Intelligent control system for multi-color laser marking based on multi-dimensional dynamic calibration

Abstract

The present application relates to the field of intelligent regulation, and specifically discloses a multi-color laser marking intelligent regulation system based on multi-dimensional dynamic calibration, which first obtains the laser marking ambient temperature values ​​at multiple predetermined time points collected by a temperature sensor, the laser equipment text parameters collected by a database, and the laser marking material property text parameters, and then uses deep learning technology to perform feature extraction and correlation analysis on the three, and finally obtains the classification result through a classifier to determine whether the parameters of the multi-color laser marking equipment need to be adjusted, thereby improving the intelligence level of the laser marking process, thereby improving production efficiency, reducing manual intervention and debugging difficulty, reducing production costs, and ensuring the reliability and efficiency of the production process.

Description

Technical Field

[0001] The present application relates to the field of intelligent control, and more specifically, to a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration. Background Art

[0002] Laser marking technology, as an important branch in the field of laser processing, is an advanced marking method that integrates laser, optics, precision machinery, electronics and computer technologies. It uses computer-controlled laser beams as a processing method. Its basic principle is to use a computer-controlled focused laser beam with high energy density to locally irradiate the metal workpiece according to a predetermined trajectory, so that the surface material is instantly vaporized or changes color, and text, patterns, barcodes, etc. with a certain depth or color are etched, thereby leaving a permanent mark on the surface of the metal workpiece.

[0003] At present, although traditional marking machines can perform color marking, their energy efficiency, accuracy and adaptability are poor, and they cannot meet modern high-precision and diversified needs.

[0004] Therefore, an intelligent control system for multi-color laser marking based on multi-dimensional dynamic calibration is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration, which first obtains the laser marking ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor, the laser equipment text parameters collected by the database, and the laser marking material attribute text parameters, and then uses deep learning technology to perform feature extraction and correlation analysis on the three, and finally obtains the classification result through the classifier to determine whether the multi-color laser marking equipment parameters need to be adjusted, thereby improving the intelligence level of the laser marking process, and then improving production efficiency, reducing manual intervention and debugging difficulty, reducing production costs, and ensuring the reliability and efficiency of the production process.

[0006] According to one aspect of the present application, a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration is provided, which includes:

[0007] A multi-color laser marking data acquisition module, used to acquire the laser marking environment temperature values ​​at multiple predetermined time points acquired by the temperature sensor, the laser equipment text parameters acquired by the database, and the laser marking material property text parameters;

[0008] A multi-color laser marking data extraction module, used to extract a laser marking ambient temperature feature vector and a laser marking parameter multimodal semantic feature vector from the laser marking ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor, the laser equipment text parameters collected by the database, and the laser marking material attribute text parameters;

[0009] The multi-color laser marking equipment parameter adjustment judgment module is used to judge whether the multi-color laser marking equipment parameters need to be adjusted based on the laser marking environment temperature feature vector and the laser marking parameter multimodal semantic feature vector.

[0010] Compared with the prior art, the present application provides a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration, which first obtains the laser marking ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor, the laser equipment text parameters and the laser marking material attribute text parameters collected by the database, and then uses deep learning technology to perform feature extraction and correlation analysis on the three, and finally obtains the classification results through the classifier to determine whether the parameters of the multi-color laser marking equipment need to be adjusted, thereby improving the intelligence level of the laser marking process, and then improving production efficiency, reducing manual intervention and debugging difficulty, reducing production costs, and ensuring the reliability and efficiency of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0012] Figure 1 It is a block diagram of a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application.

[0013] Figure 2 It is a block diagram of a multi-color laser marking data extraction module in a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application.

[0014] Figure 3 It is a block diagram of a parameter adjustment judgment module of a multi-color laser marking device in a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application.

[0015] Figure 4 Schematic diagram of the overall architecture of a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application.

[0016] Figure 5 Schematic diagram of dynamic adjustment of grating of a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application.

[0017] Figure 6 The figure is a flow chart of an intelligent control module of a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0019] Figure 1 FIG. 1 is a block diagram of a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application. Figure 1 As shown, according to the embodiment of the present application, the multi-color laser marking intelligent control system 100 based on multi-dimensional dynamic calibration includes: a multi-color laser marking data acquisition module 110, which is used to obtain the laser marking environment temperature values ​​at multiple predetermined time points collected by the temperature sensor, the laser equipment text parameters collected by the database, and the laser marking material attribute text parameters; a multi-color laser marking data extraction module 120, which is used to extract the laser marking environment temperature feature vector and the laser marking parameter multimodal semantic feature vector from the laser marking environment temperature values ​​at multiple predetermined time points collected by the temperature sensor, the laser equipment text parameters collected by the database, and the laser marking material attribute text parameters; a multi-color laser marking equipment parameter adjustment judgment module 130, which is used to judge whether the multi-color laser marking equipment parameters need to be adjusted based on the laser marking environment temperature feature vector and the laser marking parameter multimodal semantic feature vector.

[0020] In the above-mentioned multi-color laser marking intelligent control system 100 based on multi-dimensional dynamic calibration, the multi-color laser marking data acquisition module 110 is used to obtain the laser marking ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor, the laser equipment text parameters collected by the database, and the laser marking material attribute text parameters. It should be understood that in the technical solution of the present application, through data integration and analysis, the influence of temperature and equipment status on the marking quality during the laser marking process can be effectively tracked and optimized. Specifically, laser marking technology is a key branch in the field of laser processing, combining a variety of advanced technologies such as laser technology, optical principles, precision machinery, electronics and computer technology. Its working principle is to control the laser beam through a computer, and irradiate the high-energy-density focused laser onto the surface of the metal workpiece according to the set trajectory, so that the local material evaporates rapidly or undergoes physical and chemical changes, changes its color or produces an etching effect, thereby forming a permanent mark on the surface of the workpiece, such as text, patterns and barcodes. At present, metal laser color marking usually uses YAG solid laser, which has the characteristics of short wavelength and high energy density, so that the laser energy it produces can be effectively absorbed by most metal materials, and can be focused into a smaller spot, which is suitable for high-precision metal marking. However, YAG lasers also have a large heating problem, which may affect the stability and service life of the equipment. In addition, the existing metal laser color marking process involves the coordination of multiple parameters and requires precise adjustment, so it is difficult to debug and has low processing efficiency. Therefore, in the technical solution of the present application, by obtaining the laser marking ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor, the laser equipment text parameters collected by the database, and the laser marking material attribute text parameters, and combining deep learning technology, it is determined whether the parameters of the multi-color laser marking equipment need to be adjusted to improve the intelligence of the laser marking process, thereby optimizing production efficiency, reducing manual intervention and debugging difficulty, reducing production costs, and ensuring the stability and efficiency of the production process.

