Multi-axis linkage numerical control machine tool cooperative control method and system

Abstract

The invention provides a multi-axis linkage numerical control machine tool cooperative control method and system, and belongs to the technical field of numerical control machine tool control, and the method comprises the steps: collecting the motion state, processing load and external environment information of each axis in real time, processing the information through a multi-modal information fusion model, calculating target motion parameters through a self-adaptive control algorithm, and calculating the target motion parameters; and each shaft is driven to move, and adjustment is carried out by adopting a compensation control strategy based on model prediction by monitoring the deviation between an actual motion parameter and a target parameter. The system is composed of an information acquisition module, a fusion processing module, a control parameter calculation module, a drive control module, a monitoring module, a compensation module and the like. The system can comprehensively reflect the working state of the machine tool, accurately control the movement of each axis, enhance the anti-interference capability of the system, improve the collaboration of each axis, and effectively improve the machining precision, the surface quality and the production efficiency.

Description

Technical Field

[0001] This invention relates to the field of CNC machine tool control technology, specifically to a collaborative control method and system for multi-axis linkage CNC machine tools. Background Technology

[0002] In modern manufacturing, multi-axis CNC machine tools are widely used in the machining of complex parts, such as aerospace components and precision molds. The collaborative control accuracy and efficiency of multi-axis CNC machine tools directly affect the machining quality and production cycle of parts. However, existing collaborative control methods for multi-axis CNC machine tools have many problems. On the one hand, traditional control methods mostly use fixed control parameters and strategies, which cannot adaptively adjust according to changes in actual working conditions during machining, resulting in difficulty in guaranteeing machining accuracy, especially when machining parts with complex shapes and high precision requirements, where machining errors are large. On the other hand, the coordination between axes is poor, and motion incoordination is prone to occur during multi-axis linkage, leading to a decrease in machined surface quality and low machining efficiency. In addition, existing control methods lack effective countermeasures for external disturbances, such as changes in cutting force and fluctuations in ambient temperature, further affecting the machining performance of CNC machine tools. Therefore, there is an urgent need to propose a new collaborative control method and system for multi-axis CNC machine tools to improve the collaborative control accuracy and efficiency of multi-axis CNC machine tools. Summary of the Invention

[0003] This invention addresses the problems of low precision, poor efficiency, and insufficient response to external interference in existing multi-axis linkage CNC machine tools, as mentioned in the background art. It provides a multi-axis linkage CNC machine tool collaborative control method and system to achieve high-precision and high-efficiency multi-axis linkage machining.

[0004] The specific technical solution is as follows:

[0005] A collaborative control method for multi-axis linkage CNC machine tools includes the following steps:

[0006] S1: Real-time acquisition of motion status information, machining load information, and external environment information of each axis of a multi-axis linkage CNC machine tool; the motion status information includes the position, velocity, and acceleration of each axis; the machining load information includes the magnitude and direction of the cutting force; the external environment information includes ambient temperature and vibration conditions;

[0007] S2: Input the collected information into the preset multimodal information fusion model, and use the multimodal information fusion model to extract and fuse features of motion state information, processing load information and external environment information of each axis to obtain a comprehensive state feature vector;

[0008] S3: Based on the comprehensive state feature vector, the target motion parameters of each axis are calculated using an adaptive control algorithm. The adaptive control algorithm can adjust the control parameters in real time according to the changes in the comprehensive state feature vector.

[0009] S4: Send the target motion parameters of each axis to the corresponding axis drive controller, and drive each axis to move according to the target motion parameters;

[0010] S5: Monitor the actual motion parameters of each axis in real time, and compare the actual motion parameters with the target motion parameters to obtain the motion parameter deviation;

[0011] S6: Based on the motion parameter deviation, a model-based prediction compensation control strategy is adopted to compensate and adjust the motion of each axis. The model-based prediction compensation control strategy establishes a prediction model for the motion of each axis, predicts the motion state of each axis in the future, and generates compensation control commands based on the prediction results and motion parameter deviation to adjust the motion of each axis.

[0012] The above-mentioned multi-axis linkage CNC machine tool collaborative control method, wherein the multimodal information fusion model adopts a structure combining convolutional neural network and long short-term memory network, which is used to perform feature extraction and time series analysis on the collected information.

