Battery production online detection method and device, electronic equipment and storage medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUANENG CLEAN ENERGY RES INST
- Filing Date
- 2026-03-04
- Publication Date
- 2026-07-10
Smart Images
Figure CN122373670A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of data processing technology, and in particular to an online detection method and apparatus, electronic equipment and storage medium for battery production. Background Technology
[0002] Perovskite solar cells, as a core technology in the photovoltaic industry, are widely used in the industrialization of next-generation high-efficiency photovoltaic devices. Among related technologies, a complete fabrication system from the transparent conductive layer (FTO) to the metal electrode has been constructed through the synergistic operation of solution processing, thin film deposition, and laser etching.
[0003] Existing perovskite module testing methods directly employ offline testing procedures without achieving real-time quality monitoring of the production process. This may lead to the accumulation of process deviations and an increase in sample contamination rates, thereby affecting the yield of the entire batch of products. Summary of the Invention
[0004] This disclosure provides an online testing method, apparatus, electronic device, and storage medium for battery production.
[0005] According to a first aspect of this disclosure, an online testing method for battery production is provided, comprising: Integrated testing units are deployed across multiple process stations on the production line. The detection unit performs at least two different types of online non-destructive testing on each functional layer of the battery to obtain quality information of the functional layer, wherein the quality information includes surface morphology information, photophysical performance information and optical performance information. The quality information is transmitted to the data processing module for comprehensive analysis to obtain a comprehensive evaluation result regarding the quality of the functional layer; and Based on the comprehensive evaluation results, process adjustment instructions are generated to control the operating parameters of the corresponding process stations in the production line in real time.
[0006] Optionally, the at least two different types of online non-destructive testing include at least two of visual inspection, photoluminescence testing, and visible light absorption testing.
[0007] Optionally, the step of performing at least two different types of online non-destructive testing on each functional layer of the battery through the detection unit includes: The surface image of the functional layer is acquired by the first detection unit, and the surface image is analyzed to identify surface defects and / or process feature states of a preset type; and The functional layer is subjected to spectral excitation and acquisition by the second detection unit, and the crystal quality and carrier behavior characteristics of the functional layer are evaluated based on the acquired spectral data.
[0008] Optionally, analyzing the surface image to identify surface defects and / or process feature states of a preset type includes: Microstructural defects on the surface of the functional layer are identified using an image edge detection algorithm. When the size characteristics of the microstructural defects meet preset defect conditions, they are marked as defective products. The edge feature size formed by the laser etching process is detected by an image transformation algorithm. When the edge feature size exceeds the preset process tolerance range, a process warning signal is generated.
[0009] Optionally, the evaluation of the crystal quality and carrier behavior characteristics of the functional layer based on the acquired spectral data includes: Based on the collected photoluminescence spectrum, determine the spectral peak intensity and half-width at half-maximum. And / or, calculate the lifetime parameters of the charge carriers in the functional layer using time-resolved spectral test data.
[0010] Optionally, transmitting the quality information to the data processing module for comprehensive analysis to obtain a comprehensive evaluation result regarding the quality of the functional layer includes: The quality information is processed by a pre-set machine learning model, which is trained based on historical production data and is used to predict the direction of process parameter adjustment based on real-time detection data.
[0011] According to a second aspect of this disclosure, an online testing device for battery production is provided, comprising: Deployment unit, used to deploy integrated testing units across multiple process stations on a production line; The detection unit is used to perform at least two different types of online non-destructive testing on each functional layer of the battery to obtain quality information of the functional layer, wherein the quality information includes surface morphology information, photophysical performance information and optical performance information; The transmission unit is used to transmit the quality information to the data processing module; An analysis unit is used to perform comprehensive analysis of the quality information in the data processing module to obtain a comprehensive evaluation result regarding the quality of the functional layer; and The generation unit is used to generate process adjustment instructions based on the comprehensive evaluation results, so as to control the operating parameters of the corresponding process station in the production line in real time.
[0012] Optionally, the detection unit is further configured to include at least two of the at least two different types of online non-destructive testing, namely visual inspection, photoluminescence testing, and visible light absorption testing.
[0013] Optionally, the detection unit is further configured to: The surface image of the functional layer is acquired by the first detection unit, and the surface image is analyzed to identify surface defects and / or process feature states of a preset type; and The functional layer is subjected to spectral excitation and acquisition by the second detection unit, and the crystal quality and carrier behavior characteristics of the functional layer are evaluated based on the acquired spectral data.
