Online defect detection method and system for main-grid-free photovoltaic cell panel

Abstract

The invention discloses an online defect detection method for a main-grid-free photovoltaic cell panel, which comprises the following steps of: obtaining a life distribution diagram of a main-grid-free photovoltaic cell through time-resolved photoluminescence, and obtaining a heat dissipation diagram of the main-grid-free photovoltaic cell through optically-induced phase-locked thermal imaging; an ultrasonic diagram of the main-grid-free photovoltaic cell is obtained through laser ultrasound; preprocessing and registering the life distribution diagram, the heat dissipation diagram and the ultrasonic diagram so as to uniformly map the life distribution diagram, the heat dissipation diagram and the ultrasonic diagram to a cell coordinate system, extracting minority carrier life, heat dissipation power, ultrasonic propagation time delay offset and scattering energy, and forming a multi-modal feature together with a thermal phase; and based on the abnormal score, performing defect detection and classification on the multi-modal features of the possible defect area to obtain classification results of electrical defects, thermal defects and mechanical defects. The invention also discloses a system for realizing the method. According to the invention, full-coverage detection of electrical, thermal and mechanical defects is realized.

Description

TECHNICAL FIELD

[0001] The application relates to a photovoltaic cell panel detection method and system, and belongs to the technical field of battery assembly detection. BACKGROUND

[0002] Under high-speed production lines and complex process conditions, a variety of defects are prone to occur in the manufacturing, interconnection and packaging processes of the main grid-free cell, including hidden cracks, local string resistance increase, fine grid fracture, back silver paste voids, surface contamination and interlayer debonding. These defects not only reduce the photoelectric conversion efficiency of the cell, but also may cause hot spot effect in long-term operation, accelerate performance degradation, and directly threaten the 25-30 year service life target of the photovoltaic module.

[0003] The commonly used detection methods at present mainly include electroluminescence (EL) and photoluminescence (PL) imaging. In the prior art, EL imaging can directly reveal structural defects such as hidden cracks, broken grids and PID, and is widely used in the factory and operation detection of module level and finished cell. The continuous EL testing scheme for different size modules proposed in the Chinese patent with the publication number CN113257696A measures the length of the module and automatically adjusts the position of the EL camera to improve the production line adaptability and testing efficiency. However, this method needs to be excited by electricity, and the detection efficiency is limited by the electrode contact condition, which is difficult to adapt to the main grid-free cell structure. In the US patent with the publication number US20120142125A1, a PL imaging system for a silicon photovoltaic cell production line is disclosed, which excites and images the PL emission by the above band gap light source, and spatially resolves the minority carrier lifetime, diffusion length, defective crystal structure or impurity distribution in the crystal. This scheme shows good effect in identifying microcracks, crystal defects and areas affecting the diffusion length. Although the PL method can reflect the material minority carrier lifetime and recombination defects to some extent, its results depend on the brightness information, are easily disturbed by light source stability, surface texture and environmental noise, and have insufficient detection capability for hidden cracks and subsurface defects.

[0004] In addition, single modality detection methods often cannot achieve full coverage of electrical, thermal and mechanical defects. For example, life attenuation type defects are more likely to be shown in PL, but microcracks are often difficult to identify by optical means; and ultrasonic detection is sensitive to cracks, but it is difficult to quantify the corresponding electrical loss. The existing detection technology has deficiencies in multi-modal fusion, defect quantitative evaluation and high-speed online adaptation. SUMMARY

[0005] In view of the defects in the prior art, the present application aims to provide an online defect detection method for a main-grid-free photovoltaic cell panel and an online defect detection system for a main-grid-free photovoltaic cell panel, so as to solve the problem that the prior art method is difficult to adapt to the main-grid-free photovoltaic cell panel and the single modal detection method is difficult to comprehensively cover possible defects, resulting in missed detection.

[0006] The technical scheme of the present application is as follows: an online defect detection method for a main-grid-free photovoltaic cell panel, comprising the steps of:

[0007] acquiring a lifetime distribution map of the main-grid-free photovoltaic cell piece through time-resolved photoluminescence, acquiring a thermal dissipation map of the main-grid-free photovoltaic cell piece through optical-induced phase-locked thermal imaging, and acquiring an ultrasonic wave map of the main-grid-free photovoltaic cell piece through laser ultrasonic, wherein the lifetime distribution map is composed of curves of luminescence intensity of each pixel decaying with time, the thermal dissipation map is composed of phase-locked temperature amplitudes and thermal phases of each pixel, and the ultrasonic wave map is composed of ultrasonic time-domain signals of each receiving point;

[0008] preprocessing and registering the lifetime distribution map, the phase-locked temperature amplitudes of the thermal dissipation map, and the ultrasonic wave map to unify mapping to a cell piece coordinate system;

[0009] extracting a minority carrier lifetime from the lifetime distribution map after preprocessing and registration, extracting a thermal dissipation power density from the phase-locked temperature amplitudes of the thermal dissipation map after preprocessing and registration, and extracting ultrasonic propagation time delay offset and scattering energy from the ultrasonic wave map after preprocessing and registration, wherein the minority carrier lifetime, the thermal dissipation power density, the thermal phase, the ultrasonic propagation time delay offset, and the scattering energy constitute multi-modal features;

[0010] calculating an anomaly score based on the minority carrier lifetime, the thermal dissipation power density, the ultrasonic propagation time delay offset, and the scattering energy, regarding a region with an anomaly score exceeding a set threshold as a possible abnormal region, and using a multi-modal attention convolutional neural network to detect and classify defects based on the multi-modal features of the possible abnormal region, so as to obtain classification results of electrical defects, thermal defects, and mechanical defects.

