A water temperature model predictive control method, device and equipment and readable storage medium

Abstract

A water temperature model predictive control method, apparatus, device, and readable storage medium, relating to the field of automotive thermal management, includes adjusting the engine's target inlet water temperature or the target thermal protection temperature threshold corresponding to the hard constraint when a risk of violating hard constraints is detected in the MPC algorithm based on target parameters, to obtain a new inlet water temperature or a new thermal protection temperature threshold. The target parameters include the engine's actual outlet water temperature and actual inlet water temperature, as well as the historical fan speed predicted and output by the MPC algorithm. The new inlet water temperature or new thermal protection temperature threshold is used as a target constraint, which includes tracking the target inlet water temperature against the engine's actual inlet water temperature and fan power consumption. The MPC algorithm is controlled to predict the fan speed based on the target function and target constraints to output the target fan speed. The engine water temperature is controlled based on the target fan speed. This application can reasonably plan the target fan speed to reduce fan power consumption while ensuring the engine water temperature does not exceed the limit.

Description

Technical Field

[0001] This application relates to the field of automotive thermal management technology, specifically to a water temperature model predictive control method, device, equipment, and readable storage medium. Background Technology

[0002] With the development of the automotive industry, engine thermal management is crucial for fuel economy, emissions performance, and engine life. Model predictive control (MPC) algorithms, due to their ability to handle multivariate constraints and optimization objectives, are increasingly being applied to the control of engine cooling systems.

[0003] The accuracy of the model directly affects the control performance of the MPC. Inaccurate modeling and system disturbances can both lead to a decline in MPC control performance. When the error between the MPC's predictive model and the actual model is too large, the dynamic response of the control system deteriorates. This means that the system's response process exhibits significant overshoot, oscillation, or slow response. More seriously, constraint handling may fail. Due to inaccurate predictions, the controller may fail to act when it should, resulting in a violation of hard constraints. In the control of engine coolant temperature, this manifests as follows: the MPC model predicts that the coolant temperature does not exceed the hard constraints, so it outputs a lower fan speed. However, the actual system coolant temperature has exceeded the hard constraints, triggering the engine's thermal protection and affecting the normal operation of the vehicle.

[0004] Therefore, how to solve the constraint failure and engine overheating risk caused by model inaccuracy in water temperature MPC control is an urgent problem to be solved. Summary of the Invention

[0005] This application provides a water temperature model predictive control method, device, equipment, and readable storage medium, which can reasonably plan the target speed of the fan to reduce fan power consumption without exceeding the engine water temperature.

[0006] In a first aspect, embodiments of this application provide a water temperature model predictive control method, the water temperature model predictive control method comprising: When the model predictive control (MPC) algorithm is detected to have a risk of violating hard constraints based on the target parameters, the target inlet water temperature of the engine or the target thermal protection temperature threshold corresponding to the hard constraints is adjusted to obtain a new inlet water temperature or a new thermal protection temperature threshold. The target parameters include the actual outlet water temperature and the actual inlet water temperature of the engine, as well as the historical fan speed predicted by the MPC algorithm. The new inlet water temperature or the new thermal protection temperature threshold is used as the objective constraint of the objective function, which includes the tracking of the engine's actual inlet water temperature to the target inlet water temperature and the fan power consumption. The control MPC algorithm predicts the fan speed based on the objective function and the objective constraint, and outputs the target fan speed. The engine coolant temperature is controlled based on the target fan speed.

[0007] In conjunction with the first aspect, in one implementation, prior to the step of detecting a risk of hard constraint violation in the Model Predictive Control (MPC) algorithm based on the target parameters, the method further includes: If the target parameter is detected to meet all target conditions at the same time, it is determined that the MPC algorithm has a risk of violating hard constraints. The target conditions include the actual outlet water temperature being greater than the outlet water temperature threshold, the difference between the actual outlet water temperature and the actual inlet water temperature being greater than the difference threshold, the historical fan speed being less than the speed threshold, and the rate of change of the speed corresponding to the historical fan speed being less than the rate of change threshold. If the target parameter is detected to not meet at least one target condition, it is determined that the MPC algorithm does not have the risk of violating hard constraints.

[0008] In conjunction with the first aspect, in one embodiment, adjusting the target inlet water temperature of the engine or the target thermal protection temperature threshold corresponding to the hard constraint to obtain a new inlet water temperature or a new thermal protection temperature threshold includes: The target inlet water temperature or the target thermal protection temperature threshold corresponding to the hard constraint is adjusted according to the engine's current operating load to obtain a new inlet water temperature or a new thermal protection temperature threshold.

[0009] In conjunction with the first aspect, in one embodiment, adjusting the target inlet water temperature or the target thermal protection temperature threshold corresponding to the hard constraint of the engine based on the engine's current operating load to obtain a new inlet water temperature or a new thermal protection temperature threshold includes: If the current operating load is greater than the preset operating load threshold, the target inlet water temperature of the engine is reduced to obtain a new inlet water temperature; If the current operating load is less than or equal to the preset operating load threshold, the target thermal protection temperature threshold corresponding to the hard constraint is reduced to obtain a new thermal protection temperature threshold.

