Model training methods, material testing methods, systems and equipment

Abstract

The present application is applicable to the field of spectral detection technology and provides a model training method, a material detection method, a system, and an apparatus, comprising: obtaining a sample training set; wherein each sample data in the sample training set includes plasma radiation spectrum data, plasma characteristic data, and sample label information corresponding to each sample; using the plasma radiation spectrum data and the plasma characteristic data of each sample as input and the sample label information corresponding to each sample as output, to train a neural network model; the plasma radiation spectrum data includes first plasma radiation spectrum data of each sample and / or plasma radiation spectrum data obtained after preprocessing the first plasma radiation spectrum data. The present application improves the accuracy of material classification.

Description

Technical Field

[0001] The present application belongs to the field of spectral detection technology, and in particular relates to a model training method, a material detection method, a system and an apparatus. Background Art

[0002] In recent years, laser-induced breakdown spectroscopy (LIBS) has attracted widespread attention from researchers. Due to its many advantages such as minimal damage detection, low detection limit, rapid detection, high sensitivity, and real-time analysis, it has been applied in many fields such as industry, agriculture, biology, archaeology, and aerospace.

[0003] LIBS is widely used in industrial testing. It can distinguish materials by analyzing variations in spectral characteristics caused by differences in element types and content. However, due to the complexity and variability of LIBS spectral signals, they are affected not only by the type and content of elements in the sample, but also by interference from various external factors, such as laser energy, plasma state, sample surface conditions, and environmental factors. These interference factors result in low accuracy in LIBS material classification. Summary of the Invention

[0004] The embodiments of the present application provide a model training method, a material detection method, a system, and an apparatus to solve or improve the technical problem of low accuracy in material classification using LIBS technology in related technologies.

[0005] In a first aspect, an embodiment of the present application provides a neural network model training method, comprising:

[0006] Acquire a sample training set; wherein each sample data in the sample training set includes plasma radiation spectrum data, plasma characteristic data, and sample label information corresponding to each sample;

[0007] The neural network model is obtained by training using the plasma radiation spectrum data and the plasma characteristic data of each sample as input and the sample label information corresponding to each sample as output;

[0008] The plasma radiation spectrum data includes the first plasma radiation spectrum data of each sample and / or plasma radiation spectrum data obtained by preprocessing the first plasma radiation spectrum data.

[0009] In a possible implementation of the first aspect, the plasma radiation spectrum data includes plasma spectrum characteristic data of each sample;

[0010] The plasma spectrum characteristic data of each sample is obtained by performing data dimension reduction processing on the first plasma radiation spectrum data of each sample or the plasma radiation spectrum data obtained after the preprocessing;

[0011] The method comprises: taking the plasma radiation spectrum data and the plasma characteristic data of each sample as input and the sample label information corresponding to each sample as output, training a neural network model; comprising:

[0012] The plasma spectrum characteristic data and the plasma characteristic data of each sample are used as input, and the sample label information corresponding to each sample is used as output to train a neural network model.

[0013] In a possible implementation of the first aspect, the plasma characteristic data includes: physical information characteristics of the plasma image, shape characteristics of the plasma image, and texture characteristics of the plasma image;

[0014] The physical information features of the plasma image, the shape features of the plasma image, and the texture features of the plasma image are obtained based on plasma event flow data;

[0015] And / or, the data dimensionality reduction processing method includes principal component analysis, random projection, multi-scale scaling or non-negative matrix decomposition;

[0016] And / or, the label information includes a model number;

[0017] And / or, the plasma spectrum characteristic data of each sample includes a plurality of main component plasma spectrum characteristic data of each sample, and the cumulative contribution rate of the plurality of main components in the plurality of main component plasma spectrum characteristic data of each sample is greater than or equal to a preset cumulative contribution rate threshold;

[0018] And / or, the preprocessing includes background removal, baseline correction and / or noise reduction;

[0019] And / or, the physical information features of the plasma image include the plasma image area, the circularity of the plasma image and / or the number of events in the plasma image.

[0020] In a possible implementation of the first aspect, the neural network model training method further includes acquiring the plasma characteristic data; acquiring the plasma characteristic data includes:

[0021] Acquiring plasma event flow data of each sample;

[0022] reconstructing a plasma image based on the plasma event flow data;

[0023] Plasma characteristic data of each sample is extracted based on the plasma image.

[0024] In a possible implementation of the first aspect, reconstructing a plasma image according to the plasma event flow data includes:

[0025] Reconstructing a plasma image based on the plasma event flow data using a deep neural network, a spiking neural network, cluster analysis, or event accumulation;

[0026] The plasma image is a first plasma image generated based on the plasma event flow data or a Gaussian filtered plasma image obtained by performing Gaussian filtering on the first plasma image;

[0027] The step of extracting plasma characteristic data of each sample based on the plasma image comprises:

[0028] Extracting plasma shape contour features based on the plasma image to form a plasma shape contour, and calculating the area and circularity of a region enclosed by the plasma shape contour to obtain the plasma image area and circularity;

[0029] Image processing is performed on the plasma image to obtain shape features and texture features of the plasma image.

