SYSTEM AND METHOD FOR HYBRID COOLING OF AN ENGINE

Abstract

The present invention provides a system (100) and a method (2000) for hybrid cooling of an engine (400). The system (100) receives one or more parameters detected by sensors (200) connected to the system (100). Based on these parameters, the system (100) generates an action to control actuators (300) connected to the engine (400). Through a two-headed hybrid network, the system (100) determines a compensation value in real time based on the parameters and the action. The system (100) also generates a guideline through this two-headed hybrid network to predict the degree of control to be applied to the actuators (300) based on this compensation value. Furthermore, through the two-headed hybrid network, the system (100) performs hybrid cooling of the engine (400) by controlling the actuators (300) based on the control amount to be applied to them.

Description

TECHNICAL AREA

[0001] The present invention relates to thermal management and cooling systems. In particular, the present invention relates to a system and a method for efficiently implementing hybrid cooling of an engine in a vehicle. BACKGROUND

[0002] In electric vehicles, the motors operate most efficiently within a specific temperature range. If the motor overheats, this can lead to reduced efficiency, lower power output, and potential damage. Conversely, if the motor runs too cool, it cannot deliver its full power. Overheating can pose a safety risk, including the danger of fire and the failure of electrical components. Keeping the motor within the prescribed temperature range can prevent these risks.

[0003] Hybrid cooling systems combine different cooling methods (such as liquid and air cooling) to effectively control the engine's thermal behavior. This approach enables better heat dissipation and temperature control under changing operating conditions. The hybrid cooling system includes various actuators that adjust the cooling based on real-time data, such as temperature measurements and ambient conditions. This ensures that the engine remains within its optimal temperature range and adapts to changes in load and driving conditions. However, external factors such as ambient temperature, humidity, and airflow can significantly affect the engine's effective cooling. Existing cooling systems are not capable of dynamically responding to these environmental changes.

[0004] Many techniques have been developed to avoid the problems mentioned above. For example, patent US11936320B2 discloses a computer-implemented method for optimizing the thermal control of a vehicle engine, wherein the vehicle includes a cooling device with an actuator that varies the cooling power.The procedure involves training a reinforcement learning algorithm, which includes the following iterative steps: 1) Determining an action to control an actuator by applying a control function to a current state of the thermal system and implementing the action; 2) Determining a modified state of the thermal system after implementing the action; 3) Computing a compensation value based on the modified state of the thermal system and the action by implementing a thermodynamic compensation function of the motor; 4) Updating a function to estimate thermal power based on the current state of the thermal system, the modified state of the thermal system, the action, and the compensation; and 5) Modifying the control function based on the update of the function to estimate thermal power.

[0005] Although the cited document reveals various techniques for optimizing the thermal control of the vehicle engine, it does not focus on hybrid engine cooling through training a two-headed hybrid network in an interactive environment via trial and error, using feedback from its own actions and experiences. Therefore, there is still room for improvement in developing a hybrid engine cooling solution. SUBJECT OF THE PRESENT INVENTION

[0006] A general object of the present invention is to provide a system and a method for efficiently carrying out hybrid cooling of an engine in a vehicle.

[0007] Another object of the present invention is to provide a system and a method for determining a remuneration value in real time by means of a two-headed hybrid network based on one or more parameters and at least one action implemented to control actuators operationally connected to the motor.

[0008] A further object of the present invention is to provide a system and a method for creating at least one strategy based on the compensation value through the dual-headed hybrid network, wherein the at least one strategy predicts a degree of control to be applied to the actuators for cooling the motor.

[0009] Another object of the present invention is to provide a system and a method for carrying out hybrid cooling of the engine through the two-headed hybrid network by controlling the actuators on the basis of the control amount to be applied to the actuators. SUMMARY

[0010] The present invention relates to thermal management and cooling systems. In particular, the present invention relates to a system and a method for implementing hybrid cooling of an engine in a vehicle in an efficient manner.