[0010] In conjunction with the first aspect, in one embodiment, reducing the target inlet water temperature of the engine to obtain a new inlet water temperature includes: The target temperature adjustment amount is obtained by looking up the MAP table based on the current ambient temperature and current operating load. The target inlet water temperature is updated based on the target temperature adjustment amount to obtain a new inlet water temperature.

[0011] In conjunction with the first aspect, in one implementation, reducing the target thermal protection temperature threshold corresponding to the hard constraint to obtain a new thermal protection temperature threshold includes: The target thermal protection temperature threshold adjustment amount is obtained by looking up the MAP table based on the current ambient temperature and current operating load. The target thermal protection temperature threshold is updated based on the adjustment amount of the target thermal protection temperature threshold to obtain a new thermal protection temperature threshold.

[0012] In conjunction with the first aspect, in one embodiment, the method further includes: When it is detected that the MPC algorithm does not have a risk of violating hard constraints based on the target parameters, the MPC algorithm is controlled to predict the fan speed based on the target function, so as to output the target fan speed.

[0013] Secondly, embodiments of this application provide a water temperature model prediction and control device, the water temperature model prediction and control device comprising: The constraint update module is used to adjust the target inlet water temperature of the engine or the target thermal protection temperature threshold corresponding to the hard constraint when the model predictive control (MPC) algorithm is detected to have a risk of violating hard constraints based on the target parameters, so as to obtain a new inlet water temperature or a new thermal protection temperature threshold. The target parameters include the actual outlet water temperature and the actual inlet water temperature of the engine and the historical fan speed predicted by the MPC algorithm. The new inlet water temperature or the new thermal protection temperature threshold is used as the target constraint of the objective function. The objective function includes the tracking of the actual inlet water temperature of the engine to the target inlet water temperature and the fan power consumption. The speed prediction module is used to control the MPC algorithm to predict the fan speed based on the objective function and the objective constraint, so as to output the target fan speed. A water temperature control module is used to control the engine water temperature based on the target fan speed.

[0014] In conjunction with the second aspect, in one implementation, the constraint update module is further configured to: If the target parameter is detected to meet all target conditions at the same time, it is determined that the MPC algorithm has a risk of violating hard constraints. The target conditions include the actual outlet water temperature being greater than the outlet water temperature threshold, the difference between the actual outlet water temperature and the actual inlet water temperature being greater than the difference threshold, the historical fan speed being less than the speed threshold, and the rate of change of the speed corresponding to the historical fan speed being less than the rate of change threshold. If the target parameter is detected to not meet at least one target condition, it is determined that the MPC algorithm does not have the risk of violating hard constraints.

[0015] In conjunction with the second aspect, in one implementation, the constraint update module is specifically used for: The target inlet water temperature or the target thermal protection temperature threshold corresponding to the hard constraint is adjusted according to the engine's current operating load.

[0016] In conjunction with the second aspect, in one implementation, the constraint update module is further configured to: If the current operating load is greater than the preset operating load threshold, the target inlet water temperature of the engine is reduced to obtain a new inlet water temperature; If the current operating load is less than or equal to the preset operating load threshold, the target thermal protection temperature threshold corresponding to the hard constraint is reduced to obtain a new thermal protection temperature threshold.

[0017] In conjunction with the second aspect, in one implementation, the constraint update module is further configured to: The target temperature adjustment amount is obtained by looking up the MAP table based on the current ambient temperature and current operating load. The target inlet water temperature is updated based on the target temperature adjustment amount to obtain a new inlet water temperature.

[0018] In conjunction with the second aspect, in one implementation, the constraint update module is further configured to: The target thermal protection temperature threshold adjustment amount is obtained by looking up the MAP table based on the current ambient temperature and current operating load. The target thermal protection temperature threshold is updated based on the adjustment amount of the target thermal protection temperature threshold to obtain a new thermal protection temperature threshold.

[0019] In conjunction with the second aspect, in one embodiment, the speed prediction module is further configured to: when it is detected based on the target parameters that the MPC algorithm does not have a risk of violating hard constraints, control the MPC algorithm to predict the fan speed based on the target function, so as to output the target fan speed.

[0020] Thirdly, embodiments of this application provide a water temperature model prediction and control device, which includes a processor, a memory, and a water temperature model prediction and control program stored in the memory and executable by the processor. When the water temperature model prediction and control program is executed by the processor, it implements the steps of the aforementioned water temperature model prediction and control method.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a water temperature model prediction and control program, wherein when the water temperature model prediction and control program is executed by a processor, it implements the steps of the aforementioned water temperature model prediction and control method.

