Active vibration control method for tool mechanical vibrations in an aluminum processing process

Abstract

This invention discloses an active vibration reduction control method for mechanical vibration of cutting tools during aluminum machining. The method includes: acquiring multi-source chatter data of the aluminum machining tool, extracting chatter features, and filtering effective features to obtain key chatter features; performing a comprehensive risk assessment and classification of the current chatter state of the aluminum machining tool based on the key chatter features, and calculating the dominant chatter frequency and energy concentration; matching multi-level control strategies for the current aluminum machining tool based on the risk classification results; adjusting the parameters of the matched control strategies according to the dominant chatter frequency and energy concentration to generate tool chatter suppression decisions; during the execution of the tool chatter suppression decisions, when the tool chatter exceeds the current chatter risk threshold, matching the next level of control decisions and adjusting the corresponding parameters to obtain a progressively dynamically optimized active tool chatter suppression decision. This method has the effects of highly sensitive early warning, precise graded vibration reduction, and improved accuracy of vibration reduction control.

Description

Technical Field

[0001] This invention relates to the technical field of metal cutting and intelligent manufacturing, and in particular to an active vibration reduction and control method for tool mechanical vibration during aluminum processing. Background Technology

[0002] Currently, due to the metallic properties of aluminum, it is easy for built-up edge to adhere to the cutting tool during the machining process, causing mechanical vibration of the tool, affecting the machining quality and efficiency of aluminum alloys and accelerating tool wear. Therefore, higher requirements are placed on the control of mechanical vibration of cutting tools in the aluminum machining process.

[0003] Existing methods for controlling tool mechanical vibration in aluminum machining processes typically rely on a single vibration amplitude for chatter assessment. They adjust the cutting speed or feed rate appropriately based on the vibration amplitude to reduce the interaction between the tool and the aluminum alloy workpiece. However, current technologies often depend on a single threshold for tool chatter assessment, making it difficult to distinguish between stable cutting, forced vibration, and early self-excited chatter, frequently leading to false alarms or missed alarms. Furthermore, with the increasing demand for high-precision machining, simply adjusting the speed or feed rate cannot respond promptly to severe tool chatter, resulting in a lag between the control and adjustment of tool chatter reduction in aluminum machining and the actual tool chatter state. Summary of the Invention

[0004] To address the problem that the control and adjustment of chatter reduction in aluminum machining tools lags behind the actual chatter state in existing technologies, this application provides an active vibration reduction control method for mechanical vibration of tools during aluminum machining. This method can accurately and quickly identify different chatter states during tool cutting and dynamically adjust control parameters from multiple dimensions to actively suppress chatter. It has the effects of highly sensitive early warning, precise graded vibration reduction, and improved vibration reduction control accuracy.

[0005] Firstly, the above-mentioned inventive objective of this application is achieved through the following technical solution: An active vibration reduction and control method for tool mechanical vibration during aluminum processing, the method comprising: Multi-source chatter data of aluminum machining tools is acquired, chatter features of the multi-source chatter data are extracted and effective feature screening is performed to obtain key chatter features; Based on the aforementioned key characteristics of chatter, a comprehensive risk assessment and classification of the current chatter state of aluminum machining tools is performed, and the dominant chatter frequency and energy concentration are calculated. Based on the risk classification results, a multi-level control strategy is matched for the current aluminum machining tool. The parameters of the matched control strategy are adjusted according to the dominant chatter frequency and the energy concentration to generate a tool chatter suppression decision. During the execution of the tool chatter suppression decision, when the tool chatter exceeds the current chatter risk threshold, the control decision of the next level is matched and the corresponding parameters are adjusted to obtain a progressively dynamically optimized active tool chatter suppression decision.

[0006] In a preferred embodiment, this application can be further configured as follows: acquiring multi-source chatter data of aluminum machining tools, extracting chatter features from the multi-source chatter data, and performing effective feature filtering processing to obtain key chatter features, specifically including: Multi-source chatter data during aluminum processing is acquired, and the multi-source chatter data is divided into multiple multi-source chatter data segments with a unified time scale by a sliding window. Flutter features are extracted from each of the multi-source flutter data segments and normalized. The normalized flutter features are recursively eliminated and effective features of each feature dimension are selected according to the sliding window sequence to obtain key flutter features. The key flutter features include kurtosis, frequency centroid offset rate, VMD minimum instantaneous frequency entropy, flutter band energy ratio, and AE ringing count.