[0021] In the above-mentioned multi-color laser marking intelligent control system 100 based on multi-dimensional dynamic calibration, the multi-color laser marking data extraction module 120 is used to extract the laser marking environment temperature feature vector and the laser marking parameter multimodal semantic feature vector from the laser marking environment temperature values ​​at multiple predetermined time points collected by the temperature sensor, the laser equipment text parameters collected by the database, and the laser marking material attribute text parameters. It should be understood that by fusing the environment temperature feature vector, the equipment parameter feature vector, and the material attribute feature vector, a multimodal semantic feature vector can be constructed, which integrates multidimensional information such as temperature, equipment status, and material properties, and can fully describe the interaction of various factors in the laser marking process.

[0022] Figure 2FIG. 1 is a block diagram of a multi-color laser marking data extraction module in a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application. Figure 2 As shown, in a specific embodiment of the present application, the multi-color laser marking data extraction module 120 includes: a laser marking environment temperature value feature extraction unit 121, which is used to perform feature extraction on the laser marking environment temperature values ​​at multiple predetermined time points collected by the temperature sensor to obtain the laser marking environment temperature feature vector; a laser equipment text parameter feature extraction unit 122, which is used to perform feature extraction on the laser equipment text parameters collected by the database to obtain a laser equipment text semantic feature vector; a laser marking material attribute text parameter feature extraction unit 123, which is used to perform feature extraction on the laser marking material attribute text parameters to obtain a laser marking material attribute text semantic feature vector; a laser marking parameter multimodal feature association unit 124, which is used to associate the laser equipment text semantic feature vector with the laser marking material attribute text semantic feature vector to obtain the laser marking parameter multimodal semantic feature vector.

[0023] It should be understood that feature extraction of the laser marking ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor can extract key features that can reflect the environmental changes in the laser marking process from the original temperature data, and then form a laser marking ambient temperature feature vector to reveal the potential impact and rules of temperature on the marking process, and help improve the accuracy and stability of process control. Specifically, from the ambient temperature values ​​at multiple time points, the overall distribution of temperature can be summarized by calculating statistical features (such as mean, variance, maximum value, minimum value, fluctuation amplitude, etc.), which can reflect the stability and fluctuation of temperature. In addition, the rate of temperature change (i.e., the slope of temperature change) is also an important feature, because too fast or too slow temperature changes may affect the accuracy and effect of laser marking. Through the extraction of these features, a multi-dimensional feature vector is formed, which can fully describe the ambient temperature characteristics during laser marking.

[0024] Furthermore, the text parameters of laser equipment usually include power, frequency, pulse width, scanning speed, etc. These parameters directly affect the accuracy, efficiency and quality of laser processing. By extracting features from these text parameters, the potential correlation between the equipment status and the processing results can be mined, thereby optimizing the marking process. Among them, statistical methods (such as mean, standard deviation, maximum value, minimum value, etc.) can be used to extract the distribution characteristics of each parameter to reflect the operating stability and performance fluctuations of the equipment. For example, the mean and fluctuation range of laser power can characterize whether the equipment maintains stable output, while the change in frequency helps to determine whether the working mode of the equipment is normal. Secondly, for the operation log or historical parameter data of the equipment, trend features can be extracted through time series analysis, such as the change trend of equipment power, the periodic change of frequency, etc. Such trend features help capture the evolution of equipment status and potential fault signals. Finally, through the extraction of these features, a high-dimensional or low-dimensional laser equipment text semantic feature vector can be obtained to fully describe the working status and performance of the equipment. Furthermore, the properties of the laser marking material (such as material type, surface roughness, thickness, hardness, absorbance, etc.) directly affect the interaction between laser energy and the material. Extracting the characteristic vectors of these material properties helps predict and optimize the marking quality and ensure the stability and accuracy of the marking process.

[0025] In particular, laser marking is a complex multi-factor process, where equipment parameters and material properties jointly determine the marking effect. Relying on any one of these aspects alone may not accurately reflect the actual marking status and results. Therefore, associating these two types of feature vectors can more comprehensively capture the interactive relationship between equipment and materials in the marking process, thereby forming a comprehensive feature vector and enhancing the model's expressive power and prediction accuracy. Among them, appropriate fusion methods, such as weighted summation, splicing or multiplication, can be used to effectively combine these two types of feature vectors. For example, the parameter feature vector of the laser equipment and the material property feature vector can be weighted and summed in a certain proportion to obtain a fusion vector that integrates the information of equipment performance and material characteristics. In this fusion process, some key parameters (such as power, frequency, surface roughness, etc.) may need to be given higher weights to highlight their dominant role in the marking effect. Through this association process, the obtained multimodal semantic feature vector of laser marking parameters not only covers the operating conditions of the laser equipment and the physical properties of the material, but also can effectively capture the interaction and joint influence of the equipment and material in actual operation.

[0026] In a specific embodiment of the present application, the laser marking ambient temperature value feature extraction unit 121 includes: arranging the laser marking ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor into a laser marking ambient temperature input vector; passing the laser marking ambient temperature input vector through a laser marking ambient temperature timing encoder to obtain the laser marking ambient temperature feature vector.

[0027] It should be understood that ambient temperature is an important external parameter in the laser marking process, and its changes may affect the energy transfer of the laser beam, the thermal response of the material, etc. Arranging the laser marking ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor as the laser marking ambient temperature input vector can construct an input feature that can reflect the change of ambient temperature over time. This input vector can effectively capture the impact of temperature changes on the laser marking process and help analyze how temperature fluctuations affect the marking quality and stability. Specifically, the temperature values ​​at multiple predetermined time points collected by the temperature sensor usually show certain time series characteristics. Therefore, when arranging these temperature values ​​as input vectors, the order information of the time series can be retained to ensure that the model can identify the temperature change trend. For example, if the sensor collects temperature data at multiple fixed time points (such as every second or every minute), these temperature data will contain multiple values ​​arranged in order on the time axis. After arranging these values ​​into vectors in time order, each element of the vector represents the temperature value at a specific time point, thereby forming an information vector containing the time dimension. Next, in order to improve the model's sensitivity to temperature changes, these temperature values ​​can be preprocessed, such as normalization or standardization, to eliminate the dimensional differences in temperature data at different time points. For long time series, input vectors can be generated by intercepting a fixed-length time window or using a sliding window to ensure that the input vector length is consistent, which is convenient for model training and prediction. By arranging the laser marking ambient temperature values ​​at multiple time points as input vectors, the timing characteristics of temperature changes can be retained, allowing the laser marking process to respond more accurately to ambient temperature changes.

