Photovoltaic module state monitoring system and method based on multi-source data

Through multi-source data acquisition and Kalman filtering algorithm, the state monitoring index is established by combining environmental impact index and data error index, which solves the accuracy and efficiency of photovoltaic module status monitoring in traditional methods, and achieves more accurate Fault prediction and operation and maintenance decision-making.

CN118984135AActive Publication Date: 2024-11-19GUANGDONG JINGZHENG TECH CO LTD

Patent Information

Application Number
CN202411045162.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-19
Estimated Expiration
2044-08-01

AI Technical Summary

Technical Problem

Traditional photovoltaic module status monitoring methods are difficult to accurately distinguish the causes of performance degradation, are inefficient, and manual analysis is easily affected by subjective judgment, resulting in inaccurate fault prediction and poor consistency.

Method used

Using multi-source data acquisition module, data prediction module, data correction module and monitoring and analysis module, the state of photovoltaic modules is predicted through the Kalman filtering algorithm, and the environmental impact index and data error index are generated. Combined with volatility analysis, the status monitoring index is established for real-time monitoring. and early warning.

Benefits of technology

It realizes accurate distinction between the reasons for the performance degradation of photovoltaic modules, improves the accuracy and consistency of fault detection, reduces manual analysis workload, and improves the basis for operation and maintenance decision-making of photovoltaic systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118984135A_ABST
    Figure CN118984135A_ABST
Patent Text Reader

Abstract

The invention provides a photovoltaic module state monitoring system based on multi-source data and a method thereof, and relates to the technical field of photovoltaic system monitoring, the photovoltaic module state monitoring system is formed by introducing self data, environmental data and a Kalman filtering algorithm, the self data and the environmental data of a photovoltaic module are collected, and the photovoltaic module state is monitored. The future state of the assembly is predicted through the data prediction module by adopting a Kalman filtering algorithm to obtain assembly prediction data, the reasons of performance reduction of the photovoltaic assembly can be effectively distinguished through an environmental influence index introduced by the data correction module, and the prediction data is used as a reference standard to generate a self data error index; and the self data fluctuation rate is generated by using the corrected self data at the three moments and the component prediction data, a state monitoring index can be generated in combination with a data analysis model of the monitoring analysis module, the state monitoring index is compared with a preset threshold value, an early warning signal is sent out, and the accuracy of fault detection of the photovoltaic system is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic system monitoring, and in particular to a photovoltaic component state monitoring system and method based on multi-source data. Background Art

[0002] With the rapid development of renewable energy, the efficiency and stability of photovoltaic power generation systems, as an important part of it, have received widespread attention. As the core of the photovoltaic power generation system, the status of photovoltaic modules has a decisive impact on the power generation efficiency and operational safety of the entire system. However, during the long-term operation of photovoltaic modules, the performance will gradually decline due to the influence of environmental factors such as temperature and light intensity, as well as internal factors such as material aging and mechanical damage. Therefore, how to monitor and evaluate the status of photovoltaic modules in real time and timely discover and prevent potential failures has become a key technical issue to ensure the stable operation of photovoltaic systems.

[0003] Traditional PV module status monitoring methods often rely on simple data collection and manual analysis, which have great limitations in data processing and fault prediction. First, the environment of PV modules is changing. Even if the changes are small, they will cause certain impacts, such as changes in ambient temperature and fluctuations in light intensity, which often make it impossible to accurately distinguish whether the performance degradation is caused by environmental changes or module failures. Secondly, traditional methods are inefficient in processing the massive data generated by large-scale PV systems, making it difficult to achieve real-time monitoring and fault warning. In addition, manual analysis methods rely on experienced professionals and are easily affected by subjective judgments, making it difficult to ensure the consistency and accuracy of the analysis results.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The object of the present invention is to provide a photovoltaic module status monitoring system and method based on multi-source data to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A photovoltaic module status monitoring system based on multi-source data, comprising:

[0008] A data acquisition module is used to collect the self data and environmental data of the photovoltaic module at time k and time k-1, wherein the self data includes the current data, voltage data and surface temperature data of the photovoltaic module output, and the environmental data includes the surface sunlight intensity data of the photovoltaic module, the temperature data of the environment and the time of commissioning;

[0009] A data prediction module is used to predict the photovoltaic component's own data at time k+1 based on the photovoltaic component's own data and environmental data at time k and time k-1, and obtain component prediction data using a Kalman filter algorithm, wherein the component prediction data includes the photovoltaic component output current data, voltage data, and photovoltaic component surface temperature data at time k+1;

[0010] A data correction module is used to collect the self-data and environmental data of the photovoltaic component at time k+1, generate a first environmental impact index set according to the self-data and environmental data of the photovoltaic component at time k and time k-1, and use the first environmental impact index set to correct the self-data of the photovoltaic component at time k+1;

[0011] The fluctuation judgment module is used to generate a self-data error index based on the corrected self-data of the photovoltaic component at time k+1 and the component prediction data, use the first environmental impact data set to correct the self-data at time k, and generate the self-data volatility based on the self-data at the past time k-1, the corrected self-data at time k and the self-data at time k+1;

[0012] The monitoring and analysis module is used to analyze its own data volatility and its own data error index, establish a data analysis model, generate a status monitoring index, compare the status monitoring index with the threshold, and choose to issue or not issue a warning signal based on the comparison results.

[0013] Furthermore, the k+1 moment is the current moment, and the time length between the k moment and the k-1 moment is the same as the time length between the k moment and the k+1 moment.

[0014] Furthermore, the Kalman filter algorithm is used to predict the photovoltaic module's own data at time k+1, and the method for obtaining the module prediction data is based on:

[0015] Construct the state vector of the photovoltaic component at time k-1 based on its own data at time k-1, and construct the state equation of the state vector transfer from time k-1 to time k in combination with the state transfer matrix, generate the self-prediction data at time k based on the self-data and environmental data of the photovoltaic component at time k-1, and update the error covariance matrix of the self-prediction data at time k;

[0016] According to the environmental data of the photovoltaic component at time k, the observation vector of the photovoltaic component at time k is constructed, and the observation matrix is ​​constructed, and the Kalman gain is calculated by combining the updated error covariance matrix and the observation matrix;

[0017] Use the Kalman gain and the observation vector at time k to update the self-prediction data at time k, and obtain the updated self-prediction data at time k;

[0018] Using the updated self-prediction data at time k, combined with the state transfer matrix, the state equation for the transfer from time k to time k+1 is constructed to obtain the predicted self-data at time k+1, that is, the component prediction data.

[0019] Furthermore, the state vector of the photovoltaic module at time k-1 is:

[0020]

[0021] Among them, x k―1 represents the state vector of the photovoltaic module at time k-1, I k―1 、V k―1 and T k―1 Respectively represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k-1;

[0022] The state transfer matrix is:

[0023]

[0024] Where, F represents the state transfer matrix;

[0025] The formula for generating the self-prediction data at time k based on the self-data of the photovoltaic module at time k-1 and the environmental data is:

[0026] x k|k―1 =x k―1 *F

[0027] Among them, x k|k―1 Represents the self-predicted data of the photovoltaic module at time k based on its own data at time k-1 and the environmental data;

[0028] The formula for updating the error covariance matrix of the self-prediction data at time k is:

[0029] P k|k―1 =F*P k―1|k―1 *F T

[0030] Among them, P k|k―1 represents the error covariance matrix of the updated self-prediction data at time k, F T represents the transpose of the state transfer matrix, P k―1|k―1 represents the error covariance matrix of the self-prediction data at time k-1, and:

[0031]

[0032] Among them, σ I , σ U and σT They respectively represent the tolerances of the current data, voltage data and surface temperature data of the photovoltaic modules output.

