An unmanned aerial vehicle fuel cell optimal temperature curve tracking control method and device

Abstract

The present application relates to fuel cell temperature control technical field, especially in kind, a kind of unmanned aerial vehicle fuel cell optimal temperature curve tracking control method, device, equipment and computer storage medium are pointed out.The present application constructs the optimal temperature curve model that changes dynamically with current and environmental temperature and humidity, determines the optimal temperature point corresponding to the power peak of different working conditions of electric pile;Real-time monitoring of electric pile temperature, compared with the optimal temperature point determined by model generates deviation signal;Based on the deviation signal continuous closed loop adjustment fan speed, so that the electric pile temperature tracks the optimal temperature curve;When extremely cold start, electrochemical self-heating is used to warm up, and after reaching the safe temperature, the fan is controlled to intervene according to the preset curve smoothly.The present application can track the optimal temperature curve according to load and environment, improve power generation efficiency, reduce hydrogen consumption, and inhibit temperature overshoot and chattering in extremely cold environment, reduce thermal stress damage, and ensure the wide temperature range and efficient and stable operation of unmanned aerial vehicle.

Description

Technical Field

[0001] This invention relates to the field of fuel cell temperature control technology, and in particular to a method, device, equipment, and computer storage medium for tracking and controlling the optimal temperature curve of a UAV fuel cell. Background Technology

[0002] In existing thermal management technologies for unmanned aerial vehicle fuel cells, a proportional-integral-derivative (PID) feedback control strategy based on a fixed temperature setpoint is typically adopted. This involves collecting the real-time temperature of the fuel cell stack through a temperature sensor, comparing it with a preset single temperature value (such as 65°C), and then using a PID algorithm to adjust the speed of the cooling fan to maintain the stack temperature stable at that fixed setpoint.

[0003] However, the existing technology has the following drawbacks: First, because the optimal operating temperature of the fuel cell varies non-linearly with changes in load current and ambient temperature and humidity, a fixed temperature setpoint cannot adapt to wide temperature range and high dynamic load conditions. This causes the fuel cell stack to deviate from the optimal efficiency range for a long time under all operating conditions, resulting in hydrogen waste and a significant reduction in driving range. Actual measurements show that it can consume nearly 25% more hydrogen energy. Second, in environments with strong disturbances such as extreme cold, traditional PID control lacks the ability to predict thermodynamic states, and is prone to serious hysteresis response, temperature overshoot, and high-frequency control chattering. This not only accelerates the aging of the membrane electrode assembly, but also significantly increases the parasitic power consumption of the thermal management system because the fan parasitic energy consumption is proportional to the cube of the speed, affecting the lifespan and operational stability of the fuel cell. Summary of the Invention

[0004] Therefore, the technical problem to be solved by the present invention is to overcome the problems of low power generation efficiency and excessive hydrogen consumption caused by the use of a fixed temperature setpoint, which cannot adapt to wide temperature range and dynamic load changes, as well as unstable control and severe thermal stress damage in extremely cold and other strong disturbance environments.

[0005] To address the aforementioned technical problems, this invention provides a method for tracking and controlling the optimal temperature curve of a UAV fuel cell, comprising:

[0006] An optimal temperature curve model was constructed by conducting full-spectrum performance experiments, which dynamically changes with real-time current and ambient temperature and humidity. This optimal temperature curve model is used to determine the optimal temperature point corresponding to the peak power of the fuel cell stack under different operating conditions. The current temperature of the fuel cell stack is monitored in real time, and the current temperature is compared with the optimal temperature point determined by the optimal temperature curve model to generate a temperature deviation signal. Based on the temperature deviation signal, the speed of the cooling fan is dynamically adjusted using continuous closed-loop control logic so that the fuel cell stack temperature tracks the optimal temperature curve indicated by the optimal temperature curve model. Under extremely cold start-up conditions, an electrochemical self-heating strategy is adopted to increase the stack temperature, and after the stack temperature reaches a safe temperature, the cooling fan is controlled to smoothly intervene according to a preset curve.

[0007] Preferably, the step of constructing an optimal temperature curve model that dynamically changes with real-time current and ambient temperature and humidity through full-spectrum performance experiments further includes: The fuel cell stack was subjected to full-condition performance testing within a preset current density range and ambient temperature and humidity range, and the fuel cell stack output power and temperature data at each operating point were recorded. Based on the output power and temperature data, the optimal temperature point corresponding to the power peak at each current density is fitted, and a nonlinear mapping relationship between the optimal temperature and current density, ambient temperature and humidity is established to generate the optimal temperature curve model.