[0011] Further, the preprocessing includes normalizing and correcting the curve of luminescence intensity of the lifetime distribution map with time according to the following formula:

[0012] ,

[0013] In the formula, is the curve of luminescence intensity of the lifetime distribution map with time, is the corrected TRPL curve, is a dark field, is a flat field, is a time sample index;

[0014] The preprocessing includes band-pass filtering and standardizing the ultrasonic time-domain signal of the ultrasonogram according to the following formula:

[0015] ,

[0016] In the formula, is the ultrasonic time-domain signal of the ultrasonogram, is the band-pass filtered and standardized waveform, is a 0.2-2 MHz band-pass filtering operator, is the laser energy reading of each excitation.

[0017] Further, the registration is to map the phase-locked temperature amplitude of the lifetime distribution map and the heat dissipation map and the coordinates of the ultrasonogram to the battery piece coordinates, and then to resample the discrete points collected in the rolling to an equidistant grid according to the conveying encoder, so as to unify different modalities in time and space dimensions.

[0018] Further, the extraction of the minority carrier lifetime from the lifetime distribution map after preprocessing and registration is to estimate the minority carrier lifetime by using the first moment method, and the formula is:

[0019] , ,

[0020] In the formula, is the estimated minority carrier lifetime, is the curve of the decay of the luminescence intensity with time after preprocessing and registration;

[0021] The extraction of the heat dissipation power density from the phase-locked temperature amplitude of the heat dissipation map after preprocessing and registration is calculated according to the following formula:

[0022] , ,

[0023] In the formula, is the heat dissipation power density, is the phase-locked temperature amplitude after registration, is the background gray bias, is the gray-temperature conversion coefficient obtained by standardizing the standard heat source, is the thermal conductivity, is the thermal diffusivity, is the modulation angular frequency;

[0024] The calculation formula of the ultrasonic propagation time delay shift in the extraction of the ultrasonic propagation time delay shift and the scattering energy from the ultrasonogram after preprocessing and registration is:

[0025] , ,

[0026] wherein, is the ultrasonic propagation time delay offset (s), is the normalized waveform of the registered ultrasonic image, is the reference waveform of the defect-free baseline, is the correlation search displacement, is the reference arrival time, is the integration time;

[0027] The calculation formula of the scattering energy is:

[0028] ,

[0029] wherein is the scattering energy (relative dimension), is the upper and lower limits of the selected integration time window.

[0030] Further, the anomaly score is determined by the robust standardization of the minority carrier lifetime, the robust standardization of the heat dissipation power density, and the joint standardization of the ultrasonic propagation time delay offset and the scattering energy; the defect detection and classification of the multi-modal features of the possible abnormal area by the multi-modal attention convolutional neural network includes:

[0031] Convolutional feature extraction is performed on the minority carrier lifetime, the heat dissipation power density, the thermal phase, the ultrasonic propagation time delay offset, and the joint scattering energy; the convolutional feature extraction results of the heat dissipation power density and the thermal phase are convolutional mapping encoded and feature spliced in the channel dimension, and then fused to obtain a thermal feature map;

[0032] The convolutional feature extraction results of the minority carrier lifetime, the convolutional feature extraction results of the ultrasonic propagation time delay offset and the joint scattering energy, and the thermal feature map are input modalities of the multi-head attention, and the enhanced features output by the multi-head attention are aggregated to obtain a comprehensive feature tensor;

[0033] Based on the comprehensive feature tensor, a probability map of defect classification is output by a fully connected classification layer, and a defect area in the probability map of defect classification is determined by a set threshold to determine the classification results of the electrical defects, the thermal defects, and the mechanical defects.

[0034] Further, to realize the sorting and life prediction of the main grid-free photovoltaic cell panel, the method further includes the steps of: mapping the multi-modal features to the increments of the equivalent series resistance of the cell and the equivalent complex current density, calculating the effective power generation area loss based on the mechanical defect classification result, and estimating the power loss based on the increments of the equivalent series resistance, the equivalent complex current density, and the effective power generation area loss.

[0035] The scheme also realizes direct quantitative correlation of defect information and power generation performance loss through feature mapping, so that the detection result can be directly used for battery piece sorting and life prediction.

[0036] Further, the estimated power loss is a weighted sum of an increment of the equivalent series resistance, an increment of the equivalent complex current density and a loss of the effective generating area, and a weighting coefficient is obtained by numerical partial derivation of the diode model under a nominal working condition.

[0037] Further, the mapping relationship of the increment of the equivalent series resistance is:

[0038] ,

[0039] The mapping relationship of the increment of the equivalent complex current density is:

[0040] ,

[0041] In the formula, is the increment of the equivalent series resistance, , is a coefficient obtained by linear regression of the calibration sample, is a mean value of the robustly standardized heat dissipation power density, is the increment of the equivalent complex current density, , is a coefficient obtained by calibration, is a mean value of the robustly standardized minority carrier lifetime;

[0042] The loss of the effective generating area is a ratio of a mechanical defect area of the battery piece to a total area of the battery piece.

