Electrochemical device degradation model determination method, electrochemical device degradation prediction method

Abstract

The present disclosure relates to a method for determining an electrochemical device degradation model and a method for predicting electrochemical device degradation. The method includes: obtaining real-time operating data of the electrochemical device to be predicted under variable operating conditions, the real-time operating data including a first value of a first operating parameter and a second value of a second operating parameter; determining a third value of a degradation index of the electrochemical device to be predicted based on the second value and the electrochemical device model, training an initial degradation model based on the first value and the third value to obtain a trained degradation model, the electrochemical device including a battery and / or an electrolytic cell. The method for determining an electrochemical device degradation model of an embodiment of the present disclosure can train a degradation model, and the degradation model can accurately predict the degradation information of the electrochemical device to be predicted.

Description

Technical Field

[0001] The present disclosure relates to the field of computers, and in particular to a method for determining an electrochemical device degradation model and a method for predicting electrochemical device degradation. Background Art

[0002] Electrochemical devices (eg, batteries, electrolytic cells) may degrade, and accurate prediction of degradation information of electrochemical devices is of great significance. For example, the remaining life of the electrochemical device can be determined based on the degradation information.

[0003] How to accurately predict the degradation information of electrochemical devices has become an urgent problem to be solved. Summary of the invention

[0004] In view of this, the present disclosure proposes a method for determining an electrochemical device degradation model and a method for predicting electrochemical device degradation, which can train a degradation model that can accurately predict degradation information of the electrochemical device to be predicted.

[0005] According to one aspect of the present disclosure, a method for determining an electrochemical device degradation model is provided, the method comprising:

[0006] Acquiring real-time operating data of an electrochemical device to be predicted under a variable operating condition, wherein the real-time operating data includes a first value of a first operating parameter and a second value of a second operating parameter, wherein the electrochemical device includes a battery and / or an electrolytic cell;

[0007] Determining a third value of the degradation indicator of the electrochemical device to be predicted according to the second value and a pre-trained electrochemical device model;

[0008] According to the first value and the third value, an initial degradation model is trained to obtain a trained degradation model, wherein the degradation model is used to predict degradation information of the electrochemical device to be predicted.

[0009] The degradation model is constructed based on the first operating parameter and the degradation index, and the degradation index is unrelated to the first operating parameter.

[0010] In a possible implementation manner, the degradation model includes a correlation function, and the correlation function is used to characterize the relationship between the degradation information of the electrochemical device to be predicted and the first operating parameter.

[0011] In a possible implementation manner, the training of the initial degradation model according to the first value and the third value includes:

[0012] The real-time operation data includes operation data at a target time, and the method further includes:

[0013] Determine a first value and a third value for each running moment within a target time interval, wherein the target time interval is determined according to the target moment;

[0014] The step of training the initial degradation model according to the first value and the third value includes:

[0015] The model parameters of the degradation model are determined according to the first value and the third value at each operating moment in the target time interval by using the maximum likelihood method.

[0016] In one possible implementation, the electrochemical device model is constructed based on the second operating parameter and the degradation index, and the electrochemical device model is fitted according to historical operating data of the electrochemical device to be predicted under variable operating conditions, and the historical operating data includes a fourth value of the second operating parameter.

[0017] In a possible implementation, the third value of the degradation indicator determined based on the second value and the pre-trained electrochemical device model is obtained after denoising.

[0018] In one possible implementation, the second operating parameter includes a target parameter and a parameter to be predicted, the electrochemical device to be predicted is configured with target operating data, the target operating data is used to determine the predicted degradation information of the electrochemical device to be predicted under the target operating data, the target operating data includes the value of the first operating parameter and the value of the target parameter, the value of the parameter to be predicted is used to characterize the predicted degradation information of the electrochemical device to be predicted.

[0019] In one possible implementation, the battery includes one of a solid oxide fuel cell, a proton exchange membrane fuel cell and an alkaline fuel cell, the electrolytic cell includes one of a solid oxide electrolytic cell, a proton exchange membrane electrolytic cell and an alkaline electrolytic cell, and the first operating parameter includes at least one of the following: power, gas pressure, gas composition, material utilization, current density, current, voltage, temperature and gas flow rate.

[0020] According to another aspect of the present disclosure, a method for predicting degradation of an electrochemical device is provided, the method comprising:

[0021] Determining target operation data of an electrochemical device to be predicted within a target operation period, wherein the target operation data comprises a first target value of a first operation parameter, and the electrochemical device comprises a battery and / or an electrolytic cell;

[0022] Determining a third target value of the electrochemical device to be predicted at at least one operating moment within the target operating period according to the degradation model and the first target value;

[0023] determining predicted degradation information of the electrochemical device to be predicted according to the third target value of the at least one operating moment,

[0024] Wherein, the degradation model is obtained based on the above-mentioned method for determining the degradation model of the electrochemical device.

[0025] In a possible implementation, the second operating parameter includes a target parameter and a parameter to be predicted, the target operating data also includes a second target value of the target parameter, and the method further includes:

[0026] Determining a predicted value of the parameter to be predicted according to the third target value, the second target value, and a pre-trained electrochemical device model;

[0027] determining predicted degradation information of the electrochemical device to be predicted according to the predicted value,

[0028] The electrochemical device model is constructed based on the second operating parameter and the degradation index.

[0029] In a possible implementation, the method further includes:

[0030] Acquiring actual degradation information of the electrochemical device to be predicted;

[0031] Performing abnormality judgment according to the predicted degradation information and the actual degradation information;

[0032] When it is determined that the electrochemical device to be predicted is abnormal, an alarm operation is performed.

