Vibration suppression and surface quality control method for part cutting of numerical control machining center

Abstract

The invention discloses a vibration suppression and surface quality control method for part cutting of a numerical control machining center, which relates to the technical field of numerical control machining and comprises the following steps: multi-modal sensor fusion monitoring: mounting multi-modal sensors on key parts such as a main shaft, a cutter and a workbench of the numerical control machining center, comprising an acceleration sensor, a strain sensor and an acoustic emission sensor and monitors a vibration signal, a cutting force signal and an acoustic emission signal in the machining process in real time; self-adaptive machining parameter optimization is carried out, and machining parameters are preset according to machining task requirements; dynamic adjustment and intelligent feedback control of machining parameters are realized by adopting a vibration prediction model based on deep learning and an adaptive optimization algorithm; according to the technology, the automation level of the machining process is improved, machining errors and surface quality defects caused by vibration are effectively reduced, and the surface roughness and size precision of the workpiece are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of numerical control machining technology, in particular to a vibration suppression and surface quality control method for parts machining in a numerical control machining center. BACKGROUND

[0002] In the field of high-speed precision machining in numerical control machining centers, machining quality and efficiency are key indicators of production level. However, vibration problems during machining and the resulting surface quality problems have been the main bottleneck restricting the development of numerical control machining technology. Vibration not only leads to increased surface roughness of workpieces, decreased dimensional accuracy, but also causes increased tool wear and machine tool failure, which seriously affects machining efficiency and quality. Traditional vibration suppression methods mainly rely on optimizing machining parameters and improving machine tool structure design, such as adjusting cutting speed, feed rate and cutting depth to reduce vibration, or improving machine tool rigidity and installing vibration reduction devices to enhance the anti-vibration performance of the machine tool. However, these methods have certain limitations, such as the need for a large amount of experiments and experience accumulation to optimize machining parameters, which is difficult to adapt to changes in different workpiece materials and machining conditions; and the improvement of machine tool structure often requires high cost and is difficult to make large-scale modifications to existing machine tools. In recent years, with the development of sensor technology, some research has begun to try to monitor vibration signals in the machining process in real time by installing sensors and adjusting machining parameters accordingly. However, these methods mostly rely on a single type of sensor (such as an acceleration sensor), and the limited vibration information makes it difficult to fully reflect the complex vibration state during machining. In addition, traditional vibration monitoring methods lack effective prediction capabilities and can only make passive adjustments after vibration has occurred, which cannot prevent vibration in advance. In terms of surface quality control, traditional surface quality control methods mainly rely on post-machining detection, such as using a three-coordinate measuring instrument or a surface roughness meter to measure the workpiece. Although this method can accurately evaluate surface quality, it cannot be adjusted in real time during machining, and once a problem is found, it often needs to be reprocessed, resulting in reduced production efficiency and increased cost. At the same time, some research attempts to indirectly evaluate surface quality by monitoring cutting force or tool wear during machining. However, the monitoring accuracy of these methods is limited and cannot directly reflect the actual state of the workpiece surface. In addition, there is a lack of a systematic solution in existing technology that can adjust cutting parameters in real time during machining to optimize surface quality.

[0003] In summary, the existing technology has the following main problems in vibration suppression and surface quality control during high-speed precision machining of parts in numerical control machining centers: limitations of vibration monitoring and suppression, lag of surface quality control, and static nature of machining parameter optimization. These problems limit the improvement of machining efficiency and further optimization of machining quality. SUMMARY

[0004] The purpose of the present application is to provide a vibration suppression and surface quality control method for part cutting of a numerical control machining center, to solve the problems of low machining quality and production efficiency and high production cost in the prior art.

[0005] In order to achieve the above-mentioned purpose, the present application provides the following technical solution: a vibration suppression and surface quality control method for part cutting of a numerical control machining center, comprising the following steps:

[0006] S1, multi-modal sensor fusion monitoring, multi-modal sensors including acceleration sensors, strain sensors and acoustic emission sensors are installed at the spindle, tool and worktable parts of the numerical control machining center to monitor vibration signals, cutting force signals and acoustic emission signals in real time during the machining process;

[0007] S2, adaptive machining parameter optimization, machining parameters including cutting speed, feed rate and cutting depth are pre-set according to the machining task requirements and input into the numerical control system; the multi-modal signals monitored by the sensors are collected in real time during the machining process, and the signals and machining parameters are input into the vibration prediction model based on deep learning;

