Control method, device, equipment and product of solid oxide fuel cell system

Abstract

A control method and device, electronic equipment and program product are related to the field of digital data processing. The method comprises: obtaining the action data of the actuator in the solid oxide fuel cell system at the current time, determining the predicted working data of the solid oxide fuel cell system at the preset future time based on the action data; determining the expected working data corresponding to the predicted working data; the expected working data is obtained based on the first prediction model trained in advance, and the first prediction model is dynamically updated with the running time of the solid oxide fuel cell system; the action data is optimized based on the predicted working data and the expected working data, and the control instruction of the actuator is determined based on the optimized action data, so as to control the actuator based on the control instruction at the current time, realize the dynamic optimization and regulation of the control instruction of the actuator in the solid oxide fuel cell system, and improve the running stability and control precision of the solid oxide fuel cell system.

Description

Technical Field

[0001] This disclosure relates to the field of electronic digital data processing, and more particularly to a control method, apparatus, electronic device, and program product. Background Technology

[0002] Solid oxide fuel cells (SOFCs) are widely used in clean energy power generation due to their high energy efficiency and strong fuel adaptability. The system relies on dynamic parameter adjustment of actuators to ensure stable operation. However, in related technologies, the control methods for SOFCs typically employ fixed-parameter models that remain unchanged after calibration, resulting in poor system stability and control accuracy. Summary of the Invention

[0003] This invention provides a control method, device, electronic device, and program product to achieve dynamic optimization and control of actuator control commands in a solid oxide fuel cell system, thereby improving the operational stability and control accuracy of the solid oxide fuel cell system.

[0004] According to one aspect of the present invention, a control method is provided, the method comprising: Acquire the action data of the actuator in the solid oxide fuel cell system at the current moment, and determine the predicted working data of the solid oxide fuel cell system at a preset future moment based on the action data; Determine the expected working data corresponding to the predicted working data; the expected working data is obtained based on a pre-trained first prediction model, which is dynamically updated as the solid oxide fuel cell system runs. The motion data is optimized based on the predicted working data and the expected working data. The control command for the actuator is determined based on the optimized motion data so as to control the actuator based on the control command at the current moment.

[0005] According to another aspect of the present invention, a control device is provided, the device comprising: The first module is used to acquire the action data of the actuator in the solid oxide fuel cell system at the current moment, and to determine the predicted working data of the solid oxide fuel cell system at a preset future moment based on the action data. The second module is used to determine the expected working data corresponding to the predicted working data; the expected working data is obtained based on a pre-trained first prediction model, which is dynamically updated as the solid oxide fuel cell system runs. The third module is used to optimize the motion data based on the predicted working data and the expected working data, and to determine the control instructions for the actuator based on the optimized motion data, so as to control the actuator based on the control instructions at the current moment.

[0006] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: One or more processors; Storage device for storing one or more programs. When one or more programs are executed by one or more processors, the one or more processors implement any of the control methods described in the embodiments of this disclosure.

[0007] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement any of the control methods of the present invention.

[0008] According to another aspect of the present disclosure, a computer program product is provided, which, when executed by a processor, implements any of the control methods described in the embodiments of the present disclosure.

[0009] The technical solution of this disclosure, by acquiring the actuator's action data at the current moment and determining the predicted working data for a preset future moment based on this action data, enables the system to perceive the future state change trend of the solid oxide fuel cell in advance, avoiding the shortcomings of fixed parameter models that cannot predict dynamic changes. The expected working data corresponding to the predicted working data is determined, and this expected working data is obtained based on a first prediction model that is dynamically updated with the system's runtime. This allows the prediction model to continuously adapt to changes during operation, such as system aging and operating condition drift, avoiding the defect of traditional technologies where parameters remain unchanged after calibration, leading to a decrease in control accuracy. This improves the matching degree between the expected working data and the actual system requirements. The action data is optimized based on the predicted and expected working data, and the control commands for the actuator are determined accordingly. This achieves real-time correction and fine-tuning of the actuator's actions, ensuring that the control commands simultaneously consider the future state of the system and the expected goals, thereby effectively improving the system's operational stability and control accuracy. The technical solution of this disclosure solves the technical problem of poor system stability and control accuracy caused by using a fixed parameter model in a solid oxide fuel cell system, achieving dynamic optimization and control of actuator control commands, and improving the operational stability and control accuracy of the solid oxide fuel cell system.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart illustrating a control method provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of a solid oxide fuel cell system provided in an embodiment of the present disclosure; Figure 3 A flowchart illustrating a control method provided in an embodiment of this disclosure; Figure 4 A flowchart illustrating a control method provided in an embodiment of this disclosure; Figure 5 A schematic diagram illustrating an embodiment of this disclosure for obtaining a first prediction model; Figure 6 This is a schematic diagram of the structure of a control device provided in an embodiment of the present disclosure; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention 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 so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a 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.