[0028] Furthermore, the laser marking ambient temperature input vector is passed through the laser marking ambient temperature time series encoder to obtain the laser marking ambient temperature feature vector, aiming to extract the time series features in the temperature series and help the model better understand the impact of the dynamic changes of ambient temperature on the laser marking process. Among them, the laser marking process is a precision operation that is highly dependent on external conditions (such as ambient temperature). Temperature fluctuations may directly affect the energy output of the laser beam, the thermal response characteristics of the material, and the final marking effect. By processing the input vector through the time series encoder, the time dependency and pattern in the temperature change can be effectively captured, thereby providing valuable features for subsequent prediction, optimization, and control. Specifically, the laser marking ambient temperature input vector is a time series data formed by arranging the temperature values ​​collected at multiple time points in chronological order. Since there may be short-term fluctuations or long-term trends in the temperature series, traditional simple feature extraction methods (such as mean and standard deviation) may not fully reflect the impact of temperature on the marking process. Time series encoders (such as long short-term memory networks LSTM or gated recurrent units GRU) can effectively process long-term dependencies and time series patterns in time series data through their internal recurrent structures. Through the timing encoder, each temperature value in the input vector is not only related to the temperature at the current time point, but also takes into account the impact of temperature changes at previous time points on the current temperature. After the temperature input vector is processed by the timing encoder, the model extracts important time features in the temperature sequence (such as fluctuation patterns, periodic changes, trends, etc.) as a low-dimensional laser marking ambient temperature feature vector. This feature vector contains the dynamic characteristics of the ambient temperature and can be used as input for subsequent tasks (such as marking quality prediction, modeling of the impact of ambient temperature on equipment, etc.). Through its cyclic structure and memory unit, the timing encoder can capture the delay effects and nonlinear effects that temperature fluctuations may have on the laser marking process, thereby providing a more accurate representation of the ambient temperature. Specifically, the laser marking ambient temperature input vector is fully connected encoded using the fully connected layer of the laser marking ambient temperature timing encoder to extract high-dimensional implicit features of the eigenvalues ​​at each position in the laser marking ambient temperature input vector; and the laser marking ambient temperature input vector is one-dimensionally convolutionally encoded using the one-dimensional convolution layer of the sequence encoder to extract high-dimensional implicit correlation features of the correlation between the eigenvalues ​​at each position in the laser marking ambient temperature input vector.

[0029] In a specific embodiment of the present application, the laser equipment text parameter feature extraction unit 122 includes: segmenting the laser equipment text parameters collected from the database to obtain a laser equipment text parameter word sequence; passing the laser equipment text parameter word sequence through a laser equipment text bidirectional long short-term memory neural network to obtain a laser equipment text semantic feature vector.

[0030] It should be understood that the text parameters of laser equipment usually include information such as equipment model, power, frequency, spot size, etc., which may be stored in the database in the form of natural language. Direct analysis of raw text data is not only complex, but also difficult to extract useful features. Word segmentation, as an important step in text preprocessing, can break down these long texts into the most basic language units, so that the computer can perform subsequent analysis more effectively. Specifically, the text parameters of laser equipment are usually recorded in the database in the form of sentences or paragraphs, which contain multiple words describing the performance and configuration of the equipment. In order to convert these text data into input features that can be used by machine learning models, they need to be split into independent words or phrases through word segmentation. The process of word segmentation first involves linguistic analysis of the text to identify the constituent elements such as words, phrases, and symbols in the text. Among them, when segmenting Chinese words, it may be necessary to use special word segmentation tools (such as jieba, THULAC, etc.), which can identify and process professional vocabulary, numbers, units, etc., to ensure that accurate word sequences can be obtained after word segmentation. Through word segmentation, the text parameters of the laser equipment are converted into words or phrase sequences with clear meanings. These words can be used as components of the input feature vector for subsequent machine learning models to perform feature extraction and analysis.

[0031] Furthermore, the laser equipment text parameter word sequence is processed by the laser equipment text bidirectional long short-term memory neural network (Bi-LSTM) in order to extract richer semantic features from the text sequence and form a semantic feature vector that can fully characterize the equipment parameters. The text parameters of laser equipment, such as equipment model, power, frequency, etc., are usually composed of multiple words, and the meaning of these words often depends on their order and context in the text. Therefore, the use of the bidirectional long short-term memory network (Bi-LSTM) can effectively capture the temporal dependency between words, while taking into account the forward and reverse context information, thereby extracting the semantic features in the text. Specifically, the laser equipment text parameter word sequence is usually a sequence of words arranged in time or logical order, and the order of these words in the text is closely related to the context. The traditional recurrent neural network (RNN) can only process sequence data from one direction (usually from left to right), while the long short-term memory network (LSTM) can better capture long-term dependencies by introducing memory units, but it still cannot effectively take into account the forward and reverse context information at the same time. To solve this problem, bidirectional LSTM (Bi-LSTM) can obtain contextual information from left to right and from right to left by processing text data in both the forward and reverse directions, so as to more accurately understand the semantics of each word in the sequence. After the laser equipment text parameter word sequence is processed by Bi-LSTM, a vector representing the contextual information of the entire sequence will be obtained. This vector not only captures the characteristics of the vocabulary itself, but also integrates the association of each word in the context, so as to comprehensively characterize the semantics of the equipment parameters. Processing the laser equipment text parameter word sequence through a bidirectional long short-term memory neural network (Bi-LSTM) can extract its contextual semantic features while retaining the order information of each word in the vocabulary sequence. Specifically, the embedding layer of the laser device text bidirectional long short-term memory neural network is used to map each laser device text parameter word in the laser device text parameter word sequence into a word embedding vector to obtain a sequence of laser device text parameter word embedding vectors; the converter-based Bert model of the laser device text bidirectional long short-term memory neural network is used to perform global context semantic encoding on the sequence of laser device text parameter word embedding vectors to obtain multiple laser device text parameter feature vectors; and the multiple laser device text parameter feature vectors are cascaded to obtain the laser device text semantic feature vector.