[0022] The beneficial effects of the technical solutions provided in this application include: When a risk of the MPC algorithm violating hard constraints is detected by using target parameters including the engine's actual inlet and outlet water temperature and the historical fan speed predicted by the MPC algorithm, a new inlet water temperature or a new thermal protection temperature threshold is obtained by adjusting the engine's target inlet water temperature or the target thermal protection temperature threshold corresponding to the hard constraint. The new inlet water temperature or the new thermal protection temperature threshold is used as a target constraint for a target function that includes the tracking of the engine's actual inlet water temperature against the target inlet water temperature and the fan power consumption. This allows the MPC algorithm to predict the fan speed based on the target function and the target constraint, and output the target fan speed. The engine water temperature is then controlled based on the target fan speed. As can be seen, this application can promptly identify scenarios where MPC prediction fails by using the engine inlet and outlet water temperatures and the fan speed predicted by the MPC algorithm. Once a risk is identified, the target engine inlet water temperature or hard constraint threshold is adaptively reduced to force the MPC controller to output a higher fan speed or act in advance to meet the new constraint. This allows for the reasonable planning of the target fan speed, thereby ensuring the safety of the physical system even when the model is inaccurate, preventing engine overheating, and reducing fan power consumption. Furthermore, since the inlet water temperature better represents the cooling capacity of the cooling system and has a faster response, using the engine inlet water temperature as the control target (optimization target) is beneficial for reducing water temperature fluctuations. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating an embodiment of the water temperature model prediction and control method of this application; Figure 2 This is a schematic diagram of the overall architecture involved in the embodiments of this application; Figure 3 This is a schematic diagram of the engine structure involved in the embodiments of this application; Figure 4 This is a schematic diagram of the functional modules of an embodiment of the water temperature model prediction and control device of this application; Figure 5 This is a schematic diagram of the hardware structure of the water temperature model prediction and control device involved in the embodiments of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0026] In a first aspect, embodiments of this application provide a water temperature model prediction and control method.

[0027] In one embodiment, reference is made to Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the water temperature model prediction and control method of this application. Figure 1 As shown, the water temperature model predictive control method includes: Step S10: When the model predictive control (MPC) algorithm is detected to have a risk of violating hard constraints based on the target parameters, the target inlet water temperature of the engine or the target thermal protection temperature threshold corresponding to the hard constraints is adjusted to obtain a new inlet water temperature or a new thermal protection temperature threshold. The target parameters include the actual outlet water temperature and the actual inlet water temperature of the engine, as well as the historical fan speed predicted by the MPC algorithm.

[0028] As an example, it is understandable that engine coolant temperature modeling is complex and highly nonlinear. This embodiment uses data modeling to establish dynamic system equations to generate a coolant temperature prediction model and design an MPC controller; for details, see [link to relevant documentation]. Figure 2 As shown, in data modeling, vehicle speed, engine speed, engine torque, ambient temperature, fan speed, water pump speed, and thermostat opening are used as inputs, and engine inlet and outlet coolant temperatures are used as outputs. It should be noted that the dynamic system equations can be in the form of transfer functions or linear state-space models, for example, see [link to relevant documentation]. Figure 2 As shown, the dynamic system equations are dx / dt=Ax(t)+Bu(t), y(t)=Cx(t)+Du(t), where x is the system state variable of engine coolant temperature, A, B, C, and D are parameter matrices, the specific composition of which is common knowledge in this field and will not be elaborated here for the sake of simplicity. u is a vector composed of vehicle speed, engine speed, engine torque, ambient temperature, fan speed, water pump speed, and thermostat opening, and y is the predicted engine coolant temperature. In the predictive control of the engine coolant temperature prediction model, the designed control variables are fan speed, the observable disturbances are engine speed, engine torque, ambient temperature, vehicle speed, water pump speed, and thermostat opening, and the measurable outputs are engine inlet coolant temperature and engine outlet coolant temperature.

[0029] In this embodiment, MATLAB's model identification is preferably used to model the vehicle's cooling system to obtain data-driven dynamic system equations and generate a water temperature prediction model. Finally, the MPC algorithm is used to predict the future engine inlet and outlet water temperatures of the cooling system. It is understood that the MPC algorithm in this embodiment can generate optimal control variables based on the current system state and the water temperature prediction model, thereby rationally planning the target fan speed. This allows the fan to operate more in the low-speed range without exceeding the engine water temperature limit, thus reducing the power consumption of the fan accessories.

[0030] See Figure 3 As shown, since the thermostat senses the temperature of the coolant entering the engine after being cooled by the radiator, it can more accurately control the engine's inlet coolant temperature and maintain a more stable operating temperature. The engine block and cylinder head constantly receive coolant from the water pump at a relatively constant temperature, avoiding thermal stress caused by the mixing of hot and cold fluids. Based on this, this embodiment designs the objective function of the coolant temperature MPC based on the target inlet coolant temperature and fan power consumption, and uses the outlet coolant temperature as the key constraint for MPC control, thereby achieving the goal of keeping the engine operating within the optimal temperature range. Based on this, this embodiment constructs the MPC controller with a dual-sensor physical layout, that is, installing engine inlet coolant temperature sensors and engine outlet coolant temperature sensors on both sides of the engine inlet and outlet to measure the actual inlet and outlet coolant temperatures respectively. The engine outlet coolant temperature sensor is installed at the outlet of the engine cylinder head or connected to the upper coolant pipe on the upper part of the engine. It measures the temperature of the coolant that has just absorbed a large amount of heat from the engine combustion chamber and cylinder walls. This temperature represents the actual operating temperature of the engine and is the most important reference for the engine control unit to perform thermal management, directly reflecting whether the engine is overheating.

