, the engine starting condition is determined based on the engine's starting status, the battery charging condition is determined based on the battery's charging status, and the operating conditions of the passenger compartment air conditioning being on when the engine is not running, or the operating conditions of the engine and air conditioning being on simultaneously, are determined based on the engine starting status and the air conditioning starting status, etc. There are various types of vehicle operating conditions, and this embodiment will not provide examples for each one.

[0061] S102: Determine the control objective and its target state and current state based on the operating conditions;

[0062] In this embodiment, based on the operating conditions, the control objectives to be adjusted and their target states are determined, and the current state is obtained. The control objective is the controlled object in the thermal management system, and the target state is the state that the object is to achieve. For example, the control objective includes battery temperature, the inlet and / or outlet temperature of the water heater, engine temperature, energy consumption, and safety thresholds for heating and actuating components. The target state includes maintaining the battery temperature within a certain temperature range, ensuring energy consumption does not exceed a certain energy consumption threshold, and requiring heating and actuating components to operate within safety thresholds. The current state of the control objective is the current battery temperature value, energy consumption value, etc.

[0063] In some methods, different operating conditions correspond to different control objectives and target states. For example, when the engine is running, the control objectives include battery temperature, engine temperature, and heater inlet temperature. When the engine is running and the passenger compartment air conditioning is on, the control objectives include battery temperature, engine temperature, heater inlet temperature, energy consumption, and heater safety threshold. The specific control objectives and target states corresponding to each operating condition will not be listed one by one.

[0064] S103: Select control variables iteratively according to a predetermined algorithm, and determine the predicted state of the control target using a pre-built model predictive controller based on the current state of the control target and the selected control variables.

[0065] S104: When the predicted state reaches the target state, the corresponding control quantity is used as the target control quantity in the current control time domain.

[0066] In this embodiment, a model predictive controller is pre-built based on the thermal management system. A predetermined iterative algorithm is used to select control variables. The model predictive controller determines the predicted state based on the current state of the system and the selected control variables. During the iteration process, when the predicted state reaches the target state, the corresponding control variable is used as the target control variable and output to the system. The system controls the various components to work collaboratively according to the target control variable, ensuring the system operates at optimal efficiency. Because the subsystems in the vehicle's thermal management system have complex coupling relationships, the model predictive controller established in this application is more suitable for nonlinear thermal management systems. This application utilizes a model predictive controller to determine the system's target control variable, ensuring the operational efficiency of the thermal management system and meeting the thermal management requirements under different operating conditions.

[0067] Combination Figure 1 , 2As shown, the thermal management control method provided in this embodiment is applied to the thermal management system of a vehicle. Step S201: First, obtain the vehicle's operating conditions. Step S202: Based on the operating conditions, determine one or more control targets to be adjusted and the target states of each control target. Step S203: Use a solver to select the control quantity of the thermal management system according to a predetermined algorithm. Step S204: Collect the current state of each control target from the vehicle's thermal management system. Step S205: Use the current state and the currently selected control quantity as input to the model predictive controller, and output the predicted state of the control target. Step S206: Determine whether the predicted state output this time has reached the target state. If it has, output the currently selected control quantity as the target control quantity to the thermal management system, so that the thermal management system controls each component to work collaboratively according to the target control quantity. If it has not reached the target state, reselect the control quantity, and use the reselected control quantity and the current state to output the predicted state using the model predictive controller. Repeat the above process until the predicted state reaches the target state and the target control quantity is determined.

[0068] In some embodiments, there are multiple control objectives, each with a different priority;

[0069] Based on the current state of the control objective and the selected control variable, the predicted state of the control objective is determined using a pre-built model predictive controller, including:

[0070] Based on the current state of the high-priority control objective and the selected control variable, the predicted state of the high-priority control objective is determined using a model predictive controller.

[0071] In this embodiment, there are multiple control objectives under the current operating condition, with different priorities. A control variable is selected according to a predetermined algorithm. The current state of the high-priority control objective and the selected control variable are used as inputs to the model predictive controller (MMC). The MMC outputs the predicted state of the corresponding control objective. If the predicted state does not reach the target state, a new control variable is selected, and the MMC re-determines the predicted state. This process of selecting the control variable and making predictions is repeated until the predicted state obtained based on the current state and the selected control variable reaches the target state of the high-priority control objective. The control variable that reaches the target state is then used as the target control variable for the thermal management system. The thermal management system controls the actions of each component based on the target control variable, adjusting the current state of the high-priority control objective to the desired target state.

