Intelligent thermal management method of new energy motor

Abstract

The invention discloses an intelligent thermal management method of a new energy motor, and relates to the technical field of thermal management. The method comprises the steps of building a thermal management mixing channel of a target new energy motor; performing multi-dimensional information perception on the target new energy motor to obtain a motor multi-dimensional perception data stream; determining a heat limit value of the cooling channel; activating a heat cooling channel to perform strategy analysis on the multi-dimensional sensing data flow of the motor, and determining control strategy parameters of the cooling system; if the motor heat exceeds the cooling channel heat limit value, a waste heat recovery channel is activated in parallel to conduct heat exchange analysis on the difference value between the motor heat and the cooling channel heat limit value, and heat exchange control parameters are obtained; and performing parallel closed-loop thermal management on the target new energy motor based on the cooling system control strategy parameters and the heat exchange control parameters. The technical problems of low heat management efficiency and insufficient energy utilization of the new energy motor in the prior art are solved, and the technical effects of improving the heat management efficiency, optimizing energy efficiency recovery and realizing closed-loop control are achieved.

Description

Technical Field

[0001] The present invention relates to the field of thermal management technology, and in particular to an intelligent thermal management method for a new energy motor. Background Art

[0002] With the continuous development of new energy technologies, new energy motors have been widely used in various electric vehicles, wind power generation and other energy systems. However, the heat generated by new energy motors when running at high loads often affects their stability and life. Therefore, how to efficiently perform thermal management to ensure that the motor operates within the optimal operating temperature range has become an important issue that the industry needs to solve urgently. Traditional motor thermal management systems usually rely on simple cooling methods and fail to effectively integrate heat cooling and waste heat recovery functions, resulting in low energy utilization. In addition, when faced with complex working environments, control strategies are often difficult to adapt to different working conditions. In addition, the existing thermal management system has a slow response speed and cannot adjust the operating status of the motor in time. It is prone to overheating or insufficient cooling, which affects the long-term stability and performance of the motor. Summary of the invention

[0003] The present application provides an intelligent thermal management method for new energy motors, which solves the technical problems of low thermal management efficiency and insufficient energy utilization of new energy motors in the prior art.

[0004] In view of the above problems, the present application provides an intelligent thermal management method for new energy motors.

[0005] The present application provides an intelligent thermal management method for a new energy motor, the method comprising: A thermal management hybrid channel for a target new energy motor is constructed, wherein the thermal management hybrid channel includes a heat cooling channel and a waste heat recovery channel; multi-dimensional information perception is performed on the target new energy motor to obtain a multi-dimensional perception data stream of the motor, wherein the multi-dimensional perception data stream of the motor includes motor heat, cooling system operation data and external environment data; based on the thermal cooling channel, a limit analysis is performed on the characteristic parameters and operating conditions of the target new energy motor to determine the heat limit of the cooling channel; the thermal cooling channel is activated to perform a strategy analysis on the multi-dimensional perception data stream of the motor to determine the control strategy parameters of the cooling system; if the heat of the motor exceeds the heat limit of the cooling channel, the waste heat recovery channel is activated in parallel to perform a heat exchange analysis on the difference between the motor heat and the heat limit of the cooling channel to obtain the heat exchange control parameters; a PID controller is introduced to perform parallel closed-loop thermal management on the target new energy motor based on the cooling system control strategy parameters and the heat exchange control parameters.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, build the thermal management hybrid channel of the target new energy motor. The thermal management hybrid channel includes a heat cooling channel and a waste heat recovery channel. Next, perform multi-dimensional information perception on the target new energy motor to obtain the motor multi-dimensional perception data stream, which includes motor heat, cooling system operation data, and external environment data. At the same time, based on the heat cooling channel, perform limit analysis on the characteristic parameters and operating conditions of the target new energy motor to determine the heat limit of the cooling channel. Then, activate the heat cooling channel to perform strategy analysis on the motor multi-dimensional perception data stream to determine the cooling system control strategy parameters. If the motor heat exceeds the heat limit of the cooling channel, parallelly activate the waste heat recovery channel to perform heat exchange analysis on the difference between the motor heat and the heat limit of the cooling channel to obtain the heat exchange control parameters. Finally, introduce a PID controller to perform parallel closed-loop thermal management on the target new energy motor based on the cooling system control strategy parameters and the heat exchange control parameters. This solves the technical problems of low thermal management efficiency and insufficient energy utilization of new energy motors in the prior art, and achieves the technical effects of improving thermal management efficiency, optimizing energy efficiency recovery, and realizing closed-loop control. Description of the Drawings

