Perovskite photovoltaic module health monitoring method based on adaptive algorithm

Abstract

The invention discloses a perovskite photovoltaic module health monitoring method based on an adaptive algorithm. The method comprises the following steps: S1, initialization and data acquisition; s2, establishing a degradation prediction model according to the physical and chemical characteristics of the perovskite material, and constructing a self-adaptive degradation prediction model formula; s3, dynamically setting different thresholds based on different life cycle stages of the component; s4, analyzing the difference between the operation data of the current photovoltaic module and the historical data in real time based on an adaptive algorithm; s5, fault classification and positioning; and S6, based on the historical operation data and the real-time monitoring data of the component, calculating the health score of the current component through adaptive regression analysis. Compared with a traditional monitoring method, the method has the advantages that the accuracy of fault early warning is remarkably improved, the threshold value is dynamically set according to the life cycle of the component and the environment change, the external condition change can be dealt with in time, and false alarm and missing alarm are reduced.

Description

Technical Field

[0001] The present invention relates to the field of new energy technology, and in particular to a health monitoring method for perovskite photovoltaic components based on an adaptive algorithm. Background Art

[0002] In recent years, with the rapid development of renewable energy technology, perovskite photovoltaic modules have gradually become a research hotspot in the photovoltaic field due to their excellent optoelectronic properties and low-cost manufacturing potential. The light absorption capacity and electron mobility of perovskite materials are superior to those of traditional silicon materials, making perovskite photovoltaic modules show good application prospects in photovoltaic power generation. However, the long-term stability and reliability of perovskite modules are still the main challenges restricting their commercial application. Especially in actual operation, the performance of modules may be affected by many factors, including environmental conditions, material degradation, etc. Therefore, developing a health monitoring method for perovskite photovoltaic modules that can timely identify performance degradation and failure of modules is the key to improving the reliability of perovskite photovoltaic modules.

[0003] Although a variety of health monitoring technologies have been proposed, most methods have certain limitations. Traditional monitoring methods often rely on static threshold settings, which makes it difficult to achieve accurate performance evaluation and fault warning at different stages of the component life cycle and under changing environmental conditions. In addition, existing technologies mostly use linear models in the data analysis process, which fails to fully consider the complex physical and chemical properties of perovskite materials, resulting in insufficient accuracy in degradation prediction. Therefore, it is necessary to design a perovskite photovoltaic component health monitoring method based on an adaptive algorithm to solve the above problems. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the problems existing in the above-mentioned existing perovskite photovoltaic module health monitoring method based on adaptive algorithm, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide a perovskite photovoltaic module health monitoring method based on an adaptive algorithm, which is suitable for solving the problem that traditional monitoring methods often rely on static threshold settings and are difficult to achieve accurate performance evaluation and fault warning.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for health monitoring of perovskite photovoltaic modules based on an adaptive algorithm, comprising the following steps:

[0008] S1: initialization and data collection;

[0009] S2: Establish a degradation prediction model based on the physical and chemical properties of perovskite materials, and construct an adaptive degradation prediction model formula;

[0010] S3: Dynamically set different thresholds based on different life cycle stages of components;

[0011] S4: Based on the adaptive algorithm, the difference between the current PV module operation data and historical data is analyzed in real time;

[0012] S5: Fault classification and location;

[0013] S6: Based on the historical operation data and real-time monitoring data of the component, the health score of the current component is calculated through adaptive regression analysis.

[0014] As a preferred solution of the perovskite photovoltaic module health monitoring method based on the adaptive algorithm described in the present invention, the adaptive degradation prediction model formula is as follows:

[0015]

[0016] Where D(t) represents the adaptive degradation prediction value of the PV module at time t, reflecting the health status and performance changes of the PV module over time, f env (E(t), T(t), H(t)) is the environmental influence function, E(t) is the light intensity, T(t) is the temperature, H(t) is the humidity, is the temperature attenuation function, where λ 1 is the attenuation coefficient, T 0 is the nominal temperature of the photovoltaic module, T norm is the temperature normalization factor, g comp (V oc (t),I sc (t)) is the photovoltaic module electrical performance feedback function, based on the open circuit voltage V oc and short-circuit current I sc , used to measure the change in the electrical performance of photovoltaic modules, α 1 and α 2 are the weights of environmental factors and electrical performance factors, respectively, used to balance their effects in degradation prediction.