[0033] In an embodiment of the present disclosure, real-time operating data of an electrochemical device to be predicted under a variable operating condition is obtained, the real-time operating data including a first value of a first operating parameter and a second value of a second operating parameter; a third value of a degradation indicator of the electrochemical device to be predicted is determined based on the second value and an electrochemical device model, and an initial degradation model is trained based on the first value and the third value to obtain a trained degradation model, so that the degradation information of the electrochemical device to be predicted can be accurately predicted based on the degradation model.

[0034] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0036] Figure 1 A flow chart of a method for determining an electrochemical device degradation model according to an embodiment of the present disclosure is shown.

[0037] Figure 2 A flow chart of a method for predicting degradation of an electrochemical device according to an embodiment of the present disclosure is shown.

[0038] Figure 3 A flow chart of a method for determining an electrochemical device degradation model and a method for predicting electrochemical device degradation according to an embodiment of the present disclosure is shown.

[0039] Figure 4 A block diagram showing a device for determining an electrochemical device degradation model according to an embodiment of the present disclosure.

[0040] Figure 5 A block diagram of an electrochemical device degradation prediction device according to an embodiment of the present disclosure is shown.

[0041] Figure 6 A block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0042] Figure 7 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0043] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0044] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0045] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0046] Electrochemical devices (e.g., batteries, electrolytic cells) will degrade, and accurate prediction of the degradation information of electrochemical devices is of great significance. For example, the health of the electrochemical devices can be monitored, and the remaining life of the electrochemical devices can be extended by optimizing and controlling the operating parameters.

[0047] However, in the related art, there is a lack of methods that can accurately predict the degradation information of the electrochemical device, which makes it impossible to accurately determine the remaining life of the electrochemical device or whether the electrochemical device has undergone rapid degradation.

[0048] Furthermore, in the related art, there is a lack of a degradation model that can describe the relationship between the degradation information (e.g., degradation rate) of the electrochemical device and the operating parameters (e.g., temperature, voltage and other parameters), so it is impossible to achieve the purpose of reducing the degradation rate of the electrochemical device and extending the life of the electrochemical device by optimizing and controlling the operating parameters of the electrochemical device.

[0049] In order to solve the above problems, the present disclosure provides a method for determining an electrochemical device degradation model. The initial degradation model is trained by the operating data of the electrochemical device to be predicted under variable operating conditions. The degradation model obtained by training can accurately predict the degradation information of the electrochemical device to be predicted. The remaining life of the electrochemical device and the health of the electrochemical device can be determined by the predicted degradation information determined by the degradation model. For example, the health of the electrochemical device can be monitored based on the predicted degradation information, and when it is determined that the electrochemical device is suspected of rapid degradation, an alarm operation can be performed.

[0050] Among them, the predicted degradation information can be any information including the numerical value of the degradation index determined according to the degradation model, the degradation trend of the degradation index, the operating parameter value of the electrochemical device to be predicted, the change trend of the operating parameter of the electrochemical device to be predicted, etc. The present disclosure does not limit the form and content of the predicted degradation information.

[0051] Moreover, the degradation model obtained through training can also clearly and directly describe the relationship between the degradation information and the operating parameters of the electrochemical device. Thus, the preferred values ​​of one or more operating parameters can be determined according to the degradation model obtained through training, and the electrochemical device can be controlled to operate within the parameter range determined by the preferred values, thereby reducing the degradation rate of the electrochemical device and extending the life of the electrochemical device.

[0052] In some optional embodiments, the degradation model obtained through training can also be used to guide the identification of information such as material composition, process parameters, and operating modes that are conducive to slowing down the degradation of electrochemical devices. For example, the predicted degradation information predicted by the degradation models of different electrochemical devices (for example, using different material compositions, manufacturing process parameters, and operating modes) can be compared to identify information such as material composition, process parameters, and operating modes that are conducive to slowing down the degradation of electrochemical devices, and guide the design of electrochemical devices. It should be noted that for the same initial degradation model, the model parameters in the degradation models obtained through training of different electrochemical devices may be different, and the initial degradation models of different electrochemical devices may also be different.

[0053] In some optional embodiments, the degradation model obtained through training can also be used to guide the selection of the fuel electrochemical device system, system design, etc. For example, the degradation model obtained through training predicts the expected life of the fuel electrochemical device, and guides the selection of the fuel electrochemical device system, the design of the capacity configuration scheme, etc. according to the expected life, for example, assists in determining the model of the installed electrochemical device and the capacity of the electrochemical device to improve the expected life of the fuel electrochemical device system.

[0054] Figure 1 A flow chart of a method for determining an electrochemical device degradation model according to an embodiment of the present disclosure is shown. The method can be executed by an electronic device such as a terminal device or a server, and the present disclosure does not limit this. For example, the terminal device can be a user terminal, a terminal, a computing device, etc. The method can be implemented by a processor calling a computer-readable instruction stored in a memory, or the method can be executed by a server. Figure 1 As shown, the method includes:

[0055] In step S11, real-time operating data of the electrochemical device to be predicted under a variable operating condition is obtained, wherein the real-time operating data includes a first value of a first operating parameter and a second value of a second operating parameter, and the electrochemical device includes a battery and / or an electrolytic cell;

[0056] In step S12, a third value of the degradation indicator of the electrochemical device to be predicted is determined according to the second value and the pre-trained electrochemical device model;

[0057] In step S13, the initial degradation model is trained according to the first value and the third value to obtain a trained degradation model, wherein the degradation model is used to predict the degradation information of the electrochemical device to be predicted.

[0058] The degradation model is constructed based on the first operating parameter and the degradation index, and the degradation index is unrelated to the first operating parameter.

