Multi-mode intelligent belt buckle mold carving method, system and equipment and medium

Abstract

The invention relates to the technical field of multi-mode intelligent carving, in particular to a multi-mode intelligent belt buckle mold carving method, system and equipment and a medium. The method comprises the following steps: firstly, calculating a Z-axis feed amount correction value based on a temperature gradient and a tool deformation amount, and obtaining vibration spectrum characteristics through FFT (Fast Fourier Transform) analysis; matching the frequency spectrum characteristics with a material process database to obtain optimal processing parameters, and generating a compensated processing track; in the machining process, the system records parameters and quality data in real time, laser cleaning is automatically triggered when the preset cutting frequency is reached, and meanwhile a database is continuously optimized and updated; through multi-sensor monitoring and intelligent compensation control, accurate evaluation of the cutting state and targeted optimization of process parameters are achieved, and the machining precision and efficiency are improved.

Description

Technical Field

[0001] This application relates to the technical field of multimodal intelligent engraving, and in particular to a multimodal intelligent belt buckle mold engraving method, system, equipment and medium. Background Technology

[0002] The metal mold processing industry currently faces the problem of uneven tool wear caused by differences in material properties, especially for materials such as steel, copper, and aluminum, which exhibit significant differences in hardness, thermal conductivity, and cutting performance. High-precision mold processing places extremely high demands on tool life and processing stability, requiring the simultaneous optimization of high precision and high efficiency.

[0003] Existing technologies typically employ online monitoring systems and adaptive control devices to adjust parameters by measuring single physical quantities such as cutting force or spindle power. Alternatively, they utilize intelligent numerical control systems that select machining parameters based on a pre-set process database and make tool change decisions using tool life prediction models.

[0004] However, existing technologies struggle to accurately monitor and evaluate the cutting conditions of various materials, and the lack of specific process parameters makes it difficult to balance machining accuracy and efficiency. This situation needs further improvement. Summary of the Invention

[0005] To address the challenges of existing adaptive control devices for mold engraving, which struggle to accurately monitor and evaluate the cutting states of various materials and lack specific process parameters, resulting in a trade-off between machining accuracy and efficiency, this application provides a multimodal intelligent belt buckle mold engraving method, system, equipment, and medium, employing the following technical solution: In a first aspect, this application provides a multimodal intelligent belt buckle mold engraving method, comprising the following steps: A fiber optic grating sensor array and a vibration sensor are used to monitor the machining status and obtain temperature gradient, tool deformation and spindle vibration signals. Based on the temperature gradient and tool deformation, the Z-axis feed correction value is calculated using a thermal deformation compensation algorithm, and the spindle vibration signal is subjected to FFT frequency domain analysis to obtain spectral characteristics. Based on the spectral features, a material and process mapping database is matched to obtain the combination of rotational speed and feed parameters, and the compensated machining trajectory is generated by combining the Z-axis feed correction value. The cutting process is performed based on the combination of the rotation speed and feed parameters and the machining trajectory. The machining parameters and quality data are recorded in real time. When the cumulative number of cuttings reaches a preset value, the pulsed laser cleaning device is triggered to remove the built-up edge at the tool tip. Based on the correspondence between the processing parameters and the quality data, the parameter combinations in the material and process mapping database are updated.

[0006] By adopting the above technical solution, it is difficult to guarantee the required machining accuracy due to the coupling effects of multiple physical quantities such as temperature gradient fluctuations, tool deformation, and vibration during the processing of belt buckle molds, and the significant differences in the cutting characteristics of different materials. In particular, the formation of built-up edge on the tool during continuous machining can cause fluctuations in machining quality. This application first calculates the Z-axis feed correction value based on temperature gradient and tool deformation using a thermal deformation compensation algorithm, and simultaneously performs FFT frequency domain analysis on the spindle vibration signal to obtain spectral characteristics. Then, the spectral characteristics are matched with the material process mapping database to obtain the optimal combination of rotational speed and feed parameters, and combined with the correction value to generate... The system generates a compensated machining trajectory. During the cutting process, the system records machining parameters and quality data in real time. When the cumulative number of cuts reaches a preset value, the pulsed laser cleaning device is automatically triggered to remove the built-up edge at the tool tip, ensuring the continuous stability of the machining process. At the same time, based on the correspondence between machining parameters and quality data, the system continuously updates and optimizes the parameter combinations in the material and process mapping database. Through multi-sensor collaborative monitoring and intelligent compensation control, the system achieves accurate monitoring and evaluation of the cutting state of various materials. Furthermore, based on the real-time optimization of the material and process mapping database, the process parameters are made more targeted, thereby achieving a synergistic improvement in machining accuracy and efficiency.