[0008] S3, intelligent vibration prediction and feedback control, the vibration prediction model predicts the vibration situation in the subsequent machining process according to the input multi-modal signals and machining parameters, and feeds back the prediction results to the numerical control system; the numerical control system judges whether the vibration is within the allowable range according to the vibration prediction results, and if the vibration exceeds the allowable range, the machining parameters are automatically adjusted by the adaptive optimization algorithm to suppress the vibration;

[0009] S4, active vibration compensation technology, in the machining process, the piezoelectric ceramic actuator installed at the key parts of the machine tool applies reverse vibration according to the vibration signal to offset the vibration of the machine tool;

[0010] S5, real-time surface quality monitoring and feedback, in the machining process, the surface quality of the workpiece is monitored in real time, the machined workpiece surface is detected by the non-contact optical surface roughness detection device, and the detection results are fed back to the numerical control system; the numerical control system further adjusts the machining parameters according to the surface quality detection results;

[0011] S6, multi-objective optimization control, the machining parameters are dynamically adjusted by the multi-objective optimization algorithm considering vibration suppression and surface quality optimization;

[0012] S7, closed-loop control of the machining process, after the machining is completed, the workpiece is finally detected, if the surface quality of the workpiece does not meet the requirements, the machining parameters are corrected according to the detection results, and the machining is re-performed until the surface quality of the workpiece meets the requirements.

[0013] Further, the multi-modal sensor fusion monitoring further includes:

[0014] A signal preprocessing module filters, denoises, and extracts features from the collected multi-modal signals to improve the signal-to-noise ratio and correlation.

[0015] A signal fusion algorithm uses a principal component analysis-based signal fusion algorithm to fuse acceleration signals, strain signals, and acoustic emission signals to generate comprehensive vibration feature signals for more accurately reflecting the vibration state during processing.

[0016] Further, the adaptive machining parameter optimization further includes:

[0017] A dynamic parameter adjustment strategy dynamically adjusts the cutting speed, feed rate, and cutting depth based on real-time vibration state and surface quality feedback during processing to adapt to the optimal machining parameters under different workpiece materials and processing conditions.

[0018] Parameter adjustment range limitation sets the adjustment range of machining parameters to avoid unstable processing or machine overload due to excessive parameter adjustment.

[0019] Further, the intelligent vibration prediction and feedback control further includes:

[0020] Deep learning model training uses historical processing data and vibration signals to train a hybrid deep learning model based on convolutional neural networks and long short-term memory networks to improve the accuracy and real-time performance of vibration prediction.

[0021] Real-time feedback control mechanism, when the predicted vibration exceeds the allowable range, the numerical control system adjusts the machining parameters in real time to ensure that the vibration is always within the controllable range.

[0022] Further, the active vibration compensation technology further includes:

[0023] Dynamic control of piezoelectric ceramic actuators dynamically adjusts the output force and frequency of piezoelectric ceramic actuators based on real-time vibration signals to achieve precise vibration compensation.

[0024] Layout optimization of actuators, multiple piezoelectric ceramic actuators are reasonably arranged at key vibration source parts of the machine tool, such as the spindle, tool clamping part, and workbench, to improve the effect of vibration compensation.

[0025] Further, the real-time surface quality monitoring and feedback further includes:

[0026] Calibration of optical surface roughness detection device, calibrate the optical surface roughness detection device before processing to ensure the accuracy of the detection results.

[0027] Surface quality feedback control strategy, dynamically adjusts cutting parameters such as cutting speed and feed rate according to surface roughness detection results to optimize surface quality.

[0028] Further, the multi-objective optimization control further includes:

[0029] Multi-objective optimization algorithm, a hybrid multi-objective optimization algorithm based on genetic algorithm and particle swarm optimization is adopted, considering vibration suppression and surface quality optimization, dynamically adjusting processing parameters;

[0030] Optimization target weight adjustment, dynamically adjusts the target weight of vibration suppression and surface quality optimization according to the priority of the machining task, to realize the optimal control strategy under different machining conditions.

[0031] Further, the machining process closed-loop control further includes:

[0032] Final detection and correction mechanism, after machining is completed, the workpiece is comprehensively detected, including size accuracy, surface roughness and geometric tolerance, etc.; if the detection result does not meet the requirements, the machining parameters are corrected according to the detection result, and the machining is re-performed;

[0033] Machining parameter correction strategy, according to the final detection result, analyzes the problems in the machining process, such as excessive vibration or substandard surface quality, and adjusts the machining parameters, such as increasing the cutting speed or reducing the feed rate, in a targeted manner.