[0011] One aspect of the present invention relates to a system for the hybrid cooling of an engine. The system comprises a processor and memory connected to the processor. The memory contains one or more instructions executable by the processor, which, when executed, cause the processor to receive one or more parameters detected by one or more sensors connected to the system. Based on the one or more parameters, the processor generates at least one action to control one or more actuators operationally connected to the engine. The processor determines a compensation value in real time, based on the one or more parameters and the at least one action, through a two-headed hybrid network.The processor, through the two-headed hybrid network, creates at least one policy based on the compensation value, where the at least one policy predicts a degree of control to be applied to the one or more actuators. The processor, through the two-headed hybrid network, performs hybrid cooling of the motor by controlling the one or more actuators based on the amount of control to be applied to them.

[0012] In one embodiment, the one or more parameters can include at least an air temperature, an air velocity, a humidity level and an air pressure.

[0013] In one embodiment, the processor can be configured to determine the compensation value by executing at least one action. This at least one action can be implemented to detect whether one or more values ​​associated with the one or more parameters lie within a predefined trajectory range.

[0014] In one embodiment, the processor can be configured such that, if the one or more values ​​associated with the one or more parameters lie within the predetermined trajectory range, it determines the compensation value as a positive value and the at least one action as a successful action.

[0015] In one embodiment, the processor can be configured such that if one or more values ​​associated with one or more parameters lie outside the predetermined trajectory range, it determines the compensation value as a negative value and the at least one action as an error action.

[0016] In one embodiment, the processor can be configured to simultaneously determine the compensation value in real time through the hybrid two-head network and to create the at least one strategy through the hybrid two-head network by feeding one or more parameters and at least one action into the hybrid two-head network.

[0017] In one embodiment, the dual-headed hybrid network can be trained in an interactive environment based on feedback received in real time after the execution of at least one action and the determination of the compensation value.

[0018] In one embodiment, the degree of control applied to the actuator(s) can be a degree of speed control, a degree of fan control, and a degree of coolant flow control.

[0019] In one embodiment, the processor can be configured to perform hybrid cooling of the motor using a reinforcement learning technique via the dual-headed hybrid network.

[0020] One aspect of the present invention relates to a method for the hybrid cooling of an engine. The method comprises the reception of one or more parameters, detected by one or more sensors connected to the system, by a processor connected to the system. The method comprises the generation of at least one action by the processor to control one or more actuators operationally connected to the engine, based on the one or more parameters. The method comprises the determination of a compensation value by the processor in real time using a two-headed hybrid network, based on the one or more parameters and the at least one action.The method comprises generating, by the processor, through the dual-headed hybrid network, at least one guideline based on the compensation value, wherein the at least one guideline predicts a degree of control to be applied to the one or more actuators. The method comprises performing hybrid cooling of the motor by the processor, through the dual-headed hybrid network, by controlling the one or more actuators based on the degree of control to be applied to the one or more actuators.

[0021] Various objects, features, aspects and advantages of the invention will become clearer from the following detailed description of preferred embodiments together with the accompanying drawings, in which the same numbers represent the same components. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings serve to further understand the present invention and are an integral part of this description. The drawings illustrate exemplary embodiments of the present invention and, together with the description, serve to explain the principles of the present invention. Fig. Figure 1 shows a block diagram of a system for hybrid cooling of an engine according to the embodiments of the present invention. Fig. Figure 2 shows a flowchart for the implementation of a method for hybrid cooling of an engine according to the embodiments of the present invention. Fig. 3A and Fig. Figure 3B shows exemplary representations of a dual-headed hybrid network according to the embodiments of the present invention. Fig. Figure 4 shows an example of a computer system in which or with which embodiments of the system according to the embodiments of the present invention can be implemented. DETAILED DESCRIPTION

[0023] A detailed description of embodiments of the invention, illustrated in the accompanying drawings, follows. The embodiments are described in sufficient detail to clearly demonstrate the invention. However, this level of detail is not intended to limit foreseeable variations of embodiments; on the contrary, it is intended to cover all modifications, equivalents, and alternatives that fall within the scope of the present invention as defined by the accompanying claims.