[0059] According to the disclosed embodiment, the degradation model is trained based on the real-time operating data of the electrochemical device to be predicted under variable operating conditions, without the need to conduct parallel degradation experiments under constant operating conditions, which can reduce the training cost. In addition, the degradation model obtained through training can reflect the degradation information of a specific electrochemical device and determine the degradation characteristics of the specific electrochemical device, solving the problem that the degradation model fitted based on multiple fuel parallel experimental data in the related art mainly reflects the statistical degradation characteristics of a group of electrochemical devices, but cannot accurately reflect the degradation characteristics of a specific electrochemical device.

[0060] By acquiring the real-time operating data of the electrochemical device to be predicted under variable operating conditions, a third value of the degradation index that is unrelated to the first operating parameter is determined from the real-time operating data under variable operating conditions online and in real time at a low computing cost, so as to train the degradation model according to the first value and the third value of the first operating parameter. The degradation model can be trained online based on the actual real-time operating data without interrupting the normal operation process of the electrochemical device to be predicted. The degradation model obtained by such training meets the actual needs and has a high prediction accuracy.

[0061] The degradation index is not related to the first operating parameter. The term "not related" can be understood as the degradation index may not be obtained according to the definition of the first operating parameter. It should be understood that the value of the first operating parameter fluctuates violently under variable operating conditions and is not suitable as a degradation index under variable operating conditions. The degradation index that is not related to the first operating parameter is more suitable as an index for measuring degradation information of the degradation model under variable operating conditions. The degradation model determined based on the degradation index that is not related to the first operating parameter is more in line with the actual situation and can improve the accuracy of the degradation model prediction.

[0062] In one possible implementation, the electrochemical device to be predicted may include a battery and / or an electrolytic cell. Among them, the battery may include various types of fuel electrochemical devices, wherein the feed of the fuel electrochemical device is fuel. The feed of the electrolytic cell is water. When the feed is sufficient, the fuel electrochemical device can be maintained in a power generation state, and the electrolytic cell can be maintained in an electrolysis state. The electrochemical device to be predicted in the embodiment of the present disclosure may include any type of battery and / or electrolytic cell, and the present disclosure does not limit the type of electrochemical device.

[0063] It should be noted that some electrochemical devices can be used as batteries and electrolytic cells. For example, solid oxide electrochemical devices can switch between power generation and electrolysis modes. It should be understood that such electrochemical devices can also be used as the electrochemical devices to be predicted in the embodiments of the present disclosure.

[0064] In a possible implementation, the battery may include one of a solid oxide fuel cell (SOFC), a proton exchange membrane fuel cell (PEMFC), and an alkaline fuel cell (AFC).

[0065] In a possible implementation, the electrolysis cell may include one of a solid oxide electrolysis cell (SOEC), a proton exchange membrane electrolysis cell (PEMEC), and an alkaline electrolysis cell (AEC).

[0066] Among them, the degradation mechanism of solid oxide fuel cell SOFC is relatively complex, and this article takes the electrochemical device to be predicted as SOFC for illustrative explanation. The variable operating state may refer to a state different from the designed operating state. For example, when the electrochemical device is in a variable operating state, the operating parameters such as temperature and voltage are the actual operating data during the working process, and the actual operating data at different operating times may be different.

[0067] The first operating parameter is an operating parameter used to construct a degradation model. For example, the first operating parameter may include at least one of the following: power, gas pressure, gas composition, material utilization, current density, current, voltage, temperature, and gas flow rate. The temperature may include the temperature of the electrochemical device itself and the temperature of the gas; the gas flow rate may include the flow rate of the gas on both sides of the cathode and anode of the electrochemical device; the gas pressure may include the pressure of the gas on both sides of the cathode and anode of the electrochemical device; the gas composition may include the composition of the gas on both sides of the cathode and anode of the electrochemical device, etc.

[0068] The second operating parameter is an operating parameter used to construct an electrochemical device model. For example, the second operating parameter may include at least one of the following: power, gas pressure, gas composition, material utilization, current density, current, voltage, temperature, and gas flow rate. Among them, the temperature may include the temperature of the electrochemical device itself and the temperature of the gas; the gas flow rate may include the flow rate of the gas on both sides of the cathode and anode of the electrochemical device; the gas pressure may include the pressure of the gas on both sides of the cathode and anode of the electrochemical device; the gas composition may include the composition of the gas on both sides of the cathode and anode of the electrochemical device, etc.

[0069] The first operating parameter and the second operating parameter may be partially the same. For example, the first operating parameter and the second operating parameter may both include temperature and current.

[0070] In one possible implementation, the second operating parameter may include a target parameter and a parameter to be predicted, the electrochemical device to be predicted is configured with target operating data, the target operating data is used to determine the predicted degradation information of the electrochemical device to be predicted under the target operating data, the target operating data includes the value of the first operating parameter and the value of the target parameter, the value of the parameter to be predicted is used to characterize the predicted degradation information of the electrochemical device to be predicted.

[0071] Among them, the target operating data may refer to the planned operating data of the electrochemical device to be predicted, and the target operating data may include the numerical value of the first operating parameter and the numerical value of part of the second operating parameter. For example, the target operating data includes the numerical value of the target parameter in the second operating parameter, but does not include the numerical value of the parameter to be predicted in the second operating parameter.

[0072] For example, the target operating data can be used to determine the predicted degradation information of the electrochemical device to be predicted under the target operating data. For example, based on the value of the first operating parameter included in the target operating data and the trained degradation model, at least one value of the degradation index can be determined, and the at least one value of the degradation index can be used to characterize the predicted degradation information of the electrochemical device to be predicted under the target operating data.