[0007] In a preferred embodiment, this application can be further configured to: perform a comprehensive risk assessment and classification of the current chatter state of aluminum machining tools based on the aforementioned key chatter characteristics, and calculate the dominant chatter frequency and energy concentration, specifically including: A pre-trained lightweight classifier is used to perform a comprehensive risk assessment on the key flutter features, and the flutter state is classified based on the comprehensive risk assessment results to obtain the risk classification result of the current flutter state. Calculate the confidence level of the risk classification result, and when the confidence level calculation result is within the preset risk classification warning range, output the verified risk classification result; Adaptive variational mode decomposition is performed on the key flutter features, the energy ratio of each decomposed modal component is calculated, and flutter dominant mode identification is performed based on preset flutter mode identification conditions. The energy proportion calculation expression for the modal components is shown below: (1) in, This indicates the energy percentage of the modal components. Indicates the number of modal components. The first key feature decomposition of flutter is obtained by... One modal component, This represents the number of modes in the adaptive variational mode decomposition. Indicates the first The first mode decomposition yields the... One modal component; Calculate the instantaneous frequency mean and instantaneous frequency variance of the dominant flutter mode, verify the identification result of the dominant flutter mode based on the instantaneous frequency mean and instantaneous frequency variance, and take the instantaneous frequency mean as the dominant flutter frequency when the verification is successful. The energy concentration of the current flutter state is obtained by calculating the ratio between the flutter frequency band energy of the dominant flutter mode and the total energy. The expression for calculating the energy concentration is as follows: (2) in, Indicates energy concentration. Indicates the system's natural frequency. Indicates half bandwidth. Represents the vibrational power spectrum. This indicates the flutter frequency.

[0008] In a preferred embodiment, this application can be further configured as follows: calculating the confidence level of the risk classification result, and when the confidence level calculation result is within a preset risk classification warning range, outputting the verified risk classification result, specifically including: The risk classification results are weighted and fused to obtain the confidence level of the risk classification results. The expression for calculating the confidence level is as follows: (3) in, This represents the confidence coefficient. - This represents the preset centrality coefficient for each risk classification level. These represent the risk classification levels; Determine whether the confidence level calculation result is within the preset risk classification warning range of the current flutter risk level. If it is, output the risk classification result after verification.

[0009] In a preferred embodiment, this application can be further configured as follows: the multi-level control strategy matching of the current aluminum machining tool based on the risk classification result, and the parameter adjustment of the matched control strategy according to the chatter dominance frequency and the energy concentration, to generate a tool chatter suppression decision, specifically includes: Based on the risk classification results, a multi-level control strategy is matched for the current aluminum machining tool. Based on the matching results, combined with the dominant chatter frequency and the energy concentration, the optimal chatter suppression parameters for the current tool chatter state are calculated. Based on the optimal chatter suppression parameters, the tool control parameters are adjusted in a multi-dimensional coordinated manner to generate tool chatter suppression decisions.

[0010] In a preferred embodiment, this application can be further configured as follows: the multi-level control strategy matching for the current aluminum machining tool based on the risk classification results, and the calculation of the optimal chatter suppression parameters for the current tool chatter state based on the matching results combined with the dominant chatter frequency and the energy concentration, specifically including: When the first-level control decision is matched, the current spindle rotation frequency is obtained, and the optimal speed offset for tool chatter suppression is calculated in combination with the dominant chatter frequency, and the spindle speed and feed rate are adjusted synchronously. When matching to the second-level control decision, reverse active damping is calculated based on the dominant chatter frequency and the energy concentration, and the current chatter of the tool is suppressed by reverse active damping. When matching to the third level of control decision, the meshing area between the tool and the workpiece is calibrated, the cutting path of the meshing area is reconstructed, and the cutting width between the tool and the workpiece in the meshing area is adjusted. When the decision is matched to the fourth level of control, a tool retraction operation is performed and a tool change warning is issued.

[0011] In a preferred embodiment, this application can be further configured as follows: during the execution of the tool chatter suppression decision, when the tool chatter exceeds the current chatter risk threshold, the next level of control decision is matched and the corresponding parameters are adjusted to obtain a progressively dynamically optimized active tool chatter suppression decision, specifically including: During the execution of tool chatter suppression decisions at each level, the peak value of tool chatter is monitored in real time. When the peak value of tool chatter exceeds the risk threshold of the current risk level, the decision is matched to the control decision of the next level. The corresponding parameters of the control decision at the next level are adjusted, and the real-time chatter state of the tool is dynamically optimized step by step to obtain multi-level active chatter suppression decisions for the tool.

[0012] Secondly, the above-mentioned inventive objective of this application is achieved through the following technical solutions: An active vibration reduction and control system for tool mechanical vibration during aluminum processing, the system comprising: The data preprocessing module is used to acquire multi-source chatter data of aluminum machining tools, extract chatter features from the multi-source chatter data and perform effective feature screening to obtain key chatter features. The risk assessment module is used to perform a comprehensive risk assessment and classification of the current chatter state of aluminum machining tools based on the aforementioned key chatter characteristics, and to calculate the dominant chatter frequency and energy concentration. The decision matching module is used to perform multi-level control strategy matching for the current aluminum machining tool based on the risk classification results, and to adjust the parameters of the matched control strategy according to the dominant chatter frequency and the energy concentration to generate tool chatter suppression decisions. The chatter suppression module is used to match the control decision of the next level and adjust the corresponding parameters when the tool chatter exceeds the current chatter risk threshold during the execution of the tool chatter suppression decision, so as to obtain a step-by-step dynamically optimized active tool chatter suppression decision.