[0013] The above-mentioned multi-axis linkage CNC machine tool collaborative control method, wherein the adaptive control algorithm adopts a reinforcement learning-based control algorithm, using the comprehensive state feature vector as the environmental state input and the motion control effect of each axis as the reward signal for training and optimization.

[0014] In the above-mentioned multi-axis linkage CNC machine tool collaborative control method, the model prediction-based compensation control strategy uses an autoregressive integrated moving average model to establish a prediction model for the motion of each axis.

[0015] In the above-mentioned multi-axis linkage CNC machine tool collaborative control method, in step S1, a grating ruler is used to collect the position information of each axis, an encoder is used to collect the speed and acceleration information of each axis, a force sensor is used to collect the machining load information, a temperature sensor is used to collect the ambient temperature information, and a vibration sensor is used to collect the vibration information.

[0016] The present invention also provides a multi-axis linkage CNC machine tool collaborative control system for implementing the above-mentioned multi-axis linkage CNC machine tool collaborative control method, the system comprising:

[0017] The information acquisition module is used to collect motion status information, machining load information, and external environmental information of each axis of a multi-axis CNC machine tool in real time.

[0018] The information fusion processing module is used to input the collected information into a preset multimodal information fusion model. The multimodal information fusion model is used to extract and fuse features of motion state information, machining load information and external environment information of each axis to obtain a comprehensive state feature vector.

[0019] The control parameter calculation module is used to calculate the target motion parameters of each axis based on the comprehensive state feature vector using an adaptive control algorithm. The adaptive control algorithm can adjust the control parameters in real time according to the changes in the comprehensive state feature vector.

[0020] The drive control module is used to send the target motion parameters of each axis to the corresponding axis drive controller, and drive each axis to move according to the target motion parameters;

[0021] The monitoring and compensation module is used to monitor the actual motion parameters of each axis in real time, compare the actual motion parameters with the target motion parameters to obtain the motion parameter deviation, and use a model prediction-based compensation control strategy to compensate and adjust the motion of each axis based on the motion parameter deviation. The model prediction-based compensation control strategy establishes a prediction model of the motion of each axis, predicts the motion state of each axis in the future, and generates compensation control commands based on the prediction results and motion parameter deviation to adjust the motion of each axis.

[0022] The aforementioned multi-axis linkage CNC machine tool collaborative control system includes an information acquisition module comprising a grating ruler, an encoder, a force sensor, a temperature sensor, and a vibration sensor.

[0023] In the aforementioned multi-axis linkage CNC machine tool collaborative control system, the multimodal information fusion model in the information fusion processing module adopts a structure combining convolutional neural networks and long short-term memory networks.

[0024] In the aforementioned multi-axis linkage CNC machine tool collaborative control system, the adaptive control algorithm in the control parameter calculation module adopts a reinforcement learning-based control algorithm.

[0025] In the aforementioned multi-axis linkage CNC machine tool collaborative control system, the model prediction-based compensation control strategy in the monitoring and compensation module uses an autoregressive integrated moving average model to establish a prediction model for the motion of each axis.

[0026] The present invention has the following beneficial effects:

[0027] 1. This invention, by collecting various information from each axis of a multi-axis CNC machine tool in real time and performing multi-modal information fusion processing, can comprehensively and accurately reflect the actual working status of the CNC machine tool, providing a reliable basis for subsequent precise control.

[0028] 2. An adaptive control algorithm is used to calculate the target motion parameters of each axis, which can adjust the control parameters in real time according to changes in actual working conditions, making the motion control of each axis more precise and effectively improving the machining accuracy.

[0029] 3. The model-based prediction-based compensation control strategy can predict the future motion state of each axis and make timely compensation adjustments based on the deviation, which enhances the system's ability to cope with external disturbances and further ensures machining accuracy and stability.

[0030] 4. The collaborative control method and system of the present invention improve the coordination between axes, making multi-axis linkage more coordinated, thereby improving the surface quality and processing efficiency. Attached Figure Description

[0031] Figure 1 This is a flowchart of a multi-axis linkage CNC machine tool collaborative control method provided in an embodiment of the present invention;

[0032] Figure 2 The machining accuracy improvement curve of the multi-axis linkage CNC machine tool collaborative control method provided in the embodiments of the present invention;

[0033] Figure 3 A curve showing the reduction in collaborative response time of the multi-axis linkage CNC machine tool collaborative control method provided in this embodiment of the invention;

[0034] Figure 4 The dynamic collaborative compensation effect curve of the multi-axis linkage CNC machine tool collaborative control method provided in the embodiments of the present invention is shown in the figure.