[0007] Optionally, based on the temperature gradient and tool deformation, a thermal deformation compensation algorithm is used to calculate the Z-axis feed correction value, specifically including the following steps: The thermal expansion of the cutting tool is calculated based on the temperature gradient, and the thermal expansion is linearly related to the temperature gradient. The tool deformation and the thermal expansion are superimposed to obtain the total displacement of the tool tip. When the ratio of the tool deformation to the thermal expansion exceeds a preset ratio, the spindle speed is reduced according to the ratio. Based on the total displacement of the tool tip, a reverse compensation method is used to calculate the Z-axis feed correction value. The value of the correction value is equal to the total displacement and in the opposite direction. In the transition area from the inner groove of the belt buckle mold to the buckle mating surface, the feed correction value changes linearly with the distance ratio.

[0008] By adopting the above technical solution, the tool is simultaneously affected by thermal expansion and cutting force during the processing of belt buckle molds, and this effect is particularly significant in the transition area from the inner groove to the snap-fit ​​surface. Traditional single compensation methods are difficult to meet the processing requirements. This application first calculates the thermal expansion of the tool by temperature gradient and uses a linear relationship model to ensure calculation accuracy. Then, the tool deformation and thermal expansion are superimposed to obtain the total displacement at the end. When the ratio of the two exceeds a preset value, the system will automatically reduce the spindle speed according to the ratio to avoid excessive deformation. Finally, a reverse compensation method is adopted to generate a Z-axis feed correction value that is equal in value to the total displacement but opposite in direction. Especially in the transition area from the inner groove to the snap-fit ​​surface, the correction value will change linearly with the distance ratio to ensure a smooth transition. Through the coordinated compensation of thermal deformation and cutting deformation, a real-time correction mechanism for tool end displacement is established to improve the mold processing accuracy. At the same time, intelligent adjustment of the spindle speed ensures processing efficiency.

[0009] Optionally, the combination of rotational speed and feed parameters is obtained by matching the spectral characteristics with a material and process mapping database, specifically including the following steps: The spectral features are decomposed to extract the dominant frequency and amplitude features. The spectral features include the vibration features of the bottom surface of the inner groove of the belt buckle mold and the buckle mating surface during processing. The similarity between the main vibration frequency and amplitude characteristics and the pre-stored spectral characteristics in the material and process mapping database is calculated to obtain the best matching material type. The material and process mapping database stores the main shaft vibration characteristic spectrum corresponding to different materials with a preset hardness range. Based on the material type, the corresponding optimal rotational speed and feed rate are retrieved from the material and process mapping database to generate a combination of rotational speed and feed parameters.

[0010] By adopting the above technical solution, since different materials exhibit significantly different cutting characteristics when machining the bottom surface of the inner groove and the buckle mating surface of the belt buckle mold, and existing technologies often use empirical parameters, it is difficult to accurately identify material characteristics and match the optimal process parameters, resulting in unstable machining quality. This application first performs feature decomposition on the collected spectral features, focusing on extracting the main vibration frequency and amplitude characteristics during the machining of the bottom surface of the inner groove and the buckle mating surface of the mold; then, it performs similarity calculation on these characteristics with the spectral features pre-stored in the material process mapping database, which stores the spindle vibration characteristic spectrum corresponding to materials with different hardness ranges, and obtains the optimal material type through matching; finally, according to the determined material type, it retrieves the corresponding optimal combination of rotational speed and feed rate parameters from the database; by establishing the mapping relationship between vibration characteristics and material properties, it achieves accurate matching of machining parameters, making the surface roughness of the machined surface stable within the expected range, while improving machining efficiency.

[0011] Optionally, the quality data includes machining errors of the inner groove depth, machining errors of the snap-fit ​​mating surface, and consistency parameters of the surface decorative texture.

[0012] Optionally, based on the correspondence between the processing parameters and the quality data, the parameter combinations in the material and process mapping database are updated, specifically including the following steps: The relationship between the machining error of the inner groove depth and the machining error of the snap-fit ​​surface and the current machining parameters is analyzed to obtain the evaluation results of the machining accuracy of the key dimensions; The surface quality evaluation result is obtained based on the correspondence between the consistency parameters of the surface decorative texture and the current processing parameters; Based on the evaluation results of the critical dimension machining accuracy and surface quality, the current machining parameters are comprehensively scored. The processing parameter combinations whose comprehensive scores are higher than a preset threshold are updated in the material and process mapping database.

[0013] By adopting the above technical solution, this application first analyzes the correspondence between the machining error of the inner groove depth and the snap-fit ​​surface and the current machining parameters, and obtains the evaluation results of the machining accuracy of key dimensions; at the same time, it evaluates the correlation between the consistency parameters of the surface decorative texture and the machining parameters, and obtains the surface quality evaluation results; then, it weights and integrates the two evaluation results to give a comprehensive score to the current machining parameters; finally, it updates the high-quality parameter combinations with comprehensive scores exceeding the preset threshold to the material and process mapping database; thus, it realizes the dynamic optimization of machining parameters, which enables the dimensional accuracy and surface quality of the mold to be improved simultaneously, and ensures the continuous progress of the machining process through continuous database updates.