[0030] In a second aspect, an embodiment of the present application provides a material detection method, comprising:

[0031] Acquiring detection data of each material to be classified; the detection data includes plasma radiation spectrum data and plasma characteristic data of the material;

[0032] The detection data of each material to be classified is input into a neural network model obtained by using the neural network model training method, and label information of each material is output.

[0033] In a possible implementation of the second aspect,

[0034] The plasma radiation spectrum data of each material includes the first plasma radiation spectrum data of each material and / or the plasma radiation spectrum data obtained by preprocessing the first plasma radiation spectrum data;

[0035] The plasma characteristic data of each material includes: physical information characteristics of the plasma image, shape characteristics of the plasma image, and texture characteristics of the plasma image.

[0036] In a possible implementation of the second aspect, the plasma radiation spectrum data of each material includes plasma spectrum characteristic data of each material;

[0037] The plasma spectrum characteristic data of each material is obtained by performing data dimension reduction processing on the first plasma radiation spectrum data of each material or the plasma radiation spectrum data obtained after the preprocessing;

[0038] And / or, the plasma spectrum characteristic data of each material includes multiple main component plasma spectrum characteristic data of each material, and the cumulative contribution rate of the multiple main components in the multiple main component plasma spectrum characteristic data of each material is greater than or equal to a preset cumulative contribution rate threshold.

[0039] In a third aspect, an embodiment of the present application provides a laser induced breakdown spectroscopy system, comprising:

[0040] Optical path system;

[0041] Laser, connected to the optical path system;

[0042] a delay controller connected to the laser;

[0043] The spectrometer is connected to the computer, the optical path system and the delay controller respectively;

[0044] Dynamic vision sensors for acquiring plasma event flow data of materials or samples;

[0045] and a computer, respectively connected to the spectrometer and the dynamic vision sensor, for:

[0046] Acquire detection data of each material to be classified; the detection data includes plasma radiation spectrum data and plasma characteristic data of the material; the plasma characteristic data is obtained based on processing the plasma event flow data;

[0047] The detection data of each material to be classified is input into a neural network model obtained by using the neural network model training method, and label information of each material is output.

[0048] In a fourth aspect, an embodiment of the present application provides a terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the model training method and the material detection method when executing the computer program.

[0049] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising: the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the model training method and the material detection method.

[0050] In a sixth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the model training method and material detection method described in any one of the above-mentioned first aspects.

[0051] It can be understood that the beneficial effects of the second to sixth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0052] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0053] The model training method, material detection method, system and equipment of the embodiments of the present application use the plasma radiation spectrum data and the plasma characteristic data of each sample as input, and the sample label information corresponding to each sample as output. The neural network model obtained by training is used to perform material detection, which can accurately classify materials and improve the accuracy of material detection and classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0055] Figure 1 Schematic diagram of a laser induced breakdown spectroscopy system provided in one embodiment of the present application.

[0056] Figure 2 It is a flowchart of a neural network model training method according to an embodiment of the present application.

[0057] Figure 3 It is a structural diagram of the neural network model framework.

[0058] Figure 4 This is a schematic diagram of the principal component analysis of 900 LIBS test spectra of carbon steel samples.

[0059] Figure 5 This is a structural diagram of the contribution rate and cumulative contribution rate of the main components of a total of 900 LIBS test spectra of carbon steel samples.

[0060] Figure 6 It is a flowchart of a neural network model training method according to another embodiment of the present application.

[0061] Figure 7 It is a flowchart of a neural network model training method according to another embodiment of the present application.

[0062] Figure 8 It is a flow chart of the method for obtaining the plasma characteristic data.

[0063] Figure 9 This is a plasma image restored based on plasma event flow data in one embodiment of the present application; wherein (a) is the original plasma grayscale image reconstructed based on the plasma event flow data; (b) is the Gaussian filtered plasma image obtained by Gaussian filtering the image (a).

[0064] Figure 10 It is a flow chart of a material detection method according to an embodiment of the present application.

[0065] Figure 11 It is a structural diagram of a neural network model training system according to an embodiment of the present application.

[0066] Figure 12 It is a structural diagram of a material detection system according to an embodiment of the present application.

[0067] Figure 13 This is a diagram of the confusion matrix of the best classification effect obtained in verifying the model effect. DETAILED DESCRIPTION

[0068] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0069] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0070] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0071] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0072] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0073] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0074] Before introducing the embodiments of the present application, the relevant names in the embodiments of the present application are explained:

[0075] 1. Laser-induced breakdown spectroscopy (LIBS): LIBS uses high-energy laser pulses to ablate the sample surface, forming a high-temperature, high-electron-density plasma. As the plasma cools, some of its energy is radiated as a spectrum. The spectral signals are collected by a spectrometer, which provides information about the wavelength and intensity of the spectral lines. The wavelength of the spectral line can be used to determine the elemental identity of the line, while the intensity of the spectral line can, to a certain extent, reflect the elemental content.

[0076] LIBS is widely used in industrial testing. It can distinguish materials by analyzing variations in spectral characteristics caused by differences in element types and content. However, due to the complexity and variability of LIBS spectral signals, they are affected not only by the type and content of elements in the sample, but also by interference from various external factors, such as laser energy, plasma state, sample surface conditions, and environmental factors. These interference factors result in low accuracy in LIBS material classification.

