Perovskite solar cell output power monitoring method based on data analysis

Abstract

The present invention discloses a method for monitoring the output power of a perovskite solar cell based on data analysis, and relates to the technical field of solar cell output power regulation. The method for monitoring the output power of a perovskite solar cell based on data analysis comprises the following steps: perovskite material detection, output power monitoring, and monitoring compensation adjustment. The present invention detects and determines the photoelectric properties of a preset batch of perovskite materials using photoelectric characteristic detection data to obtain a perovskite material detection result, then determines whether to send an output power monitoring instruction, and finally determines whether to perform output power monitoring compensation adjustment based on the obtained output power monitoring result. This achieves more accurate monitoring of output power fluctuations during the perovskite solar cell production process, and solves the problem in the prior art that the output power fluctuation monitoring during the perovskite solar cell production process is insufficiently correlated with the differences in the photoelectric characteristics of the perovskite material.

Description

Technical Field

[0001] The present invention relates to the technical field of solar cell output power regulation, and in particular to a perovskite solar cell output power monitoring method based on data analysis. Background Art

[0002] Output power is a key performance metric for perovskite solar cells. Real-time monitoring of output power can mitigate performance variations caused by the production process. Real-time monitoring of output power changes effectively tracks the production process of perovskite solar cells. Existing technologies offer a variety of methods for monitoring the output power of perovskite solar cells, including real-time maximum power point tracking (MPPT), online monitoring, and environmental monitoring. For example, real-time maximum power point tracking involves continuously monitoring the voltage and current of the perovskite solar cell using an MPPT (Maximum Power Point Tracking) controller, then calculating the cell's output power based on the real-time measurements. The MPPT controller analyzes the battery's current-voltage characteristic curve. Based on the curve's changes, the controller's built-in algorithm dynamically determines whether the current point is the maximum power point.

[0003] For example, the invention patent announcement with announcement number: CN107992154B discloses a maximum power point tracking method and device, which includes: monitoring the output power and PV voltage of the solar panel according to a set frequency; calculating the PV voltage adjustment step base according to the monitored output power and PV voltage of the solar panel; adjusting the MPPT count value according to the output power of the current solar cell, the output power detected last time, and a preset minimum power adjustment value; adjusting the PV reference voltage based on the adjustment step base according to the comparison result between the adjusted MPPT count value and the set MPPT reference value; and using the PV reference voltage as the control target of the subsequent power circuit.

[0004] For example, the invention patent announcement with announcement number: CN115686124B discloses a self-regulating system and method for energy storage battery output power based on safety protection, including: self-regulating the output power of the energy storage battery according to the output power of the energy storage battery and the load equipment at the historical node, and obtaining the loss trend value of the load equipment by measuring the combined samples. Then, the corresponding verification sample is selected by the verification module, and the loss trend value is verified, so as to obtain the loss trend value that can be used as an adjustment indicator for adjusting the energy storage battery, and based on the loss trend value, the output power of the energy storage battery that needs to be adjusted at the current node can be calculated.

[0005] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0006] The production process of perovskite solar cells involves multiple steps, such as material preparation (including but not limited to spin coating, knife coating, spray coating and evaporation), thin film deposition (such as through thermal annealing and laser annealing), device assembly and packaging. Slight changes in each step will affect the output power of the final battery.

[0007] In addition, the output power fluctuations of perovskite solar cells are usually related to a variety of factors. Differences in the optoelectronic properties of perovskite materials will directly affect the photovoltaic conversion efficiency of the cell, which in turn causes fluctuations in the output power, because the photovoltaic conversion efficiency is derived from the input power and output power of the cell. At the same time, perovskite materials are highly photoelectrically active and are very sensitive to small changes in the production process, especially differences in photovoltaic conversion efficiency, electron mobility, and light absorption capacity. Process variables in the production process affect the quality of the perovskite layer, resulting in output power fluctuations, which in turn affects the accuracy of output power fluctuation monitoring during the perovskite solar cell production process. There is a problem that the output power fluctuation monitoring during the perovskite solar cell production process is not sufficiently correlated with the differences in the optoelectronic properties of perovskite materials. Summary of the Invention

[0008] The embodiments of the present application provide a method for monitoring the output power of a perovskite solar cell based on data analysis, thereby solving the problem in the prior art of insufficient correlation between the monitoring of output power fluctuations during the production process of a perovskite solar cell and the differences in the photoelectric properties of the perovskite material, and achieving more accurate monitoring of the output power fluctuations during the production process of a perovskite solar cell.

[0009] The embodiment of the present application provides a method for monitoring the output power of a perovskite solar cell based on data analysis, comprising the following steps: detecting and judging the photoelectric performance of a preset batch of perovskite materials based on acquired photoelectric characteristic detection data, obtaining a perovskite material detection result, the photoelectric characteristic detection data being used to describe the optical characteristic quantified data and electrical characteristic quantified data associated with the output power fluctuation of the perovskite solar cell in the preset batch of perovskite materials, the perovskite material detection result being used to determine and divide the photoelectric performance detection of the preset batch of perovskite materials to obtain an optical detection result and an electrical detection result; judging whether to send an output power monitoring instruction based on the perovskite material detection result, and if so, monitoring the output power of the preset batch of perovskite solar cells and obtaining monitoring-related data, and monitoring the preset batch of perovskite solar cells based on the acquired monitoring-related data. The degree to which the output power fluctuation of the titanium ore solar cell is affected by the difference in the photoelectric properties of the perovskite material is evaluated to obtain the output power monitoring result. Otherwise, a perovskite material detection marking instruction is sent and a marking monitoring prompt is prompted. The monitoring-related data represents the quantitative data of the output power fluctuation of the preset batch of perovskite solar cells. The output power monitoring results include qualified output power monitoring and unqualified output power monitoring. Based on the obtained output power monitoring result, it is determined whether to perform output power monitoring compensation adjustment. If performed, an output power monitoring compensation adjustment instruction is sent, otherwise an output power continuous monitoring instruction is sent. The output power monitoring compensation adjustment is used to compensate and adjust the physical quantity with the characteristic of reducing the influence of the output power fluctuation of the perovskite solar cell on the difference in the photoelectric properties of the perovskite material in the process of the preset batch of perovskite solar cells.