[0015] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0016] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0017] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0018] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0019] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0020] Figure 1 This is a flowchart illustrating a control method provided in an embodiment of this disclosure. This embodiment is applicable to controlling actuators in a solid oxide fuel cell system. The method can be executed by a control device, which can be implemented in hardware and / or software and can be configured in electronic devices such as computers or servers. Figure 1 As shown, the method in this embodiment includes: S110. Obtain the action data of the actuator in the solid oxide fuel cell system at the current moment, and determine the predicted working data of the solid oxide fuel cell system at a preset future moment based on the action data.

[0021] In this embodiment, the solid oxide fuel cell system (SOFC) uses solid oxide as the electrolyte and operates at high temperatures. Its operating temperature is typically between 800°C and 1000°C. The actuators in the SOFC system can be understood as electromechanical components that receive output signals from the control system and convert them into physical actions. These actuators are used to regulate the gas flow rate, water flow rate, reformer temperature, stack temperature, air flow rate, and burner temperature within the SOFC system to maintain stable operation of the stack within a safe operating range. In practical applications, the number of actuators in a SOFC system is usually multiple. Examples include a gas proportional valve, a gas three-way valve, an anode circulation pump, a tail gas three-way valve, a blower, and an air proportional valve. The action data can be understood as the real-time status data of the actuators at the current moment. For example, the current opening degree of the gas proportional valve is 45%, the current valve position of the gas three-way valve is set to left, the current speed of the anode circulation pump is 1500 rpm, the current valve position of the exhaust three-way valve is straight, the current speed of the blower is 3200 rpm, and the current opening degree of the air proportional valve is 60%.

[0022] In one situation, such as Figure 2 As shown, the solid oxide fuel cell system includes a fan, air preheater, stack, burner, water tank, water pump, evaporator, fuel tank, first gas proportional valve, reformer, second gas proportional valve, circulation pump, and exhaust gas processor. Its working principle is as follows: The fuel in the fuel tank is methane. The flow rate of the gas to the reformer and burner is controlled by adjusting the opening of the first and second gas proportional valves. The gas in the fuel tank mixes with the anode outlet gas recovered by the anode circulation pump and the steam from the steam generator within the stack, undergoing a reforming reaction. Fresh, cold air is supplied by the fan. Unreacted gas at the anode, fresh gas, and air are burned in the burner, providing heat for preheating the air in the air preheater, evaporating water in the evaporator, and the reforming reaction in the reformer. Finally, the remaining exhaust gas flows into the exhaust gas processor for processing before being discharged.

[0023] The preset future time can be understood as a time after the current time. For example, it could be 10 minutes or 30 minutes after the current time (before the system starts operating), or it could be 10 AM tomorrow. The preset future time can be determined according to actual needs and is not limited here. The interval between the preset future time and the current time can be flexibly set according to actual requirements. For example, the interval could be 10 seconds, 30 seconds, 10 minutes, or 1 hour. Predicted operating data can be understood as the estimated values ​​of various operating parameters of the solid oxide fuel cell system at the preset future time, based on the current actuator action data. For example, if the current actuator action data is a gas proportional valve opening of 45% and a fan speed of 3200 rpm, the predicted operating data 30 seconds later, derived from the first prediction model, would be: stack temperature 785°C and output power 81kW. In short, expected operating data can be understood as the expected operating state data that the system should achieve at the preset future time. For example, the expected stack temperature is 780°C and the expected output power is 85kW.

[0024] Specifically, at the current moment, the action data of the actuators in the solid oxide fuel cell system is collected, thereby obtaining the action data of the actuators in the solid oxide fuel cell system at the current moment. This allows for the determination of a preset future moment. Based on the action data and the preset future moment, the predicted operating data of the solid oxide fuel cell system at the preset future moment can then be determined.

[0025] In this embodiment of the disclosure, determining the predicted operating data of the solid oxide fuel cell system at a preset future time based on the action data may include: determining the predicted operating data of the solid oxide fuel cell system at a preset future time based on the action data using a pre-trained second prediction model.

[0026] The second prediction model can be understood as a model used to predict the operating data of the solid oxide fuel cell system at a preset future time based on action data. Specifically, the action data of the actuators in the solid oxide fuel cell system at the current time is provided to the pre-trained second prediction model, thereby obtaining the predicted operating data of the solid oxide fuel cell system at the preset future time. In other words, the action data of the actuators in the solid oxide fuel cell system at the current time is input into the pre-trained second prediction model to obtain the model output, which is the predicted operating data of the solid oxide fuel cell system at the preset future time.

[0027] In this embodiment of the disclosure, obtaining the second prediction model may include: acquiring a first dataset; the first dataset includes a first sample, which includes the operating data of the actuator in the solid oxide fuel cell system at a first historical moment and the corresponding first expected output result, wherein the first expected output result is the predicted operating data of the solid oxide fuel cell system at a preset future moment after the first historical moment. The first historical moment can be understood as a moment before the current moment. In this embodiment of the disclosure, the interval between the current moment and the preset future moment may be the same as or different from the interval between the preset future moments after the first historical moment. The pre-constructed first initial network model is trained using the first dataset to obtain the trained second prediction model.