[0043] Another technical solution of the application is an online defect detection system for a main-grid-free photovoltaic cell panel, comprising:

[0044] A multi-modal signal acquisition unit is configured to acquire a lifetime distribution map of the main-grid-free photovoltaic cell piece through time-resolved photoluminescence, acquire a heat dissipation map of the main-grid-free photovoltaic cell piece through optical induced lock-in thermography, and acquire an ultrasonic wave map of the main-grid-free photovoltaic cell piece through laser ultrasonic, wherein the lifetime distribution map is composed of curves of light emission intensity of each pixel decaying with time, the heat dissipation map is composed of lock-in temperature amplitude and thermal phase of each pixel, and the ultrasonic wave map is composed of ultrasonic time domain signals of each receiving point;

[0045] A data preprocessing and registration unit is configured to preprocess and register the lifetime distribution map, the lock-in temperature amplitude of the heat dissipation map and the ultrasonic wave map to be uniformly mapped to a cell piece coordinate system;

[0046] The feature extraction unit is configured to extract a minority carrier lifetime from the pre-processed and registered lifetime map, extract a heat dissipation power density from a phase-locked temperature amplitude of the pre-processed and registered heat dissipation map, and extract an ultrasonic propagation time delay offset and scattering energy from the pre-processed and registered ultrasonic map, the minority carrier lifetime, the heat dissipation power density, the heat phase, the ultrasonic propagation time delay offset, and the scattering energy forming multi-modal features;

[0047] The fusion decision unit is configured to calculate an anomaly score based on the minority carrier lifetime, the heat dissipation power density, the ultrasonic propagation time delay offset, and the scattering energy, a region with an anomaly score exceeding a set threshold being a possible abnormal region, and to perform defect detection and classification on the multi-modal features of the possible abnormal region by using a multi-modal attention convolutional neural network to obtain a classification result of electrical defects, thermal defects, and mechanical defects.

[0048] Further, the power evaluation unit is configured to map the multi-modal features to an increment of an equivalent series resistance and an increment of an equivalent complex current density of the battery piece, calculate an effective power generation area loss based on the mechanical defect classification result, and estimate a power loss based on the increment of the equivalent series resistance, the increment of the equivalent complex current density, and the effective power generation area loss.

[0049] Compared with the prior art, the present application has the following advantages:

[0050] The present application provides an online defect detection method for a main-grid-free photovoltaic battery piece based on time-resolved photoluminescence (TRPL), optical-induced lock-in thermal imaging (OP-LIT), and laser ultrasound (LU). The TRPL captures the carrier lifetime decay process, quantitatively correlates the electrical performance and optical information, and realizes high-precision electrical diagnosis of recombination defects. The OP-LIT locates thermal power and phase anomalies, not only realizes quantitative identification of thermal defects such as hot spots and series resistance, but also provides direct thermal input for power loss quantification. The LU detects wave propagation delay and scattering energy, accurately identifies mechanical defects such as micro-cracks and debonding, effectively supplements the sub-surface defect detection that cannot be penetrated by optical means, and realizes comprehensive diagnosis from the surface to the inside.

[0051] Meanwhile, a multi-modal registration and cross-modal attention deep fusion framework is adopted to cooperatively model the electrical, thermal, and mechanical information in a unified coordinate system, realize accurate positioning and type discrimination of defects, and have high robustness in anti-noise, anti-light interference, and asynchronous sampling compared with a single-modal or simple splicing method. A joint decision mechanism of physical rules and network output is introduced to improve the model interpretability and discrimination robustness. In the preferred technical solution, the multi-modal features are mapped to equivalent parameters (such as the equivalent series resistance, the equivalent complex current density, and the effective power generation area loss) of the battery piece, and the power loss is estimated based on the equivalent parameters. 、 , ), to realize quantitative evaluation of the defect on power loss.

[0052] The present application adopts non-contact and online design, does not need physical probe and coupling medium, avoids any mechanical stress or damage to the battery piece. Full coverage detection and performance prediction of electrical, thermal and mechanical defects are realized, the present application can be embedded in high-speed production line without affecting the beat, and has strong industrial application value. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 The figure is a flowchart of the online defect detection method of the main grid-free photovoltaic cell panel of the embodiment.

[0054] Figure 2 The figure is a module schematic diagram of the online defect detection system of the main grid-free photovoltaic cell panel of the embodiment.

[0055] Figure 3 The figure is a schematic diagram of the relationship of each data in the online defect detection method of the main grid-free photovoltaic cell panel of the embodiment. DETAILED DESCRIPTION

[0056] The present application will be further described in combination with the embodiments, but is not limited to the present application.

[0057] Please refer to Figure 1 , Figure 3 , the online defect detection method of the main grid-free photovoltaic cell panel of the embodiment includes the following steps:

[0058] Step 1: Obtain the lifetime distribution map of the main grid-free photovoltaic cell piece through time-resolved photoluminescence, obtain the heat dissipation map of the main grid-free photovoltaic cell piece through optical induced phase-locked thermal imaging, and obtain the ultrasonic wave map of the main grid-free photovoltaic cell piece through laser ultrasonic.