[0013] Thirdly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described active vibration reduction control method for tool mechanical vibration during aluminum processing.

[0014] Fourthly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described active vibration reduction control method for tool mechanical vibration during aluminum processing.

[0015] In summary, this application includes at least one of the following beneficial technical effects: 1. By performing feature analysis and effective feature screening on multi-source data related to chatter during aluminum processing, the data processing workload of chatter analysis is greatly reduced. Comprehensive chatter risk assessment and classification are performed through key chatter features. Tool chatter states of different risk levels are treated in a targeted manner, and the dominant chatter frequency and energy concentration are calculated to locate the main chatter location. Then, through the matching of multi-level control strategies and the dynamic adjustment of tool control parameters in combination with actual conditions, the tool chatter suppression decision can accurately meet the actual chatter reduction needs, achieving precise graded vibration reduction, energy saving and high efficiency. By monitoring whether the tool chatter exceeds the risk threshold in real time during the decision execution process, it is determined whether to enter the next level of vibration reduction suppression, achieving the effect of progressively and dynamically suppressing tool chatter. 2. This application extracts effective features by feature fusion and normalization of multi-source chatter data and variational mode decomposition, which can pre-identify microscopic stick-slip chatter precursors, achieve highly sensitive early warning, and gain critical time for parameter adjustment for proactive intervention in tool chatter, thereby reducing the lag between tool adjustment and actual vibration reduction requirements. 3. This application actively intervenes in strong, sudden chatter through active damping and path reconstruction, thereby destroying the conditions for chatter formation at the source. When active intervention fails to affect tool chatter, a tool change warning is issued, forming a whole chain of active tool chatter suppression in the aluminum machining process, from identification to diagnosis to decision-making to tool change warning, thus improving the intelligence of tool control in the aluminum machining process. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0017] Figure 1 This is a flowchart illustrating the implementation of the active vibration reduction control method for tool mechanical vibration in this embodiment.

[0018] Figure 2 This is a flowchart illustrating the implementation of step S1 of the active vibration reduction control method for tool mechanical vibration in this embodiment.

[0019] Figure 3 This is a flowchart illustrating step S2 of the active vibration reduction control method for tool mechanical vibration in this embodiment.

[0020] Figure 4 This is a flowchart illustrating the implementation of step S22 of the active vibration reduction control method for tool mechanical vibration in this embodiment.

[0021] Figure 5 This is a flowchart illustrating the implementation of step S3 in the active vibration reduction control method for tool mechanical vibration in this embodiment.

[0022] Figure 6 This is a flowchart illustrating step S4 of the active vibration reduction control method for tool mechanical vibration in this embodiment. Figure 7 This is a structural block diagram of the active vibration reduction control system for the mechanical vibration of the cutting tool in this embodiment.

[0023] Figure 8 This is a schematic diagram of the internal structure of a computer device used to implement an active vibration reduction control method for tool mechanical vibration. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] It should be understood that, when used in this specification, the terms “comprising” and “including” indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0026] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are intended to include the plural forms.

[0027] It should also be further understood that the term "and / or" as used in this specification refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes such combinations.

[0028] In one embodiment, such as Figure 1 As shown, this application discloses an active vibration reduction and control method for the mechanical vibration of cutting tools during aluminum processing, specifically including the following steps: S1: Obtain multi-source chatter data of aluminum machining tools, extract chatter features from the multi-source chatter data and perform effective feature screening to obtain key chatter features.

[0029] Specifically, such as Figure 2 As shown, step S1 includes: S11: Acquire multi-source chatter data during aluminum processing, divide the multi-source chatter data into sliding windows, and obtain multiple multi-source chatter data segments with a unified time scale.

[0030] Specifically, multi-source chatter data during aluminum processing is acquired, including time-domain vibration signals, acoustic emission (AE) signals, cutting force fluctuation signals, cutting temperature, etc. A sliding time window is set to divide the multi-source chatter data into multiple segments with a unified time scale.

[0031] S12: Extract flutter features from each multi-source flutter data segment and normalize them. Recursively eliminate the normalized flutter features according to the sliding window order and filter the effective features of each feature dimension to obtain key flutter features. Key flutter features include kurtosis, frequency centroid offset rate, VMD minimum instantaneous frequency entropy, flutter band energy ratio, and AE ringing count.

[0032] Specifically, flutter features are extracted from each multi-source flutter data segment, including time-domain features, frequency-domain features, and AE features. The time-domain features include vibration peak value, root mean square (RMS), and kurtosis. The frequency-domain features are obtained by extracting the dominant frequency component and its harmonics through fast Fourier transform of the vibration signal. The AE features are obtained through the RMS, ring count, and spectrum of the acoustic emission (AE) signal. The normalized flutter features are recursively eliminated according to the sliding window sequence, and only the effective features of each feature dimension are selected and retained to obtain the key flutter features. In this embodiment, the key flutter features include kurtosis, frequency centroid offset rate, VMD minimum instantaneous frequency entropy, flutter band energy ratio, and AE ring count.