[0072] In some methods, the priority of each control objective can be divided into at least two categories, such as high priority and low priority, or first priority, second priority, and so on up to Nth priority. The method of priority division can be determined according to the usage scenario and actual needs of the thermal management system, and the specific division method is not limited. For multiple control objectives under specific operating conditions, the priorities of each control objective may be different or partially the same. For example, under the condition of heater startup, the control objectives include heater temperature and crew cabin temperature. The target state of heater temperature is to reach the operating temperature while being less than the maximum temperature threshold, and the target state of crew cabin temperature is to reach the regulated target temperature. Considering system safety, heater temperature has high priority, while crew cabin temperature has low priority.

[0073] In some embodiments, there are multiple high-priority control objectives, and each control objective has a different weight value;

[0074] When the predicted state reaches the target state, the corresponding control quantity is used as the target control quantity in the current control time domain, including:

[0075] When the predicted state of each high-priority control objective reaches the target state, the corresponding control quantity is used as the reference control quantity for the corresponding control objective in the current control time domain.

[0076] The target control quantity is determined based on the reference control quantity and corresponding weight value of each high-priority control objective.

[0077] In this embodiment, when there are multiple high-priority control objectives, and each control objective has a different weight value, the control quantity of each high-priority control objective can be comprehensively considered to ultimately determine a target control quantity that balances all control objectives. Specifically, for each high-priority control objective, the current state of the control objective and the iteratively selected control quantity are used as inputs to the model predictive controller. The model predictive controller determines the target control quantity that can achieve the target state of the control objective. The determined target control quantity of each high-priority control objective is used as a reference control quantity. Based on the reference control quantity and corresponding weight value of each control objective, the final target control quantity is determined. In this way, the determined target control quantity comprehensively considers the target control quantity and importance of each high-priority control objective. Under the control of the target control quantity, the states of multiple high-priority control objectives can be adjusted to a more balanced optimal state. Optionally, when calculating the final target control quantity, a weighted sum can be performed based on the reference control quantity and corresponding weight value of each control objective, and the final target control quantity is determined based on the weighted sum result.

[0078] In other embodiments, the most important control objective, i.e. the high-priority control objective with the largest weight value, can be given priority. Based on this control objective, the current state of the control objective and the control quantity selected in the iteration are used as the input of the model predictive controller, which predicts the predicted state of the control objective. During the iteration process, when the predicted state of the model predictive controller reaches the target state of the control objective under a specific control quantity, the control quantity is determined as the target control quantity of the thermal management system. Based on the control of the target control quantity, the model predictive controller can predict the target state of the high-priority control objective with the largest weight value.

[0079] In some embodiments, when there are multiple high-priority control objectives, and each control objective has the same set weight value, the target control quantity of each high-priority control objective can be comprehensively considered to ultimately determine a target control quantity that can balance the various control objectives. Specifically, for each high-priority control objective, the current state of the control objective and the iteratively selected control quantity are used as inputs to the model predictive controller. The model predictive controller determines the target control quantity that can achieve the target state of the control objective. The determined target control quantity of each high-priority control objective is used as a reference control quantity. The average control quantity is calculated based on the reference control quantity of each control objective, and this average control quantity is used as the final target control quantity. The determined target control quantity comprehensively considers the target control quantities of each high-priority control objective. Under the control of the target control quantity, the states of multiple high-priority control objectives can be adjusted to a more balanced optimal state.

[0080] like Figure 3 As shown, in some embodiments, after determining the control target and its target state and current state, the method further includes:

[0081] S301: In response to the difference between the current state and the target state being greater than a preset adjustment threshold, determine multiple control time domains required to adjust the current state to the target state, and the target state of each control time domain, based on the difference.

[0082] S302: Based on the current state and the target state of each control time domain, determine the state change curve for each control time domain according to the preset state change rate; the state change curve is the curve formed by the state at each time point within the control time domain.

[0083] S303: Based on the target state of each control time domain, for each control time domain, the control quantity is iteratively selected according to a predetermined algorithm. Based on the current state of the control target and the selected control quantity, the predicted state of the control target is determined using a model predictive controller.

