A method, device, equipment and medium for self-tuning servo parameters of a carving machine

Abstract

This application relates to the field of servo control technology for CNC engraving equipment, and discloses a method, device, equipment, and medium for self-tuning servo parameters of an engraving machine. The method includes: determining a contour error that matches the standard test trajectory to characterize machining accuracy; determining a vibration index that matches the standard test trajectory to characterize machining stability; and determining a target servo parameter combination suitable for the current machining condition based on a fitness function constructed from the contour error and the vibration index, so that the servo controller of the engraving machine performs engraving processing according to the target servo parameter combination. This achieves autonomous decision-making throughout the entire process from state perception and performance evaluation to parameter self-optimization, thereby solving the technical problem of how to self-adjust according to specific working conditions during actual engraving machine processing.

Description

Technical Field

[0001] This application relates to the field of servo control technology for CNC engraving equipment, and in particular to a method, device, equipment and medium for self-tuning servo parameters of an engraving machine. Background Technology

[0002] CNC engraving machines are widely used in precision machining in industries such as mold making, advertising, and handicrafts. Their machining quality directly depends on the control performance of the permanent magnet synchronous servo system of each feed axis, and the tuning of the PI (Proportional-Integral) parameters is particularly critical.

[0003] Currently, servo parameters are typically manually tuned and fixed at the factory based on typical operating conditions, making it difficult to adapt to the complex variations in actual machining: materials range from cork and plastic to hard aluminum and metals, with significantly different load characteristics; the complexity of the machining patterns varies, especially at high-speed corners, where fixed parameters often cannot balance dynamic response and stability; and the requirements for efficiency and accuracy also differ between roughing and finishing stages. Fixed PI parameters cannot achieve the best trade-off in all operating conditions, easily leading to problems such as contour distortion, surface ripples, and even step loss, seriously affecting machining quality.

[0004] Therefore, how to solve the problem of how engraving machines can adaptively adjust according to real-time working conditions during processing has become a technical problem that needs to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and medium for self-tuning servo parameters of an engraving machine, which solves the technical problem of how to adaptively adjust the engraving machine according to real-time working conditions during processing.

[0006] To achieve the above objectives, the main technical solutions adopted in this application include:

[0007] In a first aspect, embodiments of this application provide a method for self-tuning servo parameters of an engraving machine, the method comprising:

[0008] Obtain a trajectory segment of the current processing condition, and extract a fixed trajectory unit from the trajectory segment as a standard test trajectory;

[0009] Determine the contour error that matches the standard test trajectory to characterize the machining accuracy;

[0010] Determine vibration indices that match the standard test trajectory to characterize processing smoothness;

[0011] Based on the fitness function constructed from the contour error and the vibration index, a target servo parameter combination suitable for the current processing condition is determined, so that the servo controller of the engraving machine can perform engraving processing according to the target servo parameter combination.

[0012] This embodiment provides a self-tuning method for servo parameters of an engraving machine. It constructs a multi-objective fitness function using contour accuracy and machining vibration indices, and employs a particle swarm optimization algorithm to determine the optimal servo parameter combination that matches the current machining conditions. This enables the engraving machine to achieve high-precision and highly stable engraving processing based on this parameter combination. This embodiment constitutes a closed-loop intelligent control system capable of real-time sensing of the machining status and online self-tuning of servo parameters accordingly. It achieves fully autonomous decision-making throughout the entire process, from status sensing and performance evaluation to parameter self-optimization, thereby solving the technical problem of how to self-adjust based on real-time working conditions during actual engraving machine processing.

[0013] In one implementation, determining the contour error characterizing machining accuracy that matches the standard test trajectory includes:

[0014] The standard test trajectory is sampled to obtain multiple sampling points;

[0015] For any sampling point, obtain the actual position and theoretical position of each linkage axis within the servo controller;

[0016] Based on the actual location and the theoretical location, determine the position error corresponding to any sampling point;

[0017] Based on the positional error and the number of sampling points, a contour error matching the standard test trajectory is determined to characterize the machining accuracy.

[0018] This embodiment calculates the contour error, using it as a key quantitative indicator for evaluating and optimizing the dynamic performance of the servo system. Specifically, based on the position error data obtained from each sampling point, the contour error value, characterizing the overall trajectory following accuracy, is obtained by combining the position error with the number of sampling points. This method achieves a multi-dimensional and continuous evaluation of machining accuracy, providing a direct and reliable optimization target and basis for subsequent adaptive adjustment of parameters.

[0019] In one implementation, determining the vibration index for characterizing processing smoothness that matches the standard test trajectory includes:

[0020] The standard test trajectory is sampled to obtain multiple sampling points;

[0021] Obtain the actual speed sequence of each linkage axis within the servo controller at multiple sampling points;

[0022] Perform a Fast Fourier Transform on the acquired actual velocity sequence to obtain the energy amplitude corresponding to the multiple sampling points;

[0023] The energy amplitudes exceeding the preset high-frequency threshold are aggregated, and the sum of the aggregated energy amplitudes is determined as a vibration index that matches the standard test trajectory and is used to characterize the smoothness of the processing.