[0059] Specifically, it includes step 1.1: using pulsed laser excitation (picosecond / nanosecond) to hit the cell piece, every time a pulse is hit, the pixel will emit light and gradually fade in the following tens of nanoseconds to tens of microseconds, then a high-speed camera is used to collect and record the curve of the light intensity decay over time, so that each pixel has a time curve. First, measure a standard scattering piece to obtain , then measure the sample to obtain , finally fit and , the calculation physical model is as follows:

[0060] ,

[0061] In the formula, is the curve of the light intensity decay over time observed by TRPL, is the sampling time (unit: s), is the instrument response function, is the amplitude of the mth exponential component, is the lifetime constant of the mth exponential component (unit: s), is the number of exponential components, is the background count. The formula is the physical model of instrument response convolution, where the multi-exponential decay term describes the minority carrier lifetime process, and the convolution term eliminates the influence of the instrument response function. The real lifetime decay, after the time blurring of the instrument, becomes the curve seen , which lays the foundation for subsequent lifetime estimation.

[0062] Step 1.2: Use a light source modulated at 20 Hz to irradiate the battery sheet to excite the battery sheet. If there is a current bypass, a large series resistance, or a micro-short circuit in the illuminated position, it will periodically heat up, so use an infrared camera to capture N frames of temperature maps in a period, and then substitute the N frames in the following formula to get the phase-locked temperature amplitude and thermal phase of each pixel. The formula for phase-locked demodulation calculation is as follows:

[0063] ,

[0064] ,

[0065] In the formula, is the phase-locked temperature amplitude, is the number of sampling frames in a modulation period, is the temperature disturbance value of the kth frame after radiance correction, is the sampling time of the kth frame, is the modulation angular frequency of the light source (rad / s), is the thermal phase. The formula extracts the amplitude and phase of the thermal response through Fourier components, , The two quantities can stably represent local heating, thereby realizing quantitative characterization of local hot spots and series resistance. Large amplitude can represent strong heating, and phase lag can infer thermal diffusion path and depth information.

[0066] Step 1.3: Use pulsed laser to excite elastic waves, which propagate in the sheet and deform or bypass when encountering cracks or debonding. Use LDV to receive waveforms at different points, and after Fourier transform, the frequency domain response becomes a time domain signal. The formula for synthesizing the time domain waveform is as follows:

[0067] ,

[0068] In the formula, is the time domain signal of the ultrasonic wave received at position , is the sensor coordinate position, It is the sampling time of the waveform signal in the time domain. This is the frequency domain response at that location. This formula converts the frequency domain response into a time domain signal to preserve the scattering characteristics of cracks and debonding defects.

[0069] Step 2: Preprocess and register the phase-locked temperature amplitude and ultrasonic waveform of the lifetime distribution map, heat dissipation map to uniformly map them to the cell coordinate system.

[0070] This step includes, step 2.1: Denoising and correcting the lifetime distribution map (the curve of luminescence intensity decaying over time) and the ultrasonic map (ultrasonic time-domain signal).

[0071] Specifically, for the curve of luminous intensity decaying over time, by acquiring a completely dark field and a uniformly bright flat field, the curves are linearly normalized using the following formula, thus achieving curve standardization. The calculation formula is as follows:

[0072] ,

[0073] In the formula, This is the corrected TRPL curve. Dark field, A draw. This is a time sample index.

[0074] For ultrasonic time-domain signals, the original waveform is passed through a bandpass filter and then divided by the laser energy reading to obtain a waveform on the same scale, ensuring the comparability of ultrasonic signals under different experimental conditions. The calculation formula is as follows:

[0075] ,

[0076] In the formula, The normalized waveform after bandpass filtering. It is a bandpass filter operator for 0.2–2 MHz. This represents the laser energy reading for each excitation.

[0077] Step 2.2: Cross-modal geometric registration to cell coordinates. First, take a picture of a calibration board with corner points, and use least squares to obtain the coordinates. The processed lifetime distribution map, heat dissipation map, and ultrasonic map are all projected onto the same plane coordinate system, that is, the coordinates of any modal image are mapped to the cell coordinates. The calculation formula is as follows:

[0078] ,

[0079] In the formula, It is the pixel position in the cell coordinate system. It is the pixel position in the original coordinates of the sensor.

[0080] Then, through encoder pulses, the discrete points collected during rolling are resampled to an equidistant grid by the transport encoder, so that different modes are unified in time and space dimensions. The calculation formula is as follows:

[0081] ,

[0082] In the formula, The original sequence is, that is , or ; Equidistant position index The resampled value on, that is, the corresponding value , or , The coordinates of the measurement point in the solar cell coordinate system; It's encoder counting. It is a counting scale for unit displacement.

[0083] Step 3: Extract minority carrier lifetime from the preprocessed and registered lifetime distribution map, extract heat dissipation power density from the phase-locked temperature amplitude of the preprocessed and registered heat dissipation map, and extract ultrasonic propagation time delay shift and scattered energy from the preprocessed and registered ultrasonic map. The multimodal features are composed of minority carrier lifetime, heat dissipation power density, ultrasonic propagation time delay shift, scattered energy, and thermal phase of the heat dissipation map.