[0031] It is worth noting that inaccurate modeling and system disturbances can lead to a decrease in MPC control performance, making it impossible for the MPC algorithm to accurately predict fan speed. Based on this, this embodiment will use the actual inlet and outlet water temperature and temperature difference of the engine and the fan demand speed predicted by the MPC algorithm (i.e., historical fan speed) to determine whether the MPC algorithm may trigger a scenario that violates hard constraints (hard constraints refer to the engine outlet water temperature not exceeding a preset thermal protection temperature threshold, the specific value of which can be determined according to actual needs and is not limited here), in order to determine whether it is necessary to compensate for model errors by adaptively adjusting the constraint object to ensure that hard constraints are not violated.

[0032] If the MPC algorithm poses a risk of violating hard constraints, it indicates that the algorithm's predictions are inaccurate. In other words, the MPC algorithm's internal checks will show "no constraint exceeded," resulting in a lower output fan speed. This "false safety" can lead to actual engine overheating, triggering the engine's thermal protection mechanism and affecting normal vehicle operation. Therefore, this embodiment adaptively adjusts the engine's target inlet coolant temperature or the target thermal protection temperature threshold corresponding to the hard constraints to obtain a new inlet coolant temperature or a new thermal protection temperature threshold. This new threshold is used to compensate for model errors, thereby minimizing the risk of violating hard constraints. It should be understood that the specific value of the engine's target inlet coolant temperature can be determined by comprehensively considering factors such as engine speed, engine torque, vehicle speed, and ambient temperature, and is not limited here.

[0033] Step S20: Use the new inlet water temperature or the new thermal protection temperature threshold as the objective constraint of the objective function, which includes the tracking of the engine's actual inlet water temperature against the target inlet water temperature and the fan power consumption.

[0034] As an example, this embodiment designs the objective function of water temperature MPC based on the target inlet water temperature and fan power consumption. Furthermore, the optimization solver employs Quadratic Programming (QP) to solve for the optimal output of the MPC controller; where the objective function is... This includes tracking the actual inlet water temperature of the engine against the target inlet water temperature, as well as fan power consumption (i.e., fan speed tracking). The specific expression is as follows: k represents the current control time. Describes the decision variable vector of QP. , Indicates the first The control quantity for each prediction cycle, where T represents transpose.

[0035] in, This indicates the tracking of the engine's actual inlet coolant temperature to the target inlet coolant temperature, and its specific expression is as follows: , Let i be the prediction step size and i be the prediction period. This represents the adjustment weight of the actual inlet water temperature for tracking the target inlet water temperature over the i-th prediction period. This represents the predicted inlet water temperature for the i-th prediction cycle. This represents the reference value of the inlet water temperature for the i-th prediction cycle. The specific expression for tracking fan speed is: , It is the adjustment weight of the control quantity (i.e., fan speed) in the i-th prediction cycle. This represents the control quantity for the i-th prediction period. It should be noted that... , and The specific value can be determined according to actual needs, for example =300, =100, =0.1.

[0036] Based on this, the new inlet water temperature or the new thermal protection temperature threshold is used as the objective constraint of the objective function. That is, the objective function is solved by using the new inlet water temperature or the new thermal protection temperature threshold as the objective constraint to compensate for model errors, so that the MPC algorithm can achieve accurate prediction of fan speed.

[0037] Step S30: Control the MPC algorithm to predict the fan speed based on the objective function and the objective constraint, so as to output the target fan speed.

[0038] As an example, in this embodiment, when the MPC algorithm predicts the fan speed, it solves the objective function with the new inlet water temperature or the new thermal protection temperature threshold as a constraint in order to find the optimal cooling system action (i.e., the target fan speed).

[0039] Step S40: Control the engine coolant temperature based on the target fan speed.

[0040] Exemplary, see Figure 3 As shown, after the MPC controller outputs the optimal target fan speed, it inputs it to the thermal management system so that the thermal management system can control the engine coolant temperature based on the target fan speed. The thermal management system continues to measure the real-time inlet and outlet coolant temperatures of the engine to obtain the engine coolant temperature measurement value, and feeds it back to the MPC controller to predict the fan speed.

[0041] In summary, this embodiment can promptly identify scenarios where MPC prediction fails by using the engine inlet and outlet water temperatures and the fan speed predicted by the MPC algorithm. Once a risk is identified, the target engine inlet water temperature or hard constraint threshold is adaptively reduced to force the MPC controller to output a higher fan speed or act in advance to meet the new constraint. This allows for the reasonable planning of the target fan speed, thereby ensuring the safety of the physical system even when the model is inaccurate, preventing engine overheating, and reducing fan power consumption. Furthermore, since the inlet water temperature better represents the cooling capacity of the cooling system and responds faster, using the engine inlet water temperature as the control target helps reduce water temperature fluctuations.