[0084] S304: When the predicted state matches the state change curve, the corresponding control quantity is used as the target control quantity in the corresponding control time domain.

[0085] In this embodiment, under different operating conditions, the target state of the control objective is generally an ideal state that can meet the thermal management requirements under that operating condition. However, in some cases, it is difficult to adjust the current state of the control objective to the ideal target state within a control time domain. For example, when the vehicle is in a low-temperature environment and the battery is heating up, the target state of the battery heating is a temperature of 20 degrees Celsius, while the current temperature of the battery is 0 degrees Celsius. Within the control time domain of the predictive model controller (e.g., 120 seconds), it is difficult to adjust the current state to the target state by selecting a control variable.

[0086] To address the aforementioned issues, after determining the target state of the control objective and acquiring its current state, the difference between the target state and the current state is calculated. If this difference exceeds an adjustment threshold, it is determined that the current state cannot be adjusted to the target state within a single control time domain. In this case, based on the difference, multiple control time domains required to adjust from the current state to the target state, and the target state to be achieved in each control time domain, are determined. Based on the current state and the target states of each control time domain, a state change curve for each control time domain is determined. Then, for each control time domain, a predetermined algorithm iteratively selects a control quantity. Based on the real-time acquired current state of the control objective and the selected control quantity, a model predictive controller determines the predicted state of the control objective. When the predicted state matches the state change curve, the corresponding control quantity is used as the target control quantity. In this way, considering the actual vehicle conditions, the target state of the control objective is readjusted into state change curves across multiple control time domains, ensuring that the state of high-priority control objectives can be adjusted to an optimal state within each control time domain.

[0087] In some embodiments, the method for determining a state change curve in a control time domain is to determine the state at each time point in the control time domain from the current state acquired in real time to the target state in the control time domain according to the state change rate, and then form a state change curve from the current state to the target state in the control time domain based on the states at all time points. For example, if the target battery temperature is 10 degrees Celsius, the current temperature is 0 degrees Celsius, the rate of change of battery temperature is 1 degree Celsius, one control time domain is 5 seconds, and the control step size is 1 second, then on the state change curve of the first control time domain, the temperature corresponding to the 1st second is 0 degrees Celsius, the temperature corresponding to the 2nd second is 1 degree Celsius, the temperature corresponding to the 3rd second is 2 degrees Celsius, the temperature corresponding to the 4th second is 3 degrees Celsius, and the temperature corresponding to the 5th second is 4 degrees Celsius. In the second control time domain, if the current temperature is 4 degrees Celsius, then on the state change curve of the second control time domain, the temperature corresponding to the 1st second is 4 degrees Celsius, the temperature corresponding to the 2nd second is 5 degrees Celsius, the temperature corresponding to the 3rd second is 6 degrees Celsius, the temperature corresponding to the 4th second is 7 degrees Celsius, and the temperature corresponding to the 5th second is 8 degrees Celsius. In the third control time domain, if the current temperature is 8 degrees Celsius, then on the state change curve of the third control time domain, the temperature corresponding to the 1st second is 8 degrees Celsius, the temperature corresponding to the 2nd second is 9 degrees Celsius, the temperature corresponding to the 3rd second is 10 degrees Celsius, the target temperature has been reached, and the temperature corresponding to the 4th and 5th seconds remains at 10 degrees Celsius.

[0088] In some embodiments, when the predicted state matches the state change curve, the corresponding control quantity is used as the target control quantity in the corresponding control time domain, including:

[0089] Calculate the state difference between the predicted state at each time point in the control time domain and the state at the corresponding time point on the state change curve;

[0090] The control variable corresponding to the minimum sum of state differences at each time point is taken as the target control variable.

[0091] In this embodiment, after determining a state change curve in the control time domain, when using a model predictive controller to determine the target control quantity, for each control quantity selected iteratively, the model predictive controller outputs a corresponding predicted state. The predicted state at each time point in the control time domain is compared with the state at the corresponding time point on the state change curve, and the state difference between the two is calculated. Then, the state differences at each time point are summed to obtain the sum of the state differences corresponding to the currently selected control quantity. During the iteration of the control quantity, the sum of the state differences corresponding to the previously selected control quantity and the currently selected control quantity is compared. The control quantity with the smaller sum of state differences is retained. When the iteration termination condition is met, the iteration stops, and the control quantity corresponding to the smallest sum of state differences is selected as the final target control quantity. The magnitude of the sum of state differences can evaluate the difference between the predicted state and the corresponding state on the state change curve. The larger the value, the more the predicted state deviates from the corresponding state on the curve; the smaller the value, the closer the predicted state is to the corresponding state on the curve.