[0035] Figure 5 The multi-axis coupling optimization effect curve of the multi-axis linkage CNC machine tool collaborative control method provided in the embodiments of the present invention is shown in the figure. Detailed Implementation

[0036] The technical solution of the present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0037] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual images. They should not be construed as limiting the scope of this patent. To better illustrate the embodiments of the present invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions of the product. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0038] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "inner," and "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present patent. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0039] In the description of this invention, unless otherwise explicitly specified and limited, the term "connection" or similar designation indicating a connection between components should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral part; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can refer to the internal communication between two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0040] Example: Refer to Figures 1-5 As shown, where:

[0041] Figure 1 The flowchart of the collaborative control method for multi-axis linkage CNC machine tools is demonstrated;

[0042] Figure 2 The curves showing the change of machining accuracy (such as surface roughness) with the number of machining operations are presented, and the differences between traditional PID control and the control method of the present invention are compared. As can be seen from the figure, after adopting the cooperative control method of the present invention, the surface roughness error is significantly reduced and the machining accuracy is significantly improved.

[0043] Figure 3 The curves showing the change of cooperative response time with the improvement of control method are presented. As can be seen from the figure, the cooperative response time is significantly shortened from the traditional control method to the control method of this invention, thus improving the system's response speed.

[0044] Figure 4 The curves showing the deviation between the actual motion parameters and the target motion parameters over time were displayed, and a comparison was made before and after the addition of dynamic collaborative compensation. As can be seen from the figure, the deviation of motion parameters was significantly reduced after the addition of dynamic collaborative compensation, thus improving the control accuracy.

[0045] Figure 5The figure shows the change curves of the synchronization index (such as position synchronization error) of the motion parameters of each axis during multi-axis linkage. As can be seen from the figure, after adopting the control method of the present invention, the synchronization of the motion parameters of each axis is significantly improved, and the machining error caused by asynchronous motion is reduced.

[0046] This embodiment provides a collaborative control method for multi-axis linkage CNC machine tools, including the following steps:

[0047] S1: Real-time acquisition of motion status information, machining load information, and external environment information of each axis of a multi-axis linkage CNC machine tool; motion status information includes the position, speed, and acceleration of each axis; machining load information includes the magnitude and direction of the cutting force; external environment information includes ambient temperature and vibration conditions.

[0048] S2: Input the collected information into the preset multimodal information fusion model. The multimodal information fusion model extracts and fuses the motion state information, processing load information and external environment information of each axis to obtain a comprehensive state feature vector.

[0049] S3: Based on the comprehensive state feature vector, the target motion parameters of each axis are calculated using an adaptive control algorithm. The adaptive control algorithm can adjust the control parameters in real time according to the changes in the comprehensive state feature vector.

[0050] S4: Send the target motion parameters of each axis to the corresponding axis drive controller, and drive each axis to move according to the target motion parameters;

[0051] S5: Monitor the actual motion parameters of each axis in real time, and compare the actual motion parameters with the target motion parameters to obtain the motion parameter deviation;

[0052] S6: Based on the deviation of motion parameters, a model-based prediction compensation control strategy is adopted to compensate and adjust the motion of each axis. The model-based prediction compensation control strategy establishes a prediction model of the motion of each axis, predicts the motion state of each axis in the future, and generates compensation control commands based on the prediction results and the deviation of motion parameters to adjust the motion of each axis.

[0053] By adopting the above technical solution, the motion, machining load and external environment information of each axis of the multi-axis linkage CNC machine tool are comprehensively collected. Combined with multi-modal information fusion, adaptive control algorithm, motion monitoring and model prediction-based compensation control, the machine tool's working status can be accurately perceived and dynamically controlled. This can effectively improve the coordination of multi-axis linkage, improve machining accuracy and efficiency, and enhance the system's adaptability to external interference.

[0054] The compensation control command is calculated using the multi-axis collaborative dynamic error compensation equation, which is as follows:

[0055]

[0056] in:

[0057] Δu(t): Compensation control command used to adjust the motion parameters of each axis;

[0058] e(t): The deviation of the motion parameters at the current moment (the difference between the actual value and the target value);

[0059] K p ,K i ,K d The proportional, integral, and derivative gain coefficients of the PID controller are used to handle the current deviation.