[0032] In a specific embodiment of the present application, the laser marking material attribute text parameter feature extraction unit 124 includes: embedding the laser marking material attribute text parameters through a laser marking material attribute text word encoder to obtain a laser marking material attribute text word vector sequence; passing the laser marking material attribute text word vector sequence through a laser marking material attribute text convolutional neural network based on a multi-scale neighborhood feature extraction module to obtain the laser marking material attribute text semantic feature vector.

[0033] It should be understood that the attribute text parameters of laser marking materials, such as "hardness", "density", "reflectivity", etc., often contain professional terms and their values. This information is stored in text form and is difficult to be effectively used by machine learning models directly. Through the word embedding encoder, these text data can be converted into vector form, so as to better provide input features for the model. The laser marking material attribute text parameters are processed by the laser marking material attribute text word embedding encoder, with the aim of converting the original text parameters into a more dense and semantic numerical representation, that is, a laser marking material attribute text word vector sequence. The core purpose of this process is to map each individual word or phrase into a high-dimensional space through word embedding, so that the semantic relationship between these words can be effectively captured and represented. Specifically, the laser marking material attribute text parameters are usually descriptive texts composed of multiple words. Traditional text processing methods (such as TF-IDF based on word frequency) can only consider the frequency of occurrence of words, and it is difficult to reflect the semantic relationship between words. The word embedding encoder can map each word into a continuous high-dimensional space so that words with similar semantics are close in this space. In actual operation, the laser marking material attribute text word embedding encoder first converts each word or phrase into a fixed-dimensional vector through the embedding layer. These vectors can retain the semantic information between words. Modern word embedding technologies such as Word2Vec, GloVe or more advanced BERT use large-scale corpora to learn the relationship between words, thereby obtaining a high-dimensional vector that can reflect word meaning and context information. Each parameter of the input text (such as "hardness", "density", etc.) will be mapped to a corresponding word vector, and the word vectors corresponding to multiple words will form a word vector sequence to fully express the semantic information of the material attribute text. Finally, the laser marking material attribute text word vector sequence generated by the word embedding encoder can be used as the input feature of the machine learning model to analyze the impact of material properties on the laser marking process. These vectors not only have high computational efficiency, but also can better capture the semantic information of material properties, providing support for subsequent marking process optimization, quality control and fault diagnosis.

[0034] Furthermore, after the attribute text of laser marking materials is converted into a word vector sequence through word embedding technology, although the semantics of each word has been captured, in order to fully understand the semantics of the entire text, it is necessary to extract features from the text from different angles and scales. The multi-scale neighborhood feature extraction module is precisely to effectively capture the relationship between words and their contextual information at different scales, helping the model to better understand the global semantics of the material attribute text. The laser marking material attribute text word vector sequence is processed by the laser marking material attribute text convolutional neural network (CNN) based on the multi-scale neighborhood feature extraction module, which can utilize the powerful feature extraction ability of the convolutional neural network, especially when processing text data with local patterns, to mine deeper semantic information in the text, and finally obtain a feature vector representing the semantics of the text. Specifically, the laser marking material attribute text word vector sequence is converted into a series of continuous high-dimensional vectors through the word embedding encoder, and each word vector contains the semantic information of the word. However, the semantic connection between words and the hidden patterns in the text are usually multi-scale, especially when describing material properties, different levels of information may appear. Traditional convolutional neural networks (CNNs) extract important features through local receptive fields (i.e., capturing local features within a smaller range), but when faced with text data with different levels of features, a single-scale convolution may not be sufficient to capture complex semantic relationships. Therefore, the introduction of a multi-scale neighborhood feature extraction module can perform convolution operations on the input word vector sequence at multiple scales, thereby extracting semantic features that are meaningful to the laser marking material attribute text at different scales. During the operation, the convolutional neural network based on the multi-scale neighborhood feature extraction module applies multiple convolution kernels of different sizes to each word vector sequence to extract short-range, long-range, or even more complex local features. These convolution kernels can effectively identify different levels of patterns through different window sizes, such as the features of a single attribute word, the relationship between words, and even the contextual information of the entire attribute description. The convolution layer of the network generates multiple feature maps, which are reduced and aggregated through pooling operations, and finally a high-dimensional semantic feature vector of the laser marking material attribute text is obtained, which fully represents the semantic information of the text. Using a convolutional neural network based on a multi-scale neighborhood feature extraction module to process the laser marking material attribute text word vector sequence can not only extract local features, but also capture deeper semantic relationships, thereby forming an efficient feature vector with rich semantic information. This feature vector provides more accurate and comprehensive input data for subsequent marking quality prediction, process optimization and fault diagnosis, and improves the model's understanding of the impact of material properties on laser marking.Specifically, the laser marking material attribute text convolutional neural network based on the multi-scale neighborhood feature extraction module includes: a first convolutional layer, a second convolutional layer parallel to the first convolutional layer, and a cascade layer connected to the first convolutional layer and the second convolutional layer, wherein the first convolutional layer uses a one-dimensional convolutional kernel with a first scale, and the second convolutional layer uses a one-dimensional convolutional kernel with a second scale. More specifically, the first convolutional layer of the laser marking material attribute text convolutional neural network based on the multi-scale neighborhood feature extraction module is used to perform one-dimensional convolution encoding on the laser marking material attribute text word vector sequence to obtain a first-scale feature vector; the second convolutional layer of the multi-scale neighborhood feature extraction module is used to perform one-dimensional convolution encoding on the laser marking material attribute text word vector sequence to obtain a second-scale feature vector; the first-scale feature vector and the second-scale feature vector are cascaded to obtain the laser marking material attribute text semantic feature vector.

[0035] In the above-mentioned multi-color laser marking intelligent control system 100 based on multi-dimensional dynamic calibration, the multi-color laser marking equipment parameter adjustment judgment module 130 is used to judge whether the multi-color laser marking equipment parameters need to be adjusted based on the laser marking ambient temperature feature vector and the laser marking parameter multimodal semantic feature vector. It should be understood that by integrating the ambient temperature feature vector and the laser marking parameter multimodal semantic feature vector, the environment and process parameters in the multi-color laser marking process can be fully monitored and adjusted to ensure that the equipment always maintains the best performance under various working conditions and achieve a more accurate and stable marking effect.

