A high-precision cutting machine motion control method based on Z-axis control

Abstract

The invention discloses a high-precision engraving machine motion control method based on Z-axis control, which specifically relates to the field of high-precision engraving machine motion control and solves the problems of engraving precision and thermal management. The method obtains a three-dimensional height model of a material to be engraved and vibration and wear data in the engraving process through high-resolution laser scanning and real-time monitoring, and uses a machine learning algorithm to construct a relationship model between image data and engraving parameters. In combination with the roughness coefficient of the engraving surface and the heat accumulation factor, the adaptability of the parameter combination is comprehensively evaluated, thereby realizing intelligent and refined control of the engraving process. The selected optimal parameter combination can ensure the smoothness and flatness of the engraving surface, effectively manage heat, reduce material deformation and tool wear, extend tool life, improve production efficiency and product consistency, reduce unnecessary adjustments and rework, and significantly improve the precision and stability of the engraving process.

Description

Technical Field

[0001] The present invention relates to the field of high-precision engraving machine motion control, and more specifically, to a high-precision engraving machine motion control method based on Z-axis control. Background Art

[0002] High-precision engraving machines are widely used in manufacturing, advertising, and handicraft production. Their main function is to perform fine engraving operations on the surface of materials by controlling engraving tools. In order to ensure the high quality of engraving effects, engraving machines need to have precise motion control capabilities, especially dynamic adjustment of the Z-axis height to adapt to the height changes on the surface of the material. At the same time, the heat generated during the engraving process needs to be effectively managed to prevent material deformation and tool wear, and improve engraving accuracy and efficiency.

[0003] Existing engraving machines usually rely on fixed parameter settings and pre-programmed paths to perform engraving operations, and lack the ability to respond to changes in material surface height in real time. In addition, the heat management generated during the engraving process is also insufficient, which can easily lead to material deformation and tool wear, thus affecting engraving quality and production efficiency. These shortcomings limit the application of high-precision engraving machines in complex materials and high-precision requirements, and cannot meet the needs of modern manufacturing for high-quality and high-efficiency engraving operations.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a high-precision engraving machine motion control method based on Z-axis control. Through high-resolution laser scanning and real-time monitoring, the three-dimensional height model of the material to be engraved and the vibration and wear data in the engraving process are obtained, and the relationship model between image data and engraving parameters is constructed using a machine learning algorithm. In combination with the engraving surface roughness coefficient and the heat accumulation factor, the adaptability of the parameter combination is comprehensively evaluated, thereby realizing the intelligent and refined control of the engraving process; the optimal parameter combination screened out can ensure the smoothness and flatness of the engraving surface, effectively manage heat, reduce material deformation and tool wear, extend tool life, improve production efficiency and product consistency, reduce unnecessary adjustments and rework, and significantly improve the accuracy and stability of the engraving process to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] S1, fix the material to be engraved to the designated area of ​​the equipment, use high-resolution laser to scan the surface of the material to be engraved, and generate a three-dimensional height model;

[0008] S2, analyzes the surface height change of the area to be engraved through a three-dimensional height model, monitors the vibration intensity and tool wear in real time, calculates the fit score, and determines whether the current engraving state is suitable for the area to be engraved. If it is suitable, dynamic height adjustment is performed to ensure that the engraving tool maintains a standard contact distance with the material surface. If it is not suitable, an early warning signal is issued;

[0009] S3, captures the engraving image data in real time and records the relevant parameters, uses the machine learning algorithm to build a relationship model between the image data and the engraving parameters, and generates multiple candidate parameter combinations that meet the preset quality requirements;

[0010] S4, extracting and analyzing the surface management information and thermal management information of the candidate parameter combinations, and selecting the best parameter combination by comprehensively calculating the optimization evaluation coefficients;

[0011] S5, input the best parameter combination into the equipment control computer, determine whether the current tool wear rate supports the completion of the current engraving task, and provide a signal based on the judgment result.

[0012] In a preferred embodiment, step S2 includes the following contents:

[0013] S2-1, based on the three-dimensional height model, analyze the surface height change of the area to be engraved and identify the flatness in the area;

[0014] Import the 3D height model data into the control system of the engraving machine to analyze the surface characteristics of the area to be engraved;

[0015] Assume that the 3D height model data is ,in is the plane coordinate, is the height value, calculate the height change of each point;

[0016] By standard deviation Measuring surface flatness and identifying uneven areas: ;

[0017] in, For the first The height value of the point, is the mean height, is the total number of points;

[0018] S2-2, real-time monitoring of the vibration intensity of the engraving drill and the degree of tool wear during the engraving process;

[0019] Real-time recording of the vibration data of the engraving tool and wear data ;

[0020] Assume that n vibration intensity data are collected per unit time And k times of wear degree data ; ; ;

[0021] S2-3, construct comprehensive feature vector , providing basic data for multivariate analysis;

[0022] ;

[0023] in, , , are the standardized data vectors of vibration intensity, flatness and wear degree respectively;

[0024] S2-4, let the comprehensive feature vector Follows multivariate normal distribution , construct a fitness scoring model;

[0025] Calculate the mean vector μ and covariance matrix based on historical data ; ; ;

[0026] in, represents the total number of samples, that is, the total number of comprehensive eigenvectors used to calculate the mean vector and covariance matrix; is the matrix transpose operator, which means that the vector Transpose to a row vector;

[0027] S2-5, calculate the probability density function value of the comprehensive eigenvector under the multivariate normal distribution As a fitness score ; ;

[0028] Where k is the dimension of the feature vector, is the determinant of the covariance matrix, is the inverse of the covariance matrix.