[0084] Specifically, step 3.1 involves estimating the minority carrier lifetime using the intensity-time weighted average, i.e., the first-order moment method, based on the preprocessed and registered lifetime distribution map. , The smaller the value, the more severe the composite effect and the worse the material quality. The formula is as follows:

[0085] , ,

[0086] In the formula, To estimate the minority carrier lifetime, no complex fitting was performed here. Instead, a robust lifetime index was calculated directly: the greater the brightness in later time periods, the longer the lifetime.

[0087] Step 3.2: Convert the phase-locked temperature amplitude into heat dissipation power density. This is used to quantify energy dissipation caused by series resistance or hot spots, and its calculation formula is as follows:

[0088] , ,

[0089] In the formula, the registered phase-locked temperature amplitude True temperature amplitude . Background grayscale offset. The gray-temperature conversion factor obtained for standard heat source calibration ( (grayscale) For thermal conductivity, For thermal diffusivity, This is the modulation angular frequency.

[0090] Step 3.3: Select the measurement point in the cell coordinate system. Standardized waveform of ultrasound After undergoing time synchronization and spatial registration processing in step 2.2, the waveform's time axis is now aligned with the laser excitation trigger signal. Because the time reference is consistent, the time variable can be... The equivalent is denoted as the time variable used in the cross-correlation calculation. Therefore, after unifying the time reference, a signal is obtained for cross-correlation calculation: by calculating the shift in wave arrival time through correlation, the propagation delay caused by cracks or debonding is detected, and the ultrasonic propagation time delay shift is obtained, the calculation formula of which is as follows:

[0091] , ,

[0092] In the formula, It is the ultrasonic propagation time delay offset (s). It is a test waveform. It is the reference waveform for a defect-free baseline. It is a related search displacement. This is a reference arrival time. It is the integration time. The arrival time is evidence of crack circumference and velocity variation, and how much difference remains after alignment reflects scattering and attenuation intensity.

[0093] The residual energy between the reference wave and the defect wave is measured using the scattering energy formula, which quantifies the crack intensity. The calculation formula is as follows:

[0094] ,

[0095] In the formula It is the scattered energy (relative dimension). These are the upper and lower limits of the selected integration time window. The larger the value, the more obvious the difference in waveform shape, the stronger the scattering and attenuation, which can lead to the conclusion that the defect is more serious.

[0096] Step 4: Calculate the anomaly score based on minority carrier lifetime, heat dissipation power density, ultrasonic propagation time delay offset, and scattering energy. Regions with anomaly scores exceeding a set threshold are considered potential anomaly regions. A multimodal attention convolutional neural network is used to detect and classify the multimodal features of the potential anomaly regions to obtain classification results for electrical defects, thermal defects, and mechanical defects, thus completing the defect diagnosis.

[0097] Specifically, step 4.1 involves constructing anomaly scores using weighted and standardized features. Based on the statistical significance of the multimodal features, defect areas are preliminarily identified, calculated using the following formula:

[0098] ,

[0099] In the formula, It is an anomaly score (the higher the score, the more abnormal). It is a robust standardization of low birth rate life expectancy. It is a robust standardization of heat dissipation power density. yes Joint normalization with scattering energy, , , It has three-branch weights. Before entering the multimodal attention convolutional neural network, compare... The value and the size of the set threshold, Areas where the value exceeds the set threshold are considered potentially abnormal areas. This step allows for the rapid screening of these potentially abnormal areas.

[0100] Step 4.2: Based on the initial screening, a multimodal attention convolutional neural network is used to perform deep fusion and classification of multimodal features in potentially anomalous regions. The input to the multimodal attention convolutional neural network includes five modal features: minority carrier lifetime. Heat dissipation power density thermal phase Ultrasonic propagation time delay offset and scattered energy Each modal input is processed by an independent convolutional encoder to extract spatial semantic features, which are represented as follows:

[0101] , , , ,

[0102] , , ,

[0103] in, For convolutional feature extraction functions, , They are respectively for , The encoding layer that performs convolutional mapping, This represents feature concatenation along the channel dimension. To fuse convolutional layers, thermal channels are constructed using... and The thermal feature map obtained by joint encoding is generated This also reflects the surface heating intensity (from Dominant) and thermal diffusion delay (by (Reflection), used to comprehensively characterize series resistance and hot spot defects.

[0104] Features from each modality are fed into a multi-head cross-modal attention mechanism for information exchange. The single-head form of the multi-head attention mechanism is calculated as follows:

[0105] ,

[0106] In the formula, It is a cross-modal attention output tensor. It is a query feature derived from one of the minority carrier lifetime, heat dissipation power, ultrasonic propagation time delay shift, and scattering energy. , These are the value features from the other modes. Each time, one mode is selected as Q, and the other two are selected as K / V (input modes: { , , Output the enhanced features of each modality. , , . The channel dimension is used for scaling. Then, it is fused into a comprehensive feature tensor through a channel aggregation convolutional layer.

[0107] ,

[0108] In the formula This is an aggregation convolution operation used to semantically integrate enhanced features from various modalities.