[0036] Figure 3 FIG. 1 is a block diagram of a parameter adjustment judgment module of a multi-color laser marking device in a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application. Figure 3 As shown, in a specific embodiment of the present application, the multi-color laser marking device parameter adjustment judgment module 130 includes: a laser marking device feature fusion unit 131, which is used to fuse the laser marking environment temperature feature vector and the laser marking parameter multimodal semantic feature vector to obtain a laser marking device adjustment judgment feature vector; a laser marking device feature optimization unit 132, which is used to perform topological space constraints on the laser marking device adjustment judgment feature vector based on cross-domain transfer learning to obtain an optimized laser marking device adjustment judgment feature vector; a laser marking device adjustment parameter adjustment classification judgment unit 133, which is used to pass the optimized laser marking device adjustment judgment feature vector through a classifier to obtain a classification result, and the classification result is used to determine whether the multi-color laser marking device parameters need to be adjusted.

[0037] It should be understood that the ambient temperature feature vector contains the numerical information of the current ambient temperature, which can reflect the potential impact of temperature on the marking effect; while the multimodal semantic feature vector of laser marking parameters integrates multi-dimensional marking process information (such as power, speed, focal length, etc.), and each dimension contains the different contributions of the process to the marking quality. By fusing these two feature vectors, the relationship between temperature and process parameters, as well as their combined impact on marking quality, can be captured more accurately. Through the fused optimized laser marking equipment adjustment judgment feature vector, the system can monitor the current environmental conditions and process settings in real time, and automatically determine whether the equipment parameters need to be adjusted, thereby optimizing the marking effect, improving production efficiency and avoiding quality fluctuations.

[0038] In particular, considering that the ambient temperature data is time-series numerical data, the equipment parameters and material properties are information in text form. Among them, the temperature data is converted into a feature vector through a time-series encoder, focusing on the trend of temperature changes over time, but this feature mainly reflects the physical changes in the environment and lacks deep semantic associations with equipment operation or material performance. The equipment parameters and material properties are extracted based on natural language processing methods, and semantic features are extracted through bidirectional LSTM and convolutional neural networks respectively, focusing on the semantics, grammar and context understanding of the text, which is completely different from the time-series nature of temperature data. When fusing these data from different sources, due to the significant differences in the dimensions, information types, and semantic levels of the data themselves, the fused laser marking equipment adjustment judgment feature vector may not be able to fully retain the unique information of each data type. At the same time, although the text features of equipment and materials can express complex semantic relationships, since these two types of text data are processed separately and their embedded vectors are difficult to directly reflect the real-time relationship with the external physical environment such as temperature, the intrinsic connection between data points may not be effectively strengthened in the final feature fusion. Therefore, although the fused laser marking equipment adjustment judgment feature vector contains multimodal information, due to the heterogeneity of the information and the multi-level semantic differences, it may not be able to accurately capture and express the complex interactions between factors such as temperature, equipment, and material properties while maintaining the original characteristics of various types of data. This difference makes it difficult for the fused feature vector to comprehensively improve the intrinsic connection between data points, which in turn affects the accuracy of equipment adjustment judgment. Therefore, in the technical solution of the present application, the laser marking equipment adjustment judgment feature vector is optimized by performing topological space constraints on the laser marking equipment adjustment judgment feature vector based on cross-domain transfer learning.

[0039] Among them, the laser marking equipment adjustment judgment feature vector is subjected to topological space constraints based on cross-domain transfer learning to obtain an optimized laser marking equipment adjustment judgment feature vector, including: extracting the target parameter matrix of the classifier; node-decomposing the target parameter matrix in units of row vectors to obtain a set of target parameter node encoding vectors; taking each target parameter node encoding vector in the set of target parameter node encoding vectors as a wandering topological space, and subjecting the laser marking equipment adjustment judgment feature vector to topological space constraints to obtain a set of constrained laser marking equipment adjustment judgment feature vectors; and calculating the positional mean vector of the set of constrained laser marking equipment adjustment judgment feature vectors to obtain the optimized laser marking equipment adjustment judgment feature vector.

[0040] Among them, each target parameter node coding vector in the set of target parameter node coding vectors is used as the wandering topological space, and the laser marking equipment adjustment judgment feature vector is topologically constrained to obtain a set of constrained laser marking equipment adjustment judgment feature vectors, including: multiplying the laser marking equipment adjustment judgment feature vector and the transposed vector of the target parameter node coding vector, and calculating the natural exponential function value of the multiplication result to obtain a weighted exponential response weight; calculating the Euclidean distance between the laser marking equipment adjustment judgment feature vector and the target parameter node coding vector to obtain a node coding distance value; performing point multiplication on the node coding distance value and the laser marking equipment adjustment judgment feature vector, and calculating the natural exponential function value for each eigenvalue of the vector after the point multiplication to obtain a laser marking equipment distance guidance index feature vector; multiplying the weighted exponential response weight and the laser marking equipment distance guidance index feature vector to obtain a constrained laser marking equipment adjustment judgment feature vector.

[0041] The topological space constraint based on cross-domain transfer learning is performed on the laser marking equipment adjustment judgment feature vector to obtain an optimized laser marking equipment adjustment judgment feature vector represented by the following optimization formula:

[0042]

[0043]

[0044]

[0045] in, represents the target parameter matrix, The first, second, and third sets of target parameter node encoding vectors are represented by , target parameter node encoding vector, represents the transpose of a vector, represents the adjustment judgment feature vector of the laser marking device, represents matrix multiplication, It means point multiplication by position. Represents the calculation vector and vector The Euclidean distance between The first one represents the set of feature vectors of the laser marking equipment adjustment judgment after constraint After the constraints, the laser marking equipment adjusts the judgment feature vector, Represents the total number of sets of adjustment judgment feature vectors of the laser marking equipment after constraint, Represents the optimized laser marking equipment adjustment judgment feature vector.

[0046] In the technical solution of the present application, the laser marking equipment adjustment judgment feature vector is subjected to topological space constraints based on cross-domain transfer learning. The process first extracts the key parameters for decision-making from the trained classifier. These parameters form a matrix in a high-dimensional space, and each row represents the weight or influencing factor on a different dimension. The target parameter matrix can provide insight into the location and shape of the model decision boundary, and then infer which input features are most critical to the prediction results.