[0042] Furthermore, in one embodiment, before the step of detecting a risk of hard constraint violation in the Model Predictive Control (MPC) algorithm based on the target parameters, the method further includes: If the target parameter is detected to meet all target conditions at the same time, it is determined that the MPC algorithm has a risk of violating hard constraints. The target conditions include the actual outlet water temperature being greater than the outlet water temperature threshold, the difference between the actual outlet water temperature and the actual inlet water temperature being greater than the difference threshold, the historical fan speed being less than the speed threshold, and the rate of change of the speed corresponding to the historical fan speed being less than the rate of change threshold. If the target parameter is detected to not meet at least one target condition, it is determined that the MPC algorithm does not have the risk of violating hard constraints.

[0043] As an example, in this embodiment, the following conditions will be used to determine whether the MPC algorithm is at risk of violating hard constraints: (1) The actual outlet water temperature of the engine is greater than the outlet water temperature threshold; (2) The difference between the actual outlet water temperature of the engine and the actual inlet water temperature of the engine (this difference indicates that the heat generated by the engine cannot be effectively removed and the heat accumulates inside the engine) is greater than the difference threshold. (3) The fan demand speed (i.e. historical fan speed) predicted by the MPC algorithm in the previous prediction cycle is less than the speed threshold; (4) The rate of change of the fan demand speed output by the MPC algorithm in the most recent two prediction cycles (i.e. the rate of change of the speed calculated based on the historical fan speed output in the most recent two prediction cycles) is less than the rate of change threshold. Understandably, if all the above conditions are met, it indicates that the model prediction is no longer accurate, and the MPC-controlled water temperature may be at risk of overheating. Therefore, the MPC algorithm is deemed to have violated hard constraints. In this case, the target inlet water temperature of the engine or the hard constraint threshold (i.e., the thermal protection temperature threshold) at the engine outlet can be lowered to adaptively adjust the MPC target and constraints, thereby minimizing the risk of violating hard constraints. Conversely, if at least one of the above conditions is not met, the MPC algorithm is deemed not to have violated hard constraints. It should be noted that the specific values ​​of the outlet water temperature threshold, difference threshold, speed threshold, and rate of change threshold can be determined according to actual needs and are not limited here.

[0044] Furthermore, in one embodiment, the method further includes: When it is detected that the MPC algorithm does not have a risk of violating hard constraints based on the target parameters, the MPC algorithm is controlled to predict the fan speed based on the target function, so as to output the target fan speed.

[0045] As an example, in this embodiment, if the MPC algorithm does not have the risk of violating hard constraints, it means that the model prediction is still accurate. Therefore, there is no need to perform model error compensation. Thus, the MPC algorithm can be directly controlled to predict the fan speed based on the objective function in order to accurately output the target fan speed.

[0046] Further, in one embodiment, adjusting the target inlet water temperature of the engine or the target thermal protection temperature threshold corresponding to the hard constraint to obtain a new inlet water temperature or a new thermal protection temperature threshold includes: The target inlet water temperature or the target thermal protection temperature threshold corresponding to the hard constraint is adjusted according to the engine's current operating load to obtain a new inlet water temperature or a new thermal protection temperature threshold.

[0047] As an example, it is worth noting that the adjustment of the target inlet water temperature and the target thermal protection temperature threshold in this embodiment refers to a decrease adjustment. Specifically, the core of the MPC algorithm is to minimize the error between the "predicted value" and the "target value". Therefore, this embodiment can artificially create a larger tracking error by lowering the target inlet water temperature. This means that regardless of whether the model predicts overheating, as long as the target value is lowered, the error term in the objective function will increase. In order to minimize the cost function, the solver will inevitably increase the control quantity (i.e., fan speed). This is an "actively driven" strategy. In addition, the MPC algorithm requires that all predicted values ​​must be less than the constraint threshold in the prediction time domain. Therefore, lowering the thermal protection temperature threshold in this embodiment is equivalent to narrowing the feasible region, allowing the solver to find a solution under stricter constraints, thereby achieving the purpose of acting in advance.

[0048] Understandably, when the engine is running under heavy load, its heat generation is enormous, and the cooling system is nearing its limit. At this time, the model is prone to underestimating the heat generation or overestimating the cooling capacity (e.g., failing to detect radiator blockage). When the engine is running under low load (such as idling or coasting), its heat generation is not very large, and the cooling system has a certain margin. However, model errors still exist and need to be compensated. Based on this, in this embodiment, when the risk of violating hard constraints is detected in the MPC algorithm, it will determine whether to adjust the target inlet water temperature of the engine to obtain a new inlet water temperature or adjust the target thermal protection temperature threshold to obtain a new thermal protection temperature threshold, based on the current operating load of the engine, thereby achieving more accurate model error compensation.

