KR-102964280-B1 - Control system and method for integrated thermal management system of vehicle based on AI

KR102964280B1KR 102964280 B1KR102964280 B1KR 102964280B1KR-102964280-B1

Abstract

The present invention relates to a control system and a control method for an artificial intelligence-based vehicle integrated thermal management system. The objective of the present invention is to provide a control system and a control method for an artificial intelligence-based vehicle integrated thermal management system, wherein an optimal target value is calculated to perform optimal control of the vehicle thermal management system, and a control signal is generated to track the calculated optimal target value, and wherein the generated control signal can be implemented without deviating from the hardware characteristics of the vehicle thermal management system through the implementation of artificial intelligence learning control.

Inventors

김중재
이정훈
고원식

Assignees

한온시스템 주식회사

Dates

Publication Date: 20260513
Application Date: 20220107
Priority Date: 20210113

Claims (13)

In a system for optimal control of an integrated thermal management system of a vehicle, A target value setting unit (100) that generates a target value considering energy efficiency according to input environmental condition information; A control value calculation unit (200) that generates a target control value for tracking the target setting value based on the target setting value generated by the target value setting unit (100); and A control value output unit (300) that determines whether the target control value generated by the control value calculation unit (200) is included within the safety control range of the integrated thermal management system of the vehicle that has been pre-set, and sets an output control value according to the result of the determination; Includes, The above control value calculation unit (200) is AI control unit (210) that generates the above target control value by applying two or more AI learning models; An existing control unit (220) that calculates the target control value through a hardware control means equipped with a mechanism; and A learning processing unit (230) that uses two or more AI learning engines, wherein each AI learning engine learns and processes input parameters including each environmental condition information, a main control variable having the most optimal energy efficiency according to each environmental condition information, a target setting value for control to the main control variable having the most optimal energy efficiency based on each environmental condition information, and a tracking control value to each target setting value based on the state information of the variables, and generates the AI learning model that outputs the most optimal tracking control value; Includes more, The above learning processing unit (230) A control system for an AI-based vehicle integrated thermal management system that updates the AI learning model applied to the AI control unit (210) to the latest by repeatedly performing learning by each of the above AI learning engines at predetermined intervals.
In Article 1, The above target value setting unit (100) is An analysis unit (110) receives collected data including environmental condition information collected under various experimental conditions from a connected big data server (10), control information of variables matching the collected environmental condition information, and energy consumption information based on the control information, and extracts key control variables having the most optimal energy efficiency according to each environmental condition information; A DB unit (120) that receives each major control variable matching each environmental condition information extracted by the analysis unit (110), stores and manages it in a database; and A target value derivation unit (130) that matches the input environmental condition information with the information stored by the DB unit (120), extracts key control variables having the most optimal energy efficiency based on the input environmental condition information, and generates the target setting value; A control system for an artificial intelligence-based vehicle integrated thermal management system that further includes
In Paragraph 2, The above analysis unit (110) A control system for an artificial intelligence-based vehicle integrated thermal management system that receives the collected data from the big data server (10) at a predetermined periodic interval, updates the main control variables extracted according to each environmental condition information and input current vehicle status information, and updates the DB unit (120).
In Article 1, The above AI control unit (210) is Two or more AI learning models are applied by the learning processing unit (230) to output the most optimal tracking control value for tracking the target setting value generated by the target value setting unit (100) based on the current state information of the variables, and the target control value is generated. The above existing control unit (220) is A control system for an artificial intelligence-based vehicle integrated thermal management system that calculates a target control value to follow the target setting value generated by the target value setting unit (100) based on the current state information of the variables through a hardware control means provided.
delete
In Paragraph 4, The above learning processing unit (230) By analyzing the above input parameters, the input parameters are grouped into major groups based on the above major control variables, and for each major control variable, the input parameters are grouped into minor groups based on the linkage factors that affect the corresponding major control variable. A control system for an AI-based vehicle integrated thermal management system, wherein each AI learning engine learns the input parameters grouped into subgroups and generates an AI learning model in which the corresponding linkage factor outputs the most optimal tracking control value for controlling the main control variable.