[0024] This embodiment establishes a vibration index as a quantitative evaluation parameter for the actual operating data of the servo system. The vibration index is obtained by performing frequency domain analysis on the velocity response of the linkage shaft under a standard test trajectory, extracting and accumulating the energy exceeding a preset high-frequency threshold; it directly characterizes the intensity of high-frequency oscillations generated by the mechanical system during dynamic operation, effectively reflecting the stability, anti-interference ability, and potential surface finish of the processing.

[0025] In one implementation, the fitness function is constructed as follows:

[0026] Configure the first weight of the contour error;

[0027] Configure a second weight for the vibration index;

[0028] A fitness function is constructed based on the contour error, the vibration index, the first weight, and the second weight.

[0029] This embodiment integrates contour error and vibration index into a unified quantification system by constructing a fitness function. This function uses a specific weighting method to synthesize the contour error, reflecting machining accuracy, and the vibration index, characterizing operational stability, into a single scalar value. The value of the fitness function directly reflects the comprehensive control performance of the current engraving machine under specific parameters: a larger value indicates better performance in tracking accuracy and vibration suppression, resulting in a more ideal machining state; conversely, a smaller value indicates that the current parameters need adjustment. This design provides a clear and calculable performance evaluation target for subsequent particle swarm optimization algorithms and is the core basis for achieving online parameter self-tuning.

[0030] In one implementation, determining the target servo parameter combination adapted to the current processing condition includes:

[0031] Multiple particles are generated within a predetermined range of servo parameters to characterize combinations of servo parameters.

[0032] Based on the fitness function, the fitness value of each particle is determined during the carving process along the standard test trajectory, and new particles are obtained through iterative updates until the preset conditions are met, thus obtaining the target servo parameter combination corresponding to the current processing condition.

[0033] This embodiment iteratively optimizes each particle in the particle swarm optimization algorithm based on a constructed fitness function. Specifically, each particle represents a specific set of servo controller parameters. By substituting each set of parameters into the servo controller, each axis is driven to execute a standard test trajectory, and running data is collected synchronously. Based on this data, contour error and vibration index are calculated, and then the fitness value corresponding to the particle is obtained through the fitness function. During the iterative optimization process, the algorithm dynamically updates the position (i.e., parameter combination) and velocity of each particle based on the swarm's historical best and the individual's historical best information. This process is repeated cyclically, continuously generating and evaluating new parameter particles. The iteration terminates when the iteration result meets the preset convergence conditions (e.g., the fitness value meets the preset value, the maximum number of iterations is reached). At this point, the parameter combination represented by the globally optimal particle is determined as the target servo parameter combination that can optimally balance machining accuracy and operational stability and adapt to the current machining conditions. This method realizes directional search and automatic optimization from parameter space to performance index.

[0034] In one embodiment, the servo parameter combination includes one or more combinations of position loop proportional coefficient, position loop integral coefficient, velocity loop proportional coefficient, velocity loop integral coefficient, and velocity feedforward coefficient.

[0035] This embodiment achieves optimized performance tuning through a combination of one or more parameters, including the position loop proportional coefficient, position loop integral coefficient, velocity loop proportional coefficient, velocity loop integral coefficient, and velocity feedforward coefficient. The position loop parameters primarily determine trajectory tracking accuracy and dynamic response characteristics, while the velocity loop parameters determine motion smoothness and disturbance rejection capability. Together, they determine the core performance characteristics in terms of overall stiffness, response speed, and operational stability, and are key control variables affecting the quality of the engraving process.

[0036] In one implementation, extracting fixed trajectory units from the trajectory segment as a standard test trajectory includes:

[0037] Based on a pre-set length threshold, fixed trajectory units that satisfy the length threshold are extracted from the trajectory segment;

[0038] The fixed trajectory unit is defined as the standard test trajectory.

[0039] This embodiment extracts fixed trajectory units that meet the requirements from actual trajectory segments by using a preset length threshold, and determines them as standard test trajectories. The length constraint ensures the representativeness and evaluation efficiency of the test trajectories, providing a stable and reliable evaluation benchmark for subsequent online analysis of servo performance and parameter optimization.

[0040] Secondly, embodiments of this application provide a self-tuning device for servo parameters of an engraving machine, the device comprising:

[0041] The test trajectory determination unit is used to acquire trajectory segments of the current processing condition and extract fixed trajectory units from the trajectory segments as standard test trajectories.

[0042] A contour error determination unit is used to determine a contour error that matches the standard test trajectory and is used to characterize the machining accuracy.

[0043] A vibration index determination unit is used to determine vibration indices that match the standard test trajectory and characterize the smoothness of the machining process.

[0044] The target parameter determination unit is used to determine a target servo parameter combination that is adapted to the current processing condition based on the fitness function constructed from the contour error and the vibration index, so that the servo controller of the engraving machine can perform engraving processing according to the target servo parameter combination.

[0045] Thirdly, embodiments of this application provide a computer device, including:

[0046] The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes these computer instructions to perform the vehicle drift control method described above.