[0073] The value of the degradation index and the value of the target parameter included in the target operation data can also be used to determine the value of the parameter to be predicted. For example, the value of the degradation index and the value of the target parameter can be input into a trained electrochemical device model to obtain the value of the parameter to be predicted. The value of the parameter to be predicted can also be used to characterize the predicted degradation information of the electrochemical device to be predicted.

[0074] For ease of understanding, this article takes the example that the first operating parameter includes voltage and temperature, the second operating parameter includes current, voltage and temperature, and the target operating data includes voltage value and temperature value. It should be understood that the first operating parameter, the second operating parameter and the target operating data can be set flexibly, and the target operating data can also include the numerical values ​​of other parameters besides the first operating parameter and the second operating parameter, and the present disclosure does not limit this.

[0075] The degradation model is constructed based on the first operating parameter and the degradation index. The degradation model may further include model parameters. The present disclosure does not limit the form of the degradation model.

[0076] In a possible implementation, the degradation model constructed based on the first operating parameter and the degradation index may be as shown in formula (1):

[0077] dR0(t)=g(U,T;λ1,…λm )dt+σdB t (1)

[0078] Where dR0(t) represents the change in the value of the degradation index R0(t) at time t relative to the value of the degradation index at time t-1, g(U, T; λ1, ...λ m ) can characterize the influence of the first operating parameter on the degradation information of the electrochemical device to be predicted, wherein the first operating parameter includes voltage U and temperature T, λ1, ...λ m represents the m model parameters of the degradation model, σ represents the random coefficient, B t represents standard Brownian motion, dB t Represents the amount of change in standard Brownian motion.

[0079] The degradation model obtained through training in the embodiment of the present disclosure is simple in form and has a clear input-output relationship, which facilitates subsequent optimization and control processing of the electrochemical device.

[0080] In a possible implementation manner, the degradation model includes a correlation function, and the correlation function is used to characterize the relationship between the degradation information of the electrochemical device to be predicted and the first operating parameter.

[0081] As mentioned above, g(U,T;λ1,…λ m ) is a correlation function, which can be used to characterize the relationship between the degradation information of the electrochemical device to be predicted and the first operating parameter.

[0082] In this way, the degradation model can clearly and directly indicate the impact of operating data on degradation information, facilitating the optimal control of the electrochemical device.

[0083] In a possible implementation, taking the first operating parameter including voltage U and temperature T as an example, the correlation function may be as shown in formula (2):

[0084] g(U,T;λ1,λ2,λ3)=λ1+λ2U+λ3T (2)

[0085] Among them, g(U,T;λ1,λ2,λ3) is the linear correlation function, and λ1, λ2 and λ3 are model parameters.

[0086] In a possible implementation, taking the first operating parameter including voltage U and temperature T as an example, the correlation function may be as shown in formula (3):

[0087]

[0088] Among them, g(U,T;λ1,λ2) is an exponential correlation function, and λ1 and λ2 are model parameters.

[0089] It should be understood that the degradation model trained according to the embodiment of the present disclosure includes a correlation function, which can clearly reflect the relationship between input and output, and the correlation function can be used to optimize and control the actual operating parameters of the electrochemical device model. The present disclosure does not limit the form of the correlation function or the number of model parameters.

[0090] In one possible implementation, the electrochemical device model is constructed based on the second operating parameter and the degradation index, and the electrochemical device model is fitted according to historical operating data of the electrochemical device to be predicted under variable operating conditions, and the historical operating data includes a fourth value of the second operating parameter.

[0091] The historical operation data may be actual operation data of the electrochemical device to be predicted under variable operating conditions. The historical operation data may include multiple forms, for example, a curve constructed according to the fourth value of the second operating parameter. For example, when the second operating parameter includes current and voltage, the historical operation data may be a volt-ampere curve determined according to the current value and the voltage value. The present disclosure does not limit the form of the electrochemical device model.

[0092] For example, the electrochemical device model constructed based on the second operating parameter and the degradation index may be as shown in formula (4):

[0093] U=f(I,T;R0(t),Λ) (4)

[0094] The second operating parameter includes voltage U, temperature T and current I, R0(t) represents the degradation index at time t, and Λ represents the parameters of the electrochemical device model.

[0095] The parameters of the electrochemical device model are not related to the degradation index. The present disclosure does not limit the number of parameters of the electrochemical device model.

[0096] For example, historical operating data of the electrochemical device to be predicted under variable operating conditions, such as voltammetric curves at different temperatures, can be obtained, and an electrochemical device model can be fitted based on the historical operating data to determine the value of the parameter Λ of the electrochemical device model, thereby obtaining a trained electrochemical device model.

[0097] For example, historical operation data can be obtained through variable operating condition degradation experiments. The historical operation data may include a first data set and a second data set. Both the first data set and the second data set include volt-ampere curves. For example, the first data set is a volt-ampere curve at different temperatures (taking into account the influence of temperature), and the second data set is a volt-ampere curve determined according to a preset period (for example, obtaining data every two hours) during the degradation process (taking into account the influence of temperature and degradation). The present disclosure does not limit the form of the historical operation data or the method of obtaining the historical operation data.

[0098] The electrochemical device model trained by the embodiment of the present disclosure can be a linear equation, and the calculation process is simple and fast. Therefore, the third value of the degradation index that is independent of the first operating parameter can be determined online and in real time from the real-time operating data under variable operating conditions at a low computing cost.

[0099] In a possible implementation, the method further includes: determining parameters of an initial electrochemical device model through historical operation data.

[0100] For example, the voltammetric curves in the first data set and the second data set can be fitted by the electrochemical device model to determine the model parameter Λ. The present disclosure does not limit the fitting process, the form and number of the model parameters. For example, the model parameter Λ can be determined by a step-by-step identification method. In the fitting process, it is not necessary to determine the value of the degradation index.

