A numerical control machine tool self-adaptive parameter adjusting system based on processing state sensing

Abstract

The application provides a numerical control machine tool adaptive parameter adjustment system based on processing state perception, relates to the technical field of adaptive parameter adjustment, collects processing data signals of a spindle motor of a target numerical control machine tool, extracts processing states based on the processing data signals to obtain a processing state vector; state representation fusion is performed through the processing state vector to obtain a processing stability index; prospective decision is made according to the processing information and the processing stability index to generate a parameter adjustment instruction set; the parameter adjustment instruction set and original path planning instructions are coupled smoothly to generate a motion control instruction set, and the spindle motor of the target numerical control machine tool is adjusted in parameters according to the motion control instruction set. The application can perceive the processing state in real time and predict stability changes, realize prospective adaptive adjustment of processing parameters, and improve the processing precision and the intelligent level of the numerical control machine tool.

Description

Technical Field

[0001] This application relates to the field of adaptive parameter adjustment technology, and more specifically, to an adaptive parameter adjustment system for CNC machine tools based on machining state perception. Background Technology

[0002] Currently, with the continuous development of CNC machining technology, CNC machine tools have been widely used in the efficient and high-precision machining of complex parts. Existing technologies typically control the spindle motor by pre-setting machining parameters and combining them with path planning instructions to complete predetermined machining tasks. Meanwhile, to adapt to different working conditions and machining objects, some CNC machine tools have introduced machining status monitoring methods. By collecting machining data signals such as spindle motor current, speed, and vibration, the machining process is analyzed, and machining parameters are adjusted to a certain extent based on the analysis results, thereby achieving stable operation of the machining process and ensuring machining quality.

[0003] In existing CNC machining technologies, CNC machine tools typically control machining based on preset machining parameters and predetermined path planning instructions. Although some systems possess machining status monitoring and parameter adjustment capabilities, they often focus on judging the status at a single moment or with a single characteristic, lacking a comprehensive characterization of the instantaneous state, changing trends, and frequency domain characteristics of the machining process. Furthermore, parameter adjustments in existing technologies are mostly passive or delayed responses, making it difficult to proactively predict potentially unstable working conditions. The coordination between parameter adjustments and the original machining path is also limited, easily introducing machining fluctuations. These technological limitations result in insufficiently comprehensive machining stability assessments and uneven parameter adjustments, making it difficult to achieve high-stability and high-quality machining control under complex working conditions. Therefore, how to perceive the machining status in real time and predict stability changes, achieve proactive adaptive adjustment of machining parameters, and improve machining accuracy and the intelligence level of CNC machine tools is a challenge facing the industry. Summary of the Invention

[0004] This application provides an adaptive parameter adjustment system for CNC machine tools based on machining status perception. It can perceive the machining status in real time and predict stability changes, realize the forward-looking adaptive adjustment of machining parameters, and improve machining accuracy and the intelligence level of CNC machine tools.

[0005] This application provides an adaptive parameter adjustment system for CNC machine tools based on machining state perception, the adaptive parameter adjustment system comprising:

[0006] The signal acquisition module is used to acquire the machining data signal of the spindle motor of the target CNC machine tool, and extract the machining state based on the machining data signal to obtain the machining state vector of the spindle motor of the target CNC machine tool.

[0007] The characterization fusion module is used to perform state characterization fusion on the instantaneous machining state and stability trend of the target CNC machine tool spindle motor through the machining state vector, so as to obtain the machining stability index of the target CNC machine tool spindle motor.

[0008] The instruction generation module is used to obtain the machining information of the current task of the target CNC machine tool, make forward-looking decisions based on the machining information and the machining stability index, and generate a set of parameter adjustment instructions to adjust the subsequent machining path.

[0009] The parameter adjustment module is used to smoothly couple the parameter adjustment instruction set with the original path planning instruction of the target CNC machine tool to generate a motion control instruction set for the spindle motor of the target CNC machine tool, and to adjust the parameters of the spindle motor of the target CNC machine tool according to the motion control instruction set.

[0010] In this embodiment, the processing data signals include current signals, vibration signals, and acoustic emission signals.

[0011] In this embodiment, the machining state extraction based on the machining data signal to obtain the machining state vector of the target CNC machine tool spindle motor specifically includes:

[0012] The load dynamic feature set is determined by the current signal in the processing data signal;

[0013] The vibration stability feature set is determined based on the vibration signal in the processing data signal;

[0014] The transient characteristics of acoustic emission are determined based on the acoustic emission signals in the processing data signals;

[0015] The load dynamic feature set, the vibration stability feature set, and the acoustic emission transient feature are vectorized to obtain the machining state vector of the target CNC machine tool spindle motor.