[0014] Optionally, the detection unit is further configured to: Microstructural defects on the surface of the functional layer are identified using an image edge detection algorithm. When the size characteristics of the microstructural defects meet preset defect conditions, they are marked as defective products. The edge feature size formed by the laser etching process is detected by an image transformation algorithm. When the edge feature size exceeds the preset process tolerance range, a process warning signal is generated.
[0015] Optionally, the detection unit is further configured to: Based on the collected photoluminescence spectrum, determine the spectral peak intensity and half-width at half-maximum. And / or, calculate the lifetime parameters of the charge carriers in the functional layer using time-resolved spectral test data.
[0016] Optionally, the analysis unit is further configured to: The quality information is processed by a pre-set machine learning model, which is trained based on historical production data and is used to predict the direction of process parameter adjustment based on real-time detection data.
[0017] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.
[0018] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.
[0019] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.
[0020] The online testing method, apparatus, electronic equipment, and storage medium for battery production disclosed herein, through the deployment of integrated testing units at each process station on the production line, performs multiple types of online non-destructive testing on the functional layers of the battery to obtain multi-dimensional quality information. After comprehensive analysis, process adjustment instructions are generated in real time to regulate the parameters of the corresponding workstations, thus constructing a closed-loop quality control system for the production process. Therefore, it can solve the technical problems in existing perovskite module testing methods, which use offline testing processes and fail to achieve real-time quality monitoring of the production process, resulting in the accumulation of process deviations and increased sample contamination rates, thereby affecting the yield of the entire batch of products. It achieves the technical effect of realizing real-time quality monitoring of the entire production process, reducing process deviations and sample contamination, improving the yield of the entire batch of perovskite solar cells, and thus promoting the industrialization process of perovskite photovoltaic devices.
[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description
[0022] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 This is a schematic flowchart of an online testing method for battery production provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of the structure of an online testing device for battery production provided in an embodiment of the present disclosure; Figure 3 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation
[0023] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.
[0024] The following description, with reference to the accompanying drawings, outlines an online testing method, apparatus, electronic device, and storage medium for battery production according to embodiments of the present disclosure.
[0025] Figure 1 This is a schematic flowchart of an online testing method for battery production provided in an embodiment of this disclosure.
[0026] like Figure 1 As shown, the method includes the following steps: Step 101: Deploy integrated testing units based on multiple process stations on the production line; Multiple process stations correspond to key process nodes in the fabrication of perovskite solar cells, including transparent conductive layer deposition station, hole transport layer fabrication station, perovskite active layer coating station, electron transport layer deposition station, and metal electrode fabrication station. Each process station completes the formation of its corresponding functional layer, and the quality of the formed functional layer directly affects the performance of the final device. Therefore, detection units need to be deployed at each process station to achieve real-time monitoring.
[0027] An integrated testing unit is a unified testing structure that integrates the testing needs of each workstation, rather than a collection of separate testing components. During deployment, it is necessary to fully consider the spatial layout, process rhythm, and characteristics of the testing objects at each workstation to determine the installation location and fixing method of the testing unit. This ensures that the testing unit is precisely aligned with the transmission path of the production line, enabling immediate testing after the functional layer is formed without interfering with normal production flow.
[0028] To address the varying inspection priorities at different process stations, integrated inspection units must reserve adaptable interfaces to allow for flexible configuration of subsequent inspection functions. Simultaneously, they must ensure interoperability between inspection units, providing a hardware foundation for unified data integration. During deployment, the stability and maintainability of the inspection units must be considered to prevent factors such as temperature and humidity in the production environment from affecting inspection accuracy. A scientifically designed deployment ensures the inspection units can function continuously and stably, achieving real-time quality monitoring of each process station's functional layers, providing a reliable data source for subsequent quality analysis and process adjustments.
[0029] Step 102: Perform at least two different types of online non-destructive testing on each functional layer of the battery through the detection unit to obtain the quality information of the functional layer, wherein the quality information includes surface morphology information, photophysical performance information and optical performance information; The detection unit performs at least two different types of online non-destructive testing on each functional layer of the battery to obtain the quality information of the functional layer. The online non-destructive testing will not damage the functional layer or interfere with the normal operation of the production line. It can complete the testing in time after the functional layer is formed to avoid the accumulation of quality problems.
[0030] The surface morphology information in the quality information is obtained through the image acquisition component and image processing mechanism in the detection unit. It can comprehensively reflect whether there are defects on the surface of the functional layer, the execution effect of the laser etching process, and the uniformity of the distribution of the transport layer, clearly presenting the overall morphology and local details of the surface of the functional layer.
