Health assessment method and device for aerospace solar cells based on physical information networks
Through the method based on physical information network, a health assessment model for satellite solar cells is constructed, and the neural network is optimized by physical information, which solves the problem of insufficient data for health status assessment and model update in satellite power supply systems, and realizes efficient fault detection and health status Evaluate.
Patent Information
- Application Number
- CN202410966787.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-07-18
AI Technical Summary
In the satellite power system, the machine learning-based health status evaluation method is difficult to effectively evaluate the health status of satellite solar cells due to the lack of abnormal data, and traditional models are difficult to update the model status in real time, resulting in difficulty in detecting faults.
Using a method based on physical information network, by constructing the physical mechanism equations of solar cells, physical information is assigned to the PINN-RNN neural network, a health assessment model is established, and physical constraints are added to the loss function, network weights are optimized to identify circuit parameters, and then Assess health status.
The calculation efficiency and performance of the diagnostic algorithm are improved under a small number of samples, the demand for the data volume of training samples is reduced, the problems of unclear mechanism model structure and small telemetry data are solved, and the health status evaluation of satellite solar cells is achieved.
Smart Images

Figure CN118519062B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of satellite power supply technology, and in particular to a method and device for health assessment of aerospace solar cells based on a physical information network. Background Art
[0002] The satellite power system is an important component of the satellite. Its function is to provide electrical energy to the satellite and ensure the normal operation of the satellite. During the long-term operation of the satellite, various faults may occur in the satellite power system. Satellite NewsDigest recorded 421 faults in 318 satellites, of which solar array failures accounted for as high as 63%. As the main energy source for satellite power, the health of the solar array is particularly important. If the fault is not discovered and handled in time, it will have an adverse effect on the operation of the satellite and may even cause damage to the satellite, seriously affecting the completion of the satellite mission.
[0003] At present, the two main analysis methods for health status assessment are machine learning-based and traditional model analysis-based methods. However, most of the health status assessment methods based on machine learning require a large amount of abnormal data as a training set, while the abnormal data of satellite power systems are very limited. This leads to great difficulties in the application of traditional machine learning methods in satellite power system fault detection. Specifically, the traditional mechanism model method requires detailed model knowledge, while the internal structure of the satellite object power system is complex and accurate modeling is very difficult. In addition, the external environment conditions are complex and changeable. As the use time increases, the performance of the components will decrease, and the model method is difficult to update the model status in real time. Therefore, how to effectively evaluate the on-orbit health status with a small number of samples and when the model is unknown has become an important issue in the current research on health detection of satellite power systems. Summary of the invention
[0004] Based on this, it is necessary to provide a health assessment method, device, computer equipment, computer-readable storage medium and computer program product for aerospace solar cells based on a physical information network to address the above technical problems.
[0005] In a first aspect, the present application provides a method for health assessment of aerospace solar cells based on a physical information network. The method comprises:
[0006] Construct the physical mechanism equation of solar cells:
[0007] Based on the physical mechanism equation of the solar cell, the physical information of the solar cell is assigned to the model parameters of the PINN-RNN neural network to construct a health assessment model for aerospace solar cells;
[0008] Training the health assessment model to obtain a trained health assessment model;
[0009] Inputting the operating parameters of the solar cell into the health assessment model to obtain model parameters, and obtaining the circuit parameters of the solar cell according to the model parameters and the physical mechanism equation of the solar cell;
[0010] A health status assessment result of the solar cell is obtained according to the circuit parameters of the solar cell.
[0011] In a second aspect, the present application also provides a health assessment device for aerospace solar cells based on a physical information network. The device comprises:
[0012] A construction module is used to construct a physical mechanism equation of a solar cell, and based on the physical mechanism equation of the solar cell, assign the physical information of the solar cell to the model parameters of the PINN-RNN neural network to construct a health assessment model for aerospace solar cells;
[0013] A training module, used for training the health assessment model to obtain a trained health assessment model;
[0014] A prediction module, used for inputting the operating parameters of the solar cell into the health assessment model to obtain model parameters, and obtaining the circuit parameters of the solar cell according to the model parameters and the physical mechanism equation of the solar cell;
[0015] The evaluation module is used to obtain a health status evaluation result of the solar cell according to the circuit parameters of the solar cell.