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0008] Figure 1 Schematic flowchart of the intelligent thermal management method for a new energy motor provided by an embodiment of the present application; Figure 2 Schematic flowchart of determining the heat limit of the cooling channel in the intelligent thermal management method for a new energy motor provided by an embodiment of the present application. Detailed Embodiments

[0009] The present application provides an intelligent thermal management method for a new energy motor, which solves the technical problems of low thermal management efficiency and insufficient energy utilization of new energy motors in the prior art.

[0010] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0011] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products, or devices.

[0012] Examples, such as Figure 1 As shown, the embodiments of the present application provide an intelligent thermal management method for a new energy motor. Among them, the method includes: Build a thermal management hybrid channel for the target new energy motor, and the thermal management hybrid channel includes a heat cooling channel and a waste heat recovery channel.

[0013] Build a thermal management hybrid channel in the target new energy motor. This channel consists of a heat cooling channel and a waste heat recovery channel. The heat cooling channel is used to directly cool the motor to reduce the heat generated by it; the waste heat recovery channel is used to recover the waste heat generated by the motor and effectively utilize it to improve the energy utilization efficiency. The heat cooling channel and the waste heat recovery channel do not work in isolation, but cooperate with each other to jointly form an efficient thermal management system. When the motor is operating normally, the heat cooling channel is responsible for maintaining the motor within an appropriate operating temperature range; when the heat generated by the motor exceeds the processing capacity of the cooling channel, the waste heat recovery channel is activated to recover and store or utilize the excess heat.

[0014] Perform multi-dimensional information perception on the target new energy motor to obtain a motor multi-dimensional perception data stream, and the motor multi-dimensional perception data stream includes motor heat, cooling system operation data, and external environment data.

[0015] Through the use of sensors, monitoring devices, and data acquisition systems, comprehensively perceive and real-time monitor the motor and its surrounding environment to obtain a motor multi-dimensional perception data stream. Multi-dimensional perception means not only monitoring a certain aspect of the motor, but simultaneously obtaining data on multiple dimensions related to the operating state and environment of the motor, so as to achieve a comprehensive understanding and control of the motor. The motor multi-dimensional perception data stream includes motor heat, cooling system operation data, and external environment data. Among them, the heat data of the motor includes the temperature information of the motor body, which is used to monitor the heat load generated by the motor during operation, judge whether the motor is within the normal operating temperature range, and whether additional cooling measures are required; the operation data of the cooling system involves parameters such as the flow rate, temperature, and pressure of the coolant. Through these data, the working state of the cooling system can be understood in real time, confirm whether it effectively takes away the heat generated by the motor, and then judge whether it is necessary to adjust the cooling system or activate the standby cooling channel; the external environment data includes factors such as the temperature, humidity, and air flow velocity of the working environment where the motor is located, and these external conditions directly affect the heat dissipation effect of the motor.

[0016] Based on the heat cooling channel, perform a limit analysis on the characteristic parameters and operating conditions of the target new energy motor to determine the heat limit of the cooling channel.

[0017] Based on the function of the heat cooling channel, perform a limit analysis on the characteristic parameters and operating conditions of the target new energy motor to determine the heat limit of the cooling channel. Specifically, by comprehensively considering the operating state, design parameters of the motor, and the working ability of the cooling channel, a safe heat range is set. The characteristic parameters of the motor include the rated power, working voltage, current, and heat capacity of the motor, etc. These parameters determine the maximum heat that the motor may generate during normal operation; the operating conditions refer to the actual working state of the motor under different loads, speeds, and working conditions. For example, under high load or high speed conditions, the motor will generate more heat. By analyzing these characteristic parameters and operating conditions, the heat change of the motor under various operating conditions can be calculated, so as to obtain the maximum heat that the cooling channel can withstand, that is, the heat limit of the cooling channel.

[0018] The purpose of setting the heat limit of the cooling channel is to ensure that the cooling system can dissipate the heat generated by the motor in a timely and effective manner, preventing performance degradation or damage caused by motor overheating. If the heat of the motor exceeds this limit, it means that the existing cooling system may not be able to meet the heat dissipation requirements, and corresponding measures need to be taken for intervention, such as activating additional cooling channels or starting the waste heat recovery channel, etc.