[0014] Optionally, when the overall score is lower than a preset threshold, the method further includes the following steps: The temperature gradient change rate and vibration spectrum amplitude change rate during the machining process are obtained to determine the tool state characteristics. The tool status characteristics are compared with a preset tool wear threshold to determine whether the current tool needs to be replaced. If it is determined that the tool needs to be replaced, the pulsed laser cleaning device is triggered to clean the tool and then the tool condition is reassessed. If the tool still needs to be replaced after cleaning, then replace it with a new tool; if the tool does not need to be replaced, then adjust the machining parameters and repeat the machining process.

[0015] By adopting the above technical solution, when the processing quality score is lower than the preset threshold, this application first obtains the temperature gradient change rate and vibration spectrum amplitude change rate during the processing to assess the tool condition characteristics; then, these characteristics are compared with the preset tool wear threshold to determine whether the tool needs to be replaced; if replacement is required, the system will first activate the pulsed laser cleaning device for cleaning and reassess the tool condition; finally, based on the reassessment results, it will decide whether to replace the tool with a new one or adjust the processing parameters to continue using it; by establishing an active monitoring mechanism for tool condition, precise management of tool maintenance is achieved, and the tool service life is extended through the combination of cleaning and parameter adjustment.

[0016] Secondly, this application provides a multimodal intelligent belt buckle mold engraving system, comprising: The monitoring module includes a fiber optic grating sensor array and a vibration sensor mounted on the tool clamping end, used to monitor the machining status and obtain temperature gradient, tool deformation and spindle vibration signals; The compensation calculation module is used to calculate the Z-axis feed correction value based on the temperature gradient and tool deformation, and at the same time perform FFT frequency domain analysis on the spindle vibration signal to obtain the spectral characteristics. The parameter matching module is used to match the material and process mapping database according to the spectrum characteristics, obtain the combination of rotational speed and feed parameters, and generate a compensated machining trajectory by combining the Z-axis feed correction value. The machining control module is used to perform cutting based on the combination of rotational speed and feed parameters and the machining trajectory, and to record machining parameters and quality data in real time. The cleaning module includes a pulsed laser cleaning device for removing built-up edge at the tool tip when the cumulative number of cuts reaches a preset value; The data update module is used to update the parameter combinations in the material and process mapping database based on the correspondence between the processing parameters and the quality data.

[0017] Thirdly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described multimodal intelligent belt buckle mold engraving method.

[0018] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described multimodal intelligent belt buckle mold engraving method.

[0019] In summary, this application includes at least one of the following beneficial technical effects: This application proposes a multimodal intelligent belt buckle mold engraving method. The method calculates the Z-axis feed correction value based on temperature gradient and tool deformation, and obtains vibration spectrum characteristics through FFT analysis. The spectrum characteristics are then matched with a material and process database to obtain optimal processing parameters and generate a compensated processing trajectory. During processing, the system records parameters and quality data in real time. Laser cleaning is automatically triggered when a preset number of cuts is reached, while the database is continuously optimized and updated. Through multi-sensor monitoring and intelligent compensation control, accurate assessment of the cutting state and targeted optimization of process parameters are achieved, improving processing accuracy and efficiency. This application first calculates the tool's thermal expansion using a temperature gradient, employing a linear relationship model to ensure calculation accuracy. Then, it superimposes the tool deformation and thermal expansion to obtain the total end displacement. When the ratio of these two values ​​exceeds a preset value, the system automatically reduces the spindle speed to prevent excessive deformation. Finally, a reverse compensation method is used to generate a Z-axis feed correction value that is equal in value to the total displacement but in the opposite direction. Particularly in the transition area from the inner groove to the snap-fit ​​surface, the correction value changes linearly with the distance ratio, ensuring a smooth transition. Through the coordinated compensation of thermal deformation and cutting deformation, a real-time correction mechanism for tool end displacement is established, improving mold machining accuracy. Simultaneously, intelligent adjustment of the spindle speed ensures machining efficiency. This application first performs feature decomposition on the collected spectral features, focusing on extracting the main vibration frequency and amplitude characteristics during the machining of the bottom surface of the mold inner groove and the snap-fit ​​mating surface. Then, it calculates the similarity between these characteristics and the spectral features pre-stored in the material process mapping database. This database stores the spindle vibration feature spectra corresponding to materials with different hardness ranges, and the optimal material type is obtained through matching. Finally, based on the determined material type, the corresponding optimal combination of rotational speed and feed rate parameters is retrieved from the database. By establishing a mapping relationship between vibration features and material properties, precise matching of machining parameters is achieved, ensuring that the surface roughness of the machined surface remains stable within the expected range, while improving machining efficiency. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating a multimodal intelligent belt buckle mold engraving method according to an embodiment of this application; Figure 2 This is a flowchart illustrating step S200 in the multimodal intelligent belt buckle mold engraving method of this application embodiment; Figure 3 This is a flowchart illustrating step S300 in the multimodal intelligent belt buckle mold engraving method of this application embodiment; Figure 4 This is a flowchart illustrating step S500 in the multimodal intelligent belt buckle mold engraving method of this application embodiment; Figure 5This is a flowchart illustrating the process when the score is lower than a preset threshold in the multimodal intelligent belt buckle mold engraving method of this application embodiment; Figure 6 This is a schematic diagram of the modules of the multimodal intelligent belt buckle mold engraving system according to an embodiment of this application; Figure 7 This is an internal structural diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0021] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0022] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0023] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0024] Firstly, this application provides a multimodal intelligent belt buckle mold engraving method, referring to... Figure 1 It includes the following steps: The S100 uses a fiber optic grating sensor array and a vibration sensor to monitor the machining status and obtain temperature gradient, tool deformation and spindle vibration signals.