[0010] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0011] 1. The photoelectric properties of a preset batch of perovskite materials are detected and determined through photoelectric characteristic detection data to obtain the perovskite material detection results. Then, the output power monitoring instruction is determined based on the perovskite material detection results, thereby realizing the correlation analysis between the output power fluctuation monitoring and the photoelectric characteristic difference of the perovskite material during the production process of the perovskite solar cell. Finally, based on the output power monitoring results, it is determined whether to perform output power monitoring compensation adjustment, thereby effectively reducing the influence of the output power fluctuation of the perovskite solar cell on the photoelectric characteristic difference of the perovskite material, thereby realizing more accurate output power fluctuation monitoring during the production process of the perovskite solar cell, and effectively solving the problem in the prior art that the output power fluctuation monitoring during the production process of the perovskite solar cell is insufficiently correlated with the photoelectric characteristic difference of the perovskite material.

[0012] 2. By combining the perovskite material test results to determine whether to send an output power monitoring instruction, effective judgment of the output power monitoring of perovskite solar cells is achieved. If the perovskite material test results correspond to optical detection abnormalities or electrical detection abnormalities, the output power monitoring instruction will not be sent. Otherwise, the output power monitoring instruction will be sent and a prompt will be given to perform marking monitoring, thereby improving the accuracy and reliability of the photoelectric performance detection and judgment of perovskite materials in the perovskite solar cell production process.

[0013] 3. By monitoring the correlation data and the photoelectric difference influencing factor, the degree to which the output power fluctuation of the preset batch of perovskite solar cells is affected by the difference in the photoelectric properties of the perovskite material is quantitatively evaluated, and the photoelectric difference-output power impact value is obtained, thereby realizing the correlation analysis between the output power fluctuation of the perovskite solar cell and the difference in the photoelectric properties of the perovskite material. Then, it is judged whether the photoelectric difference-output power impact value is within the preset influence allowable range to obtain the output power monitoring result, thereby realizing the improvement of the reliability of the assessment of the degree to which the output power fluctuation of the preset batch of perovskite solar cells is affected by the difference in the photoelectric properties of the perovskite material. Finally, it is judged whether to perform output power monitoring compensation adjustment, thereby effectively reducing the influence of the difference in the photoelectric properties of the perovskite material on the output power fluctuation monitoring in the output power monitoring of the perovskite solar cell. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A logic diagram of a method for monitoring the output power of a perovskite solar cell based on data analysis provided in an embodiment of the present application;

[0015] Figure 2 A flow chart of a method for monitoring the output power of a perovskite solar cell based on data analysis provided in an embodiment of the present application;

[0016] Figure 3 This is a logic diagram for judging the output power monitoring results of the perovskite solar cell output power monitoring method based on data analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The embodiments of the present application provide a perovskite solar cell output power monitoring method based on data analysis, which solves the problem in the prior art that the output power fluctuation monitoring during the perovskite solar cell production process is not sufficiently correlated with the photoelectric property differences of the perovskite material. The photoelectric properties of a preset batch of perovskite materials are detected and determined based on the acquired photoelectric property detection data to obtain a perovskite material detection result. Then, based on the perovskite material detection result, it is determined whether to send an output power monitoring instruction. If sent, the output power of the preset batch of perovskite solar cells is monitored and monitoring-related data is obtained. Based on the acquired monitoring-related data, the degree to which the output power fluctuation of the preset batch of perovskite solar cells is affected by the photoelectric property differences of the perovskite material is evaluated to obtain an output power monitoring result. Otherwise, a perovskite material detection marking instruction is sent and a marking monitoring prompt is prompted. Finally, based on the acquired output power monitoring result, it is determined whether to perform output power monitoring compensation adjustment. If performed, an output power monitoring compensation adjustment instruction is sent; otherwise, an output power continuous monitoring instruction is sent, thereby achieving more accurate output power fluctuation monitoring during the perovskite solar cell production process.

[0018] The technical solution in the embodiment of the present application is to solve the problem that the output power fluctuation monitoring in the above-mentioned perovskite solar cell production process is not sufficiently correlated with the difference in the photoelectric properties of the perovskite material. The overall idea is as follows:

[0019] By testing and judging the photoelectric properties of a preset batch of perovskite materials to obtain the perovskite material test results, then determining whether to send an output power monitoring instruction, and finally determining whether to perform output power monitoring compensation adjustment based on the output power monitoring results, more accurate output power fluctuation monitoring during the perovskite solar cell production process is achieved.

[0020] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0021] like Figure 1As shown, a logic diagram of a perovskite solar cell output power monitoring method based on data analysis provided in an embodiment of the present application is provided. The corresponding logic is: obtaining an average relative deviation of photoelectric characteristic detection based on photoelectric characteristic detection data, and obtaining a perovskite material detection result based on the average relative deviation of photoelectric characteristic detection. When the perovskite material detection result corresponds to an optical detection abnormality or an electrical detection abnormality, the output power monitoring instruction is not sent, and a perovskite material detection marking instruction is sent. Otherwise, an output power monitoring instruction is sent to monitor the output power of a preset batch of perovskite solar cells and obtain monitoring-related data, and a prompt is given to perform marking monitoring. Based on the obtained monitoring-related data, the degree to which the output power fluctuation of the preset batch of perovskite solar cells is affected by the difference in the photoelectric characteristics of the perovskite material is evaluated to obtain an output power monitoring result. The output power monitoring result includes qualified output power monitoring and unqualified output power monitoring. If the output power monitoring result is qualified, the output power monitoring compensation adjustment is not performed, and an output power continuous monitoring instruction is sent. If the output power monitoring result is unqualified, the output power monitoring compensation adjustment is performed. The output power monitoring compensation adjustment includes annealing process compensation adjustment and evaporation process compensation adjustment.