[0033] The expression for calculating the frequency centroid offset rate is shown below: (4) in, This indicates the frequency centroid offset rate; positive or negative indicates the direction of offset. , Let f(x) represent the centroid of the frequency during cutting and the centroid of the reference frequency in the chatter-free state, respectively. The calculation expressions are shown below: (5) (6) in, , These represent the maximum and minimum values ​​of the tool chatter frequency, respectively. Indicates the real-time frequency of the cutting tool. This represents the power spectral density of the cutting tool. Indicates the spindle speed. This indicates the number of teeth on the milling cutter.

[0034] S2: Based on the key characteristics of chatter, a comprehensive risk assessment and classification of the current chatter state of aluminum machining tools is performed, and the dominant chatter frequency and energy concentration are calculated.

[0035] Specifically, such as Figure 3 As shown, step S2 includes: S21: A comprehensive risk assessment of key flutter features is performed using a pre-trained lightweight classifier, and the flutter state is classified based on the comprehensive risk assessment results to obtain the risk classification result of the current flutter state.

[0036] Specifically, in this embodiment, LightGBM lightweight gradient booster is used as a classifier to perform a comprehensive risk assessment on key flutter features and output flutter state category probabilities, including four categories: stable, warning, tremor, and severe, to obtain the risk classification result of the current flutter state.

[0037] The training process of the LightGBM classifier in this embodiment: Each multi-source flutter data segment is labeled with multiple categories such as stable, early warning, flutter, and severe. The key flutter features extracted from each segment are merged into a feature matrix and Z-score standardized. The processed data is divided into training, validation, and test sets and input into the LightGBM classifier. The loss function of the LightGBM classifier is set to the multi-class cross-entropy loss function, the number of training trees is set to 100-200, the learning rate is set to 0.05, and the maximum depth is set to 5-7. The probability of the key flutter features being classified into the four risk categories is calculated as the risk assessment result.

[0038] S22: Calculate the confidence level of the risk classification result. When the confidence level calculation result is within the preset risk classification warning range, output the verified risk classification result.

[0039] Specifically, such as Figure 4 As shown, step S22 includes: S221: Perform a weighted fusion calculation on the risk classification results to obtain the confidence level of the risk classification results. The expression for calculating the confidence level is as follows: (3) in, This represents the confidence coefficient. - This represents the preset centrality coefficient for each risk classification level. These represent the risk classification levels.

[0040] S222: Determine whether the confidence level calculation result is within the preset risk classification warning range of the current flutter risk level. If it is, output the risk classification result after verification.

[0041] Specifically, if the preset center coefficient for stable state is set to 0, the preset center coefficient for warning state is set to 0.3, the preset center coefficient for flutter state is set to 0.65, and the preset center coefficient for severe state is set to 0.9, then the warning interval for stable state is 0-0.3, the warning interval for warning state is 0.3-0.65, and the warning interval for flutter state is 0.65-0.9. If the risk class probability output by the LightGBM classifier is... ,but If the value is 0.34, and the risk classification result falls within the warning range, then the output after successful verification will be in the warning state.

[0042] S23: Perform adaptive variational mode decomposition on key flutter features, calculate the energy proportion of each decomposed modal component, and identify the dominant flutter mode based on preset flutter mode identification conditions.

[0043] The energy proportion calculation expression for the modal components is shown below: (1) in, This indicates the energy percentage of the modal components. Indicates the number of modal components. The first key feature decomposition of flutter is obtained by... One modal component, This represents the number of modes in the adaptive variational mode decomposition. Indicates the first The first mode decomposition yields the... One modal component; In this embodiment, variational mode decomposition (VMD) is used to decompose the key features of flutter. The mode decomposition number K is set to 4 in this embodiment. The expressions of the modal components obtained after decomposition are as follows: (7) in, Represents modal components, Indicates instantaneous amplitude. Indicates the instantaneous phase.

[0044] In this embodiment, the modal component with the largest energy proportion and whose instantaneous frequency is not near the tooth passing frequency and its harmonics is selected as the dominant chatter mode.

[0045] In this embodiment, the modal components are subjected to Hilbert transform: To construct an analytic signal: To calculate the instantaneous phase: Instantaneous frequency is calculated based on instantaneous phase, and the expression for instantaneous frequency calculation is as follows: (8) S24: Calculate the instantaneous frequency mean and instantaneous frequency variance of the dominant flutter mode. Verify the identification result of the dominant flutter mode based on the instantaneous frequency mean and instantaneous frequency variance. If the verification is successful, take the instantaneous frequency mean as the dominant flutter frequency.