[0019] Furthermore, as Figure 2 shown, the determination of the heat limit of the cooling channel includes: Based on the characteristic parameters of the target new energy motor, drive 3D modeling to generate a 3D spatial component of the motor, and analyze the heat dissipation area and component working characteristics of the motor according to the 3D spatial component of the motor; perform an operating safety assessment on the heat dissipation area and component working characteristics of the motor according to the operating conditions to determine the heat-bearing safety margin of the motor; according to the heat cooling channel, obtain a multi-stage cooling system of the motor, analyze the heat dissipation limit of the multi-stage cooling system of the motor to obtain the heat dissipation threshold of the cooling system; take the cumulative value of the heat-bearing safety margin of the motor and the heat dissipation threshold of the cooling system as the heat limit of the cooling channel.

[0020] Specifically, using the characteristic parameters of the target new energy motor, such as rated power, current, voltage, material properties, etc., three-dimensional modeling is carried out to generate the three-dimensional space components of the motor; by analyzing the three-dimensional space components of the motor, the heat dissipation area of the motor and the working characteristics of each component can be obtained, such as heat dissipation efficiency, temperature change trend, etc.; according to the operating conditions of the motor, such as different loads, speeds, working environments, etc., the heat dissipation area of the motor and the working characteristics of each component are evaluated for operating safety. By simulating and analyzing the heat transfer process of the motor under different operating conditions, the heat-bearing safety margin of the motor is determined. The heat-bearing safety margin of the motor represents the additional heat that the motor can withstand under different operating conditions, ensuring that the motor will not overheat or be damaged due to insufficient heat dissipation. Further analyzing the design based on the heat cooling channels, a multi-stage cooling system for the motor is obtained. The multi-stage cooling system for the motor includes cooling channels of different levels, and each level of cooling channel may have different cooling capabilities and application ranges; by analyzing in detail the heat dissipation limit of the multi-stage cooling system for the motor, the maximum heat dissipation capacity of each level of cooling channel is evaluated to determine the heat dissipation threshold of the cooling system. The heat dissipation threshold of the cooling system is the maximum heat dissipation amount that the cooling system can achieve under different operating conditions. Adding the heat-bearing safety margin of the motor to the heat dissipation threshold of the cooling system gives the cumulative value of the two as the final heat limit of the cooling channel. The heat limit of the cooling channel represents the maximum heat range that the cooling system can effectively manage during the actual operation of the motor.

[0021] Activate the heat cooling channel to perform strategy analysis on the multi-dimensional perception data stream of the motor to determine the control strategy parameters of the cooling system.

[0022] When the operating state of the motor changes, activate the heat cooling channel, and at the same time start to receive and process the multi-dimensional perception data stream of the motor. By analyzing these real-time data, evaluate the current heat condition of the motor and the working state of the cooling system, and identify whether there is a risk of overheating or insufficient cooling, so as to determine the control strategy parameters. The control strategy parameters include coolant flow rate, temperature control threshold, cooling cycle and duration, etc. These strategy parameters will help adjust the operation mode of the cooling system to ensure that the motor temperature is always maintained within a reasonable range.

[0023] Furthermore, the determination of the control strategy parameters of the cooling system includes: Build a motor attribute classifier, classify the target new energy motor based on the motor attribute classifier to obtain target motor attribute parameters; call a cooling strategy analysis component library according to the heat cooling channel, and the cooling strategy analysis component library includes cooling strategy analysis components of different attribute types; match the target motor attribute parameters with the cooling strategy analysis component library to obtain a target cooling strategy analysis component; perform cooling strategy analysis on the motor multi-dimensional perception data stream based on the target cooling strategy analysis component to determine the cooling system control strategy parameters.

