Pole piece NMP residual quantity detection method, electronic equipment and computer program product

Abstract

The invention discloses a pole piece NMP residual quantity detection method, electronic equipment and a computer program product, and relates to the technical field of material analysis, the detection method comprises the following steps: obtaining a target battery pole piece, sampling the target battery pole piece to obtain a sampled pole piece, adopting a first preset instrument to carry out spectral measurement on the sampled pole piece, and calculating the NMP residual quantity of the pole piece; and obtaining target infrared spectrum data of the sampled pole piece, and inputting the target infrared spectrum data into a preset pole piece detection model to obtain the pole piece NMP residual quantity of the target battery pole piece. The technical problem that the detection efficiency of the NMP residual quantity of the pole piece is low in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of material analysis, and in particular to a method for detecting NMP residue in an electrode, an electronic device, and a computer program product. Background Art

[0002] N-Methylpyrrolidone (NMP) is a highly efficient organic solvent, which is used as a dispersed electrode material in the pulping process of lithium-ion battery manufacturing. In addition, after the baking stage of the coating process, the NMP in the pole piece should be fully removed, otherwise the residual NMP will cause sticking to the roller, thus affecting the rolling quality of the pole piece. At the same time, during the formation and capacity separation of the battery, NMP will react with the electrolyte to produce additional gas, affecting the performance of the battery cell and causing safety risks. Therefore, controlling the residual NMP in the pole piece is an important quality control point in the coating process.

[0003] At present, the quantitative analysis of NMP residue mainly relies on the use of Gas Chromatography-Mass Spectrometry (GC-MS). Although this process can provide accurate analysis results, its operation process is complicated and time-consuming. The entire test process includes: pole piece sampling, pole piece NMP ultrasonic extraction, filtration, purification, GC-MS separation of the test liquid, selection of NMP characteristic ions and other steps. The use of external standard method for quantitative analysis of NMP can accurately determine the residual amount of NMP in the pole piece, but the entire detection step is too complicated, time-consuming (i.e., poor effectiveness), and large manpower occupation. In addition, the complicated operation increases the possibility of misoperation, affecting the accuracy and reliability of the test.

[0004] Therefore, it is urgent to propose a simple and easy-to-operate method for detecting NMP residues to reduce the risk of misoperation and improve detection efficiency, accuracy and reliability.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiments of the present invention provide a method for detecting the residual amount of NMP in a pole piece, an electronic device, and a computer program product, so as to at least solve the technical problem of low efficiency in detecting the residual amount of NMP in a pole piece in the related art.

[0007] According to one aspect of an embodiment of the present invention, a method for detecting the residual amount of NMP in a pole piece is provided, comprising: obtaining a target battery pole piece, and sampling the target battery pole piece to obtain a sampled pole piece; using a first preset instrument to perform spectral measurement on the sampled pole piece to obtain target infrared spectrum data of the sampled pole piece; inputting the target infrared spectrum data into a preset pole piece detection model to obtain the residual amount of NMP in the pole piece of the target battery pole piece, wherein the preset pole piece detection model is pre-deployed in a test system, and the pole piece NMP residual amount is an amount of an organic solvent remaining on the battery pole piece.

[0008] Furthermore, before inputting the target infrared spectrum data into the preset electrode detection model to obtain the electrode NMP residual amount of the target battery electrode, it also includes: obtaining a historical battery electrode set, and performing stratified sampling on all historical battery electrodes to obtain a historical electrode sample set, wherein the historical electrode samples in the historical battery electrode sample set refer to battery electrodes with different NMP contents; for each historical electrode sample, the historical electrode sample is tested to obtain test data.

[0009] Furthermore, for each historical pole piece sample, the step of testing the historical pole piece sample to obtain test data includes: using a second preset instrument to perform an NMP residue test on the historical pole piece sample to obtain NMP residue data of the historical pole piece sample; using a first preset instrument to perform spectral measurement on the historical pole piece sample to obtain infrared spectrum data of the historical pole piece sample, wherein there is a one-to-one correspondence between the NMP residue data and the infrared spectrum data; and determining the test data based on the NMP residue data and the infrared spectrum data.

[0010] Furthermore, after testing the historical pole piece samples and obtaining the test data, it also includes: determining the raw materials of the historical pole piece samples, wherein the raw materials of the historical pole piece samples include at least: NMP, PVDF, CMC and SBR; obtaining benchmark infrared spectrum data of the raw materials, wherein the benchmark infrared spectrum data includes at least: NMP benchmark infrared spectrum data, PVDF benchmark infrared spectrum data, CMC benchmark infrared spectrum data and SBR benchmark infrared spectrum data; based on the benchmark infrared spectrum data, NMP residue data and infrared spectrum data of the historical pole piece samples, the initial pole piece detection model is trained to obtain a preset pole piece detection model.