[0016] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the health assessment method of aerospace solar cells based on a physical information network in each of the above embodiments are implemented.
[0017] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the health assessment method of aerospace solar cells based on a physical information network according to each of the above embodiments.
[0018] In a fifth aspect, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the health assessment method of aerospace solar cells based on a physical information network in the above-mentioned embodiments are implemented.
[0019] The above-mentioned health assessment method, device, computer equipment, storage medium and computer program product of aerospace solar cells based on physical information network use the equivalent dynamic circuit model of solar cells to integrate into the training mechanism of neural network, provide optimization direction for the parameter update of neural network, give physical meaning to the weight matrix of neural network, and add physical constraint loss to the loss function. In the iterative training process, the circuit parameters are identified by optimizing the network weights, and then the battery health status is identified according to the identified circuit parameters. This method uses physical information to optimize the defect of insufficient interpretability of neural network, and uses neural network to solve the problem of unclear structure of mechanism model and small amount of telemetry data. This method can not only reduce the demand for training sample data, but also improve the computational efficiency and diagnostic performance of diagnostic algorithm. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 A schematic diagram of a process of health assessment of aerospace solar cells based on a physical information network in one embodiment;
[0021] Figure 2 A schematic diagram of a flow chart of a health assessment method for aerospace solar cells based on a physical information network in another embodiment;
[0022] Figure 3 is a schematic diagram of a single diode model of a solar cell in one embodiment;
[0023] Figure 4 is a schematic diagram of a dynamic parameter model of a solar cell in one embodiment;
[0024] Figure 5 A PINN-RNN network training structure in one embodiment;
[0025] Figure 6 A structural block diagram of a health assessment device for aerospace solar cells based on a physical information network in one embodiment;
[0026] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0027] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0028] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0029] A physical information neural network is a type of neural network that imposes physical information constraints during the training process. Compared with traditional data-reliant neural networks, physical information neural networks can obtain stronger generalization capabilities with fewer data samples, and can combine existing data information to solve problems such as high-dimensional nonlinear systems and difficulties in establishing physical models.
[0030] In response to the problems of limited spacecraft diagnostic resources, insufficient experience and data, and difficulty in fault diagnosis and health management, this application proposes a health assessment method for spacecraft solar cells based on physical information networks.
[0031] like Figure 1 and Figure 2 As shown, the method includes:
[0032] Step 102, constructing the physical mechanism equation of the solar cell.
[0033] Specifically, the step includes:
[0034] Step 1: Establish a dynamic model of solar cell current.
[0035] The single diode model of a solar cell consists of a constant current source, a diode, a parallel resistor and a series resistor. The equivalent circuit is as follows: Figure 3 shown.
[0036] The solar array power generation model of the single-body model is described as follows:
[0037] (1)
[0038] Among them, I d is the equivalent diode current, I sh is the parallel resistance current, q is the electron charge constant, R s is the series resistance, R sh is the parallel resistance, A is the ideal factor of the diode, which is generally between 1 and 3, K is the Boltzmann constant, and T is the temperature during the experiment; Iph is the photocurrent, which is related to the light intensity, and I0 is the reverse saturation current of the diode;
[0039] Among them, I ph is the photocurrent, and I0 is the reverse saturation current of the diode, which can be calculated by formula (2):
[0040] (2)
[0041] In the formula, I sc and U oc is the short-circuit current and open-circuit voltage of the cell under reference conditions, T ref is the reference temperature, S ref is the reference light intensity, and S is the light intensity during the experiment.
