Intelligent brake system of surrounding type numerical control rotary table based on AI predictive control

Abstract

The invention provides a surrounding type numerical control rotary table intelligent braking system based on AI predictive control, and belongs to the technical field of intelligent manufacturing and numerical control. The problems that an existing numerical control rotary table braking system is lagged in response, lacks intelligent prediction and self-adaptive capacity, and is insufficient in control precision and attenuated in long-term performance are solved. The surrounding type numerical control rotary table intelligent brake system based on AI predictive control comprises a state acquisition module, an AI predictive module, a pressure control module, a surrounding type brake execution structure and a feedback correction module, an AI predictive mechanism and a self-correction feedback loop are introduced, intelligence, self-adaption and high responsiveness of brake control are achieved, and the brake control precision is improved. The positioning precision, the braking stability and the overall energy efficiency level of the numerical control rotary table are improved, and the numerical control rotary table has the advantages that the response speed is remarkably increased, the positioning precision is high, the self-adaptive capacity is high, the braking process is stable and the intelligent degree is high.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent manufacturing and numerical control technology, and relates to an intelligent braking system for an enveloping numerically controlled turntable based on AI predictive control. Background Art

[0002] In high-precision CNC equipment (such as five-axis machining centers), the CNC turntable is a core functional component. Its braking performance (response speed, positioning accuracy, and stability) directly affects machining quality. Currently, mainstream CNC turntable braking systems rely primarily on mechanical clamping, hydraulic / pneumatic piston clamping, or magnetic powder braking. Hydraulically / pneumatically driven brakes or chuck structures (mechanical brake structures with similar "encircling" characteristics) are relatively common solutions, but the following issues still exist: Response lag: Existing systems often rely on preset thresholds (such as position or speed thresholds) to trigger braking. When the turntable's operating status (such as speed or load) changes suddenly, they are unable to predict and initiate braking action in a timely manner, resulting in delayed braking response and long braking distance, affecting machining accuracy and equipment safety. Lack of intelligent prediction and adaptive capabilities: Traditional control is based on real-time status judgment and lacks effective prediction of the turntable's future motion trends (such as overshoot and load changes). This makes it difficult to implement early intervention in braking action and dynamic optimization and adjustment of clamping force. Control parameters are fixed and cannot adapt to different working conditions (such as high speed, low speed, heavy load, and light load). Insufficient control accuracy: Under high-speed rotation or sudden load changes, the existing system has difficulty in accurately controlling the braking process, which can easily cause overshoot or undershoot, resulting in increased positioning errors. Long-term performance degradation: Existing systems generally lack self-learning and self-correction mechanisms, and are unable to effectively compensate for performance drift caused by wear of the brake mechanism (such as friction pads), changes in oil properties, and environmental factors (such as temperature). As a result, the system's braking performance deteriorates over time, affecting the long-term operational stability of the equipment.

[0003] Therefore, it is of great significance to design an intelligent braking system for an enveloping CNC turntable based on AI predictive control. Summary of the Invention

[0004] The purpose of the present invention is to address the above-mentioned problems existing in the prior art and provide an intelligent braking system for an encircling CNC turntable based on AI predictive control.

[0005] The object of the present invention can be achieved by the following technical solutions: an encircling CNC turntable intelligent braking system based on AI predictive control, characterized by comprising: The state acquisition module is used to obtain the operating parameters of the CNC turntable in real time, collect the real-time status of the system, and provide a data basis for prediction. The operating parameters include angle, speed, load current and temperature; An AI prediction module, connected to the state acquisition module, is used to predict the future short-term motion trend and braking demand of the CNC turntable based on the acquired historical and current operating parameters using a machine learning model, and output the predicted braking start timing and clamping force control parameters; a pressure control module, connected to the AI ​​prediction module, for generating a control signal according to the predicted brake start timing and clamping force control parameters; An encircling brake actuator structure is connected to the pressure control module and is controlled by the control signal. The encircling brake actuator structure includes an elastic thin-walled brake ring 2 and a pressure oil chamber. By applying controlled oil pressure to the pressure oil chamber, the elastic thin-walled brake ring 2 is elastically deformed to tighten or loosen the turntable rotating shaft; A feedback correction module is connected to the state acquisition module and the AI ​​prediction module, and is used to collect actual braking result data, compare it with the predicted expected result of the AI ​​prediction module and calculate the error, and adjust the parameters of the machine learning model online based on the error to achieve self-learning and adaptive optimization of the system.