[0016] In this embodiment, the machining information of the current task of the target CNC machine tool includes: the cutting depth and cutting width of each path segment.

[0017] In this embodiment, the machining stability index of the target CNC machine tool spindle motor is obtained by fusing the instantaneous machining state and stability trend of the target CNC machine tool spindle motor through the machining state vector, specifically including:

[0018] Based on the machining state vector, determine the instantaneous state vector, trend state vector, and frequency domain state vector of the target CNC machine tool spindle motor;

[0019] The instantaneous state vector, the trend state vector, and the frequency domain state vector are fused to obtain the machining stability index of the target CNC machine tool spindle motor.

[0020] In this embodiment, obtaining the machining stability index of the target CNC machine tool spindle motor specifically includes:

[0021] The instantaneous state vector, the trend state vector, and the frequency domain state vector are combined to form a state feature vector;

[0022] Construct a state transition matrix based on the state feature vectors;

[0023] Based on the state transition matrix, the state feature vector of the previous time step is predicted to obtain the predicted state vector;

[0024] Error extraction is performed using the state feature vector and the predicted state vector to obtain the predicted difference vector;

[0025] Based on the predicted difference vector and the predicted state vector, the state features are corrected to obtain the corrected state vector;

[0026] Numerical fusion is performed based on the corrected state vector to obtain the machining stability index of the target CNC machine tool spindle motor.

[0027] In this embodiment, the machining stability index is used to quantitatively characterize the overall stability level of the target CNC machine tool spindle motor under the current machining state.

[0028] In this embodiment, the process of making forward-looking decisions based on the processing information and the processing stability index to generate a set of parameter adjustment instructions for adjusting subsequent processing paths specifically includes:

[0029] The machining stability index is adjusted and mapped to obtain the reference speed adjustment amount;

[0030] The influence coefficient of each path is determined based on the processing information.

[0031] The corresponding forward speed adjustment is determined based on the reference speed adjustment and the influence coefficients of each path.

[0032] A set of parameter adjustment instructions for adjusting subsequent machining paths is generated by adjusting various forward rotation speeds.

[0033] In this embodiment, the smooth coupling of the parameter adjustment instruction set and the original path planning instruction of the target CNC machine tool to generate the motion control instruction set of the target CNC machine tool spindle motor specifically includes:

[0034] Align the parameter adjustment instruction set with the original path planning instruction to obtain each adjusted path segment;

[0035] The speed curve of the parameter adjustment instruction set is smoothed to obtain each real-time adjustable speed;

[0036] The motion control instruction set for the target CNC machine tool spindle motor is generated based on each adjustment path segment and the corresponding real-time adjustment speed.

[0037] In this embodiment, the motion control command set includes: each adjustment path segment and its corresponding real-time adjustment speed.

[0038] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0039] A signal acquisition module is used to acquire machining data signals from the spindle motor of the target CNC machine tool. Based on the machining data signals, machining state is extracted to obtain a machining state vector of the target CNC machine tool spindle motor. A characterization fusion module is used to perform state characterization fusion on the instantaneous machining state and stability trend of the target CNC machine tool spindle motor using the machining state vector to obtain a machining stability index of the target CNC machine tool spindle motor. An instruction generation module is used to acquire the machining information of the current task of the target CNC machine tool, and make forward-looking decisions based on the machining information and the machining stability index to generate a parameter adjustment instruction set for adjusting the subsequent machining path. A parameter adjustment module is used to smoothly couple the parameter adjustment instruction set with the original path planning instruction of the target CNC machine tool to generate a motion control instruction set for the target CNC machine tool spindle motor, and adjust the parameters of the target CNC machine tool spindle motor according to the motion control instruction set.

[0040] Therefore, this application demonstrates that, firstly, by acquiring and processing the machining data signals of the spindle motor of the target CNC machine tool in real time, it can accurately reflect the operating characteristics of the spindle motor during machining, transforming the machining data into a machining state vector, providing a data foundation for subsequent machining state characterization fusion and adaptive parameter adjustment; secondly, by extracting and fusing the machining state vector in multiple dimensions, it can quantify the instantaneous fluctuation characteristics and evolution trends of the spindle motor during machining, forming a machining stability index, improving the comprehensiveness, accuracy, and robustness of machining stability assessment, and providing a reliable decision-making basis for subsequent adaptive adjustment of machining parameters; furthermore... By utilizing the machining information and machining stability index of the current machining task, it is possible to perform forward-looking analysis and decision-making for subsequent machining processes, and generate a set of parameter adjustment instructions accordingly. This enables adaptive optimization of the machining path and machining parameters, improving machining quality and efficiency. Finally, by smoothly coupling the parameter adjustment instruction set with the original path planning instructions, it is possible to gradually adjust the machining parameters of the spindle motor without disrupting the continuity of the established machining trajectory and the stability of the system. This avoids vibrations caused by sudden changes in instructions, thereby ensuring the stability of CNC machine tool operation and improving the safety, stability, and machining accuracy of the machining process.