[0046] In this embodiment, the instantaneous frequency mean and instantaneous frequency variance of all multi-source flutter data segments are calculated. When the ratio of the instantaneous frequency variance to the instantaneous frequency mean is greater than 0.1, i.e. the frequency fluctuation exceeds 10%, it indicates that the flutter identification result of the current flutter dominant mode is correct and is verified. The instantaneous frequency mean is then used as the flutter dominant frequency.

[0047] The instantaneous frequency variance calculation expression in this embodiment is as follows: (9) in, Represents the instantaneous frequency variance. Indicates the number of instantaneous frequencies. Indicates the first A momentary frequency, This represents the average instantaneous frequency.

[0048] S25: Calculate the ratio between the flutter band energy of the dominant flutter mode and the total energy to obtain the energy concentration of the current flutter state. The expression for calculating the energy concentration is as follows: (2) in, Indicates energy concentration. Indicates the system's natural frequency. Indicates half bandwidth. Represents the vibrational power spectrum. This indicates the flutter frequency.

[0049] S3: Based on the risk classification results, perform multi-level control strategy matching for the current aluminum machining tools, adjust the parameters of the matched control strategy according to the dominant chatter frequency and energy concentration, and generate tool chatter suppression decisions.

[0050] Specifically, such as Figure 5 As shown, step S3 includes: S31: Based on the risk classification results, perform multi-level control strategy matching for the current aluminum machining tool. Based on the matching results, combined with the dominant chatter frequency and energy concentration, calculate the optimal chatter suppression parameters for the current tool chatter state.

[0051] Specifically, based on the risk classification results, if the confidence level is in the range of 0.3-0.45, it is matched to the first-level control strategy, which suppresses chatter by adaptively adjusting tool parameters. When the confidence level is in the range of 0.45-0.65, it is matched to the second-level control strategy, which suppresses chatter by incorporating active damping. When the confidence level is in the range of 0.65-0.85, it is matched to the third-level control strategy, which suppresses chatter by reconstructing the tool path. When the confidence level is above 0.85, it is matched to the fourth-level control strategy, which provides warnings for tool retraction and tool change.

[0052] Specifically, when matching to the first level of control decision, the current spindle rotation frequency is obtained, and the optimal speed offset for tool chatter suppression is calculated in combination with the dominant chatter frequency. The spindle speed and feed rate are adjusted synchronously, such as fine-tuning the spindle speed by ±5%-10% and simultaneously increasing the feed rate by 5%-10%.

[0053] When matching to the second level of control decision, reverse active damping is calculated based on the dominant chatter frequency and energy concentration. The reverse active damping is used to suppress the current chatter of the tool, such as outputting a high-frequency displacement of 1-5μm in the reverse direction of the chatter phase of the tool and restoring the feed rate.

[0054] When matching to the third level of control decision, the meshing area between the tool and the workpiece is calibrated, the cutting path of the meshing area is reconstructed, and the cutting width between the tool and the workpiece in the meshing area is adjusted. If the confidence level cannot be reduced to below 0.5 after 2 seconds of active damping, the active damping is paused, and the milling path of the tool is replanned, such as switching from linear milling to cycloidal milling or helical interpolation, while reducing the depth of cut by 30%-50%.

[0055] When the decision is matched to the fourth level of control, a tool retraction operation is performed and a tool change warning is issued. When the confidence level exceeds 0.85 for more than 3 seconds, a tool retraction operation is triggered and a tool change warning is issued.

[0056] S32: Based on the optimal chatter suppression parameters, the tool control parameters are adjusted in a multi-dimensional coordinated manner to generate tool chatter suppression decisions.

[0057] Specifically, based on the optimal chatter suppression parameters, multi-dimensional collaborative adjustments are made to tool control parameters such as spindle speed, feed rate, phase displacement, and milling path to generate tool chatter suppression decisions.

[0058] S4: During the execution of the tool chatter suppression decision, when the tool chatter exceeds the current chatter risk threshold, the control decision of the next level is matched and the corresponding parameters are adjusted to obtain the tool chatter suppression decision that is dynamically optimized step by step.

[0059] Specifically, such as Figure 6 As shown, step S4 includes: S41: During the execution of tool chatter suppression decisions at each level, the peak value of tool chatter is monitored in real time. When the peak value of tool chatter exceeds the risk threshold of the current risk level, it is matched to the control decision of the next level.

[0060] Specifically, during the execution of tool chatter suppression decisions at each level, the peak value of the tool chatter frequency is monitored in real time. When the peak value of the tool chatter exceeds the risk threshold of the current risk level, it is matched to the control decision of the next level.

[0061] S42: Adjust the corresponding parameters for the control decision at the next level, and perform dynamic optimization of the real-time chatter state of the tool step by step to obtain multi-level active chatter suppression decisions for the tool.