[0060] α: Coordination weighting coefficient, used to adjust the intensity of multi-axis coordination compensation;

[0061] w i The dynamic weight of the i-th axis reflects the degree of influence of that axis on the overall cooperative error;

[0062] The prediction deviation of the i-th axis based on the model prediction in the future time interval Δt;

[0063] n: The number of linkage axes;

[0064] τ is the integration variable, representing the time interval from 0 to the current time t, used to calculate the cumulative value of the motion parameter deviation e(t) over time; in the integration term In PID control, the cumulative deviation within the τ interval reflects the historical accumulation effect of system deviation and is the core variable of the integral term, used to eliminate static error. The role of τ: This parameter mainly acts on the integral term of the compensation equation, together with the proportional and derivative terms, to form the traditional PID control part, and combined with the predicted deviation term to achieve dynamic compensation. By calculating the integral of the deviation within the τ interval, the compensation control command Δu(t) can comprehensively consider the current deviation, the rate of change of deviation, and the historical deviation accumulation, thereby improving the steady-state accuracy of multi-axis linkage control.

[0065] The derivation process is as follows:

[0066] This equation is derived by introducing multi-axis coordination terms and model prediction terms based on traditional PID control:

[0067] 1. Traditional PID section:

[0068]

[0069] Used to handle current and historical discrepancies.

[0070] 2. Introduce multi-axis collaborative prediction terms:

[0071]

[0072] This part achieves multi-axis collaborative compensation by predicting future deviations and weighted summation.

[0073] 3. Consolidate to obtain total compensation instruction:

[0074] Δu(t)=uPID(t)+u predict (t).

[0075] Example:

[0076] 1. Real-time deviation calculation: The actual position and velocity of each axis are collected in real time and compared with the target value to obtain the current deviation e(t).

[0077] 2. Model Prediction: The ARIMA model is used to predict the deviations of each axis over a future time interval Δt.

[0078] 3. Dynamic weight allocation: Based on the motion state of each axis (such as acceleration, load), w is dynamically adjusted. i (For example: the higher load axis has a greater weight).

[0079] 4. Generate compensation command: Calculate the final compensation amount Δu(t) by weighted summing of the current deviation, integral / derivative term and predicted deviation, and send it to the drive controller.

[0080] Technical effect

[0081] 1. Dynamic collaborative compensation: By predicting future deviations and weighted fusion, the coordination of multi-axis linkage is improved, which solves the lag problem of traditional PID control that only relies on the current deviation.

[0082] 2. Multi-axis coupling optimization: weighting coefficient w i The synergy term α significantly improves the coordination of multi-axis linkage and reduces machining errors caused by asynchronous motion.

[0083] 3. Anti-interference capability: Combined with the prediction model, it compensates for external disturbances (such as sudden changes in cutting force) in advance.

[0084] Improve system robustness.

[0085] Working principle and process

[0086] 1. Data Acquisition: Sensors collect real-time data on the status of each axis (position, speed, load) and environmental data (temperature, vibration);

[0087] 2. Deviation Calculation and Prediction: Calculate the current deviation e(t) and predict the future deviation ê using the ARIMA model. i (t+Δt);

[0088] 3. Dynamic weight adjustment: Update w based on load and motion status. i For example: wi = F i / ∑F i F i The cutting force is the cutting force on the i-th axis.

[0089] 4. Compensation command generation: The PID output and prediction deviation are weighted and fused to generate a compensation command Δu(t), which drives the adjustment motion of each axis.

[0090] This multi-axis collaborative dynamic error compensation equation combines the long-term deviation predicted by the model with the real-time response of the PID controller, overcoming the limitations of traditional control methods; it can adaptively adjust w according to the operating conditions. i The addition of α enables dynamic optimization of multi-axis linkage, a solution not addressed in existing technologies. The newly added cooperative term α·∑wi·êi(t+Δt) in the equation is an original design, directly related to multi-axis coordination and predictive control.

[0091] Specifically, in this embodiment, the multimodal information fusion model adopts a structure combining convolutional neural networks and long short-term memory networks to perform feature extraction and time series analysis on the collected information.

[0092] By adopting the above technical solution, the multimodal information fusion model uses a structure that combines convolutional neural networks and long short-term memory networks. It can efficiently extract features and perform time series analysis on the collected information, mine the deep features and change patterns of the data, and provide more accurate comprehensive state feature vectors for subsequent control, thereby ensuring the accuracy of control decisions and improving control precision.