[0024] The present invention relates to thermal management and cooling systems. In particular, the present invention relates to a system and a method for implementing hybrid cooling of an engine in a vehicle in an efficient manner.

[0025] One aspect of the present invention relates to a system for the hybrid cooling of an engine. The system comprises a processor and memory connected to the processor. The memory contains one or more instructions executable by the processor, which, when executed, cause the processor to receive one or more parameters detected by one or more sensors connected to the system. Based on the one or more parameters, the processor generates at least one action to control one or more actuators operationally connected to the engine. The processor determines a compensation value in real time, based on the one or more parameters and the at least one action, through a dual-headed hybrid network.The processor, through the two-headed hybrid network, creates at least one policy based on the compensation value, where the at least one policy predicts a degree of control to be applied to the one or more actuators. The processor, through the two-headed hybrid network, performs hybrid cooling of the motor by controlling the one or more actuators based on the amount of control to be applied to them.

[0026] One aspect of the present invention relates to a method for the hybrid cooling of an engine. The method comprises the reception of one or more parameters, detected by one or more sensors connected to the system, by a processor connected to the system. The method comprises the generation of at least one action by the processor to control one or more actuators operationally connected to the engine, based on the one or more parameters. The method comprises the determination of a compensation value by the processor in real time using a two-headed hybrid network, based on the one or more parameters and the at least one action.The method comprises generating, by the processor, through the dual-headed hybrid network, at least one guideline based on the compensation value, wherein the at least one guideline predicts a degree of control to be applied to the one or more actuators. The method comprises performing hybrid cooling of the motor by the processor, through the dual-headed hybrid network, by controlling the one or more actuators based on the degree of control to be applied to the one or more actuators.

[0027] Various embodiments of the present invention are described in detail with reference to the Fig. 1-4.

[0028] Fig. Figure 1 shows a block diagram of a system 100 for the hybrid cooling of an engine according to the embodiments of the present invention.

[0029] In relation to Fig. For example, a vehicle 1000 can be a hybrid electric vehicle. The vehicle 1000 can comprise a system 100, one or more sensors 200, one or more actuators 300, and a motor 400.

[0030] In one embodiment, the system 100 may include one or more processor(s) 102. The processor(s) 102 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and / or any devices that process data based on operating instructions. Among other capabilities, the one or more processor(s) 102 may be configured to retrieve and execute computer-readable instructions stored in a memory 104. The memory 104 may store the computer-readable instructions or routines that can be retrieved and executed to create the data units or to pass them to other elements of the system 100. The memory 104 may comprise any non-volatile storage device, such as...volatile memory such as Random-Access Memory (RAM) or non-volatile memory such as Erasable Programmable Read-Only Memory (EPROM), Flash memory, and the like.

[0031] In some embodiments, the system 100 may also include one or more interfaces 106. The interface(s) 106 may include a variety of interfaces, such as interfaces for data input and output devices, referred to as I / O devices, storage devices, and the like. The interface(s) 106 may facilitate communication between the system 100 and other components of the vehicle by using peripheral devices that enable wired and / or wireless communication. The interface(s) 106 may also provide a communication path for one or more components within the system 100. Examples of such components include, but are not limited to, the processing machine(s) 108 and a database 110.

[0032] The database 110 can contain data that is either stored or generated as a result of functions implemented by one of the components of the processing machine(s) 108.

[0033] In one embodiment, the sensors 200 may include, among other things, a coolant temperature sensor, an ambient temperature sensor, a pressure sensor, a humidity sensor, a speed sensor, and battery and energy management sensors. The sensors 200 may be configured to detect one or more parameters within the vehicle 1000. These parameters may include, among others, air temperature, air velocity, humidity, air pressure, and similar values. The sensors 200 may be communicatively connected to the system 100. The sensors 200 may be configured to transmit values ​​of the one or more parameters to the system 100.