[0033] Furthermore, the method for calculating the Kalman gain is:

[0034] K k =P k|k―1 *H T *(H*P k|k―1 *H T ) ―1

[0035] Among them, K k represents the Kalman gain, H represents the observation matrix, and H T represents the transpose of the observation matrix, and:

[0036]

[0037] The observation vector of the photovoltaic module at time k is:

[0038]

[0039] Among them, z k represents the observation vector of the photovoltaic module at time k, I k 、V k and T k They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k, respectively. k 、E k and t k They represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k respectively;

[0040] The formula for obtaining the updated self-prediction data at time k is:

[0041] x k|k =x k|k―1 +K k (z k ―H*x k|k―1 )

[0042] Among them, x k|k The updated self-prediction data at time k is expressed, and the predicted self-data at time k+1 is obtained, that is, the formula based on which the component prediction data is calculated is:

[0043]

[0044] Among them, x k+1|k Represents component prediction data, Iy k+1 , Vyk+1 and Ty k+1 They respectively represent the predicted current data, voltage data and surface temperature data of the photovoltaic component output at time k+1 in the component prediction data.

[0045] Furthermore, the first environmental impact index set includes a sunlight intensity impact index, a temperature impact index and a time impact index. The logic for generating the first environmental impact index set is:

[0046]

[0047] Among them, Gq y 、Wd y and Sj y They represent the sunlight intensity impact index, temperature impact index and time impact index respectively, k 、V k and T k They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k, respectively. k 、E k and t k They represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k, respectively. k―1 、V k―1 and T k―1 They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k-1, respectively. k―1 、E k―1 and t k―1 They respectively represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k-1;

[0048] The logic of using the first environmental impact index set to correct the data of the photovoltaic module at time k+1 is:

[0049] Ix k+1 =I k+1 +Gq y *(S k+1 ―S k―1 )

[0050] Vx k+1 =V k+1 +Wd y *(E k+1 ―E k―1 )

[0051] Tx k+1 =T k+1 +Sj y *(t k+1 ―tk―1 )

[0052] Among them, Ix k+1 、Vx k+1 and Tx k+1 They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k+1, I k+1 、V k+1 and T k+1 They represent the output current data, voltage data and surface temperature data of the photovoltaic module at the time k+1 of the photovoltaic module, respectively. k+1 、E k+1 and t k+1 They respectively represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k+1.

[0053] Furthermore, the formula for correcting the own data at time k using the first environmental impact data set is:

[0054] Ix k =I k +Gq y *(S k ―S k―1 )

[0055] Vx k =V k +Wd y *(E k ―E k―1 )

[0056] Tx k =T k +Sj y *(t k ―t k―1 )

[0057] Among them, Ix k 、Vx k and Tx k They respectively represent the current data, voltage data output by the photovoltaic module at the corrected time k, and the surface temperature data of the photovoltaic module.

[0058] Furthermore, when generating the self-data error index, the errors of the current data, voltage data and surface temperature data of the photovoltaic module output in the corrected photovoltaic module self-data and module prediction data at time k+1 are assigned corresponding weights, and the self-data error index is calculated after summing. The formula for generating the self-data error index is:

[0059]

[0060] Among them, ZW z Represents the own data error index, Ix k+1 、Vx k+1 and Tx k+1 Iy represents the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k+1, k+1 , Vy k+1 and Ty k+1 They respectively represent the predicted current data, voltage data and surface temperature data of the photovoltaic component output at time k+1 in the component prediction data, α, β and γ are the current anomaly weight, voltage anomaly weight and temperature anomaly weight respectively, α>β>γ>0, and α+β+γ=1.

[0061] Furthermore, when generating the self-data volatility based on the self-data at the past k-1 moment, the corrected self-data at the k moment and the k+1 moment, the variances of the current data, voltage data and surface temperature data of the photovoltaic module output at the three moments are calculated respectively, and the self-data volatility is obtained by calculating the average of the three groups of variances, specifically:

[0062]

[0063] Among them, Zs b is the volatility of its own data, Ix k+1 、Vx k+1 and Tx k+1 Ix represents the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k+1, respectively. k 、Vx k and Tx k They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k, respectively. k―1 、V k―1 and T k―1 They respectively represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k-1, and They represent the average current, average voltage and average surface temperature respectively, and:

[0064]

[0065] The formula used to generate the condition monitoring index is:

[0066]

[0067] Among them, ZJ z Indicates the status monitoring index. When comparing the status monitoring index with the threshold, if ZJz ≥ZJ yz , then an early warning signal of abnormality of the current photovoltaic component is issued. If ZJ z <ZJ yz , no warning signal is issued.

[0068] The present invention further provides a photovoltaic module state monitoring method based on multi-source data, the monitoring method is obtained by executing the photovoltaic module state monitoring system mentioned above, and the specific steps include:

[0069] Step 1: Collect the self-data and environmental data of the photovoltaic module at time k and time k-1, the self-data includes the current data, voltage data and surface temperature data of the photovoltaic module output, and the environmental data includes the sunlight intensity data on the surface of the photovoltaic module, the temperature data of the environment and the time of commissioning;

[0070] Step 2: Based on the photovoltaic module's own data and environmental data at time k and time k-1, a Kalman filter algorithm is used to predict the photovoltaic module's own data at time k+1 to obtain module prediction data, wherein the module prediction data includes the photovoltaic module output current data, voltage data and photovoltaic module surface temperature data at time k+1;

[0071] Step 3: Collect the self-data and environmental data of the photovoltaic component at time k+1, generate a first environmental impact index set based on the self-data and environmental data of the photovoltaic component at time k and time k-1, and use the first environmental impact index set to correct the self-data of the photovoltaic component at time k+1;

[0072] Step 4: Generate the self-data error index based on the corrected self-data of the photovoltaic component at time k+1 and the component prediction data, use the first environmental impact data set to correct the self-data at time k, and generate the self-data volatility based on the self-data at the past time k-1, the corrected self-data at time k and the self-data at time k+1;

[0073] Step 5: Analyze the volatility of its own data and its own data error index, establish a data analysis model, generate a status monitoring index, compare the status monitoring index with the threshold, and choose to issue or not issue a warning signal based on the comparison results.