[0024] Specifically, by building a motor attribute classifier, classify the target new energy motor to obtain target motor attribute parameters, including the basic electrical characteristics of the motor (such as power, voltage, current), mechanical characteristics (such as speed, torque), and parameters related to thermal management (such as heat capacity, heat dissipation efficiency, etc.); the motor attribute classifier divides the motor into different attribute types according to various characteristic parameters of the motor, such as power, speed, rated current, voltage, etc., such as high-power motors, low-load motors, high-speed motors, etc. Next, according to the heat cooling channel, call the cooling strategy analysis component library. The cooling strategy analysis component library contains multiple cooling strategy analysis components suitable for different motor attribute types. Each component is an optimized cooling scheme according to specific attributes and working conditions, such as cooling strategies suitable for different working conditions such as high-load operation, high-temperature environment, and low-load. Then, match the target motor attribute parameters with each component in the cooling strategy analysis component library to select the target cooling strategy analysis component most suitable for the target motor. Finally, perform a detailed cooling strategy analysis on the motor multi-dimensional perception data stream based on the target cooling strategy analysis component. By analyzing these data, determine the cooling system control strategy parameters, including the flow rate of the coolant, the operating mode of the cooling system, the temperature control threshold, etc.

[0025] Furthermore, the calling of the cooling strategy analysis component library according to the heat cooling channel includes: Mine and obtain the historical cooling data set of the new energy motor, use the motor attribute classifier to perform clustering identification on the historical cooling data set of the new energy motor to obtain a historical cooling data set of a multi-attribute parameter motor; select a multi-attribute parameter cooling algorithm model according to the cooling control target and data characteristic information of the historical cooling data set of the multi-attribute parameter motor; use the multi-attribute parameter cooling algorithm model to perform strategy training and optimization on the historical cooling data set of the multi-attribute parameter motor respectively to obtain a set of multi-attribute parameter cooling strategy analysis components; perform attribute identification and integration on the set of multi-attribute parameter cooling strategy analysis components to obtain a cooling strategy analysis component library and store it in the heat cooling channel.

[0026] Specifically, mine the historical cooling data set from the historical operation data of the target new energy motor. This data includes information such as coolant flow rate, temperature change, and cooling efficiency of the motor under different loads, speeds, and environmental conditions. Use the constructed motor attribute classifier to cluster and label the historical cooling data set. The motor attribute classifier will classify the historical data according to the attributes of the motor (such as power, rotational speed, load conditions, etc.). For example, the motor is divided into multiple categories such as high-power low-load motors and low-power high-load motors. This clustering process organizes the historical data into multiple subsets with similar attributes, forming a multi-attribute parameter motor historical cooling data set. According to the cooling control objectives and data characteristics of the multi-attribute parameter motor historical cooling data set, select the most suitable multi-attribute parameter cooling algorithm model. For example, a dynamic adjustment model based on temperature sensor feedback or an adaptive control algorithm based on motor load changes may be selected. Based on the selected multi-attribute parameter cooling algorithm model, train and optimize the multi-attribute parameter motor historical cooling data set. Through training, the model can learn how to adjust the cooling strategy according to different motor attributes and operating condition parameters to keep the motor within a safe and stable temperature range. After training and optimization, multiple cooling strategy analysis components will be obtained. Each component is designed for specific motor attributes and working conditions. Integrate the attribute labels of these analysis components, and classify and summarize them according to motor attributes, working conditions, cooling requirements, etc. to form a complete cooling strategy analysis component library. Store the cooling strategy analysis component library in the heat cooling channel for subsequent calls.

[0027] Furthermore, it includes: Verify the target cooling strategy analysis component to obtain component analysis performance parameters. If the component analysis performance parameters do not meet the preset performance standards, extract the parameters of the target cooling strategy analysis component to obtain the key parameters of the analysis component. Initialize the particle swarm parameters based on the key parameters of the analysis component, define a parameter fitness function to evaluate and iteratively update the particle swarm parameters, and determine the optimal parameter solution of the component. Configure and update the target cooling strategy analysis component based on the optimal parameter solution of the component.

[0028] Preferably, verify the selected target cooling strategy analysis component, and evaluate the analysis performance parameters of the component in a specific operating environment, including indicators such as its response speed, cooling efficiency, and adaptability to different working conditions. By analyzing these performance parameters, it can be determined whether the component meets the preset performance standards; if the verification result shows that the analysis performance of the cooling strategy analysis component fails to reach the preset performance standards, parameter extraction will be performed on the component. By extracting the key parameters of the analysis component, such as the coolant flow rate, the response speed of the temperature sensor, and the utilization rate of the heat dissipation area, the key factors affecting the cooling efficiency and system stability can be identified. Based on the extracted key parameters of the analysis component, the system will use the particle swarm optimization algorithm to optimize the parameters. Specifically, initialize each particle in the particle swarm, set its initial position and velocity, representing different control strategy parameters; then, define the fitness function to evaluate the cooling effect and system performance corresponding to the position of each particle (i.e., the cooling system parameters). Among them, the fitness function may be related to cooling efficiency, response accuracy, system stability, etc.; through multiple iterative updates, the particle swarm algorithm will gradually optimize the parameters, so as to find the optimal parameter solution of the cooling strategy analysis component. When the particle swarm algorithm iteration ends and the optimal parameter solution is obtained, the target cooling strategy analysis component will be configured and updated based on these optimal parameters, including adjusting the coolant flow rate, adjusting the control mode of the temperature control strategy, and optimizing the cooling cycle, so that the cooling strategy analysis component can maintain the best cooling effect under different working conditions.

