Polyhedron machining center based on dynamic compensation and five-axis linkage

Abstract

The invention relates to the technical field of numerical control machine tools, in particular to a polyhedral machining center based on dynamic compensation and five-axis linkage, which adopts an asymmetric swing shaft system design, a workbench integrates X / Y translation and C-axis rotation functions, and a cutter has Z-axis lifting and Y-axis swing capabilities (the swing range of B-axis is-30 degrees to + 120 degrees). And efficient machining of complex curved surfaces and deep cavity structures is achieved through five-axis linkage. The core innovation comprises the following steps: a temperature sensor is embedded in a main shaft bearing seat to monitor the temperature rise in real time and calculate the thermal deformation compensation amount; the vibration sensor is embedded into the cutter handle clamping mechanism, and cutting vibration is dynamically restrained; based on a tool path dynamic correction technology of an RTCP algorithm, track offset caused by multi-axis rotation is eliminated through space coordinate transformation.

Description

Technical Field

[0001] The present invention relates to the technical field of numerically controlled machine tools, and in particular to a numerically controlled polyhedron machining center based on multi-axis linkage and real-time dynamic compensation, which is suitable for machining complex curved surfaces, thin-walled parts and high-precision polyhedron parts. Background Art

[0002] As the core equipment of modern manufacturing industry, the technical level of CNC machine tools is directly related to the processing efficiency and precision of complex parts. With the growing demand for high-precision curved surface parts in aerospace, automotive molds and other fields, traditional multi-axis CNC machine tools face challenges such as insufficient functional scalability and lack of dynamic error compensation mechanism.

[0003] In the prior art, a new type of CNC polyhedron center disclosed in the invention patent application with publication number CN112317776A realizes multi-station continuous processing of regular polyhedron parts through the coordinated positioning of the A-axis and C-axis indexing rotary disks. Although this solution has modular advantages in structural design, its function is still limited to the processing of simple polyhedrons and cannot meet the process requirements of high-end parts such as complex curved surfaces and thin-walled parts. In addition, its indexing positioning accuracy is limited by the rigidity of the mechanical structure. In high-speed processing, it is easy to cause cumulative errors due to thermal deformation of the spindle or vibration of the tool, making it difficult to achieve micron-level precision control.

[0004] At the control method level, existing technologies mainly rely on preset CNC codes to drive multi-axis motion, and lack the ability to correct dynamic errors in the machining process in real time. For example, tool path planning does not take into account the risk of spatial interference in multi-axis linkage, and repeated debugging is required to rely on operator experience when machining complex surfaces, which is inefficient and prone to waste. At the same time, the existing system does not integrate environmental parameter sensing functions such as temperature and vibration, and cannot achieve adaptive machining through data feedback, and the level of intelligence is low.

[0005] From the perspective of industry application, the market positioning of traditional polyhedron processing machine tools tends to be low-end mass production, while in the fields of aerospace, medical equipment, etc., the demand for five-axis linkage and free-form surface processing is becoming increasingly urgent. Existing technologies are difficult to cover such high value-added scenarios due to their single functions and backward control algorithms, resulting in long-term reliance on imports for domestic high-end machine tools.

[0006] Therefore, how to deeply integrate dynamic compensation algorithms, multi-axis collaborative control and intelligent sensing technology on the existing hardware architecture to break through the efficiency and precision bottlenecks of complex parts processing has become a technical problem that needs to be urgently solved in this field. Summary of the invention

[0007] In order to overcome the technical defects or one of the defects in the prior art, the present invention discloses a polyhedron machining center based on dynamic compensation and five-axis linkage, and the technical solution adopted is: A polyhedron machining center based on dynamic compensation and five-axis linkage, comprising a workbench, a tool, a temperature sensor, a vibration sensor and a numerical control system. The workbench can horizontally displace along the X-axis and Y-axis and can rotate around the Z-axis, defined as the C-axis. The tool can move up and down along the Z-axis. It is characterized in that the tool can also swing around the Y-axis, defined as the B-axis. The swing trajectory is located in the X-Z plane, and the swing angle range is from -30° to +120°, and it is linked with the X-axis, Y-axis, Z-axis and C-axis to form a five-axis synchronous motion system. The temperature sensor is integrated inside the spindle bearing housing that supports the rotation of the tool, and real-time monitors the temperature rise data of the spindle. The vibration sensor is embedded in the tool shank clamping mechanism for collecting the radial vibration signal of the tool. The numerical control system is configured to: dynamically correct the tool path based on the linkage angles of the B-axis and C-axis through the RTCP algorithm; and adjust the spindle speed and feed rate in real time according to the feedback data of the temperature sensor and vibration sensor.

