Intelligent milling system and self-adaptive machining method for weak-rigidity cylindrical part

Abstract

The application discloses a weak stiffness cylinder piece intelligent milling processing system and a self-adaptive processing method, relates to the technical field of mechanical cutting processing, and comprises a six-degree-of-freedom robot, a milling device arranged at the tail end of the six-degree-of-freedom robot, an inner support floating tooling for clamping the weak stiffness cylinder piece, an industrial computer for controlling the processing system, and a robot control cabinet for controlling the spatial movement of the six-degree-of-freedom robot. The inner support floating tooling is used to detect the global deformation of the wall surface of the weak stiffness cylinder piece, a global wall surface deformation prediction model of finite element simulation-cyclic neural network is constructed and utilized to predict the wall surface deformation, and the cutting amount of a tool is adjusted in real time to dynamically compensate in the processing process. The application can improve the processing precision, reduce the processing error, improve the tool utilization rate, and reduce the production cost.

Description

Technical Field

[0001] This invention relates to the field of mechanical cutting technology, and in particular to an intelligent milling system and adaptive machining method for low-stiffness cylindrical parts. Background Technology

[0002] Low-stiffness cylindrical components are widely used in aerospace, shipbuilding, automotive industry, energy equipment and other fields. They are mainly formed by casting. However, the outer wall precision of cast cylindrical components is poor. In order to ensure that the cylindrical components have good structural strength, meet the assembly accuracy of the cylindrical components, and improve the production quality and consistency of the cylindrical components, it is necessary to perform cutting operations such as milling on the outer wall.

[0003] Currently, the machining of the outer walls of low-stiffness cylindrical components mainly relies on manual operation, resulting in low efficiency and high labor intensity. Furthermore, the reliance on manual experience to adjust machining parameters leads to poor machining accuracy, repeatability, and product consistency. The low stiffness of the cylindrical components also makes them prone to deformation during machining, resulting in significant machining errors. Due to the complex and thin outer walls of these cylindrical components, deformation prediction is difficult. To mitigate the impact of low stiffness, multi-pass milling processes are typically used to remove excess material during the outer wall cutting. However, this method is inefficient, causes high tool wear, and cannot meet the machining requirements of thin-walled cylindrical castings. In addition, the machining fixtures for low-stiffness cylindrical components are mostly custom-made and externally clamped, making them suitable only for specific processes and workpieces, resulting in low utilization. External clamping also easily leads to significant workpiece deformation, further deteriorating machining accuracy, repeatability, and product consistency. In summary, the poor rigidity and easy deformation during machining of weak stiffness cylindrical parts are the main reasons for their machining errors. There is an urgent need for a complete machining system and method to achieve high-precision machining of weak stiffness cylindrical parts.

[0004] Therefore, those skilled in the art are dedicated to developing an intelligent milling system and adaptive machining method for low-stiffness cylindrical parts. Summary of the Invention

[0005] In view of the above-mentioned deficiencies of the prior art, the technical problem to be solved by the present invention is how to improve the milling accuracy of the outer wall of a weak stiffness cylindrical part.

[0006] To achieve the above objectives, this invention provides an intelligent milling system for weakly stiff cylindrical parts, comprising a six-degree-of-freedom robot, a milling device disposed at the end of the six-degree-of-freedom robot, an internal support floating fixture for clamping the weakly stiff cylindrical part, an industrial control computer for controlling the machining system, and a robot control cabinet for controlling the spatial motion of the six-degree-of-freedom robot. The system detects the global deformation of the wall surface of the weakly stiff cylindrical part through the internal support floating fixture, constructs and utilizes a finite element simulation-recurrent neural network global wall deformation prediction model to predict wall deformation, and adjusts the cutting parameters of the tool in real time for dynamic compensation during the machining process.

[0007] Furthermore, the inner support floating fixture includes six auxiliary support modules that are evenly distributed along the circumference and contact the inner wall of the weak stiffness cylindrical component. A displacement sensor is disposed at the end of the auxiliary support module, and a communication control module is disposed inside the inner support floating fixture. The displacement sensor is an infrared displacement sensor.