[0077] 2. Plasma event stream data: Plasma event stream data refers to the real-time, continuously changing data stream collected from the plasma as high-energy laser pulses ablate the sample surface, forming a high-temperature, high-electron-density plasma. This data can be collected using high-speed cameras or dynamic vision sensors.

[0078] 3. Plasma radiation spectrum data: High-energy laser pulses ablate the sample surface to form a high-temperature, high-electron-density plasma. During the cooling process of the plasma, part of the energy is radiated in the form of a spectrum, which is collected by a spectrometer to form a spectral signal.

[0079] 4. Plasma image: Generated based on reconstruction of plasma event stream data. For example, a dynamic vision sensor can be used to acquire plasma event stream data. It is understood that a dynamic vision sensor, unlike a traditional camera or high-speed camera, does not output a frame image. Instead, it outputs pixel coordinates (x, y), a timestamp t, and an event polarity p. When the light intensity changes beyond a threshold, the pixel responds, generating an ON event (p=1) when the brightness increases and an OFF event (p=0) when the brightness decreases. The dynamic vision sensor outputs these events and data as event stream data.

[0080] 5. Plasma Characteristic Data: This refers to a collection of parameters and information that can reflect the various properties and states of a plasma. Plasma characteristic data can include the number of events derived from plasma event stream data, a plasma image reconstructed from the plasma event stream data, and the plasma image area, shape, and texture characteristics derived from the plasma image.

[0081] 6. Event Count: Generated based on plasma event stream data. Plasma event stream data can be generated by accumulating event data over a specified period of time using a dynamic vision sensor to monitor the plasma generated by laser ablation. Each time the brightness of the plasma exceeds the threshold of the dynamic vision sensor during laser ablation, an event is recorded. Pixel data for each event is recorded, including the pixel point, timestamp, and event polarity. Events generated over a specified period of time are accumulated to generate plasma event stream data, and the number of events generated over a specified period of time is counted to generate the event count.

[0082] 7. Circularity of plasma image: refers to the degree to which the outline of the plasma image is close to a circle.

[0083] 8. Shape features of plasma images: refers to shape-related features in plasma images such as arcs, angles, straight lines, broken lines, etc.

[0084] 9. Texture features of plasma images: These describe the spatial distribution of grayscale, color, or brightness of pixels in a plasma image. Common texture features include roughness, contrast, directionality, and linearity.

[0085] 10. Plasma image area: refers to the area of ​​the region enclosed by the plasma shape contour, which is calculated based on the plasma shape contour features extracted from the plasma image.

[0086] 11. Data dimensionality reduction: This technique is used to reduce the number of features in a dataset, simplifying the data structure without losing key information, thereby improving data processing efficiency and model performance. Data dimensionality reduction techniques include principal component analysis, random projections, multi-scale scaling, and non-negative matrix factorization.

[0087] 12. Principal Component Analysis (PCA): Principal Component Analysis (PCA) is a commonly used multivariate statistical analysis method that uses linear transformations to select a smaller number of significant variables. Its purpose is to use dimensionality reduction techniques to transform multiple correlated indicator variables into a small number of composite indicator variables that retain as much information as possible from the original variables while remaining independent of each other.

[0088] 13. Random Projection: Random projection is a technique used for data dimensionality reduction. Random projection is a method of mapping high-dimensional data into a low-dimensional space. The original high-dimensional data is projected into a low-dimensional subspace through a randomly generated projection matrix to achieve the purpose of data dimensionality reduction.

[0089] 14. Multiscale Scaling: Multiscale scaling is a widely used technology in various fields. It transforms data, images, etc. at different scales to obtain information or features at different scales. The core purpose of multiscale scaling is to fully utilize data information at different scales to better adapt to the diversity and complexity of data in various practical application scenarios, thereby improving the performance and generalization ability of models or algorithms.

[0090] 15. Deep Neural Network: A machine learning algorithm based on artificial neural networks that can automatically learn complex, abstract feature representations from raw input data without the need for manual feature engineering, thereby improving the model's generalization and performance.

[0091] 16. Spiking neural network: A type of neural network that processes information based on neuronal spike trains. By simulating the spike coding method of retinal ganglion cells, it can rapidly extract and process features such as edges and motion in images.

[0092] 17. Cluster Analysis: Cluster analysis is an unsupervised learning method that aims to classify objects in a dataset into distinct groups or classes, such that objects within the same class are highly similar, while objects within different classes are highly dissimilar. Cluster analysis groups data objects based on similarity metrics. Common similarity metrics include Euclidean distance, Manhattan distance, and cosine similarity. For example, Euclidean distance calculates the straight-line distance between two data points in multidimensional space; closer distances indicate greater similarity. By calculating the similarity between objects in a dataset, objects with high similarity are grouped into the same class, while objects with low similarity are grouped into different classes.

[0093] 18. Event accumulation: Event accumulation refers to the process of collecting, summarizing, and analyzing a series of related events within a specific time or spatial scope. Identified events are accumulated according to specific rules. This may involve chronological order, arranging and summarizing events in the order in which they occurred, or spatial scope, such as centralizing similar events within a specific area. During the accumulation process, relevant information about the events needs to be organized, such as event type, frequency, and scope of impact.