[0092] Optionally, multiple sets of control variables can be selected based on differential evolution algorithms or genetic algorithms. The specific algorithm principles for selecting control variables will not be explained in detail.

[0093] like Figure 4 As shown, in some embodiments, after setting the corresponding control quantity as the target control quantity in the current control time domain when the predicted state reaches the target state, the method further includes:

[0094] S401: After outputting the target control quantity to the thermal management system, obtain the actual state fed back by the thermal management system; the actual state is the actual state after the thermal management system executes the target control quantity.

[0095] S402: Determine the feedback adjustment amount based on the actual situation;

[0096] S403: Based on the feedback adjustment, the correction model predicts the target control quantity of the controller in the next control time domain.

[0097] In this embodiment, ideally, under the control of the target control quantity, the actual state fed back by the thermal management system should reach the target state. However, due to the influence of factors such as the external environment, component performance, and model accuracy, after the thermal management system executes actions based on the target control quantity, the actual state of the control target deviates from the expected target state, i.e., there is an overshoot or misalignment problem. If no adjustment is made, the deviation will continue to accumulate. Therefore, after outputting the target control quantity of the current control time domain to the thermal management system, the actual state of the control target output by the thermal management system is acquired in real time, and the control quantity of the model predictive controller in the next control time domain is corrected based on the actual state. During the prediction process of the model predictive controller, the target control quantity in the next control time domain is continuously corrected based on the actual state, so that the actual state output by the thermal management system continuously approaches the target state. The target control quantity after feedback correction acts on the thermal management system, which can improve the control effect of the thermal management system and meet the thermal management requirements of the vehicle.

[0098] In some implementations, integral regulation is used to determine the feedback adjustment amount. The model predictive controller determines multiple sets of target control quantities within the current control time domain, each set corresponding to a target state. After outputting each set of target control quantities to the thermal management system, the actual state obtained from the thermal management system under that set of target control quantities is acquired. Thus, within the current control time domain, multiple sets of target control quantities and their corresponding target and actual states can be obtained. Then, for each time point within the current control time domain, the difference between the target and actual states is calculated, and each difference is integrated within the current control time domain. The integral value is used as the feedback adjustment amount. In this embodiment, after determining the deviation between the actual and target states, integral regulation is used to determine the feedback adjustment amount based on the deviation, and the feedback adjustment amount is used to correct the control quantity in the next control time domain.

[0099] After determining the feedback adjustment amount using integral control, the target state of the control objective is adjusted using this feedback adjustment amount, and the adjusted target state is taken as the state that the control objective wants to achieve. After redetermining the target state, the control amount is iteratively selected again. The reselected control amount and the current state of the control objective are used as the inputs to the model predictive controller, which outputs the predicted state. During the iteration process, when the selected control amount enables the predicted state output by the model predictive controller to reach the adjusted target state, this control amount is used as the target control amount in the next control time domain, thus completing the feedback correction of the control amount.

[0100] In other implementations, the feedback adjustment amount is determined using a pre-constructed feedback adjustment table. This table can be determined through experimental calibration, and its entries include the actual state and the feedback adjustment amount corresponding to the cumulative state change rate within a control time domain. Therefore, during feedback correction, the actual state is acquired, and the cumulative state change rate within the current control time domain is determined. The feedback adjustment amount is then retrieved based on the actual state and the cumulative state change rate to obtain the corresponding feedback adjustment amount. In this embodiment, the feedback adjustment amount is determined based on the cumulative state change rate and the actual state, and this feedback adjustment amount is used to perform feedback correction on the control quantity in the next control time domain.