[0028] In this embodiment, a pre-constructed first initial network model is trained using a first dataset. Specifically, the operating data of the actuators in the solid oxide fuel cell system at a first historical moment is used as the actual input data to the first initial network model, and the expected output result is used as the expected output result. Specifically, after inputting the operating data of the actuators in the solid oxide fuel cell system at the first historical moment into the first initial network model, a first actual output result can be obtained. Then, based on a first loss between the first actual output result and the corresponding first expected output result, the network parameters of the first initial network can be adjusted so that, when the first loss converges or the number of iterations reaches a first preset number, the trained first initial network model is used as a second prediction model. The first preset number of iterations can be set according to actual needs and is not specifically limited here. The first initial network model can also be set according to actual needs and is not specifically limited here.

[0029] Alternatively, data prediction using the second prediction model can be expressed by the following formula: ; in, It can be represented as step size. It can represent dimensions. For example, when A value of 1 can represent airflow rate, when A value of 2 can represent the gas flow rate. A value of 3 can represent water flow rate. The value of 4 can represent the reformer temperature, when A value of 5 can represent the stack temperature, when A value of 6 indicates the burner temperature. It can be represented as the first The dimension in the first Prediction data at each step size. It can be represented as the first The dimension in the first Prediction working data with a step size of -1. It can be expressed as the first Action data at a step size of -1, such as fan speed, circulating pump speed, water pump speed, and the opening degree of the first and second gas proportional valves. It can represent a function.

[0030] S120. Determine the expected working data corresponding to the predicted working data; the expected working data is obtained based on a pre-trained first prediction model, which is dynamically updated as the solid oxide fuel cell system runs.

[0031] The expected operating data can be understood as the operating data that the solid oxide fuel cell system is expected to achieve at a preset future time, given the current action data of the actuators in the solid oxide fuel cell system. In short, the expected operating data is an expected value, not an actual value. In layman's terms, the predicted operating data reflects the natural evolution trend of the system under the current actuator state, while the expected operating data reflects the target state that the system should achieve in the future. The difference between the two represents the direction and magnitude of adjustment that the control module in the solid oxide fuel cell system needs to make. The first prediction model can be understood as a pre-trained machine learning model that can be used to determine the expected operating data corresponding to the predicted operating data. In this embodiment, the input to the first prediction model is the current operating data of the actuators in the solid oxide fuel cell system, and the output is the optimal state of the solid oxide fuel cell system at a preset future time.

[0032] In this embodiment, the first prediction model is dynamically updated as the solid oxide fuel cell system operates. That is, the first prediction model continuously updates with the increase in system operating time, achieving a technical effect of becoming more accurate with use. For example, every month, the parameters of the first prediction model are retrained or corrected based on the actual operating data accumulated by the solid oxide fuel cell system within the past month, ensuring that the model parameters are consistent with the current true characteristics of the system. As the SOFC stack operates for longer periods, electrode activity decays, sealing performance declines, and heat exchange efficiency decreases, causing the system's true response characteristics to gradually deviate from the factory calibration values. Regularly updating the first prediction model can compensate for characteristic drift caused by aging, maintain prediction accuracy over a long period, avoid misadjustments due to model mismatch, and this process can be completed automatically without manual recalibration, reducing operation and maintenance costs, enabling the system to operate efficiently within safe boundaries, and extending its economic operating life.

[0033] In this embodiment of the disclosure, obtaining the first prediction model may include: acquiring a second dataset; the second dataset includes a second sample, the second sample including the operating data of the solid oxide fuel cell system at a second historical time and a second expected output result, the second expected output result being the expected operating data that the solid oxide fuel cell system should achieve at the second historical time. Then, a pre-constructed second initial network model can be trained using the second dataset to obtain the first prediction model. In this embodiment of the disclosure, the operating data of the solid oxide fuel cell system at the second historical time is used as the data input of the second initial network model, and the second expected output result is used as the expected output result of the second initial network model. Specifically, after inputting the operating data of the solid oxide fuel cell system at the second historical time into the second initial network model, a second actual output result can be obtained. Therefore, based on the second actual output result and the corresponding second expected output result, the network parameters of the second initial network model can be adjusted to obtain the first prediction model.

[0034] S130. Optimize the motion data based on the predicted working data and the expected working data, and determine the control command for the actuator based on the optimized motion data, so as to control the actuator based on the control command at the current moment.

[0035] Control commands can be understood as instructions generated based on motion data to control actuators. Control commands include actuator identifiers and control parameters. The actuator identifier distinguishes different actuators in a solid oxide fuel cell system. Control parameters, the specific control values ​​applied to the actuator, indicate the actions the actuator should perform. For example, when the actuator is identified as a "gas proportional valve," the control parameter could be an opening of 50%; when the actuator is identified as a "fan," the control parameter could be a speed of 3000 rpm; and when the actuator is identified as a "tail gas three-way valve," the control parameter could be a valve position of "straight-through." The range of control parameter values ​​is limited by the physical characteristics and safety constraints of the corresponding actuator.