[0074] Compared with the prior art, the present invention has the following beneficial effects:

[0075] The present invention forms a photovoltaic module state monitoring system by introducing self-data, environmental data and Kalman filtering algorithm, collects the self-data and environmental data of the photovoltaic module, and predicts the future state of the module by using the Kalman filtering algorithm through the data prediction module, predicts the self-data of the photovoltaic module at the next moment, obtains the module prediction data, and effectively distinguishes the reasons for the performance degradation of the photovoltaic module through the environmental impact index introduced by the data correction module, and timely distinguishes whether the performance degradation is caused by external environmental factors or the module itself, thereby providing a more accurate decision-making basis for the operation and maintenance monitoring of the photovoltaic module;

[0076] The present invention uses the predicted data as a reference standard to generate an own data error index to evaluate whether the actual state of the photovoltaic component is normal. The self-data at three moments after correction and the component predicted data are used to generate the self-data volatility to reflect the performance changes of the photovoltaic component at adjacent time points. The self-data error index and the self-data volatility are used for analysis. In combination with the data analysis model of the monitoring and analysis module, a state monitoring index can be generated and compared with a preset threshold to issue a warning signal, thereby improving the accuracy of photovoltaic system fault detection and reducing the workload of manual analysis and the uncertainty of subjective judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 It is a schematic diagram of the overall system structure of the present invention;

[0078] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0079] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0080] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0081] Example:

[0082] See also Figure 1 , the present invention provides a technical solution:

[0083] A photovoltaic module status monitoring system based on multi-source data includes a data acquisition module, a data prediction module, a data correction module, a fluctuation judgment module and a monitoring and analysis module, wherein:

[0084] The data acquisition module collects the self-data and environmental data of the photovoltaic component at time k and time k-1, wherein the self-data includes the current data, voltage data and surface temperature data of the photovoltaic component output, and the environmental data includes the sunlight intensity data on the surface of the photovoltaic component, the temperature data of the environment and the time of commissioning. The data acquisition module sends the collected data to.

[0085] In this embodiment, the photovoltaic module refers to a photovoltaic panel or a solar panel, which is a device that uses solar energy to convert light energy into electrical energy. It is composed of multiple solar cell units, which are the basic components for making photovoltaic modules. Photovoltaic modules have a junction box that contains circuit connections and protection devices that can lead the current generated by the solar panel. The photovoltaic module in this embodiment refers to a single solar panel module that can output electrical energy. Photovoltaic modules can be used independently or installed in an array with other components to increase power output.

[0086] The current data and voltage data output by the photovoltaic module are the values ​​of the current and voltage output by the power output end of the photovoltaic module at a specific moment. The unit of the current data packet is ampere, and the unit of the voltage data is volt. The photovoltaic module surface temperature data is the surface temperature data of the photovoltaic module at a specific moment measured by a temperature sensor placed on the surface of the photovoltaic module. In order to avoid errors, the temperatures of the surfaces of the photovoltaic modules at multiple positions can be collected simultaneously, and then the average is calculated and calibrated as the photovoltaic module surface temperature data. The unit of temperature is Celsius.

[0087] The sunlight intensity data on the surface of the photovoltaic module refers to the intensity of sunlight irradiating on the surface of the photovoltaic module, in watts per square meter. This data reflects the amount of solar energy received by the photovoltaic module, which directly affects the power generation efficiency of the module. The sunlight intensity data is measured by a solar radiometer. In order to avoid errors, the intensity of sunlight on the surface of the photovoltaic module at multiple locations can be collected at the same time, and then the average is calculated and calibrated as the sunlight intensity data on the surface of the photovoltaic module. The temperature data of the environment refers to the temperature of the environment around the photovoltaic module, in degrees Celsius. The ambient temperature will affect the performance of the photovoltaic module because the efficiency of the photovoltaic cell will decrease with the increase of temperature. Therefore, monitoring the ambient temperature helps to evaluate the performance of the photovoltaic module under different climatic conditions. It can also reduce errors by measuring the temperature values ​​of multiple environments to calculate the average. The time of commissioning refers to the cumulative time since the photovoltaic module was installed and started to generate electricity, in hours. Over time, the performance of the photovoltaic module may decline due to aging, pollution, damage, etc.

[0088] The data prediction module uses the Kalman filter algorithm to predict the photovoltaic component's own data at time k+1 based on the photovoltaic component's own data and environmental data at time k and time k-1, and obtains component prediction data, wherein the component prediction data includes the current data, voltage data and surface temperature data of the photovoltaic component output at time k+1.

[0089] The Kalman filter algorithm is a recursive algorithm that can effectively combine historical data and current measurement data to make the best estimate of future states. In photovoltaic systems, it can predict key parameters such as the output current, voltage and surface temperature of photovoltaic modules.

[0090] In this embodiment, the Kalman filter algorithm is used to predict the photovoltaic module's own data at time k+1, and the method for obtaining the module prediction data is based on:

[0091] The state vector of the photovoltaic component at time k-1 is constructed based on the photovoltaic component's own data at time k-1, and the state equation for the transfer of the state vector from time k-1 to time k is constructed in combination with the state transfer matrix. The self-prediction data at time k based on the photovoltaic component's own data at time k-1 and the environmental data are generated, and the error covariance matrix of the self-prediction data at time k is updated.

[0092] Constructing the state vector is the first step of Kalman filtering, which represents the data of the photovoltaic module itself as a vector. The state transfer matrix describes the change of the system state over time, and can generate the current moment prediction data based on the historical self-data and environmental data, and update the error covariance matrix to reflect the uncertainty of the prediction, providing a basis for subsequent prediction and update.

[0093] According to the environmental data of the photovoltaic component at time k, the observation vector of the photovoltaic component at time k is constructed, and the observation matrix is ​​constructed. The Kalman gain is calculated by combining the updated error covariance matrix and the observation matrix.

[0094] The observation vector contains the actual measurements obtained from the environment, and the observation matrix links these measurements with the PV module’s own data. Calculating the Kalman gain is the core of the Kalman filter, which determines the weight between prediction and observation, and uses the actual measurement data to correct the prediction, ensuring the accuracy of the prediction.

[0095] The Kalman gain and the observation vector at time k are used to update the self-prediction data at time k, and the updated self-prediction data at time k is obtained.

[0096] The Kalman gain and observation vector are used to update the predicted data. This step is the "correction" stage of the Kalman filter, which combines the prediction and actual observation to obtain a more accurate state estimate. By fusing the prediction and actual observation, the accuracy of the prediction is improved.

[0097] Using the updated self-prediction data at time k, combined with the state transfer matrix, the state equation for the transfer from time k to time k+1 is constructed to obtain the predicted self-data at time k+1, that is, the component prediction data.

[0098] By using the updated current moment prediction data and combining it with the state transfer matrix, the state equation from the current moment to the future moment is constructed to obtain the prediction data for the future moment. This provides a reliable basis for future predictions based on the verified system model and the updated state estimation.

[0099] Furthermore, the state vector of the photovoltaic module at time k-1 is:

[0100]

[0101] Among them, x k―1 represents the state vector of the photovoltaic module at time k-1, I k―1 、V k―1 and T k―1 They respectively represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k-1.

[0102] Current, voltage and temperature are key parameters of the operating state of photovoltaic modules. The output current of photovoltaic modules is a direct indicator of their power generation capacity. The current is affected by light intensity and temperature, and changes significantly over time. It is one of the core variables of state estimation. The output voltage is also an important parameter for evaluating the performance of photovoltaic modules. The voltage change is related to the load, environmental conditions and internal impedance of the module. The surface temperature of the photovoltaic module has a direct impact on its performance. By combining these parameters into a state vector, the operating state of the photovoltaic module at a certain moment can be fully and accurately described. These state variables are not only interrelated, but also jointly affect the performance of photovoltaic modules. The purpose of constructing the state vector is to effectively track and predict these key parameters using the Kalman filter algorithm during the state estimation process.