[0047] Next, the target parameter matrix is ​​node-decomposed in units of row vectors to obtain a set of target parameter node encoding vectors. Here, each row vector is a node in graph theory, which means that each set of parameters is now regarded as an entity with potential connectivity. This transformation allows the application of methods from graph theory and network science to explore the interactions between features. The node encoding vector not only carries information about the original parameters, but also implies knowledge about the topological structure of the entire system. Node decomposition further reveals the intrinsic connection pattern or structure of the data, so that the optimized feature vector can better adapt to new task requirements.

[0048] Then, each target parameter node encoding vector in the set of target parameter node encoding vectors is used as the walking topological space, and the laser marking device adjustment judgment feature vector is respectively subjected to topological space constraints to obtain a set of laser marking device adjustment judgment feature vectors after constraints. "Walking" in the topological space defined by the node encoding vector is actually simulating an exploratory process, the purpose of which is to find feature transformations that can best maintain the characteristics of the original data structure. Each step determines the position of the next step based on the probability distribution of the current state. The topological space constraints ensure that even in different contexts, the feature representation still retains certain invariances. At the same time, it can also promote cross-domain transfer learning because it emphasizes the universal relationship between features rather than the details of a specific field. In this way, the reconstruction of the feature space is achieved, making the optimized feature vector more compact and having better generalization capabilities.

[0049] Finally, the positional mean vector of the set of the constrained laser marking device adjustment judgment feature vectors is calculated to obtain the optimized laser marking device adjustment judgment feature vector. Calculating the mean vector is a statistical aggregation method used to integrate the optimal solution from multiple perspectives. The idea behind this step is to reduce the deviation caused by a single estimate by fusing the information provided by different sample points. The averaging process is equivalent to performing a soft voting, which enhances the expressiveness of common features and makes the optimized feature vector more stable and reliable.

[0050] Furthermore, the optimized laser marking equipment adjustment judgment feature vector is a composite vector that integrates the ambient temperature feature vector and the multimodal semantic feature vector of the laser marking parameters, and contains comprehensive information about the environmental conditions and process parameters. These features can reflect the current operating status of the equipment and whether there is a risk of poor marking effect due to environmental changes or improper parameter settings. However, since this information is often high-dimensional and complex, it is difficult to achieve efficient real-time monitoring and adjustment by relying solely on manual analysis. Therefore, it is necessary to analyze these features through a machine learning model (classifier) ​​in order to make corresponding judgments. Classifiers, especially commonly used decision trees, support vector machines (SVMs), neural networks and other algorithms, can learn from historical data how environmental factors and equipment parameters affect the marking quality and establish corresponding rules or models. When a new feature vector is input, the classifier determines whether the equipment parameters need to be adjusted through the trained model. The classification result is usually "need to adjust" or "no adjustment is required". According to the predicted output, the system can automatically or prompt the operator to make appropriate adjustments to the parameters of the laser equipment. For example, when the classifier determines that the ambient temperature is too high and the current power setting is insufficient, the system may recommend increasing the power or reducing the scanning speed to ensure the stability of the color rendering effect. In this way, the laser marking equipment can intelligently determine whether the parameters need to be adjusted based on real-time environmental and process information, avoid the limitations of human intervention, and improve production efficiency and consistency of marking quality. This classifier-driven intelligent adjustment mechanism can not only automatically adapt to the changing operating environment, but also achieve fine control during the multi-color laser marking process, maximizing the quality and accuracy of the final mark.

[0051] In summary, the embodiment of the present application first obtains the laser marking ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor, the laser equipment text parameters and the laser marking material attribute text parameters collected by the database, and then uses deep learning technology to perform feature extraction and correlation analysis on the three. Finally, the classification result is obtained through the classifier to determine whether the parameters of the multi-color laser marking equipment need to be adjusted, thereby improving the intelligence level of the laser marking process, and then improving production efficiency, reducing manual intervention and debugging difficulty, reducing production costs, and ensuring the reliability and efficiency of the production process.

[0052] In another specific embodiment of the present application, considering that the traditional marking machine can perform color marking, its energy efficiency, accuracy and adaptability are poor, and it cannot meet the modern high-precision and diversified needs. In order to achieve efficient and multi-color display of laser in the full spectrum range, another specific embodiment of the present application proposes a new multi-dimensional dynamic calibration system, which combines intelligent feedback adjustment with high-precision scanning technology to break through the bottleneck of traditional processes. Specifically, another specific embodiment of the present application realizes efficient multi-color marking on the surfaces of different materials by introducing a full-spectrum laser source, an intelligent two-dimensional high-speed galvanometer, a dynamic grating system and an adaptive control algorithm. The system also has remote control, automatic fault detection and multi-level optical anti-counterfeiting functions. Among them, the laser source module adopts a tunable full-spectrum laser to support broadband operation from ultraviolet to infrared. The wavelength range of the laser source module is 200 nm-1064 nm, and the power adjustment range of the laser source module is 1 mW-200 W. The optical fiber transmission module reduces energy loss and ensures stable transmission through efficient optical fiber coupling. The intelligent high-speed galvanometer system includes X-axis and Y-axis galvanometers with a response speed of up to 1 ms and an accuracy of 0.01 degrees. The dynamic grating system uses an electrically controlled grating to achieve real-time frequency and direction adjustment. The F-Theta objective lens group enables precise scanning of the laser beam in the focal plane. The adaptive feedback system monitors temperature, humidity and vibration through real-time sensors to dynamically adjust the beam path and power. The intelligent control module supports remote monitoring and automatic fault detection, and can adjust working parameters in real time through PC software.

[0053] Figure 4 Schematic diagram of the overall architecture of a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application. Figure 5 Schematic diagram of grating dynamic adjustment of a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application. Figure 4 and Figure 5 As shown, in another specific embodiment of the present application, a PC is included, and the PC signal is connected to a laser control console and a motor control console. The PC sends a control signal to the laser through the laser control console to control the laser to send a corresponding laser beam. The PC is connected to the motor signal through the motor control console, and the motor is driven to operate through the control signal sent, driving the grating and the two-dimensional high-speed galvanometer to adjust to the corresponding angle. The pattern to be marked is entered on the PC end, and the scanning path and grating frequency of the galvanometer are optimized by simulating the marking process.