[0029] In a preferred embodiment, whether the current engraving state is suitable for the area to be engraved is determined according to the fitness score;

[0030] If the fit score is greater than or equal to the matching threshold, it is determined to be fit, an fit signal is generated, and dynamic height adjustment is prepared; otherwise, it is determined to be unfit, an abnormal warning is issued, and a warning signal is generated, indicating that the current engraving area and the engraving state of the current device are not compatible; if an fit signal is obtained, the Z-axis adjustment amount is calculated based on the three-dimensional height model and real-time monitoring data ;

[0031] in, The Z-axis drive performs adjustments for the target height, maintaining a standard contact distance between the engraving tool and the material surface.

[0032] In a preferred embodiment, step S3 includes the following contents:

[0033] S3.1, monitor the engraving area in real time through a camera, start the camera to capture images when engraving starts, synchronously record the engraving speed, engraving pressure and engraving depth, and mark each set of data with a timestamp;

[0034] S3.2, preprocessing the captured image data;

[0035] S3.3, using the synchronously recorded image data and lettering parameters as training data sets, each data sample contains image features and corresponding lettering parameters, marking the lettering quality score of each data sample, and using machine learning algorithms to build a relationship model;

[0036] S3.4, using the constructed relational model, input different engraving parameter combinations, predict the engraving quality and depth under each combination, and record the prediction results corresponding to each parameter combination; according to the relational model prediction results, output multiple candidate parameter combinations that meet the requirements.

[0037] In a preferred embodiment, step S4 includes the following contents:

[0038] For multiple candidate parameter combinations that meet the requirements, extract surface management information and thermal management information of each candidate parameter combination, wherein the surface management information includes a roughness coefficient of the lettering surface, and the thermal management information includes a heat accumulation factor;

[0039] The surface roughness coefficient and heat accumulation factor of the lettering are comprehensively analyzed and calculated to obtain the optimized evaluation coefficient;

[0040] Calculate the optimization evaluation coefficient of each candidate parameter combination, and compare the optimization evaluation coefficient with the optimization threshold. If the optimization evaluation coefficient is greater than or equal to the optimization threshold, it means that the corresponding parameter combination has met the expected requirements in terms of both the surface quality of the lettering and the thermal management effect. Then, sort the candidate parameter combinations from large to small according to the optimization evaluation coefficient, and mark the first one as the best parameter combination. On the contrary, if the optimization evaluation coefficient is less than the optimization threshold, it means that the corresponding parameter combination has failed to meet the expected requirements in terms of the surface quality of the lettering or the thermal management effect.

[0041] In a preferred embodiment, the process of obtaining the surface roughness coefficient of the lettering is as follows:

[0042] Perform multi-scale Gaussian blur on the lettering surface image of each candidate parameter combination to obtain images of different scales;

[0043] Use the Canny edge detection algorithm to extract the edges of multi-scale images and calculate the local curvature of the edge points at each scale ;

[0044] Among them, o represents the scale; v represents the index of the edge point; and is the coordinate difference of adjacent edge points;

[0045] For each scale calculate the standard deviation of the curvature ;

[0046] in, is the total number of edge points at the oth scale, is the mean curvature of the oth scale;

[0047] The surface roughness coefficient is obtained by combining the roughness of each scale. : ;

[0048] in, is the total number of scales.

[0049] In a preferred embodiment, the process of obtaining the heat accumulation factor is as follows:

[0050] According to the engraving speed , lettering pressure and material properties to create an improved model of heat generation: ; and is the material characteristic constant; is the heat generated in the bth second;

[0051] According to the thermal conductivity of the material and the heat diffusion equation, the heat diffused during the engraving process is calculated: ;λ is the thermal conductivity;γ is the thermal convection coefficient; is the temperature at the bth second; is the Laplace operator; is the heat diffused in the bth second;

[0052] Calculate the heat accumulation per second: ; is the accumulated heat at the bth second;

[0053] Combining the heat accumulation and its distribution smoothness, the heat accumulation factor is obtained: ;

[0054] in, is the standard deviation of heat accumulation; For total time.