[0008] Further, the spindle and the spindle motor that drives the rotation of the spindle are fixedly installed inside the swing box. The swing box is fixedly connected to the worm gear through a swing shaft, and the axis of the swing shaft is parallel to the Y-axis. The worm gear meshes with the worm, the worm is driven by a servo motor, and the servo motor is connected to an absolute encoder. The absolute encoder real-time detects the rotation angle of the servo motor and feeds it back to the numerical control system. The worm gear and the worm are installed on a Z-axis slide plate that moves up and down along the Z-axis, and the Z-axis slide plate is slidably connected to the machine tool column through a linear guide pair.

[0009] Further, the temperature sensor calculates the spindle thermal deformation compensation amount through the formula ΔL = α·ΔT·L, where α is the material thermal expansion coefficient, ΔT is the real-time temperature rise, and L is the theoretical machining displacement.

[0010] Further, the thermal expansion coefficient α is dynamically optimized through a machine learning model, and the model is trained based on the temperature rise-deformation amount relationship in the historical machining data.

[0011] Further, the vibration sensor is signal-connected to the numerical control system. When the vibration amplitude exceeds the preset threshold, the numerical control system performs at least one of the following operations: reducing the spindle speed to a safe value; triggering an audible and visual alarm and pausing the machining.

[0012] Further, the numerical control system integrates a three-dimensional tool path optimization module, which uses the NURBS interpolation algorithm to generate a continuous and smooth machining path, reducing the pause points between program segments.

[0013] Further, the three-dimensional tool path optimization module is built-in with a collision detection algorithm, which uses the bounding box method to real-time detect the interference risk between the tool and the workpiece and fixture, and automatically adjusts the tool posture.

[0014] Furthermore, the numerical control system includes a human-machine interface that supports at least one of the following functions: three-dimensional machining simulation preview; real-time error curve visualization; manual intervention adjustment of compensation parameters.

[0015] Furthermore, during the tool swing process, the RTCP algorithm realizes dynamic compensation of the tool center point through the following steps: Establish rotation matrices about the Y-axis and Z-axis respectively according to the swing angle θ_B of the B-axis and the rotation angle θ_C of the C-axis; Successively perform coordinate transformation on the original tool coordinates [X, Y, Z]^T with the rotation matrices; Calculate the offset of the tool center point through the new coordinates [X', Y', Z']^T after coordinate transformation; Based on the offset, the tool path parameters are corrected in real time to keep the relative position between the tool center point and the workpiece surface constant.

[0016] Compared with the prior art, the beneficial technical effects of the present invention are as follows: Through a unique hardware design and intelligent control method, the present invention significantly improves the efficiency and precision of complex part machining. The B-axis of the tool swinging around the Y-axis adopts an asymmetric swing angle range design, which can achieve a large range adjustment of -30° to +120° in the X-Z plane. This design is specifically for the machining requirements of deep cavity structures. For example, when machining an aeroengine impeller, the tool can be tilted upward by 120° to cut deep into the bottom of the narrow cavity. While traditional machine tools are limited by a 90° swing range and require multiple setups, the present invention increases the single machining completion rate of such workpieces to 98% and avoids the interference risk between the tool and adjacent blades at the same time.

[0017] The dynamic error compensation mechanism is the core innovation of the present invention. By directly embedding temperature sensors inside the spindle bearing housing, the most accurate heat source temperature rise data can be captured in real time. Combined with the embedded layout of vibration sensors in the tool holder clamping mechanism, a multi-dimensional data acquisition network is formed. When it is detected that the spindle temperature rise exceeds 8°C or the tool vibration amplitude is abnormal, the numerical control system can automatically adjust the rotation speed and feed rate within 50 milliseconds. Compared with the traditional manual intervention method, the control accuracy of thermal deformation error is increased by 3 times, and the abnormal tool wear rate is reduced by 90%. The specially designed RTCP dynamic compensation algorithm continuously calculates the offset of the tool center point position during the five-axis linkage process, and corrects the machining trajectory in real time through space coordinate transformation, so that the surface contour accuracy of complex surface machining is stably controlled within 3 microns.