[0008] Preferably, the step of fitting the optimal temperature point corresponding to the power peak at each current density includes: For each current density, a peak search is performed on the power-temperature curve, and the temperature value corresponding to the maximum power is extracted as the optimal temperature point for that current density. By performing polynomial fitting on the optimal temperature points under various current densities, the functional relationship between the optimal temperature and the current density is obtained. Combined with the environmental temperature and humidity correction coefficient, the optimal temperature curve model is constructed.

[0009] Preferably, the real-time monitoring of the current temperature of the fuel cell stack and the comparison of the current temperature with the optimal temperature point determined by the optimal temperature curve model to generate a temperature deviation signal further includes: The current temperature of the fuel cell stack is collected in real time by a temperature sensor attached to the surface of the stack at a preset sampling frequency; Based on the real-time collected current signal and ambient temperature and humidity signal, the corresponding optimal temperature point is queried from the optimal temperature curve model; The difference between the current temperature and the optimal temperature point is calculated to generate the temperature deviation signal.

[0010] Preferably, the step of dynamically adjusting the cooling fan speed using continuous closed-loop control logic based on the temperature deviation signal includes: The temperature deviation signal is input to a proportional-integral-derivative controller to calculate the initial control quantity; the initial control quantity is then subjected to amplitude limiting to generate the duty cycle of a pulse width modulation signal. The cooling fan motor is driven according to the duty cycle, and the fan speed is adjusted so that the fuel cell stack temperature converges to the optimal temperature point.

[0011] Preferably, the calculation of the initial control quantity includes: The temperature deviation signal is subjected to proportional amplification, integral accumulation and differential prediction processing to obtain proportional term, integral term and differential term; The proportional, integral, and derivative terms are weighted and summed to generate the initial control quantity. The integral term employs an anti-saturation integral algorithm, and the integral accumulation stops when the initial control quantity reaches the limit value.

[0012] Preferably, the step of using an electrochemical self-heating strategy to raise the stack temperature under extremely cold start-up conditions, and controlling the cooling fan to smoothly intervene according to a preset curve after the stack temperature reaches a safe temperature, further includes: In the initial stage of startup, the cooling fan is controlled to run at a low speed below a preset threshold or be completely shut down, and the load current of the fuel cell is increased to use the heat generated by the electrochemical reaction to raise the internal temperature of the fuel cell. The stack temperature is monitored in real time. When the stack temperature reaches the preset safe temperature threshold, the fan speed is gradually increased from zero speed or low speed according to the preset speed-time curve, so that the stack temperature smoothly transitions to the optimal temperature point determined by the optimal temperature curve model.

[0013] The present invention also provides a drone fuel cell optimal temperature curve tracking and control device, comprising: The model building module is used to build an optimal temperature curve model that dynamically changes with real-time current and ambient temperature and humidity through full spectrum performance experiments. The optimal temperature curve model is used to determine the optimal temperature point corresponding to the peak power of the fuel cell stack under different operating conditions. The deviation generation module is used to monitor the current temperature of the fuel cell stack in real time, compare the current temperature with the optimal temperature point determined by the optimal temperature curve model, and generate a temperature deviation signal. A closed-loop control module is used to dynamically adjust the speed of the cooling fan based on the temperature deviation signal using continuous closed-loop control logic, so that the stack temperature tracks the optimal temperature curve indicated by the optimal temperature curve model. The extreme cold start module is used to raise the temperature of the fuel cell stack by adopting an electrochemical self-heating strategy under extreme cold start conditions, and to control the cooling fan to smoothly intervene according to a preset curve after the fuel cell stack temperature reaches a safe temperature.

[0014] The present invention also provides a device for tracking and controlling the optimal temperature curve of a UAV fuel cell, comprising: Memory, used to store computer programs; The processor is used to implement the steps of the above-described method for tracking and controlling the optimal temperature curve of a UAV fuel cell when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for tracking and controlling the optimal temperature curve of a UAV fuel cell.

[0016] The technical solution of the present invention has the following advantages compared with the prior art: The optimal temperature curve tracking and control method for UAV fuel cells described in this invention constructs an optimal temperature curve model that dynamically changes with current and ambient temperature and humidity, generates temperature deviation signals in real time, and uses continuous closed-loop logic to adjust fan speed. Simultaneously, it implements electrochemical self-heating and smooth intervention strategies during extreme cold startup. Its beneficial effects include: enabling the fuel cell stack to accurately track the dynamically optimal temperature point under all operating conditions, significantly improving power generation efficiency and reducing hydrogen consumption; effectively suppressing temperature overshoot and system chattering in extremely cold and other highly disturbed environments, reducing parasitic power consumption of the thermal management system and thermal stress damage to the fuel cell stack, thereby extending the fuel cell's service life, and ensuring efficient, stable, and rapid startup of the UAV in complex environments across a wide temperature range. Attached Figure Description