[0103] Since the state vector contains key performance indicators, it can fully reflect the operating status of the PV module. Integrating multiple related variables into one vector simplifies the mathematical processing of state estimation and can provide reliable input for the prediction and correction steps of the Kalman filter.

[0104] The state transfer matrix is:

[0105]

[0106] Wherein, F represents a state transfer matrix, and the state transfer matrix is ​​a unit matrix, indicating that each state variable (current, voltage and temperature) is independent in the time series, and it is assumed that they are not directly affected by other state variables within a time step. When the unit matrix is ​​used as a state transfer matrix, it means that the state value predicted at the next moment is equal to the state value at the current moment, that is, in the absence of external intervention or further dynamic modeling, each state variable is assumed to be a copy of itself in time. The use of the unit matrix simplifies the complexity of state estimation. In the absence of sufficient system dynamic information or insufficient data to support complex models, the use of the unit matrix can avoid the erroneous introduction of misjudged dynamic factors. The state transfer matrix of this embodiment is used in the initial stage or in the verification stage, or when the system dynamics are relatively stable and do not change much.

[0107] Under normal conditions, the output voltage, current and surface temperature of the photovoltaic module will show relatively stable characteristics. In a short period of time, the light intensity will be relatively stable and will not change suddenly. This will cause the solar radiation received by the photovoltaic module to change little, which will cause the output current and voltage to remain at a relatively stable level. In specific seasons and geographical locations, the ambient temperature will be relatively constant, so that the surface temperature of the photovoltaic module will not change much, so that it can maintain stable output performance. Moreover, the current photovoltaic system is usually equipped with an MPPT controller, which can continuously adjust the system operating point to match the maximum power point, which means that even when the environmental conditions change slightly, close to the optimal operating conditions can be maintained, so that the output current and voltage remain relatively stable. Therefore, the state transfer matrix used in this embodiment is very suitable for scenarios where the state of the photovoltaic module does not change much.

[0108] The formula for generating the self-prediction data at time k based on the self-data of the photovoltaic module at time k-1 and the environmental data is:

[0109] x k|k―1 =x k―1 *F

[0110] Among them, x k|k―1 Represents the self-predicted data of the PV module at time k based on its own data at time k-1 and the environmental data.

[0111] According to the above description, photovoltaic modules have a certain inherent stability, so the current and voltage state changes are linear, that is, from one moment to the next, the state change can be described by a linear matrix, so as to quickly predict the state.

[0112] The formula for updating the error covariance matrix of the self-prediction data at time k is:

[0113] P k|k―1 =F*P k―1|k―1 *F T

[0114] Among them, P k|k―1 represents the error covariance matrix of the updated self-prediction data at time k, F T represents the transpose of the state transfer matrix, P k―1|k―1 represents the error covariance matrix of the self-prediction data at time k-1, and:

[0115]

[0116] Among them, σ I , σ U and σ TThey respectively represent the tolerances of the current data, voltage data and surface temperature data of the photovoltaic modules output.

[0117] In the prediction algorithm of Kalman filtering, the error covariance matrix is ​​updated based on the assumptions of linear systems and Gaussian noise. The updating process is to predict the state uncertainty of the next time step and transfer this uncertainty in the model. The error covariance matrix represents the uncertainty of the state estimation or the covariance of the error at the k-1 moment. It captures the correlation of errors between state variables and the size of their respective uncertainties. In photovoltaic module monitoring, the uncertainty of each state variable is quantified by the error covariance matrix. The diagonal elements in the matrix represent the variance of each state variable, that is, the uncertainty of measurement or prediction, and the non-diagonal elements represent the error correlation between state variables. This implementation can effectively transfer the state uncertainty through the system dynamics to the next moment by updating the error covariance matrix of its own prediction data at moment k, providing a mathematical basis for subsequent state estimation and updating.

[0118] The tolerance of the current data and voltage data output by the photovoltaic module is obtained by querying the manual of the photovoltaic module, and the surface temperature data of the photovoltaic module is obtained by querying the manual of the sensor that collects the temperature value. When processing the output data of the photovoltaic module, σ I 2 , σ V 2 and σ T 2 The error covariance matrix of the self-predicted data at time k-1 is placed on the diagonal of the matrix, which intuitively represents the measurement uncertainty of the current, voltage and temperature at time k-1, that is, the fluctuation or error size of the measured value. The error covariance matrix can take into account the uncertainty in historical information and new observation data, so as to make a more accurate state estimate. When updating, the error covariance matrix will be used in combination with the new measurement data to reduce the uncertainty of the estimate.

[0119] Furthermore, the method for calculating the Kalman gain is:

[0120] K k =P k|k―1 *H T *(H*P k|k―1 *H T ) ―1

[0121] Among them, K k represents the Kalman gain, H represents the observation matrix, and H T represents the transpose of the observation matrix, and:

[0122]

[0123] The observation vector of the photovoltaic module at time k is:

[0124]

[0125] Among them, z k represents the observation vector of the photovoltaic module at time k, I k 、V k and T k They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k, respectively. k 、E k and t k They respectively represent the surface sunlight intensity of the photovoltaic module at time k, the temperature of the environment and the time it is put into use.

[0126] The Kalman gain reflects how to adjust the estimate of the system state when the observation vector of the photovoltaic component at time k is given. The error covariance matrix of the updated self-prediction data at time k represents the uncertainty of the current state estimate after taking into account the previous state and process model. The observation matrix defines how to map from the state vector to the observation vector, and its transpose is used for dimension matching and matrix operations. This embodiment dynamically adjusts the gain by considering the previous prediction uncertainty and the current observation information, thereby more accurately fusing the prediction and observation data.

[0127] In this embodiment, the observation matrix is ​​configured to identify and select specific parts of the state vector corresponding to current, voltage and temperature to ensure that the measurements of current, voltage and temperature in the state vector can be directly mapped to the observation vector, which includes the current, voltage and surface temperature data of the photovoltaic module at time k, as well as the sunlight intensity, ambient temperature and usage time, so that the Kalman filter algorithm not only updates the state estimate based on its own measured data, but also integrates changes in environmental conditions.

[0128] The formula for obtaining the updated self-prediction data at time k is:

[0129] x k|k =x k|k―1 +K k (z k ―H*x k|k―1 )

[0130] Among them, x k|k represents the updated self-prediction data at time k, x k|k Considering the observation information z at time k k The latest estimate of the system state is obtained after the update process. This update process involves two key steps: prediction and correction. In the prediction stage, x k|k―1It is a prediction based on the state estimate of the previous moment and the dynamic model of the system, which represents the best estimate of the system state at time k before considering the latest observation. The correction phase is performed by replacing the predicted state x k|k―1 Compared with the actual observation z k Compare to adjust the state estimate. Difference z k ―H*x k|k―1 Represents the error between the observed value and the expected observed value based on the predicted state.

[0131] The Kalman gain weighs the degree of trust in the predicted state against the degree of trust in the new observation data. If the Kalman gain is large, it means that the trust in the observation data is high, so the correction of the state estimate depends more on the observation error. On the contrary, if the Kalman gain is small, it means that we have a higher degree of trust in the prediction model, so the state update depends less on the observation error.