[0101] The method for determining the cumulative state change rate is as follows: within the current control time domain, each time point corresponds to a state. Based on the initial state at the start time point and the final state at the end time point, the cumulative state change rate within the current control time domain is calculated. For example, if the control target is battery temperature, the current battery temperature is 10 degrees Celsius, and the current control time domain is 5 seconds, under the action of the target control quantity, in the first second of the current control time domain, the actual battery temperature is 10 degrees Celsius; in the second second, it is 11 degrees Celsius; in the third second, it is 12 degrees Celsius; in the fourth second, it is 13 degrees Celsius; and in the fifth second, it is 14 degrees Celsius. From the first second to the fifth second, the cumulative temperature change rate of the battery is 0.8 degrees Celsius per second ((14-10) / 5). After determining the cumulative temperature change rate, the corresponding feedback adjustment quantity is obtained by consulting the feedback adjustment table based on the current actual temperature of 14 degrees Celsius and the cumulative temperature change rate of 0.8 degrees Celsius per second.

[0102] Based on the actual state and cumulative rate of change, the feedback adjustment amount is determined by consulting the feedback adjustment table. This adjustment amount is then used to adjust the target control quantity in the current control time domain, resulting in the adjusted target control quantity. This adjusted target control quantity is then input into the model predictive controller to obtain the target state for the next control time domain. For example, if the control target is the pump speed, and the current target control quantity in the control time domain is 1000 revolutions per minute (rpm), and the feedback adjustment amount obtained from the table is 5 rpm, then the adjusted target control quantity is 1005 rpm. Repeating this feedback correction process makes the prediction results of the model predictive controller more accurate, improving the control effect of the thermal management system.

[0103] For the two feedback correction methods mentioned above, the appropriate feedback correction method can be determined based on the degree of change in the cumulative state change rate. When the cumulative state change rate is greater than or equal to a certain change threshold, the feedback adjustment amount is determined by consulting the feedback adjustment table. When the cumulative state change rate is less than the change threshold, the feedback adjustment amount is determined by integration. After determining the feedback adjustment amount, the target state or target control quantity is adjusted according to the corresponding feedback correction method.

[0104] like Figure 5 As shown, in some embodiments, there are multiple sets of target control quantities in the current control time domain; after using the corresponding control quantity as the target control quantity in the current control time domain when the predicted state reaches the target state, the method further includes:

[0105] S501: Every time a preset time interval is reached, a set of target control quantities is output to the thermal management system from multiple sets of target control quantities;

[0106] S502: Based on the computation time and the output time required to output multiple sets of target control quantities to the thermal management system, determine the calling time for obtaining multiple sets of target control quantities in the next control time domain; the computation time is the time required for the model predictive controller to determine the predicted state based on the current state and the control quantities selected in the iteration, and to determine multiple sets of target control quantities based on the predicted state and the target state.

[0107] S503: Starting with the output of the first set of target control quantities from the multiple sets of target control quantities in the current control time domain to the thermal management system, the multiple sets of target control quantities in the next control time domain are obtained every time the call time is reached.

[0108] S504: Determine the number of target control quantity groups to be output within the operation time based on the time interval and the operation time;

[0109] S505: Based on the number of target control quantities output within the calculation time, determine the first set of target control quantities to be output to the thermal management system from among the multiple sets of target control quantities in the next control time domain;

[0110] S506: At each time interval, a set of target control variables is output to the thermal management system, starting from the first set of target control variables.

[0111] In this embodiment, after determining multiple sets of target control quantities, a set of target control quantities is output to the system at predetermined time intervals to ensure that the system can continuously acquire target control quantities. For example, for 30 sets of target control quantities in a control time domain, a set of target control quantities is output to the system every second.

[0112] If all the target control quantities in the current control time domain are output before calculating the next set of target control quantities, there is a certain lag time. To ensure continuous output of target control quantities, the call time for calculating the next set of target control quantities is redefined based on the computation time required to determine the target control quantity and the output time required to output multiple sets of target control quantities. Starting from the output of the first set of target control quantities, the next set of target control quantities is calculated when the call time is reached, instead of calculating after all sets of target control quantities have been output. This eliminates the lag time between two consecutive control time domains.