[0041] In summary, the technical solution adopted in this application can sense the processing status in real time and predict stability changes, realize the forward-looking adaptive adjustment of processing parameters, and improve the processing accuracy and the intelligence level of CNC machine tools. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a module structure diagram of the CNC machine tool adaptive parameter adjustment system based on machining state perception provided in this application;

[0044] Figure 2 This is an exemplary flowchart for obtaining the machining stability index of the spindle motor of a target CNC machine tool, provided in this application.

[0045] Figure 3 This is an exemplary flowchart of the parameter adjustment instruction set for generating and adjusting subsequent processing paths provided in this application. Detailed Implementation

[0046] 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, and 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.

[0047] This application provides an adaptive parameter adjustment system for CNC machine tools based on machining state perception. Its core is to acquire machining data signals from the spindle motor of the target CNC machine tool via a signal acquisition module, extract the machining state based on the machining data signals to obtain a machining state vector for the target CNC machine tool spindle motor, and then fuse the instantaneous machining state and stability trend of the target CNC machine tool spindle motor using the machining state vector to obtain a machining stability index for the target CNC machine tool spindle motor. An instruction generation module acquires the machining information of the current task of the target CNC machine tool, makes forward-looking decisions based on the machining information and the machining stability index, and generates a set of parameter adjustment instructions to adjust the subsequent machining path. A parameter adjustment module smoothly couples the parameter adjustment instruction set with the original path planning instructions of the target CNC machine tool to generate a motion control instruction set for the target CNC machine tool spindle motor, and adjusts the parameters of the target CNC machine tool spindle motor according to the motion control instruction set. This scheme can perceive the machining state in real time and predict stability changes, achieving forward-looking adaptive adjustment of machining parameters and improving machining accuracy and the intelligence level of the CNC machine tool.

[0048] To better understand the above technical solutions, a detailed description of the technical solutions will be provided below in conjunction with the accompanying drawings and specific embodiments. (Refer to...) Figure 1 As shown in the figure, this is a block diagram of a CNC machine tool adaptive parameter adjustment system based on machining state perception according to this embodiment of the present application. The adaptive parameter adjustment system includes: a signal acquisition module 100, a characterization fusion module 200, an instruction generation module 300, and a parameter adjustment module 400, which are described below:

[0049] The signal acquisition module 100 is used to acquire the machining data signal of the spindle motor of the target CNC machine tool, extract the machining state based on the machining data signal, and obtain the machining state vector of the spindle motor of the target CNC machine tool.

[0050] In practical implementation, firstly, the machining data signals of the target CNC machine tool spindle motor can be collected. That is, the current signal of the spindle motor can be collected through a current transformer, the vibration signal of the spindle bearing housing can be collected through an ICP-type accelerometer, and the acoustic emission signal on the spindle housing can be collected through a resonant acoustic emission sensor. Thus, the current signal, vibration signal, and acoustic emission signal are used as the machining data signals of the target CNC machine tool spindle motor. The machining data signals include the current signal, vibration signal, and acoustic emission signal.

[0051] In this embodiment, the machining state extraction based on the machining data signal to obtain the machining state vector of the target CNC machine tool spindle motor can be achieved through the following steps:

[0052] The load dynamic feature set is determined by the current signal in the processing data signal;

[0053] The vibration stability feature set is determined based on the vibration signal in the processing data signal;

[0054] The transient characteristics of acoustic emission are determined based on the acoustic emission signals in the processing data signals;

[0055] The load dynamic feature set, the vibration stability feature set, and the acoustic emission transient feature are vectorized to obtain the machining state vector of the target CNC machine tool spindle motor.