[0031] Photophysical performance information is obtained through specific excitation and spectral acquisition components. By using the spectral signal generated after the excitation light source acts on the functional layer, the data related to the crystal integrity and carrier recombination characteristics of the functional layer are obtained through analysis, which intuitively reflects the core physical performance of the functional layer.
[0032] Optical performance information is acquired through visible light signal emission and detection components. Based on the absorption, transmission, and reflection characteristics of the functional layer in the visible light band, the light absorption capacity and optical bandgap-related parameters are analyzed, accurately reflecting the key optical performance indicators of the functional layer. The combined application of at least two different types of detection can comprehensively capture the quality status of the functional layer from multiple dimensions, ensuring the completeness and reliability of the acquired quality information. This provides solid data support for subsequent quality assessment and process parameter adjustments, guaranteeing the performance stability and consistency of the final battery product.
[0033] Step 103: The quality information is transmitted to the data processing module for comprehensive analysis to obtain a comprehensive evaluation result regarding the quality of the functional layer; and The quality information is transmitted to the data processing module for comprehensive analysis to obtain a comprehensive evaluation result on the quality of the functional layer. The transmission of quality information adopts a method adapted to the data flow of the production line to ensure the real-time and completeness of information transmission and avoid data loss or delay that may affect the analysis efficiency.
[0034] The data processing module, as the core analysis unit, integrates surface morphology, photophysical properties, and optical properties from multiple dimensions. It doesn't interpret single types of data in isolation, but rather cross-validates them by considering the inherent relationships between various detection dimensions. During the analysis, it invokes a pre-defined quality judgment logic. This logic, built upon a large amount of practically accumulated effective data, accurately matches the quality requirements of different functional layers. By comparing the conformity of each quality parameter with standard thresholds, it eliminates deviations caused by fluctuations in individual data points.
[0035] Simultaneously, the data processing module analyzes and identifies abnormal data to determine whether it's a detection error or an actual quality issue in the functional layer, ensuring the objectivity and reliability of the comprehensive evaluation results. The comprehensive evaluation results not only clearly state whether the functional layer's quality is up to standard, but also detail the compliance status of each quality dimension, potential quality risks, and possible directions of the problems. This provides clear and targeted evidence for subsequent product flow decisions and process parameter adjustments, ensuring that the functional layers produced at each stage of the process undergo a comprehensive and scientific quality assessment.
[0036] Step 104: Generate process adjustment instructions based on the comprehensive evaluation results to control the operating parameters of the corresponding process stations in the production line in real time.
[0037] Step 104 generates process adjustment instructions based on the comprehensive evaluation results to control the operating parameters of the corresponding process stations in the production line in real time. The comprehensive evaluation results are the core basis for instruction generation. If the evaluation results show that the quality of the functional layer fully meets the preset standards, an instruction to maintain the current operating parameters is generated to ensure the stable continuation of the production process. If the evaluation results indicate that there is a quality deviation or potential risk, the corresponding problematic process station is accurately located and an adjustment instruction is generated accordingly.
[0038] The generation of process adjustment instructions must consider the correlation between the quality requirements of each functional layer and the process parameters, and refer to a large amount of process optimization data accumulated in practice to ensure the scientific nature and operability of the instructions. The controlled operating parameters cover key parameters in the perovskite solar cell fabrication process, including parameters that directly affect the formation quality of functional layers, such as coating speed and annealing temperature. After the instructions are generated, they are sent in real time to the execution units of the corresponding process stations through the production line's control transmission channel to ensure that parameter adjustments can quickly respond to quality inspection results and avoid the continuous generation of unqualified functional layers.
[0039] Simultaneously, during parameter adjustment, the data processing module receives adjusted process operation data and subsequent quality information in real time, forming a closed-loop feedback mechanism. This continuously verifies the adjustment effect and dynamically optimizes the instructions based on actual conditions. This real-time process control mode based on comprehensive evaluation results can promptly correct process deviations during production, ensuring that the quality of each functional layer remains within acceptable limits. This effectively improves production efficiency and product yield, providing strong support for the stable industrialization of perovskite solar cells.
[0040] In some embodiments, the at least two different types of online nondestructive testing include at least two of visual inspection, photoluminescence testing, and visible light absorption testing.