[0006] In the above-mentioned AI predictive control-based surround-type CNC turntable intelligent braking system, the machine learning model is a long short-term memory network (LSTM), an XGBoost algorithm or a reinforcement learning model. The machine learning model is used to actively predict the braking demand and optimized braking control parameters in the short term in the future based on the real-time collected turntable operation status data.

[0007] In the above-mentioned encircling CNC turntable intelligent braking system based on AI predictive control, the pressure control module includes an electromagnetic proportional valve, which is used to accurately adjust the oil pressure and change rate of the pressure oil chamber entering the encircling brake actuator structure, and realize stepless, rapid and precise adjustment of the clamping force by precisely controlling the pressure oil flow and pressure entering the brake ring oil chamber.

[0008] In the aforementioned AI-based predictive control-based wraparound CNC turntable intelligent brake system, the pressure control module is configured to control the wraparound brake execution structure to sequentially execute the following steps based on the predicted clamping force control parameters: Pre-clamping stage: Quickly apply the initial clamping force to make the elastic thin-wall brake ring slightly contact with the turntable rotating axis, quickly establish initial friction contact, eliminate the gap and start deceleration; Full clamping stage: According to the predicted optimization target, the oil pressure is controlled to rise to the target value or dynamically adjusted as needed, and the oil pressure rise curve is precisely controlled to make the clamping force rise smoothly and quickly to the target value, generating a sufficiently large braking torque to completely stop the turntable within the target time.

[0009] In the above-mentioned AI predictive control-based wraparound CNC turntable intelligent braking system, the feedback correction module adjusts the weight parameters of the machine learning model online through the gradient descent algorithm, optimizes the parameters of the AI ​​predictive model, and realizes the system's self-learning and long-term performance stability.

[0010] An intelligent braking method for an encircling CNC turntable based on AI predictive control, characterized by comprising the following steps: S1: Using machine learning models, the angle, speed, load current, and temperature operating parameters of the CNC turntable are collected in real time; S2: Based on the collected historical and current operating parameters, a machine learning model is used to predict the future short-term motion trend and braking requirements of the CNC turntable, and the predicted braking start timing and clamping force control parameters are obtained; S3: Based on the predicted brake initiation timing and clamping force control parameters, a control signal is generated to drive the encircling brake actuator structure to perform a braking action, thereby controlling the action timing and clamping force application process of the encircling brake actuator structure to achieve advanced intervention and process optimization. The braking action includes elastically deforming the elastic thin-walled brake ring of the encircling brake actuator structure through controlled oil pressure to clamp the turntable rotating axis. S4: Collect actual braking result data; S5: Compare the actual braking result data with the predicted expected result and calculate the error; S6: Based on the error, the parameters of the machine learning model are adjusted online to achieve self-learning and adaptive updating of the model, thereby improving the subsequent prediction accuracy and long-term stability of the braking control performance.

[0011] Compared with existing technologies, this AI-based predictive control-based intelligent braking system for CNC turntables has the following significant advantages: 1. Significantly improved response speed: AI prediction enables the proactive initiation and optimization of braking actions, significantly shortening the response time from identifying demand to effective braking, especially under conditions such as sudden changes in speed or load.

[0012] 2. High positioning accuracy: By combining predictive control with hydraulic dynamic adjustment, precise control of the braking process is achieved. This enables more precise control of the braking process, effectively reduces overshoot and underbraking, and significantly improves final positioning accuracy (for example, the error between the target position and the actual stopping position is significantly reduced).

[0013] 3. Strong adaptability: The system can automatically adjust control parameters based on prediction results to adapt to different speed and load conditions. The online feedback correction mechanism can continuously learn and compensate for system characteristic drift such as friction plate wear and temperature changes, ensuring long-term stability and accuracy.

[0014] 4. Smooth braking process: Adopting a staged clamping force control strategy (such as pre-clamping and full clamping), the clamping force is dynamically adjusted to effectively reduce braking shock, improve the smoothness of the braking process, protect the mechanical structure and improve processing quality.

[0015] 5. High degree of intelligence: The system integrates real-time state perception, motion trend prediction, control decision optimization and online self-learning capabilities, realizing intelligent braking control and significantly improving the overall intelligence level. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the intelligent braking system of the surrounding CNC turntable based on AI predictive control.

[0017] Figure 2 This is a structural diagram of the turntable rotation axis of the AI ​​predictive control-based intelligent braking system for an enveloping CNC turntable.

[0018] Figure 3 This is a structural diagram of the pressure oil chamber of the AI ​​predictive control-based wraparound CNC turntable intelligent brake system.