[0094] In order to solve or improve the technical problem of low accuracy in material classification using LIBS technology in related technologies and to improve the accuracy of material detection and classification, the embodiments of the present application provide the following inventive concepts.

[0095] In the embodiment of the present application, a dynamic vision sensor is added to the laser induced breakdown spectroscopy system in the related art to form a new laser induced breakdown spectroscopy system.

[0096] The laser-induced breakdown spectroscopy system of related technology can use high-energy laser pulses to ablate the sample surface to form a high-temperature, high-electron-density plasma. During the cooling process of the plasma, part of the energy is radiated in the form of a spectrum. The spectral signal is collected by a spectrometer to generate the plasma radiation spectrum data of the sample.

[0097] In order to eliminate the interference of certain factors, the plasma radiation spectrum data of the sample is further preprocessed such as background removal, baseline correction and / or noise reduction to obtain the plasma radiation spectrum data of the sample.

[0098] High-energy laser pulses ablate the sample surface to form a high-temperature, high-electron-density plasma. During the cooling process, the plasma can not only collect plasma radiation spectrum data, but also plasma event flow data. For example, a dynamic vision sensor can simultaneously obtain the plasma event flow data of the sample while collecting the plasma radiation spectrum data of the sample, and can extract plasma feature data based on the plasma event flow data, which is helpful for improving the accuracy of sample classification.

[0099] By combining the plasma radiation spectrum data and plasma characteristic data of the sample, the accuracy of sample classification can be improved. The specific technical solution is as follows.

[0100] The technical solutions of the embodiments of the present application can be applied to various laser induced breakdown spectroscopy systems. Exemplarily, the technical solutions of the embodiments of the present application can be applied to systems composed of adding dynamic vision sensors to various traditional laser induced breakdown spectroscopy systems, wherein the dynamic vision sensor is used to capture plasma event flow data from the time when the sample is ablated to generate plasma to the time when the plasma cools down, and the plasma event flow data can be used to reconstruct a plasma image. It is understandable that the dynamic vision sensor can be replaced by a high-speed camera, but the amount of data generated by the dynamic vision sensor is smaller than that of the high-speed camera, and it is more conducive to extracting plasma feature data from the plasma event flow data to reconstruct a plasma image. Therefore, in the embodiments of the present application, a dynamic vision sensor is used to capture plasma event flow data from the time when the sample is ablated to generate plasma to the time when the plasma cools down.

[0101] For example, Figure 1 It is a laser induced breakdown spectroscopy system suitable for the embodiments of the present application. Figure 1 The technical solution of the embodiment of the present application is also applicable if the dynamic visual sensor is replaced by a high-speed camera.

[0102] See Figure 1 As shown, the laser induced breakdown spectroscopy system includes a laser 101 , a delay controller 102 , a spectrometer 103 , a computer 104 , a dynamic vision sensor 105 , an optical system 106 , and a sample and sample excitation stage 107 .

[0103] Laser 101 is connected to optical system 106, which in turn connects the laser 101, delay controller 102, spectrometer 103, computer 104, and dynamic vision sensor 105. The optical path of the optical system is directed toward the sample and sample excitation stage 107. Spectrometer 103 receives the plasma spectrum generated by the sample and the sample on the sample excitation stage 107. Dynamic vision sensor 105 captures event data generated by changes in plasma brightness during ablation. Selecting appropriate laser energy, light collection angle, and spectrometer delay time can produce spectral signals with high signal-to-noise and signal-to-background ratios. Furthermore, a dynamic vision sensor is incorporated to capture plasma signals.

[0104] In order to improve the accuracy of LIBS technology in classifying materials in related art, the present application embodiment provides a model training method. The method can be run in the computer of the above-mentioned laser induced breakdown spectroscopy system, or it can be run in the above-mentioned laser induced breakdown spectroscopy system after the computer is replaced with other devices. The other devices can be mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA) and other terminal devices. The present application embodiment does not impose any restrictions on the specific type of terminal device.

[0105] For example, the terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a TV set-top box (STB), customer premise equipment (CPE) and / or other devices for communicating on a wireless system and a next-generation communication system, such as a mobile terminal in a 5G network or a mobile terminal in a future evolved Public Land Mobile Network (PLMN) network.

[0106] As an example and not a limitation, when the terminal device is a wearable device, the wearable device can also be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are full-featured, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0107] Figure 2 Schematic diagram of the neural network model training method according to one embodiment of the present application. Figure 2 As shown, in one embodiment of the present application, a neural network model training method can be applied to the above-mentioned laser induced breakdown spectroscopy system, which includes the steps of:

[0108] A1. Obtain a sample training set; wherein each sample data in the sample training set includes plasma radiation spectrum data, plasma characteristic data, and sample label information corresponding to each sample;

[0109] It is understandable that the sample data in the sample training set comes from materials that can be detected using plasma radiation spectroscopy technology, such as metal materials, such as carbon steel. Each sample data may include plasma radiation spectrum data of a certain material, and plasma feature data acquired synchronously or asynchronously when acquiring the plasma radiation spectrum data of the certain material. The plasma feature data may include physical information features of the plasma image, shape features of the plasma image, and texture features of the plasma image; optionally, the physical information features of the plasma image include the area of ​​the plasma image, the circularity of the plasma image, and / or the number of events of the plasma image. The physical information features of the plasma image, the shape features of the plasma image, and the texture features of the plasma image can all be obtained based on plasma event flow data;

[0110] The sample label information includes the model of the material, such as 001. The sample label information may also include the material name. For example, if the material is carbon steel, the sample label information may be carbon steel-001.