[0008] Furthermore, the inner support floating fixture also includes an inner support floating fixture base, and a gear transmission pair consisting of a first radial transmission gear and a second radial transmission gear is disposed on the inner support floating fixture base. An auxiliary support module guide rail platform is disposed on the upper surface of the first radial transmission gear. The auxiliary support modules are evenly distributed circumferentially on the auxiliary support module guide rail platform. Through the transmission of the gear pair and the threaded pair, the auxiliary support modules move synchronously radially along the auxiliary support module guide rail.

[0009] Furthermore, the auxiliary support module includes an auxiliary support module slider disposed on the auxiliary support module guide rail platform, which moves radially along the auxiliary support module guide rail via a gear pair and a threaded pair, and an auxiliary support module end floating groove surface pressure block connected to the auxiliary support module slider via an auxiliary support module floating groove surface pressure block slider connecting pin. The groove surface of the auxiliary support module end floating groove surface pressure block is in contact with the inner surface of the weak stiffness cylindrical component, and the displacement sensor is disposed on the auxiliary support module end floating groove surface pressure block.

[0010] Furthermore, a spring is provided at the contact end between the floating groove pressure block at the end of the auxiliary support module and the inner surface of the weak stiffness cylindrical component.

[0011] Furthermore, the internal support floating fixture is mounted on the machining platform.

[0012] Furthermore, the internal support floating fixture also includes clamping holes for clamping weak stiffness cylindrical parts.

[0013] Furthermore, the milling device includes a milling spindle and a cutting tool clamped on the milling spindle.

[0014] Furthermore, an adaptive machining method using the aforementioned intelligent milling system for weak-stiffness cylindrical parts includes the following steps:

[0015] Step 1: Adaptive clamping and positioning of weak stiffness cylindrical components;

[0016] Step 2: Construct a finite element simulation-recurrent neural network global wall deformation prediction model, collect training sets, and train and validate the recurrent neural network for predicting wall temporal deformation.

[0017] Step 3: Perform cutting. Based on the minute deformation of the weak stiffness cylindrical part, predict the real-time deformation at the machining position through a global wall deformation prediction model of a recurrent neural network, adjust the cutting parameters of the tool, and perform dynamic compensation for machining.

[0018] Furthermore, step one also includes the following steps:

[0019] Step 1.1 Use the auxiliary support module to perform adaptive centering and clamping on the weak stiffness cylindrical component;

[0020] Step 1.2 Set an appropriate float based on the error characteristics of the weak stiffness cylindrical component;

[0021] Step two also includes the following steps:

[0022] Step 2.1 Import the numerical model of the weak stiffness cylindrical component into the industrial control computer, perform simulation analysis using finite element simulation software, and generate a network model dataset using the output simulation results;

[0023] Step 2.2: Perform deformation matching through feature points on the outer wall of the weak stiffness cylindrical component to obtain a global deformation result that matches the actual clamping coordinate system;

[0024] Step 2.3 Repeat steps 2.1-2.2 to obtain a sufficiently large training set and validation set for training and validation of the recurrent neural network global wall deformation prediction model;

[0025] Step three also includes the following steps:

[0026] Step 3.1 The industrial control computer outputs the machining trajectory of the outer wall of the weak stiffness cylindrical part through the digital model, and controls the machining end effector to perform outer surface machining according to the machining path;

[0027] Step 3.2 The displacement sensor detects the minute deformation displacement changes of the weak stiffness cylindrical component and outputs the data to the industrial control computer through the communication control module;

[0028] Step 3.3: Predict the real-time deformation at the processing location using a recurrent neural network global wall deformation prediction model;

[0029] Step 3.4 Generate tool cutting compensation amount based on predicted deformation amount and perform machining dynamic compensation.

[0030] Compared with the prior art, the present invention has the following advantages: it can predict the wall deformation during the milling process of cylindrical parts, thereby adjusting the tool in real time, completing dynamic compensation during the processing, and thus improving the processing accuracy; it can effectively reduce the deformation of cylindrical parts caused by the clamping of the fixture, thereby reducing the processing error; the same cylindrical part tooling can process the outer walls of cylindrical parts of multiple sizes, which can improve the tooling utilization rate, reduce production costs, and improve the level of production flexibility.