[0022] Perovskite solar cells, an emerging photovoltaic technology, have attracted widespread attention due to their advantages over traditional silicon-based solar cells, such as low cost, light weight, and flexibility. However, the production process of perovskite solar cells still suffers from instability, leading to output power fluctuations. Relying solely on post-production efficiency testing cannot promptly identify problems during the production process, making real-time monitoring of output power fluctuations particularly important.

[0023] like Figure 2As shown, it is a flow chart of a method for monitoring the output power of a perovskite solar cell based on data analysis provided in an embodiment of the present application, the method comprising the following steps: detecting and judging the photoelectric properties of a preset batch of perovskite materials based on the acquired photoelectric characteristic detection data, and obtaining the perovskite material detection results, the perovskite material detection results including optical detection results and electrical detection results; obtaining the perovskite material detection results by judging the average relative deviation of the optical detection and the average relative deviation of the electrical detection item by item, thereby achieving an improvement in the accuracy of the detection, judgment and classification of the photoelectric properties of the preset batch of perovskite materials. The photoelectric characteristic detection data is used to describe the optical characteristic quantitative data and electrical characteristic quantitative data associated with the output power fluctuation of the perovskite solar cell in the preset batch of perovskite materials. The perovskite material detection results are used to judge and divide the photoelectric performance detection of the preset batch of perovskite materials to obtain optical detection results and electrical detection results. The optical detection results include optical detection qualified and optical detection abnormal, and the electrical detection results include electrical detection qualified and electrical detection abnormal. Combined with the perovskite material detection results, it is determined whether to send an output power monitoring instruction. If sent, the output power of the preset batch of perovskite solar cells is monitored and monitoring-related data is obtained. Based on the obtained monitoring-related data, the output power fluctuation of the preset batch of perovskite solar cells is evaluated by the difference in the photoelectric characteristics of the perovskite material to obtain the output power monitoring result. The output power monitoring result includes output power monitoring qualified and output power monitoring unqualified. Otherwise, the perovskite material detection instruction is sent. The marking instruction is prompted to mark the monitoring. The monitoring-related data represents the quantitative data of the output power fluctuation of the preset batch of perovskite solar cells. The monitoring-related data includes the output power monitoring value and the average monitored output power. Specifically, the output power monitoring value is obtained by a power sensor deployed at the output end of the perovskite solar cell, and the obtained output power monitoring value is statistically analyzed by the AVERAGE function in EXCEL to obtain the average monitored output power; the output power monitoring result includes the output power monitoring qualified and the output power monitoring unqualified; based on the obtained output power monitoring result, it is determined whether to perform output power monitoring compensation adjustment. If it is performed, an output power monitoring compensation adjustment instruction is sent, otherwise an output power continuous monitoring instruction is sent. The output power monitoring compensation adjustment is used to compensate and adjust the physical quantity with the characteristic of reducing the output power fluctuation of the perovskite solar cell affected by the difference in the photoelectric properties of the perovskite material in the process of the preset batch of perovskite solar cells.

[0024] The present application effectively reduces the degree to which the output power fluctuation monitoring during the production process of perovskite solar cells is affected by the photoelectric properties differences of perovskite materials by correlating the monitoring of output power fluctuations during the production process of perovskite solar cells with the differences in the photoelectric properties of perovskite materials, thereby effectively improving the accuracy of the output power fluctuation monitoring during the production process of perovskite solar cells.

[0025] As a further solution, the photoelectric properties of a preset batch of perovskite materials are tested and determined based on the acquired photoelectric characteristic test data. The specific steps are as follows:

[0026] First, obtain the photoelectric characteristic test data of a preset batch of perovskite materials after a preset number of tests. The photoelectric characteristic test data includes optical characteristic test data and electrical characteristic test data. The optical characteristic test data includes spectral emissivity, spectral transmittance and optical band gap, which are specifically obtained by an infrared spectrometer, a spectrophotometer and an optical absorption spectrum analyzer deployed in the perovskite material detection area on the production line. The electrical characteristic test data includes material conductivity, material resistivity and carrier concentration, which are specifically obtained by a four-probe tester deployed in the perovskite material detection area on the production line to obtain material conductivity and material resistivity, and by a Hall effect tester deployed in the perovskite material detection area on the production line to obtain carrier concentration.

[0027] Secondly, the average relative deviation of photoelectric characteristic detection is obtained based on the photoelectric characteristic detection data, including the average relative deviation of optical detection and the average relative deviation of electrical detection. The average relative deviation of optical detection includes the average relative deviation of spectral emissivity, the average relative deviation of spectral transmittance, and the average relative deviation of optical band gap. The average relative deviation of electrical detection includes the average relative deviation of material conductivity, the average relative deviation of material resistivity, and the average relative deviation of carrier concentration. The average relative deviation of optical detection represents the result of averaging the relative deviations of optical detection for a preset number of detections. Specifically, the optical detection relative deviation represents the result of performing a ratio analysis between the absolute value of the difference between the optical characteristic detection threshold and the corresponding optical characteristic detection data and the corresponding optical characteristic detection threshold; the average relative deviation of electrical detection represents the result of averaging the relative deviations of electrical detection for a preset number of detections. Specifically, the electrical detection relative deviation represents the result of performing a ratio analysis between the absolute value of the difference between the electrical characteristic detection threshold and the corresponding electrical characteristic detection data and the corresponding electrical characteristic detection threshold; both the optical characteristic detection threshold and the electrical characteristic detection threshold are set by professionals according to standards in the field. For example, the optical characteristic detection threshold and the electrical characteristic detection threshold are set as the corresponding average results of the historical optical characteristic detection data and the electrical characteristic detection threshold collected item by item.