[0034] Further, the method further includes:

[0035] Tool wear monitoring and compensation, in the machining process, the tool wear condition is monitored in real time, the tool wear data is obtained through the tool wear sensor, and the machining parameters are dynamically adjusted according to the tool wear degree, such as increasing the cutting depth or reducing the cutting speed, to compensate for the influence of tool wear on machining quality;

[0036] Tool wear prediction model, using a tool wear prediction model based on machine learning, predicts the remaining service life of the tool, and reminds the operator to replace the tool when the tool approaches the wear limit.

[0037] Further, the method further includes:

[0038] Machine tool state monitoring and early warning, in the machining process, the running state of the numerical control machining center is monitored in real time, including spindle temperature, cooling liquid flow and hydraulic system pressure, etc.; through the state monitoring system, the abnormal state is warned, and timely measures are taken to avoid machine tool failure;

[0039] Periodic maintenance strategy, according to the running time and state monitoring data of the machine tool, the periodic maintenance plan is made, including spindle lubrication, guide rail cleaning and electrical system inspection, etc., to ensure the long-term stable operation of the machine tool.

[0040] Compared with the prior art, the vibration suppression and surface quality control method for cutting parts of the numerical control machining center provided by the application has the following beneficial effects:

[0041] 1、The vibration prediction model based on deep learning and the self-adaptive optimization algorithm are adopted to realize dynamic adjustment and intelligent feedback control of the machining parameters; this technology not only improves the automation level of the machining process, but also effectively reduces the machining errors and surface quality defects caused by vibration, so that the surface roughness and dimensional accuracy of the workpiece are significantly improved, thereby improving the stability of the machining quality; at the same time, the intelligent prediction and feedback mechanism can quickly respond to changes in the machining process, reduce machining interruptions and rework caused by improper vibration suppression, and thus significantly improve the machining efficiency;

[0042] 2、The multi-modal sensor fusion monitoring technology combined with signal preprocessing and fusion algorithm can more accurately reflect the vibration state in the machining process; this multi-dimensional monitoring method provides more abundant data support for intelligent vibration prediction and feedback control, so that the vibration prediction model can more accurately predict the vibration trend and take effective suppression measures in advance; in addition, the active vibration compensation technology is combined with the optimized machine tool structure design to further enhance the anti-vibration performance of the machine tool from the hardware level, reduce the interference of vibration on the machining process, and thus improve the reliability and stability of the machining process;

[0043] 3、The real-time surface quality monitoring and feedback mechanism can dynamically adjust the cutting parameters according to the surface roughness detection results; this real-time optimization not only ensures that the surface quality of the workpiece is always in the best state, but also reduces the material waste and machining time extension caused by surface quality problems; at the same time, the multi-objective optimization control strategy dynamically adjusts the machining parameters by considering vibration suppression and surface quality optimization at the same time, further improves the machining efficiency, reduces energy consumption and tool wear; in addition, the machining process closed-loop control mechanism can correct the machining parameters according to the final detection results, avoiding resource waste caused by unreasonable machining parameters, thereby effectively reducing the production cost. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0045] Figure 1 is a whole flowchart of the present application;

[0046] Figure 2 is a multi-modal sensor fusion monitoring flowchart of the present application;

[0047] Figure 3 is a process closed-loop control flowchart of the present application. DETAILED DESCRIPTION

[0048] In order for those skilled in the art to better understand the technical solutions of the present application, the present application will be further described in detail below with reference to the accompanying drawings.

[0049] As shown in the accompanying drawings Figure 1 to the accompanying drawings Figure 3 as shown:

[0050] The embodiment of the present application provides a vibration suppression and surface quality control method in high-speed precision cutting of a numerical control machining center part, comprising the following steps:

[0051] Multi-modal sensor fusion monitoring, multi-modal sensors including acceleration sensors, strain sensors and acoustic emission sensors are installed at key positions of the numerical control machining center such as the spindle, tool and worktable, to monitor vibration signals, cutting force signals and acoustic emission signals in real time during the machining process;

[0052] The multi-modal sensor fusion monitoring further comprises:

[0053] The signal preprocessing module filters, denoises and extracts features from the collected multi-modal signals to improve the signal-to-noise ratio and correlation of the signals;