[0029] If the heat of the motor exceeds the heat limit value of the cooling channel, the waste heat recovery channel is activated in parallel to perform heat exchange analysis on the difference between the heat of the motor and the heat limit value of the cooling channel, and heat exchange control parameters are obtained.

[0030] When the heat of the motor does not exceed the heat limit value of the cooling channel, only the heat cooling channel is activated to perform policy analysis on the multi-dimensional perception data stream of the motor. When the heat generated by the motor exceeds the heat limit value of the cooling channel, it means that the current cooling system cannot effectively control the temperature of the motor; in this case, the system will activate both the heat cooling channel and the waste heat recovery channel. The role of the waste heat recovery channel is to recover the excess heat generated by the motor and convert it into energy that can be utilized by other systems or processes, thereby reducing heat waste and improving the overall energy efficiency. After activating the waste heat recovery channel, heat exchange analysis is started on the difference between the motor heat and the heat limit value of the cooling channel, that is, calculating the excess heat exceeding the heat limit value of the cooling channel and the heat that the waste heat recovery channel needs to process; based on the heat exchange analysis, a set of heat exchange control parameters will be obtained, and these parameters include the working intensity of the waste heat recovery channel, the heat exchange rate, the quantity of recovered heat, etc. Through these control parameters, the system can precisely adjust the working state of the waste heat recovery channel to ensure that the recovered heat can be effectively converted into useful energy or other available processing.

[0031] Furthermore, obtaining the heat exchange control parameters includes: Activating the waste heat recovery channel, starting the waste heat recovery device of the target new energy motor according to the waste heat recovery channel; configuring a heat exchange control space based on the waste heat recovery device, where the heat exchange control space includes historical heat exchange control parameters and corresponding waste heat recovery effect data; determining the waste heat recovery value according to the difference between the motor heat and the heat limit value of the cooling channel, and using the waste heat recovery value as a control constraint parameter; performing global analysis and optimization in the heat exchange control space based on the control constraint parameter to determine the heat exchange control parameter.

[0032] When the heat of the motor exceeds the heat limit value of the cooling channel, the waste heat recovery channel is activated, and the waste heat recovery equipment is started, such as a heat exchanger or a heat pump. These equipment recover the excess heat generated by the motor and convert it into available energy. Based on the working principle and performance of the waste heat recovery equipment, the system will configure a heat exchange control space, which includes historical heat exchange control parameters and corresponding waste heat recovery effect data. The historical heat exchange control parameters reflect the efficiency of heat exchange, the amount of waste heat recovered, and their corresponding control parameters under different working conditions. The waste heat recovery effect data includes data such as the heat recovery rate and equipment efficiency under different working conditions. According to the difference between the motor heat and the heat limit value of the cooling channel, the system calculates the waste heat recovery value, that is, the amount of excess heat generated by the motor that needs to be recovered. The waste heat recovery value is an important parameter in the heat exchange control process of the system, and it will be input as a control constraint parameter into the subsequent heat exchange optimization process. The control constraint parameter ensures that the recovered heat does not exceed the processing capacity of the system, and at the same time ensures that enough heat can be recovered to meet the needs of the motor. Based on the above control constraint parameters, global analysis and optimization are carried out in the heat exchange control space to find the most suitable heat exchange control parameters for the current working conditions. By analyzing the influence of different control strategies on the heat exchange efficiency, global optimization algorithms, such as particle swarm optimization or genetic algorithms, are used to adjust the control parameters. Finally, the optimal heat exchange control parameters are determined, so as to optimize the operation efficiency of the waste heat recovery equipment and ensure that the motor always operates within a safe and stable temperature range.