[0062] Specifically, the corresponding parameters are adjusted for the next level of control decision, and the tool chatter status is monitored in real time to determine whether the current parameter adjustment has achieved the effect of suppressing chatter. If the tool chatter peak value is reduced to a safe range under the current parameter control, it indicates that there is a chatter suppression effect. If the tool chatter peak value continues to maintain the original value or is increasing, then the next level of control strategy is entered until the tool chatter is suppressed to a safe range, thus obtaining a multi-level active tool chatter suppression decision.

[0063] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0064] In one embodiment, an active vibration reduction control system for tool mechanical vibration during aluminum machining is provided, which corresponds one-to-one with the active vibration reduction control method for tool mechanical vibration during aluminum machining described in the above embodiments. For example... Figure 7 As shown, the active vibration reduction control system for tool mechanical vibration during aluminum processing includes a data preprocessing module, a risk assessment module, a decision matching module, and a chatter suppression module. Detailed descriptions of each functional module are as follows: The data preprocessing module is used to acquire multi-source chatter data of aluminum machining tools, extract chatter features from the multi-source chatter data, and perform effective feature screening to obtain key chatter features.

[0065] The risk assessment module is used to perform a comprehensive risk assessment and classification of the current chatter status of aluminum machining tools based on key chatter characteristics, and to calculate the dominant chatter frequency and energy concentration.

[0066] The decision matching module is used to match multi-level control strategies for the current aluminum machining tools based on the risk classification results. It adjusts the parameters of the matched control strategies according to the dominant chatter frequency and energy concentration to generate tool chatter suppression decisions.

[0067] The chatter suppression module is used to match the control decision of the next level and adjust the corresponding parameters when the tool chatter exceeds the current chatter risk threshold during the execution of the tool chatter suppression decision, so as to obtain the active tool chatter suppression decision that is dynamically optimized step by step.

[0068] Preferably, the data preprocessing module specifically includes: The data partitioning submodule is used to acquire multi-source chatter data during aluminum processing, and to divide the multi-source chatter data into multiple multi-source chatter data segments with a unified time scale by using a sliding window.

[0069] The feature extraction submodule is used to extract flutter features from each multi-source flutter data segment and perform normalization processing. The normalized flutter features are recursively eliminated according to the sliding window order, and the effective features of each feature dimension are selected to obtain the key flutter features. The key flutter features include kurtosis, frequency centroid offset rate, VMD minimum instantaneous frequency entropy, flutter band energy ratio, and AE ringing count.

[0070] Preferably, the risk assessment module specifically includes: The state classification submodule is used to perform a comprehensive risk assessment of key flutter features using a pre-trained lightweight classifier, and to classify the flutter state based on the comprehensive risk assessment results, thereby obtaining the risk classification result of the current flutter state.

[0071] The classification result verification submodule is used to calculate the confidence level of the risk classification result. When the confidence level calculation result is within the preset risk classification warning range, the verified risk classification result is output.

[0072] The flutter mode recognition submodule is used to perform adaptive variational mode decomposition on key flutter features, calculate the energy ratio of each mode component obtained after decomposition, and identify the dominant flutter mode based on preset flutter mode recognition conditions. The energy proportion calculation expression for the modal components is shown below: (1) in, This indicates the energy percentage of the modal components. Indicates the number of modal components. The first key feature decomposition of flutter is obtained by... One modal component, This represents the number of modes in the adaptive variational mode decomposition. Indicates the first The first mode decomposition yields the... One modal component. The modal recognition verification submodule is used to calculate the instantaneous frequency mean and instantaneous frequency variance of the flutter dominant mode. Based on the instantaneous frequency mean and instantaneous frequency variance, the recognition result of the flutter dominant mode is verified. When the verification is successful, the instantaneous frequency mean is taken as the flutter dominant frequency.

[0073] The energy concentration calculation submodule is used to calculate the ratio between the flutter frequency band energy of the dominant flutter mode and the total energy, thus obtaining the energy concentration of the current flutter state. The energy concentration calculation expression is as follows: (2) in, Indicates energy concentration. Indicates the system's natural frequency. Indicates half bandwidth. Represents the vibrational power spectrum. This indicates the flutter frequency.

[0074] Preferably, the classification result verification submodule specifically includes: The confidence score calculation unit is used to perform weighted fusion calculations on the risk classification results to obtain the confidence score of the risk classification results. The expression for calculating the confidence score is as follows: (3) in, This represents the confidence coefficient. - This represents the preset centrality coefficient for each risk classification level. These represent the risk classification levels. The risk classification result verification unit is used to determine whether the confidence level calculation result is within the preset risk classification warning range of the current flutter risk level. If it is, the unit outputs the risk classification result after verification.

[0075] Preferably, the decision matching module specifically includes: The suppression parameter calculation submodule is used to perform multi-level control strategy matching for the current aluminum machining tool based on the risk classification results. Based on the matching results, combined with the dominant chatter frequency and energy concentration, the optimal chatter suppression parameters for the current tool chatter state are calculated.