[0055] In a preferred embodiment, step S5 includes the following contents:

[0056] Input the best parameter combination into the equipment’s control computer;

[0057] The control computer calculates the wear rate of the current tool based on the wear data monitored in real time;

[0058] Based on the current wear rate and the estimated time required for the engraving task, the total wear required to complete the entire engraving task is predicted;

[0059] Compare the predicted total wear with the maximum allowable wear; if the predicted total wear is less than or equal to the maximum allowable wear, it means that the current tool wear rate can support the completion of the lettering task; conversely, if the predicted total wear is greater than the maximum allowable wear, it means that the current tool wear rate cannot support the completion of the lettering task;

[0060] Based on the judgment result, the control computer will issue the corresponding operation signal; if the tool wear rate can support the completion of the task, it will issue a continue operation signal and the engraving task will continue; if the tool wear rate cannot support the completion of the task, it will issue a warning signal to prompt the operator to replace the tool or adjust the engraving parameters.

[0061] The technical effects and advantages of the high-precision engraving machine motion control method based on Z-axis control of the present invention are as follows:

[0062] 1. The present invention can accurately evaluate the matching degree between the current lettering state and the area to be lettered by constructing a comprehensive feature vector and setting it to obey the multivariate normal distribution and calculating the fitness score. In practical applications, the vibration intensity and tool wear degree are monitored in real time to ensure the accuracy of the data, so that the construction of the comprehensive feature vector is more comprehensive. The fitness scoring model is trained by historical data and can accurately reflect the statistical characteristics of various lettering states, thereby realizing accurate control of the lettering process. When the fitness score is higher than the threshold, dynamic height adjustment is automatically performed to maintain the standard contact distance between the lettering tool and the material surface, improve the lettering accuracy and quality, and reduce unnecessary errors and scrap rates. When the fitness score is lower than the threshold, an early warning signal is issued in time to avoid continuing to letter under incompatible conditions, effectively preventing tool damage and material waste. This method not only improves the efficiency and accuracy of lettering, but also greatly reduces the frequency of manual intervention, enhances the level of automation and intelligence, and makes the entire lettering process more stable and efficient.

[0063] 2. The present invention captures the image data in the engraving process, combines the parameters such as engraving speed, engraving pressure and engraving depth, and uses a machine learning algorithm to construct a relationship model between image data and engraving parameters, predicts the engraving quality and depth under different parameter combinations, and screens out parameter combinations that meet the preset quality requirements. The engraving surface roughness coefficient and heat accumulation factor are further extracted, and the candidate parameter combinations are screened by comprehensive calculation and optimization of the evaluation coefficient to ensure that the final selected parameter combination can achieve the best engraving surface quality and thermal management effect in actual operation. It can ensure the smoothness and flatness of the engraving product, improve the overall quality level of the engraving process, and effectively manage heat, reduce material deformation and tool wear, extend tool service life, and improve production efficiency and product consistency. By optimizing the engraving parameter combination, unnecessary adjustments and rework are reduced, and finally reliable data support and scientific basis are provided for the high-precision engraving process, which significantly improves the accuracy and stability of the engraving process. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A schematic flow chart of a high-precision engraving machine motion control method based on Z-axis control according to the present invention;

[0065] Figure 2 The figure is a schematic diagram of the processing steps of step S1 of a high-precision engraving machine motion control method based on Z-axis control of the present invention. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Example

[0068] Figure 1 The present invention provides a high-precision plotter motion control method based on Z-axis control, comprising:

[0069] S1, fix the material to be engraved to the designated area of ​​the equipment, use high-resolution laser to scan the surface of the material to be engraved, and generate a three-dimensional height model;

[0070] S2, analyzes the surface height change of the area to be engraved through a three-dimensional height model, monitors the vibration intensity and tool wear in real time, calculates the fit score, and determines whether the current engraving state is suitable for the area to be engraved. If it is suitable, dynamic height adjustment is performed to ensure that the engraving tool maintains a standard contact distance with the material surface. If it is not suitable, an early warning signal is issued;

[0071] S3, captures the engraving image data in real time and records the relevant parameters, uses the machine learning algorithm to build a relationship model between the image data and the engraving parameters, and generates multiple candidate parameter combinations that meet the preset quality requirements;

[0072] S4, extracting and analyzing the surface management information and thermal management information of the candidate parameter combinations, and selecting the best parameter combination by comprehensively calculating the optimization evaluation coefficients;

[0073] S5, input the best parameter combination into the equipment control computer, determine whether the current tool wear rate supports the completion of the current engraving task, and provide a signal based on the judgment result.

[0074] like Figure 2 As shown, step S1 includes the following contents:

[0075] S1.1, place the material to be engraved on the workbench of the engraving machine, and use a clamp, vacuum adsorption or other fixing device to secure the material in the specified position to prevent the material from moving during processing.

[0076] S1.2, start the high-resolution laser scanner, perform preliminary calibration on the scanner, verify that it is working properly, and synchronize with the control system of the engraving machine to accurately capture the details of the material surface.