[0033] Furthermore, the determining of the heat exchange control parameters includes: Performing parameter interval analysis on the heat exchange control space based on the control constraint parameters to obtain a selection interval for the heat exchange control parameters; evaluating and fitting the waste heat recovery effect data according to the waste heat recovery control target to construct a waste heat recovery effect fitness function; randomly selecting multiple heat exchange control parameters within the selection interval of the heat exchange control parameters, and using the waste heat recovery effect fitness function to expand the solution set of the multiple heat exchange control parameters to obtain an expanded population of control parameters; performing global comparison and optimization within the expanded population of control parameters to determine the heat exchange control parameters.

[0034] Based on the control constraint parameters, the parameter interval of the heat exchange control space is analyzed to determine the possible variation range of the heat exchange control parameters under the current working conditions, and the selection interval of the heat exchange control parameters is obtained. These intervals define the adjustable range of each control parameter, providing a reference for subsequent parameter optimization. Next, according to the waste heat recovery control target, the historical waste heat recovery effect data is evaluated and fitted. Through data fitting methods (such as the least squares method, regression analysis, or machine learning algorithms), the relationship between the waste heat recovery effect data and the control parameters of the cooling system (such as coolant flow rate, cooling method, working time, etc.) is modeled. During the fitting process, the system constructs a waste heat recovery effect fitness function based on factors such as recovery efficiency, heat recovery ratio, and energy loss. This fitness function is used to quantify the working effect of the waste heat recovery equipment under different parameter configurations and evaluate the impact of each cooling strategy on the heat recovery efficiency. Subsequently, multiple heat exchange control parameters are randomly selected within the heat exchange control parameter selection interval. These parameters represent different configurations within the current control interval. Using the previously constructed waste heat recovery effect fitness function, the solution set of these randomly selected multiple control parameters is expanded, that is, the solution space of these parameters is expanded through an algorithm to explore more possible parameter combinations. Finally, global comparison and optimization are performed within the expanded population of control parameters, that is, the expanded control parameters are compared and optimized through a global search algorithm (such as a genetic algorithm or a particle swarm optimization algorithm). By comparing the fitness function values under different parameter configurations, the final heat exchange control parameters are determined.

[0035] Furthermore, obtaining the expanded population of control parameters includes: Evaluating the effects of the multiple heat exchange control parameters using the waste heat recovery effect fitness function to obtain multiple control parameter fitnesses; selecting a preset number of optimal solutions of the multiple heat exchange control parameters based on the multiple control parameter fitnesses; and expanding the multiple heat exchange control parameters through crossover and mutation based on the multiple control parameter optimal solutions to obtain the expanded population of control parameters.

[0036] The effects of multiple selected heat exchange control parameters are evaluated using the previously constructed fitness function for waste heat recovery. Each control parameter represents a potential cooling strategy configuration, such as coolant flow rate, heat dissipation mode, etc.; the fitness function evaluates the recovery effects of these parameters by quantifying the recovery efficiency and the amount of heat recovered under different operating conditions, and assigns a fitness value to each control parameter, indicating the quality of the configuration under specific working conditions. Based on the fitness of multiple control parameters in the evaluation results, the optimal solutions of these control parameters are selected; according to the preset optimization objectives (such as maximizing the recovery efficiency, minimizing the energy consumption, etc.), the system will select the parameter combinations with higher fitness values as the optimal solutions of multiple control parameters, and these optimal solutions represent the cooling strategy configurations that are most likely to achieve the optimal recovery effect under the current working conditions. Based on the selected optimal solutions of multiple control parameters, the system performs crossover and mutation expansion. Specifically, the system randomly selects multiple optimal solutions, generates new control parameter configurations through crossover operations (such as parameter exchange, merging, etc.), and at the same time performs mutation operations (such as slightly adjusting the parameter values) to generate new control parameters. Through crossover and mutation expansion, the system finally obtains an expanded population of control parameters, which contains multiple new control parameter configurations, and these new control parameter combinations will help to further optimize the performance of the waste heat recovery system, improve the recovery efficiency, and ensure the intelligence and dynamic adaptability of the cooling strategy.

[0037] A PID controller is introduced to perform parallel closed-loop thermal management on the target new energy motor based on the control strategy parameters of the cooling system and the heat exchange control parameters.