[0025] In this embodiment, the fiber optic grating sensor array refers to a combination of wavelength-modulated fiber optic sensors mounted at the tool holder end, used to measure the temperature distribution in the cutting area. Tool deformation refers to the change in tool geometry caused by thermal expansion and cutting force during machining. Spindle vibration signal refers to the axial and radial vibration waveforms generated during spindle rotation.

[0026] Specifically, eight fiber Bragg grating sensors are arranged in a ring array at the tool holder end, evenly distributed at 45-degree intervals, with a sampling frequency of 1kHz. A piezoelectric vibration sensor is fixed to the spindle housing, with a sampling frequency of 10kHz. The system establishes a temperature data acquisition table to record the real-time temperature values ​​of the sensors at different locations; simultaneously, tool deformation is calculated using the wavelength drift of the grating sensors. Taking the machining of aluminum alloy belt buckle molds as an example, the temperature gradient range is 0-100℃, and the deformation range is 0-20μm.

[0027] S200: Based on temperature gradient and tool deformation, the Z-axis feed correction value is calculated through a thermal deformation compensation algorithm. At the same time, the spindle vibration signal is analyzed by FFT frequency domain to obtain the spectral characteristics.

[0028] In this embodiment, the thermal deformation compensation algorithm is based on a linear mapping relationship between temperature gradient and deformation, used to calculate the tool position deviation caused by thermal deformation. The Z-axis feed correction value is the tool axial displacement adjustment amount to compensate for thermal deformation. FFT frequency domain analysis is a mathematical processing method that converts time-domain vibration signals into frequency-domain features.

[0029] Specifically, a temperature gradient-deformation mapping table is established, dividing the temperature gradient into three intervals: low temperature zone (0-50℃), medium temperature zone (51-150℃), and high temperature zone (151-300℃). Different compensation coefficients are used to calculate correction values ​​for each interval. A 1024-point FFT transform is applied to the spindle vibration signal to extract the spectral characteristics within the 0-2000Hz range, mainly including the amplitudes of the fundamental frequency, second harmonic, and third harmonic. For aluminum alloy processing, the fundamental frequency typically appears in the 200-400Hz range.

[0030] S300: Based on the spectral characteristics, match the material and process mapping database to obtain the combination of rotational speed and feed parameters, and generate the compensated machining trajectory by combining the Z-axis feed correction value.

[0031] In this embodiment, the material-process mapping database stores the correspondence between vibration characteristic spectra of different materials and optimal machining parameters. The combination of spindle speed and feed parameters includes two key parameters: spindle speed and feed rate. The compensated machining trajectory is a tool motion path corrected for thermal deformation.

[0032] Specifically, the database establishes a three-level index structure based on material hardness: soft materials (HRC20-35), medium materials (HRC36-45), and hard materials (HRC46-60). Each material records a standard vibration spectrum and its corresponding optimal parameter combination. The system selects the best-matching parameter combination by calculating the similarity between the current spectral characteristics and the standard spectra in the database. Taking the machining of HRC30 aluminum alloy as an example, the spindle speed range is 8000-12000 rpm, and the feed rate range is 2000-4000 mm / min.

[0033] The S400 performs cutting based on the combination of speed and feed parameters and the machining trajectory, and records machining parameters and quality data in real time.

[0034] When the cumulative number of cuts reaches a preset value, the pulsed laser cleaning device is triggered to remove the built-up edge at the tool tip.

[0035] S500: Based on the correspondence between processing parameters and quality data, update the parameter combinations in the material and process mapping database.

[0036] In this embodiment, the machining parameters include three key indicators: actual spindle speed, feed rate, and depth of cut. Quality data includes surface roughness and critical dimensional errors. A pulsed laser cleaning device is used to remove chips and built-up edge from the tool surface.

[0037] Specifically, the system uses a data acquisition card to record real-time parameters during the machining process, with a sampling interval of 1 second. Surface roughness and dimensional error data are acquired through an online measuring instrument. After every 5 cutting cycles, a pulsed laser is activated to clean the tool. A parameter-quality mapping table is established to record the machining quality indicators corresponding to each set of parameters. Parameter combinations with surface roughness Ra < 0.8 μm and dimensional error < 0.01 mm are selected and updated to the database. For aluminum alloy machining, the main optimized parameters include three indicators: spindle speed, feed rate, and depth of cut.