[0011] Furthermore, before the initial pole piece detection model is trained based on the benchmark infrared spectrum data, NMP residue data and infrared spectrum data of historical pole piece samples to obtain the preset pole piece detection model, it also includes: constructing the initial pole piece detection model; adding the NMP residue data and the infrared spectrum data to the sample data set; obtaining the first preset number of sample data in the sample data set to obtain the training sample data set.

[0012] Furthermore, the initial pole piece detection model is trained based on the benchmark infrared spectrum data, NMP residue data and infrared spectrum data of historical pole piece samples to obtain a preset pole piece detection model, including: obtaining a second preset number of sample data in the sample data set to obtain a verification sample data set, wherein the sum of the first preset number and the second preset number is equal to the total amount of sample data in the sample data set; based on the benchmark infrared spectrum data and the training sample data set, the initial pole piece detection model is trained using a preset function, and the initial pole piece detection model is verified using the verification sample data set until the verification accuracy is greater than a preset threshold, thereby obtaining a preset pole piece detection model.

[0013] Furthermore, the method for detecting the residual amount of NMP in the pole piece also includes: when the verification accuracy is less than a preset threshold, increasing the training time of the initial pole piece detection model; or, increasing the sample data in the training sample data set to obtain an expanded training sample data set; training the initial pole piece detection model based on the benchmark infrared spectrum data and the expanded training sample data set.

[0014] Furthermore, after obtaining the preset pole piece detection model, it also includes: deploying the preset pole piece detection model to the test system.

[0015] According to another aspect of an embodiment of the present invention, a device for detecting the residual amount of NMP in a pole piece is also provided, comprising: a sampling unit, used to obtain a target battery pole piece, and sample the target battery pole piece to obtain a sampled pole piece; a measuring unit, used to perform spectral measurement on the sampled pole piece using a first preset instrument to obtain target infrared spectral data of the sampled pole piece; an input unit, used to input the target infrared spectral data into a preset pole piece detection model to obtain the residual amount of NMP in the pole piece of the target battery pole piece, wherein the preset pole piece detection model is pre-deployed in the test system, and the pole piece NMP residual amount is an amount of an organic solvent remaining on the battery pole piece.

[0016] Furthermore, the detection device includes: a first sampling module, which is used to obtain a historical battery pole piece set before inputting the target infrared spectrum data into a preset pole piece detection model to obtain the pole piece NMP residual amount of the target battery pole piece, and stratified sampling of all historical battery pole pieces to obtain a historical pole piece sample set, wherein the historical pole piece samples in the historical battery pole piece sample set refer to battery pole pieces with different NMP contents; a first testing module, which is used to test the historical pole piece samples for each historical pole piece sample to obtain test data.

[0017] Furthermore, the first test module includes: a first test submodule, used to use a second preset instrument to perform an NMP residue test on the historical pole piece samples to obtain the NMP residue data of the historical pole piece samples; a first measurement submodule, used to use the first preset instrument to perform spectral measurement on the historical pole piece samples to obtain infrared spectrum data of the historical pole piece samples, wherein there is a one-to-one correspondence between the NMP residue data and the infrared spectrum data; a first determination submodule, used to determine the test data based on the NMP residue data and the infrared spectrum data.

[0018] Furthermore, the detection device also includes: a first determination module, which is used to determine the raw materials of the historical pole piece samples after testing the historical pole piece samples and obtaining the test data, wherein the raw materials of the historical pole piece samples include at least: NMP, PVDF, CMC and SBR; a first acquisition module, which is used to obtain benchmark infrared spectrum data of the raw materials, wherein the benchmark infrared spectrum data includes at least: NMP benchmark infrared spectrum data, PVDF benchmark infrared spectrum data, CMC benchmark infrared spectrum data and SBR benchmark infrared spectrum data; a first training module, which is used to train the initial pole piece detection model based on the benchmark infrared spectrum data, NMP residue data and infrared spectrum data of the historical pole piece samples to obtain a preset pole piece detection model.

[0019] Furthermore, the detection device also includes: a first construction module, used to train the initial pole piece detection model based on the benchmark infrared spectrum data, NMP residue data and infrared spectrum data of historical pole piece samples to construct an initial pole piece detection model before obtaining a preset pole piece detection model; a first adding module, used to add the NMP residue data and infrared spectrum data to the sample data set; and a second acquisition module, used to acquire a first preset number of sample data in the sample data set to obtain a training sample data set.