[0031] The following will further explain the concept, specific structure, and technical effects of the present invention in conjunction with the accompanying drawings, so as to fully understand the purpose, features, and effects of the present invention. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of one embodiment of the present invention;

[0033] Figure 2 This is a schematic diagram of a floating internal support tooling structure according to one embodiment of the present invention;

[0034] Figure 3 This is a schematic flowchart of a processing control method according to one embodiment of the present invention.

[0035] The components are: 1-Six-DOF robot, 2-Milling device, 3-Internal support floating fixture, 301-Internal support floating fixture base, 302-Auxiliary support module guide rail platform, 303-Auxiliary support module slider, 304-Auxiliary support module end floating groove surface pressure block, 305-Auxiliary support module floating groove surface pressure block slider connecting pin, 306-Displacement sensor, 307-First radial transmission gear, 308-Second radial transmission gear, 309-Clamping hole, 310-Communication control module, 4-Weak stiffness cylindrical component, 5-Industrial computer, 6-Robot control cabinet, 7-Machining platform. Detailed Implementation

[0036] The preferred embodiments of the present invention are described below with reference to the accompanying drawings to make the technical content clearer and easier to understand. The present invention can be embodied in many different forms, and the scope of protection of the present invention is not limited to the embodiments mentioned herein.

[0037] In the accompanying drawings, components with the same structure are indicated by the same numerical designation, and components with similar structures or functions are indicated by similar numerical designations. The dimensions and thicknesses of each component shown in the drawings are arbitrary, and the present invention does not limit the dimensions and thicknesses of each component. To make the illustrations clearer, the thickness of some components has been appropriately exaggerated in the drawings.

[0038] like Figure 1As shown, the intelligent machining system for milling the complex outer wall of a weak-stiff cylindrical component of the present invention includes a six-degree-of-freedom robot 1, a milling device 2 mounted at the end of the six-degree-of-freedom robot 1, a machining platform 7 corresponding to the milling device 2, an inner support floating fixture 3 mounted on the upper surface of the machining platform 7, a weak-stiff cylindrical component 4 to be machined being clamped on the machining platform 7 by the inner support floating fixture 3, an industrial control computer 5 controlling the entire machining system, performing finite element simulation (FES), recurrent neural network (RNN) training, and data transmission and processing, and a robot control cabinet 6 controlling the spatial motion of the six-degree-of-freedom robot 1. The industrial control computer 5 controls the spatial motion degrees of freedom of the six-degree-of-freedom robot 1 through the robot control cabinet 6 to realize the milling of the outer wall of the weak-stiff cylindrical component 4 by the milling device 2.

[0039] like Figure 2 As shown, the inner support floating fixture 3 includes an inner support floating fixture base 301 mounted on the upper surface of the processing platform 7. The inner support floating fixture 3 is provided with clamping holes 309 for clamping the weak-rigidity cylindrical part 4. The upper part of the inner support floating fixture 3 is provided with a gear transmission pair consisting of a first radial transmission gear 307 and a second radial transmission gear 308. An auxiliary support module guide rail platform 302 is mounted on the upper surface of the first radial transmission gear 307. Six auxiliary support modules are evenly distributed along the circumference of the auxiliary support module guide rail platform 302. Through the transmission of the gear pair and the threaded pair, the six auxiliary support modules can be adjusted by moving synchronously along the auxiliary support module guide rail.

[0040] The auxiliary support module includes an auxiliary support module slider 303 mounted on an auxiliary support module guide rail platform 302, which moves radially along the auxiliary support module guide rail via a gear pair and a threaded pair. An auxiliary support module end floating groove surface pressure block 304 is connected to the auxiliary support module slider 303 via an auxiliary support module floating groove surface pressure block slider connecting pin 305. Thus, the auxiliary support module slider 303 can drive the auxiliary support module end floating groove surface pressure block 304 to move, allowing the groove surface of the auxiliary support module end floating groove surface pressure block 304 to contact the inner surface of the weak stiffness cylindrical component 4. This increases the contact area with the weak stiffness cylindrical component 4, effectively reducing clamping pressure and minimizing the weak stiffness deformation of the weak stiffness cylindrical component 4. A spring is provided at the contact end of the floating groove pressure block 304 at the end of the auxiliary support module and the inner surface of the weak stiffness cylindrical part 4. This spring can provide the pre-tightening force for workpiece clamping and is used for floating positioning support of the weak stiffness cylindrical part 4. This helps to maintain clamping stability and reduces vibration during processing by utilizing the vibration absorption property of the spring.