[0034] In one embodiment, the actuators 300 can include, among other things, centrifugal fans, cooling pumps, and coolant fans. The actuators 300 can be operatively connected to the engine 400 housed in the engine compartment. The centrifugal fans can be used to draw air through the engine compartment to dissipate heat from critical components. By providing an efficient airflow, the centrifugal fans can maintain optimal operating temperatures for an internal combustion engine connected to the engine 400, thus contributing to overall performance and efficiency. The cooling pumps can be operated in conjunction with other components, such as thermostats and temperature sensors, to optimize cooling based on real-time conditions.The coolant fans can generate an additional airflow through the radiator pumps when the vehicle is idling or traveling at low speeds where the natural airflow is insufficient.

[0035] In one embodiment, the motor 400 can provide propulsion during acceleration and charge a battery pack during braking or deceleration. Although the motors 400 have a high efficiency, they generate considerable heat depending on the torque and speed required for operation. Therefore, it is necessary to manage the heat and efficiently cool the motor 400 by controlling the actuators 300.

[0036] In one embodiment, the processing machine(s) 108 can be implemented as a combination of hardware and software (e.g., programmable instructions) to implement one or more functions of the processing machine(s) 108. In the examples described here, such combinations of hardware and software can be implemented in various ways. For instance, the software for the processing machine(s) 108 can consist of processor-executable instructions stored on a non-volatile, machine-readable storage medium, and the hardware for the processing machine(s) 108 can include a processing resource (e.g., one or more processors) to execute such instructions. In other embodiments, the processing machine(s) 108 can be implemented by an electronic circuit.

[0037] In some embodiments, the one or more processor(s) 102 can receive one or more parameters via the processing machine(s) 108, which are detected by the sensors 200 connected to the system 100. In some embodiments, the one or more processors 102 can generate at least one action for controlling the actuators 300 operationally connected to the motor 400, based on the one or more parameters, via the processing machine(s) 108.

[0038] In some embodiments, a hybrid network with two heads can be trained in an interactive environment by feeding one or more parameters and at least one action into the hybrid network with two heads, as in the Fig. 3A and Fig. 3B. In some embodiments, the one or more processor(s) 102 can determine a compensation value in real time via the processing machine(s) 108 through the hybrid dual-head network, based on the one or more parameters and the at least one action. The one or more processor(s) 102 can determine the compensation value by executing the at least one action. The at least one action can be implemented to detect whether the values ​​associated with the one or more parameters lie within a predetermined trajectory range. If the one or more values ​​associated with the one or more parameters lie within the predetermined trajectory range, the one or more processors 102 can be configured to determine the compensation value as a positive value and the at least one action as a successful action.If one or more values ​​associated with one or more parameters lie outside the predetermined trajectory range, the one or more processors 102 can be configured to determine the compensation value as a negative value and the at least one action as a failure. Based on the determination of the compensation value, the one or more processor(s) 102 can send feedback to the two-headed hybrid network via the processing machine(s) 108.

[0039] In some embodiments, the one or more processors 102 can, via the processing machine(s) 108 and the dual-headed hybrid network, create at least one guideline based on the compensation value. The at least one guideline is a function that maps the one or more parameters to the at least one action. The at least one guideline can be created to predict a degree of control to be applied to the actuators 300. The degree of control to be applied to the actuators 300 can include, among other things, a degree of speed control, a degree of fan control, and a degree of coolant flow control.

[0040] The hybrid two-head network can be trained to simultaneously determine the compensation value in real time, create at least one policy, and output the compensation value via a value header and the at least one policy via a policy header, as shown in Fig. Figure 3A illustrates this. The hybrid two-head network can be trained in the interactive environment based on feedback received after performing at least one action and determining the compensation value in real time.

[0041] In some embodiments, the one or more processor(s) 102 can control the actuators 300 in a continuous operating state via the processing machine(s) 108, based on the control amount applied to the actuators 300. By controlling the actuators 300, the one or more processor(s) 102 can implement hybrid cooling of the motor 400 via the two-head hybrid network via the processing machine(s) 108. The one or more processor(s) 102 can implement hybrid cooling of the motor 400 using a reinforcement learning technique via the processing module(s) 108.