[0076] The control parameter adjustment submodule is used to perform multi-dimensional coordinated adjustment of tool control parameters based on the optimal chatter suppression parameters, and generate tool chatter suppression decisions.

[0077] Preferably, the suppression parameter calculation submodule specifically includes: When matching the first level of control decision, the current spindle rotation frequency is obtained, and the optimal speed offset for tool chatter suppression is calculated in combination with the dominant chatter frequency, and the spindle speed and feed rate are adjusted synchronously.

[0078] When matching to the second-level control decision, reverse active damping is calculated based on the dominant chatter frequency and energy concentration, and the current chatter of the tool is suppressed by reverse active damping.

[0079] When matching to the third level of control decision, the meshing area between the tool and the workpiece is calibrated, the cutting path of the meshing area is reconstructed, and the cutting width between the tool and the workpiece in the meshing area is adjusted.

[0080] When the decision is matched to the fourth level of control, a tool retraction operation is performed and a tool change warning is issued.

[0081] Preferably, the flutter suppression module specifically includes: The decision execution submodule is used to monitor the peak value of tool chatter in real time during the execution of tool chatter suppression decisions at each level. When the peak value of tool chatter exceeds the risk threshold of the current risk level, it is matched to the control decision of the next level.

[0082] The multi-level adjustment submodule is used to adjust the corresponding parameters of the control decision at the next level, and to perform step-by-step dynamic optimization of the real-time tool chatter state to obtain multi-level active tool chatter suppression decisions.

[0083] Specific limitations regarding the active vibration reduction control system for tool mechanical vibration during aluminum machining can be found in the above-mentioned limitations on the active vibration reduction control method for tool mechanical vibration during aluminum machining, and will not be repeated here. Each module in the aforementioned active vibration reduction control system for tool mechanical vibration during aluminum machining can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0084] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores relevant data for active vibration reduction of aluminum machining tools. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements an active vibration reduction control method for the mechanical vibration of tools during aluminum machining.

[0085] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements an active vibration reduction control method for tool mechanical vibration during aluminum machining.

[0086] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application of the technical solution and the constraints involved. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0087] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0088] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0089] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for actively reducing and controlling the mechanical vibration of cutting tools during aluminum processing, characterized in that, The method includes: Multi-source chatter data of aluminum machining tools is acquired, chatter features of the multi-source chatter data are extracted and effective feature screening is performed to obtain key chatter features; Based on the aforementioned key characteristics of chatter, a comprehensive risk assessment and classification of the current chatter state of aluminum machining tools is performed, and the dominant chatter frequency and energy concentration are calculated. Based on the risk classification results, a multi-level control strategy is matched for the current aluminum machining tool. The parameters of the matched control strategy are adjusted according to the dominant chatter frequency and the energy concentration to generate a tool chatter suppression decision. During the execution of the tool chatter suppression decision, when the tool chatter exceeds the current chatter risk threshold, the control decision of the next level is matched and the corresponding parameters are adjusted to obtain a progressively dynamically optimized active tool chatter suppression decision.

2. The active vibration reduction and control method for tool mechanical vibration during aluminum processing according to claim 1, characterized in that, The process involves acquiring multi-source chatter data from aluminum machining tools, extracting chatter features from the multi-source chatter data, and performing effective feature filtering to obtain key chatter features, specifically including: Multi-source chatter data during aluminum processing is acquired, and the multi-source chatter data is divided into multiple multi-source chatter data segments with a unified time scale by a sliding window. Flutter features are extracted from each of the multi-source flutter data segments and normalized. The normalized flutter features are recursively eliminated and effective features of each feature dimension are selected according to the sliding window sequence to obtain key flutter features. The key flutter features include kurtosis, frequency centroid offset rate, VMD minimum instantaneous frequency entropy, flutter band energy ratio, and AE ringing count.

3. The active vibration reduction and control method for tool mechanical vibration during aluminum processing according to claim 1, characterized in that, Based on the aforementioned key chatter characteristics, a comprehensive risk assessment and classification of the current chatter state of aluminum machining tools is performed, and the dominant chatter frequency and energy concentration are calculated. Specifically, this includes: A pre-trained lightweight classifier is used to perform a comprehensive risk assessment on the key flutter features, and the flutter state is classified based on the comprehensive risk assessment results to obtain the risk classification result of the current flutter state. Calculate the confidence level of the risk classification result, and when the confidence level calculation result is within the preset risk classification warning range, output the verified risk classification result; Adaptive variational mode decomposition is performed on the key flutter features, the energy ratio of each decomposed modal component is calculated, and flutter dominant mode identification is performed based on preset flutter mode identification conditions. The energy proportion calculation expression for the modal components is shown below: （1） in, This indicates the energy percentage of the modal components. Indicates the number of modal components. The first key feature decomposition of flutter is obtained by... One modal component, This represents the number of modes in the adaptive variational mode decomposition. Indicates the first The first mode decomposition yields the... One modal component; Calculate the instantaneous frequency mean and instantaneous frequency variance of the dominant flutter mode, verify the identification result of the dominant flutter mode based on the instantaneous frequency mean and instantaneous frequency variance, and take the instantaneous frequency mean as the dominant flutter frequency when the verification is successful. The energy concentration of the current flutter state is obtained by calculating the ratio between the flutter frequency band energy of the dominant flutter mode and the total energy. The expression for calculating the energy concentration is as follows: （2） in, Indicates energy concentration. Indicates the system's natural frequency. Indicates half bandwidth. Represents the vibrational power spectrum. This indicates the flutter frequency.