[0049] Further, in one embodiment, adjusting the target inlet water temperature or the target thermal protection temperature threshold corresponding to the hard constraint based on the engine's current operating load to obtain a new inlet water temperature or a new thermal protection temperature threshold includes: If the current operating load is greater than the preset operating load threshold, the target inlet water temperature of the engine is reduced to obtain a new inlet water temperature; If the current operating load is less than or equal to the preset operating load threshold, the target thermal protection temperature threshold corresponding to the hard constraint is reduced to obtain a new thermal protection temperature threshold.

[0050] As an example, it should be noted that the specific value of the preset operating load threshold can be determined according to actual needs and is not limited here. If the current operating load is greater than the preset operating load threshold, it indicates that the engine generates a large amount of heat and the cooling system is close to its limit. In this case, the target inlet water temperature of the engine can be reduced to obtain a new inlet water temperature, thereby increasing the tracking error value in the objective function (i.e., the error between the actual inlet water temperature and the target inlet water temperature), forcing the MPC solver to output a higher fan speed to eliminate the error. If the current operating load is less than or equal to the preset operating load threshold, it indicates that although the engine generates a small amount of heat, there is still a model error that needs to be compensated. In this case, the target thermal protection temperature threshold of the engine can be reduced to obtain a new thermal protection temperature threshold, thereby tightening the constraints of the MPC and forcing the solver to find a solution under stricter constraints, so as to achieve the purpose of early action.

[0051] Furthermore, in one embodiment, reducing the target inlet water temperature of the engine to obtain a new inlet water temperature includes: The target temperature adjustment amount is obtained by looking up the MAP table based on the current ambient temperature and current operating load. The target inlet water temperature is updated based on the target temperature adjustment amount to obtain a new inlet water temperature.

[0052] As an example, in this embodiment, the relationship between the temperature regulation amount and the ambient temperature and operating load can be constructed through pre-experimentation to form a first MAP table. When it is determined that the target inlet water temperature of the engine needs to be reduced, the first MAP table can be queried through the current ambient temperature and the current operating load to retrieve the target temperature regulation amount corresponding to the current ambient temperature and the current operating load. Then, the target inlet water temperature is updated according to the target temperature regulation amount, that is, the difference between the target inlet water temperature and the target temperature regulation amount is used as the new inlet water temperature.

[0053] Further, in one embodiment, reducing the target thermal protection temperature threshold corresponding to the hard constraint to obtain a new thermal protection temperature threshold includes: The target thermal protection temperature threshold adjustment amount is obtained by looking up the MAP table based on the current ambient temperature and current operating load. The target thermal protection temperature threshold is updated based on the adjustment amount of the target thermal protection temperature threshold to obtain a new thermal protection temperature threshold.

[0054] As an example, in this embodiment, the relationship between the thermal protection temperature threshold adjustment amount and the ambient temperature and operating load can be constructed through pre-experimentation to form a second MAP table. When it is determined that the thermal protection temperature threshold needs to be reduced, the second MAP table can be queried using the current ambient temperature and current operating load to retrieve the target thermal protection temperature threshold adjustment amount corresponding to the current ambient temperature and current operating load. Then, the target thermal protection temperature threshold is updated according to the target thermal protection temperature threshold adjustment amount, that is, the difference between the target thermal protection temperature threshold and the target thermal protection temperature threshold adjustment amount is used as the new thermal protection temperature threshold.

[0055] In summary, this embodiment employs a dual-sensor physical layout of engine inlet and outlet coolant temperatures. The inlet coolant temperature controls the cooling system's actuator fan, while the outlet coolant temperature serves as the constraint for the MPC controller. This approach offers at least the following advantages: the engine inlet coolant temperature better represents the current cooling capacity than the outlet temperature, resulting in a faster actuator response; compared to outlet temperature control, inlet temperature control allows for complete shut-off (or limited circulation) of coolant entering the engine during cold starts, forcing the coolant to circulate rapidly within the engine for heating without interference from the cold water in the radiator. This further reduces temperature fluctuations and shortens warm-up time, thereby lowering fuel consumption and emissions; and the different heat loads on various engine components (e.g., exhaust) further reduce these loads. The air-side and cylinder head bridge area have extremely high temperatures, while the intake side is relatively lower. Inlet control is usually combined with counter-flow or cross-flow design to achieve better cylinder block thermal load control (i.e., prevent local overheating). For example, by controlling the coolant to enter first from the parts that need cooling the most (such as the high-temperature area of ​​the cylinder head), a more uniform cylinder block temperature distribution can be achieved. In contrast, outlet control often allows hot water to rise naturally, so the heat exchange efficiency is not as good as directional inlet control under such extreme local temperature differences. Under the same target water temperature, the minimum actual water temperature of inlet control will be higher than that of outlet control, and the increase in minimum water temperature helps to improve fuel economy. In addition, the outlet water temperature is more representative of the current thermal state of the engine, and as a constraint for solving MPC, it can prevent the engine from triggering thermal protection.

[0056] In addition, this embodiment controls the fan in advance by predicting the water temperature value in a certain time domain in the future, and achieves the effect of improving the stability of water temperature control and reducing fan power consumption through the design of dual objective functions of water temperature and fan power consumption.