[0109] Subsequently, a fully connected classification layer is used to predict the probability of each pixel across multiple classes, yielding the probability distributions for three types of defects: electrical, thermal, and mechanical. The calculation formula is as follows:

[0110] ,

[0111] In the formula For pixels The probability vector of the defect category. It is the last thing the network passes through The three defect probability maps output by the classification layer correspond to the three physical domains of electricity, heat, and mechanics, respectively. This is the classification layer weight matrix. It is the bias vector;

[0112] ,

[0113] In the formula Characterizes the spatial distribution of defects of various physical types, where 1 represents a defect area and 0 represents a normal area. For the set threshold, If lifespan is extremely short in a certain place ( High), judged as an electrical defect area; if the local thermal amplitude is large and the phase lag is large ( High), judged as a hotspot; if the wave propagation delay is significant ( (High), judged as a crack.

[0114] The above process, through the combination of multimodal features and cross-modal deep learning, ultimately achieves accurate identification of electrical, thermal, and mechanical defects in gridless photovoltaic cells.

[0115] In order to enable the test results to be directly applied to cell sorting and life prediction, as a preferred embodiment, the method of this embodiment further includes step 5: mapping the multimodal features to the increment of the equivalent series resistance and the increment of the equivalent composite current density of the cell, calculating the effective power generation area loss based on the mechanical defect classification results, estimating the power loss based on the increment of the equivalent series resistance, the increment of the equivalent composite current density and the effective power generation area loss, and evaluating the power generation performance.

[0116] Specifically, step 5.1 involves mapping the average heat dissipation power density to the increment of the series resistance; and mapping the average minority carrier lifetime to the increment of the recombination current density, using the following formula:

[0117] , ,

[0118] In the formula, It is the increment of the equivalent series resistance. , The coefficients are obtained from linear regression of the calibration sample. To achieve a robust and standardized average heat dissipation power, It is the increment of the equivalent composite current density. , The coefficients obtained from calibration This represents the mean of the minority carrier lifetime, which is robustly standardized. A higher heat dissipation power density results in a greater increase in the equivalent series resistance. The larger the value, the worse the minority carrier lifetime, the stronger the recombination, and the greater the increase in the equivalent recombination current density. The larger.

[0119] Then, the crack mask ratio is calculated, representing the effective power generation area loss. The defect area is calculated from the defect detection results in step 4. Specifically, the probability map output by the mechanical defect branch of the multimodal attention convolutional neural network in step 4 is... Its value range is [0,1]. A threshold is set... A binary mask for defects can be obtained. :

[0120] ,

[0121] In the formula This is the threshold, typically set to 0.4–0.6, calibrated based on the ROC curve. Defect binary mask. Used to identify defective pixels, pixels with a value of 1 in the mask represent defective areas, and pixels with a value of 0 represent normal areas. Let the total number of defective pixels in the binary defect mask be... The actual area corresponding to each pixel in the battery cell coordinate system is (Determined by imaging calibration or coordinate mapping), the area of ​​the defect region can then be calculated as:

[0122] ,

[0123] Since the cracked area generates virtually no electricity, the effective area loss is estimated based on the area ratio. The calculation formula is:

[0124] .

[0125] Step 5.2: Simultaneous Combination , , The power loss under standard operating conditions is obtained. This is used to directly evaluate the grade of solar cells, and its calculation formula is as follows:

[0126] ,

[0127] In the formula This refers to the output power loss under standard operating conditions (STC). , , The sensitivity coefficient is obtained by taking the partial derivative of a diode model under nominal operating conditions.

[0128] Please combine Figure 2 As shown, another embodiment of the present invention is an online defect detection system for gridless photovoltaic panels that implements the method of the aforementioned embodiments, which specifically includes: a multimodal signal acquisition unit 1, a data preprocessing and registration unit 2, a feature extraction unit 3, a fusion decision unit 4, and a power evaluation unit 5.

[0129] The multimodal signal acquisition unit 1 includes a time-resolved photoluminescence (TRPL) detection module 101, an optically induced phase-locked thermal imaging (OP-LIT) detection module 102, and a laser ultrasound (LU) detection module 103.

[0130] The time-resolved photoluminescence (TRPL) detection module 101 is used to obtain a lifetime distribution map of the grid-less photovoltaic cell through time-resolved photoluminescence. The lifetime distribution map is composed of the curves showing the decay of the luminous intensity of each pixel over time. The optically induced phase-locked-in thermal imaging (OP-LIT) detection module 102 is used to obtain a heat dissipation map of the grid-less photovoltaic cell through optically induced phase-locked-in thermal imaging. The heat dissipation map is composed of the phase-locked-in temperature amplitude and phase demodulation map of each pixel. The laser ultrasound (LU) detection module 103 is used to obtain an ultrasonic image of the grid-less photovoltaic cell through laser ultrasound. The ultrasonic image is composed of the ultrasonic time-domain signals from each receiving point.

[0131] For details on the implementation of the multimodal signal acquisition unit 1, please refer to step 1 of the aforementioned embodiment.

[0132] The data preprocessing and registration unit 2 is used to preprocess and register the phase-locked temperature amplitude and ultrasonic wave of the lifetime distribution map and heat dissipation map to uniformly map them to the cell coordinate system. For the specific functional implementation process of the data preprocessing and registration unit 2, please refer to step 2 of the aforementioned embodiment.