[0111] A2. The plasma radiation spectrum data and the plasma characteristic data of each sample are input, and the sample label information corresponding to each sample is output to train the neural network model;

[0112] The plasma radiation spectrum data of each sample and the plasma characteristic data of each sample can be input together, or the plasma radiation spectrum data of each sample can be input first and then the plasma characteristic data of each sample. The label information of each sample has a corresponding relationship with the plasma radiation spectrum data of each sample and the plasma characteristic data of each sample.

[0113] The neural network model trained in this way can be used for material classification, especially for distinguishing types of materials within the same category, such as the difference between carbon steel series materials.

[0114] For example, the framework model of the neural network model can be adopted Figure 3 As shown in Figure 3. Specifically, the neural network model consists of four convolutional modules, each consisting of a 3x3 convolutional layer, a batch normalization layer, and a ReLU activation layer. Each module is followed by a max pooling layer to reduce the size of the feature map. The number of filters in the convolutional layers increases gradually, to 128, 256, 512, and 512, respectively, to capture more complex features. After feature extraction, the network passes through a fully connected layer for feature integration, using a ReLU activation function to introduce nonlinearity, and a dropout layer (50% dropout rate) to prevent overfitting. Finally, the network passes through a fully connected layer to output the number of classes, and a softmax layer to convert the output into a probability distribution. Finally, a classification layer is used to calculate the loss and evaluate model performance. During training, the Adam optimization algorithm is used, with an initial learning rate of 0.001, which is gradually reduced using a piecewise learning rate adjustment strategy. The maximum number of training epochs is set to 1000, the mini-batch size is 32, and the data is shuffled at each epoch to improve training robustness. In addition, L2 regularization (with a coefficient of 0.001) is used to further prevent overfitting.

[0115] The plasma radiation spectrum data includes first plasma radiation spectrum data of each sample and / or plasma radiation spectrum data obtained by preprocessing the first plasma radiation spectrum data. Exemplarily, the first plasma radiation spectrum data may be raw plasma radiation spectrum data obtained using a spectrometer without preprocessing, and the plasma radiation spectrum data may be obtained by preprocessing the raw plasma radiation spectrum data, where the preprocessing includes background removal, baseline correction, and / or noise reduction.

[0116] Since the spectral dimension is large and most features are not representative, in order to extract effective features, prevent the analysis model from overfitting, and reduce computational costs, it is necessary to perform data dimension reduction on the spectral data to extract features. Considering that there are many components in each material, the amount of data that needs to be processed when training the above-mentioned neural network model is very large. In order to reduce the amount of data for training the neural network model, reduce the impact of interfering components on the classification results, and improve the accuracy of classification, the plasma radiation spectrum data of each sample in the training set or the plasma radiation spectrum data is subjected to dimension reduction processing. Specifically, the plasma radiation spectrum data includes the plasma spectrum characteristic data of each sample; the plasma spectrum characteristic data of each sample is obtained by performing data dimension reduction processing on the first plasma radiation spectrum data of each sample or the plasma radiation spectrum data obtained after the preprocessing.

[0117] Optionally, principal component analysis (PCA) is used as a data dimensionality reduction method. A threshold of 85% is preset for the cumulative contribution rate of the plasma spectral characteristic data of the multiple principal components of each sample. For example, using carbon steel as an example, PCA is used to perform dimensionality reduction on the plasma radiation spectrum data of the carbon steel sample. LIBS tests were performed on nine carbon steel samples, with each sample measured 100 times, for a total of 900 times. Information on the nine carbon steel samples is shown in Table 1.

[0118] Table 1 Information of 9 carbon steel samples

[0119]

[0120] Here we use principal component analysis as an example to obtain Figure 4 and 5 The principal component analysis results are shown in Figure 2. The scatter plots of the first and second principal components show clear sample clustering, indicating that the spectral data can distinguish different materials to a certain extent. The contribution rate and cumulative contribution rate change with the number of principal components, indicating that the first principal component contributes 30%, and the cumulative contribution rate of the first 100 principal components exceeds 85%. Therefore, the first 100 principal components can be used as model input.

[0121] See Figure 6 As shown, step A2. takes the plasma radiation spectrum data and the plasma characteristic data of each sample as input and the sample label information corresponding to each sample as output, training a neural network model; comprising:

[0122] A21. Train a neural network model using the plasma spectrum characteristic data and the plasma characteristic data of each sample as input and the sample label information corresponding to each sample as output.