[0042] Fig. Figure 2 shows a flowchart for carrying out a method 2000 for hybrid cooling of the motor 400 according to the embodiments of the present invention. Fig. The reference numbers 214, 216, 218, 220, 222, 224, 226, 228, 230, 232, 234, 236, 238, 240, 242 and 244 represent heat dissipation rate, heat generation, rotational speed, torque, loss calculation, control of coolant flow, mechanical power (torque, rotational speed), electrical power (current, voltage), airflow, coolant flow, heat pipes, optimal power consumption for cooling depending on the operating environment, guideline, sensor data, environment or specified trajectory range.

[0043] With reference to Fig. 2. The procedure 2000 can comprise one or more steps for carrying out the hybrid cooling of the motor 400. The one or more steps can be executed by the processor 102 connected to the system 100.

[0044] In 202, the procedure 2000 can include the reception of one or more parameters detected by the sensors 200 connected to the system 100.

[0045] In 204, the method 2000 can include generating at least one action 201-b to control the actuators 300 operationally connected to the motor 400 on the basis of one or more parameters.

[0046] In the case of 206, the procedure 2000 can include the processor 102 determining the compensation value 206-a in real time through the two-headed hybrid network 209, based on one or more parameters and at least one action. The at least one action is implemented to detect whether one or more values ​​associated with the one or more parameters lie within a predefined trajectory range 244.

[0047] In the case of 208, the procedure 2000 can include the transfer of the remuneration value 206-a to the two-head hybrid network 209. The two-head hybrid network can be configured to generate signals corresponding to the remuneration value.

[0048] At 210, the procedure 2000 can include the creation of at least one guideline 238 by the dual-headed hybrid network 209 based on the generated signals corresponding to the compensation value. The at least one guideline 238 can be created to predict the extent of control to be applied to the actuators 300. The extent of control to be applied to the actuators 300 can include, among other things, the extent of speed control of the actuators 300, the extent of fan control, and the extent of coolant flow control 224.

[0049] In 212, the method 2000 can include the implementation of hybrid cooling of the motor 400 by the two-head hybrid network 209, by controlling the actuators 300 based on the control amount to be applied to the actuators 300. The hybrid cooling of the motor 400 can be carried out by converting one or more signals generated by the two-head hybrid network 209, corresponding to at least one action.

[0050] Fig. 3A and Fig. Figures 3B show exemplary illustrations 300A and 300B of a hybrid network with two heads according to the embodiments of the present invention. Fig. In 3A, the reference numbers 302 and 304 represent the value header and the guideline header, respectively. Fig. The reference numbers 306, 308, 310, 312-1, 312-2, 312-3, 312-N, 314, 316 and 318 represent the main network, the network, the entrance(s), worker 1, worker 2, worker 3, worker N, air temperature, air velocity and humidity.

[0051] With reference to Fig. 3A and Fig. 3B allows the two-head hybrid network to be trained in the interactive environment by inputting one or more parameters and at least one action into the two-head hybrid network. The one or more parameters can include, among others, air temperature (314), air velocity (316), humidity (318), and air pressure. The two-head hybrid network can determine the compensation value in real time based on the one or more parameters and the at least one action. The two-head hybrid network can create at least one policy based on the compensation value. The two-head hybrid network can create at least one policy based on the actual value / compensation value of any action (e.g., actuator setting) at a given temperature.

[0052] Implementing a dual-head hybrid network can fundamentally change a control design for training as a hybrid approach. One or more parameters can be shared to converge a gradient for both the value head and the policy head simultaneously. This can be more consistent and stable because it does not rely on assumptions about a target environment. This avoids errors and instability, as the dual-head hybrid network cannot over- or underestimate the reward values ​​of certain actions, which is a key reason for efficient cooling.

[0053] By employing the dual-headed hybrid network, System 100 learns to handle extreme nonlinear conditions, thereby fostering human-like intelligence within System 100. This allows the dual-headed hybrid network to determine the appropriate level of actuator control based on the operating environment of Vehicle 1000, resulting in significant energy savings while simultaneously increasing the engine's lifespan and safety.