[0093] Specifically, in this embodiment, the adaptive control algorithm adopts a reinforcement learning-based control algorithm, using the comprehensive state feature vector as the environmental state input and the motion control effect of each axis as the reward signal for training and optimization.

[0094] By adopting the above technical solution, an adaptive control algorithm based on reinforcement learning is trained and optimized based on the comprehensive state feature vector and motion control effect. It can dynamically adjust the control parameters according to the real-time working conditions of the machine tool, so that the calculation of the target motion parameters of each axis is more in line with the actual needs, improve the accuracy and response speed of motion control of each axis, and ensure the machining quality.

[0095] Specifically, in this embodiment, the compensation control strategy based on model prediction uses an autoregressive integrated moving average model to establish a prediction model for the motion of each axis.

[0096] The above technical solution uses an autoregressive integrated moving average model to establish a motion prediction model for each axis. Based on historical data, it predicts the future motion state and combines motion parameter deviations for compensation and adjustment. This enables forward-looking control of the motion of each axis, timely correction of motion deviations, reduction of external interference, and ensures the stability of machine tool motion and machining accuracy.

[0097] Specifically, in this embodiment, in step S1, a grating ruler is used to collect the position information of each axis, an encoder is used to collect the speed and acceleration information of each axis, a force sensor is used to collect the machining load information, a temperature sensor is used to collect the ambient temperature information, and a vibration sensor is used to collect the vibration information.

[0098] By adopting the above technical solution, the sensors used for each type of information acquisition are clearly defined, ensuring the accuracy and reliability of information acquisition, providing a solid data foundation for the entire collaborative control, ensuring that the subsequent processing and control strategies based on this information can be effectively implemented, and thus guaranteeing the operation and processing effect of the machine tool.

[0099] This embodiment also provides a multi-axis linkage CNC machine tool collaborative control system for implementing the above-mentioned multi-axis linkage CNC machine tool collaborative control method. The system includes: an information acquisition module, an information fusion processing module, a control parameter calculation module, a drive control module, and a monitoring and compensation module, wherein:

[0100] The information acquisition module is used to collect motion status information, machining load information, and external environmental information of each axis of a multi-axis CNC machine tool in real time.

[0101] The information fusion processing module is used to input the collected information into the preset multimodal information fusion model. Through the multimodal information fusion model, the motion state information, machining load information and external environment information of each axis are extracted and fused to obtain a comprehensive state feature vector.

[0102] The control parameter calculation module is used to calculate the target motion parameters of each axis based on the comprehensive state feature vector and the adaptive control algorithm. The adaptive control algorithm can adjust the control parameters in real time according to the changes in the comprehensive state feature vector.

[0103] The drive control module is used to send the target motion parameters of each axis to the corresponding axis drive controller, and drive each axis to move according to the target motion parameters;

[0104] The monitoring and compensation module is used to monitor the actual motion parameters of each axis in real time, compare the actual motion parameters with the target motion parameters to obtain the motion parameter deviation, and use a model prediction-based compensation control strategy to compensate and adjust the motion of each axis based on the motion parameter deviation. The model prediction-based compensation control strategy establishes a prediction model of the motion of each axis, predicts the motion state of each axis in the future, and generates compensation control commands based on the prediction results and motion parameter deviation to adjust the motion of each axis.

[0105] By adopting the above technical solution, the various modules of the system work together to achieve a collaborative control method. Information acquisition provides data, fusion processing extracts effective information, control parameters are calculated to generate target parameters, drive control to execute motion, and monitoring and compensation ensure motion accuracy. Overall, the system integration and collaboration are improved, and high-precision, high-efficiency multi-axis linkage machining is achieved.

[0106] Specifically, in this embodiment, the information acquisition module includes a grating ruler, an encoder, a force sensor, a temperature sensor, and a vibration sensor.

[0107] By adopting the above technical solution, the specific sensor composition of the information acquisition module is determined to ensure that the acquired information is comprehensive, accurate, and stable. This enables the system to obtain reliable machine tool operating status data in real time, providing a guarantee for stable system operation and precise control, and avoiding control errors caused by information acquisition problems.

[0108] Specifically, in this embodiment, the multimodal information fusion model in the information fusion processing module adopts a structure that combines convolutional neural networks and long short-term memory networks.