[0057] Secondly, embodiments of this application also provide a water temperature model prediction and control device.

[0058] In one embodiment, reference is made to Figure 4 , Figure 4 This is a schematic diagram of the functional modules of an embodiment of the water temperature model prediction and control device of this application. Figure 4As shown, the water temperature model prediction and control device includes: The constraint update module is used to adjust the target inlet water temperature of the engine or the target thermal protection temperature threshold corresponding to the hard constraint when the model predictive control (MPC) algorithm is detected to have a risk of violating hard constraints based on the target parameters, so as to obtain a new inlet water temperature or a new thermal protection temperature threshold. The target parameters include the actual outlet water temperature and the actual inlet water temperature of the engine and the historical fan speed predicted by the MPC algorithm. The new inlet water temperature or the new thermal protection temperature threshold is used as the target constraint of the objective function. The objective function includes the tracking of the actual inlet water temperature of the engine to the target inlet water temperature and the fan power consumption. The speed prediction module is used to control the MPC algorithm to predict the fan speed based on the objective function and the objective constraint, so as to output the target fan speed. A water temperature control module is used to control the engine water temperature based on the target fan speed.

[0059] Furthermore, in one embodiment, the constraint update module is also used for: If the target parameter is detected to meet all target conditions at the same time, it is determined that the MPC algorithm has a risk of violating hard constraints. The target conditions include the actual outlet water temperature being greater than the outlet water temperature threshold, the difference between the actual outlet water temperature and the actual inlet water temperature being greater than the difference threshold, the historical fan speed being less than the speed threshold, and the rate of change of the speed corresponding to the historical fan speed being less than the rate of change threshold. If the target parameter is detected to not meet at least one target condition, it is determined that the MPC algorithm does not have the risk of violating hard constraints.

[0060] Furthermore, in one embodiment, the constraint update module is specifically used for: The target inlet water temperature or the target thermal protection temperature threshold corresponding to the hard constraint is adjusted according to the engine's current operating load.

[0061] Furthermore, in one embodiment, the constraint update module is specifically used for: If the current operating load is greater than the preset operating load threshold, the target inlet water temperature of the engine is reduced to obtain a new inlet water temperature; If the current operating load is less than or equal to the preset operating load threshold, the target thermal protection temperature threshold corresponding to the hard constraint is reduced to obtain a new thermal protection temperature threshold.

[0062] Furthermore, in one embodiment, the constraint update module is specifically used for: The target temperature adjustment amount is obtained by looking up the MAP table based on the current ambient temperature and current operating load. The target inlet water temperature is updated based on the target temperature adjustment amount to obtain a new inlet water temperature.

[0063] Furthermore, in one embodiment, the constraint update module is specifically used for: The target thermal protection temperature threshold adjustment amount is obtained by looking up the MAP table based on the current ambient temperature and current operating load. The target thermal protection temperature threshold is updated based on the adjustment amount of the target thermal protection temperature threshold to obtain a new thermal protection temperature threshold.

[0064] Furthermore, in one embodiment, the speed prediction module is also used to: when it is detected that the MPC algorithm does not have a risk of violating hard constraints based on the target parameters, control the MPC algorithm to predict the fan speed based on the target function, so as to output the target fan speed.

[0065] The functions of each module in the above-mentioned water temperature model prediction and control device correspond to the steps in the above-mentioned water temperature model prediction and control method embodiment, and their functions and implementation processes will not be described in detail here.

[0066] Thirdly, embodiments of this application provide a water temperature model prediction and control device, which can be a personal computer (PC), laptop computer, server, or other device with data processing capabilities.

[0067] Reference Figure 5 , Figure 5 This is a schematic diagram of the hardware structure of the water temperature model prediction and control device involved in the embodiments of this application. In the embodiments of this application, the water temperature model prediction and control device may include a processor, a memory, a communication interface, and a communication bus.

[0068] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0069] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting internal components of the water temperature model predictive control device, as well as interfaces used for interconnecting the water temperature model predictive control device with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0070] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0071] The processor can be a general-purpose processor, which can call the water temperature model prediction and control program stored in the memory and execute the water temperature model prediction and control method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the water temperature model prediction and control program is called can be referred to in the various embodiments of the water temperature model prediction and control method of this application, and will not be described again here.

[0072] Those skilled in the art will understand that Figure 5 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0073] Fourthly, embodiments of this application also provide a computer-readable storage medium.

[0074] The present application has a water temperature model prediction control program stored on a readable storage medium, wherein when the water temperature model prediction control program is executed by a processor, it implements the steps of the water temperature model prediction control method as described above.

[0075] The method implemented when the water temperature model predictive control program is executed can be referred to in various embodiments of the water temperature model predictive control method of this application, and will not be repeated here.