[0054] Specifically, in the high-speed precision cutting process of the numerical control machining center, in order to comprehensively monitor the machining state and effectively suppress vibration, the present application installs multi-modal sensors at key positions such as the spindle, tool and worktable, which include acceleration sensors, strain sensors and acoustic emission sensors. The acceleration sensor is used to measure the vibration acceleration signal during the machining process, which can reflect the intensity and frequency characteristics of the vibration; the strain sensor is used to detect the strain of the tool and machine tool structure, thereby indirectly reflecting the size and distribution of the cutting force; the acoustic emission sensor captures the acoustic emission signals generated during the machining process to perceive information such as micro-fracture of the material and tool wear. Through the cooperative work of the three sensors, vibration signals, cutting force signals and acoustic emission signals during the machining process can be obtained in real time, providing rich data support for subsequent vibration suppression and surface quality control.

[0055] In addition, the multi-modal sensor fusion monitoring also includes a signal preprocessing module that filters the collected multi-modal signals to remove high-frequency noise and interference components, improving signal purity. At the same time, a noise reduction algorithm is used to further reduce the impact of background noise on the signal and enhance the signal-to-noise ratio. Finally, feature extraction techniques are used to extract key features related to vibration and processing status from the original signal, such as amplitude, frequency, phase, and cutting force peak, mean, variance, etc., to improve signal relevance and usability. The pre-processed signal can more accurately reflect the actual state of the processing process, providing a high-quality data foundation for subsequent vibration prediction, feedback control, and surface quality monitoring, and helping to achieve more precise vibration suppression and surface quality optimization control.

[0056] Signal fusion algorithm: A signal fusion algorithm based on principal component analysis is used to fuse acceleration signals, strain signals, and acoustic emission signals to generate a comprehensive vibration feature signal for more accurate reflection of the vibration state during processing.

[0057] Adaptive processing parameter optimization: According to the requirements of the processing task, the processing parameters are pre-set, including cutting speed, feed rate, cutting depth, etc., and these parameters are input into the numerical control system. The processing process is controlled in real time by the numerical control system, and the multi-modal signals monitored by the sensors are collected and input into the vibration prediction model based on deep learning along with the processing parameters.

[0058] Adaptive processing parameter optimization also includes:

[0059] Dynamic parameter adjustment strategy: According to the real-time vibration state and surface quality feedback during processing, dynamically adjust the cutting speed, feed rate, and cutting depth to adapt to the optimal processing parameters under different workpiece materials and processing conditions.

[0060] Parameter adjustment range limitation: Set the adjustment range of the processing parameters to avoid instability of the processing process or overload of the machine tool due to excessive parameter adjustment.

[0061] Specifically, in the high-speed precision cutting process of the numerical control machining center, in order to further improve the machining quality and efficiency, the adaptive machining parameter optimization strategy of the present application not only bases on the pre-set machining parameters, but also introduces a dynamic parameter adjustment mechanism and a parameter adjustment range limit. Specifically, the dynamic parameter adjustment strategy can flexibly adjust the key machining parameters such as cutting speed, feed rate and cutting depth according to the real-time monitoring of vibration state and surface quality feedback information in the machining process. This adjustment method makes the machining process automatically adapt to the optimal parameter requirements of different workpiece materials (steel, aluminum alloy, composite materials, etc.) and different machining conditions (rough machining, semi-finish machining, finish machining, etc.), so as to ensure the machining quality, improve the machining efficiency and reduce the tool wear;

[0062] At the same time, in order to avoid the instability of the machining process (vibration intensification, surface quality deterioration) or the overload of the machine tool (spindle power over-limit, feed system failure) caused by the too large parameter adjustment range, the present application also sets the adjustment range limit of the machining parameters. This limit mechanism ensures that the adjustment of the machining parameters is always within a safe and reasonable range, which not only fully utilizes the advantages of dynamic adjustment, but also effectively avoids potential risks, and guarantees the stability and reliability of the machining process. Through this adaptive machining parameter optimization method, the numerical control machining center can realize efficient and stable operation in complex and changeable machining environment, and significantly improve the machining quality and production efficiency.