[0028] In this embodiment, the average relative deviation of the photoelectric characteristic detection is obtained by obtaining the photoelectric characteristic detection data, thereby improving the data reliability in the photoelectric performance detection of a preset batch of perovskite materials, and further improving the accuracy of the photoelectric performance detection of perovskite materials in the perovskite solar cell production process.

[0029] As a further solution, the perovskite material test results are obtained and combined with the perovskite material test results to determine whether to send an output power monitoring instruction. The specific process is as follows:

[0030] First, determine item by item whether the corresponding items in the average relative deviation of optical detection are all within the corresponding allowable range of optical detection deviation obtained from the preset database. If so, the corresponding optical detection result will be recorded as qualified optical detection; otherwise, the corresponding optical detection result will be recorded as abnormal optical detection; among which, the allowable range of optical detection deviation corresponding to each item in the average relative deviation of optical detection is set by professionals according to standards in the field.

[0031] Secondly, determine item by item whether the corresponding items in the average relative deviation of the electrical test are all within the corresponding allowable range of the electrical test deviation obtained from the preset database. If so, the corresponding electrical test result will be recorded as a qualified electrical test; otherwise, the corresponding electrical test result will be recorded as an abnormal electrical test; among which, the allowable range of the electrical test deviation corresponding to each item in the average relative deviation of the electrical test is set by professionals according to the standards in the field.

[0032] In addition, the system determines whether the perovskite material test results correspond to optical or electrical test abnormalities. If so, the system does not send an output power monitoring instruction, but instead sends a perovskite material test marking instruction for marking a preset batch of perovskite materials as a batch with photoelectric test abnormalities. Otherwise, the system sends an output power monitoring instruction to monitor the output power of the preset batch of perovskite solar cells, obtain monitoring-related data, and prompt the user to perform marking monitoring.

[0033] Specifically, the specific process of labeling monitoring is as follows:

[0034] A1, determine whether the perovskite material test results correspond to qualified optical testing and qualified electrical testing. If so, mark the preset batch of perovskite materials as a qualified batch for photoelectric testing, and monitor and sample the output power of the preset qualified batch of perovskite solar cells for photoelectric testing according to the initial monitoring frequency to obtain monitoring-related data. Otherwise, execute A2; wherein, the initial monitoring frequency is set by professionals according to standards in the field.

[0035] A2, determine whether the perovskite material test results correspond to optical detection abnormalities and electrical detection qualified. If so, mark the preset batch of perovskite materials as an optical detection abnormality batch, and monitor and sample the output power of the preset optical detection abnormality batch of perovskite solar cells according to the optical monitoring frequency to obtain monitoring related data. Otherwise, execute A3, the optical monitoring frequency is the sum of the initial monitoring frequency and the optical monitoring frequency adjustment value, and the optical monitoring frequency adjustment value is the result of mapping from the preset database after weighted coupling of the optical detection average relative deviation; the weight in the weighted coupling is set in advance by the preset personnel and stored in the preset database, which is used to describe the degree of influence of the optical detection average relative deviation on the optical monitoring frequency adjustment value; in addition, a mapping relationship between the result of weighted coupling of the optical detection average relative deviation and the optical monitoring frequency adjustment value has been established in the preset database.

[0036] A3. Mark a preset batch of perovskite materials as an abnormal electrical detection batch, and monitor and sample the output power of the perovskite solar cells in the preset abnormal electrical detection batch according to the electrical monitoring frequency to obtain monitoring-related data. The electrical monitoring frequency is the sum of the initial monitoring frequency and the electrical monitoring frequency adjustment value. The electrical monitoring frequency adjustment value is the result of weighted coupling of the average relative deviation of electrical detection mapped from a preset database. The weights in the weighted coupling are set in advance by the preset personnel and stored in the preset database to describe the degree of influence of the average relative deviation of electrical detection on the electrical monitoring frequency adjustment value. In addition, a mapping relationship between the result of weighted coupling of the average relative deviation of electrical detection and the electrical monitoring frequency adjustment value has been established in the preset database.

[0037] In this embodiment, by judging whether the perovskite material detection result corresponds to an optical detection abnormality or an electrical detection abnormality to execute whether to send an output power monitoring instruction, and performing mark monitoring when sending the output power monitoring instruction, differentiated processing of the photoelectric characteristics of the perovskite material in the output power monitoring of the perovskite solar cell is achieved, thereby achieving improved accuracy in monitoring output power fluctuations in the production process of the perovskite solar cell.

[0038] As a further approach, the degree to which the output power fluctuation of a preset batch of perovskite solar cells is affected by the differences in the optoelectronic properties of the perovskite material is evaluated based on the acquired monitoring correlation data. The specific steps are as follows:

[0039] M1, combined with monitoring-related data, quantitatively evaluates the degree to which the output power fluctuation of a preset batch of perovskite solar cells is affected by the differences in the photoelectric properties of the perovskite material, and obtains the photoelectric difference-output power impact value.

[0040] Specifically, the specific process for obtaining the photoelectric difference-output power impact value is as follows:

[0041] M11, the result of harmonic average of the optical difference impact score and the electrical difference impact score is used as the photoelectric difference impact factor, that is, Y in the photoelectric difference-output power impact value a . The optical difference impact score is the result of the weighted coupling corresponding to the average relative deviation of optical detection. The weights in the weighted coupling are set in advance by the preset personnel and stored in the preset database. It is used to describe the degree of influence of the average relative deviation of optical detection on the optical difference impact score. The electrical difference impact score is the result of the weighted coupling corresponding to the average relative deviation of electrical detection. The weights in the weighted coupling are set in advance by the preset personnel and stored in the preset database. It is used to describe the degree of influence of the average relative deviation of electrical detection on the electrical difference impact score.