[0036] Specifically, the predicted operating data and the expected operating data are compared to obtain a comparison result. If the predicted operating data and the expected operating data are inconsistent, the action data can be optimized to obtain optimized action data. Then, control commands for the actuator can be determined based on the optimized action data. At the current moment, the actuator can be controlled based on the control commands to make the actual operating state of the solid oxide fuel cell system approach the expected operating state, thereby reducing the deviation between the predicted and expected operating data and ensuring stable system operation within safety constraints.

[0037] In this embodiment of the disclosure, the optimization processing of the action data based on the predicted working data and the expected working data may include: determining a loss value between the predicted working data and the expected working data; if the loss value is not lower than a loss threshold, then optimizing the working data. Here, the loss value refers to the degree of deviation between the predicted working data and the expected working data. In this embodiment of the disclosure, the loss value can be used to quantify the degree of inconsistency between the predicted working data and the expected working data. Optionally, the loss value can be a deviation, i.e., the difference between the predicted working data and the expected working data in each preset dimension; it can also be the sum of the absolute values ​​of the deviations, i.e., the accumulation of the absolute values ​​of the deviations in each dimension; or it can be a weighted sum of the deviations, i.e., summing the deviations of different dimensions after assigning different weights.

[0038] In one scenario, with the objective of minimizing the loss between predicted and expected work data, the formula can be: ; in, It can be represented as step size. It can represent the start time of a preset time domain. It can represent the end time of the prediction time domain. It can represent dimensions. For example, when A value of 1 can represent the dimension of airflow. A value of 2 can represent the gas flow dimension. A value of 3 can represent the dimension of water flow. A value of 4 can represent the reformer temperature dimension, when A value of 5 can represent the temperature dimension of the fuel cell stack. A value of 6 can represent the burner temperature dimension. It can represent the first The weights corresponding to each dimension. It can represent the first The dimension in the first Prediction data at each step size. It can represent the first Expected working data in each dimension.

[0039] The technical solution of this disclosure, by acquiring the actuator's action data at the current moment and determining the predicted working data for a preset future moment based on this action data, enables the system to perceive the future state change trend of the solid oxide fuel cell in advance, avoiding the shortcomings of fixed parameter models that cannot predict dynamic changes. The expected working data corresponding to the predicted working data is determined, and this expected working data is obtained based on a first prediction model that is dynamically updated with the system's runtime. This allows the prediction model to continuously adapt to changes during operation, such as system aging and operating condition drift, avoiding the defect of traditional technologies where parameters remain unchanged after calibration, leading to a decrease in control accuracy. This improves the matching degree between the expected working data and the actual system requirements. The action data is optimized based on the predicted and expected working data, and the control commands for the actuator are determined accordingly. This achieves real-time correction and fine-tuning of the actuator's actions, ensuring that the control commands simultaneously consider the future state of the system and the expected goals, thereby effectively improving the system's operational stability and control accuracy. The technical solution of this disclosure solves the technical problem of poor system stability and control accuracy caused by using a fixed parameter model in a solid oxide fuel cell system, achieving dynamic optimization and control of actuator control commands, and improving the operational stability and control accuracy of the solid oxide fuel cell system.

[0040] Figure 3 This is a flowchart illustrating another control method provided in this embodiment. The technical solution of this embodiment can be combined with other embodiments; for the same or related parts, they can be described in conjunction with the descriptions of other embodiments, and will not be repeated here. Figure 3 As shown, the method in this embodiment may specifically include: S310. Obtain the action data of the actuator in the solid oxide fuel cell system at the current moment, and determine the predicted working data of the solid oxide fuel cell system at a preset future moment based on the action data.

[0041] S320. The initial working data of the solid oxide fuel cell system is obtained by using the particle swarm optimization algorithm, and the initial working data is used as the working data to be updated.

[0042] In this embodiment, Particle Swarm Optimization (PSO) is an intelligent optimization method that simulates the foraging behavior of bird flocks. Each possible working data solution is considered a "particle," and each particle flies in the solution space, remembering its own optimal position and the optimal position found by the entire flock. Based on this, it continuously adjusts its flight direction and speed, gradually approaching the global optimum. This algorithm can find better combinations of working data. PSO pre-sets the particle swarm size, particle dimension, number of iterations, inertia weight, learning factor, position of each particle, and velocity of each particle according to actual needs. For example, the particle swarm size is 100, the particle dimension is 6, the number of iterations is 100, the inertia weight is [1.2, 0.8], and the learning factor is [1.5, 1.5].