4. The active vibration reduction and control method for tool mechanical vibration during aluminum processing according to claim 3, characterized in that, The process involves calculating the confidence level of the risk classification result. When the confidence level calculation result falls within a preset risk classification warning range, the verified risk classification result is output, specifically including: The risk classification results are weighted and fused to obtain the confidence level of the risk classification results. The expression for calculating the confidence level is as follows: （3） in, This represents the confidence coefficient. - This represents the preset centrality coefficient for each risk classification level. These represent the risk classification levels; Determine whether the confidence level calculation result is within the preset risk classification warning range of the current flutter risk level. If it is, output the risk classification result after verification.

5. The active vibration reduction and control method for tool mechanical vibration during aluminum processing according to claim 1, characterized in that, The process of matching multi-level control strategies for the current aluminum machining tool based on risk classification results, adjusting the parameters of the matched control strategies according to the dominant chatter frequency and the energy concentration, and generating tool chatter suppression decisions specifically includes: Based on the risk classification results, a multi-level control strategy is matched for the current aluminum machining tool. Based on the matching results, combined with the dominant chatter frequency and the energy concentration, the optimal chatter suppression parameters for the current tool chatter state are calculated. Based on the optimal chatter suppression parameters, the tool control parameters are adjusted in a multi-dimensional coordinated manner to generate tool chatter suppression decisions.

6. The active vibration reduction and control method for tool mechanical vibration during aluminum processing according to claim 5, characterized in that, The process involves matching multi-level control strategies for the current aluminum machining tool based on risk classification results. Based on the matching results, combined with the dominant chatter frequency and energy concentration, the optimal chatter suppression parameters for the current tool chatter state are calculated, specifically including: When the first-level control decision is matched, the current spindle rotation frequency is obtained, and the optimal speed offset for tool chatter suppression is calculated in combination with the dominant chatter frequency, and the spindle speed and feed rate are adjusted synchronously. When matching to the second-level control decision, reverse active damping is calculated based on the dominant chatter frequency and the energy concentration, and the current chatter of the tool is suppressed by reverse active damping. When matching to the third level of control decision, the meshing area between the tool and the workpiece is calibrated, the cutting path of the meshing area is reconstructed, and the cutting width between the tool and the workpiece in the meshing area is adjusted. When the decision is matched to the fourth level of control, a tool retraction operation is performed and a tool change warning is issued.

7. The active vibration reduction and control method for tool mechanical vibration during aluminum processing according to claim 1, characterized in that, During the execution of the tool chatter suppression decision, when the tool chatter exceeds the current chatter risk threshold, the next level of control decision is matched and the corresponding parameters are adjusted to obtain a progressively dynamically optimized active tool chatter suppression decision, specifically including: During the execution of tool chatter suppression decisions at each level, the peak value of tool chatter is monitored in real time. When the peak value of tool chatter exceeds the risk threshold of the current risk level, the decision is matched to the control decision of the next level. The corresponding parameters of the control decision at the next level are adjusted, and the real-time chatter state of the tool is dynamically optimized step by step to obtain multi-level active chatter suppression decisions for the tool.

8. An active vibration reduction control system for tool mechanical vibration during aluminum processing, characterized in that, The system includes: The data preprocessing module is used to acquire multi-source chatter data of aluminum machining tools, extract chatter features from the multi-source chatter data and perform effective feature screening to obtain key chatter features. The risk assessment module is used to perform a comprehensive risk assessment and classification of the current chatter state of aluminum machining tools based on the aforementioned key chatter characteristics, and to calculate the dominant chatter frequency and energy concentration. The decision matching module is used to perform multi-level control strategy matching for the current aluminum machining tool based on the risk classification results, and to adjust the parameters of the matched control strategy according to the dominant chatter frequency and the energy concentration to generate tool chatter suppression decisions. The chatter suppression module is used to match the control decision of the next level and adjust the corresponding parameters when the tool chatter exceeds the current chatter risk threshold during the execution of the tool chatter suppression decision, so as to obtain a step-by-step dynamically optimized active tool chatter suppression decision.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the active vibration reduction control method for tool mechanical vibration during aluminum processing as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the active vibration reduction control method for tool mechanical vibration during aluminum processing as described in any one of claims 1 to 7.

Images