[0020] Furthermore, the first training module includes: a first acquisition submodule, used to acquire a second preset number of sample data in the sample data set to obtain a verification sample data set, wherein the sum of the first preset number and the second preset number is equal to the total amount of sample data in the sample data set; a first verification submodule, used to train the initial pole piece detection model based on the benchmark infrared spectrum data and the training sample data set using a preset function, and verify the initial pole piece detection model using the verification sample data set until the verification accuracy is greater than a preset threshold, thereby obtaining a preset pole piece detection model.

[0021] Furthermore, the detection device also includes: a first adding module, used to increase the training time of the initial pole piece detection model when the verification accuracy is less than a preset threshold; a second adding module, used to increase the sample data in the training sample data set to obtain an expanded training sample data set; a second training module, used to train the initial pole piece detection model based on the benchmark infrared spectrum data and the expanded training sample data set.

[0022] Furthermore, the detection device also includes: a first deployment module, which is used to deploy the preset pole piece detection model to the test system after obtaining the preset pole piece detection model.

[0023] According to another aspect of an embodiment of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, any of the above-mentioned methods for detecting the residual NMP amount of an electrode is implemented.

[0024] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement any one of the above-mentioned methods for detecting the residual NMP content of an electrode.

[0025] In the present invention, a target battery pole piece is obtained, and a sample of the target battery pole piece is taken to obtain a sampled pole piece. A first preset instrument is used to perform spectral measurement on the sampled pole piece to obtain target infrared spectrum data of the sampled pole piece. The target infrared spectrum data is input into a preset pole piece detection model to obtain the pole piece NMP residue of the target battery pole piece, thereby solving the technical problem of low pole piece NMP residue detection efficiency in the related art.

[0026] In the present invention, a sampled electrode is obtained by sampling a target battery electrode, and a first preset instrument is used to perform spectral measurement on the sampled electrode to obtain infrared spectrum data of the sampled electrode. The infrared spectrum data is then input into a preset electrode detection model to detect the NMP residue in the target battery electrode, thereby simplifying the detection process, avoiding the complicated sample preparation and analysis steps in the traditional GC-MS detection method, greatly shortening the detection time, reducing the dependence on manpower, and reducing the risk of misoperation, thereby improving the efficiency, accuracy and reliability of detection, thereby achieving the technical effect of quickly and accurately detecting the N-methylpyrrolidone (NMP) residue on the target battery electrode. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0028] Figure 1 is a flow chart of an optional method for detecting the residual amount of NMP in a pole piece according to an embodiment of the present invention;

[0029] Figure 2 is a schematic diagram of an optional test process for the NMP residue of a pole piece according to an embodiment of the present invention;

[0030] Figure 3 is a schematic diagram of an optional model training process according to an embodiment of the present invention;

[0031] Figure 4 is a schematic diagram of an optional device for detecting residual NMP in a pole piece according to an embodiment of the present invention;

[0032] Figure 5 It is a hardware structure block diagram of an electronic device (or mobile device) for a method for detecting NMP residue in an electrode according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) collected and involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set between the system and the relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0036] In the present invention, since the main materials of the positive and negative electrode sheets and the conductive agent are high-purity inorganic substances, the organic substances involved are NMP, PVDF, CMC and SBR. For a stably operating production line, the physical and chemical properties of the organic raw materials are stable, and each phase in the electrode (i.e., different components of the electrode material) has a stable infrared characteristic spectrum. When the phase composition of the electrode changes, the infrared spectrum of the electrode will change. The present invention utilizes the correlation between the infrared characteristic spectrum of the stable phase in the electrode and the NMP residue, combines the first preset instrument to perform rapid spectral measurement, and inputs the measured infrared spectrum data into a pre-trained preset electrode detection model to obtain the NMP residue. Only two steps, electrode sampling and infrared spectrum testing, are required to complete the determination of the NMP residue in a very short time (e.g., within 10 minutes), which not only reduces labor costs and the risk of misoperation, but also ensures the accuracy and reliability of the detection.

[0037] The present invention is described in detail below in conjunction with various embodiments.

[0038] Embodiment 1

[0039] According to an embodiment of the present invention, an embodiment of a method for detecting the residual amount of NMP in an electrode is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] Figure 1 is a flow chart of an optional method for detecting the residual amount of NMP in a pole piece according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0041] Step S101, obtaining a target battery electrode sheet, and sampling the target battery electrode sheet to obtain a sampled electrode sheet.

[0042] Optionally, in the manufacturing process of lithium-ion batteries, the pole piece is one of the core components of the battery, which is composed of a current collector (usually a metal foil), an active material, a conductive agent and a binder, wherein the active material is a chemical substance used to store charge, and the conductive agent and the binder are used to improve the conductivity and maintain the structural stability of the material. The target battery pole piece refers to the pole piece sample of a specific batch or production line that needs to be tested for NMP residue.