[0113] When determining multiple sets of target control quantities for the next control time domain, within the computation time, the multiple sets of target control quantities in the current control time domain continue to output one set of target control quantities to the system at regular intervals. During this process, each time the system receives a set of target control quantities, it executes a control action according to the current target control quantity, and the current state of the system is adjusted under the control of the current target control quantity. Among the multiple sets of target control quantities for the next control time domain determined within the computation time, the current state corresponding to some target control quantities is the same as the current state of some target control quantities in the current control time domain. If all target control quantities in the current control time domain are output, and then the multiple sets of target control quantities for the next control time domain are directly and continuously output, since the current state of the system has changed under the control of some target control quantities in the current control time domain, some target control quantities in the next control time domain can no longer achieve accurate control based on the latest current state of the system. Therefore, it is necessary to determine the number of sets of target control quantities to be output within the computation time based on the time interval of the output target control quantities and the computation time. To ensure control accuracy, these target control quantities are no longer output.

[0114] After determining the number of target control quantity sets to be output within the computation time, the first target control quantity to be output to the system from the multiple target control quantities in the next control time domain is determined based on this number. Then, starting from this first target control quantity, target control quantities are output to the system according to the time interval. In this way, not only can the continuous output of target control quantities be guaranteed and the lag time be eliminated, but the accuracy of the continuously output target control quantities can also be guaranteed, thereby improving the system control precision.

[0115] In some implementations, for the first control time domain in the control process, multiple sets of target control quantities in this control time domain are output at regular intervals, starting from the first set of target control quantities, until all target control quantities are output. The output time of the multiple sets of target control quantities in the first control time domain is the time required to output all target control quantities. For example, if there are 30 sets of target control quantities in the first control time domain, and one set is output every second, the output time of the 30 sets of target control quantities is 30 seconds.

[0116] In other embodiments, for other control time domains after the initial control time domain in the control process, since the call time has been readjusted, the multiple sets of target control quantities in other control time domains are not output from the first set, but from the newly determined first set of target control quantities. Therefore, the output time of the multiple sets of target control quantities in other control time domains is not the time required to output all target control quantities, but the time required from the output of the newly determined first set of target control quantities to the last set of target control quantities. The output time is the time obtained by subtracting the calculation time from the time required to output all target control quantities.

[0117] In some methods, after determining the computation time and the output time of multiple sets of control quantities, the time difference between the computation time and the output time is calculated, and this time difference is used as the calling time. That is, the time difference is determined by the computation time and the output time of multiple sets of target control quantities, and multiple sets of target control quantities in the next control time domain are obtained based on this time difference. This allows multiple sets of control quantities in the next control time domain to be obtained before all control quantities obtained in the current control time domain have been fully output, so that the control quantities in the current control time domain and the next control time domain can be output continuously, eliminating the delay in control quantity output caused by waiting for computation time between the two control time domains.

[0118] For example, if there are 30 target control variables in the first control time domain, and one variable is output every second, then the output time for these 30 target control variables is 30 seconds. If the computation time is 3 seconds, then the processing time is 27 seconds. That is, starting from the output of the first target control variable, the calculation of the second set of 30 target control variables begins at the 27th second. The first, second, and third target control variables in the second control time domain utilize the current states corresponding to the 28th, 29th, and 30th target control variables in the first control time domain, respectively. After the 30th target control variable in the first control time domain is output, the current state of the system is adjusted under this control variable. If the outputs are sequentially started from the first target control variable in the second control time domain, then the output target control variables will be inaccurate because the current state has changed. The latest current state of the system only begins from the fourth target control variable in the second control time domain. Therefore, after all 30 sets of target control quantities in the first control time domain are output, starting from the fourth set of target control quantities in the second control time domain, a new set of target control quantities is output to the system at regular time intervals, achieving continuous output of control quantities and ensuring system stability and control accuracy. Since 27 sets of target control quantities were actually output from the 30 sets in the second control time domain, with an actual output time of 27 seconds, the call time is 24 seconds. That is, starting from the output of the fourth set of target control quantities in the second control time domain, the 30 sets of target control quantities in the third control time domain are calculated after 24 seconds. Similarly, after all 27 sets of target control quantities in the second control time domain are output, the output starts from the fourth set of target control quantities in the third control time domain. By following the above cyclical process of calculating and outputting target control quantities, continuous output of target control quantities to the system is achieved, ensuring system stability and control accuracy.