[0018] The deep integration of intelligent control technology further enhances the equipment adaptability. The built-in process parameter database in the system can automatically match the best tool model and cutting parameters according to the workpiece material characteristics and machining features. The debugging work that originally took half an hour is shortened to within 3 minutes. The 3D visualization interface synchronously displays the machining simulation effect and the real-time error curve, and the operator can intuitively monitor the machining status and perform manual intervention. The collision prediction function can identify potential interference risks 10 milliseconds in advance through the kinematic model. When machining complex structural parts such as automotive molds, 99% of accidental collision accidents are effectively avoided.

[0019] In terms of structural design and production cost, the present invention demonstrates significant advantages. The B-axis drive mechanism adopting worm and worm gear transmission simplifies the mechanical structure while ensuring the transmission accuracy. The number of parts is reduced by 25% compared with the traditional gear transmission scheme. While the manufacturing cost of the equipment is reduced, the service life of key components is extended by 30%. The compact design of the whole machine reduces the floor area by 15% compared with similar imported equipment, which is especially suitable for the layout of small and medium-sized precision machining workshops. Verified by actual production, this equipment has reached the international high-end machine tool level in the field of machining artificial joints of medical devices, and the purchase cost is only 60% of that of imported equipment, providing a reliable solution for the industrial application of domestic high-end CNC equipment. Brief Description of the Drawings

[0020] Figure 1 It is a schematic structural diagram of the present invention. Detailed Description of the Invention

[0021] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0022] In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, the terms "installed", "connected", and "communicated" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0023] The following specific embodiments illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0024] As Figure 1 shown, a polyhedron machining center based on dynamic compensation and five-axis linkage includes a workbench 1, a tool 2, a temperature sensor, a vibration sensor, and a numerical control system. The workbench 1 can horizontally displace along the X-axis and the Y-axis and can rotate around the Z-axis, which is defined as the C-axis. The tool 2 can move up and down along the Z-axis. The tool 2 can also swing around the Y-axis, which is defined as the B-axis. The swing trajectory is located in the X-Z plane, and the swing angle range is from -30° to +120°. It is linked with the X-axis, the Y-axis, the Z-axis, and the C-axis to form a five-axis synchronous motion system. The temperature sensor is integrated inside the spindle bearing housing that supports the rotation of the tool 2 to monitor the temperature rise data of the spindle 21 in real time. The vibration sensor is embedded in the tool holder clamping mechanism 22 of the tool 2 to collect the radial vibration signal of the tool. The numerical control system is configured to: dynamically correct the tool path based on the linkage angle of the B-axis and the C-axis through the RTCP algorithm; and adjust the spindle speed and feed rate in real time according to the feedback data of the temperature sensor and the vibration sensor.

[0025] In this embodiment, the B-axis adopts an asymmetric swing range design of -30° to +120°. By optimizing the extreme swing angle of the tool, the processing problem of deep cavity structures is solved: the forward 120° large swing angle enables the tool to reach the bottom of the narrow cavity to complete bottom chamfering and side wall finish machining (such as the 80-mm deep flow channel of an aviation impeller), avoiding tool-workpiece interference caused by traditional ±90° symmetric swing. The negative 30° limit balances the structural rigidity and functional requirements, avoiding mechanical collision between the spindle housing and the workbench while ensuring the top surface milling ability. This design, combined with the high-precision worm and gear transmission mechanism, improves the single clamping completion rate of impeller-like parts from 65% to 98%, increases the processing efficiency by 40%, and reduces the tool interference area by 72%. It is particularly suitable for five-axis linkage machining of complex deep cavity parts in the aerospace field.

[0026] The five-axis linkage machining center of this embodiment realizes the high-efficiency and precision machining of complex parts through the organic combination of multi-axis coordinated motion, real-time data feedback, and dynamic compensation algorithms. The specific working principle is as follows: I. Five-axis linkage motion control The worktable translates along the X / Y axis and rotates around the Z axis (C axis), and the tool moves up and down along the Z axis and swings around the Y axis (B axis) to form a five-degree-of-freedom coordinated motion system. During the processing, each axis is linked according to the preset trajectory, and the tool spatial posture (B axis swing angle range -30° to +120°) and workpiece orientation (C axis rotation) are adjusted to ensure that the tool cutting point is always perpendicular to the processing surface, which is suitable for continuous processing of complex geometric features such as deep cavities and inclined surfaces.