[0047] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions, which are used to cause a computer to execute the vehicle drift control method described above. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0049] Figure 1 A flowchart illustrating a method for self-tuning servo parameters of an engraving machine, provided as an embodiment of this application;

[0050] Figure 2 A flowchart of step S31 provided in an embodiment of this application;

[0051] Figure 3 A flowchart of step S51 provided in an embodiment of this application;

[0052] Figure 4 A flowchart of step S711 provided in an embodiment of this application;

[0053] Figure 5 A flowchart of step S731 provided in an embodiment of this application;

[0054] Figure 6 A flowchart of step S11 provided in an embodiment of this application;

[0055] Figure 7 This application provides a self-tuning device for servo parameters of an engraving machine.

[0056] Figure 8 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0058] CNC engraving machines are widely used in precision machining in industries such as mold making, advertising, and handicrafts. Their machining quality highly depends on the control performance of the X, Y, and Z feed axis servo systems. As a core power component, the PI parameter tuning of the permanent magnet synchronous servo system is crucial. Currently, servo parameters are usually manually tuned and fixed by technicians before shipment based on typical working conditions (such as carving medium-hardness wood). However, actual machining conditions are complex and varied: in terms of materials, from cork and plastic to hard aluminum and metals, the cutting load and characteristics of different materials differ significantly; in terms of patterns, simple contours and complex 3D reliefs have different requirements for the dynamic response of the servo system, especially at high-speed corners, where excessive gain can easily cause overshoot and vibration, while insufficient gain will increase contour errors; in terms of machining stages, roughing prioritizes efficiency and can tolerate some vibration, while finishing pursues high surface finish and contour accuracy. Fixed PI parameters are difficult to achieve the best balance under all working conditions, easily leading to contour distortion, surface ripples, and even step loss, seriously affecting machining quality. Traditional solutions rely on technicians manually adjusting repeatedly, consuming a lot of manpower and time.

[0059] In conclusion, how to enable the engraving machine to automatically adjust itself based on real-time working conditions during actual processing has become a technical problem that needs to be solved.

[0060] To address the aforementioned technical problems, according to an embodiment of this application, a method for self-tuning servo parameters of an engraving machine is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0061] This embodiment provides a method for self-tuning servo parameters of an engraving machine. Figure 1 A flowchart illustrating a self-tuning method for servo parameters of an engraving machine provided in this application embodiment is shown below. Figure 1 As shown, the process includes the following steps:

[0062] Step S1: Obtain the trajectory segment of the current processing condition, and extract the fixed trajectory unit from the trajectory segment as the standard test trajectory.

[0063] Specifically, by processing continuous trajectory segments in real time using a CNC engraving machine, a fixed trajectory unit (e.g., a 5mm short trajectory) is extracted from these segments as a standard test trajectory. This process can be achieved by parsing pre-stored G-code through the CNC system of the engraving machine, combined with the real-time operating parameters of the engraving machine. The processing conditions involve different materials, and this method provides a basic scenario for online self-tuning of the servo system, eliminating reliance on fixed parameters and manual adjustments.

[0064] Step S3: Determine the contour error that matches the standard test trajectory to characterize the machining accuracy.

[0065] Specifically, the actual motion trajectory of the servo axis is precisely acquired during the execution of a standard test trajectory. By comparing and analyzing this trajectory with the standard test trajectory, the contour error, a quantitative indicator reflecting machining accuracy, is calculated. This reflects the maximum distance the actual machining trajectory deviates from the theoretical trajectory, thus transforming the quality objective of machining accuracy into a quantitative target that can be directly processed by optimization algorithms, providing a crucial evaluation basis for the iterative optimization of servo parameters.

[0066] Step S5: Determine the vibration index that matches the standard test trajectory to characterize the smoothness of the process.

[0067] Specifically, by determining a vibration evaluation index that matches the standard test trajectory and is used to quantitatively characterize the stability of the engraving process, it can reflect instability phenomena such as chatter and overshoot caused by poor servo parameter matching during trajectory tracking in real time. This transforms the quality objective of processing stability into a quantitative objective that can be directly processed by the optimization algorithm, providing a key evaluation basis for the iterative optimization of servo parameters.

[0068] Step S7: Based on the fitness function constructed from the contour error and vibration index, determine the target servo parameter combination that is suitable for the current processing condition, so that the servo controller of the engraving machine can perform engraving processing according to the target servo parameter combination.

[0069] Specifically, online self-tuning of servo parameters is achieved through a particle swarm optimization algorithm. The fitness function, constructed from contour error and vibration indicators, serves as the optimization objective. Servo controller parameters (such as the gain coefficients of the position and velocity loops) are used as the particle position coordinates, and real-time search and iteration are performed during the actual operation of the engraving machine. Through this online optimization process, a target servo parameter combination adapted to the current processing material and motion characteristics can be obtained. This allows the engraving machine servo controller to execute processing tasks based on the optimized parameters, achieving a comprehensive improvement in both accuracy and stability.

[0070] This embodiment provides a self-tuning method for servo parameters of an engraving machine. It constructs a multi-objective fitness function using contour accuracy and machining vibration indices, and employs a particle swarm optimization algorithm to determine the optimal servo parameter combination that matches the current machining conditions. This enables the engraving machine to achieve high-precision and highly stable engraving processing based on this parameter combination. This embodiment constitutes a closed-loop intelligent control system capable of real-time sensing of the machining status and online self-tuning of servo parameters accordingly. It achieves fully autonomous decision-making throughout the entire process, from status sensing and performance evaluation to parameter self-optimization, thereby solving the technical problem of how to self-adjust based on real-time working conditions during actual engraving machine processing.