[0101] It should be noted that at least one baseline value of the degradation index can be determined based on the reference operating data in the second data set and the electrochemical device model. The baseline value can be used to determine the accuracy of the third value of the degradation index determined based on the real-time operating data. The values ​​of the operating parameters in the reference operating data and the real-time operating data are the same or similar.

[0102] It should be understood that the voltammetric curve can comprehensively reflect the performance of the electrochemical device within an operating range. The value of the degradation indicator identified based on the reference operating data in the second data set is used as a baseline value to compare the accuracy of the degradation indicator identified from the real-time operating data that is the same or similar to the reference operating data.

[0103] In the disclosed embodiment, real-time operating data of the electrochemical device to be predicted under variable operating conditions may be obtained, wherein the real-time operating data includes a first value of a first operating parameter and a second value of a second operating parameter.

[0104] For example, the current value, voltage value, and temperature value of the electrochemical device to be predicted under the variable operating state can be obtained according to a preset period (for example, once per minute). The first value of the first operating parameter may include a voltage value and a temperature value, and the second value of the second operating parameter may include a current value, a voltage value, and a temperature value.

[0105] In a possible implementation, determining the third value of the degradation index of the electrochemical device to be predicted based on the second value and the pre-trained electrochemical device model may refer to inputting the current value, voltage value and temperature value into the pre-trained electrochemical device model mentioned above to determine the third value of the degradation index, or may refer to determining the third value of the degradation index corresponding to the real-time operating data by a sliding average method.

[0106] The third value of the degradation index may not be determined by direct measurement, but may be indirectly calculated through the electrochemical device model and the second value.

[0107] In a possible implementation, the third value of the degradation indicator determined based on the second value and the pre-trained electrochemical device model is obtained after denoising.

[0108] For example, the third value of the degradation index corresponding to the second value can be obtained by denoising through sliding average and various filters. The sliding average denoising can include weighted sliding average denoising, and the present disclosure does not limit the denoising method.

[0109] In a possible implementation manner, the real-time operation data includes operation data at a reference time, and the method further includes:

[0110] Determining a second value for each operating moment within a target time window, wherein the target time window is determined based on the reference moment;

[0111] Wherein, determining the third value of the degradation index of the electrochemical device to be predicted according to the second value and the pre-trained electrochemical device model includes:

[0112] Determining corresponding third values ​​respectively according to the second values ​​at each operating moment and the electrochemical device model;

[0113] An average value of a plurality of third values ​​is determined as the third value corresponding to the operation data at the reference time.

[0114] The target time window may be a target time period including a reference time, for example, a target time period starting from a reference time, or a target time period with an intermediate time as a reference time. Exemplarily, the target time window may be greater than or equal to 300 minutes and less than or equal to 900 minutes. The present disclosure does not limit the determination method of the target time window or the length of the time window.

[0115] For example, the target time window may include multiple operating moments, and the corresponding third values ​​may be determined according to the second value at each operating moment and the electrochemical device model. For example, the second value at each operating moment is input into the pre-trained electrochemical device model to determine the corresponding third value of the degradation index, and the average value of the multiple third values ​​is determined as the third value corresponding to the operating data at the reference moment.

[0116] In this way, the determined numerical value of the degradation index can be denoised, further improving the prediction accuracy of the trained degradation model.

[0117] The training of the initial degradation model according to the first value and the third value may be training the initial degradation model according to the first value and the third value at each operating moment in the target time interval. The initial degradation model may be a degradation model that is constructed according to the first operating parameter and the degradation index and has not yet been trained.

[0118] In the disclosed embodiment, the training process may be online, in a real-time continuous target time interval, to continuously identify the model parameters in the initial degradation model. The target time interval may be a relatively long time interval, and within the target time interval, the third value is continuously determined based on each acquired real-time operation data, and the model parameters in the initial degradation model are continuously identified based on the first value and the third value at each operation moment, wherein before the degradation model is obtained through training, the model parameters in the initial degradation model may be changing at each operation moment.

[0119] In a possible implementation, the real-time operation data includes operation data at a target time, and the method further includes:

[0120] Determine a first value and a third value for each running moment within a target time interval, wherein the target time interval is determined according to the target moment;

[0121] The step of training the initial degradation model according to the first value and the third value includes:

[0122] The model parameters of the degradation model are determined according to the first value and the third value at each operating moment in the target time interval by using the maximum likelihood method.

[0123] Among them, the target time interval can be any time interval including the target moment, for example, it can be a time interval starting from the target moment, or a time interval ending at the target moment. The target moment can also be a running moment in the middle of the target time interval, and the present disclosure does not impose any restrictions on this.

[0124] The length of the target time interval may be greater than or equal to a duration threshold, and the duration threshold may be flexibly set. The target time interval may be a longer time interval, and the present disclosure does not impose any limitation on this.

[0125] For example, the model parameters in the degradation model can be identified online by using the maximum likelihood method. For example, a likelihood function can be determined according to the degradation model, wherein the likelihood function includes the model parameters in the degradation model, and the model parameters that minimize the likelihood function are solved to obtain the model parameters of the degradation model.

[0126] In a possible implementation, the discrete mode of the degradation model can be shown as formula (5):

[0127]

[0128] Among them, ξ conforms to the standard normal distribution, as shown in formula (5), ΔR0 is obtained by multiplication and addition operations based on ξ, so ΔR0 also obeys the normal distribution,

[0129] Among them, the probability density function of ΔR0 can be shown as formula (6):

[0130]

[0131] In a possible implementation, the probability P of observing N-1 increments of the third value of the degradation indicator may be as follows:

[0132]

[0133] Where k is a variable, and the value of k is between 1 and N-1. p(ΔR 0,k ;λ1,…λ m , σ 2 ) is the probability of observing the kth increment.