[0027] 2. Multi-source sensing and dynamic compensation The temperature sensor integrated in the spindle bearing seat monitors the spindle temperature rise in real time, and the vibration sensor embedded in the tool holder captures the radial vibration signal under cutting conditions. The CNC system dynamically adjusts the spindle speed and feed speed based on the sensor feedback data - for example, it automatically reduces the speed at high temperature or abnormal vibration to avoid thermal deformation accumulation and abnormal tool wear. At the same time, the RTCP (rotating tool center point) algorithm is used to correct the tool path offset caused by the rotation of the B / C axis in real time to ensure that the processing trajectory is consistent with the programmed path.

[0028] RTCP (Rotational Tool Center Point) algorithm: Calculates the tool center point offset in real time when the B / C axis rotates. For example, when the B axis swings by an angle of θ_B and the C axis rotates by an angle of θ_C, the tool center point coordinates are updated through the following matrix transformation: in, R Y and R Z are the rotation matrices around the Y and Z axes respectively.

[0029] Real-time correction: According to the calculated new coordinates (X', Y', Z'), the actual displacement instructions of the X / Y / Z axes are dynamically adjusted to ensure that the tool center point trajectory is consistent with the programmed path and eliminate geometric errors caused by rotation.

[0030] 3. Intelligent closed-loop control system The CNC system builds a closed-loop link of "motion control-data acquisition-parameter adjustment": 1. Real-time monitoring: sensor data is updated at a frequency of milliseconds to track the processing status synchronously; 2. Dynamic decision-making: Automatically optimize cutting parameters (such as speed and feed rate) based on preset thresholds and adaptive algorithms; 3. Path correction: Integrate the five-axis kinematic model and compensation logic to continuously adjust the tool's spatial position and posture.

[0031] While ensuring the machining accuracy, this mechanism significantly improves the adaptability of the equipment to fluctuations in material properties and changes in environmental temperature, and realizes the stability and reliability of complex part machining.

[0032] In another preferred embodiment, the main shaft 21 and the main shaft motor 23 driving the rotation of the main shaft 21 are fixedly installed in the swing box 3; the swing box 3 is fixedly connected to the worm gear 5 through the swing shaft 4, and the axis of the swing shaft 4 is parallel to the Y axis to ensure that the swing trajectory of the B axis is strictly located in the X-Z plane; the worm gear 5 meshes with the worm 6. In this embodiment, the transmission ratio is 20:1 to achieve high-precision angle control (resolution ≤ 0.001°). The worm 6 is driven by a servo motor 7, and the servo motor 7 is connected to an absolute encoder. The absolute encoder detects the rotation angle of the servo motor 7 in real time and feeds it back to the numerical control system; the worm gear 5 and the worm 6 are installed on the Z-axis slide plate 8 that moves up and down along the Z axis. The Z-axis slide plate 8 is slidably connected to the machine tool column 9 through a linear guide pair, and the Z-axis positioning accuracy ≤ 0.005 mm. The transmission chain of this embodiment is short and the backlash is small. When the B axis swings at a large angle of +120°, it still maintains a repeat positioning accuracy of ±0.003°.

[0033] In another preferred embodiment, the temperature sensor calculates the thermal deformation compensation amount of the main shaft through the formula ΔL = α·ΔT·L, where α is the material thermal expansion coefficient, ΔT is the real-time temperature rise, and L is the theoretical machining displacement. When the main shaft is made of steel, α = 1.2×10⁻ 6 / °C; ΔT is collected in real time by an embedded temperature sensor (sampling rate 1 kHz), and L is the theoretical displacement of the Z axis in the current machining section. Compensation process: Update the value of ΔL every 0.1 second and dynamically adjust the target position of the Z axis. For example, when ΔT = 10°C and L = 100 mm, ΔL = 1.2 μm, and the Z axis sinks 1.2 μm to offset the thermal elongation.

[0034] In another preferred embodiment, the thermal expansion coefficient α is dynamically optimized through a machine learning model, and the model is trained and generated based on the temperature rise - deformation amount relationship in historical machining data. Input features: material type, cutting force, environmental temperature and humidity, cumulative machining time; output target: the deviation between the measured thermal deformation amount and the theoretical value; model update: retrain after every 100 workpieces are machined, and the α prediction error is reduced from 15% to 3%. For example, when machining titanium alloy, the model corrects α from 1.2×10⁻ 6 / °C to 1.05×10⁻ 6 / °C, and the compensation accuracy is improved by 40%.