[0038] In one embodiment, refer to Figure 2 In step S200, based on the temperature gradient and tool deformation, the Z-axis feed correction value is calculated using a thermal deformation compensation algorithm, specifically including the following steps: S210. Calculate the thermal expansion of the tool based on the temperature gradient. The thermal expansion is linearly related to the temperature gradient.

[0039] In this embodiment, the temperature gradient refers to the temperature difference between different locations on the tool, characterizing the distribution of cutting heat within the tool. Thermal expansion refers to the volumetric expansion and deformation of the tool material due to temperature changes. A linear relationship indicates that the thermal expansion is proportional to the temperature gradient, and this relationship can be described by a linear equation.

[0040] Specifically, a temperature gradient-thermal expansion mapping table is established, dividing the temperature gradient into four intervals: 0-50℃, 51-100℃, 101-200℃, and 201-300℃. The thermal expansion is calculated for each interval using linear interpolation. Taking the machining of aluminum alloy belt buckle molds as an example, when the temperature gradient is 100℃, the corresponding thermal expansion is obtained by looking up the table based on the thermal expansion coefficient of the tool material.

[0041] S220. The tool deformation and thermal expansion are superimposed to obtain the total displacement of the tool tip. When the ratio of the tool deformation to the thermal expansion exceeds the preset ratio, the spindle speed is reduced according to the ratio.

[0042] In this embodiment, tool deformation refers to the elastic deformation displacement under the action of cutting force. The total displacement at the tool tip is the vector sum of thermal expansion and tool deformation. The preset ratio is a safety threshold ratio of deformation and thermal expansion based on experience.

[0043] Specifically, a two-dimensional data table is created, with the horizontal axis representing thermal expansion and the vertical axis representing tool deformation. The total displacement is calculated using vector addition. Three ratio ranges are defined: less than 0.5 is the safe range, 0.5-0.8 is the warning range, and greater than 0.8 is the danger range. When the ratio enters the warning range, the spindle speed is reduced by 20%; when it enters the danger range, it is reduced by 40%.

[0044] S230. Based on the total displacement of the tool tip, the Z-axis feed correction value is calculated using the reverse compensation method. The value of the correction value is equal to the total displacement and in the opposite direction.

[0045] In the transition area from the inner groove of the belt buckle mold to the buckle mating surface, the feed correction value changes linearly with the distance ratio.

[0046] In this embodiment, the reverse compensation method refers to applying a displacement correction on the tool movement trajectory that is equal in magnitude but opposite in direction to the total displacement. The feed rate correction value is the compensation distance in the Z-axis direction. The transition region refers to the connection between the mold inner groove and the snap-fit ​​mating surface.

[0047] Specifically, a transition zone compensation table is established, dividing the transition zone distance into ten equal division points. A full correction value is applied at the starting point, no correction is applied at the ending point, and the correction value at each intermediate point decreases linearly proportionally to the distance. For an inner groove with a depth of 10mm and a transition zone length of 2mm, the difference in correction value between adjacent division points is 10% of the total correction value. The system obtains the actual correction value for each processing point through a table lookup method, ensuring the processing continuity of the transition zone.

[0048] In one embodiment, refer to Figure 3In step S300, the combination of rotational speed and feed parameters is obtained by matching the material and process mapping database according to the spectral characteristics. This specifically includes the following steps: S310. Perform feature decomposition on the spectral features to extract the dominant frequency and amplitude features. The spectral features include the vibration features during the processing of the bottom surface of the inner groove of the belt buckle mold and the mating surface of the buckle.

[0049] In this embodiment, spectral characteristics refer to the frequency domain distribution of the vibration signal after FFT transformation. The dominant frequency is the frequency component with the highest energy in the spectrum. Amplitude characteristics include dominant frequency amplitude, harmonic amplitude, and band energy. The bottom surface of the inner groove of the belt buckle mold and the buckle mating surface are two key machining parts with different cutting characteristics.

[0050] Specifically, a spectrum analysis table is established, dividing the 0-2000Hz frequency range into low-frequency (0-500Hz), mid-frequency (501-1000Hz), and high-frequency (1001-2000Hz) bands. The maximum amplitude and corresponding frequency of each band are extracted to form a feature vector. For machining the bottom surface of the inner groove, the focus is on low-frequency features; for snap-fit ​​surfaces, mid-frequency features are also considered. The system stores these feature data in a working condition feature table for subsequent matching.

[0051] S320. Calculate the similarity between the main oscillation frequency and amplitude characteristics and the pre-stored spectral characteristics in the material and process mapping database to obtain the best matching material type.

[0052] The material and process mapping database stores spindle vibration characteristic maps corresponding to different materials with preset hardness ranges.

[0053] In this embodiment, the material-process mapping database is a multi-dimensional data structure that stores the standard spectral characteristics of different materials under various processing conditions. Similarity calculation quantifies the degree of feature matching using the Euclidean distance or cosine similarity of feature vectors. The best match refers to the material type with the highest similarity.

[0054] Specifically, standard spectral feature maps are recorded under each category, including the dominant frequency range and amplitude distribution characteristics. The similarity between the current feature and the material features in the database is calculated using the sliding window method, and the material type with the highest similarity is selected.