[0134] In one possible implementation, the likelihood function L is the negative logarithm of the probability P, which can be shown as follows:

[0135]

[0136] Among them, the model parameters that minimize the likelihood function can be solved by Newton's method to obtain the model parameters of the degradation model.

[0137] In this way, the maximum likelihood method can be used to identify the degradation model online at a low computational cost. Moreover, degradation is a long-time process. Based on long-time scale (hundreds to thousands of hours) data, the results can be identified more stably, and are not easily affected by random fluctuations in short time scales. The overall degradation trend in the training data can be identified, and the overall degradation trend of the electrochemical device can be fitted, so that when the degradation model is trained to predict degradation information, the predicted degradation information has small fluctuations and strong stability.

[0138] Figure 2 A flow chart of a method for predicting electrochemical device degradation according to an embodiment of the present disclosure is shown. Figure 2 As shown, the method includes:

[0139] In step S21, target operation data of the electrochemical device to be predicted within a target operation period is determined, wherein the target operation data includes a first target value of a first operation parameter;

[0140] In step S22, a third target value of the electrochemical device to be predicted at at least one operating moment within the target operating period is determined according to the degradation model and the first target value;

[0141] In step S23, the predicted degradation information of the electrochemical device to be predicted is determined according to the third target value of the at least one operating moment.

[0142] Wherein, the degradation model is obtained according to the above-mentioned method for determining the degradation model of the electrochemical device.

[0143] The electrochemical device degradation prediction method of the disclosed embodiment can determine a third target value of the electrochemical device to be predicted at at least one operating moment within the target operating period based on the target operating data within the target operating period and the degradation model obtained through the training as described above, wherein the third target value is the value of the predicted degradation index, and the predicted degradation information of the electrochemical device to be predicted can be determined. For example, when determining multiple third target values, the degradation trend of the electrochemical device to be predicted can be determined, and based on the degradation trend, the remaining life, health status and other information of the electrochemical device to be predicted in operation can be predicted.

[0144] In a possible implementation, the third target value of the degradation indicator during the target operation period may be iteratively predicted by the Monte Carlo method to determine the third target value of the degradation indicator of the electrochemical device to be predicted at at least one operating moment during the target operation period.

[0145] For example, the target operation data at the tth time during the target operation period includes the voltage value and the temperature value of the first operation parameter, and the value of dR0(t) can be determined according to the degradation model of formula (1). The third target value R0(t) of the degradation index at the tth time is determined according to the value of dR0(t) and the third target value of the degradation index at the t-1th time.

[0146] In a possible implementation, the third target value at the k+1th moment may be determined by the following formula:

[0147]

[0148] in, Used to represent the third target value at the k+1th moment, Used to represent the third target value at the kth moment, ξ k Used to represent the sample value drawn from the standard normal distribution at each prediction step, Δt k It is used to represent the time interval between the k+1th moment and the kth moment, which is the prediction step length.

[0149] In the disclosed embodiment, the degradation model may be used to describe the dynamic degradation trajectory of the degradation indicator. For example, the degradation trajectory of the degradation indicator may be predicted under a given target operation plan (eg, target operation data within a target operation period).

[0150] In a possible implementation, the second operating parameter includes a target parameter and a parameter to be predicted, the target operating data also includes a second target value of the target parameter, and the method further includes:

[0151] Determining a predicted value of the parameter to be predicted according to the third target value, the second target value, and a pre-trained electrochemical device model;

[0152] determining predicted degradation information of the electrochemical device to be predicted according to the predicted value,

[0153] The electrochemical device model is constructed based on the second operating parameter and the degradation index.

[0154] For example, the third target value R0(t) of the degradation indicator at the tth moment and the second target value of the target parameter in the target operation data at the tth moment (for example, the voltage value U and the temperature value T) can be substituted into the pre-trained electrochemical device model to determine the predicted value of the parameter to be predicted (for example, the current I).

[0155] It should be understood that the above is an exemplary description of the target operating data including voltage value and temperature value. When the target operating data includes current value and temperature value, the target parameter includes current and temperature, and the parameter to be predicted includes voltage. The predicted degradation information of different operating parameters can reflect the performance of the electrochemical device to be predicted, and the present disclosure does not limit this.

[0156] The predicted value of the predicted parameter of the electrochemical device to be predicted is calculated by the electrochemical device model, the third target value of the degradation index, and the value of the target parameter in the target operation data. The predicted value can characterize the performance of the parameter to be predicted. For example, it can be the current performance of the electrochemical device to be predicted, and the power performance can also be determined based on the determined current value and the current value in the target operation data, and the present disclosure does not limit this.

[0157] The above method can be used to determine the predicted value of the parameter to be predicted at each operating moment in the target operating period, and the degradation trend of the parameter to be predicted can be determined based on the predicted value of the parameter to be predicted at each operating moment.

[0158] It should be noted that different predicted degradation information is required in different application scenarios. For example, if you want to determine whether the output performance of the electrochemical device to be predicted meets the requirements under the target operating data, you can determine the predicted value of the parameter to be predicted, and judge whether the output performance of the electrochemical device to be predicted meets the requirements based on the predicted value. If you want to judge the health of the electrochemical device to be predicted, you can determine the third target value of the degradation index, and judge the health of the electrochemical device to be predicted based on the third target value of the degradation index. The degradation index is independent of the first operating parameter and can intrinsically reflect the health of the electrochemical device to be predicted. The predicted value of the parameter to be predicted can reflect the performance of the electrochemical device to be predicted under the target operating data.