[0042] In actual working conditions, when the external environment such as light intensity and temperature changes suddenly, the photocurrent of the photovoltaic cell I ph The transient response will be affected. Without considering the uneven temperature and light on the battery surface, the dynamic model is equivalent to a photocurrent source, a series-parallel resistor and a forward diode, and also shows the capacitance characteristics of the junction capacitor and the series inductance. LS .
[0043] Establish as Figure 4 The dynamic model of photovoltaic cells taking into account the forward and reverse characteristics is shown, and its IV characteristic equation is:
[0044] (3)
[0045] In the formula, the parallel capacitor C p Including barrier capacitance and diffusion capacitance, I Cp is the capacitor current, U d is the diode voltage.
[0046] Step 2: Establish the physical mechanism equation of solar cells.
[0047] According to the solar cell dynamic parameter model established in the first two steps and the relationship satisfied by some special points in the volt-ampere characteristic, the following equation can be obtained:
[0048] (4)
[0049] Combining equation (3) and equation (4):
[0050] (5)
[0051] make:
[0052] (6)
[0053] Then formula (5) can be expressed as:
[0054] (7)
[0055] in, U d is the diode voltage, U s is the equivalent series resistance voltage, U L is the equivalent series inductor voltage, R s , L and C are the equivalent series resistance, equivalent series inductance and equivalent parallel capacitance of the equivalent dynamic circuit model, respectively. ph is the photocurrent determined by calculation, I is the actual output current of the solar cell, and U is the actual voltage of the solar cell.
[0056] Step 104, based on the physical mechanism equation of the solar cell, the physical information of the solar cell is assigned to the model parameters of the PINN-RNN neural network to construct a health assessment model for aerospace solar cells.
[0057] Specifically, this step is used to construct a physical-data information model.
[0058] The structure of the PINN-RNN network of an embodiment is as follows: Figure 5 As shown, specifically, the established physical mechanism model of solar cells is used to construct RNN in a specialized way, and the above algebraic differential equations are discretized and processed. Then, at the kth moment, the discrete mathematical model of the solar cell can be obtained by using the Euler difference method.
[0059] The classic expression of RNN network:
[0060] (8)
[0061] in, W hh , W hx , W yh and W yx is the coefficient matrix, b h is a constant vector, h k is the hidden layer state, x k is the kth unit input,y k is the output of the kth unit. Considering the nonlinear characteristics of the diode equivalent model in the solar cell array, the state update expression link of the network is constructed using formula (9):
[0062] (9)
[0063] The activation function g uses the Relu type function, which can approximately describe the nonlinear characteristics of the exponential function.
[0064] (10)
[0065] in, I k , T k is the current and corresponding temperature T at the kth moment, U k is the output voltage at the kth moment, U L_k , U d_k and U s_k are the inductor voltage, diode side terminal voltage and series resistance voltage at the kth moment.
[0066] Then, the weight matrix should be able to reflect the size of the capacitance, resistance, inductance and other parameters in the solar cell.
[0067] Step 106: training the health assessment model to obtain a trained health assessment model.
[0068] Specifically, this step includes constructing model loss and offline model training.
[0069] The steps of constructing the model loss, specifically, the solar cell physical mechanism model constructed in the previous step reflects the training rules of the PINN network and gives the physical information meaning of the neural network neurons. The model must meet the actual physical constraints and meet the accuracy requirements.
[0070] The loss function of PINN is generally expressed as:
[0071] (11)
[0072] in, MSE u is the sample numerical loss, which is used to ensure that the model can accurately fit the rules presented by the sample data and is defined as:
[0073] (12)
[0074] in, Ui_0 is the observed value, U i is the predicted value.
[0075] The offline model training step, specifically, uses ground experimental data or public data set samples to obtain the IV sample data of the solar cell and the corresponding temperature T. I and T are input into the model, and the Adam optimization algorithm is used for iterative calculation. When the MSE is less than the threshold, the training ends.
[0076] Step 108, inputting the operating parameters of the solar cell into the health assessment model to obtain model parameters, and obtaining the circuit parameters of the solar cell according to the model parameters and the physical mechanism equation of the solar cell.
