Control method of fuel cell phase change cooling thermal management system

Abstract

The invention discloses a control method of a fuel cell phase change cooling thermal management system. The method comprises the following steps: optimizing an active-disturbance-rejection controller through a whale optimization algorithm; setting a target electric pile temperature according to the working temperature range of the fuel cell, and inputting the target electric pile temperature into the tracking differentiator to obtain an optimized target electric pile temperature; acquiring the actual stack temperature of the fuel cell stack, comparing the actual stack temperature with the optimized target stack temperature to obtain an error signal, and inputting the error signal into an active disturbance rejection controller to generate a basic control quantity through proportional control; and the final control quantity is obtained according to the linear expansion state observer, and the organic working medium circulating pump is controlled through the final control quantity. According to the invention, the problem of insufficient anti-disturbance capability for complex vehicle operation conditions in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of fuel cell technology, and more particularly to a control method for a fuel cell phase change cooling thermal management system. Background Technology

[0002] Proton exchange membrane fuel cells (PEMFCs) offer advantages such as high efficiency, zero carbon emissions, low-temperature start-up, long driving range, and fast hydrogen refueling, making them a crucial technological route for new energy power in vehicles. The thermal management system is key to ensuring the efficient, stable, and long-life operation of fuel cells. Most automotive PEMFCs employ a deionized water single-phase liquid cooling thermal management scheme, relying on sensible heat exchange for heat dissipation. While this scheme meets basic temperature control requirements, it has significant drawbacks: firstly, the single-phase heat exchange capacity is limited, requiring a substantial increase in coolant flow rate for high-power stacks, leading to increased power consumption in components such as water pumps and radiators, and reducing the system's net output power; secondly, it can only passively dissipate heat and cannot recover low-temperature waste heat from the stack, resulting in energy waste and hindering overall system efficiency improvement. Therefore, PEMFC phase change cooling technology has become a hot topic. This technology uses a low-boiling-point organic working fluid, coupling the Organic Rankine Cycle (ORC) with the stack cooling loop. The working fluid directly enters the cooling channel, achieving efficient heat dissipation through boiling phase change, while simultaneously absorbing waste heat to complete a thermodynamic cycle, converting low-grade thermal energy into electrical energy. This solution simplifies the system structure, balances precise temperature control of the fuel cell stack with waste heat recovery, and effectively improves the overall energy efficiency of the fuel cell. Onboard fuel cell thermal management systems are prone to failure, untimely adjustments, and excessive auxiliary power due to various disturbances. Therefore, precise control of cooling and waste heat recovery requirements is necessary to ensure the normal operation of the thermal management system.

[0003] A patent application with application number 202322184174.5, entitled "A Fuel Cell Waste Heat Utilization System," discloses a technical solution: This system connects a thermoelectric conversion component and a plate heat exchanger component in parallel, using the waste heat from the fuel cell stack for thermoelectric conversion and vehicle interior heating, respectively. The thermoelectric device converts the waste heat of the fuel cell stack coolant into electrical energy through the thermoelectric effect of the PN junction semiconductor; simultaneously, the fuel cell stack coolant provides heating to the vehicle interior through the plate heat exchanger. This solution relies on the sensible heat transfer of the coolant to achieve waste heat recovery and dissipation. When the fuel cell stack heat load fluctuates, it relies solely on the thermostat and radiator for passive adjustment, resulting in low temperature control accuracy.

[0004] Patent application number 202311113260.5, entitled "Hydrogen-Heat Integrated Power Generation System and Method Based on PEMFC and Organic Rankine Cycle," discloses a technical solution: a temperature monitoring point is set up on the heat recovery branch, and a fuzzy logic PID controller is used to control the corresponding heat recovery circulation pump, enabling it to adjust its flow rate in a timely manner according to changes in system heat generation, thus stabilizing the fuel cell stack at the optimal operating temperature. This technical solution achieves temperature control solely by adjusting the circulation pump flow rate, resulting in a relatively simple adjustment method. Furthermore, it does not fully consider the coupling constraints between PEMFC temperature control and ORC waste heat recovery, making it difficult to achieve precise temperature regulation when the system load changes rapidly.