[0076] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0077] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0078] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0079] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0080] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0081] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0082] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A water temperature model predictive control method, characterized in that, The water temperature model prediction and control method includes: When the model predictive control (MPC) algorithm is detected to have a risk of violating hard constraints based on the target parameters, the target inlet water temperature of the engine or the target thermal protection temperature threshold corresponding to the hard constraints is adjusted to obtain a new inlet water temperature or a new thermal protection temperature threshold. The target parameters include the actual outlet water temperature and the actual inlet water temperature of the engine, as well as the historical fan speed predicted by the MPC algorithm. The new inlet water temperature or the new thermal protection temperature threshold is used as the objective constraint of the objective function, which includes the tracking of the engine's actual inlet water temperature to the target inlet water temperature and the fan power consumption. The control MPC algorithm predicts the fan speed based on the objective function and the objective constraint, and outputs the target fan speed. The engine coolant temperature is controlled based on the target fan speed.

2. The water temperature model prediction and control method as described in claim 1, characterized in that, Before the step of detecting a risk of hard constraint violation in the Model Predictive Control (MPC) algorithm based on the target parameters, the method further includes: If the target parameter is detected to meet all target conditions at the same time, it is determined that the MPC algorithm has a risk of violating hard constraints. The target conditions include the actual outlet water temperature being greater than the outlet water temperature threshold, the difference between the actual outlet water temperature and the actual inlet water temperature being greater than the difference threshold, the historical fan speed being less than the speed threshold, and the rate of change of the speed corresponding to the historical fan speed being less than the rate of change threshold. If the target parameter is detected to not meet at least one target condition, it is determined that the MPC algorithm does not have the risk of violating hard constraints.

3. The water temperature model prediction and control method as described in claim 1, characterized in that, The adjustment of the target inlet water temperature of the engine or the target thermal protection temperature threshold corresponding to the hard constraint to obtain a new inlet water temperature or a new thermal protection temperature threshold includes: The target inlet water temperature or the target thermal protection temperature threshold corresponding to the hard constraint is adjusted according to the engine's current operating load to obtain a new inlet water temperature or a new thermal protection temperature threshold.

4. The water temperature model prediction and control method as described in claim 3, characterized in that, The adjustment of the target inlet water temperature or the target thermal protection temperature threshold corresponding to the hard constraint based on the engine's current operating load to obtain a new inlet water temperature or a new thermal protection temperature threshold includes: If the current operating load is greater than the preset operating load threshold, the target inlet water temperature of the engine is reduced to obtain a new inlet water temperature; If the current operating load is less than or equal to the preset operating load threshold, the target thermal protection temperature threshold corresponding to the hard constraint is reduced to obtain a new thermal protection temperature threshold.

5. The water temperature model prediction and control method as described in claim 4, characterized in that, The process of reducing the target inlet water temperature of the engine to obtain a new inlet water temperature includes: The target temperature adjustment amount is obtained by looking up the MAP table based on the current ambient temperature and current operating load. The target inlet water temperature is updated based on the target temperature adjustment amount to obtain a new inlet water temperature.

6. The water temperature model prediction and control method as described in claim 4, characterized in that, The process of reducing the target thermal protection temperature threshold corresponding to the hard constraint to obtain a new thermal protection temperature threshold includes: The target thermal protection temperature threshold adjustment amount is obtained by looking up the MAP table based on the current ambient temperature and current operating load. The target thermal protection temperature threshold is updated based on the adjustment amount of the target thermal protection temperature threshold to obtain a new thermal protection temperature threshold.

7. The water temperature model prediction and control method as described in claim 1, characterized in that, The method further includes: When it is detected that the MPC algorithm does not have a risk of violating hard constraints based on the target parameters, the MPC algorithm is controlled to predict the fan speed based on the target function, so as to output the target fan speed.

8. A water temperature model prediction and control device, characterized in that, The water temperature model prediction and control device includes: The constraint update module is used to adjust the target inlet water temperature of the engine or the target thermal protection temperature threshold corresponding to the hard constraint when the model predictive control (MPC) algorithm is detected to have a risk of violating hard constraints based on the target parameters, so as to obtain a new inlet water temperature or a new thermal protection temperature threshold. The target parameters include the actual outlet water temperature and the actual inlet water temperature of the engine and the historical fan speed predicted by the MPC algorithm. The new inlet water temperature or the new thermal protection temperature threshold is used as the target constraint of the objective function. The objective function includes the tracking of the actual inlet water temperature of the engine to the target inlet water temperature and the fan power consumption. The speed prediction module is used to control the MPC algorithm to predict the fan speed based on the objective function and the objective constraint, so as to output the target fan speed. A water temperature control module is used to control the engine water temperature based on the target fan speed.

9. A water temperature model prediction and control device, characterized in that, The water temperature model prediction and control device includes a processor, a memory, and a water temperature model prediction and control program stored in the memory and executable by the processor, wherein when the water temperature model prediction and control program is executed by the processor, it implements the steps of the water temperature model prediction and control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a water temperature model prediction and control program, wherein when the water temperature model prediction and control program is executed by a processor, it implements the steps of the water temperature model prediction and control method as described in any one of claims 1 to 7.

Images