[0043] In this embodiment, existing sampling equipment (such as automatic samplers, manual sampling tools, layered sampling devices, etc.) can be used to sample the target battery pole piece to obtain a sampled pole piece, which provides a basis for subsequent infrared spectroscopy analysis.

[0044] Step S102, using a first preset instrument to perform spectral measurement on the sampling electrode to obtain target infrared spectral data of the sampling electrode.

[0045] Optionally, the first preset instrument (such as Fourier Transform Infrared Spectroscopy Instrument (FTIR)) is an instrument capable of acquiring infrared spectra of samples at high speed and high precision. FTIR determines the chemical composition of a substance by measuring its absorption of infrared light. It has unique recognition capabilities for organic substances in battery electrodes such as NMP, PVDF (Polyvinylidene fluoride), CMC (Carboxymethylcellulose) and SBR (Styrene-Butadiene Rubber).

[0046] In this embodiment, in order to identify and quantitatively analyze the residual NMP through a specific infrared absorption peak, a first preset instrument can be used to perform spectral measurement on the sampling electrode to obtain target infrared spectrum data of the sampling electrode.

[0047] Step S103, inputting the target infrared spectrum data into a preset pole piece detection model to obtain the pole piece NMP residue of the target battery pole piece, wherein the preset pole piece detection model is pre-deployed in the test system, and the pole piece NMP residue is the amount of an organic solvent remaining on the battery pole piece.

[0048] In this embodiment, the target infrared spectrum data is input into a preset pole piece detection model (i.e., a detection model pre-trained with a large amount of pole piece infrared spectrum data and corresponding NMP residue data). The preset pole piece detection model can predict the residual amount of NMP based on the input infrared spectrum data.

[0049] It should be noted that the preset pole piece detection model can also output the content of other organic matter in the battery pole piece (such as PVDF content, CMC content and SBR content).

[0050] In this embodiment, the preset electrode detection model is pre-deployed in the test system, which can quickly obtain the prediction result of NMP residue, eliminate the cumbersome sample preparation and instrument analysis steps in the traditional test method, and greatly reduce the labor cost and test time.

[0051] Figure 2 is a schematic diagram of an optional test process for the residual NMP content of a pole piece according to an embodiment of the present invention, such as Figure 2 As shown, firstly, the electrode piece (i.e., the target electrode piece) is sampled to obtain the sampled electrode piece, and then the FTIR test is performed to obtain the infrared spectrum data of the sampled electrode piece. After that, the infrared spectrum data is input into the calculation model (i.e., the preset electrode piece detection model), and the NMP residue can be output.

[0052] In summary, by sampling the target battery electrode, a sampled electrode is obtained, and FTIR is used to perform spectral measurement on the sampled electrode to obtain infrared spectral data. Then, the obtained infrared spectral data is analyzed using a preset electrode detection model, thereby achieving rapid and accurate detection of NMP residues, thereby solving the technical problem of low efficiency in detecting NMP residues in electrode pieces in related technologies.

[0053] In order to accurately obtain test data, in the method for detecting the residual NMP content of the electrode provided in Example 1 of the present application, a set of historical battery electrodes is obtained, and stratified sampling is performed on all historical battery electrodes to obtain a set of historical electrode samples, wherein the historical electrode samples in the set of historical battery electrode samples refer to battery electrodes with different NMP contents; for each historical electrode sample, the historical electrode sample is tested to obtain test data.

[0054] Optionally, the historical battery electrode collection refers to electrode samples from previous production processes, covering various NMP residue conditions that may be encountered in battery production. These electrode samples are selected from different production batches, different drying conditions and different production line sections to ensure the diversity and representativeness of the samples.

[0055] In this embodiment, the dried historical battery pole pieces are sampled in layers to ensure that the selected pole piece sample set contains pole pieces with different NMP contents (such as completely free of NMP, NMP residues close to the upper limit (that is, the maximum NMP residue allowed in the pole piece without affecting the battery performance and safety, which can be determined based on the specific design of the battery, the materials used, and the internal quality control standards of the battery manufacturer), NMP residues slightly exceeding the upper limit, and NMP residues far exceeding the upper limit), so that subsequent test data can fully reflect the changes in NMP residues, and for each historical pole piece sample, NMP residue tests and spectral measurements are performed on the historical pole piece samples to obtain test data.

[0056] In order to improve the accuracy of determining test data, in the method for detecting the NMP residue in the electrode provided in Example 1 of the present application, a second preset instrument is used to perform NMP residue test on historical electrode samples to obtain NMP residue data of the historical electrode samples; a first preset instrument is used to perform spectral measurement on the historical electrode samples to obtain infrared spectrum data of the historical electrode samples, wherein there is a one-to-one correspondence between the NMP residue data and the infrared spectrum data; and the test data is determined based on the NMP residue data and the infrared spectrum data.