[0063] Intelligent vibration prediction and feedback control: the vibration prediction model predicts the vibration situation in the subsequent machining process according to the input multi-modal signal and machining parameters, and feeds back the prediction result to the numerical control system; the numerical control system judges whether the vibration is within the allowable range according to the vibration prediction result, if the vibration exceeds the allowable range, the machining parameters are automatically adjusted by the adaptive optimization algorithm to suppress the vibration;

[0064] Specifically, a deep learning-based vibration prediction model is used, which can receive multi-modal sensor collected vibration signals, cutting force signals and acoustic emission signals, and current machining parameters (such as cutting speed, feed rate and cutting depth) as input. By analyzing these input data, the vibration prediction model can predict the vibration situation in the subsequent machining process, including the amplitude, frequency and trend of vibration. The prediction results will be fed back to the numerical control system in real time, and the numerical control system will judge whether the vibration is within the allowable range according to the prediction information. If the prediction result shows that the vibration will exceed the allowable range, the numerical control system will automatically adjust the machining parameters through adaptive optimization algorithm. This adjustment is to reduce the cutting speed to reduce the cutting force, or to change the feed rate to optimize the stability of the cutting process. In this way, intelligent vibration prediction and feedback control can take preventive measures before vibration actually occurs, effectively suppress the generation of vibration, reduce the machining error and surface quality defects caused by vibration, and improve the stability and machining quality of the machining process. This forward-looking control method not only improves the machining efficiency, but also prolongs the tool life and reduces the risk of machine tool failure.

[0065] Intelligent vibration prediction and feedback control also includes:

[0066] Deep learning model training, using historical machining data and vibration signals, trains a hybrid deep learning model based on convolutional neural network and long short-term memory network to improve the accuracy and real-time performance of vibration prediction;

[0067] Specifically, in intelligent vibration prediction and feedback control, deep learning model training is one of the key links; the following is the convolution layer formula in convolutional neural network (CNN):

[0068] Z [l] =W [l] ·A [l-I] +b [l]

[0069] A [l] =ReLU(z [l] )

[0070] Where, Z [l] : linear output of the lth layer. W [l] : convolution kernel weight of the lth layer. -A [l-1] : activation output of the l-1th layer. -b [l] : bias term of the lth layer. ReLU: activation function, used to introduce nonlinearity.

[0071] Real-time feedback control mechanism: when the vibration is predicted to exceed the allowable range, the numerical control system adjusts the machining parameters quickly through the real-time feedback control mechanism to ensure that the vibration is always within the controllable range.

[0072] Active vibration compensation technology: During the machining process, active vibration compensation technology is adopted, through the piezoelectric ceramic actuators installed in the key parts of the machine tool, according to the vibration signal, the opposite vibration is applied to offset the vibration of the machine tool;

[0073] Specifically, in the high-speed precision cutting process of the numerical control machining center, in order to effectively suppress vibration and ensure the machining quality, the present application adopts real-time feedback control mechanism and active vibration compensation technology. The core of the real-time feedback control mechanism is that when the vibration prediction model predicts that the vibration exceeds the allowed range, the numerical control system can quickly respond by adjusting the machining parameters (such as cutting speed, feed rate and cutting depth) to reduce the vibration level. This rapid adjustment ensures that the vibration is always within the controllable range, thereby avoiding machining errors and surface quality defects caused by excessive vibration.

[0074] At the same time, the present application also introduces active vibration compensation technology, through the installation of piezoelectric ceramic actuators in the key parts of the machine tool, these actuators can apply force or motion opposite to the vibration direction according to the real-time monitored vibration signal, thereby offsetting the vibration of the machine tool. This active compensation technology not only can effectively reduce the influence of vibration on the machining process, but also can further improve the stability and surface quality of the machining process. Through the synergistic effect of real-time feedback control mechanism and active vibration compensation technology, the present application can realize efficient and stable machining process under complex and variable machining conditions, significantly improve the machining quality and production efficiency.

[0075] Active vibration compensation technology also includes:

[0076] Dynamic control of piezoelectric ceramic actuators, according to real-time vibration signals, dynamically adjusting the output force and frequency of piezoelectric ceramic actuators to achieve precise vibration compensation;

[0077] Layout optimization of actuators, reasonable layout of multiple piezoelectric ceramic actuators at key vibration source parts of the machine tool, such as main shaft, tool clamping part and workbench, to improve the effect of vibration compensation.

[0078] Real-time surface quality monitoring and feedback, in the machining process, real-time monitoring of workpiece surface quality, through non-contact optical surface roughness detection device to detect the machined workpiece surface, and feedback the detection result to the numerical control system; the numerical control system adjusts the machining parameters according to the surface quality detection result to optimize the workpiece surface quality;

[0079] Specifically, in the high-speed precision cutting process of the numerical control machining center, in order to further improve the vibration suppression effect and workpiece surface quality, the present application adopts dynamic control and layout optimization technology of piezoelectric ceramic actuators, combined with real-time surface quality monitoring and feedback mechanism.