[0077] S1.3, according to the size and shape of the material to be engraved, set the scanning range and resolution parameters to cover the entire area to be engraved and capture the slight undulations on the surface.

[0078] S1.4, start the high-resolution laser scanner to perform a comprehensive scan on the fixed material surface to obtain surface height data, avoid vibration and other interference during the process, and obtain high-precision scanning results.

[0079] S1.5, transmits the height data acquired by the laser scanner to the control system, corrects and filters the scanned data through the data processing algorithm, removes noise and errors, and generates a high-precision three-dimensional height model.

[0080] S1.6, using the processed height data, a three-dimensional height model of the surface of the material to be engraved is generated, and the model accurately reflects the real shape and height difference of the material surface.

[0081] S1.7, check the generated 3D height model to verify its consistency with the actual material surface height. If necessary, perform a second scan or data correction to ensure the accuracy and reliability of the model.

[0082] S1.8, the generated three-dimensional height model data is stored in the system database for backup to prevent data loss, and the model data is transmitted to the lettering control system to provide a reference for the subsequent lettering process.

[0083] Step S2 includes the following contents:

[0084] S2-1, based on the three-dimensional height model, analyze the surface height change of the area to be engraved and identify the flatness in the area.

[0085] Import the 3D height model data into the control system of the engraving machine to analyze the surface characteristics of the area to be engraved;

[0086] Assume that the 3D height model data is ,in is the plane coordinate, is the height value, and the height change of each point is calculated.

[0087] By standard deviation Measuring surface flatness and identifying uneven areas: ;

[0088] in, For the first The height value of the point, is the mean height, is the total number of points.

[0089] S2-2, real-time monitoring of the vibration intensity of the engraving drill and the degree of tool wear during the engraving process to ensure the accuracy of the data.

[0090] Install vibration sensors and wear sensors on the engraving tools to record vibration data in real time and wear data ;

[0091] Assume that n vibration intensity data are collected per unit time And k times of wear degree data ; ; ;

[0092] S2-3, construct comprehensive feature vector , providing basic data for multivariate analysis.

[0093] ;

[0094] in, , , They are the standardized data vectors of vibration intensity, flatness and wear degree respectively.

[0095] S2-4, assuming the comprehensive feature vector Follows multivariate normal distribution , build a fitness scoring model.

[0096] Calculate the mean vector μ and covariance matrix based on historical data ; ; ;

[0097] in, represents the total number of samples, that is, the total number of comprehensive eigenvectors used to calculate the mean vector and covariance matrix; is the matrix transpose operator, which means that the vector Transpose to a row vector.

[0098] S2-5, calculate the probability density function value of the comprehensive eigenvector under the multivariate normal distribution As a fitness score ; ;

[0099] Where k is the dimension of the feature vector, is the determinant of the covariance matrix, is the inverse of the covariance matrix.

[0100] A higher score indicates that the current engraving state is more compatible with the flatness of the area to be engraved. The adaptability of the current engraving state is quantitatively evaluated by calculating the probability density function of the multivariate normal distribution.

[0101] Determine whether the current engraving state is suitable for the area to be engraved based on the fitness score;

[0102] If the fit score is greater than or equal to the matching threshold, it is determined to be fit, an adaptation signal is generated, and dynamic height adjustment is prepared; otherwise, it is determined to be mismatched, an abnormal warning is issued, and a warning signal is generated, indicating that the current area to be engraved and the engraving status of the current device are not compatible, and the quality of the engraving cannot be met.

[0103] If the adaptation signal is obtained, the adjustment amount of the Z axis is calculated based on the 3D height model and real-time monitoring data. ;

[0104] in, The Z-axis drive is used to adjust the target height to maintain the standard contact distance between the engraving tool and the material surface. This ensures that the engraving tool works at the optimal height and improves engraving accuracy.

[0105] The present invention can accurately evaluate the matching degree between the current lettering state and the area to be lettered by constructing a comprehensive feature vector, assuming that it obeys a multivariate normal distribution, and calculating the fitness score. In practical applications, the vibration intensity and tool wear degree are monitored in real time to ensure the accuracy of the data, so that the construction of the comprehensive feature vector is more comprehensive. The fitness scoring model is trained by historical data and can accurately reflect the statistical characteristics of various lettering states, thereby realizing precise control of the lettering process. When the fitness score is higher than the threshold, dynamic height adjustment is automatically performed to maintain the standard contact distance between the lettering tool and the material surface, improve the lettering accuracy and quality, and reduce unnecessary errors and scrap rates. When the fitness score is lower than the threshold, an early warning signal is issued in time to avoid continuing to letter under incompatible conditions, effectively preventing tool damage and material waste. This method not only improves the efficiency and accuracy of lettering, but also greatly reduces the frequency of manual intervention, enhances the level of automation and intelligence, and makes the entire lettering process more stable and efficient.