[0057] In this embodiment, for each historical pole piece sample in the historical pole piece sample set, a standard gas chromatograph-mass spectrometer (GC-MS) is first used to accurately measure the NMP residue to obtain the NMP content data of each historical pole piece sample. At the same time, a Fourier transform infrared spectrometer (FTIR) is used to measure the infrared spectrum of the same historical pole piece sample to obtain its infrared spectrum data. Based on the NMP residue data and the infrared spectrum data, the test data of each historical pole piece sample is determined. The purpose is to establish a correlation data set between the NMP residue and the pole piece infrared spectrum data for training the initial pole piece detection model.

[0058] In order to accurately obtain the preset pole piece detection model, in the pole piece NMP residue detection method provided in Example 1 of the present application, the raw materials of the historical pole piece samples are determined, wherein the raw materials of the historical pole piece samples include at least: NMP, PVDF, CMC and SBR; the benchmark infrared spectrum data of the raw materials are obtained, wherein the benchmark infrared spectrum data at least includes: NMP benchmark infrared spectrum data, PVDF benchmark infrared spectrum data, CMC benchmark infrared spectrum data and SBR benchmark infrared spectrum data; based on the benchmark infrared spectrum data, NMP residue data and infrared spectrum data of historical pole piece samples, the initial pole piece detection model is trained to obtain the preset pole piece detection model.

[0059] Optionally, it is necessary to clarify the types of raw materials contained in the historical pole piece samples, which raw materials include at least NMP, PVDF, CMC and SBR. The purpose of determining the raw materials is to ensure that the infrared spectrum data obtained subsequently can fully reflect the characteristics of each component in the pole piece.

[0060] In this embodiment, a Fourier transform infrared spectrometer can be used to perform infrared spectrum measurement on the determined raw materials, and NMP benchmark infrared spectrum data, PVDF benchmark infrared spectrum data, CMC benchmark infrared spectrum data, and SBR benchmark infrared spectrum data can be obtained. The acquisition of the benchmark infrared spectrum data is to establish the characteristic spectrum lines of each raw material in the infrared spectrum, and these characteristic spectrum lines will be used in subsequent model training to identify and quantitatively analyze the content of each raw material in the pole piece.

[0061] In this embodiment, based on the infrared spectrum data of historical pole piece samples and the corresponding NMP residue data, the initial pole piece detection model (such as a deep neural network model) can be trained in combination with the benchmark infrared spectrum data of each raw material to obtain a preset pole piece detection model. Through a large amount of historical data input, the model can learn the complex relationship between infrared spectrum and NMP residue, thereby achieving fast and accurate detection.

[0062] In order to obtain a training sample data set with certainty, in the method for detecting the NMP residue in the electrode provided in Example 1 of the present application, an initial electrode detection model is constructed; the NMP residue data and the infrared spectrum data are added to the sample data set; and the first preset number of sample data in the sample data set is obtained to obtain a training sample data set.

[0063] Optionally, an initial pole piece detection model can be constructed using a deep learning framework, which is a neural network designed to predict the residual amount of NMP by analyzing the infrared spectral data of the pole piece.

[0064] In this embodiment, NMP residue data and infrared spectrum data are added to the sample data set, and a first preset number of sample data (such as 2 / 3 of the sample data in the sample data set) can be randomly selected to form a training sample data set.

[0065] In order to improve the accuracy of the preset pole piece detection model, in the pole piece NMP residue detection method provided in Example 1 of the present application, a second preset number of sample data in the sample data set is obtained to obtain a verification sample data set, wherein the sum of the first preset number and the second preset number is equal to the total amount of sample data in the sample data set; based on the benchmark infrared spectrum data and the training sample data set, the initial pole piece detection model is trained using a preset function, and the initial pole piece detection model is verified using the verification sample data set until the verification accuracy is greater than the preset threshold, thereby obtaining a preset pole piece detection model.

[0066] In this embodiment, a second preset number of sample data in the sample data set (such as 1 / 3 of the sample data in the sample data set) is obtained to obtain a verification sample data set. The sum of the first preset number and the second preset number should be equal to the total amount of sample data in the sample data set. The verification sample data set is established to objectively verify the performance of the model after the model training is completed.

[0067] In this embodiment, based on the benchmark infrared spectrum data and the training sample data set, a preset function (such as the Lorentzian-Gaussian function (i.e., the Lorentz-Gaussian function)) is used to train and fit the initial pole piece detection model, and the verification sample data set is used to verify the initial pole piece detection model until the verification accuracy is greater than a preset threshold (such as 99.7%), so as to obtain a preset pole piece detection model, thereby ensuring that the model can not only perform well on the training data, but also achieve accurate NMP residue prediction in actual, unknown sample data.