[0119] like Figure 6As shown, in some embodiments, a model predictive controller is constructed based on the thermal management system model of the range-extended vehicle. The vehicle's thermal management system includes an engine, motor, battery, passenger compartment, heater, radiator, compressor, water pump, fan, cooling circulation piping, etc. Under specific operating conditions, some or all components in the thermal management system coordinate with each other to achieve the thermal management requirements of the range-extended vehicle through this coordinated control process. Correspondingly, the thermal management system model includes engine thermal model, motor thermal model, battery thermal model, passenger compartment thermal model, water pump thermal model, heater thermal model, radiator model, compressor thermal model, fan thermal model, cooling piping model, etc. During the coordinated control process of each model, a predicted result of the control target can be obtained within a certain time. For example, by inputting the current temperature and torque of the motor, other parameters (e.g., ambient temperature, coolant temperature, heater inlet water temperature, etc.) and selected control quantities into the motor thermal model, predicted results such as the predicted motor temperature and the predicted motor outlet water temperature can be obtained.

[0120] In this embodiment, to address the control of the thermal management system of a range-extended vehicle, a model predictive controller is constructed based on the thermal management system model of the range-extended vehicle and according to the Model Predictive Control (MPC) framework. After determining the control objective of the range-extended vehicle, the model predictive controller predicts the predicted state of the control objective under different control variables. During the prediction process, a predetermined algorithm iteratively selects different control variables until the model predictive controller can obtain the predicted state of achieving the target state based on the current state of the control objective and the selected control variables. At this point, the selected control variable is used as the target control variable and applied to the vehicle's thermal management system, enabling the thermal management system to achieve optimal operating efficiency after adjustment according to the target control variable, thus meeting the vehicle's thermal management requirements under the current operating conditions.

[0121] This application provides a vehicle thermal management control method applied to a vehicle's thermal management system. By acquiring the vehicle's operating conditions, a control objective, its target state, and its current state are determined based on these conditions. Then, based on the current state of the control objective and iteratively selected control variables, a pre-built model predictive controller is used to determine the predicted state of the control objective. When the predicted state reaches the target state, the corresponding control variable is used as the target control variable in the current control time domain. This application, based on a pre-built model predictive controller suitable for the thermal management system, uses the model predictive controller to determine the system's target control variable, ensuring the operational efficiency of the thermal management system and meeting the thermal management requirements under different operating conditions.

[0122] like Figure 7 As shown in the illustration, this application also provides a vehicle thermal management control device, comprising:

[0123] The acquisition module 701 is used to acquire the vehicle's operating conditions;

[0124] The target determination module 702 is used to determine the control target, the target state, and the current state of the control target based on the operating conditions.

[0125] The model prediction module 703 is used to iteratively select control quantities according to a predetermined algorithm. Based on the current state of the control target and the selected control quantity, the predicted state of the control target is determined using a pre-built model prediction controller. When the predicted state reaches the target state, the corresponding control quantity is used as the target control quantity in the current control time domain.

[0126] For ease of description, the above apparatus is described in terms of function, divided into various modules. Of course, when implementing one or more embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware.

[0127] The apparatus described above is used to implement the corresponding methods in the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0128] Figure 8 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0129] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0130] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0131] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0132] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0133] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0134] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0135] The electronic devices described above are used to implement the corresponding methods in the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0136] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0137] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of this application as described above, which are not provided in detail for the sake of brevity.

[0138] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0139] One or more embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. A vehicle thermal management control method, applied to range-extended vehicles, characterized in that, include: Obtain the vehicle's operating status; Based on the operating conditions, determine the control target and the target state and current state of the control target; In response to the difference between the current state and the target state being greater than a preset adjustment threshold, multiple control time domains required to adjust the current state to the target state, and the target state of each control time domain, are determined based on the difference. Based on the current state and the target state of each control time domain, a state change curve for each control time domain is determined according to a preset state change rate; the state change curve is a curve formed by the state at each time point within the control time domain. The control quantity is iteratively selected according to a predetermined algorithm. Based on the current state of the control target and the selected control quantity, the predicted state of the control target is determined using a pre-built model predictive controller. This includes: based on the target state of each control time domain, for each control time domain, the control quantity is iteratively selected according to a predetermined algorithm. Based on the current state of the control target and the selected control quantity, the predicted state of the control target is determined using the model predictive controller. When the predicted state reaches the target state, the corresponding control quantity is used as the target control quantity in the current control time domain, including: when the predicted state matches the state change curve, the corresponding control quantity is used as the target control quantity in the corresponding control time domain.