[0055] S330. Based on the material type, retrieve the corresponding optimal rotational speed and feed rate from the material and process mapping database to generate a combination of rotational speed and feed parameters.

[0056] In this embodiment, the optimal spindle speed refers to the highest spindle speed while ensuring machining quality. The feed rate is the linear movement speed of the tool relative to the workpiece. The combination of spindle speed and feed parameters represents the optimal balance between these two parameters.

[0057] In one embodiment, the quality data includes machining errors of the inner groove depth, machining errors of the snap-fit ​​mating surface, and consistency parameters of the surface decorative texture; refer to Figure 4 In step S500, based on the correspondence between processing parameters and quality data, the parameter combinations in the material and process mapping database are updated, specifically including the following steps: S510. Analyze the correspondence between the machining error of the inner groove depth and the machining error of the snap-fit ​​surface and the current machining parameters to obtain the evaluation results of the machining accuracy of the key dimensions.

[0058] In this embodiment, the machining error of the inner groove depth refers to the deviation between the actual machining depth and the designed depth. The machining error of the snap-fit ​​mating surface refers to the difference between the actual size and the standard size of the mating surface. The evaluation result of the machining accuracy of the critical dimensions is a quantitative assessment value of these two error indicators. The current machining parameters include three key indicators: spindle speed, feed rate, and depth of cut.

[0059] Specifically, a dimensional accuracy evaluation table is established, dividing the inner groove depth error into four ranges: excellent (0-5μm), good (6-10μm), acceptable (11-15μm), and unacceptable (>15μm); the mating surface error is also divided into four ranges: excellent (0-3μm), good (4-7μm), acceptable (8-10μm), and unacceptable (>10μm). The system records the two error values ​​under each set of processing parameters, calculates the weighted average score according to a weight ratio of 4:6, and obtains the accuracy evaluation score.

[0060] S520. Based on the correspondence between the consistency parameters of the surface decorative texture and the current processing parameters, the surface quality evaluation result is obtained.

[0061] In this embodiment, the consistency parameters of the surface decorative texture include three indicators: texture spacing uniformity, texture depth uniformity, and texture directionality. The surface quality evaluation result is a comprehensive assessment value of these parameters. The current processing parameters are the same as in step S510, used to analyze the influence of the parameters on surface quality.

[0062] Specifically, a surface quality evaluation table is established, and scoring standards are set for three indicators: spacing uniformity deviation range (0-10%), depth consistency deviation range (0-15%), and directionality deviation range (0-5 degrees). These parameters are measured using image processing methods, and the measurement results are weighted and averaged according to a weight of 3:4:3 to obtain the surface quality score.

[0063] S530: Based on the evaluation results of critical dimension machining accuracy and surface quality, a comprehensive score is given to the current machining parameters.

[0064] In this embodiment, the comprehensive score is the total score calculated by weighting the evaluation results of critical dimension machining accuracy and surface quality according to a certain proportion. A preset threshold is the scoring standard for selecting high-quality machining parameters. The evaluation of the current combination of machining parameters uses a percentage-based scoring method.

[0065] Specifically, a comprehensive scoring table is established, and the overall score is calculated by weighting the critical dimension accuracy score and the surface quality score at a ratio of 7:3. Four scoring levels are set: Excellent (90-100 points), Good (80-89 points), Pass (70-79 points), and Unsatisfactory (<70 points). The system records the score of each set of parameters, providing a basis for parameter optimization.

[0066] S540. Update the processing parameter combinations with comprehensive scores higher than the preset threshold to the material and process mapping database.

[0067] In this embodiment, the material-process mapping database is a dynamically updated parameter library that stores the optimal processing parameter combinations for different materials. A preset threshold is the standard score line for parameter selection. Update operations include adding high-quality parameter combinations and deleting inefficient parameter combinations.

[0068] Specifically, a parameter update rule table is established, with an update threshold of 85 points. For parameter combinations whose overall score exceeds the threshold, their complete process parameter information, including spindle speed, feed rate, and depth of cut, is recorded. Simultaneously, a parameter combination usage frequency statistics table is established. When the database capacity reaches its limit, parameter combinations with low usage frequency and low scores are prioritized for deletion. The system performs an update operation after each batch of machining tasks is completed.

[0069] In one embodiment, refer to Figure 5 When the overall score is lower than a preset threshold, the method also includes the following steps: S550: Obtain the rate of change of temperature gradient and the rate of change of vibration spectrum amplitude during the machining process to obtain the tool state characteristics.

[0070] In this embodiment, the temperature gradient change rate refers to the rate of change of the temperature gradient in the cutting zone per unit time. The vibration spectrum amplitude change rate refers to the rate of increase of the amplitude of the dominant frequency. Tool condition characteristics are a comprehensive indicator reflecting the degree of tool wear. The machining process refers to the continuous machining stage from the start of cutting to the current moment.