[0043] In this embodiment, the initial working data can be understood as a set of optimal working data obtained by using a particle swarm optimization algorithm to search the model parameter space for the first time before the first prediction model has undergone any actual operational data correction. This set of working data can serve as the initial state benchmark for the first prediction model. Specifically, during the model initialization phase, each dimension of the working data is used as the search variable for the particle swarm optimization algorithm. The optimization objective is to minimize the deviation between the predicted and actual values, and a global search is performed within a reasonable range of values ​​for each dimension. Each particle represents a complete working data scheme. The initial working data is obtained by searching with the particle swarm optimization algorithm to achieve the optimal initial accuracy of the first prediction model. The working data to be updated can be understood as the working data that needs to be updated in the solid oxide fuel cell system.

[0044] S330. The evaluation index of the solid oxide fuel cell system is obtained by using the first prediction model based on the working data to be updated; the expected working data is obtained based on the pre-trained first prediction model, and the first prediction model is dynamically updated with the running time of the solid oxide fuel cell system.

[0045] The evaluation index can be understood as a quantitative result used to measure the quality of the solid oxide fuel cell system's operating state at a predetermined future time. Specifically, the operating data to be updated is provided to the first prediction model, thereby obtaining the model output. The evaluation index of the solid oxide fuel cell system can then be determined based on the model output.

[0046] S340. If the evaluation index meets the convergence condition of the particle swarm optimization algorithm, the working data to be updated is taken as the expected working data corresponding to the predicted working data.

[0047] In this embodiment, the convergence condition of the particle swarm optimization algorithm can be understood as satisfying the criterion for stopping the search during the search for the working data to be updated, with the evaluation index as the optimization target. In each search iteration, the particle swarm optimization algorithm adjusts the working data to be updated based on the current evaluation index. The search process is considered to have converged when either of the following conditions is met: the improvement of the evaluation index is less than a preset threshold for several consecutive iterations, meaning that continuing the search can no longer significantly improve the evaluation index; or, the number of search iterations reaches a preset upper limit. After the convergence condition is met, it indicates that the current working data to be updated has made the evaluation index optimal, that is, the deviation between the predicted working data and the expected working data corresponding to the working data to be updated is minimal. At this time, the working data to be updated can be determined as the expected working data corresponding to the predicted working data.

[0048] In this embodiment of the disclosure, if the evaluation index does not meet the convergence condition of the particle swarm optimization algorithm, the working data to be updated can be updated, the updated working data can be used as the working data to be updated, and the operation based on the working data to be updated by the first prediction model can be returned to be executed.

[0049] Specifically, if the evaluation metric fails to meet the convergence condition of the particle swarm optimization algorithm, at least one of the following parameters can be adjusted: particle position, particle velocity, swarm optimal fitness, swarm optimal position, and inertia weight. Based on the adjusted parameters, a new set of optimal working data is obtained, thus completing the update process for the data to be updated. The updated working data can then be used as the working data to be updated, and the operation based on the working data to be updated using the first prediction model is executed again to obtain the expected working data corresponding to the predicted working data.

[0050] S350. Optimize the motion data based on the predicted working data and the expected working data, and determine the control command for the actuator based on the optimized motion data, so as to control the actuator based on the control command at the current moment.

[0051] The technical solution of this disclosure adopts a particle swarm optimization algorithm to obtain the initial working data of the solid oxide fuel cell system, and uses the initial working data as the working data to be updated; the first prediction model obtains the evaluation index of the solid oxide fuel cell system based on the working data to be updated; when the evaluation index reaches the convergence condition of the particle swarm optimization algorithm, the working data to be updated is used as the expected working data corresponding to the predicted working data, thereby realizing intelligent automatic optimization of the expected working data of the solid oxide fuel cell system and achieving the technical effect of improving the accuracy of parameter optimization.

[0052] Figure 4 This is a flowchart illustrating another control method provided in this embodiment. The technical solution of this embodiment can be combined with other embodiments; for the same or related parts, they can be described in conjunction with the descriptions of other embodiments, and will not be repeated here. Figure 4 As shown, the method in this embodiment may specifically include: S410. Obtain the action data of the actuator in the solid oxide fuel cell system at the current moment, and determine the predicted working data of the solid oxide fuel cell system at a preset future moment based on the action data.

[0053] S420. The initial working data of the solid oxide fuel cell system is obtained by using the particle swarm optimization algorithm, and the initial working data is used as the working data to be updated.

[0054] S430. Input the working data to be updated into the first prediction model to obtain the system efficiency and voltage decay rate of the solid oxide fuel cell system; the expected working data is obtained based on the pre-trained first prediction model, and the first prediction model is dynamically updated with the running time of the solid oxide fuel cell system.