[0071] Figure 2 The flowchart for step S3 provided in the embodiments of this application may include the following steps:

[0072] Step S31: Sample the standard test trajectory to obtain multiple sampling points.

[0073] Specifically, a series of sampling points with temporal relationships are obtained by discretizing the standard test trajectory. The sampling interval during the sampling process is not a fixed value, but a dynamic value adapted to the current processing conditions. For example, a smaller sampling interval (such as 125us) is used for finishing / high-speed corner / hard material processing to increase the sampling density and capture micron-level positional deviations (the precision requirement for finishing of engraving machines is usually at the μm level); a larger sampling interval (such as 250us) is used for roughing / soft material processing to reduce the amount of data acquisition and subsequent calculations while ensuring the accuracy of error analysis, thus saving the computing power of the servo controller.

[0074] Step S33: For any sampling point, obtain the actual position and theoretical position of each linkage axis in the servo controller.

[0075] Specifically, the theoretical position refers to the positional command data for each linkage axis issued by the CNC system to the servo controller. It represents the ideal spatial position that each axis should reach at that sampling point and serves as the benchmark value for error calculation. The actual position refers to the real motion position signal of each linkage axis collected by the servo controller through position feedback elements such as encoders / grating rulers. It represents the actual spatial position of each axis at that sampling point and serves as the measured value for error calculation. For each sampling point, the actual position of each linkage axis received by the servo controller and the theoretical command position data issued by the CNC system for that sampling point are collected simultaneously to construct comparative information for subsequent precise analysis.

[0076] Step S35: Determine the position error corresponding to any sampling point based on the actual position and the theoretical position.

[0077] Specifically, by establishing the correspondence between actual and theoretical positions, the real-time position deviation of each sampling point is calculated, thereby achieving precise quantification of the trajectory tracking error for each sampling point. The position error PosErr of a single sampling point. a =Actual position - Theoretical position.

[0078] Step S37: Based on the position error and the number of sampling points, determine the contour error that matches the standard test trajectory to characterize the machining accuracy.

[0079] Specifically, the contour error expression is as follows:

[0080]

[0081] Among them, PosErr a Let a be the position error of the a-th sampling point. The number of sampling points. This is the standard test trajectory for the i-th segment.

[0082] This embodiment calculates the contour error, using it as a key quantitative indicator for evaluating and optimizing the dynamic performance of the servo system. Specifically, based on the position error data obtained from each sampling point, the contour error value, characterizing the overall trajectory following accuracy, is obtained by combining the position error with the number of sampling points. This method achieves a multi-dimensional and continuous evaluation of machining accuracy, providing a direct and reliable optimization target and basis for subsequent adaptive adjustment of parameters.

[0083] Figure 3 The flowchart for step S5 provided in the embodiments of this application may include the following steps:

[0084] Step S51: Sample the standard test trajectory to obtain multiple sampling points.

[0085] Specifically, a series of sampling points with temporal relationships are obtained by discretizing the standard test trajectory.

[0086] Step S53: Obtain the actual speed sequence of each linkage axis in the servo controller at multiple sampling points.

[0087] Specifically, for each sampling point, the actual operating speeds of all linked axes within the servo controller are synchronously acquired, and a sequence of actual speeds for each axis is constructed in chronological order. This provides continuous, synchronous, and trajectory-bound time-domain speed data for subsequent frequency domain analysis. For example, by acquiring speeds using 1024 evenly distributed sampling points, the actual speed sequence of the linked axes at the corresponding sampling time is obtained. This sequence fully records the dynamic speed response of each axis during the execution of the standard test trajectory, providing a speed data foundation for subsequent performance analysis, identification of dynamic characteristics, and evaluation of control effectiveness.

[0088] Step S55: Perform a fast Fourier transform on the obtained actual velocity sequence to obtain the energy amplitude corresponding to multiple sampling points.

[0089] Specifically, by performing a Fourier transform on the actual speed sequence of the linkage shaft, it is converted from the time domain to the frequency domain, generating a corresponding spectrum. Based on this spectrum, the energy distribution of the frequency domain signal at each frequency component (i.e., the frequency domain energy spectrum) can be analyzed and determined, thereby achieving a quantitative characterization of the dynamic characteristics of different frequencies in the speed response of the engraving machine.

[0090] Step S57: The energy amplitudes exceeding the preset high-frequency threshold are summarized, and the sum of the summarized energy amplitudes is determined as a vibration index that matches the standard test trajectory and is used to characterize the smoothness of the process.

[0091] Specifically, based on the obtained frequency domain energy spectrum, the energy amplitudes corresponding to all frequency components exceeding a preset high-frequency threshold are summed, and this cumulative value is determined as a vibration quantification index that matches the standard test trajectory. This index, by quantifying high-frequency oscillation energy, directly reflects the vibration level of the engraving machine during operation, thereby effectively characterizing the stability and surface quality of actual processing.