[0019] Figure 4 This is the AI ​​control strategy flow chart of the intelligent braking system of the enveloping CNC turntable based on AI predictive control.

[0020] In the figure, 1. Turntable rotation axis; 101. State acquisition module; 102. AI prediction module; 103. Pressure control module; 104. Encircling brake execution structure; 105. Feedback correction module; 2. Elastic thin-walled brake ring; 201. Pressure oil chamber; 3. Brake ring housing; 301. Channel hole 1; 302. Channel hole 2; 303. Channel hole 3; 304. Channel hole 4; 4. Brake base; 401. Oil inlet hole; 402. Oil outlet hole; 5. O-ring 1; 6. O-ring 2. DETAILED DESCRIPTION

[0021] The following are specific embodiments of the present invention and the accompanying drawings to further describe the technical solutions of the present invention, but the present invention is not limited to these embodiments.

[0022] like Figure 1-4 As shown in the figure, this AI predictive control-based wraparound CNC turntable intelligent braking system includes: State acquisition module 101: It is composed of sensors installed on the turntable (such as photoelectric encoders to measure angular displacement / speed, current transformers to measure motor load current, and temperature sensors), and is used to collect the turntable's angular displacement, speed, load current, system temperature and other pipe operating parameters in real time.

[0023] AI prediction module 102: A software module running in a control system (such as a PLC, industrial computer, or embedded processor) that uses a trained machine learning model (preferably an LSTM time series prediction model, but can also be XGBoost, Transformer, or other applicable time series models or reinforcement learning agents). Its input is the historical and real-time data streams provided by the state acquisition module 101, and its output is the predicted braking demand (for example: the need to start braking within the next XX milliseconds, the predicted stopping position, the required initial clamping force, and the clamping force change curve recommendation).

[0024] Pressure control module 103: Receives instructions from the AI ​​prediction module 102 and converts them into precise control signals for the brake actuator. The preferred implementation scheme is a hydraulic / pneumatic pressure regulating system composed of an electromagnetic proportional valve, which achieves stepless, rapid and precise adjustment of the clamping force by precisely controlling the flow and pressure of the pressure oil entering the brake ring oil chamber. Alternative solutions may include a mechanical actuator driven by a servo motor. Predictive control combined with dynamic pressure regulation can more accurately control the braking process, effectively reduce overshoot and underbraking, and greatly improve the final positioning accuracy. For example, the error between the target position and the actual stop position is significantly reduced.

[0025] The encircling brake execution structure 104 includes an elastic thin-walled brake ring 2 and a pressure oil chamber 201 . By applying controlled oil pressure to the pressure oil chamber 201 , the elastic thin-walled brake ring 2 is elastically deformed to tighten or loosen the turntable rotating shaft 1 .

[0026] Feedback correction module 105: After the braking action is completed, the actual braking result is collected, such as the actual stopping position read by the encoder and the time-speed curve of the braking process.

[0027] The actual braking result is compared with the previous prediction value of the AI ​​prediction module 102, and the error (such as position error and speed curve fitting error) is calculated. This error information is used to fine-tune the model parameters in the AI ​​prediction module 102 online through a back-propagation algorithm, so as to continuously optimize the prediction accuracy of the model. The feedback correction mechanism can continuously learn and compensate for system changes (such as wear and temperature effects) to ensure long-term stability and accuracy.

[0028] The encircling brake execution structure 104 comprises: Turntable rotation axis 1: braked object; Elastic thin-wall brake ring 2: core component, usually made of metal material with good elasticity (such as spring steel) into a thin-walled ring structure, see Figure 3 ; Brake ring housing 3: fixed component; Brake base 4: fixed component.

[0029] The upper end of the elastic thin-walled brake ring 2 is connected to the brake ring shell 3 by screws, the lower end of the elastic thin-walled brake ring 2 is connected to the brake base 4, and the brake base 4 is connected to the brake ring shell 3 by screws, so that the elastic thin-walled brake ring 2, the brake ring shell 3 and the brake base 4 form a rigid whole.

[0030] The outer walls of the upper and lower ends of the elastic thin-walled brake ring 2 are provided with sealing ring grooves, and the inner wall of the middle section of the elastic thin-walled brake ring 2 is provided with an annular groove, which constitutes the pressure oil chamber 201. The O-ring 1 5 and the O-ring 2 6 are respectively installed in the upper and lower sealing ring grooves to ensure the sealing of the pressure oil chamber 201.