[0041] In some embodiments, performing at least two different types of online non-destructive testing on each functional layer of the battery through the detection unit includes: The surface image of the functional layer is acquired by the first detection unit, and the surface image is analyzed to identify surface defects and / or process feature states of a preset type; and The functional layer is subjected to spectral excitation and acquisition by the second detection unit, and the crystal quality and carrier behavior characteristics of the functional layer are evaluated based on the acquired spectral data.
[0042] The detection unit performs at least two different types of online non-destructive testing on each functional layer of the battery, specifically including surface image analysis and detection by a first detection unit and spectral excitation acquisition and detection by a second detection unit. The first detection unit is equipped with a high-resolution image acquisition component and a uniform illumination device, enabling it to accurately capture surface images of each functional layer. The acquisition process is synchronized with the production line flow and does not contact the functional layers, thus avoiding damage. After acquisition, the surface images are analyzed at the pixel level using a preset image processing algorithm to identify preset types of surface defects, including pinholes, cracks, and contamination that affect the performance of the functional layers. Simultaneously, it can detect process characteristic states, covering the execution status of laser etching processes and the uniformity of the transport layer distribution, comprehensively reflecting the surface morphology and process execution effect of the functional layers.
[0043] The second detection unit is equipped with a specific wavelength excitation source and a high-sensitivity spectral acquisition device. The excitation source, acting on the functional layer, generates a characteristic spectrum, which the spectral acquisition device captures in real time and converts into analyzable data signals. By analyzing the spectral data, the crystal quality of the functional layer can be accurately assessed, determining whether the crystallization is complete and uniform. Simultaneously, carrier behavior characteristics can be analyzed, including the generation and recombination processes and lifetime of carriers. These two detection types complement each other, acquiring quality information from two core dimensions: surface morphology and intrinsic performance. This ensures the comprehensiveness and specificity of the detection results, providing rich and reliable basic data for the subsequent comprehensive analysis by the data processing module, guaranteeing accurate determination of the functional layer's quality.
[0044] In some embodiments, analyzing the surface image to identify surface defects and / or process feature states of a preset type includes: Microstructural defects on the surface of the functional layer are identified using an image edge detection algorithm. When the size characteristics of the microstructural defects meet preset defect conditions, they are marked as defective products. The edge feature size formed by the laser etching process is detected by an image transformation algorithm. When the edge feature size exceeds the preset process tolerance range, a process warning signal is generated.
[0045] The analysis of the surface image to identify surface defects and / or process feature states of a preset type is specifically achieved through the collaborative application of image edge detection algorithms and image transformation algorithms. The image edge detection algorithm has a high sensitivity to capture subtle features and can accurately identify microstructural defects such as pinholes, cracks, and contamination on the functional layer surface. This algorithm enhances the grayscale difference between defective and normal areas in the image, clearly outlining the contour of microstructural defects and extracting key dimensional features such as diameter, length, and contrast.
[0046] The preset defect conditions are quantitative standards based on the performance requirements of the functional layer and production practice data. For example, the diameter threshold for pinhole defects, the length threshold for crack defects, and the contrast threshold for contamination defects. When a detected microstructural defect meets the preset defect condition in any size feature, the corresponding functional layer is judged to be substandard and marked as a non-conforming product.
[0047] Image transformation algorithms focus on edge feature detection formed during laser etching. By performing geometric transformations and feature enhancement on the surface image, they accurately measure edge feature dimensions such as over-etching depth, under-etching length, and clearing width. A preset process tolerance range is a critical range of process parameters to ensure battery performance. When the measured edge feature dimensions exceed this range, it indicates a deviation in the laser etching process that may affect subsequent processes or device performance. In this case, the system automatically generates a process warning signal, promptly prompting staff to investigate problems in the etching equipment parameters or operating procedures, ensuring the stability and consistency of the laser etching process. The targeted application of these two algorithms enables accurate identification and quantitative judgment of surface defects and process feature states, providing a direct and reliable basis for quality control and process optimization.
[0048] In some embodiments, evaluating the crystal quality and carrier behavior characteristics of the functional layer based on the acquired spectral data includes: Based on the collected photoluminescence spectrum, determine the spectral peak intensity and half-width at half-maximum. And / or, calculate the lifetime parameters of the charge carriers in the functional layer using time-resolved spectral test data.