[0055] In this embodiment, the working data to be updated, corrected by the particle swarm optimization algorithm, is used as input to the first prediction model. The first prediction model performs prediction calculations based on this data, outputting two key performance indicators of the solid oxide fuel cell system under its current operating state: system efficiency and voltage decay rate. System efficiency can be understood as a quantitative indicator calculated by the first prediction model based on the working data to be updated, used to measure the energy utilization level of the solid oxide fuel cell system. Voltage decay rate can be understood as a quantitative indicator calculated by the first prediction model based on the working data to be updated, used to measure the degree of performance degradation of the solid oxide fuel cell stack over operating time. Specifically, the working data to be updated is input into the first prediction model to obtain the model output results, namely the system efficiency and voltage decay rate of the solid oxide fuel cell system.

[0056] In this embodiment of the disclosure, obtaining the first prediction model may include: acquiring a third dataset; the third dataset may include multiple third samples; each third sample includes the operating data of the solid oxide fuel cell system at a third historical time and a third expected output result, wherein the third expected output result is the system efficiency and voltage decay rate of the solid oxide fuel cell system at the third historical time; and training a pre-constructed third initial network model using the third dataset to obtain the first prediction model. Specifically, the operating data of the solid oxide fuel cell system at the third historical time is used as the third actual input to the model, and the third expected output result is used as the expected output result of the model. During the training of the third initial network model using the third dataset, the operating data of the solid oxide fuel cell system at the third historical time is input into the third initial network model to obtain the third actual output result. Then, based on the third loss between the third actual output result and the third expected output result, the network parameters of the third initial network model can be adjusted to obtain the first prediction model, see [link to relevant documentation]. Figure 5 .

[0057] S440. Based on the system efficiency and the voltage decay rate, determine the evaluation index of the solid oxide fuel cell system.

[0058] In one scenario, the evaluation metric can be a Boolean value. In another scenario, the evaluation metric can be a graded value. For example, the system can be divided into several intervals based on a combination of system efficiency and voltage decay rate, with each interval corresponding to a graded value. In the embodiments of this disclosure, there are multiple ways to determine the evaluation metric of the solid oxide fuel cell system based on the system efficiency and the voltage decay rate.

[0059] As an optional implementation in this disclosure, upper or lower threshold values ​​are set for system efficiency and voltage decay rate. If the values ​​exceed the threshold range, the evaluation indicators of the solid oxide fuel cell system are deemed unqualified. If the values ​​do not exceed the threshold range, the evaluation indicators of the solid oxide fuel cell system are deemed qualified.

[0060] As another optional implementation in this disclosure, a first weight corresponding to the system efficiency and a second weight corresponding to the voltage decay rate are determined; the first weight and the second weight are dynamically adjusted based on the working data of the solid oxide fuel cell system; and an evaluation index for the solid oxide fuel cell system is determined based on the system efficiency, the voltage decay rate, the first weight, and the second weight.

[0061] The first weight can be understood as a weight dynamically configured for system efficiency based on the actual operating data of the solid oxide fuel cell system. The second weight can be understood as a weight dynamically configured for voltage decay rate based on the actual operating data of the solid oxide fuel cell system. For example, if the system voltage decay is small in the initial stage of operation, the weight of system efficiency can be appropriately increased; if the system voltage decay is large in the later stage of operation, the weight of voltage decay rate can be appropriately increased. The sum of the first weight and the second weight is equal to one.

[0062] Alternatively, the evaluation index of a solid oxide fuel cell system can be determined based on system efficiency, voltage decay rate, a first weight, and a second weight using the following formula: ; in, This can be expressed as an evaluation metric for solid oxide fuel cell systems; This can be expressed as system efficiency; This can be expressed as the voltage decay rate; This can be represented as the first weight; This can be represented as the second weight; It can represent the operating time of a solid oxide fuel cell system.

[0063] S450. If the evaluation index meets the convergence condition of the particle swarm optimization algorithm, the working data to be updated is taken as the expected working data corresponding to the predicted working data.

[0064] S460. Optimize the motion data based on the predicted working data and the expected working data, and determine the control command for the actuator based on the optimized motion data, so as to control the actuator based on the control command at the current moment.

[0065] The technical solution of this disclosure embodiment obtains the system efficiency and voltage decay rate of the solid oxide fuel cell system by inputting the working data to be updated into the first prediction model; based on the system efficiency and the voltage decay rate, the evaluation index of the solid oxide fuel cell system is determined, realizing the dual-index synergistic evaluation based on system efficiency and voltage decay rate, and achieving the technical effect of avoiding the optimization bias of a single index.

[0066] Figure 6 This is a schematic diagram of a control device provided in an embodiment of the present disclosure. Figure 6As shown, the control device includes a first module 610, a second module 620, and a third module 630. The first module 610 is used to acquire the action data of the actuator in the solid oxide fuel cell system at the current moment, and determine the predicted operating data of the solid oxide fuel cell system at a preset future moment based on the action data. The second module 620 is used to determine the expected operating data corresponding to the predicted operating data; the expected operating data is obtained based on a pre-trained first prediction model, which is dynamically updated with the running time of the solid oxide fuel cell system. The third module 630 is used to optimize the action data based on the predicted operating data and the expected operating data, and determine the control command for the actuator based on the optimized action data, so as to control the actuator at the current moment based on the control command.