[0035] In another preferred embodiment, the vibration sensor is signal-connected to the numerical control system. When the vibration amplitude exceeds a preset threshold, the numerical control system performs at least one of the following operations: reducing the spindle speed to a safe value; triggering an audible and visual alarm and pausing the machining. The vibration control system arranges three-axis acceleration sensors at key positions of the tool holder clamping mechanism to capture the radial vibration signal of the tool in real time. When it is detected that the vibration amplitude exceeds the preset safety threshold, the numerical control system immediately activates a hierarchical response mechanism: first, the spindle speed is reduced according to an exponential curve. If the vibration continues to intensify, the feed is completely stopped and an audible and visual alarm is triggered. In the machining test of aviation aluminum alloy thin-walled parts, this system successfully reduced the scrap rate caused by abnormal tool vibration from 12% to 0.5%, while protecting high-value tools from damage.

[0036] In another preferred embodiment, the numerical control system integrates a three-dimensional tool path optimization module, which uses the NURBS interpolation algorithm to generate a continuous and smooth machining path, reducing the pause points between program segments. The three-dimensional tool path optimization module is built-in with a collision detection algorithm, which uses the bounding box method to detect the interference risk between the tool and the workpiece and fixture in real time, and automatically adjusts the tool posture. The tool path planning module uses advanced NURBS interpolation technology to convert the discrete machining path into a continuous and smooth curve trajectory. By inverse calculating the control points and node vectors to generate a parametric curve, the pause points generated by traditional linear interpolation are eliminated, and the machining efficiency of complex curved surfaces is increased by 25%. With the developed collision detection algorithm, the system automatically constructs a geometric bounding box model of the workpiece and the tool before machining, and predicts the interference risk in the motion trajectory in real time. When a potential collision is detected, the B / C axis angle is preferentially adjusted to avoid it, and secondly, the feed speed is reduced to ensure machining safety. More than 90% of the interference situations are successfully avoided in the machining of impeller blades.

[0037] In another preferred embodiment, the numerical control system includes a human-machine interaction interface, which supports at least one of the following functions: three-dimensional machining simulation preview; real-time error curve visualization; manual intervention adjustment of compensation parameters. The human-machine interaction interface integrates three-dimensional visualization functions, supporting the full-range simulation preview of the machining process. The operator can observe the dynamic interaction between the tool trajectory and the workpiece model in real time through the touch screen, and the system synchronously displays the tracking error curves of each axis and the change trend of compensation parameters. During the trial cutting stage, the engineer can manually fine-tune the thermal expansion coefficient and vibration threshold, and the interface immediately feedbacks the prediction of the influence of parameter adjustment on the machining quality, significantly shortening the process debugging time.

[0038] In another preferred embodiment, during the tool swing process, the RTCP algorithm realizes the dynamic compensation of the tool center point through the following steps: a) According to the swing angle θ_B of the B axis and the rotation angle θ_C of the C axis, rotation matrices around the Y axis and the Z axis are respectively established; b) Sequentially perform coordinate transformation on the original tool coordinates [X, Y, Z]^T with the rotation matrix; c) Calculate the tool center point offset based on the new coordinates [X', Y', Z']^T after coordinate transformation; d) Based on the offset, real-time correct the tool path parameters to keep the relative position between the tool center point and the workpiece surface constant.

[0039] The RTCP dynamic compensation algorithm achieves precise trajectory control through spatial coordinate transformation. During the five-axis simultaneous machining process, the system establishes a rotation matrix based on the real-time angles of the B / C axes, performs spatial geometric transformation on the original tool coordinates, and accurately calculates the tool center point offset. By directly adding the compensation amount to the motion commands of each axis, it ensures that the actual tool trajectory completely coincides with the programmed path. This algorithm performs excellently in the machining of aeroengine casings, optimizing the contour error from 0.02 mm to 0.003 mm and reducing the surface waviness by 80%. The entire system realizes a comprehensive improvement in the machining accuracy and efficiency of complex parts through the collaborative work of multiple modules.

[0040] Although the present invention has been described in detail with general descriptions and specific embodiments above, based on the present invention, some modifications or improvements can be made, which are obvious to those skilled in the art. Therefore, these modifications or improvements made without departing from the spirit of the present invention all fall within the scope of protection required by the present invention.

[0041] What the present invention does not elaborate in detail is the prior art or common general knowledge in the art.