[0132] Obtaining updated self-prediction data at time k reflects an optimization process whose goal is to minimize the uncertainty of the system state estimate, so the Kalman filter algorithm can dynamically adjust its correction to the state estimate at each moment.

[0133] The formula for obtaining the predicted self-data at time k+1, that is, the component prediction data, is:

[0134]

[0135] Among them, x k+1|k Represents component prediction data, Iy k+1 , Vy k+1 and Ty k+1 They respectively represent the predicted current data, voltage data and surface temperature data of the photovoltaic component output at time k+1 in the component prediction data.

[0136] x k+1|k is the best estimate x based on the current time, i.e. time k. k|k To predict the state of the next moment, that is, the state at time k+1, the Kalman filter algorithm can not only provide an accurate estimate of the current state, but also predict the future system state, x k+1|k It represents the prediction of the state at time k+1 under the condition at time k.

[0137] The data correction module collects the self-data and environmental data of the photovoltaic component at time k+1, generates a first environmental impact index set based on the self-data and environmental data of the photovoltaic component at time k and time k-1, and uses the first environmental impact index set to correct the self-data of the photovoltaic component at time k+1.

[0138] By considering the PV module's own data and environmental data at time k and time k-1, the PV module's own data at time k+1 can be predicted more accurately. Under different environmental conditions, the performance of the PV module will change to a certain extent, although the change is small. Therefore, the generation and application of the environmental impact index set enables the self-data to be corrected according to the impact of environmental changes on the output of the PV module.

[0139] In this embodiment, the first environmental impact index set includes a sunlight intensity impact index, a temperature impact index and a time impact index. The logic for generating the first environmental impact index set is:

[0140]

[0141] Among them, Gq y 、Wd y and Sj y They represent the sunlight intensity impact index, temperature impact index and time impact index respectively, k 、V k and T k They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k, respectively. k 、E k and t k They represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k, respectively. k―1 、V k―1 and T k―1 They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k-1, respectively. k―1 、E k―1 and t k―1 They respectively represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k-1.

[0142] In this embodiment, the surface sunlight intensity data is used to correct the current data, the ambient temperature data is used to correct the voltage data, and the time of use is used to correct the surface temperature data of the photovoltaic module, because the current output of the photovoltaic module mainly depends on the sunlight intensity. The increase in light intensity usually causes more photons to hit the solar cell, stimulating more electrons, thereby generating a larger current, and the voltage output of the photovoltaic module is closely related to the ambient temperature. The increase in ambient temperature will cause the energy band gap of the semiconductor material to decrease, thereby reducing the voltage output. Therefore, using the ambient temperature to correct the voltage data can effectively calibrate the voltage fluctuation caused by temperature changes. The long-term use of the photovoltaic module will affect its thermal properties, because the aging of the material may affect its thermal conductivity and heat capacity, thereby affecting the surface temperature of the module. The length of time in use can be used as an indicator to measure the degree of aging of the module. Therefore, using it to correct the surface temperature data can help evaluate and adjust the changes in thermal properties caused by the use time. The correction strategy adopted in this embodiment allows the specific impact of each environmental and operating factor to be specifically considered and calibrated.

[0143] In this embodiment, the impact index evaluates the degree of influence of environmental factors on the performance of photovoltaic modules by calculating the rate of change between two consecutive time points. The sunlight intensity impact index is used to evaluate the impact of sunlight intensity changes on the output current of photovoltaic modules. k ―I k―1 and the change in sunlight intensity S k ―S k―1 The ratio of the current to the sunlight intensity is obtained to obtain the change in current when the sunlight intensity changes by one unit. The sunlight intensity impact index reflects the sensitivity of the photovoltaic module to light changes.

[0144] The temperature impact index is used to evaluate the impact of ambient temperature changes on the output voltage of photovoltaic modules. k ―V k―1 and temperature change E k ―E k―1 The ratio of the voltage change for each unit change in temperature is obtained, which reflects the sensitivity of the photovoltaic module to temperature changes. The time impact index is used to evaluate the impact of the use time of the photovoltaic module on the surface temperature. By calculating the surface temperature change T k ―T k―1 The change in usage time t k ―t k―1 The ratio of the surface temperature to the temperature of the photovoltaic module is obtained for each unit increase in usage time. This index reflects the change in the thermal characteristics of the photovoltaic module as the usage time increases.

[0145] By calculating the rate of change, the dynamic impact of environmental factors on the performance of PV modules can be captured more accurately, taking into account the direct impact of environmental factors and the changing trends of these factors over time, thus providing a more precise basis for data correction.

[0146] Furthermore, the logic of using the first environmental impact index set to correct the photovoltaic component's own data at time k+1 is:

[0147] Ix k+1 =I k+1 +Gq y *(S k+1 ―S k―1 )

[0148] Vx k+1 =V k+1 +Wd y *(E k+1 ―E k―1 )

[0149] Tx k+1 =T k+1 +Sj y *(t k+1 ―t k―1 )

[0150] Among them, Ix k+1 、Vx k+1 and Tx k+1 They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k+1, I k+1 、V k+1 and T k+1 They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the time k+1 of the photovoltaic module, respectively. k+1 、E k+1 and t k+1 They respectively represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k+1.

[0151] In this embodiment, a known influence index is used to adjust the photovoltaic module data at a certain moment in the future, so as to obtain data that more accurately reflects the actual working status. The current data at moment k+1 is adjusted by using the sunlight intensity influence index and the difference in sunlight intensity between two moments. The voltage data at moment k+1 is adjusted by using the temperature influence index and the difference in ambient temperature between two moments, taking into account the influence of ambient temperature changes on voltage output. The surface temperature data at moment k+1 is adjusted by using the time influence index and the difference in usage time between two moments, taking into account the potential influence of long-term use on surface temperature.

[0152] The current output of a photovoltaic module is primarily determined by the process by which photons excite electrons to produce current. As the intensity of sunlight increases, more photons are absorbed, producing more electron-hole pairs, which in turn increases the current output. This relationship can be considered linear because the mechanism of photon absorption and current generation is stable under normal operating conditions. As the ambient temperature increases, the band gap of the semiconductor material decreases, causing the voltage output to drop. This temperature effect on voltage can usually be described by a negative temperature coefficient, meaning that for every degree increase in temperature, the voltage drops by a fixed percentage, so this relationship can also be considered linear over a certain temperature range.

[0153] The surface temperature of photovoltaic modules will change with the increase of usage time. Within a certain period of time (such as several months to several years), the change in surface temperature is proportional to the change in usage time, which can be approximated as a linear relationship. Therefore, by using the various impact indexes of previous time periods, the data at future times can be corrected to obtain performance that is closer to the actual situation.

[0154] The fluctuation judgment module generates its own data error index based on the corrected self-data of the photovoltaic component at time k+1 and the component prediction data, uses the first environmental impact data set to correct the self-data at time k, and generates its own data volatility based on the self-data at the past time k-1, the corrected time k and the self-data at time k+1.