[0005] Patent application number CN202510632512.8, entitled "A Waste Heat Utilization System and Coupling Method Based on PEMFC-ORC-TEG Coupling," discloses a technical solution that couples three modules: a PEMFC, an ORC, and a thermoelectric generator (TEG). The heat dissipation of the fuel cell system is absorbed by cooling water, with initial heat exchange achieved through the TEG. Then, the cooling water exchanges heat with the working fluid circulating in the ORC through an evaporator. While this technical solution achieves cascaded utilization of PEMFC waste heat, the series arrangement of the TEG and ORC means that the TEG preferentially consumes the high-grade heat of the cooling water, causing a decrease in the heat source temperature entering the ORC evaporator. This reduces the ORC cycle efficiency and affects the overall energy utilization rate of the system.

[0006] Existing thermal management systems and control methods for fuel cells have the following problems:

[0007] 1. The system uses multiple working fluids, resulting in high complexity, high maintenance and integration costs, and does not meet the design requirements of vehicle fuel cells for compactness and lightweight design.

[0008] 2. The system control is not robust enough to withstand disturbances under complex vehicle operating conditions.

[0009] 3. The system control is poorly adaptable to heat load fluctuations, has limited control and adjustment methods, slow adjustment response, poor control accuracy, and low stability and reliability of waste heat utilization.

[0010] 4. The system has low waste heat utilization efficiency, limited heat exchange methods, and significant irreversible heat loss during the heat transfer process.

[0011] There is currently no effective solution to the aforementioned problems in the relevant technologies. Summary of the Invention

[0012] The main objective of this application is to provide a control method for a fuel cell phase change cooling thermal management system, so as to at least solve the problem of insufficient anti-disturbance capability in related technologies for complex vehicle operating conditions.

[0013] To achieve the above objectives, according to one aspect of this application, a control method for a fuel cell phase change cooling thermal management system is provided. The method includes: optimizing an active disturbance rejection controller (ADRC) using a whale optimization algorithm; setting a target stack temperature based on the fuel cell's operating temperature range, and inputting the target stack temperature into a tracking differentiator to obtain the optimized target stack temperature; acquiring the actual stack temperature of the fuel cell stack, comparing the actual stack temperature with the optimized target stack temperature to obtain an error signal, and inputting the error signal into the ADRC to generate a basic control quantity through proportional control; obtaining the final control quantity based on a linearly extended state observer, and controlling the organic working fluid circulation pump using the final control quantity.

[0014] Optionally, candidate parameters are obtained, including a first candidate parameter, a second candidate parameter, and a third candidate parameter; in step S201, the distance between the current position of each candidate parameter and the optimal solution is calculated, a random value is determined, and the position vector of each candidate parameter is updated; in step S202, the fitness of the position vector is evaluated; the above steps S201-S202 are repeated until the fitness meets the requirements.

[0015] Optionally, when the absolute value of the random value is greater than 1, the position vector is updated using a random search: ,in, The position vector is generated randomly. The number of iterations is The position vector, The number of iterations is The position vector, The coefficients are generated from random numbers. It is a random vector in the range [0,2]. As the first candidate parameter, As the second candidate parameter, It is the third candidate parameter; when the absolute value of the random value is less than or equal to 1, a second determination is made.

[0016] Optionally, the choice between a contraction-loop path and a spiral path is determined based on a formula, which is as follows: in, For probability, and It is a random number between [0,1]. It is the constant that defines the logarithmic spiral path.