[0017] To make the content of this invention easier to understand, the invention will be further described in detail below with reference to specific embodiments and accompanying drawings, wherein: Figure 1 This is a flowchart illustrating the implementation of an optimal temperature curve tracking and control method for a UAV fuel cell provided by the present invention. Figure 2 This is a structural block diagram of an optimal temperature curve tracking and control device for a UAV fuel cell provided in an embodiment of the present invention. Detailed Implementation

[0018] The core of this invention is to provide a method, device, equipment, and computer storage medium for tracking and controlling the optimal temperature curve of a UAV fuel cell. This method can track the optimal temperature curve in real time based on the dynamic changes in load current and ambient temperature and humidity, effectively solving the problems of efficiency loss caused by fixed temperature settings and unstable control in extremely cold environments in the prior art. This improves power generation efficiency, reduces hydrogen consumption, and enhances the robustness and start-up reliability of the system under wide temperature range conditions.

[0019] To enable those skilled in the art to better understand the present invention, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Please refer to Figure 1. Figure 1 The flowchart illustrates the implementation of an optimal temperature curve tracking control method for a UAV fuel cell provided by this invention; the specific operation steps are as follows: S101: An optimal temperature curve model is constructed through full-spectrum performance experiments to dynamically change with real-time current and ambient temperature and humidity. The optimal temperature curve model is used to determine the optimal temperature point corresponding to the peak power of the fuel cell stack under different operating conditions. S102: Monitor the current temperature of the fuel cell stack in real time, compare the current temperature with the optimal temperature point determined by the optimal temperature curve model, and generate a temperature deviation signal; S103: Based on the temperature deviation signal, the speed of the cooling fan is dynamically adjusted using continuous closed-loop control logic so that the stack temperature tracks the optimal temperature curve indicated by the optimal temperature curve model. S104: Under extremely cold start-up conditions, an electrochemical self-heating strategy is adopted to increase the stack temperature, and after the stack temperature reaches a safe temperature, the cooling fan is controlled to smoothly intervene according to a preset curve.

[0021] Based on the above embodiments, in some embodiments, the construction of the optimal temperature curve model dynamically changing with real-time current and ambient temperature and humidity through full-spectrum performance experiments further includes: The fuel cell stack was subjected to full-condition performance testing within a preset current density range and ambient temperature and humidity range, and the fuel cell stack output power and temperature data at each operating point were recorded. Based on the output power and temperature data, the optimal temperature point corresponding to the power peak at each current density is fitted, and a nonlinear mapping relationship between the optimal temperature and current density, ambient temperature and humidity is established to generate the optimal temperature curve model.

[0022] In other embodiments, the method further includes the step of dynamically updating the optimal temperature profile model during UAV flight: Real-time acquisition of ambient temperature, ambient humidity, and fuel cell load current data; The optimal temperature curve model is dynamically updated based on the ambient temperature, ambient humidity, and load current data to compensate for the impact of fuel cell performance degradation and environmental changes on the optimal temperature point.

[0023] In one specific embodiment, in a laboratory environment, the load current changes of the UAV under different flight conditions are simulated using an electronic load. Simultaneously, an environmental test chamber is used to simulate ambient temperatures ranging from -50°C to 50°C and different humidity conditions, enabling comprehensive performance calibration of the fuel cell stack. The tests cover all operating conditions that the UAV might encounter in actual flight, such as current density ranging from low-load no-load to high-load climb conditions, ambient temperature ranging from extremely cold -50°C to high-temperature 50°C, and ambient humidity ranging from dry to saturated. High-precision sensors synchronously record the output power of the fuel cell stack and the corresponding stack temperature data at each operating point, forming a raw dataset.

[0024] Specifically, a peak search is performed on the power-temperature curve for each current density, and the temperature value corresponding to the maximum power is extracted as the optimal temperature point for that current density. For example, if the power-temperature curve exhibits a single-peak characteristic of first rising and then falling at a certain current density, the temperature corresponding to the peak point is the optimal temperature point under that operating condition. After extracting the optimal temperature points for all current densities, these discrete optimal temperature points are fitted with a polynomial to obtain the functional relationship between the optimal temperature and the current density. A cubic or quartic polynomial can be used for fitting to accurately describe its nonlinear variation trend.

[0025] It should be noted that this step establishes an optimal temperature target that changes dynamically with operating conditions, enabling the thermal management system to adjust the control benchmark in real time according to the actual operating state of the fuel cell stack. This avoids efficiency loss caused by a fixed temperature setting and lays the foundation for improving the energy conversion efficiency of the fuel cell system under all operating conditions.