[0017] As a preferred solution of the method for health monitoring of perovskite photovoltaic modules based on the adaptive algorithm described in the present invention, the threshold D is set in the output result of the adaptive degradation prediction model formula. th ;

[0018] If D(t)≥D th , it means that the PV panels are operating normally;

[0019] If D(t)<D th , it means that the PV panel has performance degradation or failure.

[0020] As a preferred solution of the perovskite photovoltaic module health monitoring method based on the adaptive algorithm described in the present invention, a dynamic threshold adjustment formula is constructed according to the output result of the adaptive degradation prediction model formula, and the dynamic threshold adjustment formula is as follows:

[0021] τ(t)=D(t)·(1+κ·sin(ω·t))

[0022] Among them, τ(t) represents the dynamically adjusted threshold value, which is based on the degradation prediction value D(t) of the PV module and the time-related dynamic adjustment term, κ is the dynamic adjustment coefficient, which controls the amplitude of the threshold fluctuation, sin(ω·t) is the periodic fluctuation term, and ω is the frequency of the fluctuation, which reflects the periodic environmental fluctuation or the periodic change of the state of the PV module.

[0023] As a preferred solution of the perovskite photovoltaic module health monitoring method based on the adaptive algorithm described in the present invention, the threshold value is set as τ in the output result of the dynamic threshold adjustment formula. th ;

[0024] If τ th ≥τ(t), it means that the threshold is within the normal fluctuation range;

[0025] If τ th <τ(t), an abnormality occurs and further analysis and monitoring of the PV module status are required.

[0026] As a preferred solution of the perovskite photovoltaic module health monitoring method based on the adaptive algorithm described in the present invention, a comprehensive judgment and feedback mechanism formula is constructed according to the output result of the dynamic threshold adjustment formula, and the comprehensive judgment and feedback mechanism formula is as follows:

[0027]

[0028] Among them, p(t) is the final performance evaluation function, which is used to comprehensively judge the health status and operating performance of photovoltaic modules. It is the superposition of multiple attenuation mechanisms, β i is the weight of each attenuation mechanism, γ i is the time-dependent attenuation coefficient, s i are constants or characteristic data associated with each attenuation mechanism.

[0029] As a preferred solution of the method for health monitoring of perovskite photovoltaic modules based on the adaptive algorithm described in the present invention, the threshold value p is set in the output result of the comprehensive judgment and feedback mechanism formula.th ;

[0030] If p(t)≥p th , indicating that the component is in a healthy state;

[0031] If p(t)<p th , it means that the performance of the PV panel has declined or failed, and it should be repaired or replaced immediately.

[0032] As a preferred solution of the method for health monitoring of perovskite photovoltaic modules based on the adaptive algorithm described in the present invention, wherein: env (E(t), T(t), H(t)) reflects the comprehensive impact of the environment on the performance of photovoltaic modules. Reflects the attenuation effect of temperature fluctuations on perovskite materials.

[0033] Beneficial effects of the present invention: The adaptive degradation prediction model constructed based on the characteristics of perovskite materials can more accurately reflect the performance changes of components. Compared with traditional monitoring methods, it significantly improves the accuracy of fault warning. The threshold is dynamically set according to the life cycle of the component and environmental changes, which can respond to changes in external conditions in a timely manner, reduce false alarms and missed alarms, and improve the reliability and effectiveness of the monitoring method.

[0034] Combining historical operation data and real-time monitoring information, the health score is calculated through adaptive regression analysis, so that maintenance work can be based on data-driven decisions, reasonably arrange maintenance time and resources, and reduce maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0036] Figure 1 This is a schematic diagram of the steps of the perovskite photovoltaic module health monitoring method based on the adaptive algorithm proposed in the present invention. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0039] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0040] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0041] Example

[0042] Reference Figure 1 , as an embodiment of the present invention, provides a perovskite photovoltaic module health monitoring method based on an adaptive algorithm, comprising the following steps:

[0043] S1: initialization and data collection;

[0044] S2: Establish a degradation prediction model based on the physical and chemical properties of perovskite materials, and construct an adaptive degradation prediction model formula;

[0045] In the monitoring of perovskite photovoltaic modules, an adaptive degradation prediction model based on the characteristics of perovskite materials is innovatively introduced. Compared with the traditional fixed model, this adaptive model can dynamically adjust the prediction parameters according to the characteristics of the module under different physical and chemical conditions, greatly improving the accuracy of the prediction of the module health status;