[0017] Alternatively, when using a spiral path to approximate the optimal parameters, the formula is: ,in, The number of iterations is The position vector, The number of iterations is The optimal position vector, The coefficients are generated from random numbers. It is a random vector in the range [0,2], with coefficients... The value decreases during the iteration process. As the first candidate parameter, As the second candidate parameter, It is the third candidate parameter.

[0018] Optionally, fitness is calculated using the following formula: ,in, For fitness, This is the set value for the temperature difference between the coolant inlet and outlet. Real-time actual value of the temperature difference between the inlet and outlet of the coolant; For the target stack temperature, The actual temperature of the fuel cell stack This refers to the fuel cell stack operating time.

[0019] Optionally, in step S701, the original final control quantity is input into the linear extended state observer to obtain the disturbance estimate and the actual stack temperature; in step S702, the difference between the basic control quantity and the disturbance estimate is calculated to obtain the disturbance compensation value; in step S703, the disturbance compensation value is processed... Gain scaling is performed to obtain the final control quantity; in step S704, the final control quantity is used as the original final control quantity and steps S701-S703 are repeated to continuously update the final control quantity.

[0020] This application employs the following steps: optimizing the active disturbance rejection controller (ADRC) using the whale optimization algorithm; setting a target stack temperature based on the fuel cell's operating temperature range, and inputting the target stack temperature into a tracking differentiator to obtain the optimized target stack temperature; acquiring the actual stack temperature of the fuel cell, comparing the actual stack temperature with the optimized target stack temperature to obtain an error signal, and inputting the error signal into the ADRC to generate a basic control quantity through proportional control; obtaining the final control quantity based on a linearly extended state observer, and controlling the organic working fluid circulation pump through the final control quantity. This solves the problem of insufficient anti-disturbance capability in related technologies for complex vehicle operating conditions, thereby achieving the effect of rapid and stable tracking of the target temperature of the fuel cell stack and dynamic matching of fuel cell heat dissipation with the organic Rankine cycle. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a control method for a fuel cell phase change cooling thermal management system according to an embodiment of this application;

[0023] Figure 2 For control logic diagram;

[0024] Figure 3 This is a schematic diagram of a first-order linear active disturbance rejection control.

[0025] Figure 4 This is a schematic diagram of the WOA algorithm process;

[0026] Figure 5 This is an active disturbance rejection control method for a phase change cooling thermal management system. Detailed Implementation

[0027] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0031] PEMFC: Proton Exchange Membrane Fuel Cell; ORC: Organic Rankine Cycle; ADRC: First-Order Linear Active Disturbance Rejection; WOA: Whale Optimization Algorithm; LESO: Linear Extended State Observer; TD: Tracking Differentiator; P Control: Proportional Control.

[0032] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0033] This embodiment provides a control method for a fuel cell phase change cooling thermal management system that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0034] Figure 1 This is a flowchart of a control method for a fuel cell phase change cooling thermal management system according to an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0035] Step S101: Optimize the active disturbance rejection controller using the whale optimization algorithm;

[0036] Specifically, the whale optimization algorithm first initializes the position vectors of all candidate parameters and calculates the fitness of each position vector. Next, it calculates the distance between the current position of each candidate parameter and the optimal solution. Then, it updates the position vector of each candidate parameter according to different behavior patterns (shrinking loop path, spiral path, or random search). Next, it evaluates the fitness of the new position vectors and updates the optimal position vector. Finally, it repeats the above steps until no significant optimization is achieved after several consecutive iterations.

[0037] Step S102: Set the target stack temperature according to the operating temperature range of the fuel cell, and input the target stack temperature into the tracking differentiator to obtain the optimized target stack temperature.

[0038] Specifically, the operating parameters of the fuel cell stack are collected in real time, and the target stack temperature is set according to the operating temperature range of the fuel cell, which is then used as a reference input signal to the tracking differentiator (TD) of the control system.

[0039] Step S103: Collect the actual stack temperature of the fuel cell stack, compare the actual stack temperature with the optimized target stack temperature to obtain an error signal, and input the error signal into the active disturbance rejection controller to generate a basic control quantity through proportional control.