[0056] In practical implementation, the load dynamic characteristic set can be determined by analyzing the current signal in the processed data signal. Specifically, the Clark-Parker transform can be performed on the current signal to obtain the quadrature-axis current. A time window is set, and within this window, the mean and standard deviation of the current signal are calculated. The mean of the current signal is divided by the current value corresponding to the rated torque, and the result is used as the average load rate. The standard deviation of the current signal is then divided by the mean of the current signal, and the result is used as the load fluctuation coefficient. Thus, the average load rate and the load fluctuation coefficient are combined into a vector, which is then used as the load dynamic characteristic set. Next, the vibration stability characteristic set can be determined based on the vibration signal in the processed data signal. This can be achieved by synthesizing the vibration signals, i.e., calculating the sum of squares of the vibration signals, and then taking the square root of the result. This result is used as the overall vibration intensity. All overall vibration intensities within the time window are squared and summed, and the result is divided by the total number of data points, and then the square root of the result is taken. The obtained results are used as broadband vibration energy, and the fourth-order statistical moment of the overall vibration intensity is calculated. The obtained results are used as time-domain impact kurtosis, thus using broadband vibration energy and time-domain impact kurtosis as the vibration stability feature set. Furthermore, the acoustic emission transient characteristics can be determined based on the acoustic emission signals in the machining data signals. That is, the Hilbert transform of the acoustic emission signals can be performed to obtain the envelope signals. Within the time window, all envelope signals are squared and summed. The result is then divided by the number of all data points, and the square root of the result is used as the emission level, thus using the emission level as the acoustic emission transient characteristic. Finally, the load dynamic feature set, vibration stability feature set, and acoustic emission transient characteristics can be vector-encapsulated to obtain the machining state vector of the target CNC machine tool spindle motor. That is, the load dynamic feature set, vibration stability feature set, and acoustic emission transient characteristics can be vector-concatenated, and the resulting vector is used as the machining state vector of the target CNC machine tool spindle motor.

[0057] The characterization fusion module 200 is used to perform state characterization fusion on the instantaneous machining state and stability trend of the target CNC machine tool spindle motor through the machining state vector, so as to obtain the machining stability index of the target CNC machine tool spindle motor.

[0058] In this embodiment, the machining stability index of the target CNC machine tool spindle motor is obtained by fusing the instantaneous machining state and stability trend of the target CNC machine tool spindle motor through the machining state vector. This can be achieved through the following steps:

[0059] Based on the machining state vector, determine the instantaneous state vector, trend state vector, and frequency domain state vector of the target CNC machine tool spindle motor;

[0060] The instantaneous state vector, the trend state vector, and the frequency domain state vector are fused to obtain the machining stability index of the target CNC machine tool spindle motor.

[0061] In practical implementation, firstly, the instantaneous state vector, trend state vector, and frequency domain state vector of the target CNC machine tool spindle motor can be determined based on the machining state vector. That is, each feature in the machining state vector can be normalized, and the normalized vector is used as the instantaneous state vector of the target CNC machine tool spindle motor. A sliding window is set to obtain the machining state vectors at all time points within the window. The corresponding feature sequences in all machining state vectors are extracted, and linear regression is performed to calculate the first-order slope of each feature sequence to obtain the state trend of each feature. Then, the second-order acceleration of each feature sequence is calculated to obtain the trend acceleration of each feature. Thus, the state trend and trend acceleration of each feature are combined into a vector, and the obtained vector is used as the trend state vector. Then, a Hanning window is applied to each feature sequence before calculation. The FFT is used to calculate the power spectrum of the obtained results. The frequency corresponding to the maximum value of the power spectrum is then extracted as the main peak frequency. The natural frequency and bandwidth of the target CNC machine tool are obtained. The natural frequency plus the bandwidth is used as the chatter band. In the power spectrum, all frequency points within the chatter band are summed to obtain the chatter band energy. The sum of frequency points in the entire frequency range is then calculated to obtain the total energy. The chatter band energy is then divided by the total energy, and the result is used as the chatter energy ratio. The main peak frequency and the chatter energy ratio are combined into a vector, and the resulting vector is used as the frequency domain state vector. Then, the instantaneous state vector, trend state vector, and frequency domain state vector can be fused to obtain the machining stability index of the target CNC machine tool spindle motor, which can be obtained by the following steps.

[0062] Preferably, in this embodiment, reference Figure 2 As shown, this figure is an exemplary flowchart of obtaining the machining stability index of the target CNC machine tool spindle motor in an embodiment of this application. The specific steps for obtaining the machining stability index of the target CNC machine tool spindle motor in this embodiment are as follows:

[0063] In step S21, the instantaneous state vector, the trend state vector, and the frequency domain state vector are combined to form a state feature vector;

[0064] In step S22, a state transition matrix is ​​constructed based on the state feature vector;

[0065] In step S23, the state feature vector of the previous time step is predicted based on the state transition matrix to obtain the predicted state vector.