[0049] The evaluation of the crystal quality and carrier behavior characteristics of the functional layer based on the acquired spectral data is specifically achieved through photoluminescence spectroscopy analysis and time-resolved spectroscopy testing. During photoluminescence spectroscopy analysis, the excitation source in the detection unit acts on the functional layer to induce photoluminescence. The spectral acquisition device accurately captures this spectral signal and converts it into quantifiable data. Two key parameters, peak intensity and full width at half maximum (FWHM), are extracted through analysis of the spectral curve.
[0050] The peak intensity of the spectrum directly reflects the radiative recombination efficiency of charge carriers in the functional layer. A higher peak intensity usually indicates better crystal quality and less carrier recombination loss. The full width at half maximum (FWHM) reflects the uniformity of the crystal particles and the integrity of the crystal lattice. A narrower FWHM indicates a more regular crystal structure and a lower defect density in the functional layer. In time-resolved spectroscopy, the decay process of the photoluminescence signal over time is recorded using specific testing techniques to obtain time-resolved spectral test data. A professional data analysis model is then used to fit and calculate the decay curve to obtain the lifetime parameters of charge carriers in the functional layer.
[0051] Carrier lifetime is a core indicator for measuring carrier transport and recombination characteristics. A longer carrier lifetime indicates more efficient carrier transport within the functional layer, a higher probability of participation in photoelectric conversion, and superior photoelectric performance of the functional layer. By acquiring and analyzing these parameters, the crystal quality and carrier behavior characteristics of the functional layer can be accurately evaluated at the microscopic level, providing crucial intrinsic performance data for the comprehensive assessment of functional layer quality.
[0052] In some embodiments, transmitting the quality information to a data processing module for comprehensive analysis to obtain a comprehensive evaluation result regarding the quality of the functional layer includes: The quality information is processed by a pre-set machine learning model, which is trained based on historical production data and is used to predict the direction of process parameter adjustment based on real-time detection data.
[0053] The quality information is transmitted to the data processing module for comprehensive analysis to obtain a comprehensive evaluation result on the quality of the functional layer. Specifically, this includes applying a pre-set machine learning model to professionally process the quality information. The machine learning model is built upon massive amounts of historical production data, which encompasses various functional layer quality information accumulated during past production processes, corresponding process parameter records, and final product performance test results. Through cleaning, preprocessing, feature extraction, and correlation analysis of this multi-dimensional data, and by employing appropriate algorithms to train and optimize the model, the model can accurately learn the inherent correlation between quality information and process parameters.
[0054] In real-time inspection scenarios, this well-trained machine learning model can quickly receive and integrate surface morphology, photophysical performance, and optical performance information. Through built-in analysis logic, it performs in-depth analysis of real-time inspection data, not only determining whether the functional layer quality is up to standard, but also accurately predicting the direction of process parameter adjustments based on data characteristics. For example, when poor crystallization quality of the functional layer is detected, the model can combine historical data to predict the specific direction requiring an increase in annealing temperature or an adjustment in coating speed. This provides scientific and efficient decision support for generating subsequent process adjustment instructions, making process parameter adjustments more targeted and forward-looking, and further improving the intelligent control level of the production line and the stability of product quality.
[0055] Corresponding to the online testing method for battery production described above, this invention also proposes an online testing device for battery production. Since the device embodiments of this invention correspond to the method embodiments described above, details not disclosed in the device embodiments can be referred to in the method embodiments described above, and will not be repeated here.
[0056] Figure 2 This is a schematic diagram of the structure of an online testing device for battery production provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, it includes: Deployment unit 21 is used to deploy integrated testing units based on multiple process stations on the production line; The detection unit 22 is used to perform at least two different types of online non-destructive testing on each functional layer of the battery to obtain quality information of the functional layer, wherein the quality information includes surface morphology information, photophysical performance information and optical performance information; Transmission unit 23 is used to transmit the quality information to the data processing module; Analysis unit 24 is used to perform comprehensive analysis of the quality information in the data processing module to obtain a comprehensive evaluation result regarding the quality of the functional layer; and The generation unit 25 is used to generate process adjustment instructions based on the comprehensive evaluation results, so as to control the operating parameters of the corresponding process station in the production line in real time.
[0057] Furthermore, in one possible implementation of this disclosure embodiment, the detection unit 22 is further configured to: include at least two of the at least two different types of online non-destructive testing, namely visual inspection, photoluminescence testing, and visible light absorption testing.
[0058] Furthermore, in one possible implementation of this disclosure, the detection unit 22 is further configured to: The surface image of the functional layer is acquired by the first detection unit, and the surface image is analyzed to identify surface defects and / or process feature states of a preset type; and The functional layer is subjected to spectral excitation and acquisition by the second detection unit, and the crystal quality and carrier behavior characteristics of the functional layer are evaluated based on the acquired spectral data.