[0109] By adopting the above technical solution, the information fusion processing module uses a specific model structure, which can perform deep fusion processing of multi-source information, improve information utilization, provide better data support for control parameter calculation, thereby optimizing the motion control of each axis and improving processing quality and efficiency.

[0110] Specifically, in this embodiment, the adaptive control algorithm in the control parameter calculation module adopts a reinforcement learning-based control algorithm.

[0111] By adopting the above technical solution, the control parameter calculation module uses a reinforcement learning-based algorithm, which can adaptively adjust the control parameters according to the actual situation of the machine tool, realize precise dynamic control of the motion of each axis, enhance the system's adaptability to complex working conditions, and ensure machining accuracy and efficiency.

[0112] Specifically, in this embodiment, the model-based compensation control strategy in the monitoring and compensation module uses an autoregressive integrated moving average model to establish a predictive model for the motion of each axis.

[0113] By adopting the above technical solution, the monitoring and compensation module uses a specific prediction model to predict and compensate for the motion of each axis in advance, reduce the accumulation of motion errors, improve system stability and reliability, and ensure high precision and high quality in multi-axis linkage machining processes.

[0114] In summary, the specific implementation methods of the multi-axis linkage CNC machine tool collaborative control method and each module in the system provided in this embodiment are as follows:

[0115] 1. Specific implementation of the information collection module

[0116] The information acquisition module employs multiple sensors to collect data. For the motion status information of each axis, a high-precision optical scale is used to acquire position information, and an encoder is used to acquire speed and acceleration information. Machining load information is acquired using a force sensor installed between the tool and the workpiece to obtain the magnitude and direction of the cutting force. For external environmental information, ambient temperature is measured by a temperature sensor, and vibration is monitored by a vibration sensor. These sensors transmit the acquired information to the information fusion processing module in real time.

[0117] 2. Specific Implementation of the Information Fusion Processing Module

[0118] The multimodal information fusion model employs a structure combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory Networks (LSTMs) from deep learning. CNNs are used to extract features from the collected information, capturing local features; LSTMs are used to process time-series information, learning the changing patterns of information over time. The motion state information of each axis, processing load information, and external environment information are normalized and then input into the multimodal information fusion model. After computation and processing by the model, a comprehensive state feature vector is output.

[0119] 3. Specific implementation of the control parameter calculation module

[0120] The adaptive control algorithm employs a reinforcement learning-based approach. During training, the comprehensive state feature vector serves as the environmental state input, while the motion control performance of each axis is used as the reward signal. Through continuous interaction and learning with the environment, the control parameters are optimized. Once the comprehensive state feature vector is obtained, the adaptive control algorithm calculates the target motion parameters for each axis, such as target position, target velocity, and target acceleration, based on the current state and the trained strategy.

[0121] 4. Specific implementation of the drive control module

[0122] The drive control module encodes and converts the target motion parameters for each axis obtained from the control parameter calculation module, and sends them to the corresponding axis drive controller via fieldbus or dedicated communication interface. The axis drive controller then drives servo motors and other actuators according to the received target motion parameters, causing each axis to move according to the target motion parameters.

[0123] 5. Specific implementation of the monitoring and compensation module

[0124] The monitoring and compensation module collects the actual motion parameters of each axis in real time and compares them with the target motion parameters to calculate the motion parameter deviation. The model-based prediction compensation control strategy uses an autoregressive integrated moving average (ARIMA) model to establish a predictive model for the motion of each axis. The prediction model is trained and optimized based on historical motion parameter data to accurately predict the motion state of each axis over a future period. Based on the prediction results and motion parameter deviations, the controller generates compensation control commands and sends them to the axis drive controller to compensate and adjust the motion of each axis.

[0125] The above are merely preferred embodiments of the present invention and are not intended to limit the implementation methods and protection scope of the present invention. Those skilled in the art should recognize that any equivalent substitutions and obvious changes made based on the description and illustrations of the present invention should be included within the protection scope of the present invention.