[0042] M12, the photoelectric difference impact factor and the output power monitoring value difference processing result are processed by parameter interaction to obtain the photoelectric difference-output power impact value. The numerical expression of the photoelectric difference-output power impact value is as follows:

[0043] ;

[0044] Where, Indicates the photoelectric difference-output power impact value, represents the photoelectric difference impact factor, n represents the monitoring time within the preset monitoring period, , N represents the total number of monitoring moments in the preset monitoring period, It represents the output power monitoring value at the nth monitoring moment within the preset monitoring period, and P represents the average monitored output power within the preset monitoring period.

[0045] It should be added that the parameter interaction processing is used to describe the interaction between the photoelectric difference influencing factor and the output power monitoring value difference processing result; the output power monitoring value difference processing result is the photoelectric difference - output power influence value. part.

[0046] It should be understood that the photoelectric difference-output power impact value represents the quantitative data of the monitoring correlation data and the photoelectric difference impact factor on the degree to which the output power fluctuation of a preset batch of perovskite solar cells is affected by the difference in the photoelectric properties of the perovskite material, and is used to quantitatively evaluate the degree to which the output power fluctuation of a preset batch of perovskite solar cells is affected by the difference in the photoelectric properties of the perovskite material; specifically, the photoelectric difference-output power impact value includes parameters in multiple aspects, for example, the photoelectric difference impact factor is the result of the harmonic average of the optical difference impact score and the electrical difference impact score, and as the optical difference impact score and the electrical difference impact score increase, the photoelectric difference impact factor increases accordingly; at the same time, the optical difference impact score and the electrical difference impact score are the results of the weighted coupling corresponding to the average relative deviation of optical detection and the average relative deviation of electrical detection, respectively, where the spectral emissivity reflects the radiation ability of the perovskite material in different wavelength ranges, and the spectral transmittance reflects the material's transmittance to light of different wavelengths. force, the optical band gap describes the ability of the perovskite material to absorb photons; with the increase of the optical difference influence score, the photoelectric difference influence factor increases accordingly, and the output power monitoring value difference processing result increases accordingly, indicating that the output power fluctuation of the perovskite solar cell is increasingly affected by the difference in the photoelectric properties of the perovskite material, and the photoelectric difference-output power influence value also increases accordingly; similarly, the material conductivity reflects the ability of the perovskite material to conduct current under the action of an electric field. With the increase of the electrical difference influence score, the photoelectric difference influence factor increases accordingly, the output power monitoring value difference processing result increases accordingly, and the photoelectric difference-output power influence value also increases accordingly. Therefore, through a quantitative method, the photoelectric difference-output power influence value is obtained based on the correlation and mutual influence relationship between the parameters, which realizes a more accurate judgment of the degree to which the output power fluctuation of the perovskite solar cell is affected by the difference in the photoelectric properties of the perovskite material, thereby achieving an improvement in the reliability of the output power fluctuation monitoring of the perovskite solar cell.

[0047] M2 compares the photoelectric difference-output power impact value with the preset impact allowable range obtained from the preset database to obtain the output power monitoring result. Specifically, the preset impact allowable range is set by professionals based on standards in the field.

[0048] like Figure 3As shown, a logic diagram for judging the output power monitoring result of the perovskite solar cell output power monitoring method based on data analysis provided in an embodiment of the present application is provided, and the corresponding logic is: judging whether the photoelectric difference-output power impact value is within the preset impact allowable range to obtain the output power monitoring result; if so, the output power monitoring result is that the output power monitoring is qualified, the output power monitoring compensation adjustment is not performed, and an output power continuous monitoring instruction is sent; otherwise, the output power monitoring result is that the output power monitoring is unqualified, and the output power monitoring compensation adjustment is performed. The output power monitoring compensation adjustment includes annealing process compensation adjustment and evaporation process compensation adjustment. The annealing process compensation adjustment indicates compensating and adjusting the annealing temperature and annealing time in the annealing process of a preset batch of perovskite solar cells; the evaporation process compensation adjustment indicates compensating and adjusting the evaporation temperature and evaporation rate in the evaporation process of a preset batch of perovskite solar cells.

[0049] As a further solution, the specific process of determining whether to perform output power monitoring compensation adjustment based on the obtained output power monitoring result is as follows:

[0050] N1. If the photoelectric difference-output power impact value is within the preset impact allowable range, the corresponding output power monitoring result will be recorded as qualified output power monitoring, the output power monitoring compensation adjustment will not be performed, and an output power continuous monitoring instruction will be sent. The output power continuous monitoring instruction is used to update the preset monitoring period to a monitoring adjustment period, and obtain monitoring-related data of a preset batch of perovskite solar cells within the monitoring adjustment period; wherein the monitoring adjustment period is the sum of the preset monitoring period length and the monitoring period adjustment length, and the monitoring period adjustment length represents the result of mapping the photoelectric difference-output power impact value from the preset database, and a mapping relationship between the photoelectric difference-output power impact value and the monitoring period adjustment length has been established in the preset database.

[0051] N2: If the photoelectric difference-output power impact value is not within the preset allowable impact range, the corresponding output power monitoring result is recorded as output power monitoring failure, and output power monitoring compensation adjustment is performed. Output power monitoring compensation adjustment includes annealing process compensation adjustment and evaporation process compensation adjustment. Annealing process compensation adjustment refers to compensating for the annealing temperature and annealing time during the annealing process of a preset batch of perovskite solar cells; evaporation process compensation adjustment refers to compensating for the evaporation temperature and evaporation rate during the evaporation process of a preset batch of perovskite solar cells.