[0066] In step S24, error is extracted using the state feature vector and the predicted state vector to obtain the predicted difference vector;

[0067] In step S25, state feature correction is performed based on the predicted difference vector and the predicted state vector to obtain the corrected state vector;

[0068] In step S26, numerical fusion is performed based on the corrected state vector to obtain the machining stability index of the target CNC machine tool spindle motor.

[0069] In practical implementation, firstly, the instantaneous state vector, trend state vector, and frequency domain state vector can be combined to form a state feature vector. That is, the instantaneous state vector, trend state vector, and frequency domain state vector can be concatenated, and the resulting vector is used as the state feature vector. Then, a state transition matrix can be constructed based on the state feature vector. Specifically, the instantaneous feature transition matrix can be determined based on the trend-following state vector within the state feature vector. This is achieved by analyzing experimental data to obtain various instantaneous attenuation coefficients. It should be noted that the instantaneous attenuation coefficient refers to the value of the diagonal elements in the state transition matrix, representing the degree of attenuation of each state component to its value at the next time step. Finally, the coupling relationship between the various features is analyzed... Analysis, such as: (when the average load rate increases, the load fluctuation coefficient increases; when the load fluctuation coefficient increases, the broadband vibration energy increases; when the broadband vibration energy increases, the time-domain impact kurtosis increases; when the time-domain impact kurtosis increases, the emission level increases), uses the empirical coefficient method to determine each coupling strength, uses the attenuation coefficient as the diagonal element of the matrix, and uses each coupling strength as the coupling term, setting other terms to 0, thus obtaining the instantaneous feature transformation matrix. Then, based on the trend state vector in the state feature vector, the trend feature transformation matrix is ​​determined. That is, based on the characteristics of the trend feature, using a diagonal matrix, each trend attenuation rate can be obtained from the experimental data analysis. The trend attenuation coefficient of the trend feature transformation matrix can be obtained by the following formula:

[0070]

[0071] in, This represents the i-th trend decay coefficient in the trend feature transformation matrix; This represents the rate of decay of the i-th trend; The sampling interval is represented by the trend attenuation coefficients, which are then used as the diagonal elements of the matrix. The resulting matrix is ​​used as the trend feature transformation matrix. The frequency domain feature transformation matrix is ​​then determined based on the frequency domain state vector in the state feature vector. In other words, the frequency domain attenuation rate can be obtained from experimental data analysis. The frequency domain attenuation coefficients are calculated using the trend attenuation coefficient formula, and the frequency domain coupling coefficients are determined using the empirical coefficient method. The frequency domain attenuation coefficients are then used as the diagonal elements of the matrix, and the frequency domain coupling coefficients are used as the matrix coupling coefficients. The resulting matrix is ​​used as the frequency domain feature transformation matrix. Finally, the instantaneous feature transformation matrix, trend feature transformation matrix, and frequency domain feature transformation matrix are used as the diagonal elements of the matrix to construct a new matrix, which is then used as the state transformation matrix. For example:

[0072]

[0073] in, Represents the state transition matrix; Represents the instantaneous feature transformation matrix; Represents the trend feature transformation matrix; This represents the frequency domain feature transformation matrix.

[0074] Furthermore, in practical implementation, the state feature vector of the previous time step can be predicted based on the state transition matrix to obtain the predicted state vector. That is, the state feature vector of the previous time step is obtained, and multiplied by the state transition matrix, with the result used as the predicted state vector. Then, error extraction can be performed on the state feature vector and the predicted state vector to obtain the predicted difference vector. That is, the predicted state vector can be subtracted from the state feature vector, with the result used as the predicted difference vector. Further, state feature correction can be performed based on the predicted difference vector and the predicted state vector to obtain the corrected state vector. That is, the process noise matrix can be set based on expert experience, where the process noise matrix is ​​used to describe the uncertainty in the state evolution process of the dynamic system. Then, the covariance matrix of the predicted state vector is calculated to obtain the predicted covariance matrix. Thus, the corrected gain matrix can be obtained by the following formula:

[0075]

[0076] in, Represents the modified gain matrix; Represents the predicted covariance matrix; Let represent the process noise matrix, where the corrected gain matrix is ​​used to quantitatively weigh the predicted and observed values. The corrected state vector can then be obtained by the following formula:

[0077]

[0078] in, This represents the modified state vector; Represents the predicted state vector; Represents the modified gain matrix; This represents the predicted difference vector. Finally, numerical fusion can be performed based on the corrected state vector to obtain the machining stability index of the target CNC machine tool spindle motor. That is, each feature in the corrected state vector can be normalized, and then the weights of each feature can be set according to historical data. Each feature is multiplied by its corresponding weight, and then all the multiplication results are summed. The result is used as the machining stability index of the target CNC machine tool spindle motor. The machining stability index is used to quantitatively characterize the comprehensive stability level of the target CNC machine tool spindle motor under the current machining state.