Claims

1. A collaborative control method for a multi-axis linkage CNC machine tool, characterized in that, Includes the following steps: S1: Real-time acquisition of motion status information, machining load information, and external environment information of each axis of a multi-axis linkage CNC machine tool; the motion status information includes the position, velocity, and acceleration of each axis; the machining load information includes the magnitude and direction of the cutting force; the external environment information includes ambient temperature and vibration conditions; S2: Input the collected information into the preset multimodal information fusion model, and use the multimodal information fusion model to extract and fuse features of motion state information, processing load information and external environment information of each axis to obtain a comprehensive state feature vector; S3: Based on the comprehensive state feature vector, the target motion parameters of each axis are calculated using an adaptive control algorithm. The adaptive control algorithm can adjust the control parameters in real time according to the changes in the comprehensive state feature vector. S4: Send the target motion parameters of each axis to the corresponding axis drive controller, and drive each axis to move according to the target motion parameters; S5: Monitor the actual motion parameters of each axis in real time, and compare the actual motion parameters with the target motion parameters to obtain the motion parameter deviation; S6: Based on the motion parameter deviation, a model-based prediction compensation control strategy is adopted to compensate and adjust the motion of each axis. The model-based prediction compensation control strategy establishes a prediction model for the motion of each axis, predicts the motion state of each axis in the future, and generates compensation control commands based on the prediction results and motion parameter deviation to adjust the motion of each axis.

2. The multi-axis linkage CNC machine tool collaborative control method according to claim 1, characterized in that, The multimodal information fusion model adopts a structure combining convolutional neural networks and long short-term memory networks to perform feature extraction and time series analysis on the collected information.

3. The multi-axis linkage CNC machine tool collaborative control method according to claim 1, characterized in that, The adaptive control algorithm adopts a reinforcement learning-based control algorithm, using the comprehensive state feature vector as the environmental state input and the motion control effect of each axis as the reward signal for training and optimization.

4. The multi-axis linkage CNC machine tool collaborative control method according to claim 1, characterized in that, The model-based compensation control strategy uses an autoregressive integrated moving average model to establish a predictive model for the motion of each axis.

5. The multi-axis linkage CNC machine tool collaborative control method according to claim 1, characterized in that, In step S1, a grating ruler is used to collect position information of each axis, an encoder is used to collect speed and acceleration information of each axis, a force sensor is used to collect machining load information, a temperature sensor is used to collect ambient temperature information, and a vibration sensor is used to collect vibration information.

6. A collaborative control system for a multi-axis linkage CNC machine tool, characterized in that, The system is used to implement the multi-axis linkage CNC machine tool collaborative control method according to any one of claims 1-5, the system comprising: The information acquisition module is used to collect motion status information, machining load information, and external environmental information of each axis of a multi-axis CNC machine tool in real time. The information fusion processing module is used to input the collected information into a preset multimodal information fusion model. The multimodal information fusion model is used to extract and fuse features of motion state information, machining load information and external environment information of each axis to obtain a comprehensive state feature vector. The control parameter calculation module is used to calculate the target motion parameters of each axis based on the comprehensive state feature vector using an adaptive control algorithm. The adaptive control algorithm can adjust the control parameters in real time according to the changes in the comprehensive state feature vector. The drive control module is used to send the target motion parameters of each axis to the corresponding axis drive controller, and drive each axis to move according to the target motion parameters; The monitoring and compensation module is used to monitor the actual motion parameters of each axis in real time, compare the actual motion parameters with the target motion parameters to obtain the motion parameter deviation, and use a model prediction-based compensation control strategy to compensate and adjust the motion of each axis based on the motion parameter deviation. The model prediction-based compensation control strategy establishes a prediction model of the motion of each axis, predicts the motion state of each axis in the future, and generates compensation control commands based on the prediction results and motion parameter deviation to adjust the motion of each axis.

7. The multi-axis linkage CNC machine tool collaborative control system according to claim 6, characterized in that, The information acquisition module includes a grating ruler, an encoder, a force sensor, a temperature sensor, and a vibration sensor.

8. The multi-axis linkage CNC machine tool collaborative control system according to claim 6, characterized in that, The multimodal information fusion model in the information fusion processing module adopts a structure that combines convolutional neural networks and long short-term memory networks.

9. The multi-axis linkage CNC machine tool collaborative control system according to claim 6, characterized in that, The adaptive control algorithm in the control parameter calculation module adopts a reinforcement learning-based control algorithm.

10. The multi-axis linkage CNC machine tool collaborative control system according to claim 6, characterized in that, The model-based compensation control strategy in the monitoring and compensation module uses an autoregressive integrated moving average model to establish a predictive model for the motion of each axis.

Images