[0046] S3: Dynamically set different thresholds based on different life cycle stages of components;

[0047] Dynamically setting thresholds based on different stages of the component life cycle is more flexible and innovative than existing technologies. Traditional health monitoring methods mostly use fixed thresholds, while this dynamic threshold setting can adapt to the actual attenuation of components, ensuring that the monitoring results are closer to the actual operating status and avoiding misjudgments caused by improper threshold settings;

[0048] S4: Based on the adaptive algorithm, the difference between the current PV module operation data and historical data is analyzed in real time;

[0049] S5: Fault classification and location;

[0050] S6: Based on the historical operation data and real-time monitoring data of the component, the health score of the current component is calculated through adaptive regression analysis;

[0051] By combining historical data and real-time monitoring data, the health status of components is dynamically scored through a regression algorithm. Compared with the existing simple status monitoring, the present invention uses big data analysis and adaptive regression to enable the health score to reflect the actual working status and potential performance changes of the components.

[0052] The adaptive degradation prediction model formula is as follows:

[0053]

[0054] Where D(t) represents the adaptive degradation prediction value of the PV module at time t, reflecting the health status and performance changes of the PV module over time, f env (E(t), T(t), H(t)) is the environmental impact function, which reflects the comprehensive impact of the environment on the performance of photovoltaic modules. E(t) is the light intensity, T(t) is the temperature, and H(t) is the humidity. is the temperature attenuation function, reflecting the attenuation effect of temperature fluctuation on the perovskite material, where λ 1 is the attenuation coefficient, T 0 is the nominal temperature of the photovoltaic module, T norm is the temperature normalization factor, g comp (V oc (t),I sc (t)) is the photovoltaic module electrical performance feedback function, based on the open circuit voltage V oc and short-circuit current I sc , used to measure the change in the electrical performance of photovoltaic modules, α 1 and α 2 are the weights of environmental factors and electrical performance factors, respectively, used to balance their effects in degradation prediction.

[0055] Set the threshold D in the output of the adaptive degradation prediction model formula th ;

[0056] If D(t)≥D th , it means that the PV panels are operating normally;

[0057] If D(t)<D th , it means that the PV panel has performance degradation or failure.

[0058] A dynamic threshold adjustment formula is constructed according to the output result of the adaptive degradation prediction model formula, and the dynamic threshold adjustment formula is as follows:

[0059] τ(t)=D(t)·(1+κ·sin(ω·t))

[0060] Among them, τ(t) represents the dynamically adjusted threshold value, which is based on the degradation prediction value D(t) of the PV module and the time-related dynamic adjustment term, κ is the dynamic adjustment coefficient, which controls the amplitude of the threshold fluctuation, sin(ω·t) is the periodic fluctuation term, and ω is the frequency of the fluctuation, which reflects the periodic environmental fluctuation or the periodic change of the state of the PV module.

[0061] In the output of the dynamic threshold adjustment formula, the threshold is set to τ th ;

[0062] If τ th ≥τ(t), it means that the threshold is within the normal fluctuation range;

[0063] If τ th <τ(t), an abnormality occurs and further analysis and monitoring of the PV module status are required.

[0064] A comprehensive judgment and feedback mechanism formula is constructed according to the output result of the dynamic threshold adjustment formula, and the comprehensive judgment and feedback mechanism formula is as follows:

[0065]

[0066] Among them, p(t) is the final performance evaluation function, which is used to comprehensively judge the health status and operating performance of photovoltaic modules. It is the superposition of multiple attenuation mechanisms, β i is the weight of each attenuation mechanism, γ i is the time-dependent attenuation coefficient, s i are constants or characteristic data associated with each attenuation mechanism.

[0067] Set the threshold p in the output result of the comprehensive judgment and feedback mechanism formula th ;

[0068] If p(t)≥p th , indicating that the component is in a healthy state;

[0069] If p(t)<p th , it means that the performance of the PV panel has declined or failed, and it should be repaired or replaced immediately.

[0070] During use, the adaptive degradation prediction model built based on the characteristics of perovskite materials can more accurately reflect the performance changes of components. Compared with traditional monitoring methods, it significantly improves the accuracy of fault warning. The threshold is dynamically set according to the life cycle of the component and environmental changes, which can respond to changes in external conditions in a timely manner, reduce false alarms and missed alarms, and improve the reliability and effectiveness of the monitoring method. Combined with historical operating data and real-time monitoring information, the health score is calculated through adaptive regression analysis, so that maintenance work can be based on data-driven decision-making, reasonably arrange maintenance time and resources, and reduce maintenance costs.