[0040] Specifically, the actual temperature of the fuel cell stack is collected by a temperature sensor and used as the system output. This output is compared with the target stack temperature, which has been smoothed by a tracking differentiator, to obtain a temperature control error feedback signal. This error signal is then input to the active disturbance rejection controller (ADRC) for adjustment. Since the phase change cooling system is approximated as a first-order controlled object, P-control is used instead of linear state error feedback. The temperature control error is input to the proportional controller to generate a basic control quantity, which is used to quickly adjust the response of the phase change cooling thermal management system, enabling the stack temperature to rapidly approach the target value, thereby improving the dynamic response speed.

[0041] Step S104: Obtain the final control quantity based on the linear expansion state observer, and control the organic working fluid circulation pump through the final control quantity.

[0042] Specifically, the actual stack temperature and the final control inputs to the fuel cell phase change cooling thermal management system are input into LESO. LESO then expands unmodeled external and internal disturbances such as changes in phase change cooling heat transfer capacity, changes in working fluid properties, and pipeline resistance into a new system state, estimating the total disturbance in real time and outputting the tracking observation value of the actual stack temperature. Subsequently, the basic control output from the P controller is subtracted to compensate for the internal and external disturbances of the fuel cell phase change cooling thermal management system, and then... Gain scaling The equivalent gain between the system input and output is used to obtain the updated final control quantity. The updated final control quantity is applied to the organic working fluid circulation pump to adjust the pump speed, thereby changing the working fluid flow rate in the organic Rankine cycle and the heat exchange capacity of the phase change cooling system. This enables the fuel cell stack temperature to quickly and stably track the target temperature and achieves dynamic matching between the fuel cell heat dissipation and the organic Rankine cycle.

[0043] like Figure 2 As shown, to adapt to changes in heat load caused by variations in PEMFC stack operating conditions, it is necessary to determine the stack's operating state and control target state, and to precisely regulate the control target. When the fuel cell operating conditions change, it will directly trigger synchronous changes in system temperature and heat load; subsequently, the system compares and judges the current control target with the preset value. The thermal management system control method mentioned in this invention uses the inlet temperature of the organic working fluid in the stack cooling channel and the inlet-outlet temperature difference as the control target, with the stack temperature as the controlled object. If the control target does not deviate, the thermal management system directly enters an adaptive state to match the current heat load demand; if the control target deviates, the thermal management system will output a control signal, and the controller will adjust the operating power of the water pump and fan according to the signal, pushing the control target to gradually fall back to a reasonable range, and finally achieving dynamic balance of system heat load through feedback regulation, ensuring the temperature stability of the fuel cell under varying operating conditions.

[0044] This control method approximates the phase change cooling system as a first-order controlled object, treating all other higher-order dynamics and uncertainties in the control system as a total disturbance, which is estimated and compensated by an extended state observer. The linear extended state observer (LESO), as the core observation module, extends the internal and external disturbances of the working fluid circulation pump into a new state, estimates the total disturbance in real time, and cancels it in the control loop, making the fuel cell phase change cooling thermal management system equivalent to a standard integral object. Then, based on the error between the target temperature and the actual temperature of the fuel cell stack, a controller is constructed to adjust the circulation pump speed and condenser fan power to match the heat dissipation of the fuel cell stack, thereby improving flow tracking accuracy and system anti-interference capability. Specifically, as follows... Figure 3 As shown.

[0045] Reference Figure 4 The process involves obtaining candidate parameters, including a first candidate parameter, a second candidate parameter, and a third candidate parameter; step S201: calculating the distance between the current position of each candidate parameter and the optimal solution, determining a random value, and updating the position vector of each candidate parameter; step S202: evaluating the fitness of the position vector; repeating steps S201-S202 until the fitness meets the requirements.