[0054] Specifically, a radiator is arranged on the outside of the laser, and a fan radiator is used as the radiator. The fan radiator is used to solve the problem of severe temperature efficiency and high heat generation of the laser, so as to improve the overall processing efficiency of the marking machine. A marking workpiece is arranged at the end of the laser light speed. An optical fiber, a grating, a convex lens, a two-dimensional high-speed galvanometer and an F-Theta objective lens are arranged in sequence from the laser to the marking workpiece between the laser and the marking workpiece. The grating and the two-dimensional high-speed galvanometer are connected to a motor, and the angles of the grating and the two-dimensional high-speed galvanometer can be adjusted by the motor.

[0055] Specifically, the optical fiber can couple the laser beam. The laser beam is emitted from the laser, and the optical properties of the laser beam itself are further improved by the coupling effect of the optical fiber. The laser beam coupled by the optical fiber is irradiated onto the grating.

[0056] Specifically, the grating is installed on a workbench and controlled by a motor. When it is rotated to different positions, gratings of different frequencies are aligned with the laser beam, so that the grating stripes irradiated on the workpiece also have different spatial frequencies. At the same time, the rotation of the optical head makes the captured grating have different grating orientations.

[0057] The grating irradiates the laser beam onto the convex lens, which focuses the laser beam onto the two-dimensional high-speed galvanometer. The function of the convex lens is to make the light emitted from the laser a beam of convergent light. If this lens is not added, the light emitted from the laser may be divergent light, so the energy of the light will be reduced.

[0058] Specifically, the two-dimensional high-speed galvanometer includes an X-axis galvanometer and a Y-axis galvanometer, which are connected to the output end of the motor, and the angle and direction of the X-axis galvanometer and the Y-axis galvanometer are adjusted by the forward or reverse rotation of the motor.

[0059] Among them, the two-dimensional high-speed galvanometer is the execution unit of the laser marking machine movement, that is, a certain technical means is used to make the propagation direction of the laser beam deflect according to certain rules. Generally speaking, the propagation direction of the laser beam is changed by physical effects such as reflection and diffraction to achieve the purpose of light scanning. The laser beam completes the light scanning process through the two-dimensional high-speed galvanometer. The two-dimensional high-speed galvanometer is the core component of laser marking. During the laser marking process, by controlling the movement of the two-dimensional high-speed galvanometer, it can be moved arbitrarily in the two-dimensional direction of the surface of the workpiece to achieve laser marking.

[0060] Next, the two-dimensional high-speed galvanometer will project the laser beam onto the F-Theta objective lens, which interferes and exposes the workpiece. The rotation of the high-speed two-dimensional galvanometer combined with the frequency selection of different gratings can engrave color-changeable graphics or text on the surface of the workpiece. The laser frequency λ is 532nm, k=±1, and d is the grating constant. The so-called grating constant means that when the number of light rays within 1mm is n, the distance between each two light rays is d=1 / n, and the unit is micrometer (μm). Commonly used gratings are 300dpi, 400dpi, and 500dpi, and their grating constants are 3.3μm, 2.5μm, and 2μm respectively.

[0061] The grating is controlled by a motor, and when it rotates to different positions, it will have different frequencies, so-called grating alignment laser beams, so that the grating stripes irradiated on the workpiece also have different spatial frequencies; at the same time, the rotation of the optical head makes the captured grating have different grating orientations. The rotation of the two-dimensional galvanometer exposes each point on the workpiece to form a light-variable image composed of pixel gratings with different grating orientations and spatial frequencies, so that color-variable graphics or texts can be engraved to form multi-color graphics.

[0062] Specifically, the multi-color graphics are formed by a tiny pixel grating matrix. Under different observation angles, pixel grating groups with the same characteristics will form specific graphics, and pixel gratings with different characteristics will present graphics with different effects. The optical parameters describing the optically variable image are: position: set values ​​of the X-axis and Y-axis, diffraction direction of the pixel grating: set value of the grating angle, density distribution of the pixel grating: set value of the color, and luminous efficiency of the pixel: set value of the brightness.

[0063] Among them, as the light moves or the observation direction changes, the color and shape of the optically variable image will change, and the diffraction of light on each pixel grating satisfies the grating equation, that is:

[0064] That is to say, the color of the marking pattern will change with the movement of light and the change of the observer's position, which has a very good color rendering effect. This will better solve the problem of poor color combination of previous laser marking machines.

[0065] Among them, the color-changing laser marking system is a system that uses the interference of laser beams on the surface of the material. The rotation of the grating in the system changes the fringe orientation of the interference light spots, and reasonably arranges the interference fringe orientation of each light spot in the graphic, so that the recorded graphics can reproduce beautiful text or graphics under white light.

[0066] Figure 6 FIG. 1 is a flow chart of an intelligent control module of a multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to an embodiment of the present application. Figure 6 As shown, in another specific embodiment of the present application, firstly, the printed graphics are input on the PC and the marking is simulated on the PC, and the parameters of the marking machine are saved at the end of the simulation, mainly including the parameter setting of the laser control console and the parameter setting of the motor. The parameters of the laser control console mainly involve the beam quality factor, far-field divergence angle, polarization direction, polarization ratio, pulse energy, pulse width, beam directivity and power, etc. The determination of the above parameters needs to be obtained by simulating the characteristics of the metal device on the PC. The parameters of the motor control console include the motor parameters for controlling the rotation direction of the grating and the motor parameters for controlling the scanning direction of the two-dimensional high-speed galvanometer.

[0067] By controlling the rotation of the pixel grating through a motor, grating orientations of different angles and directions can be obtained. When it turns to different positions, pixel gratings of different frequencies will be aligned with the laser beam, thereby making the grating stripes irradiated on the metal workpiece diverse.

[0068] The motor controls the two-dimensional high-speed galvanometer. When the motor controls the X-axis galvanometer and Y-axis galvanometer in the two-dimensional high-speed galvanometer, its response time is 1ms. It is controlled by analog signals sent by the PC. The coordinate values ​​corresponding to each point in the figure are converted into corresponding voltage values. The rotation angle of the X-axis galvanometer and the Y-axis galvanometer is linearly related to the voltage signal, and the ratio is: the voltage changes by 0.5V for each degree of rotation; the control voltage signal of the galvanometer is ±10V, so its rotation angle is ±20º. The laser beam is transferred to the F-Theta objective lens through the polarization rotation of the two-dimensional high-speed galvanometer. For a normal focusing lens, parallel light at infinity will be imaged on the focal plane, but the ideal image height and the scanning angle are often not linearly related, and it is impossible to achieve constant speed scanning, which will affect the accuracy of laser marking. The F-Theta objective lens can solve the above problems well, so that the incident beam deflected at equal angular velocity can achieve linear scanning on the focal plane.