In Paragraph 4, The above control value output unit (300) is A judgment unit (310) that determines whether the target control value generated by the AI control unit (210) is included within the safety control range of the vehicle's integrated thermal management system that is preset; and A control output unit (320) that, according to the judgment result of the judgment unit (310), if the target control value generated by the AI control unit (210) deviates from the safety control range, sets the target control value generated by the existing control unit (220) as the output control value; Includes more, The above control output unit (320) is A control system for an artificial intelligence-based vehicle integrated thermal management system that, according to the judgment result of the judgment unit (310), if the target control value generated by the AI control unit (210) is included within the safety control range, sets the target control value generated by the AI control unit (210) as the output control value.
In a method for optimal control of an integrated thermal management system of a vehicle, In the target value setting unit, a DB creation step (S100) is performed to receive collected data including environmental condition information collected under various experimental conditions from a connected big data server, control information of variables matching the collected environmental condition information, and energy consumption information based on the control information, to extract key control variables having the most optimal energy efficiency according to each environmental condition information, and to receive each key control variable matching each extracted environmental condition information, and to create a database to store and manage the data. A target value setting step (S200) that generates a target value considering energy efficiency according to input environmental condition information in the target value setting unit; In the control value calculation unit, a control value setting step (S300) generates a target control value that follows the target setting value generated by the target value setting step (S200) based on the current state information of the variables; In the control value output unit, a determination step (S400) for determining whether the target control value generated by the control value setting step (S300) is included within the safety control range of the vehicle's integrated thermal management system that is preset; and In the control value output unit, an output value setting step (S500) sets the target control value as the output control value according to the judgment result of the judgment step (S400); Includes, The above control value setting step (S300) is AI control value setting step (S310) for generating the above target control value by applying two or more AI learning models; A conventional control value setting step (S320) for calculating the target control value through a hardware control means provided in the past; and A learning processing step (S330) for generating the AI learning model that outputs the most optimal tracking control value by using two or more AI learning engines, wherein each AI learning engine learns input parameters including each environmental condition information, a main control variable having the most optimal energy efficiency according to each environmental condition information, a target setting value for control to the main control variable having the most optimal energy efficiency based on each environmental condition information, and a tracking control value to each target setting value based on the state information of the variables; Includes more, The above learning processing step (S330) is A control method for an AI-based vehicle integrated thermal management system, wherein learning by the AI learning engine is repeatedly performed at predetermined intervals to update the AI learning model applied in the AI control value setting step (S310) to the latest version.
In Paragraph 8, The above DB creation step (S100) is A control method for an artificial intelligence-based vehicle integrated thermal management system, wherein the collected data is transmitted from the big data server at a predetermined interval, and the main control variables extracted according to each environmental condition information and input current vehicle status information are updated to update the database.
In Paragraph 8, The above AI control value setting step (S310) is Two or more AI learning models are applied according to the above learning processing step (S330) to output the most optimal tracking control value that tracks the above target setting value generated based on the current state information of the variables, and the above target control value is generated. The above existing control value setting step (S320) is A control method for an artificial intelligence-based vehicle integrated thermal management system, which calculates a target control value that follows the target set value generated based on current state information of variables through a hardware control means provided.
delete
In Article 10, The above learning processing step (S330) is By analyzing the above input parameters, the input parameters are grouped into major groups based on the above major control variables, and for each major control variable, the input parameters are grouped into minor groups based on the linkage factors that affect the corresponding major control variable. A control method for an AI-based vehicle integrated thermal management system, wherein each AI learning engine learns the input parameters grouped into subgroups and generates an AI learning model in which the corresponding linkage factor outputs the most optimal tracking control value for controlling the main control variable.
In Article 10, The above judgment step (S400) is In the above AI control value setting step (S310), it is determined whether the target control value is included within the safety control range of the vehicle's integrated thermal management system that is preset, and The above output value setting step (S500) is According to the result of the judgment step (S400), if the target control value generated by the AI control value setting step (S310) is included within the safety control range, the target control value generated by the AI control value setting step (S310) is set as the output control value. A control method for an artificial intelligence-based vehicle integrated thermal management system, wherein, depending on the result of the judgment step (S400), if the target control value generated by the AI control value setting step (S310) deviates from the safety control range, the target control value generated by the existing control value setting step (S320) is set as the output control value.