[0026] Based on the above embodiments, in some embodiments, fitting the optimal temperature point corresponding to the power peak at each current density includes: For each current density, a peak search is performed on the power-temperature curve, and the temperature value corresponding to the maximum power is extracted as the optimal temperature point for that current density. By performing polynomial fitting on the optimal temperature points under various current densities, the functional relationship between the optimal temperature and the current density is obtained. Combined with the environmental temperature and humidity correction coefficient, the optimal temperature curve model is constructed.

[0027] In other embodiments, current density, ambient temperature, and ambient humidity are used as input variables. Through a combination of this functional relationship and correction coefficients, a nonlinear mapping relationship between the optimal temperature and current density, ambient temperature, and humidity is established, generating the optimal temperature curve model. This model can output the optimal temperature setpoint that precisely matches the current operating conditions in real time.

[0028] In one specific embodiment, the controller dynamically calculates and outputs the optimal temperature point corresponding to the peak power of the fuel cell stack under the current operating conditions by querying the model or executing the interpolation algorithm built into the model, based on the real-time current, ambient temperature and ambient humidity at the current moment.

[0029] Specifically, the environmental temperature and humidity correction coefficient is calibrated based on experimental data and is used to compensate for the basic optimal temperature value obtained by the above polynomial fitting.

[0030] It should be noted that this specific implementation significantly improves the adaptability and accuracy of the optimal temperature curve model under long-term operation and complex working conditions by introducing dynamic feedback of real-time environmental parameters and load current, thereby further optimizing the power generation efficiency of the fuel cell stack and reducing energy loss caused by model mismatch.

[0031] Based on the above embodiments, in some embodiments, the real-time monitoring of the current temperature of the fuel cell stack and the comparison of the current temperature with the optimal temperature point determined by the optimal temperature curve model to generate a temperature deviation signal further includes: The current temperature of the fuel cell stack is collected in real time by a temperature sensor attached to the surface of the stack at a preset sampling frequency; Based on the real-time collected current signal and ambient temperature and humidity signal, the corresponding optimal temperature point is queried from the optimal temperature curve model; The difference between the current temperature and the optimal temperature point is calculated to generate the temperature deviation signal.

[0032] In other embodiments, the temperature sensor is a thermocouple or a thermistor, attached to the cathode outlet side of the fuel cell stack or in the central region of the stack to accurately reflect the actual operating temperature inside the stack. The preset sampling frequency can be set according to the system's dynamic response requirements, for example, a fixed value between 10 Hz and 100 Hz, to ensure timely capture of transient temperature information even under high dynamic load changes. The acquired current temperature signal is filtered and amplified by the signal conditioning circuit before being converted into a digital input to the controller.

[0033] In one specific embodiment, the current signal is acquired in real time from the fuel cell stack output via a Hall current sensor, while the ambient temperature and humidity signals are collected by a temperature and humidity sensor installed at the UAV's air intake. The controller uses the current value and the ambient temperature and humidity values ​​as input parameters and substitutes them into the optimal temperature curve model. This model uses current and ambient temperature and humidity as independent variables and the optimal temperature point as the dependent variable, and quickly outputs the optimal temperature point corresponding to the peak power of the fuel cell stack under the current operating conditions through a lookup table or interpolation algorithm. The temperature deviation signal is defined as the difference between the current temperature and the optimal temperature point; its sign and magnitude directly reflect the degree to which the actual temperature of the fuel cell stack deviates from the optimal operating point.

[0034] Specifically, the controller calculates the difference between the current temperature and the optimal temperature point, generating the temperature deviation signal. This temperature deviation signal is defined as the difference between the current temperature and the optimal temperature point, and its sign and magnitude directly reflect the degree to which the actual temperature of the fuel cell stack deviates from the optimal operating point.

[0035] It should be noted that this specific implementation significantly improves the generation accuracy and response speed of the temperature deviation signal by introducing a high-precision temperature sensor, real-time acquisition of multi-source signals, and a model-based optimal temperature point query mechanism. This provides a reliable foundation for subsequent closed-loop control and effectively avoids the efficiency loss and control lag problems caused by traditional fixed temperature setpoints. Based on the above embodiments, in some embodiments, the step of dynamically adjusting the speed of the cooling fan using continuous closed-loop control logic based on the temperature deviation signal includes: The temperature deviation signal is input to a proportional-integral-derivative controller to calculate the initial control quantity; the initial control quantity is then subjected to amplitude limiting to generate the duty cycle of a pulse width modulation signal. The cooling fan motor is driven according to the duty cycle, and the fan speed is adjusted so that the fuel cell stack temperature converges to the optimal temperature point.

[0036] In other embodiments, the continuous closed-loop control logic employs a real-time monitoring-deviation processing-peak tracing control strategy. By monitoring the fuel cell stack temperature at high frequency and dynamically fine-tuning the fan speed, the temperature error is controlled within a very small range, thereby eliminating system oscillations and reducing thermal stress damage to the fuel cell stack.