[0123] A03. Extracting plasma characteristic data of each sample based on the plasma image; comprising:

[0124] A031. Extracting plasma shape contour features based on the plasma image to form a plasma shape contour, and calculating the area and circularity of the region enclosed by the plasma shape contour to obtain the plasma image area and circularity;

[0125] A032. Perform image processing on the plasma image to obtain shape features and texture features of the plasma image.

[0126] See Figure 7 and 8 As shown, the neural network model training method further includes A0. obtaining the plasma characteristic data; A0. obtaining the plasma characteristic data includes:

[0127] A01. Obtaining plasma event flow data for each sample;

[0128] A02. Reconstructing a plasma image based on the plasma event flow data;

[0129] A03. Extract plasma characteristic data of each sample based on the plasma image.

[0130] Optionally, A02. Reconstructing a plasma image according to the plasma event flow data; comprising:

[0131] A021. Reconstructing a plasma image based on the plasma event flow data using a deep neural network, a pulse neural network, cluster analysis, or event accumulation;

[0132] The plasma image is a first plasma image generated based on the plasma event flow data or a Gaussian filtered plasma image obtained by Gaussian filtering the first plasma image. The first plasma image can be an original plasma image directly reconstructed from the plasma event flow data.

[0133] Exemplary references Figure 9 As shown, the event frame image of the plasma can be reconstructed by event accumulation. The plasma event flow data can be accumulated within a certain time range. The plasma image can be obtained through the plasma event flow data. Figure 9 As shown in the figure, the accumulation time is 200ms, and the accumulation time can also be selected according to the actual plasma event data. Figure 9 (a) is a plasma image generated based on the plasma event flow data, Figure 9(b) is the Gaussian filtered plasma image obtained after Gaussian filtering of (a). The subsequent steps can be Figure 9 The image in (a) or (b) extracts the area of ​​the region enclosed by the plasma shape outline, the circularity of the plasma image, or other plasma feature data such as the shape feature of the plasma image, the texture feature of the plasma image, and the like.

[0134] As you can understand, plasma imaging requires identifying plasma boundaries. This typically involves using image processing algorithms, such as the Canny operator and the Sobel operator, to detect edges in the image. Key plasma parameters, such as temperature and density, are calculated based on spectral or image data. Image generation requires reconstructing plasma images from plasma event flow data using image processing software or algorithms. These images can be two-dimensional grayscale or color images, or three-dimensional stereo images.

[0135] See Figure 10 As shown, the embodiment of the present application provides a material detection method, comprising:

[0136] S1. Acquire detection data of each material to be classified; the detection data includes plasma radiation spectrum data and plasma characteristic data of the material;

[0137] S2. Input the detection data of each material to be classified into the neural network model obtained by using the neural network model training method, and output the label information of each material.

[0138] Optionally, the plasma radiation spectrum data of each material includes first plasma radiation spectrum data of each material and / or plasma radiation spectrum data obtained by preprocessing the first plasma radiation spectrum data;

[0139] The plasma characteristic data of each material includes: physical information characteristics of the plasma image, shape characteristics of the plasma image, and texture characteristics of the plasma image.

[0140] Optionally, the plasma radiation spectrum data of each material includes plasma spectrum characteristic data of each material, and the plasma spectrum characteristic data of each material is obtained by performing data dimensionality reduction processing on the first plasma radiation spectrum data of each material or the plasma radiation spectrum data obtained after the preprocessing; the plasma spectrum characteristic data of each material includes multiple main component plasma spectrum characteristic data of each material, and the cumulative contribution rate of the multiple main components in the multiple main component plasma spectrum characteristic data of each material is greater than or equal to a preset cumulative contribution rate threshold; preferably, the preset cumulative contribution rate threshold is 85%.

[0141] For example, based on the 9 types of carbon steel samples in Table 1, the effect of the neural network model obtained by the neural network model training method is verified.

[0142] The plasma spectrum characteristic data of the first 100 principal components of each of the nine types of carbon steel samples (denoted as LIBS-PCA) were used as the input of the neural network model obtained by the above-mentioned neural network model training method, and the label information of the corresponding carbon steel samples, such as model information, was used as the output to obtain the LIBS-PCA verification data;

[0143] The plasma shape feature data (denoted as DVS-T) of each of the nine types of carbon steel samples was used as the input of the neural network model obtained by the above-mentioned neural network model training method, and the label information of the corresponding carbon steel samples, such as model information, was used as the output to obtain DVS-T verification data;

[0144] The plasma texture feature data (denoted as DVS-F) of each of the nine types of carbon steel samples was used as the input of the neural network model obtained by the above-mentioned neural network model training method, and the label information of the corresponding carbon steel samples, such as model information, was used as the output to obtain the verification data of DVS-F.

[0145] The neural network model obtained by the above neural network model training method was trained using the plasma spectrum characteristic data of the first 100 principal components of each sample (denoted as LIBS-PCA) and the plasma shape characteristic data of each sample (denoted as DVS-T) as input. The label information of the corresponding carbon steel sample, such as model information, was used as output to obtain the validation data of DVS-T+LIBS-PCA.