[0159] In a possible implementation, the method further includes:

[0160] Acquiring actual degradation information of the electrochemical device to be predicted;

[0161] Performing abnormality judgment according to the predicted degradation information and the actual degradation information;

[0162] When it is determined that the electrochemical device to be predicted is abnormal, an alarm operation is performed.

[0163] For example, the actual degradation information of the electrochemical device to be predicted can be obtained, and an abnormality judgment can be performed based on the predicted degradation information and the actual degradation information. For example, it can be judged whether the electrochemical device to be predicted has a rapid degradation phenomenon. If it is determined that a rapid degradation phenomenon has occurred, the electrochemical device is considered abnormal and an alarm operation is performed.

[0164] In a possible implementation, an abnormality judgment is performed based on the predicted degradation information and the actual degradation information, which may be to compare whether the change trends of the predicted degradation information and the actual degradation information are similar or whether the data gap between the predicted degradation information and the actual degradation information is greater than or equal to an abnormal threshold. For example, when the change trends of the predicted degradation information and the actual degradation information are obviously different or the data gap is greater than or equal to the abnormal threshold, an abnormality may be determined.

[0165] In this way, the health of the electrochemical device to be predicted can be monitored in real time, improving the intelligence and accuracy of the performance monitoring of the electrochemical device.

[0166] It should be noted that, although the examples described above describe the electrochemical device degradation model determination method and the electrochemical device degradation prediction method, those skilled in the art will appreciate that the present disclosure should not be limited thereto.

[0167] Figure 3 A flow chart of a method for determining an electrochemical device degradation model and a method for predicting electrochemical device degradation according to an embodiment of the present disclosure is shown.

[0168] like Figure 3 As shown, the electrochemical device to be predicted is a battery as an example, for example, the battery is a fuel cell for exemplary description. The parameters of the initial battery model can be identified based on historical operating data to obtain a pre-trained battery model (S31). For example, based on the historical operating data of SOFC under variable operating conditions, the parameters of the initial battery model are identified to obtain a pre-trained battery model. For example, the battery model is constructed based on current, voltage, temperature and degradation indicators. This step can be an offline operation.

[0169] Real-time operation data may be obtained, and a third value of a degradation indicator corresponding to each real-time operation data may be determined according to the real-time operation data and the pre-trained battery model (S32). For example, real-time operation data of the SOFC may be obtained online and in real time, and may include, for example, the current, voltage, and temperature of the SOFC. The third value of the degradation indicator corresponding to each real-time operation data may be determined according to the real-time operation data and the pre-trained battery model.

[0170] The model parameters in the initial degradation model can be determined according to the third value corresponding to each real-time operation data and the first operation parameter in the real-time operation data (S33). For example, the model parameters in the initial degradation model are determined online and in real time according to the third value of the degradation index corresponding to each real-time operation data and the first operation parameter in the real-time operation data, such as voltage and temperature. For example, the model parameters in the degradation model are identified based on the maximum likelihood method. The degradation model is constructed based on the first operation parameter and the degradation index. S32 and S33 can be online operations.

[0171] The degradation information can be predicted based on the trained degradation model (S34). For example, the third target value of the degradation index during the target operation period can be iteratively predicted by the Monte Carlo method to determine the third target value of the degradation index of the SOFC at at least one operation time during the target operation period. The third target value R0(t) of the degradation index at the tth moment and the second target value of the target parameter in the target operation data at the tth moment (for example, the voltage value U and the temperature value T) can also be substituted into the pre-trained battery model to determine the predicted value of the parameter to be predicted (for example, the current I).

[0172] Figure 4 FIG. 1 is a block diagram showing a device for determining an electrochemical device degradation model according to an embodiment of the present disclosure. Figure 4 As shown, the device comprises:

[0173] An acquisition module 41 is used to acquire real-time operating data of the electrochemical device to be predicted under a variable operating condition, wherein the real-time operating data includes a first value of a first operating parameter and a second value of a second operating parameter;

[0174] A first determination module 42, configured to determine a third value of the degradation indicator of the electrochemical device to be predicted according to the second value and a pre-trained electrochemical device model;

[0175] The second determination module 43 is used to train the initial degradation model according to the first value and the third value to obtain a trained degradation model, wherein the degradation model is used to predict the degradation information of the electrochemical device to be predicted.

[0176] The degradation model is constructed based on the first operating parameter and the degradation index, and the degradation index is unrelated to the first operating parameter.

[0177] Figure 5 FIG. 1 is a block diagram of an electrochemical device degradation prediction device according to an embodiment of the present disclosure. Figure 5 As shown, the device comprises:

[0178] A third determination module 51 is used to determine target operation data of the electrochemical device to be predicted within a target operation period, wherein the target operation data includes a first target value of a first operation parameter;

[0179] a fourth determination module 52, configured to determine a third target value of the electrochemical device to be predicted at at least one operating moment within the target operating period according to the degradation model and the first target value;

[0180] A fifth determining module 53 is used to determine the predicted degradation information of the electrochemical device to be predicted according to the third target value of the at least one operating moment,

[0181] Wherein, the degradation model is obtained based on the above-mentioned method for determining the degradation model of the electrochemical device.

[0182] Figure 6 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. For example, the device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0183] Reference Figure 6 , the device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0184] The processing component 802 generally controls the overall operation of the device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0185] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0186] The power supply component 806 provides power to the various components of the device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 800.

[0187] The multimedia component 808 includes a screen that provides an output interface between the device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0188] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the device 800 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0189] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0190] The sensor assembly 814 includes one or more sensors for providing various aspects of the status assessment of the device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the device 800, and the sensor assembly 814 can also detect the position change of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, the orientation or acceleration / deceleration of the device 800, and the temperature change of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0191] The communication component 816 is configured to facilitate wired or wireless communication between the device 800 and other devices. The device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0192] In an exemplary embodiment, the apparatus 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0193] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 804 including computer program instructions, which can be executed by the processor 820 of the device 800 to perform the above method.