[0067] The technical solution of this disclosure, by acquiring the actuator's action data at the current moment and determining the predicted working data for a preset future moment based on this action data, enables the system to perceive the future state change trend of the solid oxide fuel cell in advance, avoiding the shortcomings of fixed parameter models that cannot predict dynamic changes. The expected working data corresponding to the predicted working data is determined, and this expected working data is obtained based on a first prediction model that is dynamically updated with the system's runtime. This allows the prediction model to continuously adapt to changes during operation, such as system aging and operating condition drift, avoiding the defect of traditional technologies where parameters remain unchanged after calibration, leading to a decrease in control accuracy. This improves the matching degree between the expected working data and the actual system requirements. The action data is optimized based on the predicted and expected working data, and the control commands for the actuator are determined accordingly. This achieves real-time correction and fine-tuning of the actuator's actions, ensuring that the control commands simultaneously consider the future state of the system and the expected goals, thereby effectively improving the system's operational stability and control accuracy. The technical solution of this disclosure solves the technical problem of poor system stability and control accuracy caused by using a fixed parameter model in a solid oxide fuel cell system, achieving dynamic optimization and control of actuator control commands, and improving the operational stability and control accuracy of the solid oxide fuel cell system.

[0068] In some embodiments of this disclosure, optionally, the second module 620 includes a first unit, a second unit, and a third unit. The first unit is used to obtain initial operating data of the solid oxide fuel cell system using a particle swarm optimization algorithm, and uses the initial operating data as operating data to be updated. The second unit is used to obtain evaluation metrics of the solid oxide fuel cell system based on the operating data to be updated using the first prediction model. The third unit, when the evaluation metrics meet the convergence condition of the particle swarm optimization algorithm, uses the operating data to be updated as expected operating data corresponding to the predicted operating data.

[0069] In some embodiments of this disclosure, the second module 620 may optionally include a fourth unit; wherein the fourth unit is used to update the working data to be updated when the evaluation index does not meet the convergence condition of the particle swarm optimization algorithm, take the updated working data as the working data to be updated, and return to execute the operation based on the working data to be updated by the first prediction model.

[0070] In some embodiments of this disclosure, optionally, the second unit includes a first subunit and a second subunit; wherein, the first subunit is used to input the working data to be updated into the first prediction model to obtain the system efficiency and voltage decay rate of the solid oxide fuel cell system; the second subunit is used to determine the evaluation index of the solid oxide fuel cell system based on the system efficiency and the voltage decay rate.

[0071] In some embodiments of this disclosure, optionally, a second subunit is used to determine a first weight corresponding to the system efficiency and a second weight corresponding to the voltage decay rate; the first weight and the second weight are dynamically configured based on the actual operating data of the solid oxide fuel cell system; and an evaluation index of the solid oxide fuel cell system is determined based on the system efficiency, the voltage decay rate, the first weight, and the second weight.

[0072] In some embodiments of this disclosure, optionally, the first module 610 is used to determine the predicted operating data of the solid oxide fuel cell system at a preset future time based on the action data using a pre-trained second prediction model.

[0073] In some embodiments of this disclosure, optionally, the third module 630 is used to determine the loss value between the predicted working data and the expected working data, and if the loss value is not lower than the loss threshold, then the working data is optimized.

[0074] The control device provided in this disclosure can execute the control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0075] It is worth noting that the various units and modules included in the above control device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0076] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0077] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0078] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0079] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the automatic completion method for programming language end tags.

[0080] In some embodiments, the automatic completion method for programming language end tags may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory (ROM) 12 and / or communication unit 19. When the computer program is loaded into random access memory (RAM) 13 and executed by processor 11, one or more steps of the automatic completion method for programming language end tags described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the automatic completion method for programming language end tags by any other suitable means (e.g., by means of firmware).

[0081] Various embodiments of the systems and techniques described above can be implemented in digital circuit systems, integrated circuits, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, at least one input device, and at least one output device.

[0082] Computer programs for implementing the automatic completion method for programming language end tags of this disclosure can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0083] This disclosure provides a computer-readable storage medium storing computer instructions for causing a processor to execute a control method, comprising: acquiring action data of an actuator in a solid oxide fuel cell system at a current time; determining predicted operating data of the solid oxide fuel cell system at a preset future time based on the action data; determining expected operating data corresponding to the predicted operating data; the expected operating data being obtained based on a pre-trained first prediction model, the first prediction model being dynamically updated with the operating time of the solid oxide fuel cell system; optimizing the action data based on the predicted operating data and the expected operating data; and determining control instructions for the actuator based on the optimized action data, so as to control the actuator at the current time based on the control instructions.

[0084] In the context of this disclosure, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0085] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0086] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0087] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Servers (VPS) in terms of management difficulty and weak business scalability.

[0088] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of embodiments of this disclosure.