[0038] According to the cooling system control strategy parameters and heat exchange control parameters, a control strategy is provided for the thermal management process of the motor. The control strategy parameters include coolant flow rate, temperature control threshold, heat dissipation mode, etc., while the heat exchange control parameters are related to the efficiency of waste heat recovery, heat exchange speed, recovery capacity, etc. A PID controller is introduced into the thermal management process. Through proportional, integral, and derivative control, the PID controller can accurately adjust the temperature of the motor in real time. Proportional control is used to adjust according to the difference between the current motor temperature and the set target temperature to ensure a quick response to temperature fluctuations; integral control is used to eliminate the deviation in the system to ensure that the system can be stable within the set temperature range in the long term; derivative control is used to predict the future temperature change trend and take corresponding control measures in advance to avoid excessive temperature fluctuations. The PID controller dynamically adjusts the cooling system control strategy parameters and heat exchange control parameters by real-time monitoring of multi-dimensional data such as the temperature of the motor, the operating state of the cooling system, and the heat exchange effect. Specifically, when the temperature change of the motor exceeds the predetermined range, the PID controller will adjust the coolant flow rate, cooling mode, or heat exchange rate according to the preset proportional, integral, and derivative coefficients. In this way, the PID controller realizes the parallel closed-loop thermal management of the motor temperature. During the closed-loop control process, the cooling system and the waste heat recovery system can continuously cooperate with each other under the guidance of the PID controller, dynamically adjust the cooling and heat recovery strategies, and ensure that the motor always maintains a stable and safe operating temperature range.

[0039] In summary, the embodiments of this application at least have the following technical effects: First, a thermal management hybrid channel for the target new energy motor is built. The thermal management hybrid channel includes a heat cooling channel and a waste heat recovery channel. Then, multi-dimensional information perception of the target new energy motor is carried out to obtain the motor multi-dimensional perception data stream, which includes motor heat, cooling system operation data, and external environment data. At the same time, based on the heat cooling channel, a limit analysis of the characteristic parameters and operating conditions of the target new energy motor is carried out to determine the heat limit of the cooling channel. Then, the heat cooling channel is activated to conduct a strategy analysis on the motor multi-dimensional perception data stream to determine the cooling system control strategy parameters. If the motor heat exceeds the heat limit of the cooling channel, the waste heat recovery channel is activated in parallel to perform a heat exchange analysis on the difference between the motor heat and the heat limit of the cooling channel to obtain the heat exchange control parameters. Finally, a PID controller is introduced to perform parallel closed-loop thermal management on the target new energy motor based on the cooling system control strategy parameters and the heat exchange control parameters. This solves the technical problems of low thermal management efficiency and insufficient energy utilization in the prior art for new energy motors, and achieves the technical effects of improving thermal management efficiency, optimizing energy efficiency recovery, and realizing closed-loop control.

[0040] It should be noted that the above-mentioned order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification has been made. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0041] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0042] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An intelligent thermal management method for a new energy motor, characterized in that, The method includes: Construct a thermal management hybrid channel for the target new energy motor, where the thermal management hybrid channel includes a heat cooling channel and a waste heat recovery channel; Perform multi-dimensional information perception on the target new energy motor to obtain a motor multi-dimensional perception data stream, where the motor multi-dimensional perception data stream includes motor heat, cooling system operation data, and external environment data; Based on the heat cooling channel, perform limit analysis on the characteristic parameters and operating conditions of the target new energy motor to determine the heat limit of the cooling channel; Activate the heat cooling channel to perform strategy analysis on the motor multi-dimensional perception data stream to determine the control strategy parameters of the cooling system; If the motor heat exceeds the heat limit of the cooling channel, activate the waste heat recovery channel in parallel to perform heat exchange analysis on the difference between the motor heat and the heat limit of the cooling channel to obtain heat exchange control parameters; Introduce a PID controller and perform parallel closed-loop thermal management on the target new energy motor based on the control strategy parameters of the cooling system and the heat exchange control parameters.

2. The intelligent thermal management method of the new energy motor according to claim 1, characterized in that, The determination of the heat limit of the cooling channel includes: Drive three-dimensional modeling based on the characteristic parameters of the target new energy motor to generate a three-dimensional space component of the motor, and analyze the heat dissipation area and component working characteristics of the motor according to the three-dimensional space component of the motor; Perform operating safety assessment on the heat dissipation area and component working characteristics of the motor according to the operating conditions to determine the heat-bearing safety margin of the motor; According to the heat cooling channel, obtain a multi-stage cooling system for the motor, and perform heat dissipation limit analysis on the multi-stage cooling system of the motor to obtain the heat dissipation threshold of the cooling system; Take the cumulative value of the heat-bearing safety margin of the motor and the heat dissipation threshold of the cooling system as the heat limit of the cooling channel.