[0037] In one specific embodiment, the controller receives a real-time temperature signal from a fuel cell temperature sensor and a load current signal from a current sensor as inputs. The proportional-integral-derivative (PID) controller performs proportional amplification, integral accumulation, and derivative prediction processing on the temperature deviation signal to generate corresponding proportional, integral, and derivative terms. The proportional term is used to provide an immediate response to the current temperature deviation, the integral term is used to eliminate steady-state errors, and the derivative term is used to predict the trend of temperature changes in order to apply control action in advance.

[0038] Specifically, the initial control quantity reflects the cooling intensity required to eliminate temperature deviations. The control quantity, after being limited, is converted into a duty cycle of a pulse-width modulation (PWM) signal, which is positively correlated with the desired fan speed. Finally, a corresponding PWM signal is generated based on this duty cycle, driving the cooling fan motor to precisely adjust the fan speed.

[0039] It should be noted that this specific implementation method, by introducing a proportional-integral-derivative controller and combining it with an anti-saturation integral algorithm, achieves precise processing of temperature deviation signals and continuous dynamic adjustment of fan speed. This effectively avoids the system oscillation and response lag problems caused by integral saturation in traditional control strategies, significantly improving the stability and speed of temperature control, thereby ensuring that the fuel cell stack always operates in the optimal efficiency range under all operating conditions.

[0040] Based on the above embodiments, in some embodiments, the calculation of the initial control quantity includes: The temperature deviation signal is subjected to proportional amplification, integral accumulation and differential prediction processing to obtain proportional term, integral term and differential term; The proportional, integral, and derivative terms are weighted and summed to generate the initial control quantity. The integral term employs an anti-saturation integral algorithm, and the integral accumulation stops when the initial control quantity reaches the limit value.

[0041] In other embodiments, when the initial control quantity reaches a preset limit value, the integral accumulation operation is stopped immediately to prevent excessive accumulation of the integral term from causing controller output saturation, which in turn leads to system oscillation and response lag.

[0042] In one specific embodiment, the initial control quantity is subjected to amplitude limiting processing, and its value is constrained within a preset upper and lower limit range to avoid the actuator from exceeding the safe operating range due to the control quantity being too large or too small.

[0043] Specifically, the formulas for calculating the proportional, integral, and derivative terms are as follows: Proportional term = Kp × e(t), Integral term = Ki × ∫e(t)dt, Derivative term = Kd × de(t) / dt, where Kp, Ki, and Kd are the proportional, integral, and derivative coefficients, respectively, and e(t) is a function of the temperature deviation signal with respect to time t. The initial control quantity u(t) = proportional term + integral term + derivative term. When u(t) reaches the preset limit value U_max or U_min, the integral term stops accumulating.

[0044] It should be noted that the anti-saturation integral algorithm can effectively prevent integral saturation, avoiding the infinite increase of the integral term due to the long-term existence of errors. This ensures that the controller can quickly respond to reverse changes in error under the limiting state, improving the dynamic performance and control accuracy of the system. Based on the above embodiments, in some embodiments, the step of using an electrochemical self-heating strategy to increase the stack temperature under extremely cold start-up conditions, and controlling the cooling fan to smoothly intervene according to a preset curve after the stack temperature reaches a safe temperature, further includes: In the initial stage of startup, the cooling fan is controlled to run at a low speed below a preset threshold or be completely shut down, and the load current of the fuel cell is increased to use the heat generated by the electrochemical reaction to raise the internal temperature of the fuel cell. The stack temperature is monitored in real time. When the stack temperature reaches the preset safe temperature threshold, the fan speed is gradually increased from zero speed or low speed according to the preset speed-time curve, so that the stack temperature smoothly transitions to the optimal temperature point determined by the optimal temperature curve model.

[0045] In other embodiments, the controller determines whether the current ambient temperature is below a preset extreme cold start threshold (e.g., -30°C). If so, it outputs a low duty cycle pulse-width modulation signal to the cooling fan drive circuit, controlling the fan to operate at a low speed below the preset threshold, or directly outputs a zero duty cycle signal to completely shut down the fan. The purpose of this action is to minimize heat loss from the fuel cell stack to the outside environment through forced convection. Subsequently, the controller increases the load current setpoint of the fuel cell stack, which is sent as input to the power converter, which draws a larger current from the fuel cell. The increased load current accelerates the electrochemical reaction rate inside the fuel cell stack, thereby generating more ohmic heat and polarization heat, which, as output, causes the internal temperature of the fuel cell stack to rise rapidly.