[0089] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements an automatic completion method for programming language end tags according to any embodiment of this disclosure.

[0090] In implementing a computer program product, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0091] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0092] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A control method for a solid oxide fuel cell system, characterized in that, The method includes: The system acquires the action data of the actuators in the solid oxide fuel cell system at the current moment, and determines the predicted operating data of the solid oxide fuel cell system at a preset future moment based on the action data; the action data includes gas flow rate, water flow rate, reformer temperature, stack temperature, air flow rate, and burner temperature; the predicted operating data includes stack temperature and output power. Determine the expected working data corresponding to the predicted working data; the expected working data is obtained based on a pre-trained first prediction model, which is dynamically updated as the solid oxide fuel cell system runs. The motion data is optimized based on the predicted working data and the expected working data. The control command for the actuator is determined based on the optimized motion data so as to control the actuator based on the control command at the current moment. The step of determining the expected working data corresponding to the predicted working data includes: obtaining the initial working data of the solid oxide fuel cell system using a particle swarm optimization algorithm, and using the initial working data as the working data to be updated; obtaining the evaluation index of the solid oxide fuel cell system based on the working data to be updated using the first prediction model; and using the working data to be updated as the expected working data corresponding to the predicted working data when the evaluation index meets the convergence condition of the particle swarm optimization algorithm. The step of obtaining the evaluation index of the solid oxide fuel cell system based on the working data to be updated using the first prediction model includes: inputting the working data to be updated into the first prediction model to obtain the system efficiency and voltage decay rate of the solid oxide fuel cell system; and determining the evaluation index of the solid oxide fuel cell system based on the system efficiency and the voltage decay rate. The step of determining the evaluation index of the solid oxide fuel cell system based on the system efficiency and the voltage decay rate includes: determining a first weight corresponding to the system efficiency and a second weight corresponding to the voltage decay rate; the first weight and the second weight are dynamically configured based on the actual working data of the solid oxide fuel cell system; and determining the evaluation index of the solid oxide fuel cell system based on the system efficiency, the voltage decay rate, the first weight, and the second weight.

2. The control method according to claim 1, characterized in that, The method further includes: If the evaluation metric does not meet the convergence condition of the particle swarm optimization algorithm, the working data to be updated is updated, and the updated working data is used as the working data to be updated. Then, the operation based on the working data to be updated using the first prediction model is returned to be executed.

3. The control method according to claim 1, characterized in that, The step of determining the predicted operating data of the solid oxide fuel cell system at a preset future time based on the action data includes: Based on the action data, a pre-trained second prediction model is used to determine the predicted operating data of the solid oxide fuel cell system at a preset future time.

4. The control method according to claim 1, characterized in that, The optimization processing of the action data based on the predicted working data and the expected working data includes: Determine the loss value between the predicted working data and the expected working data. If the loss value is not lower than the loss threshold, then optimize the working data.

5. A control device for a solid oxide fuel cell system, characterized in that, The device includes: The first module is used to acquire the action data of the actuators in the solid oxide fuel cell system at the current moment, and to determine the predicted operating data of the solid oxide fuel cell system at a preset future moment based on the action data; the action data includes gas flow rate, water flow rate, reformer temperature, stack temperature, air flow rate, and burner temperature; the predicted operating data includes stack temperature and output power. The second module is used to determine the expected working data corresponding to the predicted working data; the expected working data is obtained based on a pre-trained first prediction model, which is dynamically updated as the solid oxide fuel cell system runs. The third module is used to optimize the motion data based on the predicted working data and the expected working data, and to determine the control instructions for the actuator based on the optimized motion data, so as to control the actuator based on the control instructions at the current moment. The step of determining the expected working data corresponding to the predicted working data includes: obtaining the initial working data of the solid oxide fuel cell system using a particle swarm optimization algorithm, and using the initial working data as the working data to be updated; obtaining the evaluation index of the solid oxide fuel cell system based on the working data to be updated using the first prediction model; and using the working data to be updated as the expected working data corresponding to the predicted working data when the evaluation index meets the convergence condition of the particle swarm optimization algorithm. The step of obtaining the evaluation index of the solid oxide fuel cell system based on the working data to be updated using the first prediction model includes: inputting the working data to be updated into the first prediction model to obtain the system efficiency and voltage decay rate of the solid oxide fuel cell system; and determining the evaluation index of the solid oxide fuel cell system based on the system efficiency and the voltage decay rate. The step of determining the evaluation index of the solid oxide fuel cell system based on the system efficiency and the voltage decay rate includes: determining a first weight corresponding to the system efficiency and a second weight corresponding to the voltage decay rate; the first weight and the second weight are dynamically configured based on the actual working data of the solid oxide fuel cell system; and determining the evaluation index of the solid oxide fuel cell system based on the system efficiency, the voltage decay rate, the first weight, and the second weight.

6. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the control method as described in any one of claims 1-4.

7. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the control method according to any one of claims 1-4.

Images