[0106] In modern high-precision engraving processes, real-time monitoring and optimization of engraving parameters are essential to ensure engraving quality and efficiency. To achieve this goal, advanced image processing technology and machine learning algorithms must be used to capture and analyze data during the engraving process. By capturing engraving image data in real time with a high-resolution camera and simultaneously recording key parameters such as engraving speed, engraving pressure, and engraving depth, comprehensive engraving status information can be obtained. Combining this data with a machine learning algorithm, a relationship model between image data and engraving parameters can be constructed to reveal the impact of different parameter combinations on the engraving effect. This process can not only generate multiple parameter combinations that meet the preset quality requirements, but also comprehensively evaluate and screen these combinations by calculating key indicators such as the engraving surface roughness coefficient and heat accumulation factor. Ultimately, the best parameter combination can be screened out to optimize the engraving effect, reduce defects, increase tool life, and achieve higher production efficiency. This comprehensive approach provides scientific data support and a strong model foundation for high-precision engraving, making the engraving process more intelligent and efficient, and bringing significant technological progress and economic benefits to industrial applications.

[0107] Step S3 includes the following contents:

[0108] S3.1, install a high-resolution camera on the engraving machine, configure the camera's resolution, frame rate, exposure time and other parameters, so that the camera can monitor the engraving area in real time, and start the camera to capture images when engraving starts, and transmit image data to the control system through a high-speed interface. The image frame rate is set to 30 frames per second to capture the continuity and details of the engraving process, while synchronously recording the engraving speed, engraving pressure and engraving depth, and marking each set of data with a timestamp.

[0109] S3.2, denoise the captured image data to improve the image quality, then apply contrast enhancement and edge detection algorithms (such as Canny edge detection) to extract the edges of the lettering area and obtain the clear outline of the lettering lines. Calculate the lettering depth through the image analysis algorithm, estimate the difference between the actual lettering depth and the preset depth, and detect the lettering quality, identify defects such as uneven lines and breaks, and record the location and nature of each lettering defect.

[0110] S3.3, use the synchronously recorded image data and engraving parameters as training data sets, each data sample contains image features (such as edge, depth information) and corresponding engraving parameters (engraving speed, engraving pressure, engraving depth), and mark the engraving quality score of each data sample. Extract key features from image data, use PCA (principal component analysis) or other dimensionality reduction methods to reduce feature dimensions, select appropriate machine learning algorithms (such as multivariate regression, random forest or neural network) to build a relationship model, input feature data into the machine learning model for training, optimize model parameters, and use an independent validation set to evaluate model performance, calculate indicators such as prediction accuracy and mean square error (MSE), and adjust model parameters and feature extraction methods based on the evaluation results.

[0111] S3.4, using the constructed relational model, input different combinations of lettering parameters, predict the lettering quality and depth under each combination, and record the corresponding prediction results of each parameter combination, including lettering speed, lettering pressure, and lettering depth. According to the model prediction results, filter out the parameter combinations that meet the preset quality requirements, set the minimum standard for lettering quality (such as depth deviation, surface finish, etc.), filter out the combinations that do not meet the standards, and output multiple candidate parameter combinations that meet the requirements for further analysis and optimization in subsequent steps. Each candidate combination includes lettering speed, lettering pressure, lettering depth, and predicted lettering quality score.

[0112] Step S4 includes the following contents:

[0113] For multiple candidate parameter combinations that meet the requirements, surface management information and thermal management information of each candidate parameter combination are extracted, wherein the surface management information includes the roughness coefficient of the lettering surface, and the thermal management information includes the heat accumulation factor.

[0114] The surface roughness coefficient of the lettering reflects the smoothness and flatness of the lettering surface, directly affects the visual and tactile effects of the lettering, and is an important indicator of the lettering quality. A low roughness coefficient indicates that the lettering surface is smooth and of high quality, and can meet the requirements of fine processing. Therefore, by evaluating the surface roughness coefficient of the lettering, it can be ensured that the final selected parameter combination can achieve the best lettering surface quality in actual operation.

[0115] The heat accumulation factor measures the heat management of tools and materials during the engraving process. Excessive heat accumulation may cause material deformation, increased tool wear, and even engraving failure. Therefore, good thermal management is the key to ensuring continuous and stable engraving. By evaluating the heat accumulation factor, it can be ensured that the final selected parameter combination has a good thermal management effect in actual operation, extending the tool life, and ensuring production efficiency and product consistency.

[0116] Although the model can output multiple parameter combinations that meet the requirements, these combinations are only optimized based on basic parameters such as lettering depth, speed and pressure, and fail to fully consider the comprehensive impact of surface quality and thermal management during the actual processing process. Through further screening of the lettering surface roughness coefficient and heat accumulation factor, the actual effect of the parameter combination can be more comprehensively evaluated to ensure that the final selected parameter combination not only meets the requirements in theory, but also achieves the best effect in actual operation.