[0155] Furthermore, the formula for correcting the own data at time k using the first environmental impact data set is:

[0156] Ix k =I k +Gq y *(S k ―S k―1 )

[0157] Vx k =V k +Wd y *(E k ―E k―1 )

[0158] Tx k =T k +Sj y *(t k ―t k―1 )

[0159] Among them, Ix k 、Vx k and Tx k They respectively represent the current data, voltage data output by the photovoltaic module at the corrected time k, and the surface temperature data of the photovoltaic module.

[0160] Correcting the output current data, voltage data and surface temperature data of the photovoltaic module at time k also uses the change in environmental data at the previous moment to correct the photovoltaic module data at the current moment, thereby obtaining more accurate current, voltage and surface temperature to compensate for the instantaneous impact of environmental factors on the performance of the photovoltaic module.

[0161] The photovoltaic module status monitoring system is constructed by introducing its own data, environmental data and Kalman filtering algorithm. The photovoltaic module's own data and environmental data are collected, and the Kalman filtering algorithm is used to predict the future state of the module through the data prediction module. The photovoltaic module's own data at the next moment is predicted to obtain the module prediction data. The environmental impact index introduced by the data correction module can effectively distinguish the reasons for the performance degradation of the photovoltaic module, and timely distinguish whether the performance degradation is caused by external environmental factors or problems of the module itself, thereby providing a more accurate decision-making basis for the operation and maintenance monitoring of the photovoltaic module.

[0162] In this embodiment, when generating the self-data error index, the errors of the current data, voltage data and surface temperature data of the photovoltaic module output in the corrected photovoltaic module self-data and module prediction data at time k+1 are respectively assigned corresponding weights, and the self-data error index is calculated after summing. The formula for generating the self-data error index is:

[0163]

[0164] Among them, ZW z Represents the own data error index, Ix k+1 、Vx k+1 and Tx k+1 Iy represents the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k+1, k+1 , Vy k+1 and Ty k+1 They respectively represent the predicted current data, voltage data and surface temperature data of the photovoltaic component output at time k+1 in the component prediction data, α, β and γ are the current anomaly weight, voltage anomaly weight and temperature anomaly weight respectively, α>β>γ>0, and α+β+γ=1.

[0165] By calculating the corrected data Ix k+1 、Vx k+1 and Tx k+1 With the predicted data Iy k+1 , Vy k+1 and Ty k+1The absolute difference between the two items is used to measure the deviation between the actual performance and the prediction. The absolute difference of each item is divided by the minimum value of these items to convert it into a relative error, so as to compare the accuracy of each data more fairly.

[0166] By assigning different weights to the relative errors of current, voltage and surface temperature, which reflect the importance of different types of data in evaluating the performance accuracy of PV modules, the weighted relative errors of current, voltage and surface temperature are added together to generate the own data error index.

[0167] The self-data error index uses the predicted data as a reference standard to evaluate whether the actual status of the PV module is normal. The larger the value, the more abnormal the status of the PV module. The predicted data is calculated based on historical self-data and environmental conditions, and represents the expected performance of the PV module at a specific moment. Therefore, the predicted data can be used as a reasonable benchmark for comparing the actual observed data.

[0168] The purpose of the self-data error index is to timely detect and evaluate the performance anomalies of photovoltaic modules by comparing the actual data with the predicted data. k+1 、Vx k+1 and Tx k+1 And measured data k+1 , Vy k+1 and Ty k+1 If the actual data after correction deviates significantly from the predicted data, it means that the performance of the component is in line with expectations and the status is normal. If the actual data after correction deviates significantly from the predicted data, it may indicate that the performance of the component is affected by some abnormal factors and the status may be abnormal. Therefore, the larger the error index of the data itself, the more abnormal the failure of the PV component may be.

[0169] Relative error is used instead of absolute error because it can better reflect the percentage of data change, which is fairer for data comparisons of different magnitudes. For example, the absolute values ​​of current, voltage, and surface temperature may vary greatly. Direct comparison of absolute errors may not accurately reflect the actual performance deviation. Different performance indicators have different degrees of influence on the overall performance of photovoltaic modules. Current is a direct factor in the energy output of photovoltaic systems. The magnitude of current directly affects the amount of electrical energy generated by photovoltaic panels. Therefore, the accuracy of current is extremely important for system performance. Voltage changes have a smaller direct impact on energy output than current. Voltage is a key factor affecting system stability and safety. Voltage stability is crucial to maintaining the normal operation of the system and preventing electrical accidents such as overload or short circuit. Although surface temperature has little effect on immediate power output, high temperature will reduce the efficiency of photovoltaic modules and accelerate aging, affecting the long-term stability and life of the modules.

[0170] Therefore, current is the most important due to its direct relationship to energy output, followed by voltage, and surface channel temperature, although more indirect, is equally critical to long-term operation and is therefore given the smallest weight, so α>β>γ. This weight distribution helps to more accurately evaluate and monitor the performance status of the photovoltaic system.

[0171] The monitoring and analysis module analyzes its own data volatility and its own data error index, establishes a data analysis model, generates a status monitoring index, compares the status monitoring index with the threshold, and chooses to issue or not issue a warning signal based on the comparison results.

[0172] In this embodiment, when generating the self-data fluctuation rate based on the self-data at the past k-1 moment, the corrected self-data at the k moment and the k+1 moment, the variances of the current data, voltage data and surface temperature data of the photovoltaic module output at the three moments are calculated respectively, and the self-data fluctuation rate is obtained by calculating the average of the three groups of variances, which is specifically:

[0173]

[0174] Among them, Zs b is the volatility of its own data, Ix k+1 、Vx k+1 and Tx k+1 Ix represents the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k+1, respectively. k 、Vx k and Tx k They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k, respectively. k―1 、V k―1 and T k―1 They respectively represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k-1, and They represent the average current, average voltage and average surface temperature respectively, and:

[0175]

[0176] In this embodiment, the data volatility of the own data is calculated by specifically using the data at time k-1, time k and time k+1 to evaluate the performance stability of the photovoltaic module. By analyzing the data fluctuations of current, voltage and surface temperature, information about the performance changes of the module in a specific time period can be obtained. By selecting data at three times, the short-term fluctuation characteristics of the performance of the photovoltaic module in the time series can be captured. The square of the difference between the current, voltage and temperature data at each moment and their corresponding average values ​​is calculated, and then summed and averaged. This is actually a variant of calculating the variance, which is used to measure the dispersion or volatility of the data.

[0177] By considering data from three consecutive moments, short-term fluctuations in the output of PV modules can be captured more sensitively. Since the volatility of its own data is generated by using its own data at the past k-1 moment, the corrected k moment, and the k+1 moment, the influence of environmental factors has been excluded. This fluctuation is judged to be caused by the failure of the PV module itself.

[0178] The greater the volatility of its own data, the greater the performance changes of the PV modules at adjacent time points, indicating that its condition is worse. There may be faults inside the PV modules, resulting in unstable performance. For example, the greater the volatility of its own data, it may indicate that the fluctuation of current or voltage exceeds the normal range, and there may be circuit problems, module damage or connection problems, causing the condition of the PV modules to be worse.