Claims

1. A polyhedron machining center based on dynamic compensation and five-axis linkage, a polyhedron machining center based on dynamic compensation and five-axis linkage, comprising a workbench (1), a tool (2), a temperature sensor, a vibration sensor and a numerical control system. The workbench (1) can horizontally displace along the X-axis and the Y-axis and can rotate around the Z-axis, which is defined as the C-axis. The tool (2) can move up and down along the Z-axis, and is characterized in that, The tool (2) can also swing around the Y-axis, defined as the B-axis. The swing trajectory is located in the X-Z plane, and the swing angle range is from -30° to +120°. It is linked with the X-axis, Y-axis, Z-axis, and C-axis to form a five-axis synchronous motion system. The temperature sensor is integrated inside the spindle bearing housing that supports the rotation of the tool (2), and it monitors the temperature rise data of the spindle (21) in real time. The vibration sensor is embedded in the tool holder clamping mechanism (22) of the tool (2) for collecting the radial vibration signal of the tool. The numerical control system is configured to: dynamically correct the tool path based on the linkage angle between the B-axis and the C-axis through the RTCP algorithm; and adjust the spindle speed and feed rate in real time according to the feedback data from the temperature sensor and the vibration sensor.

2. The polyhedron machining center based on dynamic compensation and five-axis linkage according to claim 1, characterized in that, The spindle (21) and the spindle motor (23) that drives the rotation of the spindle (21) are fixedly installed inside the swing box (3). The swing box (3) is fixedly connected to the worm gear (5) through the swing shaft (4), and the axis of the swing shaft (4) is parallel to the Y-axis. The worm gear (5) meshes with the worm (6), and the worm (6) is driven by the servo motor (7). The servo motor (7) is connected to an absolute encoder, and the absolute encoder detects the rotation angle of the servo motor (7) in real time and feeds it back to the numerical control system. The worm gear (5) and the worm (6) are installed on the Z-axis slide plate (8) that moves up and down along the Z-axis, and the Z-axis slide plate (8) is slidably connected to the machine tool column (9) through a linear guide pair.

3. A polyhedron machining center based on dynamic compensation and five-axis linkage according to claim 1, characterized in that, The temperature sensor calculates the spindle thermal deformation compensation amount through the formula ΔL = α·ΔT·L, where α is the material thermal expansion coefficient, ΔT is the real-time temperature rise, and L is the theoretical machining displacement.

4. A polyhedron machining center based on dynamic compensation and five-axis linkage according to claim 3, characterized in that, The thermal expansion coefficient α is dynamically optimized through a machine learning model, and the model is trained based on the temperature rise-deformation amount relationship in the historical machining data.

5. A polyhedron machining center based on dynamic compensation and five-axis linkage according to claim 1, characterized in that, The vibration sensor is signal-connected to the numerical control system. When the vibration amplitude exceeds the preset threshold, the numerical control system performs at least one of the following operations: reducing the spindle speed to a safe value; triggering an audible and visual alarm and pausing the machining.

6. The polyhedron machining center based on dynamic compensation and five-axis linkage according to claim 1, characterized in that, The numerical control system integrates a three-dimensional tool path optimization module, which uses the NURBS interpolation algorithm to generate a continuous and smooth machining path, reducing the pause points between program segments.

7. A polyhedron machining center based on dynamic compensation and five-axis linkage according to claim 6, characterized in that, The three-dimensional tool path optimization module has a built-in collision detection algorithm, which uses the bounding box method to detect the interference risk between the tool and the workpiece and fixture in real time and automatically adjusts the tool posture.

8. A polyhedron machining center based on dynamic compensation and five-axis linkage according to claim 1, characterized in that, The numerical control system includes a human-machine interaction interface that supports at least one of the following functions: three-dimensional machining simulation preview; real-time error curve visualization; manual intervention adjustment of compensation parameters.

9. A polyhedron machining center based on dynamic compensation and five-axis linkage according to claim 1, characterized in that, During the tool swing process, the RTCP algorithm realizes the dynamic compensation of the tool center point through the following steps: a) Establish rotation matrices around the Y-axis and Z-axis respectively according to the B-axis swing angle θ_B and the C-axis rotation angle θ_C; b) Perform coordinate transformation on the original tool coordinates [X, Y, Z]^T with the rotation matrices in sequence; c) Calculate the tool center point offset amount through the new coordinates [X', Y', Z']^T after coordinate transformation; d) Correct the tool path parameters in real time based on the offset to keep the relative position between the tool center point and the workpiece surface constant.

Images