[0146] The plasma spectrum feature data of the first 100 principal components of each of the 9 types of carbon steel samples (referred to as LIBS-PCA) and the plasma texture feature data of each of the 9 types of carbon steel samples (referred to as DVS-F) were used as the input of the neural network model obtained by the above neural network model training method. The label information of the corresponding carbon steel samples, such as model information, was used as the output to obtain the validation data of DVS-F+LIBS-PCA. The validation data of the above 9 types of carbon steel materials for testing the above neural network model are summarized as shown in Table 2 below. The confusion matrix of the best classification effect was generated, see Figure 13 shown.

[0147] Table 2 Model validation results

[0148]

[0149] The experimental results show that different data types significantly influence the performance of convolutional neural network models. When using LIBS-PCA data alone, the model performed poorly (73.5% accuracy), indicating limited spectral feature information. In contrast, models using DVS data demonstrated superior feature representation, particularly the neural network model DVS-F, which achieved an accuracy of 95.67%, significantly outperforming the 92.89% accuracy of the neural network model DVS-T. Classification performance was further improved when LIBS-PCA was fused with DVS data, with the combination of the neural network model DVS-F and LIBS-PCA achieving the highest performance, with an accuracy of 98.39%. This demonstrates that the fusion of LIBS-PCA and DVS data effectively complements each other, fully exploiting feature information and improving the model's classification capabilities.

[0150] Confusion matrix reference for best classification results Figure 13 As shown in the confusion matrix, the model has high overall classification performance, with prediction accuracy for most categories approaching 100%. For example, the true categories 1, 3, 6, and 7 are correctly classified. However, some categories are misclassified. For example, 1.8% of category 2 is misclassified as category 9, 0.51% of category 4 is misclassified as category 5, and a small number of category 5 are misclassified as categories 8 and 9.

[0151] Therefore, the method of the embodiment of the present application uses the plasma radiation spectrum data and the plasma characteristic data of each sample as input, and the sample label information corresponding to each sample as output. The trained neural network model has high accuracy. By using this neural network model to perform material detection, the material can be accurately classified, thereby improving the accuracy of material detection and classification.

[0152] It is understood that the above-mentioned neural network training method and material detection method can be used in the laser induced breakdown spectroscopy system. Figure 1 As shown, the embodiment of the present application further provides a laser induced breakdown spectroscopy system, comprising: an optical path system 106; a laser 101 connected to the optical path system; a delay controller 102 connected to the laser; a spectrometer 103 connected to a computer, the optical path system, and the delay controller, respectively; a dynamic vision sensor 105 for acquiring plasma event flow data of a material or sample; and a computer 104 connected to the spectrometer and the dynamic vision sensor, respectively, for:

[0153] A1. Acquire detection data for each material to be classified; the detection data includes plasma radiation spectrum data and plasma characteristic data of the material; plasma characteristic data is obtained based on processing of the plasma event flow data;

[0154] A2. Input the detection data of each material to be classified into the neural network model obtained by the neural network model training method, and output the label information of each material;

[0155] S1. Acquire detection data of each material to be classified; the detection data includes plasma radiation spectrum data and plasma characteristic data of the material;

[0156] S2. Input the detection data of each material to be classified into the neural network model obtained by using the neural network model training method, and output the label information of each material.

[0157] It is understandable that the above-mentioned laser induced breakdown spectroscopy system can also perform other method steps of the above-mentioned neural network model training method and material detection method, and the effects are the same or similar to the corresponding features in the above-mentioned neural network model training method and material detection method, which will not be repeated here.

[0158] See Figure 11 As shown, the embodiment of the present application further provides a neural network model training system 200, comprising:

[0159] A sample data acquisition unit 201 is used to acquire the plasma characteristic data;

[0160] The sample data acquisition unit 201 includes: a first acquisition unit 2011, used to acquire plasma event flow data of each sample; a second acquisition unit 2012, used to acquire plasma radiation spectrum data of each sample; a generation unit 2013, used to reconstruct a plasma image based on the plasma event flow data of each sample; an extraction unit 2014, used to extract plasma feature data of each sample based on the plasma image; and a training unit 202; used to train a neural network model with the plasma radiation spectrum data of each sample and the plasma feature data of each sample as input and the sample label information corresponding to each sample as output.

[0161] It is understandable that each unit in the above-mentioned neural network model training system can also execute other corresponding method steps in the above-mentioned neural network model training method, and the effects are the same or similar to the corresponding technical features in the above-mentioned neural network model training method, which will not be repeated here.

[0162] See Figure 12As shown, the embodiment of the present application also provides a material detection system 300, including: a third acquisition unit 301, used to obtain detection data of each material to be classified; a detection unit 303, including a neural network model obtained by using a neural network model training method; an input unit 302, used to input the detection data of each material to be classified into the detection unit; an output unit 304, used to output the detection result of the detection unit; the detection result includes label information of each material to be classified.

[0163] It is understandable that each unit in the above-mentioned material detection system can also perform other corresponding method steps in the above-mentioned material detection method, and the effects are the same or similar to the corresponding technical features in the above-mentioned material detection method, which will not be repeated here.

[0164] An embodiment of the present application also provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the model training method and the material detection method when executing the computer program.

[0165] An embodiment of the present application also provides a computer-readable storage medium, including: the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the model training method and the material detection method.