[0179] The formula used to generate the condition monitoring index is:

[0180]

[0181] Among them, ZJ z Indicates the status monitoring index. When comparing the status monitoring index with the threshold, if ZJ z ≥ZJ yz , then an early warning signal of abnormality of the current photovoltaic component is issued. If ZJ z <ZJ yz , no warning signal is issued

[0182] The condition monitoring index evaluates the overall condition of the PV module through its own data error index and its own data volatility. The larger the condition monitoring index is, the greater the problem or abnormality of the operating status of the PV module may be. As the error index increases, the condition monitoring index will also increase, reflecting the deterioration of the module performance. As the volatility increases, the condition monitoring index will also increase, indicating that the output of the module is more unstable, which may point to unstable module performance or potential failures.

[0183] The own data error index is fitted with a logarithmic function, because although larger error data is important, its growth will not linearly affect the overall index, which can avoid the overall evaluation result being dominated by a single or a few large error values. In addition, the logarithmic function is particularly suitable for amplifying small values ​​close to zero, so that the condition monitoring index can also sensitively respond to small own data error indices. Therefore, a logarithmic function is used to reflect the impact of the own data error index on the condition monitoring index, and the own data volatility is fitted with an exponential function, because higher volatility usually means higher risk or instability. Through exponential transformation, the impact caused by larger volatility is significantly amplified, which helps to give enough attention in the evaluation. Small fluctuations in voltage, current, etc. will not have a significant impact on PV modules, while large fluctuations may cause serious problems. The growth rate of the exponential function is much faster than the linear rate, which enables the condition monitoring index to respond quickly and provide rapid warnings in the face of extreme fluctuations.

[0184] The predicted data is used as a reference standard to generate the own data error index, which is used to evaluate whether the actual status of the PV module is normal. The corrected own data at three moments and the module predicted data are used to generate the own data volatility, which reflects the performance changes of the PV module at adjacent time points. The own data error index and the own data volatility are used for analysis.

[0185] Combined with the data analysis model of the monitoring and analysis module, it is possible to generate a status monitoring index, compare it with the preset threshold, and issue a warning signal, thereby improving the accuracy of photovoltaic system fault detection and reducing the workload of manual analysis and the uncertainty of subjective judgment.

[0186] In this embodiment, the k+1 moment is the current moment, the time length between the k moment and the k-1 moment is the same as the time length between the k moment and the k+1 moment, and the time intervals between the k-1 moment, the k moment and the k+1 moment are the same, which means that the sampling frequency is consistent, such as every hour, every day, every second, etc.

[0187] See also Figure 2 The present invention also provides a photovoltaic module status monitoring method based on multi-source data, the monitoring method is obtained by executing the photovoltaic module status monitoring system mentioned above, and the specific steps include:

[0188] Step 1: Collect the self-data and environmental data of the photovoltaic module at time k and time k-1, the self-data includes the current data, voltage data and surface temperature data of the photovoltaic module output, and the environmental data includes the sunlight intensity data on the surface of the photovoltaic module, the temperature data of the environment and the time of commissioning;

[0189] Step 2: Based on the photovoltaic module's own data and environmental data at time k and time k-1, a Kalman filter algorithm is used to predict the photovoltaic module's own data at time k+1 to obtain module prediction data, wherein the module prediction data includes the photovoltaic module output current data, voltage data and photovoltaic module surface temperature data at time k+1;

[0190] Step 3: Collect the self-data and environmental data of the photovoltaic component at time k+1, generate a first environmental impact index set based on the self-data and environmental data of the photovoltaic component at time k and time k-1, and use the first environmental impact index set to correct the self-data of the photovoltaic component at time k+1;

[0191] Step 4: Generate the self-data error index based on the corrected self-data of the photovoltaic component at time k+1 and the component prediction data, use the first environmental impact data set to correct the self-data at time k, and generate the self-data volatility based on the self-data at the past time k-1, the corrected self-data at time k and the self-data at time k+1;

[0192] Step 5: Analyze the volatility of its own data and its own data error index, establish a data analysis model, generate a status monitoring index, compare the status monitoring index with the threshold, and choose to issue or not issue a warning signal based on the comparison results.

[0193] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0194] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0195] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0196] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A photovoltaic module status monitoring system based on multi-source data, It is characterized in that include: A data acquisition module is used to collect the self data and environmental data of the photovoltaic module at time k and time k-1, wherein the self data includes the current data, voltage data and surface temperature data of the photovoltaic module output, and the environmental data includes the surface sunlight intensity data of the photovoltaic module, the temperature data of the environment and the time of commissioning; The data prediction module is used to predict the photovoltaic module's own data at time k+1 based on the photovoltaic module's own data and environmental data at time k and time k-1, and obtain the component prediction data, which includes the photovoltaic module output current data, voltage data and photovoltaic module surface temperature data at time k+1. A data correction module is used to collect the self-data and environmental data of the photovoltaic component at time k+1, generate a first environmental impact index set according to the self-data and environmental data of the photovoltaic component at time k and time k-1, and use the first environmental impact index set to correct the self-data of the photovoltaic component at time k+1; A fluctuation judgment module is used to generate a self-data error index based on the corrected self-data of the photovoltaic component at time k+1 and the component prediction data, use the first environmental impact data set to correct the self-data at time k, and generate a self-data volatility based on the self-data at time k-1 in the past, the corrected self-data at time k and the self-data at time k+1; The monitoring and analysis module is used to analyze its own data volatility and its own data error index, establish a data analysis model, generate a status monitoring index, compare the status monitoring index with the threshold, and choose to issue or not issue a warning signal based on the comparison results.

2. A photovoltaic module status monitoring system based on multi-source data according to claim 1, Features: The k+1 moment is the current moment, and the time length between the k moment and the k-1 moment is the same as the time length between the k moment and the k+1 moment.

3. A photovoltaic module status monitoring system based on multi-source data according to claim 1, Features: The Kalman filter algorithm is used to predict the photovoltaic module's own data at time k+1. The method for obtaining the module prediction data is based on: The state vector of the photovoltaic module at time k-1 is constructed based on the photovoltaic module's own data at time k-1, and the state equation of the state vector transfer from time k-1 to time k is constructed in combination with the state transfer matrix, and the self-prediction data at time k based on the photovoltaic module's own data at time k-1 and the environmental data are generated, and the error covariance matrix of the self-prediction data at time k is updated; According to the environmental data of the photovoltaic component at time k, the observation vector of the photovoltaic component at time k is constructed, and the observation matrix is ​​constructed, and the Kalman gain is calculated by combining the updated error covariance matrix and the observation matrix; Use the Kalman gain and the observation vector at time k to update the self-prediction data at time k, and obtain the updated self-prediction data at time k; Using the updated self-prediction data at time k, combined with the state transfer matrix, the state equation for the transition from time k to time k+1 is constructed to obtain the predicted self-data at time k+1, that is, the component prediction data.

4. A photovoltaic module status monitoring system based on multi-source data according to claim 3, Features: The state vector of the photovoltaic module at time k-1 is: Among them, x k--1 represents the state vector of the photovoltaic module at time k-1, I k-1 、V k-1 and T k-1 Respectively represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k-1 time; The state transfer matrix is: Where, F represents the state transfer matrix; The formula for generating the self-prediction data of the photovoltaic module at time k based on its own data at time k-1 and the environmental data is: Xk|k-- 1 =xk-- 1 *F Among them, x k|k-1 Represents the self-predicted data of the photovoltaic component at time k based on its own data at time k-1 and environmental data; The formula for updating the error covariance matrix of the self-prediction data at time k is: P k|k-1 =F*P k-1|k-1 *F T Among them, P k|k-1 represents the error covariance matrix of the updated self-prediction data at time k, F T represents the transpose of the state transfer matrix, P k-1|k-1 represents the error covariance matrix of the self-prediction data at time k-1, and: Among them, σ I , σ U and σ T They respectively represent the tolerances of the current data, voltage data and surface temperature data of the photovoltaic modules output.