[0041] The inner support floating fixture 3 also includes a displacement sensor 306 installed on the floating groove surface pressure block 304 at the end of the auxiliary support module. The displacement sensor 306 is used to detect the slight displacement change between the floating groove surface pressure block and the front end of the auxiliary support module, that is, the slight deformation and displacement of the weak stiffness cylindrical part 4 due to the cutting force when the tool contacts the weak stiffness cylindrical part 4. The displacement sensor 306 is preferably an infrared displacement sensor. The communication control module 310 installed inside the inner support floating fixture 3 is used to output the detected slight displacement change to the industrial control computer.

[0042] The milling device 2 includes a milling spindle and a cutting tool clamped on the milling spindle. The milling device 2 serves as an end effector for milling the outer wall of the weak rigidity cylindrical part 4.

[0043] When clamping the weak stiffness cylindrical part 4, six auxiliary support modules move synchronously inward or outward in the radial direction through gear pairs and threaded pairs to achieve automatic centering of the weak stiffness cylindrical part 4, adapting to the clamping of weak stiffness cylindrical parts 4 of different sizes to be processed. Since casting errors can cause uneven thickness of the weak stiffness cylindrical part 4, a floating amount can be set according to the error characteristics of the weak stiffness cylindrical part 4 to be processed, so as to ensure the clamping force of the weak stiffness cylindrical part 4. An appropriate floating amount can also suppress vibration during processing, increase cutting parameters, and reduce processing deformation.

[0044] When machining the weak-stiffness cylindrical part 4, the inner support floating fixture 3 provides outward support force to the outer wall of the weak-stiffness cylindrical part 4 in the normal direction. This can offset part of the deformation caused by the cutting force when the outer wall contacts the tool, reduce the error caused by the weak-stiffness deformation of the weak-stiffness cylindrical part 4, and improve the machining accuracy. Due to the floating setting of the auxiliary support module and the weak-stiffness deformation of the weak-stiffness cylindrical part 4 itself, when the tool contacts the weak-stiffness cylindrical part 4, the weak-stiffness cylindrical part 4 will produce a slight displacement and deformation due to the cutting force. The displacement sensor 306 detects the slight displacement change at the front end of the floating groove pressure block 304 at the end of the auxiliary support module, and outputs it to the central processing unit of the industrial control computer 5 through the communication control module 310 as the input of the global wall deformation prediction model of the recurrent neural network. The prediction model will output the workpiece deformation amount for the next step. The industrial control computer 5 adjusts the tool cutting parameters in real time to perform dynamic error compensation during the machining process, thereby effectively improving the wall machining accuracy.

[0045] like Figure 3 As shown, the adaptive machining method based on the above-mentioned intelligent machining system for complex outer wall milling of weak stiffness cylindrical thin-walled parts includes the following steps:

[0046] Step 1: Adaptive clamping and positioning of weak stiffness cylindrical components

[0047] First, weak-stiffness cylindrical parts of different sizes are placed on the internal support fixture. The auxiliary support module is adjusted using gear pairs and threaded pairs to achieve adaptive centering and clamping of the weak-stiffness cylindrical parts. Then, an appropriate float is set based on the error characteristics of the weak-stiffness cylindrical parts.

[0048] Step 2: Construct a finite element simulation-recurrent neural network global wall deformation prediction model, and collect training data and train and validate the recurrent neural network for predicting wall temporal deformation.

[0049] The digital model of the weakly stiff cylindrical component is imported into an industrial control computer. Using finite element simulation software, simulation conditions such as finite element mesh generation, material parameters, and boundary constraints are set. By applying a certain force to the weakly stiff cylindrical component to induce a certain displacement, the simulation results are output, generating a network model dataset. This step can also be performed offline using a proxy model for finite element simulation and result output, thereby improving model training efficiency and reducing manual labor.