[0092] This embodiment establishes a vibration index as a quantitative evaluation parameter for the actual operating data of the servo system. The vibration index is obtained by performing frequency domain analysis on the velocity response of the linkage shaft under a standard test trajectory, extracting and accumulating the energy exceeding a preset high-frequency threshold; it directly characterizes the intensity of high-frequency oscillations generated by the mechanical system during dynamic operation, effectively reflecting the stability, anti-interference ability, and potential surface finish of the processing.

[0093] Figure 4 The present application provides a flowchart for constructing the fitness function, which may include the following steps:

[0094] Step S711: Configure the first weight of the contour error.

[0095] Step S713: Configure the second weight of the vibration index.

[0096] Step S715: Construct a fitness function based on contour error, vibration index, first weight, and second weight.

[0097] Specifically, the expression for the fitness function is:

[0098]

[0099] in, As the first weight, As the second weight, For contour error, This is a vibration index.

[0100] This embodiment integrates contour error and vibration index into a unified quantification system by constructing a fitness function. Through a weighted method, the contour error, reflecting machining accuracy, and the vibration index, characterizing the smoothness of machining operation, are synthesized into a single scalar value. The value of the fitness function directly reflects the comprehensive control performance of the current engraving machine under specific parameters: a larger value indicates better performance in tracking accuracy and vibration suppression, and a more ideal machining state; conversely, a smaller value indicates that the current parameters need adjustment. This design provides a clear and calculable performance evaluation target for subsequent particle swarm optimization algorithms and is the core basis for achieving online parameter self-tuning.

[0101] Figure 5 The flowchart for step S7 provided in the embodiments of this application may include the following steps:

[0102] Step S731: Generate multiple particles within a predetermined range of servo parameters to characterize the combination of servo parameters.

[0103] Specifically, the servo parameters include at least the position loop proportional coefficient, position loop integral coefficient, velocity loop proportional coefficient, velocity loop integral coefficient, and velocity feedforward coefficient. Based on the pre-defined range of servo control parameter values, a multi-dimensional parameter space is constructed. This is then used to generate an initial population of multiple particles, where each particle is a multi-dimensional vector, with each dimension corresponding to a specific servo parameter (such as the position loop proportional coefficient, position loop integral coefficient, velocity loop proportional coefficient, velocity loop integral coefficient, and velocity feedforward coefficient). During the iterative update of the particle swarm, a mutation operation is performed on a specified or probabilistically selected type of particle. The specific method of this mutation operation is as follows: First, two different particles are selected from the current particle swarm; second, the direction vectors of these two particles are weighted and combined to generate an intermediate particle; finally, a random perturbation vector generated by a pre-defined distribution (such as a Gaussian or uniform distribution) is added to this intermediate particle, thereby generating a new particle with mutation characteristics, which replaces or partially replaces the original update method of the particle. The significance of this mutation operation lies in introducing new exploration directions into the population, enhancing the particle swarm's ability to escape local optima, and thus coordinating with the standard update mechanism of the particle swarm optimization algorithm to ultimately achieve a more efficient and robust acquisition of the target servo parameter combination under the current processing conditions.

[0104] Step S733: Based on the fitness function, determine the fitness value of each particle during the carving process along the standard test trajectory, and iteratively update to obtain new particles until the preset conditions are met, thereby obtaining the target servo parameter combination corresponding to the current processing condition.

[0105] Specifically, parameter optimization is not performed in a simulation environment, but rather by directly driving the machine tool to cut along the current standard test trajectory. During this process, motion data for each axis is collected in real time, and the fitness value corresponding to that set of parameters is calculated accordingly. This allows for direct evaluation of performance under actual machining conditions. A higher fitness function value indicates better performance in both trajectory tracking accuracy and vibration suppression, resulting in a more ideal machining state and clearly indicating the effective direction of parameter optimization. The core of the driving parameter iterative update is the exploration mechanism of the particle swarm optimization algorithm, whose position and velocity updates are described by the following PSO mathematical model:

[0106]

[0107]

[0108] Among them, V i =The velocity vector of the particle moving in the parameter space, V i—1 =The velocity vector of the particle in the previous round of movement in the parameter space, This represents the optimal position for all particles globally. The optimal position for each particle. It is the current particle position. It is the particle's next position. and It is the convergence constant. It is a random number generator. It is a constant. In each iteration, the fitness value of each particle's current position is first evaluated and compared with its own historical best value, thereby updating the optimal position of each particle. Subsequently, the algorithm after all updates A global comparison is performed, and the position with the best fitness is established as the new global optimal position for the particle. By driving and The continuous updating guides the entire particle swarm to converge towards a better region in the parameter space. The next parameter update is calculated, and the process is iterated repeatedly. The iteration terminates when the iteration results meet preset convergence conditions (e.g., the fitness value meets a preset value, or the maximum number of iterations is reached).

[0109] This embodiment iteratively optimizes each particle in the particle swarm optimization algorithm based on a constructed fitness function. Specifically, each particle represents a specific set of servo controller parameters. By substituting each set of parameters into the servo controller, each axis is driven to execute a standard test trajectory, and running data is collected synchronously. Based on this data, contour error and vibration index are calculated, and then the fitness value corresponding to the particle is obtained through the fitness function. During the iterative optimization process, the algorithm dynamically updates the position (i.e., parameter combination) and velocity of each particle based on the swarm's historical best and the individual's historical best information. This process is repeated cyclically, continuously generating and evaluating new parameter particles. The iteration terminates when the iteration result meets the preset convergence conditions (e.g., the fitness value meets the preset value, the maximum number of iterations is reached). At this point, the parameter combination represented by the globally optimal particle is determined as the target servo parameter combination that can optimally balance machining accuracy and operational stability and adapt to the current machining conditions. This method realizes directional search and automatic optimization from parameter space to performance index.