[0117] The surface roughness coefficient and heat accumulation factor of the lettering are comprehensively analyzed and calculated to obtain the optimized evaluation coefficient. For example, it can be obtained by the following calculation formula: ;

[0118] in, To optimize the evaluation coefficient; and are the surface roughness coefficient and heat accumulation factor of the lettering surface respectively; α and β are the preset proportional coefficients of the surface roughness coefficient and heat accumulation factor of the lettering surface respectively, and both are greater than zero.

[0119] Calculate the optimization evaluation coefficient of each candidate parameter combination, compare the optimization evaluation coefficient with the optimization threshold, if the optimization evaluation coefficient is greater than or equal to the optimization threshold, it means that the parameter combination has met the expected requirements in both the surface quality of the lettering and the thermal management effect, then sort the candidate parameter combinations from large to small according to the optimization evaluation coefficient, and mark the first ranked parameter combination as the best parameter combination, which is an ideal parameter combination suitable for actual operation, can provide high-quality lettering effects and maintain the service life of the tool. On the contrary, if the optimization evaluation coefficient is less than the optimization threshold, it means that the parameter combination has not met the expected requirements in terms of the surface quality of the lettering or the thermal management effect, which may lead to rough lettering surface, material deformation or increased tool wear, and is not suitable for actual operation. It is necessary to readjust the parameter combination or select other candidate combinations. Through this evaluation and screening method, it can be ensured that the parameter combination finally selected can provide the best performance and effect in the actual lettering process, improve production efficiency and product quality.

[0120] The process of obtaining the surface roughness coefficient of the lettering is as follows:

[0121] Multi-scale Gaussian blur is performed on the lettering surface image of each candidate parameter combination to obtain images of different scales.

[0122] Use the Canny edge detection algorithm to extract the edges of multi-scale images and calculate the local curvature of the edge points at each scale ;

[0123] Among them, o represents the scale; v represents the index of the edge point; and is the coordinate difference between adjacent edge points.

[0124] The Canny edge detection algorithm is used to extract edge information from images. The local curvature calculation of edge points can reflect the degree of change in surface shape and help quantify surface roughness.

[0125] For each scale calculate the standard deviation of the curvature ;

[0126] in, is the total number of edge points at the oth scale, is the mean curvature of the oth scale.

[0127] Standard Deviation It is used to measure the degree of discreteness of curvature. The larger the curvature standard deviation, the higher the surface roughness, which means the greater the surface unevenness.

[0128] The surface roughness coefficient is obtained by combining the roughness of each scale. : ;

[0129] in, is the total number of scales.

[0130] The surface roughness coefficient of lettering is used to reflect and express the smoothness and flatness of the lettering surface, and is one of the important indicators for measuring the quality of lettering. The size of the roughness coefficient directly reflects the surface treatment effect during the lettering process. A smaller roughness coefficient means that the lettering surface is smoother and more uniform, the lettering quality is higher, and it can meet the high-precision and high-demand processing requirements, and reduce the subsequent polishing and processing procedures. At the same time, a smoother surface can improve the aesthetics and feel of the lettering product, making the product more competitive in the market. On the contrary, a larger roughness coefficient means that there are more unevenness on the lettering surface, and the lettering quality is lower, which not only affects the aesthetics of the lettering effect, but also may cause functional problems in practical applications, such as increased friction or unfavorable subsequent processing. Therefore, by controlling and optimizing the surface roughness coefficient of lettering, the overall quality level of the lettering process can be effectively improved.

[0131] The process of obtaining the heat accumulation factor is as follows:

[0132] According to the engraving speed , lettering pressure and material properties to establish an improved heat generation model to calculate the heat generated during the lettering process. ;

[0133] in, and is the material characteristic constant; is the heat generated in the bth second.

[0134] According to the thermal conductivity of the material and the heat diffusion equation, the heat diffused during the engraving process is calculated to evaluate the heat loss. ;

[0135] Among them, λ is the thermal conductivity; γ is the thermal convection coefficient; is the temperature at the bth second; is the Laplace operator; is the heat diffused in the bth second.

[0136] Calculate the accumulated heat per second to evaluate the heat accumulation during the engraving process. ;

[0137] in, is the accumulated heat at the bth second.

[0138] The heat accumulation factor is obtained by combining the heat accumulation amount and its distribution smoothness to comprehensively evaluate the heat management situation. ;

[0139] in, is the standard deviation of heat accumulation; For total time.

[0140] The heat accumulation factor is used to reflect and represent the heat management of tools and materials during the engraving process, and is an important indicator for evaluating the thermal effect during the engraving process. The size of the heat accumulation factor reflects whether the heat is effectively managed during the engraving process. A smaller heat accumulation factor means that the heat can be evenly distributed and quickly dissipated during the engraving process, and the thermal management effect is good, which helps to maintain the optimal working state of tools and materials, reduce thermal deformation of materials and wear of tools, thereby extending the service life of tools and improving processing stability. Good thermal management can prevent excessive heat accumulation and avoid causing structural damage to materials or abnormal conditions during the engraving process. On the contrary, a larger heat accumulation factor means that more heat accumulates during the engraving process, the heat dissipation effect is poor, and the thermal management effect is poor, which may lead to thermal deformation of materials, rapid wear of tools, and even engraving failure, affecting production efficiency and product quality. Therefore, by controlling and optimizing the heat accumulation factor, the stability and reliability of the engraving process can be effectively improved to ensure high-quality processing results.