[0079] It should be noted that by extracting and fusing the machining state vector in multiple dimensions, the instantaneous fluctuation characteristics and evolution trend of the spindle motor during machining can be quantified, and a machining stability index can be formed. This improves the comprehensiveness, accuracy and robustness of machining stability assessment, and provides a reliable decision-making basis for the adaptive adjustment of subsequent machining parameters.

[0080] The instruction generation module 300 is used to obtain the machining information of the current task of the target CNC machine tool, make forward-looking decisions based on the machining information and the machining stability index, and generate a set of parameter adjustment instructions to adjust the subsequent machining path.

[0081] In practical implementation, to obtain the machining information of the current task of the target CNC machine tool, the cutting depth and cutting width of each path segment of the current task of the target CNC machine tool can be obtained from the background system of the target CNC machine tool. The cutting depth and cutting width of each path segment of the current task are then used as the machining information of the current task of the target CNC machine tool. The machining information of the current task of the target CNC machine tool includes the cutting depth and cutting width of each path segment.

[0082] Preferably, in this embodiment, reference Figure 3 As shown, this figure is an exemplary flowchart of generating a set of parameter adjustment instructions for adjusting subsequent processing paths in an embodiment of this application. In this embodiment, the generation of the set of parameter adjustment instructions for adjusting subsequent processing paths based on the processing information and the processing stability index can be achieved by the following steps:

[0083] In step S31, the processing stability index is adjusted and mapped to obtain the reference speed adjustment amount;

[0084] In step S32, the influence coefficient of each path is determined based on the processing information;

[0085] In step S33, the corresponding forward speed adjustment is determined based on the reference speed adjustment amount and the influence coefficients of each path;

[0086] In step S34, a set of parameter adjustment instructions for adjusting the subsequent machining path is generated by adjusting each forward rotation speed adjustment.

[0087] In practical implementation, firstly, the machining stability index can be adjusted and mapped to obtain the reference speed adjustment amount. That is, a decision mode can be set according to the machining stability index, such as: (when the machining stability index is greater than 0.75, it is a stable mode; when the machining stability index is less than 0.75 but greater than 0.35, it is a defensive mode; when the machining stability index is less than 0.35, it is an emergency mode). Based on each decision mode and the machining stability index, the reference speed adjustment amount is determined. That is, when the decision mode is stable, the reference speed adjustment amount is 0; when the decision mode is defensive, 0.75 is subtracted from the machining stability index, the result is multiplied by -0.6, and the result is used as the reference speed adjustment amount; when the decision mode is emergency, the reference speed adjustment amount is -0.25. The reference speed adjustment is obtained. Then, the influence coefficient of each path can be determined based on the machining information. That is, the influence coefficient of each path can be determined based on the cutting depth and cutting width of each path segment in the machining information. Specifically, for each path segment, the cutting depth and cutting width of the path segment are multiplied, and then the cutting depth and cutting width of the previous path segment are multiplied. The two multiplication results are subtracted, and the absolute value of the result is taken. The result is then divided by the result of multiplying the cutting depth and cutting width of the previous path segment. The result is used as the path influence coefficient of that path segment, thus obtaining the influence coefficient of each path. Furthermore, the corresponding look-ahead speed adjustment is determined based on the reference speed adjustment and the influence coefficient of each path. That is, the look-ahead speed adjustment can be obtained by the following formula:

[0088]

[0089] in, This represents the forward speed adjustment amount for the k-th path segment; Indicates the amount of adjustment to the reference speed; This represents the path influence coefficient of the k-th path segment, thus obtaining the various look-ahead speed adjustment amounts. Finally, a set of parameter adjustment instructions for adjusting subsequent processing paths can be generated using these various look-ahead speed adjustment amounts. That is, each look-ahead speed adjustment amount and its corresponding path segment can be combined and output as a set, which is then used as the parameter adjustment instruction set.

[0090] It should be noted that by utilizing the processing information and processing stability index of the current processing task, it is possible to conduct forward-looking analysis and decision-making for subsequent processing, and generate a set of parameter adjustment instructions in a targeted manner, thereby achieving adaptive optimization of processing paths and processing parameters, and improving processing quality and processing efficiency.