[0110] In one alternative embodiment, the servo parameter combination includes one or more combinations of position loop proportional coefficient, position loop integral coefficient, velocity loop proportional coefficient, velocity loop integral coefficient, and velocity feedforward coefficient.

[0111] This embodiment achieves a significant improvement in system performance by combining and optimizing one or more parameters from the position loop proportional coefficient, position loop integral coefficient, velocity loop proportional coefficient, velocity loop integral coefficient, and velocity feedforward coefficient. The position loop parameters (mainly the position loop proportional coefficient Kp_pos and the position loop integral coefficient Ki_pos) dominate the accuracy of trajectory tracking and the dynamic response characteristics of the system: increasing Kp_pos improves response speed and tracking tightness; while Ki_pos is theoretically used to eliminate steady-state position error. The velocity loop parameters (mainly the velocity loop proportional coefficient Kp_speed and the velocity loop integral coefficient Ki_speed) determine the smoothness and disturbance rejection capability of the motion process: Kp_speed enhances system rigidity and velocity response, but excessively high Kp_speed can easily lead to oscillations; Ki_speed is used to eliminate steady-state velocity error, ensuring the accuracy of velocity control. Furthermore, the velocity feedforward coefficient VFF, through look-ahead compensation, can effectively reduce tracking lag, further improving dynamic performance.

[0112] Figure 6 The flowchart for step S1 provided in the embodiments of this application may include the following steps:

[0113] Step S11: Extract fixed trajectory units that meet the length threshold from the trajectory segment according to the preset length threshold.

[0114] Step S13: Determine the fixed trajectory unit as the standard test trajectory.

[0115] This embodiment extracts fixed trajectory units that meet the requirements from actual trajectory segments by using a preset length threshold, and determines them as standard test trajectories. The length constraint ensures the representativeness and evaluation efficiency of the test trajectories, providing a stable and reliable evaluation benchmark for subsequent online analysis of servo performance and parameter optimization.

[0116] The specific implementation of the present invention will now be described in conjunction with an example device. Taking a three-axis CNC engraving machine as an example, its servo parameters can be obtained in the following way:

[0117] Step 1001: When the CNC system of the engraving machine parses the finishing instruction (such as a specific comment in the G code or the high-precision mode M code), it acquires a trajectory segment of the hard aluminum finishing condition and, based on a preset length threshold, filters and extracts a fixed trajectory unit (e.g., a 5mm short trajectory, taking approximately 200ms) that meets the requirements for straight-line machining from the segment. This fixed trajectory unit is then established as the standard test trajectory.

[0118] Step 1002: When entering the finishing stage, to meet higher precision requirements, the test trajectory is continuously sampled at a high frequency (e.g., every 125 microseconds) to obtain 1600 sampling points. For each sampling point, the actual position coordinates fed back by the linkage axis are synchronously read and compared in real time with the theoretical command position issued by the CNC interpolator. By calculating the difference between the two, the position error at each sampling point is obtained. Finally, based on the position error sequence of all sampling points, the contour error value, which quantifies the trajectory following accuracy, is calculated according to the contour error calculation formula. This value directly reflects the trajectory reproduction accuracy and contour tracking capability of the theoretical path when executing this type of trajectory. The lower the contour error value, the higher the consistency between the actual machining trajectory and the theoretical trajectory, and the better the obtained contour accuracy.

[0119] Step 1003: The real-time operating speed of the linkage axis servo drive is synchronously acquired using the same high-frequency rhythm as the position sampling (e.g., every 125 microseconds) to obtain 1600 sampling points. The speed data obtained through time-series acquisition forms a continuous, high-precision time-domain speed dataset strictly bound to the test trajectory. Subsequently, a Fast Fourier Transform is performed on the speed sequence of the linkage axis to transform it from the time domain to the frequency domain, thereby obtaining the energy amplitude distribution spectrum of the linkage axis speed fluctuation at different frequency components. By setting a threshold, all energy amplitudes exceeding a preset high-frequency threshold are filtered out. These high-frequency energy amplitudes from each axis are accumulated; this quantified "sum" is determined as a vibration index that matches the current standard test trajectory and characterizes the smoothness of processing. This index directly reflects the total high-frequency vibration energy excited by the overall mechanical structure and drive components when executing such a trajectory. The lower the high-frequency energy, the smoother the operation and the lower the potential risk of vibration or resonance.

[0120] Step 1004: Based on the real-time acquired contour accuracy and vibration stability indices, the optimization process is triggered. To guide the direction of finishing optimization, the following fitness function is constructed:

[0121] F = 0.7 / (1 + contour error) + 0.3 / (1 + vibration index), by setting the weights of 0.7 and 0.3 to prioritize contour accuracy.