[0046] Specifically, the whale optimization algorithm is used to perform first-order linear ADRC. Parameter optimization. It determines system bandwidth and response speed, and affects control accuracy; Used in observer design to determine the speed and accuracy of system state and disturbance estimation, as well as system stability; Used to compensate for control variables, affecting control effectiveness and system robustness.

[0047] In an alternative embodiment, when the absolute value of the random value is greater than 1, the position vector is updated using a random search: ,in, The position vector is generated randomly. The number of iterations is The position vector, The number of iterations is The position vector, The coefficients are generated from random numbers. It is a random vector in the range [0,2]. As the first candidate parameter, As the second candidate parameter, It is the third candidate parameter; when the absolute value of the random value is less than or equal to 1, a second determination is made.

[0048] In one optional embodiment, the choice between a contraction-loop path and a spiral path is determined according to a formula, which is: in, For probability, and It is a random number between [0,1]. It is the constant that defines the logarithmic spiral path.

[0049] Specifically, during algorithm iteration, the optimal parameters are approximated by either a shrinking circular path or a spiral path, each with a 50% probability.

[0050] In an alternative embodiment, when using a spiral path to approximate the optimal parameters, the formula is: ,in, The number of iterations is The position vector, The number of iterations is The optimal position vector, The coefficients are generated from random numbers. It is a random vector in the range [0,2], with coefficients... The value decreases during the iteration process. As the first candidate parameter, As the second candidate parameter, It is the third candidate parameter.

[0051] In an optional embodiment, fitness is calculated using the following formula: ,in, For fitness, This is the set value for the temperature difference between the coolant inlet and outlet. Real-time actual value of the temperature difference between the inlet and outlet of the coolant; For the target stack temperature, The actual temperature of the fuel cell stack This refers to the fuel cell stack operating time.

[0052] Specifically, the WOA algorithm uses the sum of the time multiplied by the absolute error integral of the temperature difference between the inlet and outlet coolant of the fuel cell stack and the temperature difference between the inlet and outlet coolant of the fuel cell stack cooling channel as the fitness function.

[0053] In an optional embodiment, step S701 involves inputting the original final control quantity into the linear extended state observer to obtain the disturbance estimate and the actual stack temperature; step S702 involves calculating the difference between the basic control quantity and the disturbance estimate to obtain the disturbance compensation value; and step S703 involves processing the disturbance compensation value. Gain scaling is performed to obtain the final control quantity; in step S704, the final control quantity is used as the original final control quantity and steps S701-S703 are repeated to continuously update the final control quantity.

[0054] In one optional embodiment, the WOA-ADRC phase change cooling thermal management control method proposed in this invention achieves temperature control of the PEMFC stack and efficient waste heat recovery. The control objective of the thermal management control system is to maintain a stable operating temperature of the PEMFC stack.

[0055] The specific process is as follows:

[0056] First, the WOA algorithm is used to optimize the parameters of the PEMFC stack. The termination condition is that the fitness function converges to a steady state and no significant optimization is achieved after multiple iterations. The optimal first-order linear ADRC controller parameters are then obtained. , , Complete controller initialization.

[0057] Then, the target temperature is set according to the operating temperature range of the PEMFC stack. The actual temperature at the inlet of the fuel cell stack is collected in real time by a temperature sensor. The target temperature of the PEMFC stack is smoothed by a tracking differentiator to avoid system impact caused by step commands. Then, the smoothed target temperature is compared with the observed value of the actual temperature at the stack inlet obtained by LESO processing to obtain the error signal of the stack inlet temperature. At the same time, the error signal is passed through the proportional control loop to obtain the basic control quantity.