[0080] Firstly, the dynamic control technology of piezoelectric ceramic actuators can dynamically adjust the output force and frequency of the actuators according to real-time vibration signals, thereby achieving precise vibration compensation. This dynamic adjustment method enables the piezoelectric ceramic actuators to quickly respond to vibration changes during the machining process and apply counter-vibration in a timely manner to offset the vibration of the machine tool. For example, when the outer surface of the induction cover is iced, the structural stiffness and mass will change, causing the natural frequency to change. At this time, the pulse voltage generating circuit board sends a pulse electrical signal to the signal conditioning circuit board, which conditions the pulse electrical signal into a standard pulse voltage signal and transmits it to the piezoelectric ceramic. The piezoelectric ceramic generates transient deformation under the excitation of the standard pulse voltage signal, thereby generating a transient pulse excitation force on the induction cover, causing it to vibrate transiently at its natural frequency.

[0081] Secondly, the layout optimization technology of actuators further improves the vibration suppression effect by reasonably arranging multiple piezoelectric ceramic actuators at key vibration source parts of the machine tool, such as the main shaft, tool clamping part, and workbench. Research shows that the layout of piezoelectric actuators has a significant impact on the active control vibration suppression effect. Through simulation example analysis, the optimal layout of piezoelectric actuators adhering to the cantilever beam can be obtained, thereby improving the active control vibration suppression effect.

[0082] In addition, the real-time surface quality monitoring and feedback mechanism detects the surface of the machined workpiece through a non-contact optical surface roughness detection device and feeds back the detection results to the numerical control system. The numerical control system further adjusts the machining parameters based on the surface quality detection results to optimize the surface quality of the workpiece. This real-time monitoring and feedback mechanism can ensure that the surface quality of the workpiece is always in the best state, reducing material waste and prolonging processing time caused by surface quality problems.

[0083] Real-time surface quality monitoring and feedback also includes:

[0084] Calibration of optical surface roughness detection device, the optical surface roughness detection device is calibrated before machining to ensure the accuracy of the detection results;

[0085] Surface quality feedback control strategy, dynamically adjusts the cutting parameters such as cutting speed and feed rate based on the surface roughness detection results to optimize the surface quality.

[0086] Multi-objective optimization control, through multi-objective optimization algorithm, simultaneously considers vibration suppression and surface quality optimization, dynamically adjusts machining parameters to ensure the efficiency of the machining process and the stability of the surface quality of the workpiece;

[0087] Multi-objective optimization control also includes:

[0088] The multi-objective optimization algorithm adopts a hybrid multi-objective optimization algorithm based on genetic algorithm and particle swarm optimization, considering vibration suppression and surface quality optimization, and dynamically adjusting the machining parameters;

[0089] The optimization target weight adjustment dynamically adjusts the target weights of vibration suppression and surface quality optimization according to the priority of the machining task, to achieve the optimal control strategy under different machining conditions.

[0090] The machining process closed-loop control detects the workpiece after machining, and if the surface quality of the workpiece does not meet the requirements, the machining parameters are corrected according to the detection results, and the machining is performed again until the surface quality of the workpiece meets the requirements.

[0091] The machining process closed-loop control further includes:

[0092] The final detection and correction mechanism comprehensively detects the workpiece after machining, including size accuracy, surface roughness and geometric tolerance, etc.; if the detection result does not meet the requirements, the machining parameters are corrected according to the detection results, and the machining is performed again;

[0093] The machining parameter correction strategy analyzes the problems in the machining process according to the final detection results, such as excessive vibration or substandard surface quality, and adjusts the machining parameters accordingly, such as increasing the cutting speed or reducing the feed amount.

[0094] Specifically, the control mechanism includes the final detection and correction mechanism and the machining parameter correction strategy; specifically, the final detection and correction mechanism requires comprehensive detection of the workpiece after machining, covering key indicators such as size accuracy, surface roughness and geometric tolerance; if the detection result fails to meet the predetermined quality standard, the system will correct the machining parameters according to the detection result and restart the machining process until the workpiece quality meets the requirements.

[0095] The machining parameter correction strategy focuses on analyzing the problems in the machining process according to the final detection results, such as excessive vibration or substandard surface quality; in view of these problems, the system will take targeted measures, such as appropriately increasing the cutting speed or reducing the feed amount, to optimize the machining parameters; this closed-loop control mechanism can effectively ensure the stability of the machining quality, reduce the scrap rate caused by unreasonable machining parameters, and improve the production efficiency and economic benefits; through this closed-loop control method, the numerical control machining center can realize efficient and stable machining process under complex and variable machining conditions, significantly improving the machining quality and production efficiency.