[0133] Feature extraction unit 3 is used to extract minority carrier lifetime from the preprocessed and registered lifetime distribution map, extract heat dissipation power density from the phase-locked temperature amplitude of the preprocessed and registered heat dissipation map, and extract ultrasonic propagation time delay shift and scattered energy from the preprocessed and registered ultrasonic map. Minority carrier lifetime, heat dissipation power density, thermal phase, ultrasonic propagation time delay shift, and scattered energy constitute multimodal features. For the specific functional implementation process of feature extraction unit 3, please refer to step 3 of the aforementioned embodiment.

[0134] The fusion decision unit 4 is used to calculate anomaly scores based on minority carrier lifetime, heat dissipation power density, ultrasonic propagation time delay offset, and scattering energy. Regions with anomaly scores exceeding a set threshold are considered potential anomaly regions. A multimodal attention convolutional neural network is used to detect and classify defects in the multimodal features of potential anomaly regions, resulting in classifications of electrical, thermal, and mechanical defects. For a detailed explanation of the specific functional implementation of the fusion decision unit 4, please refer to step 4 of the aforementioned embodiment.

[0135] The power assessment unit 5 is used to map multimodal characteristics to the increments of the equivalent series resistance and the equivalent composite current density of the solar cell, calculate the effective power generation area loss based on the mechanical defect classification results, and estimate the power loss based on the increments of the equivalent series resistance, the equivalent composite current density, and the effective power generation area loss. For the specific functional implementation process of the power assessment unit 5, please refer to step 5 of the aforementioned embodiment.

[0136] This invention solves the problem that traditional methods cannot locate multiple types of defects. In complex process environments, it enables real-time online defect detection of grid-less photovoltaic cells, offering advantages such as high detection accuracy and strong adaptability, significantly improving the quality control and production line sorting efficiency of photovoltaic modules.

Claims

1. A method for online defect detection of gridless photovoltaic panels, characterized in that, Includes the following steps: The lifetime distribution map of the gridless photovoltaic cell was obtained by time-resolved photoluminescence, the heat dissipation map of the gridless photovoltaic cell was obtained by optically induced phase-locked thermal imaging, and the ultrasonic map of the gridless photovoltaic cell was obtained by laser ultrasound. The lifetime distribution map is composed of the curve of the luminous intensity of each pixel decaying over time. The heat dissipation map is composed of the phase-locked temperature amplitude and thermal phase of each pixel. The ultrasonic map is composed of the ultrasonic time-domain signal of each receiving point. The phase-locked temperature amplitude and ultrasonic wave of the lifetime distribution map, heat dissipation map and the ultrasonic wave are preprocessed and registered to be uniformly mapped to the cell coordinate system. Minority carrier lifetime is extracted from the lifetime distribution map after preprocessing and registration; heat dissipation power density is extracted from the phase-locked temperature amplitude of the heat dissipation map after preprocessing and registration; and ultrasonic propagation time delay shift and scattered energy are extracted from the ultrasonic map after preprocessing and registration. The minority carrier lifetime, heat dissipation power density, thermal phase, ultrasonic propagation time delay shift and scattered energy constitute multimodal features. Anomaly scores are calculated based on minority carrier lifetime, heat dissipation power density, ultrasonic propagation time delay offset, and scattering energy. Regions with anomaly scores exceeding a set threshold are considered potential anomaly regions. A multimodal attention convolutional neural network is used to detect and classify the multimodal features of potential anomaly regions, resulting in classifications of electrical, thermal, and mechanical defects.

2. The online defect detection method for gridless photovoltaic panels according to claim 1, characterized in that, The preprocessing includes normalizing the curve of luminescence intensity decay over time in the lifetime distribution map using the following formula: ， In the formula, It is the curve of luminescence intensity decaying over time in the lifetime distribution map. This is the corrected TRPL curve. Dark field, A draw. For time sample index; The preprocessing includes bandpass filtering and normalization of the ultrasonic time-domain signal of the ultrasound image using the following formula: ， In the formula, This is the ultrasonic time-domain signal of the ultrasound image. The normalized waveform after bandpass filtering. It is a bandpass filter operator for 0.2–2 MHz. This represents the laser energy reading for each excitation.

3. The online defect detection method for gridless photovoltaic panels according to claim 1, characterized in that, The registration process involves mapping the coordinates of the preprocessed lifetime distribution map, the phase-locked temperature amplitude of the heat dissipation map, and the ultrasonic map to the cell coordinates. Then, through encoder pulses, the discrete points collected during the rolling process are resampled to an equidistant grid by the delivery encoder, so that different modes are unified in time and space dimensions.

4. The online defect detection method for gridless photovoltaic panels according to claim 1, characterized in that, The extraction of minority carrier lifetime from the preprocessed and registered lifetime distribution map is achieved by estimating the minority carrier lifetime using the first-order moment method, with the following formula: ， ， In the formula, For the estimated minority carrier lifetime, The curves showing the decay of luminescence intensity over time after preprocessing and registration are shown. The heat dissipation power density is extracted from the phase-locked temperature amplitude of the preprocessed and registered heat dissipation map and calculated according to the following formula: ， ， In the formula, For heat dissipation power density, The phase-locked loop temperature amplitude after registration. Background grayscale offset. The grayscale-temperature conversion factor obtained from standard heat source calibration. For thermal conductivity, For thermal diffusivity, The modulation angular frequency; The formula for extracting the ultrasonic propagation time delay offset and calculating the ultrasonic propagation time delay offset in the scattered energy from the preprocessed and registered ultrasonic image is as follows: ， ， In the formula, It is the ultrasonic propagation time delay offset (s). The standardized waveform for the registered ultrasound image. It is the reference waveform for a defect-free baseline. It is a related search displacement. This is a reference arrival time. It is the integration time; The formula for calculating scattering energy is: ， In the formula It is scattered energy. These are the upper and lower limits of the selected integration time window.