[0058] Reference Figure 5 The error signal is then input into a first-order linear active disturbance rejection controller for dynamic adjustment. The first-order active disturbance rejection controller collects the actual temperature at the fuel cell inlet and the internal unmodeled dynamics and external disturbances in the phase change cooling thermal management system mentioned in this invention in real time via LESO. It first performs a unified estimate of the internal and external disturbances to obtain the total disturbance estimate. After completing disturbance compensation and then scaling by 1 / b0 gain, the final control quantity of the circulating working fluid pump is obtained. The final control quantity is used as a drive signal to act on the circulating working fluid pump in the organic Rankine cycle system mentioned in this invention, thereby adjusting the speed of the circulating working fluid pump.

[0059] The working fluid flow rate of the organic Rankine cycle changes with the rotational speed of the working fluid circulation pump. Furthermore, the changing thermal equilibrium state of the PEMFC stack causes the actual stack temperature to rapidly approach the set target temperature. Specifically, when the actual temperature at the PEMFC stack inlet is higher than the target temperature, the first-order linear ADRC controller proposed in this invention compensates for the disturbance caused by the increased load in real time using LESO, generating an increased final control quantity, increasing the working fluid pump speed, increasing the organic working fluid flow rate, enhancing phase change heat transfer, efficiently absorbing waste heat from the stack, and rapidly reducing the stack temperature. Conversely, when the actual temperature at the PEMFC stack inlet is lower than the target value, the first-order linear ADRC controller repeats the above process, compensating for the disturbance caused by the change in operating conditions in real time using LESO, generating a decreased final control quantity, reducing the rotational speed of the circulating working fluid pump in the thermal management system, reducing the organic working fluid flow rate, reducing phase change heat transfer, and preventing the stack temperature from becoming too low.

[0060] The aforementioned closed-loop control process dynamically regulates the temperature of the PEMFC stack, enabling the system to maintain a stable operating temperature under different load conditions. Simultaneously, adjusting the flow rate of the organic Rankine cycle working fluid achieves a dynamic match between the stack's heat dissipation requirements and waste heat recovery capabilities, improving the overall thermal efficiency and operational stability of the system.

[0061] The logical flow of the control method of the present invention is as follows:

[0062] 1. Operating condition triggering and thermal load response: When the operating conditions of the fuel cell change, the heat generation rate of the stack reaction changes synchronously, directly causing dynamic changes in the system's thermal load.

[0063] 2. Control Target Determination: The thermal management system uses the inlet temperature of the organic working fluid in the fuel cell stack cooling channel and the inlet-outlet temperature difference as the control target. The system collects the working fluid temperature in real time and compares it with the preset value: if the control target is greater than the preset value, it means that the current heat dissipation is not matched with the heat load, and the first-order linear ADRC outputs a control signal; if the control target is not greater than the preset value, the thermal management system maintains the current operating state.

[0064] 3. Closed-loop regulation and target reduction: The actuator receives the control signal output by the first-order linear ADRC, adjusts the operating status of the circulating water pump and the condenser fan, changes the circulation flow rate of the organic working fluid, regulates the cooling intensity of the fuel cell stack, and controls the target to gradually return to the preset value range.

[0065] 4. Loop Feedback: After the control target is achieved, the system continues to respond to the changes in heat load caused by the changes in fuel cell operating conditions, repeating the above judgment and adjustment process to form a closed-loop control.

[0066] The technical effects achieved by this invention are as follows:

[0067] 1. The first-order linear active disturbance rejection controller used in this invention, through its core linear extended state observer, treats all uncertainties such as fuel cell heat load fluctuations and pipeline resistance changes as a unified "total disturbance" for estimation and compensation. Without the need to establish an accurate thermal management system model, it can actively resist the influence of various external disturbances, improving the system's dynamic response speed and control accuracy under complex automotive operating conditions.

[0068] 2. This invention constructs a closed-loop control logic based on the fuel cell stack temperature error, and combines the constant temperature characteristics of latent heat transfer from phase change to precisely adjust the circulating working fluid flow rate through first-order linear ADRC. Even under strong disturbance conditions, it can maintain smaller temperature overshoot and faster adjustment speed, achieving dynamic matching between fuel cell stack heat dissipation requirements and waste heat recovery capabilities.