[0068] In order to further improve the accuracy of the preset pole piece detection model, in the pole piece NMP residue detection method provided in Example 1 of the present application, when the verification accuracy is less than the preset threshold, the training time of the initial pole piece detection model is increased; or, the sample data in the training sample data set is increased to obtain an expanded training sample data set; the initial pole piece detection model is trained based on the benchmark infrared spectrum data and the expanded training sample data set.

[0069] In this embodiment, when the verification accuracy is less than a preset threshold, the training time of the initial pole piece detection model can be increased. The training time directly affects the learning degree of the model. A longer training time means that the model has more opportunities to optimize its internal parameters to fit the training data more accurately.

[0070] Optionally, a larger training data set (i.e., an expanded training sample data set) can be constructed by adding sample data to enhance the training basis of the model, and then the initial pole piece detection model can be retrained based on the baseline infrared spectrum data and the expanded training sample data set.

[0071] In order to improve the detection rate of the preset pole piece detection model, in the method for detecting the residual NMP amount of the pole piece provided in the first embodiment of the present application, the preset pole piece detection model is deployed to the test system.

[0072] Optionally, in order to ensure that the model can run efficiently and without faults in the application, the preset pole piece detection model can be deployed to the test system, and before the preset pole piece detection model is deployed to the test system, the software and hardware environment of the test system can be prepared to ensure that the preset pole piece detection model can run smoothly.

[0073] Figure 3 is a schematic diagram of an optional model training process according to an embodiment of the present invention, such as Figure 3 As shown, firstly, the pole piece is sampled to obtain a historical pole piece sample set, and then a GC-MS test is performed on the historical pole piece samples in the historical pole piece sample set to obtain the NMP residue of the historical pole piece samples, and then an FTIR test is performed on the historical pole piece samples in the historical pole piece sample set to obtain the infrared spectrum of the historical pole piece samples, and then a database (i.e., a sample data set) can be established according to the NMP residue and the infrared spectrum, and a model (i.e., an initial pole piece detection model) and a training model are established. The model is trained according to the data in a first preset number of databases (i.e., a training sample data set), and then the model is verified according to the data in a second preset number of databases (i.e., a verification sample data set). Whether the model is valid is determined based on whether the verification accuracy is greater than a preset threshold. When the verification accuracy is greater than the preset threshold, a valid model (i.e., a preset pole piece detection model) is obtained. When the verification accuracy is less than the preset threshold, the model is determined to be invalid and the model is retrained.

[0074] In an embodiment of the present invention, by training a preset pole piece detection model that takes pole piece infrared spectrum data as input and NMP residue as output, and deploying the preset pole piece detection model to a test system, the NMP residue of the pole piece can be quickly detected using the preset pole piece detection model. It is only necessary to first perform pole piece sampling and use FTIR to obtain the infrared spectrum data of the pole piece, and then input the obtained infrared spectrum data into the preset pole piece detection model. The NMP residue detection can be completed in a short time, thereby greatly shortening the detection time and reducing the risk of misoperation in the detection.

[0075] The following is a detailed description in conjunction with another embodiment.

[0076] Embodiment 2

[0077] The device for detecting the residual NMP amount of an electrode provided in this embodiment includes a plurality of implementation units, each of which corresponds to each implementation step in the above-mentioned embodiment 1.

[0078] Figure 4 is a schematic diagram of an optional detection device for the residual amount of NMP in a pole piece according to an embodiment of the present invention, such as Figure 4 As shown, the device for detecting the residual amount of NMP in the pole piece may include: a sampling unit 40, a measuring unit 41, and an input unit 42.

[0079] The sampling unit 40 is used to obtain the target battery electrode piece and sample the target battery electrode piece to obtain the sampled electrode piece;

[0080] The measuring unit 41 is used to perform spectrum measurement on the sampling pole piece by using a first preset instrument to obtain target infrared spectrum data of the sampling pole piece;

[0081] The input unit 42 is used to input the target infrared spectrum data into the preset pole piece detection model to obtain the pole piece NMP residue of the target battery pole piece, wherein the preset pole piece detection model is pre-deployed in the test system, and the pole piece NMP residue is the amount of an organic solvent remaining on the battery pole piece.

[0082] The above-mentioned detection device for the residual NMP amount of the electrode piece can obtain the target battery electrode piece through the sampling unit 40, and sample the target battery electrode piece to obtain the sampled electrode piece, and use the first preset instrument to perform spectral measurement on the sampled electrode piece through the measuring unit 41 to obtain the target infrared spectrum data of the sampled electrode piece, and input the target infrared spectrum data into the preset electrode piece detection model through the input unit 42 to obtain the electrode piece NMP residual amount of the target battery electrode piece.