[0096] The method further includes:

[0097] Tool wear monitoring and compensation, during the machining process, real-time monitoring of tool wear, through the tool wear sensor to obtain the tool wear data, and according to the tool wear degree dynamic adjustment processing parameters, such as increasing the cutting depth or reducing the cutting speed, to compensate for the influence of tool wear on the processing quality;

[0098] Tool wear prediction model, using machine learning-based tool wear prediction model, predict the remaining service life of the tool, and remind the operator to replace the tool when the tool approaches the wear limit.

[0099] The method further comprises:

[0100] Machine tool state monitoring and early warning, during the machining process, real-time monitoring of the running state of the numerical control machining center, including spindle temperature, cooling liquid flow and hydraulic system pressure, etc.; through the state monitoring system, abnormal state is warned, and timely measures are taken to avoid machine tool failure;

[0101] Regular maintenance strategy, according to the running time and state monitoring data of the machine tool, regular maintenance plan is made, including spindle lubrication, guide rail cleaning and electrical system inspection, etc., to ensure the long-term stable operation of the machine tool.

[0102] Specifically, during the machining process, the system real-time monitors the key running state parameters of the numerical control machining center, such as spindle temperature, cooling liquid flow and hydraulic system pressure, etc. Through the state monitoring system, once the abnormal state is detected, such as the spindle temperature is too high or the cooling liquid flow is insufficient, the system will immediately issue a warning signal. The operator can take timely measures accordingly, such as adjusting the cooling liquid flow or reducing the machining speed, so as to effectively avoid the occurrence of machine tool failure and reduce the risk of production interruption and equipment damage caused by sudden failure.

[0103] In addition, according to the running time and state monitoring data of the machine tool, the system will make a regular maintenance plan; the plan covers key maintenance items such as spindle lubrication, guide rail cleaning and electrical system inspection; regular lubrication of the spindle can reduce friction and prolong the service life of the spindle; regular cleaning of the guide rail can ensure the motion accuracy of the machine tool; regular inspection of the electrical system can prevent electrical failure; through these regular maintenance measures, the service life of the machine tool can be effectively prolonged, the reliability and production efficiency of the equipment can be improved, and the numerical control machining center can always maintain good working condition during long-time operation, so as to realize efficient and stable production process.

[0104] The above only describes certain exemplary embodiments of the present application by way of illustration, and it is needless to say that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present application. Therefore, the above figures and description are illustrative in nature and should not be understood as limiting the scope of protection of the claims of the present application.

Claims

1. A method for vibration suppression and surface quality control during the cutting of parts in a CNC machining center, characterized in that, Includes the following steps: S1. Multimodal sensor fusion monitoring: Multimodal sensors, including acceleration sensors, strain sensors and acoustic emission sensors, are installed on the spindle, tool and worktable of the CNC machining center to monitor vibration signals, cutting force signals and acoustic emission signals in real time during the machining process. S2. Adaptive machining parameter optimization: Based on the machining task requirements, machining parameters, including cutting speed, feed rate, and depth of cut, are preset and input into the CNC system. The CNC system controls the machining process in real time, while simultaneously acquiring multimodal signals monitored by sensors and inputting the signals and machining parameters into a deep learning-based vibration prediction model. S3. Intelligent vibration prediction and feedback control: The vibration prediction model predicts the vibration that will occur during subsequent processing based on the input multimodal signals and processing parameters, and feeds the prediction results back to the CNC system. The CNC system determines whether the vibration is within the allowable range based on the vibration prediction results. If the vibration exceeds the allowable range, the processing parameters are automatically adjusted through an adaptive optimization algorithm to suppress the vibration. S4. Active vibration compensation technology: During the processing, active vibration compensation technology is adopted. Through piezoelectric ceramic actuators installed in key parts of the machine tool, reverse vibration is applied according to the vibration signal to counteract the vibration of the machine tool. S5. Real-time surface quality monitoring and feedback: During the processing, the surface quality of the workpiece is monitored in real time. The surface of the processed workpiece is inspected by a non-contact optical surface roughness detection device, and the detection results are fed back to the CNC system. The CNC system further adjusts the processing parameters based on the surface quality detection results. S6. Multi-objective optimization control: Through a multi-objective optimization algorithm, vibration suppression and surface quality optimization are considered simultaneously, and processing parameters are dynamically adjusted. S7. Closed-loop control of the processing process: After processing is completed, the workpiece is finally inspected. If the surface quality of the workpiece does not meet the requirements, the processing parameters are corrected according to the inspection results, and the processing is repeated until the surface quality of the workpiece meets the requirements.