[0031] Oil channel: The pressure oil reaches the pressure oil chamber 201 through the oil inlet hole 401, channel hole 1 301, and channel hole 2 302 in sequence; it can reach the oil outlet hole 402 through channel hole 303 and channel hole 4 304 in sequence and flow back to the oil tank. Channel hole 1 301, channel hole 2 302, channel hole 303, and channel hole 4 304 are all inside the brake ring housing 3.

[0032] Working principle: Normal operation: A designed gap (for example, 0.1 mm) is maintained between the outer circle of the turntable rotating shaft 1 and the inner wall of the elastic thin-walled brake ring 2 to ensure free rotation of the turntable.

[0033] Braking process: When braking is required, the pressure oil enters the pressure oil chamber 201 through the above-mentioned oil circuit. The oil pressure acts on the thin-walled part of the elastic thin-walled brake ring 2 in the pressure oil chamber 201, forcing the thin-walled area to produce inward elastic deformation, so that the inner wall of the elastic thin-walled brake ring 2 tightly fits the outer circle of the turntable rotating shaft 1, generating a strong friction braking torque, causing the turntable to stop quickly.

[0034] Release the brake: When the turntable needs to resume rotation, the oil pressure in the pressure oil chamber 201 is unloaded (the pressure oil passes through channel hole three 303 and channel hole four 304, reaches the oil outlet 402 and flows back to the oil tank), and the elastic thin-walled brake ring 2 relies on the elastic restoring force of its own material to restore to its original shape. The gap (0.1mm) between the inner wall and the outer circle of the turntable rotating shaft 1 reappears, the friction disappears, and the turntable can rotate freely.

[0035] AI control strategy process, such as Figure 4 : S1: State acquisition module 101: continuously collects data such as angular displacement θ, speed ω, load current I, temperature T, etc. in real time.

[0036] S2: AI prediction module 102: inputs the collected real-time data stream (including historical fragments) into the trained LSTM model; The model outputs prediction results, for example: predicting whether an event requiring emergency braking will occur within a short time window in the future (such as Δt = 300ms) (such as predicting possible tool breakage based on the load current mutation rate dI / dt); Predict the future motion trajectory of the turntable (speed change, expected stopping position); Predict the required braking start time, initial clamping force (e.g. percentage of maximum clamping force, 30% F_max), and the time or curve for the clamping force to reach the target value; If braking is predicted to be required, a processing pause request is immediately sent to the numerical control system, and a braking instruction containing detailed control parameters (such as target pressure and pressure rising slope) is sent to the pressure control module 103.

[0037] S3: Pressure control module 103 (pressure control execution): Pre-clamping stage (fast response): The pressure control module 103 (proportional valve system) opens rapidly according to the command, allowing the pressurized oil to quickly enter the pressure oil chamber 201 of the elastic thin-walled brake ring 2, pushing the inner wall of the brake ring into slight contact with the turntable rotating axis 1 (applying a pre-clamping force, for example, 30% F_max). This stage aims to quickly establish initial frictional contact, eliminate backlash, and initiate deceleration. Full clamping stage (precise control): After or simultaneously with pre-clamping, the pressure control module 103 precisely controls the oil pressure rise curve based on the optimization goal predicted by the AI ​​(such as avoiding overshoot), so that the clamping force rises smoothly and quickly to the target value (100% F_max or a value dynamically adjusted according to the prediction), generating a sufficiently large braking torque to completely stop the turntable within the target time (for example, ≤80ms). This stage can avoid the impact caused by rough braking.

[0038] S4: Feedback correction module 105: After braking is completed, the encoder accurately records the actual stop position of the turntable (θ_stop_actual) and the speed change curve (ω(t)) during the entire braking process; Compare the actual stop position θ_stop_actual with the target stop position θ_stop_predicted predicted by the AI ​​prediction module 102 to calculate the position error Δθ; Compare the actual speed change curve ω(t)_actual with the expected speed curve ω(t)_predicted predicted by the AI ​​prediction module 102 (e.g., calculate the mean square error); Based on the above error information (Δθ, speed curve error), the feedback correction module 105 uses an online learning algorithm (such as parameter update based on gradient descent) to fine-tune the LSTM model parameters in the AI ​​prediction module 102. Through this continuous "prediction-execution-feedback-learning" closed loop, the model's prediction accuracy continues to improve over time, and the system's adaptive capabilities are enhanced.

[0039] The specific embodiments described herein are merely illustrative of the spirit of the present invention. Persons skilled in the art may make various modifications, additions, or substitutions to the described specific embodiments without departing from the spirit of the present invention or exceeding the scope of the appended claims.