3. The intelligent thermal management method for a new energy motor according to claim 1, wherein, The determination of the control strategy parameters of the cooling system includes: Construct a motor attribute classifier, classify the target new energy motor based on the motor attribute classifier to obtain target motor attribute parameters; Call a cooling strategy analysis component library according to the heat cooling channel, where the cooling strategy analysis component library includes cooling strategy analysis components of different attribute types; Match the target motor attribute parameters with the cooling strategy analysis component library to obtain a target cooling strategy analysis component; Based on the target cooling strategy analysis component, perform cooling strategy analysis on the motor multi-dimensional perception data stream to determine the control strategy parameters of the cooling system.

4. The intelligent thermal management method of the new energy motor according to claim 3, wherein, The call of the cooling strategy analysis component library according to the heat cooling channel includes: Mine and obtain the historical cooling data set of new energy motors, and use the motor attribute classifier to perform clustering identification on the historical cooling data set of new energy motors to obtain a historical cooling data set of motors with multi-attribute parameters; Select a multi-attribute parameter cooling algorithm model according to the cooling control target and data characteristic information of the historical cooling data set of motors with multi-attribute parameters; Use the multi-attribute parameter cooling algorithm model to perform strategy training and optimization on the historical cooling data set of motors with multi-attribute parameters respectively to obtain a set of multi-attribute parameter cooling strategy analysis components; Integrate the attribute identifications of the multi-attribute parameter cooling strategy analysis component set to obtain a cooling strategy analysis component library and store it in the heat cooling channel.

5. The intelligent thermal management method of the new energy motor according to claim 3, characterized in that, The method includes: Verify the target cooling strategy analysis component to obtain component analysis performance parameters; If the component analysis performance parameters do not meet the preset performance standards, extract parameters from the target cooling strategy analysis component to obtain key analysis component parameters; Initialize the particle swarm parameters based on the key analysis component parameters, define a parameter fitness function to evaluate and iteratively update the particle swarm parameters, and determine the optimal parameter solution for the component; Update the configuration of the target cooling strategy analysis component based on the optimal component parameter solution.

6. The intelligent thermal management method for a new energy motor according to claim 1, characterized in that, The obtaining of the heat exchange control parameters includes: Activate the waste heat recovery channel and start the waste heat recovery device of the target new energy motor according to the waste heat recovery channel; Configure a heat exchange control space based on the waste heat recovery device, where the heat exchange control space includes historical heat exchange control parameters and corresponding waste heat recovery effect data; Determine the waste heat recovery value according to the difference between the motor heat and the heat limit value of the cooling channel, and use the waste heat recovery value as a control constraint parameter; Perform global analytical optimization in the heat exchange control space based on the control constraint parameter to determine the heat exchange control parameter.

7. The intelligent thermal management method of the new energy motor according to claim 6, characterized in that, The determination of the heat exchange control parameter includes: Perform parameter interval analysis on the heat exchange control space based on the control constraint parameter to obtain a selection interval for the heat exchange control parameter; Evaluate and fit the waste heat recovery effect data according to the waste heat recovery control target to construct a waste heat recovery effect fitness function; Randomly select multiple heat exchange control parameters within the selection interval of the heat exchange control parameter, and use the waste heat recovery effect fitness function to expand the solution set of the multiple heat exchange control parameters to obtain an expanded population of control parameters; Perform global comparison and optimization within the expanded population of control parameters to determine the heat exchange control parameter.

8. The intelligent thermal management method of the new energy motor according to claim 7, wherein The obtaining of the expanded population of control parameters includes: Use the waste heat recovery effect fitness function to evaluate the effects of the multiple heat exchange control parameters to obtain multiple control parameter fitnesses; Select a preset number of optimal solutions for the multiple heat exchange control parameters based on the multiple control parameter fitnesses; Perform cross-mutation expansion on the multiple heat exchange control parameters based on the multiple optimal solutions of the control parameters to obtain the expanded population of control parameters.

Images