[0141] The present invention captures image data during the engraving process, combines parameters such as engraving speed, engraving pressure and engraving depth, and uses a machine learning algorithm to construct a relationship model between image data and engraving parameters, predicts the engraving quality and depth under different parameter combinations, and screens out parameter combinations that meet preset quality requirements. The engraving surface roughness coefficient and heat accumulation factor are further extracted, and the candidate parameter combinations are screened by comprehensive calculation and optimization of the evaluation coefficient to ensure that the final selected parameter combination can achieve the best engraving surface quality and thermal management effect in actual operation. It can ensure the smoothness and flatness of the engraving product, improve the overall quality level of the engraving process, effectively manage heat, reduce material deformation and tool wear, extend tool service life, and improve production efficiency and product consistency. By optimizing the engraving parameter combination, unnecessary adjustments and rework are reduced, and reliable data support and scientific basis are finally provided for the high-precision engraving process, which significantly improves the accuracy and stability of the engraving process.

[0142] Step S5 includes the following contents:

[0143] Input the best parameter combination into the control computer of the equipment to ensure that the equipment performs engraving operations according to the optimized parameters.

[0144] The wear sensor installed on the engraving tool monitors the wear of the tool in real time, collects wear data every second, and records changes in wear values.

[0145] The control computer calculates the wear rate of the current tool based on the wear data monitored in real time. The calculation takes into account the wear amount of the tool per unit time and the specific rate is obtained through the wear change value within the time interval.

[0146] Based on the current wear rate and the estimated time required for the engraving task, the total wear required to complete the entire engraving task is predicted. This step estimates the total wear of the tool before the task is completed by analyzing the current wear rate and the total time required for the engraving task.

[0147] Compare the predicted total wear with the maximum allowable wear. If the predicted total wear is less than or equal to the maximum allowable wear, it means that the current tool wear rate can support the completion of the lettering task; conversely, if the predicted total wear is greater than the maximum allowable wear, it means that the current tool wear rate cannot support the completion of the lettering task.

[0148] According to the judgment result, the control computer will issue the corresponding operation signal. If the tool wear rate can support the completion of the task, it will issue a continue operation signal and the engraving task will continue. If the tool wear rate cannot support the completion of the task, it will issue a warning signal to prompt the operator to replace the tool or adjust the engraving parameters to ensure the smooth progress of the engraving process and the service life of the tool.

[0149] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0150] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0151] It should be noted that, in this article, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0152] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A high-precision cutting plotter motion control method based on Z-axis control, characterized in that: S1, fix the material to be engraved to the designated area of ​​the equipment, use high-resolution laser to scan the surface of the material to be engraved, and generate a three-dimensional height model; S2, analyzes the surface height change of the area to be engraved through a three-dimensional height model, monitors the vibration intensity and tool wear in real time, calculates the fit score, and determines whether the current engraving state is suitable for the area to be engraved. If it is suitable, dynamic height adjustment is performed to ensure that the engraving tool maintains a standard contact distance with the material surface. If it is not suitable, an early warning signal is issued; S3, captures the engraving image data in real time and records the relevant parameters, uses the machine learning algorithm to build a relationship model between the image data and the engraving parameters, and generates multiple candidate parameter combinations that meet the preset quality requirements; S4, extracting and analyzing the surface management information and thermal management information of the candidate parameter combinations, and selecting the best parameter combination by comprehensively calculating the optimization evaluation coefficients; S5, input the best parameter combination into the equipment control computer, determine whether the current tool wear rate supports the completion of the current engraving task, and provide a signal based on the judgment result.

2. According to the high-precision cutting plotter motion control method based on Z-axis control as described in claim 1, it is characterized by: Step S2 includes the following contents: S2-1, based on the three-dimensional height model, analyze the surface height change of the area to be engraved and identify the flatness in the area; Import the 3D height model data into the control system of the engraving machine to analyze the surface characteristics of the area to be engraved; Assume that the 3D height model data is ,in is the plane coordinate, is the height value, calculate the height change of each point; By standard deviation Measuring surface flatness and identifying uneven areas: ； in, For the first The height value of the point, is the mean height, is the total number of points; S2-2, real-time monitoring of the vibration intensity of the engraving drill and the degree of tool wear during the engraving process; Real-time recording of the vibration data of the engraving tool and wear data ; Assume that the collection Sub-vibration intensity data and Wear degree data ; ； S2-3, construct comprehensive feature vector , providing basic data for multivariate analysis; ； in, , , are the standardized data vectors of vibration intensity, flatness and wear degree respectively; S2-4, let the comprehensive feature vector Follows multivariate normal distribution , construct a fitness scoring model; Calculate the mean vector based on historical data and the covariance matrix ; ; ; in, represents the total number of samples, that is, the total number of comprehensive eigenvectors used to calculate the mean vector and covariance matrix; is the matrix transpose operator, which means that the vector Transpose to a row vector; S2-5, calculate the probability density function value of the comprehensive eigenvector under multivariate normal distribution As a fitness score ; ; in, is the dimension of the feature vector, is the determinant of the covariance matrix, is the inverse of the covariance matrix.