[0052] Specifically, annealing process compensation adjustment includes annealing temperature compensation adjustment and annealing time compensation adjustment. Annealing temperature compensation adjustment refers to updating the annealing temperature in the annealing process of a preset batch of perovskite solar cells to the annealing adjustment temperature. The annealing adjustment temperature is the sum of the annealing temperature and the annealing temperature adjustment value. The annealing temperature adjustment linear regression mapping model outputs the corresponding annealing temperature adjustment value by inputting the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value. The annealing temperature adjustment linear regression mapping model is a pre-trained linear regression model used to fit the mapping relationship between the absolute deviation between the input photoelectric difference-output power impact value and the output power impact reference value and the annealing temperature adjustment value. The annealing temperature adjustment linear regression mapping model is obtained by inputting annealing adjustment temperature data into the linear regression model and training it using the scikit-learn framework based on the least squares method. The annealing adjustment temperature data includes the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value within a historical time period, as well as the annealing temperature adjustment value set by the preset staff based on the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value. The absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value represents the absolute value of the difference between the output power impact reference value and the photoelectric difference-output power impact value, and the result of calculating the percentage of the difference with the output power impact reference value. The output power impact reference value is the minimum value of the historical photoelectric difference-output power impact values.

[0053] Annealing time compensation adjustment refers to updating the annealing time in the annealing process of a preset batch of perovskite solar cells to the annealing adjustment time. The annealing adjustment time is the sum of the annealing time and the annealing time adjustment value. The absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value is input into the annealing time adjustment linear regression mapping model to output the corresponding annealing time adjustment value. The annealing time adjustment linear regression mapping model is a pre-trained linear regression model used to fit the mapping relationship between the absolute deviation between the input photoelectric difference-output power impact value and the output power impact reference value and the annealing time adjustment value. The annealing time adjustment linear regression mapping model is obtained by inputting annealing adjustment time data into the linear regression model and training it based on the least squares method using the scikit-learn framework. The annealing adjustment time data includes the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value within a historical time period, as well as the annealing time adjustment value set by the preset staff based on the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value. Among them, the annealing temperature and annealing time are set by professionals according to field standards and obtained through the integrated automated control system and data acquisition system on the production line.

[0054] In addition, the evaporation process compensation adjustment includes evaporation temperature compensation adjustment and evaporation rate compensation adjustment; wherein, the evaporation temperature compensation adjustment means updating the evaporation temperature in the evaporation process of a preset batch of perovskite solar cells to the evaporation adjustment temperature, and the evaporation adjustment temperature is the sum of the evaporation temperature and the evaporation temperature adjustment value. The absolute deviation between the input photoelectric difference-output power impact value and the output power impact reference value is input to the evaporation temperature adjustment linear regression mapping model to output the corresponding evaporation temperature adjustment value. The evaporation temperature adjustment linear regression mapping model is a pre-trained linear regression model for fitting the mapping relationship between the absolute deviation between the input photoelectric difference-output power impact value and the output power impact reference value and the evaporation temperature adjustment value. The evaporation temperature adjustment linear regression mapping model is obtained by inputting the evaporation adjustment temperature data into the linear regression model and training it through the scikit-learn framework based on the least squares method. The evaporation adjustment temperature data includes the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value in the historical time period, and the evaporation temperature adjustment value set by the preset staff according to the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value.

[0055] Evaporation rate compensation adjustment means updating the evaporation rate in the evaporation process of a preset batch of perovskite solar cells to an evaporation adjustment rate. The evaporation adjustment rate is the sum of the evaporation rate and the evaporation rate adjustment value. The absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value is input into the evaporation rate adjustment linear regression mapping model to output the corresponding evaporation rate adjustment value. The evaporation rate adjustment linear regression mapping model is a pre-trained linear regression model used to fit the mapping relationship between the absolute deviation between the input photoelectric difference-output power impact value and the output power impact reference value and the evaporation rate adjustment value. The evaporation rate adjustment linear regression mapping model is obtained by inputting evaporation adjustment rate data into the linear regression model and training it based on the least squares method using the scikit-learn framework. The evaporation adjustment rate data includes the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value within a historical time period, as well as the evaporation rate adjustment value set by the preset staff based on the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value. Among them, the evaporation temperature and evaporation rate are set by professionals according to standards in the field and obtained through the integrated automation control system and data acquisition system on the production line.

[0056] In this embodiment, the output power monitoring result is obtained by judging the photoelectric difference-output power impact value, which realizes the quantitative judgment of the degree to which the output power fluctuation of the perovskite solar cell is affected by the difference in the photoelectric properties of the perovskite material, and judges whether to perform output power monitoring compensation adjustment based on the output power monitoring result, thereby realizing the correlation analysis and adjustment of the output power fluctuation monitoring and the photoelectric property difference of the perovskite material during the production process of the perovskite solar cell, thereby effectively reducing the influence of the photoelectric property difference of the perovskite material on the output power fluctuation monitoring in the output power monitoring of the perovskite solar cell.

[0057] In summary, the embodiment of the present application detects and determines the photoelectric properties of a preset batch of perovskite materials through photoelectric property detection data to obtain the perovskite material detection results, and then determines whether to send an output power monitoring instruction based on the perovskite material detection results, thereby realizing the correlation analysis between the output power fluctuation monitoring and the photoelectric property differences of the perovskite material during the perovskite solar cell production process, and finally, based on the output power monitoring results, determining whether to perform output power monitoring compensation adjustment, thereby effectively reducing the influence of the output power fluctuation of the perovskite solar cell on the photoelectric property differences of the perovskite material, thereby realizing more accurate output power fluctuation monitoring during the perovskite solar cell production process, and effectively solving the problem in the prior art of insufficient correlation between the output power fluctuation monitoring and the photoelectric property differences of the perovskite material during the perovskite solar cell production process.