[0194] Figure 7 1900 is a block diagram of an electronic device according to an embodiment of the present disclosure. For example, the device 1900 may be provided as a server. Figure 7, the apparatus 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions, such as an application, that can be executed by the processing component 1922. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0195] The device 1900 may also include a power supply component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input / output (I / O) interface 1958. The device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, MacOS X™, Unix™, Linux™, FreeBSD™, or the like.

[0196] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the device 1900 to perform the above method.

[0197] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0198] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0199] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0200] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0201] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0202] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0203] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0204] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0205] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for determining an electrochemical device degradation model, characterized in that: The method comprises: Acquiring real-time operating data of the electrochemical device to be predicted under a variable operating condition, the real-time operating data comprising a first value of a first operating parameter and a second value of a second operating parameter, the electrochemical device comprising a battery and / or an electrolytic cell, wherein the first operating parameter is an operating parameter used to construct a degradation model, the first value is a value of the first operating parameter when the electrochemical device to be predicted is in real-time operation, the second operating parameter is an operating parameter used to construct an electrochemical device model, and the second value is a value of the second operating parameter when the electrochemical device to be predicted is in real-time operation; Determining a third value of the degradation index of the electrochemical device to be predicted according to the second value and the pre-trained electrochemical device model, wherein the degradation index is an index for measuring degradation information of the electrochemical device to be predicted, and the third value is a value of the degradation index determined according to the second value and the pre-trained electrochemical device model; According to the first value and the third value, an initial degradation model is trained to obtain a trained degradation model, wherein the degradation model is used to predict degradation information of the electrochemical device to be predicted. wherein the degradation model is constructed based on the first operating parameter and the degradation index, and the degradation index is unrelated to the first operating parameter; The degradation model is used to predict the degradation trajectory of the degradation indicator under a given target operation plan.

2. The method according to claim 1, characterized in that The degradation model includes a correlation function, and the correlation function is used to characterize the relationship between the degradation information of the electrochemical device to be predicted and the first operating parameter.

3. The method according to claim 1, characterized in that The real-time operation data includes operation data at a target time, and the method further includes: Determine a first value and a third value for each running moment within a target time interval, wherein the target time interval is determined according to the target moment; The step of training the initial degradation model according to the first value and the third value includes: The model parameters of the degradation model are determined according to the first value and the third value at each operating moment in the target time interval by using the maximum likelihood method.

4. The method according to claim 1, characterized in that: The electrochemical device model is constructed based on the second operating parameter and the degradation index. The electrochemical device model is fitted according to the historical operating data of the electrochemical device to be predicted under variable operating conditions. The historical operating data includes a fourth value of the second operating parameter, wherein the fourth value is the value of the second operating parameter during the historical operation of the electrochemical device to be predicted.

5. The method according to claim 1, characterized in that The third value of the degradation indicator determined according to the second value and the pre-trained electrochemical device model is obtained after denoising.

6. The method according to claim 1, characterized in that The second operating parameters include target parameters and parameters to be predicted. The electrochemical device to be predicted is configured with target operating data. The target operating data is used to determine the predicted degradation information of the electrochemical device to be predicted under the target operating data. The target operating data includes the value of the first operating parameter and the value of the target parameter. The value of the parameter to be predicted is used to characterize the predicted degradation information of the electrochemical device to be predicted. The target parameter is other parameters in the second operating parameters except the parameter to be predicted.

7. The method according to any one of claims 1 to 6, characterized in that: The battery includes one of a solid oxide fuel cell, a proton exchange membrane fuel cell and an alkaline fuel cell, the electrolysis cell includes one of a solid oxide electrolysis cell, a proton exchange membrane electrolysis cell and an alkaline electrolysis cell, and the first operating parameter includes at least one of the following: power, gas pressure, gas composition, material utilization, current density, current, voltage, temperature and gas flow rate.

8. A method for predicting degradation of an electrochemical device, characterized in that: The method comprises: Determining target operating data of the electrochemical device to be predicted within a target operating period, the target operating data comprising a first target value of a first operating parameter, the electrochemical device comprising a battery and / or an electrolytic cell, wherein the first operating parameter is an operating parameter used to construct a degradation model, and the first target value is a value of the first operating parameter when the electrochemical device to be predicted operates within the target operating period; Determining, according to the degradation model and the first target value, a third target value of a degradation index of the electrochemical device to be predicted at at least one operating moment during the target operating period, wherein the degradation index is an index for measuring degradation information of the electrochemical device to be predicted, and the third target value is a value of the degradation index determined according to the first target value and the degradation model; determining predicted degradation information of the electrochemical device to be predicted according to the third target value of the at least one operating moment, Wherein, the degradation model is obtained based on the method for determining the degradation model of the electrochemical device according to any one of claims 1-7.

9. The method according to claim 8, characterized in that The second operating parameter includes a target parameter and a parameter to be predicted, the target operating data also includes a second target value of the target parameter, the second target value is a value of the target parameter included in the target operating data, and the method further includes: Determining a predicted value of the parameter to be predicted according to the third target value, the second target value, and a pre-trained electrochemical device model; determining predicted degradation information of the electrochemical device to be predicted according to the predicted value, The electrochemical device model is constructed based on the second operating parameter and the degradation index.

10. The method according to claim 8 or 9, characterized in that: The method further comprises: Acquiring actual degradation information of the electrochemical device to be predicted; Performing abnormality judgment according to the predicted degradation information and the actual degradation information; When it is determined that the electrochemical device to be predicted is abnormal, an alarm operation is performed.

Images