[0091] The parameter adjustment module 400 is used to smoothly couple the parameter adjustment instruction set and the original path planning instruction of the target CNC machine tool to generate a motion control instruction set for the spindle motor of the target CNC machine tool, and to adjust the parameters of the spindle motor of the target CNC machine tool according to the motion control instruction set.

[0092] In this embodiment, the smooth coupling of the parameter adjustment instruction set and the original path planning instruction of the target CNC machine tool to generate the motion control instruction set of the target CNC machine tool spindle motor can be achieved through the following steps:

[0093] Align the parameter adjustment instruction set with the original path planning instruction to obtain each adjusted path segment;

[0094] The speed curve of the parameter adjustment instruction set is smoothed to obtain each real-time adjustable speed;

[0095] The motion control instruction set for the target CNC machine tool spindle motor is generated based on each adjustment path segment and the corresponding real-time adjustment speed.

[0096] In practical implementation, firstly, the parameter adjustment instruction set can be aligned with the original path planning instruction to obtain each adjustment path segment. That is, the original path planning instruction can be obtained from the target CNC machine tool's backend system, and each path segment in the parameter adjustment instruction set can be aligned with the original path planning instruction, thus using each path segment in the parameter adjustment instruction set as the adjustment path segment. Secondly, the speed curve of the parameter adjustment instruction set can be smoothed to obtain each real-time adjustment speed. That is, each look-ahead speed adjustment amount in the parameter adjustment instruction set can be multiplied by the starting speed of each adjustment path segment, and the result can be used as the target speed. Then, linear interpolation is used to linearly transition between the starting speed and the target speed of each adjustment path segment to obtain each real-time adjustment speed. Finally, the motion control instruction set of the target CNC machine tool spindle motor can be generated based on each adjustment path segment and the corresponding real-time adjustment speed. That is, each real-time adjustment speed and the corresponding adjustment path segment can be output as a set, and the resulting set can be used as the motion control instruction set of the target CNC machine tool spindle motor. The motion control instruction set includes: each adjustment path segment and the corresponding real-time adjustment speed.

[0097] In practice, the parameters of the spindle motor of the target CNC machine tool are adjusted according to the motion control instruction set. That is, for the motor speed of the spindle motor of the target CNC machine tool, the real-time adjustment speed corresponding to each adjustment path segment in the motion control instruction set is taken as the motor speed of the spindle motor of the target CNC machine tool when it reaches the corresponding adjustment path segment, thereby completing the parameter adjustment of the spindle motor of the target CNC machine tool.

[0098] Therefore, this application demonstrates that, firstly, by acquiring and processing the machining data signals of the spindle motor of the target CNC machine tool in real time, it can accurately reflect the operating characteristics of the spindle motor during machining, transforming the machining data into a machining state vector, providing a data foundation for subsequent machining state characterization fusion and adaptive parameter adjustment; secondly, by extracting and fusing the machining state vector in multiple dimensions, it can quantify the instantaneous fluctuation characteristics and evolution trends of the spindle motor during machining, forming a machining stability index, improving the comprehensiveness, accuracy, and robustness of machining stability assessment, and providing a reliable decision-making basis for subsequent adaptive adjustment of machining parameters; furthermore... By utilizing the machining information and machining stability index of the current machining task, it is possible to perform forward-looking analysis and decision-making for subsequent machining processes, and generate a set of parameter adjustment instructions accordingly. This enables adaptive optimization of the machining path and machining parameters, improving machining quality and efficiency. Finally, by smoothly coupling the parameter adjustment instruction set with the original path planning instructions, it is possible to gradually adjust the machining parameters of the spindle motor without disrupting the continuity of the established machining trajectory and the stability of the system. This avoids vibrations caused by sudden changes in instructions, thereby ensuring the stability of CNC machine tool operation and improving the safety, stability, and machining accuracy of the machining process.

[0099] In summary, the technical solution adopted in this application can sense the processing status in real time and predict stability changes, realize the forward-looking adaptive adjustment of processing parameters, and improve the processing accuracy and the intelligence level of CNC machine tools.

[0100] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products 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.

[0101] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compactdisc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0102] 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 process, method, article, or apparatus. Unless otherwise specified, 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 that element.