[0054] Furthermore, the hybrid network with two heads can process each of the one or more parameters, such as, but not limited to, air temperature 314, air velocity 316, and humidity 318, based on its adaptability, without combining the one or more parameters as in Fig. Figure 3B illustrates this. Ultimately, a master network 306 can integrate all the machine intelligence. This represents a significant advancement in training large environmental datasets to create a more efficient system. Due to its inherent flexibility, the System 100 with the hybrid network can operate in both continuous and discrete environments (e.g., air velocity vs. air temperature). Furthermore, a worker node can be extended to incorporate new environmental factors for precise training, providing greater flexibility without requiring a complete redesign of the System 100, as shown in Figure 3B. Fig. 3B is shown.

[0055] Fig. Figure 4 shows an example of a computer system 4000 in which or with which embodiments of the system 100 according to the embodiments of the present invention can be implemented.

[0056] System 100 and Procedure 2000 can be implemented in a Computer System 4000. As in Fig.As shown in Figure 4, the computer system 4000 can comprise an external storage device 410, a bus 420, main memory 430, read-only memory 440, a mass storage device 450, a communication port 460, and a processor 470. A person skilled in the art will understand that the computer system 4000 can comprise more than one processor 470 and communication ports 460. The processor 470 can include various modules connected to embodiments of the present invention. The communication port 460 can be a recommended standard 232 port for use with a modem-based dial-up connection, a 10 / 100 Ethernet port, a Gigabit or 10 Gigabit port over copper or fiber optic cable, a serial port, a parallel port, or other existing or future ports. The communication port 460 can be selected depending on the network, e.g.,a Local Area Network (LAN), a Wide Area Network (WAN) or any other network to which the Computer System 4000 is connected.

[0057] In one embodiment, the memory 430 can be random-access memory (RAM) or any other dynamic storage device generally known in the art. The read-only memory (ROM) 440 can be any static storage device, such as, but not limited to, a programmable read-only memory (PROM) chip for storing static information. The mass storage device 450 can be any current or future mass storage solution that can be used to store information and / or instructions. Examples of mass storage solutions include, but are not limited to: Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, such as with Universal Serial Bus (USB) and / or FireWire interfaces), one or more optical disks, redundant array of independent disks (RAID) storage, etc.an array of hard drives (e.g. SATA arrays).

[0058] In one embodiment, bus 420 provides communication between the processor(s) 470 and the other memory, storage, and communication blocks. Bus 420 can be, for example, a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), USB, or similar, for connecting expansion cards, drives, and other subsystems, as well as other buses, such as a Front Side Bus (FSB) that connects the processor 470 to the computer system 4000.

[0059] In another embodiment, operator and management interfaces, such as a screen, keyboard, and cursor control device, can also be connected to bus 420 to support direct operator interaction with the computer system 4000. Other operator and management interfaces can be provided via network connections made through communication port 460. In some embodiments, the external storage device 410 can be any type of external hard disk drive, floppy disk drive, Compact Disc - Read Only Memory (CD-ROM), Compact Disc - Re-Writable (CD-RW), or Digital Video Disc - Read Only Memory (DVD-ROM). The components described above are given only as examples of various possibilities. The computer system 4000 mentioned is not intended to limit the scope of the present invention in any way.

[0060] While the foregoing describes various embodiments of the present invention, other and further embodiments of the present invention can be developed without departing from the basic scope. The scope of the present invention is defined by the following claims. The present invention is not limited to the described embodiments, versions, or examples, which are included to enable a person with ordinary technical knowledge to manufacture and use the present invention when combined with the information and knowledge available to such a person. ADVANTAGES OF THE PRESENT INVENTION

[0061] The present invention enables efficient hybrid cooling of an engine installed in a vehicle.

[0062] The present invention simultaneously determines a compensation value in real time based on one or more parameters and at least one action implemented to control actuators, and creates a guideline based on the compensation value through a two-headed hybrid network.

[0063] Within the scope of the present invention, a control amount is predicted that must be applied to the actuators in order to cool the motor according to the guideline.

[0064] The present invention provides hybrid cooling of the engine through the double-headed hybrid network by controlling the actuators in a continuous driving condition. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] US 11936320B2

[0004]

Images