2. The vibration suppression and surface quality control method for CNC machining center parts cutting according to claim 1, characterized in that, The multimodal sensor fusion monitoring also includes: The signal preprocessing module performs filtering, noise reduction, and feature extraction on the acquired multimodal signals; The signal fusion algorithm, based on principal component analysis, fuses acceleration signals, strain signals, and acoustic emission signals to generate a comprehensive vibration characteristic signal, which reflects the vibration state during the processing.

3. The method for vibration suppression and surface quality control during CNC machining of parts according to claim 1, characterized in that, The adaptive machining parameter optimization also includes: The dynamic parameter adjustment strategy dynamically adjusts the cutting speed, feed rate, and depth of cut based on the real-time vibration state and surface quality feedback during the machining process, in order to adapt to the optimal machining parameters under different workpiece materials and machining conditions. Parameter adjustment range limit: Set the adjustment range of processing parameters.

4. The method for vibration suppression and surface quality control during CNC machining center part cutting according to claim 1, characterized in that, The intelligent vibration prediction and feedback control also includes: Deep learning model training uses historical processing data and vibration signals to train a hybrid deep learning model based on convolutional neural networks and long short-term memory networks. The real-time feedback control mechanism allows the CNC system to quickly adjust machining parameters when vibration is predicted to exceed the allowable range, ensuring that the vibration remains within a controllable range.

5. The method for vibration suppression and surface quality control during CNC machining of parts according to claim 1, characterized in that, The active vibration compensation technology also includes: Dynamic control of piezoelectric ceramic actuators: Based on real-time vibration signals, the output force and frequency of the piezoelectric ceramic actuators are dynamically adjusted. The actuator layout is optimized by rationally arranging multiple piezoelectric ceramic actuators at key vibration sources of the machine tool, such as the spindle, tool clamping area, and worktable.

6. The method for vibration suppression and surface quality control during the cutting of parts in a CNC machining center according to claim 1, characterized in that, The real-time surface quality monitoring and feedback also includes: Calibration of the optical surface roughness detection device: The optical surface roughness detection device is calibrated before processing. The surface quality feedback control strategy dynamically adjusts the cutting parameters based on the surface roughness detection results.

7. The method for vibration suppression and surface quality control during CNC machining center part cutting according to claim 1, characterized in that, The multi-objective optimization control also includes: The multi-objective optimization algorithm adopts a hybrid multi-objective optimization algorithm based on genetic algorithm and particle swarm optimization, which simultaneously considers vibration suppression and surface quality optimization, and dynamically adjusts the processing parameters; The target weights are optimized by dynamically adjusting them based on the priority of the processing tasks, focusing on vibration suppression and surface quality optimization.

8. The method for vibration suppression and surface quality control during CNC machining center part cutting according to claim 1, characterized in that, The closed-loop control of the processing procedure also includes: The final inspection and correction mechanism involves a comprehensive inspection of the workpiece after processing, including dimensional accuracy, surface roughness, and geometric tolerances. If the inspection results do not meet the requirements, the processing parameters are corrected based on the inspection results, and the processing is repeated. The processing parameter correction strategy analyzes problems in the processing process based on the final test results, such as excessive vibration or substandard surface quality, and adjusts the processing parameters accordingly.

9. The method for vibration suppression and surface quality control during the cutting of parts in a CNC machining center according to claim 1, characterized in that, The method further includes: Tool wear monitoring and compensation involves real-time monitoring of tool wear during machining, acquiring tool wear data through a tool wear sensor, and dynamically adjusting machining parameters based on the degree of tool wear. The tool wear prediction model uses a machine learning-based tool wear prediction model to predict the remaining service life of the tool and remind the operator to replace the tool when it is close to the wear limit.

10. The method for vibration suppression and surface quality control during the cutting of parts in a CNC machining center according to claim 1, characterized in that, The method further includes: Machine tool condition monitoring and early warning: During the machining process, the operating status of the CNC machining center is monitored in real time; the condition monitoring system provides early warning of abnormal conditions and takes timely measures to avoid machine tool failure. A regular maintenance strategy is implemented, which involves developing a regular maintenance plan based on the machine tool's operating time and status monitoring data.

Images