[0077] Specifically, the operating parameters include IV data and the corresponding temperature T of the solar cell.
[0078] The step of inputting the operating parameters of the solar cell into the health assessment model to obtain model parameters, and obtaining the battery aging state description parameters of the solar cell according to the model parameters and the physical mechanism equation of the solar cell, includes: obtaining IV data and corresponding temperature T of the solar cell under real-time operation; inputting the IV data and corresponding temperature T into the health assessment model to output model parameters; obtaining the circuit parameters of the solar cell according to the model parameters and the physical mechanism equation of the solar cell, wherein the circuit parameters include series resistance R s , Parallel resistance R sh , equivalent capacitance C , equivalent inductance L , diode reverse saturation current I 0 , short circuit current parameters I sc and open circuit voltage parameters U oc At least one of .
[0079] Step 110: obtaining a health status assessment result of the solar cell according to the circuit parameters of the solar cell.
[0080] Specifically, according to the series resistance R s , Parallel resistance R sh , equivalent capacitance C Determine the aging status of solar cells from the circuit model level; according to the equivalent inductance L , diode reverse saturation current I 0 , short circuit current parametersI sc and open circuit voltage parameters U oc , describing the battery aging state from the IV curve characteristic level; comparing the battery aging state with the critical fault state to obtain the health status assessment result of the solar cell.
[0081] Therefore, fault prediction can be carried out in time before the component ages and evolves into failure.
[0082] The working environment of spacecraft is complex, and there are problems such as large temperature changes and large changes in light intensity due to frequent entry and exit. Existing solar cells mostly consider static models under constant working conditions, which are not suitable for the health status assessment of solar cells used in aerospace. This application is inspired by the modeling of new perovskite solar cells and introduces a dynamic circuit model of solar cells. It has a wide range of applications and can take into account the capacitive characteristics of some solar cells under sudden changes in working conditions.
[0083] The existing method of using neural network to identify solar cell parameters relies on a large amount of training data. When the data is insufficient, the hyperparameters of the neural network cannot characterize the features extracted by the model of the model, which generally manifests as overfitting. The optimization algorithm can extract various parameters of the solar cell, but it is limited by the initial value of the parameter and is not suitable for online identification scenarios. This application uses the equivalent dynamic circuit model of the solar cell to integrate into the training mechanism of the neural network, provides an optimization direction for the parameter update of the neural network, gives physical meaning to the weight matrix of the neural network, and adds physical constraint loss to the loss function. In the iterative training process, the circuit parameters are identified by optimizing the network weights. The defect of insufficient interpretability of the neural network is optimized by using physical information, and the problem of unclear structure of the mechanism model and insufficient telemetry data is solved by using neural network. This method can not only reduce the demand for the amount of training sample data, but also improve the computational efficiency and diagnostic performance of the diagnostic algorithm.
[0084] This application is applied to the health status assessment of aerospace solar cells. Offline model training is carried out in combination with certain ground test data, and the trained model is migrated to the online test. Data information, physical mechanism information and expert prior knowledge required for health assessment are combined, and they are coupled with each other. The demand for data volume and accurate modeling is not high, and the algorithm occupies small resources. In the actual application stage, online health assessment can be realized without additional testing.
[0085] Based on the same application concept, the embodiment of the present application also provides a physical information network-based aerospace solar cell health assessment device for implementing the above-mentioned physical information network-based aerospace solar cell health assessment method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more physical information network-based aerospace solar cell health assessment devices provided below can refer to the above-mentioned limitations on the physical information network-based aerospace solar cell health assessment method, which will not be repeated here.
[0086] In one embodiment, Figure 6 As shown, a health assessment device for aerospace solar cells based on a physical information network is provided, comprising:
[0087] A construction module 602 is used to construct a physical mechanism equation of a solar cell, and based on the physical mechanism equation of the solar cell, assign the physical information of the solar cell to the model parameters of the PINN-RNN neural network to construct a health assessment model of aerospace solar cells;
[0088] A training module 604 is used to train the health assessment model to obtain a trained health assessment model;
[0089] A prediction module 606 is used to input the operating parameters of the solar cell into the health assessment model to obtain model parameters, and obtain circuit parameters of the solar cell according to the model parameters and the physical mechanism equation of the solar cell;
[0090] The evaluation module 608 is used to obtain the health status evaluation result of the solar cell according to the circuit parameters of the solar cell.