[0083] Optionally, the detection device includes: a first sampling module, used to obtain a historical battery pole piece set before inputting the target infrared spectrum data into a preset pole piece detection model to obtain the pole piece NMP residual amount of the target battery pole piece, and perform stratified sampling on all historical battery pole pieces to obtain a historical pole piece sample set, wherein the historical pole piece samples in the historical battery pole piece sample set refer to battery pole pieces with different NMP contents; a first testing module, used to test each historical pole piece sample to obtain test data.

[0084] Optionally, the first test module includes: a first test submodule, used to use a second preset instrument to perform an NMP residue test on a historical pole piece sample to obtain NMP residue data of the historical pole piece sample; a first measurement submodule, used to use a first preset instrument to perform spectral measurement on the historical pole piece sample to obtain infrared spectrum data of the historical pole piece sample, wherein there is a one-to-one correspondence between the NMP residue data and the infrared spectrum data; and a first determination submodule, used to determine the test data based on the NMP residue data and the infrared spectrum data.

[0085] Optionally, the detection device also includes: a first determination module, used to determine the raw materials of the historical pole piece samples after testing the historical pole piece samples and obtaining test data, wherein the raw materials of the historical pole piece samples include at least: NMP, PVDF, CMC and SBR; a first acquisition module, used to obtain benchmark infrared spectrum data of the raw materials, wherein the benchmark infrared spectrum data includes at least: NMP benchmark infrared spectrum data, PVDF benchmark infrared spectrum data, CMC benchmark infrared spectrum data and SBR benchmark infrared spectrum data; a first training module, used to train the initial pole piece detection model based on the benchmark infrared spectrum data, NMP residue data and infrared spectrum data of the historical pole piece samples to obtain a preset pole piece detection model.

[0086] Optionally, the detection device also includes: a first construction module, used to train the initial pole piece detection model based on benchmark infrared spectrum data, NMP residue data and infrared spectrum data of historical pole piece samples to construct an initial pole piece detection model before obtaining a preset pole piece detection model; a first adding module, used to add NMP residue data and infrared spectrum data to a sample data set; and a second acquisition module, used to acquire a first preset number of sample data in the sample data set to obtain a training sample data set.

[0087] Optionally, the first training module includes: a first acquisition submodule, used to acquire a second preset number of sample data in the sample data set to obtain a verification sample data set, wherein the sum of the first preset number and the second preset number is equal to the total amount of sample data in the sample data set; a first verification submodule, used to train an initial pole piece detection model based on benchmark infrared spectrum data and a training sample data set using a preset function, and verify the initial pole piece detection model using a verification sample data set until the verification accuracy is greater than a preset threshold, thereby obtaining a preset pole piece detection model.

[0088] Optionally, the detection device also includes: a first adding module, used to increase the training time of the initial pole piece detection model when the verification accuracy is less than a preset threshold; a second adding module, used to increase the sample data in the training sample data set to obtain an expanded training sample data set; a second training module, used to train the initial pole piece detection model based on the benchmark infrared spectrum data and the expanded training sample data set.

[0089] Optionally, the detection device further includes: a first deployment module, configured to deploy the preset pole piece detection model to the test system after obtaining the preset pole piece detection model.

[0090] The above-mentioned electrode NMP residual amount detection device may also include a processor and a memory. The above-mentioned sampling unit 40, measuring unit 41, input unit 42, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0091] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the target infrared spectrum data is input into the preset pole piece detection model by adjusting the kernel parameters to obtain the pole piece NMP residue of the target battery pole piece.

[0092] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0093] According to another aspect of an embodiment of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, any of the above-mentioned methods for detecting the residual NMP amount of an electrode is implemented.

[0094] When the computer program product is executed on a data processing device, it is suitable for executing a program that is initialized with the following method steps: obtaining a target battery electrode and sampling the target battery electrode to obtain a sampled electrode; using a first preset instrument to perform spectral measurement on the sampled electrode to obtain target infrared spectrum data of the sampled electrode; inputting the target infrared spectrum data into a preset electrode detection model to obtain the electrode NMP residue of the target battery electrode.

[0095] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement the above-mentioned method for detecting the NMP residue in the electrode.

[0096] Figure 5 1 is a hardware structure block diagram of an electronic device (or mobile device) for detecting the residual NMP content of an electrode according to an embodiment of the present invention. Figure 5 As shown, the electronic device may include one or more processors (e.g., Figure 5The processor 502a, processor 502b, ..., processor 502n, etc., which may include but are not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 504 for storing data. In addition, it may also include: a display, an input / output interface (I / 0 interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / 0 interface), a network interface, a keyboard, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 5 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 5 More or fewer components as shown, or with Figure 5 Different configurations shown.