Description

Control system and method for integrated thermal management system of vehicle based on AI The present invention relates to a control system and a control method for an artificial intelligence-based vehicle integrated thermal management system, and more specifically, to a control system and a control method for an artificial intelligence-based vehicle integrated thermal management system capable of implementing optimal control such that the generated control signal does not deviate from the hardware characteristics of the vehicle thermal management system, wherein the control signal is generated to track an optimal target value calculated to perform optimal control of the vehicle thermal management system. Eco-friendly vehicles refer to pure electric vehicles that drive using an electric motor, hybrid vehicles that run on both an engine and an electric motor, and fuel cell vehicles that drive an electric motor using electricity generated from a fuel cell. These eco-friendly vehicles have been developed to minimize environmental problems and resource depletion issues, such as environmental pollution caused by exhaust gases from conventional internal combustion engine vehicles, global warming caused by carbon dioxide, and the induction of respiratory diseases due to ozone formation. Just like conventional internal combustion engine vehicles, eco-friendly vehicles require cooling and heating devices to cool or heat up heat generated from various components, such as high-voltage parts, and, of course, are equipped with heating and cooling systems to provide and maintain a comfortable environment inside the vehicle. For example, eco-friendly vehicles are equipped with water pipes to address self-heating in components such as powertrains containing various power electronic parts or high-voltage batteries, and a cooling system is configured to supply and circulate coolant through these pipes so that the coolant absorbs the heat generated from the corresponding parts. The flow of this coolant is controlled through an integrated thermal management system, which is used to control the air conditioning state so that the driver can drive in a comfortable environment. Recently, it has become possible to provide an optimized air conditioning state by considering the current usage environment (outdoor temperature, indoor temperature, etc.) without the user directly controlling the air conditioning system, or to provide an optimized air conditioning state by learning the user's usual usage habits using AI learning and considering the current usage environment and the user's habits. However, when controlling the air conditioning state using AI learning in this way, the air conditioning state may be controlled without considering the hardware characteristics of the refrigerant system itself. If such an air conditioning state persists, problems may arise, such as a decrease in cooling efficiency and performance, a reduction in vehicle fuel economy (electric efficiency) and vehicle drive motor output, or even damage to the refrigerant system itself. In this regard, Korean registered patent No. 10-1199665 ("Learning-type vehicle air conditioning control method") discloses a method for maintaining an air conditioning state that suits the user's preferences when automatically air-conditioning by learning the user's usage habits; however, this method still includes the problem that the air conditioning state is controlled without considering the hardware characteristics of the refrigerant system itself, as described above. FIG. 1 is an example diagram of the configuration of a control system of an artificial intelligence-based vehicle integrated thermal management system according to one embodiment of the present invention. FIG. 2 is a detailed configuration example of a control value calculation unit (200) in a control system of an artificial intelligence-based vehicle integrated thermal management system according to one embodiment of the present invention. FIG. 3 is an example flowchart of a control method for an artificial intelligence-based vehicle integrated thermal management system according to an embodiment of the present invention. Hereinafter, a control system and a control method of an artificial intelligence-based vehicle integrated thermal management system according to the present invention having the configuration as described above will be explained in detail with reference to the attached drawings. Furthermore, a system refers to a set of components, including devices, mechanisms, and means, that are organized and interact regularly to perform necessary functions. A control system and a control method for an artificial intelligence-based vehicle integrated thermal management system according to one embodiment of the present invention are a control system and a control method for performing optimal control in terms of reducing energy consumption of an existing vehicle integrated thermal management system, wherein t