5. The online defect detection method for gridless photovoltaic panels according to claim 1, characterized in that, The anomaly score is determined by a weighted sum of robust normalization of minority carrier lifetime, robust normalization of heat dissipation power density, and joint normalization of ultrasonic propagation time delay offset and scattered energy; the multimodal attention convolutional neural network performs defect detection and classification on the multimodal features of potentially anomalous regions, including: Convolutional feature extraction is performed on the minority carrier lifetime, heat dissipation power density, thermal phase, and ultrasonic propagation time delay offset combined scattering energy; the convolutional feature extraction results of heat dissipation power density and thermal phase are convolutionally mapped and encoded, and the features are concatenated in the channel dimension, and then fused convolution to obtain thermal feature mapping; The convolutional feature extraction results of minority carrier lifetime, the convolutional feature extraction results of ultrasonic propagation time delay offset and scattering energy, and the thermal feature mapping are used as input modes of multi-head attention. The enhanced features output by multi-head attention are aggregated and convolved to obtain a comprehensive feature tensor. Based on the comprehensive feature tensor, a probability map of defect classification is output by the fully connected classification layer. The defect region in the probability map is judged by a set threshold, and the classification results of electrical defects, thermal defects and mechanical defects are determined.

6. The online defect detection method for gridless photovoltaic panels according to any one of claims 1 to 5, characterized in that, The method also includes the steps of: mapping the multimodal features to the increment of the equivalent series resistance of the battery cell and the increment of the equivalent composite current density, calculating the effective power generation area loss based on the mechanical defect classification results, and estimating the power loss based on the increment of the equivalent series resistance, the increment of the equivalent composite current density, and the effective power generation area loss.

7. The online defect detection method for gridless photovoltaic panels according to claim 6, characterized in that, The estimated power loss is calculated as a weighted sum of the increment of the equivalent series resistance, the increment of the equivalent composite current density, and the effective power generation area loss. The weighting coefficients are obtained by numerically calculating the partial derivatives of the diode model under nominal operating conditions.

8. The online defect detection method for gridless photovoltaic panels according to claim 6, characterized in that, The mapping relationship for the increment of the equivalent series resistance is as follows: ， The mapping relationship for the increment of the equivalent composite current density is as follows: ， In the formula, It is the increment of the equivalent series resistance. , The coefficients are obtained from linear regression of the calibration sample. The mean of the heat dissipation power density is a robustly standardized value. It is the increment of the equivalent composite current density. , These are the coefficients obtained from calibration. This represents the mean of the robustly standardized minority carrier lifetime. The effective power generation area loss is the ratio of the area of ​​the mechanical defect region of the solar cell to the total area of ​​the solar cell.

9. An online defect detection system for gridless photovoltaic panels, characterized in that, include: A multimodal signal acquisition unit is used to acquire a lifetime distribution map of a gridless photovoltaic cell by time-resolved photoluminescence, a heat dissipation map of a gridless photovoltaic cell by optically induced phase-locked thermal imaging, and an ultrasonic map of a gridless photovoltaic cell by laser ultrasound. The lifetime distribution map is composed of the curve of the luminous intensity of each pixel decaying over time. The heat dissipation map is composed of the phase-locked temperature amplitude and thermal phase of each pixel. The ultrasonic map is composed of the ultrasonic time-domain signal of each receiving point. The data preprocessing and registration unit is used to preprocess and register the phase-locked temperature amplitude and ultrasonic wave of the lifetime distribution map and heat dissipation map to uniformly map them to the cell coordinate system. The feature extraction unit is used to extract minority carrier lifetime from the preprocessed and registered lifetime distribution map, extract heat dissipation power density from the phase-locked temperature amplitude of the preprocessed and registered heat dissipation map, and extract ultrasonic propagation time delay shift and scattered energy from the preprocessed and registered ultrasonic map. The minority carrier lifetime, heat dissipation power density, thermal phase, ultrasonic propagation time delay shift and scattered energy constitute multimodal features. The fusion decision unit is used to calculate anomaly scores based on minority carrier lifetime, heat dissipation power density, ultrasonic propagation time delay offset, and scattering energy. Regions with anomaly scores exceeding a set threshold are considered potential anomaly regions. A multimodal attention convolutional neural network is used to detect and classify defects in the multimodal features of potential anomaly regions, resulting in classification results for electrical defects, thermal defects, and mechanical defects.

10. The online defect detection system for gridless photovoltaic panels according to claim 9, characterized in that, It includes a power assessment unit for mapping the multimodal characteristics to the increment of the equivalent series resistance of the battery cell and the increment of the equivalent composite current density, calculating the effective power generation area loss based on the mechanical defect classification results, and estimating the power loss based on the increment of the equivalent series resistance, the increment of the equivalent composite current density, and the effective power generation area loss.

Images