[0040] Although more terms are used herein, the possibility of using other terms is not excluded. These terms are used only to more conveniently describe and explain the essence of the present invention; interpreting them as any additional limitations is contrary to the spirit of the present invention.

Claims

1. An intelligent braking system for an enveloping CNC turntable based on AI predictive control, characterized in that: include: A state acquisition module (101) is used to obtain the operating parameters of the CNC turntable in real time, collect the real-time state of the system, and provide a data basis for prediction, wherein the operating parameters include angle, speed, load current and temperature; An AI prediction module (102), connected to the state acquisition module (101), is used to predict the future short-term motion trend and braking demand of the CNC turntable based on the acquired historical and current operating parameters using a machine learning model, and output the predicted braking start timing and clamping force control parameters; A pressure control module (103), connected to the AI ​​prediction module (102), is used to generate a control signal according to the predicted brake start timing and clamping force control parameters; An encircling brake execution structure (104) is connected to the pressure control module (103) and is controlled by the control signal. The encircling brake execution structure (104) includes an elastic thin-walled brake ring (2) and a pressure oil chamber (201). By applying controlled oil pressure to the pressure oil chamber (201), the elastic thin-walled brake ring (2) is elastically deformed to tighten or loosen the turntable rotating shaft (1); A feedback correction module (105) is connected to the state acquisition module (101) and the AI ​​prediction module (102), and is used to collect actual braking result data, compare it with the predicted expected result of the AI ​​prediction module (102) and calculate the error, and adjust the parameters of the machine learning model online based on the error to achieve self-learning and adaptive optimization of the system.

2. The AI ​​predictive control-based wraparound CNC turntable intelligent braking system according to claim 1 is characterized in that: The machine learning model is a long short-term memory network (LSTM), an XGBoost algorithm or a reinforcement learning model. The machine learning model is used to actively predict the braking demand and optimized braking control parameters in the short term in the future based on the turntable operation status data collected in real time.

3. The AI ​​predictive control-based wraparound CNC turntable intelligent braking system according to claim 1 is characterized in that: The pressure control module (103) includes an electromagnetic proportional valve for accurately adjusting the oil pressure and the rate of change of the pressure oil chamber (201) entering the encircling brake actuator structure (104), thereby achieving stepless, rapid and precise adjustment of the clamping force by accurately controlling the flow rate and pressure of the pressure oil entering the brake ring oil chamber.

4. The AI ​​predictive control-based wraparound CNC turntable intelligent braking system according to claim 1 is characterized in that: The pressure control module (103) is configured to control the encircling brake execution structure (104) to sequentially execute the following according to the predicted clamping force control parameter: Pre-clamping stage: quickly apply the initial clamping force to make the elastic thin-wall brake ring (2) slightly contact with the turntable rotating shaft (1), quickly establish initial friction contact, eliminate the gap and start deceleration; Full clamping stage: According to the predicted optimization target, the oil pressure is controlled to rise to the target value or dynamically adjusted as needed, and the oil pressure rise curve is precisely controlled to make the clamping force rise smoothly and quickly to the target value, generating a sufficiently large braking torque to completely stop the turntable within the target time.

5. The AI ​​predictive control-based wraparound CNC turntable intelligent braking system according to claim 1 is characterized in that: The feedback correction module (105) adjusts the weight parameters of the machine learning model online through a gradient descent algorithm, optimizes the parameters of the AI ​​prediction model, and realizes self-learning and long-term performance stability of the system.

6. An intelligent braking method for an encircling CNC turntable based on the AI ​​predictive control according to any one of claims 1 to 5, characterized in that: The following steps are involved: S1: Using machine learning models, the angle, speed, load current, and temperature operating parameters of the CNC turntable are collected in real time; S2: Based on the collected historical and current operating parameters, a machine learning model is used to predict the future short-term motion trend and braking requirements of the CNC turntable, and the predicted braking start timing and clamping force control parameters are obtained; S3: Based on the predicted braking start timing and clamping force control parameters, a control signal is generated and the encircling brake execution structure (104) is driven to execute a braking action, so as to control the action timing and clamping force application process of the encircling brake execution structure (104) to achieve advanced intervention and process optimization, wherein the braking action includes elastically deforming the elastic thin-walled brake ring (2) of the encircling brake execution structure (104) through controlled oil pressure to clamp the turntable rotating shaft (1); S4: Collect actual braking result data; S5: Compare the actual braking result data with the predicted expected result and calculate the error; S6: Based on the error, the parameters of the machine learning model are adjusted online to achieve self-learning and adaptive updating of the model, thereby improving the subsequent prediction accuracy and long-term stability of the braking control performance.

Images