5. A photovoltaic module status monitoring system based on multi-source data according to claim 4, Features: The calculation of Kalman gain is based on the method: K k =P k|k-1 *H T *(H*P k|k--1 *H T ) -1 Among them, K k represents the Kalman gain, H represents the observation matrix, and H T represents the transpose of the observation matrix, and: The observation vector of the photovoltaic module at time k is: Among them, z k represents the observation vector of the photovoltaic module at time k, I k 、V k and T k They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k, respectively. k 、E k and t k They represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k respectively; The formula for obtaining the updated self-prediction data at time k is: x k|k =x k|k-1 +K k (z k -H*x k|k-1 ) Among them, x k|k The updated self-prediction data at time k is expressed, and the predicted self-data at time k+1 is obtained, that is, the formula based on which the component prediction data is calculated is: Among them, x k+1|k Represents component prediction data, Iy k+1 , Vy k+1 and Ty k+1 They respectively represent the predicted current data, voltage data and surface temperature data of the photovoltaic component output at time k+1 in the component prediction data.

6. A photovoltaic module status monitoring system based on multi-source data according to claim 1, Features: The first environmental impact index set includes a sunlight intensity impact index, a temperature impact index and a time impact index. The logic for generating the first environmental impact index set is: Among them, Gq y 、Wd y and Sj y They represent the sunlight intensity impact index, temperature impact index and time impact index respectively, I k 、V k and T k They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k, respectively. k 、E k and t k They represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k, respectively. k-1 、V k-1 and T k-1 They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k-1, respectively. k--1 、E k--1 and t k--1 They represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k-1 respectively; The logic of using the first environmental impact index set to correct the photovoltaic module's own data at time k+1 is: Ix k+1 =I k+1 +Gq y *(S k+1 -S k-1 ) Vx k+1 =V k+1 +Wd y *(E k+1 -E k-1 ) Tx k+1 =T k+1 +Sj y *(t k+1 -t k-1 ) Among them, Ix k+1 、Vx k+1 and Tx k+1 They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k+1, I k+1 、V k+1 and T k+1 They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the time k+1 of the photovoltaic module, respectively. k+1 、E k+1 and t k+1 They respectively represent the surface sunlight intensity, ambient temperature and time of use of the photovoltaic module at time k+1.

7. A photovoltaic module status monitoring system based on multi-source data according to claim 6, Features: The formula for using the first environmental impact data set to correct the own data at time k is: Ix k =I k +Gq y *(S k -S k-1 ) Vx k =V k +Wd y *(E k -E k-1 ) Tx k =T k +Sj y *(t k -t k-1 ) Among them, Ix k 、Vx k and Tx k They respectively represent the current data, voltage data output by the photovoltaic module at the corrected time k, and the surface temperature data of the photovoltaic module.

8. A photovoltaic module status monitoring system based on multi-source data according to claim 1, Features: When generating the self-data error index, the errors of the current data, voltage data and surface temperature data of the photovoltaic module output in the corrected photovoltaic module self-data and module prediction data at time k+1 are assigned corresponding weights, and the self-data error index is calculated after summing. The formula for generating the self-data error index is: Among them, ZW z Represents the own data error index, Ix k+1 、Vx k+1 and Tx k+1 Iy represents the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k+1, k+1 , Vy k+1 and Ty k+1 They respectively represent the predicted current data, voltage data and surface temperature data of the photovoltaic component output at time k+1 in the component prediction data, α, β and γ are the current anomaly weight, voltage anomaly weight and temperature anomaly weight respectively, α>β>γ>0, and α+β+γ=1.

9. A photovoltaic module status monitoring system based on multi-source data according to claim 1, Features: When generating the self-data volatility based on the self-data at the past k-1 moment, the corrected self-data at the k moment and the k+1 moment, the variances of the current data, voltage data and surface temperature data of the photovoltaic modules at the three moments are calculated respectively, and the self-data volatility is obtained by calculating the average of the three groups of variances, specifically: Among them, Zs b is the volatility of its own data, Ix k+1 、Vx k+1 and Tx k+1 Ix represents the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k+1, respectively. k 、Vx k and Tx k They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the corrected time k, respectively. k-1 、V k-1 and T k-1 They represent the current data, voltage data and surface temperature data of the photovoltaic module output at the photovoltaic module k-1 time, respectively. and They represent the average current, average voltage and average surface temperature respectively, and: The formula used to generate the condition monitoring index is: Among them, ZJ z Indicates the status monitoring index. When comparing the status monitoring index with the threshold, if ZJ z ≥ZJ yz , then an early warning signal of abnormality of the current photovoltaic component is issued. If ZJ z <ZJ yz , no warning signal is issued.

10. A photovoltaic module status monitoring method based on multi-source data, Features: The monitoring method is obtained by executing the photovoltaic module status monitoring system according to any one of claims 1 to 9, and the specific steps include: Step 1: Collect the self data and environmental data of the photovoltaic module at time k and time k-1, the self data includes the current data, voltage data and surface temperature data of the photovoltaic module output, and the environmental data includes the sunlight intensity data on the surface of the photovoltaic module, the temperature data of the environment and the time of commissioning; Step 2: Based on the photovoltaic module's own data and environmental data at time k and time k-1, a Kalman filter algorithm is used to predict the photovoltaic module's own data at time k+1 to obtain module prediction data, wherein the module prediction data includes the photovoltaic module output current data, voltage data and photovoltaic module surface temperature data at time k+1; Step 3: Collect the self-data and environmental data of the photovoltaic component at time k+1, generate a first environmental impact index set based on the self-data and environmental data of the photovoltaic component at time k and time k-1, and use the first environmental impact index set to correct the self-data of the photovoltaic component at time k+1; Step 4: Generate a self-data error index based on the corrected self-data of the photovoltaic component at time k+1 and the component prediction data, use the first environmental impact data set to correct the self-data at time k, and generate the self-data volatility based on the self-data at time k-1 in the past, the corrected self-data at time k and the self-data at time k+1; Step 5: Analyze the volatility of its own data and its own data error index, establish a data analysis model, generate a status monitoring index, compare the status monitoring index with the threshold, and choose to issue or not issue a warning signal based on the comparison results.

Citation Information

Patent Citations

  • Method for testing power of solar photovoltaic modules

    CN103116065A

  • Short-term forecast method and system for temperature of photovoltaic assembly

    CN108615087A

  • Data processing method of photovoltaic power generation system

    CN114519250A

  • Photovoltaic power station performance monitoring and analyzing method

    CN118032124A

  • Photovoltaic panel supporting device

    CN212063888U

Cited By

  • Method and system for monitoring power supply state of engineering robot

    CN122362198A

  • An engineering robot power supply state monitoring method and system

    CN122362198B