[0097] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0098] The embodiments or examples of the present disclosure are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0099] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0100] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0101] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0102] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0103] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0104] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting the residual amount of NMP in a pole piece, characterized in that: Applied to test systems, including: Acquire a target battery electrode piece, and sample the target battery electrode piece to obtain a sample electrode piece; Using a first preset instrument to perform spectrum measurement on the sampling pole piece to obtain target infrared spectrum data of the sampling pole piece; The target infrared spectrum data is input into a preset pole piece detection model to obtain the pole piece NMP residue of the target battery pole piece, wherein the preset pole piece detection model is pre-deployed in the test system, and the pole piece NMP residue is the amount of an organic solvent remaining on the battery pole piece.

2. The method for detecting the residual amount of NMP in the pole piece according to claim 1, characterized in that: Before inputting the target infrared spectrum data into a preset pole piece detection model to obtain the pole piece NMP residue of the target battery pole piece, the method further includes: Acquire a historical battery pole piece set, and perform stratified sampling on all the historical battery pole pieces to obtain a historical pole piece sample set, wherein the historical pole piece samples in the historical battery pole piece sample set refer to battery pole pieces with different NMP contents; For each of the historical pole piece samples, the historical pole piece sample is tested to obtain test data.

3. The method for detecting the residual amount of NMP in the pole piece according to claim 2, characterized in that: For each of the historical electrode samples, the step of testing the historical electrode sample to obtain test data includes: Using a second preset instrument to perform an NMP residue test on the historical pole piece sample to obtain NMP residue data of the historical pole piece sample; Using the first preset instrument to perform spectral measurement on the historical pole piece sample to obtain infrared spectrum data of the historical pole piece sample, wherein the NMP residue data and the infrared spectrum data have a one-to-one correspondence relationship; The test data is determined based on the NMP residual data and the infrared spectrum data.

4. The method for detecting the residual amount of NMP in the pole piece according to claim 3, characterized in that: After testing the historical pole piece samples and obtaining the test data, the following steps are also included: Determining the raw materials of the historical pole piece samples, wherein the raw materials of the historical pole piece samples at least include: NMP, PVDF, CMC and SBR; Obtaining benchmark infrared spectrum data of the raw materials, wherein the benchmark infrared spectrum data at least includes: NMP benchmark infrared spectrum data, PVDF benchmark infrared spectrum data, CMC benchmark infrared spectrum data, and SBR benchmark infrared spectrum data; The initial pole piece detection model is trained based on the benchmark infrared spectrum data, the NMP residue data and the infrared spectrum data of the historical pole piece samples to obtain a preset pole piece detection model.

5. The method for detecting the residual amount of NMP in the pole piece according to claim 4, characterized in that: Before training the initial pole piece detection model based on the reference infrared spectrum data, the NMP residue data and the infrared spectrum data of the historical pole piece samples to obtain the preset pole piece detection model, the method further includes: Constructing the initial pole piece detection model; Adding the NMP residual data and the infrared spectrum data to a sample data set; A first preset number of sample data in the sample data set is obtained to obtain a training sample data set.

6. The method for detecting the residual amount of NMP in the pole piece according to claim 5, characterized in that: The step of training an initial pole piece detection model based on the reference infrared spectrum data, the NMP residue data and the infrared spectrum data of the historical pole piece samples to obtain a preset pole piece detection model includes: Acquire a second preset number of the sample data in the sample data set to obtain a verification sample data set, wherein the sum of the first preset number and the second preset number is equal to the total amount of sample data in the sample data set; Based on the benchmark infrared spectrum data and the training sample data set, the initial pole piece detection model is trained using a preset function, and the initial pole piece detection model is verified using the verification sample data set until the verification accuracy is greater than a preset threshold, thereby obtaining the preset pole piece detection model.

7. The method for detecting the residual amount of NMP in the pole piece according to claim 6, characterized in that: The method for detecting the residual amount of NMP in the pole piece also includes: When the verification accuracy is less than the preset threshold, increasing the duration of training the initial pole piece detection model; or, Adding the sample data in the training sample data set to obtain an expanded training sample data set; The initial pole piece detection model is trained based on the benchmark infrared spectrum data and the expanded training sample data set.

8. The method for detecting the residual amount of NMP in the pole piece according to claim 4, characterized in that: After obtaining the preset pole piece detection model, it also includes: deploying the preset pole piece detection model to the test system.

9. A computer program product, characterized in that It includes a non-volatile computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method for detecting the residual NMP content of the electrode piece as described in any one of claims 1 to 8.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for detecting the residual NMP content of the electrode piece as described in any one of claims 1 to 8.

Images