[0091] Each module in the above-mentioned aerospace solar cell health assessment device based on physical information network can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0092] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store training data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a health assessment method for aerospace solar cells based on a physical information network is implemented.
[0093] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0094] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the health assessment method of aerospace solar cells based on a physical information network of the above-mentioned embodiments are implemented.
[0095] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the health assessment method of aerospace solar cells based on a physical information network in the above-mentioned embodiments are implemented.
[0096] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the health assessment method of aerospace solar cells based on a physical information network of the above-mentioned embodiments.
[0097] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0098] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0099] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A health assessment method for aerospace solar cells based on physical information network, It is characterized in that include: Construct the physical mechanism equation of solar cells: The physical mechanism equation of the solar cell is: in, U d is the diode voltage of the equivalent dynamic circuit model of the solar cell, U s is the equivalent series resistance voltage of the equivalent dynamic circuit model of the solar cell, U L is the equivalent series inductor voltage of the equivalent dynamic circuit model of the solar cell, R s , L, C and R sh are the equivalent series resistance, equivalent series inductance, equivalent parallel capacitance and equivalent parallel resistance of the equivalent dynamic circuit model of the solar cell, Ip h is the calculated photocurrent, I is the actual output current of the solar cell, and U is the actual voltage of the solar cell; ;I 0 is the reverse saturation current of the diode, q is the electron charge constant, A is the ideal factor of the diode, K is the Boltzmann constant, and T is the temperature during the experiment; the equivalent dynamic circuit model of the solar cell includes: a photocurrent source, a diode, an equivalent parallel resistor, an equivalent series resistor, an equivalent parallel capacitor, and an equivalent series inductor; the photocurrent source is connected in parallel with the equivalent parallel resistor, the equivalent parallel capacitor, and the diode, and the photocurrent source is connected in series with the equivalent series resistor and the equivalent series inductor; Based on the physical mechanism equation of the solar cell, the physical information of the solar cell is assigned to the model parameters of the PINN-RNN neural network to construct a health assessment model for aerospace solar cells; Training the health assessment model to obtain a trained health assessment model; Inputting the operating parameters of the solar cell into the health assessment model to obtain model parameters, and obtaining the circuit parameters of the solar cell according to the model parameters and the physical mechanism equation of the solar cell; A health status assessment result of the solar cell is obtained according to the circuit parameters of the solar cell.
2. The health assessment method for aerospace solar cells based on physical information network according to claim 1, It is characterized in that Based on the physical mechanism equation of the solar cell, the physical information of the solar cell is assigned to the model parameters of the PINN-RNN neural network to construct a health assessment model for aerospace solar cells, including: The established physical mechanism model of the solar cell is used to perform a special construction of the RNN, and the algebraic differential equation of the physical mechanism model of the solar cell is discretized and processed. Then, at the kth moment, the discrete mathematical model of the solar cell can be obtained by using the Euler difference method; The classic expression of RNN network: in, W hh , W hx , W yh and W yx is the coefficient matrix, b h is a constant vector, h k is the hidden layer state, x k is the kth unit input, y k Output of the kth unit; The state update expression link of the network is constructed using the classic expression of the RNN network: The activation function uses the Relu function to construct the corresponding relationship between the physical information of the solar cell and the model parameters of the PINN-RNN neural network, and obtains the health assessment model of aerospace solar cells; in, I k , T k is the current and corresponding temperature T at the kth moment, U k is the output voltage at the kth moment, U L_k , U d_k and U s_k are the inductor voltage, diode side terminal voltage and series resistance voltage at the kth moment.