[0122] Particle swarm optimization is initiated, with its core parameters initially set as follows: number of particles N=15, maximum number of iterations K=8 (both can be dynamically adjusted according to actual working conditions). The optimization target is the key gain parameters in the servo controller, including the position loop proportional gain coefficient Kp_pos, position loop integral gain coefficient Ki_pos, velocity loop proportional gain coefficient Kp_speed, velocity loop integral gain coefficient Ki_speed, and velocity feedforward coefficient VFF. Each particle represents a set of gain parameters. A 5mm trajectory (approximately 200ms) is continuously executed along the current actual machining path by driving the machine tool, serving as a dynamic performance test for this set of parameters. During this micro-segment machining process, trajectory data is collected in real time, and the corresponding contour error and high-frequency vibration energy of the particle are calculated. These values ​​are then substituted into the fitness function F to obtain the fitness value. Based on the calculated fitness value, the parameters are updated... (Each particle's optimal position) and updating the particle swarm by comparing the fitness values ​​of all particles in the current iteration. (Global optimal particle position). Then, the velocity vector of the particle in the parameter space is calculated according to the PSO mathematical model formula, and the parameter combination for each particle in the next step is calculated based on the velocity vector. Simultaneously, the top M (even number) optimal particles are selected from the current particle swarm and paired into M / 2 pairs. Next, the direction vectors of these two particles are weighted and combined to generate an intermediate particle. Finally, a random perturbation vector generated by a preset distribution (such as a Gaussian or uniform distribution) is added to this intermediate particle, thereby generating a new particle with mutation characteristics, which replaces or partially replaces the worst M / 2 particles.

[0123] Repeat the above process until the preset number of iterations is reached (or the fitness value meets the preset value). For example, after 8 iterations, output the optimal gain combination that maximizes fitness:

[0124] [Kp*_pos, Ki*_pos, Kp*_speed, Ki*_speed, VFF*].

[0125] This set of parameters is the engraving machine servo parameter obtained through autonomous optimization for the current hard aluminum precision machining conditions. It can significantly improve contour tracking accuracy while simultaneously suppressing motion, and achieve adaptive optimization of the machining process.

[0126] Accordingly, please refer to Figure 7 A block diagram of a self-tuning device for servo parameters of an engraving machine provided in this application embodiment, the device comprising:

[0127] The test trajectory determination unit 101 is used to acquire trajectory segments of the current processing condition and extract fixed trajectory units from the trajectory segments as standard test trajectories.

[0128] The contour error determination unit 103 is used to determine the contour error that matches the standard test trajectory and is used to characterize the machining accuracy.

[0129] Vibration index determination unit 105 is used to determine vibration indexes that match the standard test trajectory and characterize the smoothness of the process.

[0130] The target parameter determination unit 107 is used to determine the target servo parameter combination that is suitable for the current processing condition based on the fitness function constructed based on the contour error and vibration index, so that the servo controller of the engraving machine can perform engraving processing according to the target servo parameter combination.

[0131] In some optional implementations, the contour error determination unit 103 is as follows:

[0132] The standard test trajectory is sampled to obtain multiple sampling points.

[0133] For any given sampling point, obtain the actual and theoretical positions of each linkage axis within the servo controller.

[0134] Determine the position error corresponding to any sampling point based on the actual and theoretical positions.

[0135] Based on the positional error and the number of sampling points, a contour error is determined that matches the standard test trajectory to characterize the machining accuracy.

[0136] Perform a Fast Fourier Transform on the obtained actual velocity sequence to obtain the energy amplitude corresponding to multiple sampling points.

[0137] In some alternative implementations, the vibration index determination unit 105 is as follows:

[0138] The standard test trajectory is sampled to obtain multiple sampling points.

[0139] Obtain the actual speed sequence of each linkage axis in the servo controller at multiple sampling points.

[0140] The energy amplitudes exceeding the preset high-frequency threshold are aggregated, and the sum of the aggregated energy amplitudes is determined as a vibration index that matches the standard test trajectory and is used to characterize the smoothness of the process.

[0141] In some optional implementations, the target parameter determination unit 107 is as follows:

[0142] Configure the first weight of the contour error.

[0143] Configure the second weight of the vibration index.

[0144] A fitness function is constructed based on contour error, vibration index, first weight, and second weight.

[0145] In some optional implementations, the target parameter determination unit 107 is as follows:

[0146] Multiple particles are generated within a predetermined range of servo parameters to characterize the combination of servo parameters.

[0147] Based on the fitness function, the fitness value of each particle is determined during the carving process along the standard test trajectory, and new particles are obtained through iterative updates until the preset conditions are met, thus obtaining the target servo parameter combination corresponding to the current processing condition.

[0148] In some optional implementations, the target parameter determination unit 107 is as follows:

[0149] The servo parameter combination includes one or more combinations of position loop proportional coefficient, position loop integral coefficient, velocity loop proportional coefficient, velocity loop integral coefficient, and velocity feedforward coefficient.

[0150] In some optional implementations, the test trajectory determination unit 101 is as follows:

[0151] Based on a pre-set length threshold, fixed trajectory units that meet the length threshold are extracted from the trajectory segment.

[0152] The fixed trajectory unit is defined as the standard test trajectory.

[0153] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0154] In this embodiment, a vehicle drift control device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.