[0058] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0059] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0060] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0061] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0062] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0063] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for monitoring the output power of a perovskite solar cell based on data analysis, characterized in that: The following steps are involved: Based on the acquired photoelectric characteristic test data, the photoelectric properties of a preset batch of perovskite materials are tested and determined, and a perovskite material test result is obtained, wherein the photoelectric characteristic test data is used to describe quantitative optical and electrical characteristic data associated with output power fluctuations of the perovskite solar cell in the preset batch of perovskite materials, and the perovskite material test result is used to determine and divide the photoelectric performance test of the preset batch of perovskite materials to obtain an optical test result and an electrical test result; Determine whether to send an output power monitoring instruction based on the perovskite material detection result; if so, monitor the output power of a preset batch of perovskite solar cells and obtain monitoring-related data; evaluate the degree to which the output power fluctuation of the preset batch of perovskite solar cells is affected by the differences in the photoelectric properties of the perovskite material based on the obtained monitoring-related data, and obtain an output power monitoring result; otherwise, send a perovskite material detection marking instruction and prompt for marking monitoring; the monitoring-related data represents quantitative data on the output power fluctuation of the preset batch of perovskite solar cells; the output power monitoring result includes output power monitoring qualified and output power monitoring unqualified; The specific steps of evaluating the degree to which the output power fluctuation of a preset batch of perovskite solar cells is affected by the difference in the photoelectric properties of the perovskite material based on the acquired monitoring correlation data are as follows: Acquire monitoring correlation data of a preset batch of perovskite solar cells within a preset monitoring period, and quantitatively evaluate the degree to which output power fluctuations of the preset batch of perovskite solar cells are affected by differences in the photoelectric properties of the perovskite material based on the monitoring correlation data, thereby obtaining a photoelectric difference-output power impact value; The numerical expression of the photoelectric difference-output power impact value is as follows: ； Where DP represents the photoelectric difference-output power impact value, Y a represents the photoelectric difference impact factor, n represents the monitoring time within the preset monitoring period, , N represents the total number of monitoring moments in the preset monitoring period, P n Indicates the output power monitoring value at the nth monitoring moment within the preset monitoring period, and P represents the average monitored output power within the preset monitoring period; Based on the obtained output power monitoring results, it is determined whether to execute output power monitoring compensation adjustment. If executed, an output power monitoring compensation adjustment instruction is sent, otherwise an output power continuous monitoring instruction is sent. The output power monitoring compensation adjustment is used to compensate and adjust the physical quantity with the characteristic of reducing the output power fluctuation of the perovskite solar cell affected by the difference in the photoelectric properties of the perovskite material in the process of a preset batch of perovskite solar cells.

2. The method for monitoring the output power of a perovskite solar cell based on data analysis according to claim 1, wherein: The specific steps of detecting and judging the photoelectric performance of a preset batch of perovskite materials based on the acquired photoelectric characteristic detection data are as follows: Obtaining photoelectric characteristic test data of a preset batch of perovskite materials after a preset number of tests, the photoelectric characteristic test data including optical characteristic test data and electrical characteristic test data, the optical characteristic test data including spectral emissivity, spectral transmittance, and optical band gap, and the electrical characteristic test data including material conductivity, material resistivity, and carrier concentration; Obtaining an average relative deviation of photoelectric characteristic detection according to the photoelectric characteristic detection data, wherein the average relative deviation of photoelectric characteristic detection includes an average relative deviation of optical detection and an average relative deviation of electrical detection; The optical detection average relative deviation represents the result of averaging the optical detection relative deviations of a preset number of detections, and the electrical detection average relative deviation represents the result of averaging the electrical detection relative deviations of a preset number of detections; The optical detection average relative deviation includes the spectral emissivity average relative deviation, the spectral transmittance average relative deviation and the optical band gap average relative deviation, and the electrical detection average relative deviation includes the material conductivity average relative deviation, the material resistivity average relative deviation and the carrier concentration average relative deviation.

3. The method for monitoring the output power of a perovskite solar cell based on data analysis according to claim 2, wherein: The specific process of obtaining the perovskite material test results is as follows: Determine item by item whether the corresponding items in the average relative deviation of the optical inspection are all within the corresponding optical inspection deviation allowable range obtained from the preset database. If so, the corresponding optical inspection result is recorded as optical inspection qualified; otherwise, the corresponding optical inspection result is recorded as optical inspection abnormal; Determine item by item whether the corresponding items in the average relative deviation of the electrical test are all within the corresponding electrical test deviation allowable range obtained from the preset database. If so, the corresponding electrical test result is recorded as a qualified electrical test; otherwise, the corresponding electrical test result is recorded as an abnormal electrical test; The perovskite material detection results include optical detection results and electrical detection results.

4. The method for monitoring the output power of a perovskite solar cell based on data analysis according to claim 2, wherein: The specific process of judging whether to send an output power monitoring instruction based on the perovskite material detection result is as follows: Determine whether the perovskite material test result corresponds to an optical test abnormality or an electrical test abnormality. If so, do not send the output power monitoring instruction, and send a perovskite material test marking instruction for marking a preset batch of perovskite materials as a photoelectric test abnormality batch; Otherwise, an output power monitoring instruction is sent to monitor the output power of a preset batch of perovskite solar cells and obtain monitoring-related data, and a prompt is given to mark the monitoring.