[0046] In one specific embodiment, in extremely cold environments, a strategy of briefly shutting off the fan during the initial startup can be adopted to rapidly raise the fuel cell stack temperature using electrochemical self-heating. When the fuel cell stack temperature reaches a preset safe temperature threshold (e.g., 5°C or 10°C), the controller initiates the fan intervention procedure. The controller uses the real-time monitored fuel cell stack temperature as input and compares it with the preset safe temperature threshold. Once the condition is met, the fan speed is gradually increased according to a preset speed-time curve. This preset curve is stored in the controller's non-volatile memory, with time on the horizontal axis and the set value of the fan speed on the vertical axis. The curve shape is typically a smooth S-shape or an exponentially rising curve to ensure that the fan speed increases slowly and continuously from zero or extremely low speed.

[0047] Specifically, the controller looks up the target speed from the curve based on the current time point and converts it into a corresponding pulse width modulation duty cycle signal, which is then output to the fan drive circuit. As the fan speed gradually increases, the heat dissipation capacity of the fuel cell stack also increases, thereby offsetting some of the heat generated by self-heating. This allows the fuel cell stack temperature to smoothly transition to the optimal temperature point under the current operating conditions determined by the optimal temperature curve model, avoiding sudden temperature drops and system oscillations caused by the fan suddenly running at full speed.

[0048] It should be noted that this specific implementation method achieves rapid and safe startup in extremely cold environments by actively reducing heat dissipation and utilizing electrochemical self-heating, avoiding startup failure or thermal stress damage caused by lag in traditional PID control. Simultaneously, a preset smooth intervention curve ensures a smooth transition from self-heating mode to normal temperature tracking mode, eliminating temperature overshoot and control chattering, and significantly improving the system's robustness and stability over a wide temperature range.

[0049] To meet the low-resistance requirements of the air-cooled system and support the implementation of the aforementioned thermal management control, this embodiment also provides a three-stage low-resistance filtration structure for pre-treating the cathode air entering the fuel cell stack. This structure includes: an axial-flow cyclone pre-separation module for efficient pre-filtration of large dust particles; a nanofiber gradient precision filtration module for deep dust containment and low-resistance operation; and a functionalized chemical filtration module for removing toxic gases. These three components work together to ensure low-resistance and clean air intake, providing the basic operating conditions for thermal management control. The low-resistance filtration device ensures that the fan can still supply oxygen at low speeds, providing necessary support for the thermal management control logic of "low-speed warming and self-heating start-up." Dynamic thermal management control avoids high-speed no-load losses from the fan, reduces the load on the filtration module, and extends the filter element life.

[0050] It should be noted that this embodiment deeply couples the low-resistivity filtration device with a dynamic thermal management control method based on the optimal temperature curve, constructing a complete control system that coordinates physical filtration and electrochemical thermal management. This effectively solves the core defects of rigid temperature control and poor adaptability in existing technologies, enabling long-term stable operation of air-cooled fuel cells in high-dust and extremely cold mining environments. The control method of this invention is mainly applied to industrial-grade hydrogen-powered drones performing comprehensive surveying and inspection tasks in extremely cold and complex climatic environments. For example, in mining areas like the Baorixile open-pit coal mine, where the lowest nighttime temperature can reach -50°C and the temperature difference between day and night is huge, hydrogen-powered drones undertake important tasks such as high-precision surveying under 5G networks, monitoring of unmanned heavy mining truck formations, and inspection of high-risk environments.

[0051] Please refer to Figure 2 , Figure 2 A structural block diagram of an optimal temperature curve tracking and control device for a UAV fuel cell is provided in an embodiment of the present invention; the specific device may include: The model building module 100 is used to build an optimal temperature curve model that dynamically changes with real-time current and ambient temperature and humidity through full spectrum performance experiments. The optimal temperature curve model is used to determine the optimal temperature point corresponding to the peak power of the fuel cell stack under different operating conditions. The deviation generation module 200 is used to monitor the current temperature of the fuel cell stack in real time, compare the current temperature with the optimal temperature point determined by the optimal temperature curve model, and generate a temperature deviation signal. The closed-loop control module 300 is used to dynamically adjust the speed of the cooling fan based on the temperature deviation signal using continuous closed-loop control logic, so that the stack temperature tracks the optimal temperature curve indicated by the optimal temperature curve model. The extreme cold start module 400 is used to raise the temperature of the fuel cell stack by adopting an electrochemical self-heating strategy under extreme cold start conditions, and to control the cooling fan to smoothly intervene according to a preset curve after the fuel cell stack temperature reaches a safe temperature.

[0052] In other embodiments, the model building module 100 is further configured to: perform full-condition performance testing on the fuel cell stack within a preset current density range and ambient temperature and humidity range, record the fuel cell stack output power and temperature data corresponding to each operating point; based on the output power and temperature data, fit the optimal temperature point corresponding to the power peak at each current density, and establish a nonlinear mapping relationship between the optimal temperature and current density, ambient temperature and humidity, so as to generate the optimal temperature curve model.