[0071] Specifically, a tool condition monitoring table is established to record historical data on temperature gradient and vibration amplitude. The machining process is divided into 10 time periods, and the rate of change between adjacent time periods is calculated. The rate of change of temperature gradient is divided into four intervals: stable (0-2℃ / min), gradual change (2-5℃ / min), rapid change (5-10℃ / min), and abrupt change (>10℃ / min). The rate of change of vibration amplitude is also divided into four intervals: stable (0-3% / min), gradual change (3-8% / min), rapid change (8-15% / min), and abrupt change (>15% / min).

[0072] S560. Based on the tool condition characteristics, compare them with the preset tool wear threshold to determine whether the current tool needs to be replaced.

[0073] In this embodiment, the tool wear threshold is a tool replacement standard determined based on a large amount of experimental data. The preset tool wear threshold includes two indicators: a temperature gradient change rate threshold and a vibration amplitude change rate threshold. The comparison process is a judgment procedure that compares the current state characteristics with these thresholds.

[0074] Specifically, a tool wear judgment table is established, setting the threshold for temperature gradient change rate to 8℃ / min and the threshold for vibration amplitude change rate to 12% / min. The actual values ​​of both indicators are divided by their corresponding thresholds to obtain the wear index. Three wear levels are defined: slight wear (index < 0.6), moderate wear (index 0.6-0.9), and severe wear (index > 0.9). When any indicator reaches the severe wear level, the tool is deemed necessary to replace.

[0075] S570. If it is determined that the tool needs to be replaced, the pulsed laser cleaning device is triggered to clean the tool and then the tool condition is reassessed.

[0076] In this embodiment, the pulsed laser cleaning device is a tool used to remove debris and adhering substances from the surface of cutting tools. Re-evaluation refers to repeating the tool condition detection process after cleaning. The cleaning process includes two stages: laser scanning and cooling.

[0077] Specifically, a laser cleaning parameter table is established, setting the cleaning process parameters: laser power range (100-500W), pulse frequency range (0.5-2kHz), and scanning speed range (10-50mm / s). The appropriate parameter combination is selected based on the tool material, and the cleaning procedure is executed. After cleaning, a 1-minute cooling period is allowed, followed by re-collecting the temperature gradient and vibration signals, and calculating the rate of change for evaluation.

[0078] S580. If the tool still needs to be replaced after cleaning, replace it with a new tool; if the tool does not need to be replaced, adjust the machining parameters and re-machine.

[0079] In this embodiment, "new tool" refers to an unused tool that has been replaced. "Adjusting machining parameters" means reducing the cutting load based on the original parameters. "Re-machining" means continuing the machining program using the adjusted parameters.

[0080] Specifically, a parameter adjustment rule table is established. When it is determined that no tool change is needed, the parameters are adjusted according to the following rules: spindle speed reduced by 10%-20%, feed rate reduced by 15%-25%, and depth of cut reduced by 20%-30%. The adjusted parameter combination must meet the minimum efficiency requirements. When replacing with a new tool, machining is restarted using the standard parameter combination in the database. The system records the specific details of each adjustment or replacement to optimize the tool management strategy.

[0081] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0082] Secondly, this application provides a multimodal intelligent belt buckle mold engraving system. The multimodal intelligent belt buckle mold engraving system of this application will be described below in conjunction with the above-mentioned multimodal intelligent belt buckle mold engraving method.

[0083] Reference Figure 6 A multimodal intelligent belt buckle mold engraving system, comprising: The monitoring module includes a fiber optic grating sensor array and a vibration sensor mounted on the tool clamping end, used to monitor the machining status and obtain temperature gradient, tool deformation and spindle vibration signals; The compensation calculation module is used to calculate the Z-axis feed correction value based on the temperature gradient and tool deformation, and at the same time perform FFT frequency domain analysis on the spindle vibration signal to obtain the spectral characteristics. The parameter matching module is used to match the material and process mapping database according to the spectrum characteristics, obtain the combination of rotation speed and feed parameters, and generate the compensated machining trajectory by combining the Z-axis feed correction value. The machining control module is used to perform cutting based on the combination of speed and feed parameters and the machining trajectory, and to record machining parameters and quality data in real time. The cleaning module includes a pulsed laser cleaning device for removing built-up edge at the tool tip when the cumulative number of cuts reaches a preset value; The data update module is used to update the parameter combinations in the material and process mapping database based on the correspondence between processing parameters and quality data.

[0084] In one embodiment, this application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Figure 7As shown, the electronic device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a multimodal intelligent belt buckle mold engraving method.