3. The health assessment method for aerospace solar cells based on physical information network according to claim 2, It is characterized in that The step of training the health assessment model to obtain a trained health assessment model includes: The loss function of PINN is generally expressed as: in, MSE u is the sample value loss, defined as: in, U i_0 is the observed value, U i is the predicted value; Use ground experimental data or public data set samples to obtain IV sample data of solar cells and the corresponding temperature T; The IV sample data and the corresponding temperature T are input into the health assessment model for training, and the Adam optimization algorithm is used for iterative operation. When the loss is less than the threshold, the training ends and a trained health assessment model is obtained.
4. The health assessment method for aerospace solar cells based on physical information network according to claim 2 or 3, It is characterized in that The operating parameters include IV data of the solar cell and the corresponding temperature T; The step of inputting the operating parameters of the solar cell into the health assessment model to obtain model parameters, and obtaining the battery aging state description parameters of the solar cell according to the model parameters and the physical mechanism equation of the solar cell, comprises: Obtain the IV data and corresponding temperature T of the solar cell in real-time operation; Input the IV data and the corresponding temperature T into the health assessment model, and output the model parameters; According to the model parameters and the physical mechanism equation of the solar cell, the circuit parameters of the solar cell are obtained, and the circuit parameters include the series resistance R s , Parallel resistance R sh , equivalent capacitance C , equivalent inductance L , diode reverse saturation current I 0 , short circuit current parameters I sc and open circuit voltage parameters U oc At least one of .
5. The health assessment method for aerospace solar cells based on physical information network according to claim 4, It is characterized in that The step of obtaining a health status assessment result of the solar cell according to the circuit parameters of the solar cell comprises: According to the series resistance R s , Parallel resistance R sh , equivalent capacitance C Determine the aging status of solar cells from the circuit model level; According to the equivalent inductance L , diode reverse saturation current I 0 , short circuit current parameters I sc and open circuit voltage parameters U oc , describing the battery aging state from the IV curve characteristics level; The battery aging state is compared with the critical fault state to obtain a health status assessment result of the solar cell.
6. A health assessment device for aerospace solar cells based on physical information network, It is characterized in that The device comprises: A construction module is used to construct a physical mechanism equation of a solar cell, and based on the physical mechanism equation of the solar cell, assign the physical information of the solar cell to the model parameters of the PINN-RNN neural network to construct a health assessment model for aerospace solar cells; The physical mechanism equation of the solar cell is: in, U d is the diode voltage of the equivalent dynamic circuit model of the solar cell, U s is the equivalent series resistance voltage of the equivalent dynamic circuit model of the solar cell, U L is the equivalent series inductor voltage of the equivalent dynamic circuit model of the solar cell, R s , L, C and R sh are the equivalent series resistance, equivalent series inductance, equivalent parallel capacitance and equivalent parallel resistance of the equivalent dynamic circuit model of the solar cell, respectively. ph is the calculated photocurrent, I is the actual output current of the solar cell, and U is the actual voltage of the solar cell; ;I 0 is the reverse saturation current of the diode, q is the electron charge constant, A is the ideal factor of the diode, K is the Boltzmann constant, and T is the temperature during the experiment; the equivalent dynamic circuit model of the solar cell includes: a photocurrent source, a diode, an equivalent parallel resistor, an equivalent series resistor, an equivalent parallel capacitor, and an equivalent series inductor; the photocurrent source is connected in parallel with the equivalent parallel resistor, the equivalent parallel capacitor, and the diode, and the photocurrent source is connected in series with the equivalent series resistor and the equivalent series inductor; A training module, used for training the health assessment model to obtain a trained health assessment model; A prediction module, used for inputting the operating parameters of the solar cell into the health assessment model to obtain model parameters, and obtaining the circuit parameters of the solar cell according to the model parameters and the physical mechanism equation of the solar cell; The evaluation module is used to obtain a health status evaluation result of the solar cell according to the circuit parameters of the solar cell.
7. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.
8. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.
9. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.