[0053] In other embodiments, the model building module 100 is further configured to: perform peak search on the power-temperature curve for each current density, extract the temperature value corresponding to the maximum power value as the optimal temperature point for that current density; perform polynomial fitting on the optimal temperature points for each current density to obtain the functional relationship between the optimal temperature and the current density, and combine the ambient temperature and humidity correction coefficient to construct the optimal temperature curve model.

[0054] In other embodiments, the deviation generation module 200 is specifically used to: collect the current temperature of the fuel cell stack in real time at a preset sampling frequency using a temperature sensor attached to the surface of the fuel cell stack; query the corresponding optimal temperature point from the optimal temperature curve model based on the real-time collected current signal and ambient temperature and humidity signal; calculate the difference between the current temperature and the optimal temperature point, and generate the temperature deviation signal.

[0055] In other embodiments, the closed-loop control module 300 is specifically used to: input the temperature deviation signal to a proportional-integral-derivative controller to calculate an initial control quantity; perform amplitude limiting processing on the initial control quantity to generate a duty cycle of a pulse width modulation signal; drive a cooling fan motor according to the duty cycle to adjust the fan speed so that the fuel cell stack temperature converges to the optimal temperature point.

[0056] In other embodiments, the closed-loop control module 300 is further configured to: perform proportional amplification, integral accumulation, and differential prediction processing on the temperature deviation signal to obtain a proportional term, an integral term, and a differential term; and perform a weighted summation of the proportional term, integral term, and differential term to generate the initial control quantity, wherein the integral term adopts an anti-saturation integral algorithm, and the integral accumulation stops when the initial control quantity reaches the limit value.

[0057] In other embodiments, the extreme cold start module 400 is specifically used to: control the cooling fan to run at a low speed below a preset threshold or to shut it off completely during the initial start-up phase, and increase the load current of the fuel cell stack to raise the internal temperature of the fuel cell stack by utilizing the heat generated by the electrochemical reaction; monitor the fuel cell stack temperature in real time, and when the fuel cell stack temperature reaches a preset safe temperature threshold, gradually increase the fan speed from zero speed or low speed according to a preset speed-time curve, so that the fuel cell stack temperature smoothly transitions to the optimal temperature point determined by the optimal temperature curve model.

[0058] In one specific embodiment, the device further includes a filtration module comprising a three-stage low-resistance filtration structure: an axial-flow cyclone pre-separation module for efficient pre-filtration of large particulate dust; a nanofiber gradient precision filtration module for deep dust containment and low-resistance operation; and a functionalized chemical filtration module for removing toxic gases. The filtration module is used to pre-treat the cathode air entering the fuel cell stack.

[0059] The UAV fuel cell optimal temperature curve tracking control device of this embodiment is used to implement the aforementioned UAV fuel cell optimal temperature curve tracking control method. Therefore, the specific implementation of the UAV fuel cell optimal temperature curve tracking control device can be found in the previous embodiment section of the UAV fuel cell optimal temperature curve tracking control method. For example, the model building module 100, the deviation generation module 200, the closed-loop control module 300, and the extreme cold start module 400 are respectively used to implement steps S101, S102, S103, and S104 in the above-mentioned UAV fuel cell optimal temperature curve tracking control method. Therefore, its specific implementation can be referred to the description of the corresponding embodiments, which will not be repeated here.

[0060] A specific embodiment of the present invention also provides a drone fuel cell optimal temperature curve tracking and control device, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the above-described drone fuel cell optimal temperature curve tracking and control method.

[0061] A specific embodiment of the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for tracking and controlling the optimal temperature curve of a UAV fuel cell.

[0062] 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.

[0063] 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.

[0064] 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.

[0065] 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.

[0066] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for tracking and controlling the optimal temperature curve of a fuel cell in an unmanned aerial vehicle (UAV), characterized in that, Includes the following steps: An optimal temperature curve model was constructed by conducting full-spectrum performance experiments, which dynamically changes with real-time current and ambient temperature and humidity. This optimal temperature curve model is used to determine the optimal temperature point corresponding to the peak power of the fuel cell stack under different operating conditions. The current temperature of the fuel cell stack is monitored in real time, and the current temperature is compared with the optimal temperature point determined by the optimal temperature curve model to generate a temperature deviation signal. Based on the temperature deviation signal, the speed of the cooling fan is dynamically adjusted using continuous closed-loop control logic so that the fuel cell stack temperature tracks the optimal temperature curve indicated by the optimal temperature curve model. Under extremely cold start-up conditions, an electrochemical self-heating strategy is adopted to increase the stack temperature, and after the stack temperature reaches a safe temperature, the cooling fan is controlled to smoothly intervene according to a preset curve.