[0085] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0086] In one embodiment, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0087] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0088] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method for engraving a multimodal intelligent belt buckle mold, characterized in that, Includes the following steps: A fiber optic grating sensor array and a vibration sensor are used to monitor the machining status and obtain temperature gradient, tool deformation and spindle vibration signals. Based on the temperature gradient and tool deformation, the Z-axis feed correction value is calculated using a thermal deformation compensation algorithm, and the spindle vibration signal is subjected to FFT frequency domain analysis to obtain spectral characteristics. Based on the spectral features, a material and process mapping database is matched to obtain the combination of rotational speed and feed parameters, and the compensated machining trajectory is generated by combining the Z-axis feed correction value. The cutting process is performed based on the combination of the rotation speed and feed parameters and the machining trajectory. The machining parameters and quality data are recorded in real time. When the cumulative number of cuttings reaches a preset value, the pulsed laser cleaning device is triggered to remove the built-up edge at the tool tip. Based on the correspondence between the processing parameters and the quality data, the parameter combinations in the material and process mapping database are updated.

2. The multimodal intelligent belt buckle mold engraving method according to claim 1, characterized in that, Based on the temperature gradient and tool deformation, the Z-axis feed correction value is calculated using a thermal deformation compensation algorithm, specifically including the following steps: The thermal expansion of the cutting tool is calculated based on the temperature gradient, and the thermal expansion is linearly related to the temperature gradient. The tool deformation and the thermal expansion are superimposed to obtain the total displacement of the tool tip. When the ratio of the tool deformation to the thermal expansion exceeds a preset ratio, the spindle speed is reduced according to the ratio. Based on the total displacement of the tool tip, a reverse compensation method is used to calculate the Z-axis feed correction value. The value of the correction value is equal to the total displacement and in the opposite direction. In the transition area from the inner groove of the belt buckle mold to the buckle mating surface, the feed correction value changes linearly with the distance ratio.

3. The multimodal intelligent belt buckle mold engraving method according to claim 1, characterized in that, Based on the spectral characteristics, a material and process mapping database is matched to obtain the combination of rotational speed and feed parameters, specifically including the following steps: The spectral features are decomposed to extract the dominant frequency and amplitude features. The spectral features include the vibration features of the bottom surface of the inner groove of the belt buckle mold and the buckle mating surface during processing. The similarity between the main vibration frequency and amplitude characteristics and the pre-stored spectral characteristics in the material and process mapping database is calculated to obtain the best matching material type. The material and process mapping database stores the main shaft vibration characteristic spectrum corresponding to different materials with a preset hardness range. Based on the material type, the corresponding optimal rotational speed and feed rate are retrieved from the material and process mapping database to generate a combination of rotational speed and feed parameters.

4. The multimodal intelligent belt buckle mold engraving method according to claim 1, characterized in that, The quality data includes machining errors in the inner groove depth, machining errors in the snap-fit ​​mating surface, and consistency parameters of the surface decorative texture.

5. The multimodal intelligent belt buckle mold engraving method according to claim 4, characterized in that, Based on the correspondence between the processing parameters and the quality data, the parameter combinations in the material and process mapping database are updated, specifically including the following steps: The relationship between the machining error of the inner groove depth and the machining error of the snap-fit ​​surface and the current machining parameters is analyzed to obtain the evaluation results of the machining accuracy of the key dimensions; The surface quality evaluation result is obtained based on the correspondence between the consistency parameters of the surface decorative texture and the current processing parameters; Based on the evaluation results of the critical dimension machining accuracy and surface quality, the current machining parameters are comprehensively scored. The processing parameter combinations whose comprehensive scores are higher than a preset threshold are updated in the material and process mapping database.

6. The multimodal intelligent belt buckle mold engraving method according to claim 5, characterized in that, When the overall score is lower than a preset threshold, the method further includes the following steps: The temperature gradient change rate and vibration spectrum amplitude change rate during the machining process are obtained to determine the tool state characteristics. The tool status characteristics are compared with a preset tool wear threshold to determine whether the current tool needs to be replaced. If it is determined that the tool needs to be replaced, the pulsed laser cleaning device is triggered to clean the tool and then the tool condition is reassessed. If the tool still needs to be replaced after cleaning, then replace it with a new tool; if the tool does not need to be replaced, then adjust the machining parameters and repeat the machining process.

7. A multimodal intelligent belt buckle mold engraving system, characterized in that, include: The monitoring module includes a fiber optic grating sensor array and a vibration sensor mounted on the tool clamping end, used to monitor the machining status and obtain temperature gradient, tool deformation and spindle vibration signals; The compensation calculation module is used to calculate the Z-axis feed correction value based on the temperature gradient and tool deformation, and at the same time perform FFT frequency domain analysis on the spindle vibration signal to obtain the spectral characteristics. The parameter matching module is used to match the material and process mapping database according to the spectrum characteristics, obtain the combination of rotational speed and feed parameters, and generate a compensated machining trajectory by combining the Z-axis feed correction value. The machining control module is used to perform cutting based on the combination of rotational speed and feed parameters and the machining trajectory, and to record machining parameters and quality data in real time. The cleaning module includes a pulsed laser cleaning device for removing built-up edge at the tool tip when the cumulative number of cuts reaches a preset value; The data update module is used to update the parameter combinations in the material and process mapping database based on the correspondence between the processing parameters and the quality data.

8. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the multimodal intelligent belt buckle mold engraving method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the multimodal intelligent belt buckle mold engraving method according to any one of claims 1-6.

Images