5. The method for monitoring the output power of a perovskite solar cell based on data analysis according to claim 4, wherein: The specific process of labeling monitoring is as follows: A1, determining whether the perovskite material test results correspond to passing the optical test and passing the electrical test. If so, marking the preset batch of perovskite materials as a photoelectric test-qualified batch, and monitoring and sampling the output power of the preset photoelectric test-qualified batch of perovskite solar cells according to the initial monitoring frequency to obtain monitoring-related data; otherwise, executing A2; A2, determining whether the perovskite material test results correspond to optical detection abnormalities and electrical detection qualified. If so, marking a preset batch of perovskite materials as an optical detection abnormality batch, and monitoring and sampling the output power of the preset optical detection abnormality batch of perovskite solar cells according to the optical monitoring frequency to obtain monitoring-related data; otherwise, executing A3, the optical monitoring frequency is the sum of the initial monitoring frequency and the optical monitoring frequency adjustment value, and the optical monitoring frequency adjustment value is the result of mapping from a preset database after weighted coupling of the optical detection average relative deviation; A3, marking a preset batch of perovskite materials as an electrical detection abnormal batch, and monitoring and sampling the output power of the preset electrical detection abnormal batch of perovskite solar cells according to the electrical monitoring frequency to obtain monitoring related data.

6. The method for monitoring the output power of a perovskite solar cell based on data analysis according to claim 5, wherein: The step of evaluating the degree to which the output power fluctuation of a preset batch of perovskite solar cells is affected by the difference in the photoelectric properties of the perovskite material based on the acquired monitoring correlation data further includes: The monitoring-related data includes the output power monitoring value and the average monitored output power. The photoelectric difference-output power impact value is used to quantitatively evaluate the degree to which the output power fluctuation of a preset batch of perovskite solar cells is affected by the difference in the photoelectric properties of the perovskite material; The photoelectric difference-output power impact value is compared with the preset impact allowable range obtained from the preset database to obtain an output power monitoring result, which includes output power monitoring qualified and output power monitoring unqualified.

7. The method for monitoring the output power of a perovskite solar cell based on data analysis according to claim 6, wherein: The specific process of obtaining the photoelectric difference-output power impact value is as follows: The result of harmonic averaging of the optical difference influence score and the electrical difference influence score is used as the photoelectric difference influence factor, wherein the optical difference influence score is the result of weighted coupling corresponding to the average relative deviation of optical detection, and the electrical difference influence score is the result of weighted coupling corresponding to the average relative deviation of electrical detection; Performing parameter interaction processing on the photoelectric difference impact factor and the output power monitoring value difference processing result to obtain the photoelectric difference-output power impact value, wherein the parameter interaction processing is used to describe the interaction between the photoelectric difference impact factor and the output power monitoring value difference processing result; The photoelectric difference-output power impact value represents the quantitative data of the degree to which the output power fluctuation of a preset batch of perovskite solar cells is affected by the differences in the photoelectric properties of the perovskite material, based on the monitoring correlation data and the photoelectric difference impact factor.

8. The method for monitoring the output power of a perovskite solar cell based on data analysis according to claim 6, wherein: The specific process of determining whether to perform output power monitoring compensation adjustment based on the obtained output power monitoring result is as follows: If the photoelectric difference-output power impact value is within the preset allowable impact range, the corresponding output power monitoring result is recorded as qualified output power monitoring, the output power monitoring compensation adjustment is not performed, and an output power continuous monitoring instruction is sent. The output power continuous monitoring instruction is used to update the preset monitoring period to the monitoring adjustment period and obtain monitoring-related data of the preset batch of perovskite solar cells within the monitoring adjustment period; If the photoelectric difference-output power impact value is not within the preset allowable impact range, the corresponding output power monitoring result is recorded as output power monitoring failure, and output power monitoring compensation adjustment is performed, and the output power monitoring compensation adjustment includes annealing process compensation adjustment and evaporation process compensation adjustment; The annealing process compensation adjustment refers to compensating and adjusting the annealing temperature and annealing time during the annealing process of a preset batch of perovskite solar cells; The evaporation process compensation adjustment refers to compensating and adjusting the evaporation temperature and evaporation rate during the evaporation process of a preset batch of perovskite solar cells.

9. The method for monitoring the output power of a perovskite solar cell based on data analysis according to claim 8, wherein: The annealing process compensation adjustment includes annealing temperature compensation adjustment and annealing time compensation adjustment; The annealing temperature compensation adjustment means updating the annealing temperature in the annealing process of a preset batch of perovskite solar cells to the annealing adjustment temperature, wherein the annealing adjustment temperature is the sum of the annealing temperature and the annealing temperature adjustment value, and the annealing temperature adjustment value is the result of inputting the absolute deviation of the photoelectric difference-output power impact value and the output power impact reference value into the annealing temperature adjustment linear regression mapping model; The annealing time compensation adjustment means updating the annealing time in the annealing process of a preset batch of perovskite solar cells to the annealing adjustment time, where the annealing adjustment time is the sum of the annealing time and the annealing time adjustment value, and the annealing time adjustment value is the result of inputting the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value into the annealing time adjustment linear regression mapping model.

10. The method for monitoring the output power of a perovskite solar cell based on data analysis according to claim 8, wherein: The evaporation process compensation adjustment includes evaporation temperature compensation adjustment and evaporation rate compensation adjustment; The evaporation temperature compensation adjustment means updating the evaporation temperature in the evaporation process of a preset batch of perovskite solar cells to the evaporation adjustment temperature, wherein the evaporation adjustment temperature is the sum of the evaporation temperature and the evaporation temperature adjustment value, and the evaporation temperature adjustment value is the result output by inputting the absolute deviation of the photoelectric difference-output power impact value and the output power impact reference value into the evaporation temperature adjustment linear regression mapping model; The evaporation rate compensation adjustment means updating the evaporation rate in the evaporation process of a preset batch of perovskite solar cells to an evaporation adjustment rate, wherein the evaporation adjustment rate is the sum of the evaporation rate and the evaporation rate adjustment value, and the evaporation rate adjustment value is the result output by inputting the absolute deviation between the photoelectric difference-output power impact value and the output power impact reference value into the evaporation rate adjustment linear regression mapping model.

Images