3. A method according to claim 2 based on Axis-controlled high-precision plotter motion control method, characterized by: Determine whether the current engraving state is suitable for the area to be engraved based on the fitness score; If the fit score is greater than or equal to the matching threshold, it is determined to be fit, an fit signal is generated, and dynamic height adjustment is prepared; otherwise, it is determined to be unfit, an abnormal warning is issued, and a warning signal is generated, indicating that the current engraving area and the engraving state of the current device are not compatible; if an fit signal is obtained, the 3D height model and real-time monitoring data are used to calculate the fit. Axis adjustment : ; in, is the target height, through The axis drive performs the adjustment to maintain a standard contact distance between the engraving tool and the material surface.

4. A method according to claim 3 based on Axis-controlled high-precision plotter motion control method, characterized by: Step S3 includes the following contents: S3.1, monitor the engraving area in real time through a camera, start the camera to capture images when engraving starts, synchronously record the engraving speed, engraving pressure and engraving depth, and mark each set of data with a timestamp; S3.2, preprocessing the captured image data; S3.3, using the synchronously recorded image data and lettering parameters as training data sets, each data sample contains image features and corresponding lettering parameters, marking the lettering quality score of each data sample, and using machine learning algorithms to build a relationship model; S3.4, using the constructed relational model, input different engraving parameter combinations, predict the engraving quality and depth under each combination, and record the prediction results corresponding to each parameter combination; according to the relational model prediction results, output multiple candidate parameter combinations that meet the requirements.

5. A method according to claim 4 based on Axis-controlled high-precision plotter motion control method, characterized by: Step S4 includes the following contents: For multiple candidate parameter combinations that meet the requirements, extract surface management information and thermal management information of each candidate parameter combination, wherein the surface management information includes a roughness coefficient of the lettering surface, and the thermal management information includes a heat accumulation factor; The surface roughness coefficient and heat accumulation factor of the lettering are comprehensively analyzed and calculated to obtain the optimized evaluation coefficient; Calculate the optimization evaluation coefficient of each candidate parameter combination, and compare the optimization evaluation coefficient with the optimization threshold. If the optimization evaluation coefficient is greater than or equal to the optimization threshold, it means that the corresponding parameter combination has met the expected requirements in terms of both the surface quality of the lettering and the thermal management effect. Then, sort the candidate parameter combinations from large to small according to the optimization evaluation coefficient, and mark the first one as the best parameter combination. On the contrary, if the optimization evaluation coefficient is less than the optimization threshold, it means that the corresponding parameter combination has failed to meet the expected requirements in terms of the surface quality of the lettering or the thermal management effect.

6. A method according to claim 5 based on Axis-controlled high-precision plotter motion control method, characterized by: The process of obtaining the surface roughness coefficient of the lettering is as follows: Perform multi-scale Gaussian blur on the lettering surface image of each candidate parameter combination to obtain images of different scales; Use the Canny edge detection algorithm to extract the edges of multi-scale images and calculate the local curvature of the edge points at each scale ; ; in, Indicates scale; Indicates the index of the edge point; and is the coordinate difference of adjacent edge points; For each scale calculate the standard deviation of the curvature : ; in, For the The total number of edge points at each scale, For the The mean curvature of the scales; The roughness coefficient of the lettering surface is obtained by combining the roughness of each scale. : ； in, is the total number of scales.

7. A method according to claim 6 based on Axis-controlled high-precision plotter motion control method, characterized by: Step S5 includes the following contents: Input the best parameter combination into the equipment’s control computer; The control computer calculates the wear rate of the current tool based on the wear data monitored in real time; Based on the current wear rate and the estimated time required for the engraving task, the total wear required to complete the entire engraving task is predicted; Compare the predicted total wear with the maximum allowable wear; if the predicted total wear is less than or equal to the maximum allowable wear, it means that the current tool wear rate can support the completion of the lettering task; conversely, if the predicted total wear is greater than the maximum allowable wear, it means that the current tool wear rate cannot support the completion of the lettering task; Based on the judgment result, the control computer will issue the corresponding operation signal; if the tool wear rate can support the completion of the task, it will issue a continue operation signal and the engraving task will continue; if the tool wear rate cannot support the completion of the task, it will issue a warning signal to prompt the operator to replace the tool or adjust the engraving parameters.

Images