[0166] An embodiment of the present application also provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the model training method and material detection method described in any one of the first aspects above.

[0167] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0168] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to the camera / terminal device, a recording medium, computer memory, read-only memory (ROM), random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Examples include a USB flash drive, a removable hard drive, a magnetic disk, or an optical disk.

[0169] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0170] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0171] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0172] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the technical solution of this embodiment.

[0173] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A neural network model training method, characterized in that: include: Acquire a sample training set; wherein each sample data in the sample training set includes plasma radiation spectrum data, plasma characteristic data, and sample label information corresponding to each sample; The neural network model is obtained by training using the plasma radiation spectrum data and the plasma characteristic data of each sample as input and the sample label information corresponding to each sample as output; The plasma radiation spectrum data includes the first plasma radiation spectrum data of each sample and / or the plasma radiation spectrum data obtained by preprocessing the first plasma radiation spectrum data; the plasma radiation spectrum data includes the plasma spectrum characteristic data of each sample; The plasma spectrum characteristic data of each sample is obtained by performing data dimension reduction processing on the first plasma radiation spectrum data of each sample or the plasma radiation spectrum data obtained after the preprocessing; The method comprises: taking the plasma radiation spectrum data and the plasma characteristic data of each sample as input and the sample label information corresponding to each sample as output, training the neural network model; and The neural network model is obtained by training using the plasma spectrum characteristic data and the plasma characteristic data of each sample as input and the sample label information corresponding to each sample as output; The plasma characteristic data includes: physical information characteristics of the plasma image, shape characteristics of the plasma image and texture characteristics of the plasma image; The physical information features of the plasma image, the shape features of the plasma image, and the texture features of the plasma image are obtained based on plasma event flow data.

2. The neural network model training method according to claim 1, characterized in that: The data dimensionality reduction processing method includes principal component analysis, random projection, multi-scale scaling or non-negative matrix decomposition; And / or, the label information includes a model number; And / or, the plasma spectrum characteristic data of each sample includes a plurality of main component plasma spectrum characteristic data of each sample, and the cumulative contribution rate of the plurality of main components in the plurality of main component plasma spectrum characteristic data of each sample is greater than or equal to a preset cumulative contribution rate threshold; And / or, the preprocessing includes background removal, baseline correction and / or noise reduction; And / or, the physical information features of the plasma image include the plasma image area, the circularity of the plasma image and / or the number of events in the plasma image.

3. The neural network model training method according to claim 1, characterized in that: The method further includes acquiring the plasma characteristic data; The acquiring of the plasma characteristic data comprises: Acquiring plasma event flow data of each sample; reconstructing a plasma image based on the plasma event flow data; Plasma characteristic data of each sample is extracted based on the plasma image.

4. The neural network model training method according to claim 3, characterized in that: The method of reconstructing a plasma image according to the plasma event flow data comprises: Reconstructing a plasma image based on the plasma event flow data using a deep neural network, a spiking neural network, cluster analysis, or event accumulation; The plasma image is a first plasma image generated based on the plasma event flow data or a Gaussian filtered plasma image obtained by performing Gaussian filtering on the first plasma image; The step of extracting plasma characteristic data of each sample based on the plasma image comprises: Extracting plasma shape contour features based on the plasma image to form a plasma shape contour, and calculating the area and circularity of a region enclosed by the plasma shape contour to obtain the plasma image area and circularity; Image processing is performed on the plasma image to obtain shape features and texture features of the plasma image.

5. A material detection method, characterized in that: include: Acquiring detection data of each material to be classified; the detection data includes plasma radiation spectrum data and plasma characteristic data of the material; The detection data of each material to be classified is input into a neural network model obtained by the neural network model training method according to any one of claims 1 to 4, and the label information of each material is output.

6. The material detection method according to claim 5, characterized in that: The plasma radiation spectrum data of each material includes the first plasma radiation spectrum data of each material and / or the plasma radiation spectrum data obtained by preprocessing the first plasma radiation spectrum data; The plasma characteristic data of each material includes: physical information characteristics of the plasma image, shape characteristics of the plasma image, and texture characteristics of the plasma image.

7. The material detection method according to claim 6, characterized in that: The plasma radiation spectrum data of each material includes plasma spectrum characteristic data of each material; The plasma spectrum characteristic data of each material is obtained by performing data dimension reduction processing on the first plasma radiation spectrum data of each material or the plasma radiation spectrum data obtained after the preprocessing; And / or, the plasma spectrum characteristic data of each material includes multiple main component plasma spectrum characteristic data of each material, and the cumulative contribution rate of the multiple main components in the multiple main component plasma spectrum characteristic data of each material is greater than or equal to a preset cumulative contribution rate threshold.

8. A laser induced breakdown spectroscopy system, characterized in that: include: Optical path system; Laser, connected to the optical path system; a delay controller connected to the laser; The spectrometer is connected to the computer, the optical path system and the delay controller respectively; Dynamic vision sensors for acquiring plasma event flow data of materials or samples; and a computer, respectively connected to the spectrometer and the dynamic vision sensor, for implementing the material detection method according to any one of claims 5 to 7.

9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 4 or any one of claims 5 to 7 is implemented.

Images