[0069] 3. This invention uses first-order ADRC to precisely regulate the circulating pump and condenser fan, so as to achieve rapid and stable tracking of the target temperature of the fuel cell stack and dynamic matching of the heat dissipation of the fuel cell with the organic Rankine cycle.

[0070] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0071] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0072] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0073] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0074] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0075] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0076] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0077] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0078] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A control method for a fuel cell phase change cooling thermal management system, characterized in that, include: The active disturbance rejection controller is optimized using the whale optimization algorithm; The target stack temperature is set according to the operating temperature range of the fuel cell, and the target stack temperature is input into the tracking differentiator to obtain the optimized target stack temperature. The actual stack temperature of the fuel cell stack is collected, and the actual stack temperature is compared with the optimized target stack temperature to obtain an error signal. The error signal is then input into the active disturbance rejection controller to generate a basic control quantity through proportional control. The final control quantity is obtained based on the linear expansion state observer, and the organic working fluid circulation pump is controlled by the final control quantity.

2. The method according to claim 1, characterized in that, The active disturbance rejection controller is optimized using the whale optimization algorithm, including: Obtain candidate parameters, which include a first candidate parameter, a second candidate parameter, and a third candidate parameter; Step S201: Calculate the distance between the current position of each candidate parameter and the optimal solution, determine the random value, and update the position vector of each candidate parameter; Step S202: Evaluate the fitness of the position vector; Repeat steps S201-S202 until the fitness meets the requirements.

3. The method according to claim 2, characterized in that, Step S201, calculate the distance between the current position of each candidate parameter and the optimal solution, determine a random value and update the position vector of each candidate parameter, including: When the absolute value of the random value is greater than 1, the position vector is updated using a random search: ,in, The position vector is generated randomly. The number of iterations is The position vector, The number of iterations is The position vector, The coefficients are generated from random numbers. It is a random vector in the range [0,2]. This is the first candidate parameter. This is the second candidate parameter. The third candidate parameter; When the absolute value of the random value is less than or equal to 1, a second determination is performed.

4. The method according to claim 3, characterized in that, When the absolute value of the random value is less than or equal to 1, a secondary determination is performed, including: The formula determines whether to use a contraction-loop path or a spiral path. The formula is as follows: in, For probability, and It is a random number between [0,1]. It is the constant that defines the logarithmic spiral path.

5. The method according to claim 4, characterized in that, The formula determines whether to use a contraction-loop path or a spiral path, including: When using a spiral path to approximate the optimal parameters, the formula is: ,in, The number of iterations is The position vector, The number of iterations is The optimal position vector, The coefficients are generated from random numbers. It is a random vector in the range [0,2], with coefficients... The value decreases during the iteration process. This is the first candidate parameter. This is the second candidate parameter. This is the third candidate parameter.

6. The method according to claim 2, characterized in that, Step S202, evaluating the fitness of the position vector, includes: The fitness is calculated using the following formula: ,in, For the fitness, This is the set value for the temperature difference between the coolant inlet and outlet. Real-time actual value of the temperature difference between the inlet and outlet of the coolant; For the target stack temperature, The actual temperature of the fuel cell stack This refers to the fuel cell stack operating time.

7. The method according to claim 1, characterized in that, The final control quantity is obtained based on the linear expansion state observer, and the organic working fluid circulation pump is controlled through the final control quantity, including: Step S701: Input the original final control quantity into the linear extended state observer to obtain the disturbance estimate and the actual stack temperature; Step S702: Calculate the difference between the basic control quantity and the disturbance estimate to obtain the disturbance compensation value; Step S703, perform the disturbance compensation value... Gain scaling is used to obtain the final control value; Step S704: Repeat steps S701-S703 using the final control quantity as the original final control quantity to continuously update the final control quantity.

Images