[0059] Furthermore, in one possible implementation of this disclosure, the detection unit 22 is further configured to: Microstructural defects on the surface of the functional layer are identified using an image edge detection algorithm. When the size characteristics of the microstructural defects meet preset defect conditions, they are marked as defective products. The edge feature size formed by the laser etching process is detected by an image transformation algorithm. When the edge feature size exceeds the preset process tolerance range, a process warning signal is generated.
[0060] Furthermore, in one possible implementation of this disclosure, the detection unit 22 is further configured to: Based on the collected photoluminescence spectrum, determine the spectral peak intensity and half-width at half-maximum. And / or, calculate the lifetime parameters of the charge carriers in the functional layer using time-resolved spectral test data.
[0061] Furthermore, in one possible implementation of this disclosure, the analysis unit 24 is further configured to: The quality information is processed by a pre-set machine learning model, which is trained based on historical production data and is used to predict the direction of process parameter adjustment based on real-time detection data.
[0062] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.
[0063] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.
[0064] Figure 3 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0065] like Figure 3 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.
[0066] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0067] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the online testing method for battery production. For example, in some embodiments, the online testing method for battery production can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned online detection method for battery production by any other suitable means (e.g., by means of firmware).
[0068] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0069] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0070] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0071] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0072] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.
[0073] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.
[0074] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.
[0075] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0076] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.
Claims
1. An online testing method for battery production, characterized in that, include: Integrated testing units are deployed across multiple process stations on the production line. The detection unit performs at least two different types of online non-destructive testing on each functional layer of the battery to obtain quality information of the functional layer, wherein the quality information includes surface morphology information, photophysical performance information and optical performance information. The quality information is transmitted to the data processing module for comprehensive analysis to obtain a comprehensive evaluation result regarding the quality of the functional layer; and Based on the comprehensive evaluation results, process adjustment instructions are generated to control the operating parameters of the corresponding process stations in the production line in real time.
2. The method according to claim 1, characterized in that, The at least two different types of online non-destructive testing include at least two of visual inspection, photoluminescence testing, and visible light absorption testing.
3. The method according to claim 1, characterized in that, The process of performing at least two different types of online non-destructive testing on each functional layer of the battery through the detection unit includes: The surface image of the functional layer is acquired by the first detection unit, and the surface image is analyzed to identify surface defects and / or process feature states of a preset type; and The functional layer is subjected to spectral excitation and acquisition by the second detection unit, and the crystal quality and carrier behavior characteristics of the functional layer are evaluated based on the acquired spectral data.
4. The method according to claim 3, characterized in that, The step of analyzing the surface image to identify surface defects and / or process feature states of a preset type includes: Microstructural defects on the surface of the functional layer are identified using an image edge detection algorithm. When the size characteristics of the microstructural defects meet preset defect conditions, they are marked as defective products. The edge feature size formed by the laser etching process is detected by an image transformation algorithm. When the edge feature size exceeds the preset process tolerance range, a process warning signal is generated.
5. The method according to claim 3, characterized in that, The evaluation of the crystal quality and carrier behavior characteristics of the functional layer based on the collected spectral data includes: Based on the collected photoluminescence spectrum, determine the spectral peak intensity and half-width at half-maximum. And / or, calculate the lifetime parameters of the charge carriers in the functional layer using time-resolved spectral test data.
6. The method according to claim 1, characterized in that, The step of transmitting the quality information to the data processing module for comprehensive analysis to obtain a comprehensive evaluation result on the quality of the functional layer includes: The quality information is processed by a pre-set machine learning model, which is trained based on historical production data and is used to predict the direction of process parameter adjustment based on real-time detection data.
7. An online testing device for battery production, characterized in that, include: Deployment unit, used to deploy integrated testing units across multiple process stations on a production line; The detection unit is used to perform at least two different types of online non-destructive testing on each functional layer of the battery to obtain quality information of the functional layer, wherein the quality information includes surface morphology information, photophysical performance information and optical performance information; The transmission unit is used to transmit the quality information to the data processing module; An analysis unit is used to perform comprehensive analysis of the quality information in the data processing module to obtain a comprehensive evaluation result regarding the quality of the functional layer; and The generation unit is used to generate process adjustment instructions based on the comprehensive evaluation results, so as to control the operating parameters of the corresponding process station in the production line in real time.
8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.
9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.
10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.