2. The method according to claim 1, characterized in that, The construction of the optimal temperature curve model dynamically changing with real-time current and ambient temperature and humidity through full-spectrum performance experiments further includes: The fuel cell stack was subjected to full-condition performance testing within a preset current density range and ambient temperature and humidity range, and the fuel cell stack output power and temperature data at each operating point were recorded. Based on the output power and temperature data, the optimal temperature point corresponding to the power peak at each current density is fitted, and a nonlinear mapping relationship between the optimal temperature and current density, ambient temperature and humidity is established to generate the optimal temperature curve model.

3. The method according to claim 2, characterized in that, The optimal temperature points corresponding to the peak power at each current density are obtained by fitting the following: For each current density, a peak search is performed on the power-temperature curve, and the temperature value corresponding to the maximum power is extracted as the optimal temperature point for that current density. By performing polynomial fitting on the optimal temperature points under various current densities, the functional relationship between the optimal temperature and the current density is obtained. Combined with the environmental temperature and humidity correction coefficient, the optimal temperature curve model is constructed.

4. The method according to claim 1, characterized in that, The real-time monitoring of the current temperature of the fuel cell stack, and the comparison of the current temperature with the optimal temperature point determined by the optimal temperature curve model to generate a temperature deviation signal, further includes: The current temperature of the fuel cell stack is collected in real time by a temperature sensor attached to the surface of the stack at a preset sampling frequency; Based on the real-time collected current signal and ambient temperature and humidity signal, the corresponding optimal temperature point is queried from the optimal temperature curve model; The difference between the current temperature and the optimal temperature point is calculated to generate the temperature deviation signal.

5. The method according to claim 1, characterized in that, The dynamic adjustment of the cooling fan speed based on the temperature deviation signal using continuous closed-loop control logic includes: The temperature deviation signal is input to a proportional-integral-derivative controller to calculate the initial control quantity; the initial control quantity is then subjected to amplitude limiting to generate the duty cycle of a pulse width modulation signal. The cooling fan motor is driven according to the duty cycle, and the fan speed is adjusted so that the fuel cell stack temperature converges to the optimal temperature point.

6. The method according to claim 5, characterized in that, The initial control values ​​obtained from the calculation include: The temperature deviation signal is subjected to proportional amplification, integral accumulation and differential prediction processing to obtain proportional term, integral term and differential term; The proportional, integral, and derivative terms are weighted and summed to generate the initial control quantity. The integral term employs an anti-saturation integral algorithm, and the integral accumulation stops when the initial control quantity reaches the limit value.

7. The method according to claim 1, characterized in that, The method of using an electrochemical self-heating strategy to raise the stack temperature under extremely cold start-up conditions, and controlling the cooling fan to smoothly intervene according to a preset curve after the stack temperature reaches a safe temperature, further includes: In the initial stage of startup, the cooling fan is controlled to run at a low speed below a preset threshold or be completely shut down, and the load current of the fuel cell is increased to use the heat generated by the electrochemical reaction to raise the internal temperature of the fuel cell. The stack temperature is monitored in real time. When the stack temperature reaches the preset safe temperature threshold, the fan speed is gradually increased from zero speed or low speed according to the preset speed-time curve, so that the stack temperature smoothly transitions to the optimal temperature point determined by the optimal temperature curve model.

8. A tracking and control device for the optimal temperature curve of a fuel cell in an unmanned aerial vehicle (UAV), characterized in that, include: The model building module is used to build an optimal temperature curve model that dynamically changes with real-time current and ambient temperature and humidity through full spectrum performance experiments. The optimal temperature curve model is used to determine the optimal temperature point corresponding to the peak power of the fuel cell stack under different operating conditions. The deviation generation module is used to monitor the current temperature of the fuel cell stack in real time, compare the current temperature with the optimal temperature point determined by the optimal temperature curve model, and generate a temperature deviation signal. A closed-loop control module is used to dynamically adjust the speed of the cooling fan based on the temperature deviation signal using continuous closed-loop control logic, so that the stack temperature tracks the optimal temperature curve indicated by the optimal temperature curve model. The extreme cold start module is used to raise the temperature of the fuel cell stack by adopting an electrochemical self-heating strategy under extreme cold start conditions, and to control the cooling fan to smoothly intervene according to a preset curve after the fuel cell stack temperature reaches a safe temperature.

9. A device for tracking and controlling the optimal temperature curve of a fuel cell in an unmanned aerial vehicle (UAV), characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the method for tracking and controlling the optimal temperature curve of a fuel cell for an unmanned aerial vehicle as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for tracking and controlling the optimal temperature curve of a fuel cell for an unmanned aerial vehicle as described in any one of claims 1 to 7.

Images