2. The method according to claim 1, characterized in that, There are multiple control objectives, each with a different priority. Based on the current state of the control objective and the selected control variable, the predicted state of the control objective is determined using a pre-built model predictive controller, including: Based on the current state of the high-priority control objective and the selected control variable, the model predictive controller determines the predicted state of the high-priority control objective.

3. The method according to claim 2, characterized in that, There are multiple high-priority control objectives, and each control objective has a different weight value; When the predicted state reaches the target state, the corresponding control quantity is used as the target control quantity in the current control time domain, including: When the predicted state of each high-priority control objective reaches the target state, the corresponding control quantity is used as the reference control quantity for the corresponding control objective in the current control time domain. The target control quantity is determined based on the reference control quantity and corresponding weight value of each high-priority control objective.

4. The method according to claim 1, characterized in that, When the predicted state matches the state change curve, the corresponding control quantity is used as the target control quantity in the corresponding control time domain, including: Calculate the state difference between the predicted state at each time point in the control time domain and the state at the corresponding time point on the state change curve; The control quantity corresponding to the minimum sum of state differences at each time point is taken as the target control quantity.

5. The method according to claim 1, characterized in that, When the predicted state reaches the target state, after setting the corresponding control quantity as the target control quantity in the current control time domain, the following steps are also included: After outputting the target control quantity to the thermal management system, the actual state fed back by the thermal management system is obtained; the actual state is the actual state after the thermal management system executes according to the target control quantity. Based on the actual state, determine the feedback adjustment amount; Based on the feedback adjustment, the target control quantity of the model predictive controller is corrected in the next control time domain.

6. The method according to claim 1, characterized in that, The current control time domain has multiple target control quantities; when the predicted state reaches the target state, after using the corresponding control quantity as the target control quantity in the current control time domain, it further includes: At each preset time interval, a set of target control variables is output to the thermal management system from multiple sets of target control variables; Based on the computation time and the output time required to output multiple sets of target control quantities to the thermal management system, the calling time for obtaining multiple sets of target control quantities in the next control time domain is determined; the computation time is the time required for the model predictive controller to determine the predicted state based on the current state and the control quantities selected in the iteration, and to determine multiple sets of target control quantities based on the predicted state and the target state. Starting with the output of the first set of target control quantities from the multiple sets of target control quantities in the current control time domain to the thermal management system, the multiple sets of target control quantities in the next control time domain are obtained every time the calling time is reached. Based on the time interval and the calculation time, determine the number of target control quantity groups output within the calculation time. Based on the number of target control quantities output within the calculation time, determine the first set of target control quantities output to the thermal management system from the multiple sets of target control quantities in the next control time domain. At each time interval, a set of target control variables is output to the thermal management system, starting from the first set of target control variables.

7. A vehicle thermal management control device, applied to a range-extended vehicle, characterized in that, include: The acquisition module is used to acquire the vehicle's operating conditions; The target determination module is used to determine the control target and the target state and current state of the control target according to the operating conditions; in response to the difference between the current state and the target state being greater than a preset adjustment threshold, it determines multiple control time domains required to adjust the current state to the target state, and the target state of each control time domain, based on the difference. Based on the current state and the target state of each control time domain, a state change curve for each control time domain is determined according to a preset state change rate; the state change curve is a curve formed by the state at each time point within the control time domain. The model prediction module is used to iteratively select control quantities according to a predetermined algorithm, and determine the predicted state of the control target based on the current state of the control target and the selected control quantity using a pre-built model prediction controller. This includes: for each control time domain, iteratively selecting control quantities according to a predetermined algorithm based on the target state of each control time domain; determining the predicted state of the control target based on the current state of the control target and the selected control quantity using the model prediction controller; and when the predicted state reaches the target state, using the corresponding control quantity as the target control quantity for the current control time domain. This includes: when the predicted state matches the state change curve, using the corresponding control quantity as the target control quantity for the corresponding control time domain.

8. An electronic device 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 program, it implements the method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the method according to any one of claims 1 to 6. 。 10. A vehicle, characterized in that, Including the electronic device as described in claim 8.

Images