[0069] In this way, precise control of multi-color dynamic marking can be achieved, adaptive multi-frequency adjustment can be performed, and real-time sensors and control algorithms can ensure the long-term stability of the system. Laser interference and multi-dimensional scanning technology can be integrated to perform multi-level anti-counterfeiting functions, making it easy to maintain and upgrade and adapt to different industrial scenarios.

[0070] As described above, the multi-color laser marking intelligent control system 100 based on multi-dimensional dynamic calibration according to the embodiment of the present application can be implemented in various terminal devices. In one example, the multi-color laser marking intelligent control system 100 based on multi-dimensional dynamic calibration can be integrated into the terminal device as a software module and / or hardware module. For example, the multi-color laser marking intelligent control system 100 based on multi-dimensional dynamic calibration can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the multi-color laser marking intelligent control system 100 based on multi-dimensional dynamic calibration can also be one of the many hardware modules of the terminal device.

[0071] Alternatively, in another example, the multi-color laser marking intelligent control system 100 based on multi-dimensional dynamic calibration and the terminal device may also be separate devices, and the multi-color laser marking intelligent control system 100 based on multi-dimensional dynamic calibration may be connected to the terminal device via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

Claims

1. A multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration, characterized in that: include: A multi-color laser marking data acquisition module, used to acquire the laser marking environment temperature values ​​at multiple predetermined time points acquired by the temperature sensor, the laser equipment text parameters acquired by the database, and the laser marking material property text parameters; A multi-color laser marking data extraction module, used to extract a laser marking ambient temperature feature vector and a laser marking parameter multimodal semantic feature vector from the laser marking ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor, the laser equipment text parameters collected by the database, and the laser marking material attribute text parameters; A multi-color laser marking device parameter adjustment judgment module, used to judge whether the multi-color laser marking device parameters need to be adjusted based on the laser marking environment temperature feature vector and the laser marking parameter multimodal semantic feature vector; Wherein, the multi-color laser marking data extraction module includes: A laser marking environment temperature value feature extraction unit, used for performing feature extraction on the laser marking environment temperature values ​​at a plurality of predetermined time points collected by the temperature sensor to obtain the laser marking environment temperature feature vector; A laser equipment text parameter feature extraction unit, used for extracting features from the laser equipment text parameters collected from the database to obtain a laser equipment text semantic feature vector; A laser marking material attribute text parameter feature extraction unit, used for extracting features from the laser marking material attribute text parameters to obtain a laser marking material attribute text semantic feature vector; The laser marking parameter multimodal feature association unit is used to associate the laser equipment text semantic feature vector with the laser marking material attribute text semantic feature vector to obtain the laser marking parameter multimodal semantic feature vector.

2. The multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to claim 1 is characterized in that: The laser marking environment temperature value feature extraction unit comprises: Arranging the laser marking environment temperature values ​​at a plurality of predetermined time points collected by the temperature sensor as a laser marking environment temperature input vector; The laser marking environment temperature input vector is passed through a laser marking environment temperature timing encoder to obtain the laser marking environment temperature feature vector.

3. The multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to claim 2 is characterized in that: The laser device text parameter feature extraction unit comprises: Segmenting the laser equipment text parameters collected from the database to obtain a laser equipment text parameter word sequence; The laser equipment text parameter word sequence is passed through a laser equipment text bidirectional long short-term memory neural network to obtain the laser equipment text semantic feature vector.

4. The multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to claim 3 is characterized in that: The laser marking material attribute text parameter feature extraction unit comprises: Embedding the laser marking material attribute text parameters through a laser marking material attribute text word encoder to obtain a laser marking material attribute text word vector sequence; The laser-marked material attribute text word vector sequence is passed through a laser-marked material attribute text convolutional neural network based on a multi-scale neighborhood feature extraction module to obtain the laser-marked material attribute text semantic feature vector.

5. The multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to claim 4 is characterized in that: The multi-color laser marking equipment parameter adjustment judgment module includes: A laser marking equipment feature fusion unit, used to fuse the laser marking environment temperature feature vector and the laser marking parameter multimodal semantic feature vector to obtain a laser marking equipment adjustment judgment feature vector; A laser marking equipment feature optimization unit, used for performing topological space constraints on the laser marking equipment adjustment judgment feature vector based on cross-domain transfer learning to obtain an optimized laser marking equipment adjustment judgment feature vector; The laser marking equipment adjustment parameter adjustment classification judgment unit is used to pass the optimized laser marking equipment adjustment judgment feature vector through a classifier to obtain a classification result, and the classification result is used to judge whether the multi-color laser marking equipment parameters need to be adjusted.

6. The multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to claim 5 is characterized in that: The laser marking equipment feature optimization unit comprises: Extract the target parameter matrix of the classifier; Decomposing the target parameter matrix into nodes in units of row vectors to obtain a set of target parameter node encoding vectors; Taking each target parameter node encoding vector in the set of target parameter node encoding vectors as the walking topological space, topological space constraints are respectively applied to the laser marking device adjustment judgment feature vectors to obtain a set of constrained laser marking device adjustment judgment feature vectors; and The position mean vector of the set of the constrained laser marking equipment adjustment judgment feature vectors is calculated to obtain the optimized laser marking equipment adjustment judgment feature vector.

7. The multi-color laser marking intelligent control system based on multi-dimensional dynamic calibration according to claim 6 is characterized in that: Taking each target parameter node encoding vector in the set of target parameter node encoding vectors as the walking topological space, topological space constraints are respectively performed on the laser marking device adjustment judgment feature vectors to obtain a set of constrained laser marking device adjustment judgment feature vectors, including: After multiplying the laser marking device adjustment judgment feature vector and the transposed vector of the target parameter node encoding vector, a natural exponential function value of the multiplication result is calculated to obtain a weighted exponential response weight; Calculating the Euclidean distance between the laser marking device adjustment judgment feature vector and the target parameter node coding vector to obtain a node coding distance value; Performing a dot multiplication on the node coding distance value and the laser marking device adjustment judgment feature vector, and calculating a natural exponential function value for each feature value of the vector after the dot multiplication to obtain a laser marking device distance guidance index feature vector; The weighted index response weight and the laser marking device distance guidance index feature vector are multiplied to obtain a constrained laser marking device adjustment judgment feature vector.

Images