Claims

1. A machining state perception based adaptive parameter adjustment system for a CNC machine tool, characterized in that, The adaptive parameter adjustment system includes: The signal acquisition module is used to acquire the machining data signal of the spindle motor of the target CNC machine tool, and extract the machining state based on the machining data signal to obtain the machining state vector of the spindle motor of the target CNC machine tool. The characterization fusion module is used to perform state characterization fusion on the instantaneous machining state and stability trend of the target CNC machine tool spindle motor through the machining state vector, so as to obtain the machining stability index of the target CNC machine tool spindle motor. The instruction generation module is used to obtain the machining information of the current task of the target CNC machine tool, make forward-looking decisions based on the machining information and the machining stability index, and generate a set of parameter adjustment instructions to adjust the subsequent machining path. The parameter adjustment module is used to smoothly couple the parameter adjustment instruction set with the original path planning instruction of the target CNC machine tool to generate a motion control instruction set for the spindle motor of the target CNC machine tool, and to adjust the parameters of the spindle motor of the target CNC machine tool according to the motion control instruction set.

2. A machining state awareness based adaptive parameter adjustment system for CNC machine tools as claimed in claim 1 wherein, The processing data signals include current signals, vibration signals, and acoustic emission signals.

3. The adaptive parameter adjustment system for CNC machine tools based on machining state perception as described in claim 1, characterized in that, Based on the machining data signal, the machining state is extracted to obtain the machining state vector of the target CNC machine tool spindle motor, which specifically includes: The load dynamic feature set is determined by the current signal in the processing data signal; The vibration stability feature set is determined based on the vibration signal in the processing data signal; The transient characteristics of acoustic emission are determined based on the acoustic emission signals in the processing data signals; The load dynamic feature set, the vibration stability feature set, and the acoustic emission transient feature are vectorized to obtain the machining state vector of the target CNC machine tool spindle motor.

4. The adaptive parameter adjustment system for CNC machine tools based on machining state perception as described in claim 1, characterized in that, The machining information for the current task of the target CNC machine tool includes: the cutting depth and cutting width of each path segment.

5. The adaptive parameter adjustment system for CNC machine tools based on machining state perception as described in claim 1, characterized in that, The instantaneous machining state and stability trend of the target CNC machine tool spindle motor are fused using the machining state vector to obtain the machining stability index of the target CNC machine tool spindle motor, which specifically includes: Based on the machining state vector, determine the instantaneous state vector, trend state vector, and frequency domain state vector of the target CNC machine tool spindle motor; The instantaneous state vector, the trend state vector, and the frequency domain state vector are fused to obtain the machining stability index of the target CNC machine tool spindle motor.

6. The adaptive parameter adjustment system for CNC machine tools based on machining state perception as described in claim 5, characterized in that, The specific components for obtaining the machining stability index of the target CNC machine tool spindle motor include: The instantaneous state vector, the trend state vector, and the frequency domain state vector are combined to form a state feature vector; Construct a state transition matrix based on the state feature vectors; Based on the state transition matrix, the state feature vector of the previous time step is predicted to obtain the predicted state vector; Error extraction is performed using the state feature vector and the predicted state vector to obtain the predicted difference vector; Based on the predicted difference vector and the predicted state vector, the state features are corrected to obtain the corrected state vector; Numerical fusion is performed based on the corrected state vector to obtain the machining stability index of the target CNC machine tool spindle motor.

7. The adaptive parameter adjustment system for CNC machine tools based on machining state perception as described in claim 1, characterized in that, The machining stability index is used to quantitatively characterize the overall stability level of the spindle motor of the target CNC machine tool under the current machining state.

8. The adaptive parameter adjustment system for CNC machine tools based on machining state perception as described in claim 1, characterized in that, Based on the processing information and the processing stability index, a forward-looking decision is made to generate a set of parameter adjustment instructions for adjusting subsequent processing paths, specifically including: The machining stability index is adjusted and mapped to obtain the reference speed adjustment amount; The influence coefficient of each path is determined based on the processing information. The corresponding forward speed adjustment is determined based on the reference speed adjustment and the influence coefficients of each path. A set of parameter adjustment instructions for adjusting subsequent machining paths is generated by adjusting various forward rotation speeds.

9. The adaptive parameter adjustment system for CNC machine tools based on machining state perception as described in claim 1, characterized in that, The process of smoothly coupling the parameter adjustment instruction set with the original path planning instructions of the target CNC machine tool to generate the motion control instruction set for the spindle motor of the target CNC machine tool specifically includes: Align the parameter adjustment instruction set with the original path planning instruction to obtain each adjusted path segment; The speed curve of the parameter adjustment instruction set is smoothed to obtain each real-time adjustable speed; The motion control instruction set for the target CNC machine tool spindle motor is generated based on each adjustment path segment and the corresponding real-time adjustment speed.

10. The adaptive parameter adjustment system for CNC machine tools based on machining state perception as described in claim 1, characterized in that, The motion control command set includes: each adjustment path segment and its corresponding real-time adjustment speed.

Images