[0155] Please see Figure 8 , Figure 8 This application provides a schematic diagram of the structure of a computer device, as shown in the embodiment of the present application. Figure 8As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 Take a processor 10 as an example.

[0156] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0157] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0158] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0159] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0160] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0161] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0162] The apparatus and units described in the above embodiments can be implemented by a computer chip or physical entity, or by a product with a certain function. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0163] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0164] Those skilled in the art will understand that the embodiments of this application can be provided as methods or apparatus. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0165] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, and devices according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0166] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0167] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0168] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0169] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0170] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

[0171] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for self-tuning servo parameters of a carving machine, characterized in that, The method includes: Obtain a trajectory segment of the current processing condition, and extract a fixed trajectory unit from the trajectory segment as a standard test trajectory; The standard test trajectory is sampled to obtain multiple sampling points; For any given sampling point, obtain the actual and theoretical positions of each linkage axis within the servo controller; Based on the actual location and the theoretical location, determine the position error corresponding to any sampling point; Based on the position error and the number of sampling points, a contour error that matches the standard test trajectory and is used to characterize the machining accuracy is determined. The standard test trajectory is sampled to obtain multiple sampling points; Obtain the actual speed sequence of each linkage axis within the servo controller at multiple sampling points; Perform a Fast Fourier Transform on the acquired actual velocity sequence to obtain the energy amplitude corresponding to the multiple sampling points; The energy amplitudes exceeding the preset high-frequency threshold are summarized, and the sum of the summarized energy amplitudes is determined as a vibration index that matches the standard test trajectory and is used to characterize the processing stability. Multiple particles are generated within a predetermined range of servo parameters to characterize the combination of servo parameters. Each particle represents a set of servo loop parameter combinations, which include one or more combinations of position loop proportional coefficient, position loop integral coefficient, velocity loop proportional coefficient, velocity loop integral coefficient, and velocity feedforward coefficient. Based on the fitness function constructed from the contour error and the vibration index, a target servo parameter combination suitable for the current processing condition is determined through particle swarm optimization, so that the servo controller of the engraving machine can perform engraving processing according to the target servo parameter combination. The fitness function is: F=ω1 / (1+ψ)+ω2 / (1+ζ), where ω1 is the first weight, ω2 is the second weight, ψ is the contour error, and ζ is the vibration index.

2. The method according to claim 1, characterized in that, The fitness function is constructed as follows: Configure the first weight of the contour error; Configure a second weight for the vibration index; A fitness function is constructed based on the contour error, the vibration index, the first weight, and the second weight.

3. The method according to claim 1, characterized in that, The determination of the target servo parameter combination adapted to the current processing condition includes: Multiple particles are generated within a predetermined range of servo parameters to characterize combinations of servo parameters. Based on the fitness function, the fitness value of each particle is determined during the carving process along the standard test trajectory, and new particles are obtained through iterative updates until the preset conditions are met, thus obtaining the target servo parameter combination corresponding to the current processing condition.

4. The method according to claim 1, characterized in that, The step of extracting fixed trajectory units from the trajectory segment as a standard test trajectory includes: Based on a pre-set length threshold, fixed trajectory units that satisfy the length threshold are extracted from the trajectory segment; The fixed trajectory unit is defined as the standard test trajectory.

5. A self-tuning device for servo parameters of an engraving machine, the device comprising: The test trajectory determination unit is used to acquire trajectory segments of the current processing condition and extract fixed trajectory units from the trajectory segments as standard test trajectories. A contour error determination unit is used to sample the standard test trajectory to obtain multiple sampling points; For any given sampling point, obtain the actual and theoretical positions of each linkage axis within the servo controller; Based on the actual position and the theoretical position, determine the position error corresponding to any sampling point; based on the position error and the number of sampling points, determine the contour error that matches the standard test trajectory to characterize the machining accuracy; The vibration index determination unit is used to sample the standard test trajectory to obtain multiple sampling points; Obtain the actual speed sequence of each linkage axis within the servo controller at multiple sampling points; Perform a Fast Fourier Transform on the acquired actual velocity sequence to obtain the energy amplitude corresponding to the multiple sampling points; The energy amplitudes exceeding the preset high-frequency threshold are summarized, and the sum of the summarized energy amplitudes is determined as a vibration index that matches the standard test trajectory and is used to characterize the processing stability. The target parameter determination unit is used to generate multiple particles representing servo parameter combinations within a predetermined servo parameter range. Each particle represents a set of servo loop parameter combinations, which include one or more combinations of position loop proportional coefficient, position loop integral coefficient, velocity loop proportional coefficient, velocity loop integral coefficient, and velocity feedforward coefficient. Based on the fitness function constructed from the contour error and the vibration index, the unit determines the target servo parameter combination suitable for the current processing condition through particle swarm optimization, so that the servo controller of the engraving machine can perform engraving processing according to the target servo parameter combination. The fitness function is: F=ω1 / (1+ψ)+ω2 / (1+ζ), where ω1 is the first weight, ω2 is the second weight, ψ is the contour error, and ζ is the vibration index.

6. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the computer instructions to perform the self-tuning method for the engraving machine servo parameters according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the self-tuning method for the engraving machine servo parameters according to any one of claims 1 to 4.

Images