[0071] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for health monitoring of perovskite photovoltaic modules based on an adaptive algorithm, characterized in that: The following steps are involved: S1: initialization and data collection; S2: Establish a degradation prediction model based on the physical and chemical properties of perovskite materials, and construct an adaptive degradation prediction model formula; S3: Dynamically set different thresholds based on different life cycle stages of components; S4: Based on the adaptive algorithm, the difference between the current PV module operation data and historical data is analyzed in real time; S5: Fault classification and location; S6: Based on the historical operation data and real-time monitoring data of the component, the health score of the current component is calculated through adaptive regression analysis.

2. The method for health monitoring of perovskite photovoltaic modules based on an adaptive algorithm according to claim 1, characterized in that: The adaptive degradation prediction model formula is as follows: Where D(t) represents the adaptive degradation prediction value of the PV module at time t, reflecting the health status and performance changes of the PV module over time, f env (E(t), T(t), H(t)) is the environmental influence function, E(t) is the light intensity, T(t) is the temperature, H(t) is the humidity, is the temperature attenuation function, where λ1 is the attenuation coefficient, T0 is the nominal temperature of the photovoltaic module, and T norm is the temperature normalization factor, g comp (V oc (t),I sc (t)) is the photovoltaic module electrical performance feedback function, based on the open circuit voltage V oc and short-circuit current I sc , which is used to measure the change of electrical performance of PV modules. α1 and α2 are the weights of environmental factors and electrical performance factors, respectively, which are used to balance their effects in degradation prediction.

3. The method for health monitoring of perovskite photovoltaic modules based on an adaptive algorithm according to claim 2, characterized in that: Set the threshold D in the output of the adaptive degradation prediction model formula th ; If D(t)≥D th , it means that the PV panels are operating normally; If D(t)<D th , it means that the PV panel has performance degradation or failure.

4. The method for health monitoring of perovskite photovoltaic modules based on an adaptive algorithm according to claim 2, characterized in that: A dynamic threshold adjustment formula is constructed according to the output result of the adaptive degradation prediction model formula, and the dynamic threshold adjustment formula is as follows: τ(t)=D(t)·(1+κ·sin(ω·t)) Among them, τ(t) represents the dynamically adjusted threshold value, which is based on the degradation prediction value D(t) of the PV module and the time-related dynamic adjustment term, κ is the dynamic adjustment coefficient, which controls the amplitude of the threshold fluctuation, sin(ω·t) is the periodic fluctuation term, and ω is the frequency of the fluctuation, which reflects the periodic environmental fluctuation or the periodic change of the state of the PV module.

5. The method for health monitoring of perovskite photovoltaic modules based on an adaptive algorithm according to claim 4, characterized in that: Set the threshold value to τ in the output result of the dynamic threshold adjustment formula th ; If τ th ≥τ(t), it means that the threshold is within the normal fluctuation range; If τ th <τ(t), an abnormality occurs and further analysis and monitoring of the PV module status are required.

6. The method for health monitoring of perovskite photovoltaic modules based on an adaptive algorithm according to claim 4, characterized in that: A comprehensive judgment and feedback mechanism formula is constructed according to the output result of the dynamic threshold adjustment formula, and the comprehensive judgment and feedback mechanism formula is as follows: Among them, p(t) is the final performance evaluation function, which is used to comprehensively judge the health status and operating performance of photovoltaic modules. It is the superposition of multiple attenuation mechanisms, β i is the weight of each attenuation mechanism, γ i is the time-dependent attenuation coefficient, s i are constants or characteristic data associated with each attenuation mechanism.

7. The method for health monitoring of perovskite photovoltaic modules based on an adaptive algorithm according to claim 6, characterized in that: Set the threshold p in the output result of the comprehensive judgment and feedback mechanism formula th ; If p(t)≥p th , indicating that the component is in a healthy state; If p(t)<p th , it means that the performance of the PV panel has declined or failed, and it should be repaired or replaced immediately.

8. The method for health monitoring of perovskite photovoltaic modules based on an adaptive algorithm according to claim 2, characterized in that: f env (E(t), T(t), H(t)) reflects the comprehensive impact of the environment on the performance of photovoltaic modules. Reflects the attenuation effect of temperature fluctuations on perovskite materials.

Images