[0050] By matching the simulated coordinate system with the actual clamping coordinate system using feature points on the outer wall of the weakly stiff cylindrical component, a global deformation result matching the actual clamping coordinate system is obtained. The displacement sensor location signal extracted from the global deformation result is used as the input variable of the wall deformation prediction model, and the global deformation result is used as the output label of the wall deformation prediction model. The above simulation process is repeated to obtain a sufficiently large training set and validation set for training and validating the recurrent neural network global wall deformation prediction model.

[0051] Step 3: Perform cutting. Based on the minute deformation of the weak stiffness cylindrical part, predict the real-time deformation at the machining position using a recurrent neural network global wall deformation prediction model, adjust the tool cutting parameters, and perform dynamic compensation for machining.

[0052] The robot performs workpiece and tool coordinate system alignment. The industrial computer outputs the machining trajectory of the weak-stiffness cylindrical part's outer wall via a digital model, controlling the end effector to perform outer surface machining according to the machining path. Displacement sensors detect minute deformations and displacement changes in the weak-stiffness cylindrical part, outputting this information to the industrial computer via a communication control module. The industrial computer's central processing unit predicts the real-time deformation at the machining position using a recurrent neural network global wall deformation prediction model. Based on the predicted deformation, it generates cutting compensation amounts and adjusts the tool cutting parameters in real time, performing dynamic compensation during the machining process.

[0053] This invention can predict wall deformation during the milling process of cylindrical parts, thereby adjusting the cutting tool in real time, completing dynamic compensation during the machining process, realizing adaptive machining of weak-rigidity cylindrical parts, improving machining accuracy, increasing production efficiency, and reducing labor costs; it can improve clamping stability, effectively reduce cylindrical part deformation caused by clamping, effectively suppress vibration during machining, increase cutting parameters, and thus reduce machining errors and improve machining accuracy; the same cylindrical part tooling can be used to position and clamp cylindrical parts of multiple sizes for outer wall machining, improving the flexible production level of weak-rigidity cylindrical parts, increasing fixture utilization, and saving production costs.

[0054] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A weak stiffness cylinder intelligent milling processing system, characterized in that, The weak stiffness cylinder is clamped by the inner support floating tool, and the weak stiffness cylinder is clamped by the inner support floating tool. The inner support floating tool comprises six auxiliary support modules which are uniformly distributed in the circumferential direction and are in contact with the inner wall of the weak stiffness cylinder, displacement sensors arranged at the ends of the auxiliary support modules, and a communication control module arranged in the inner support floating tool. The inner support floating tool further comprises an inner support floating tool base, a gear transmission pair composed of a first radial transmission gear and a second radial transmission gear arranged on the inner support floating tool base, an auxiliary support module guide rail platform arranged on the upper surface of the first radial transmission gear, the auxiliary support modules being uniformly distributed in the circumferential direction on the auxiliary support module guide rail platform, and the auxiliary support modules moving synchronously in the radial direction along the auxiliary support module guide rail through gear transmission and threaded transmission. The auxiliary support module comprises an auxiliary support module slider which moves in the radial direction along the auxiliary support module guide rail through gear transmission and threaded transmission, an auxiliary support module end floating groove surface pressing block connected to the auxiliary support module slider through an auxiliary support module floating groove surface pressing block slider connecting pin, and the groove surface of the auxiliary support module end floating groove surface pressing block being in contact with the inner surface of the weak stiffness cylinder. The displacement sensor detects the slight displacement change of the front end of the auxiliary support module end floating groove surface pressing block, and outputs the slight displacement change to the central processing unit of the industrial computer through the communication control module as the input of the recurrent neural network global wall deformation prediction model.

2. The weak stiffness cylindrical workpiece intelligent milling system of claim 1, wherein, A spring is arranged at the contact end of the auxiliary support module end floating groove surface pressing block and the inner surface of the weak stiffness cylinder.

3. The weak stiffness cylinder intelligent milling system according to any one of claims 1, wherein, The inner support floating tool is arranged on a machining platform.

4. The weak stiffener cylindrical workpiece intelligent milling system of any one of claims 1, wherein, The inner support floating tool further comprises a clamping hole for clamping the weak stiffness cylinder.

5. The weak stiffener cylindrical workpiece intelligent milling system of any one of claims 1, wherein, The milling device comprises a milling spindle and a cutter clamped on the milling spindle.

6. An adaptive machining method using the weak-rigidity cylinder piece intelligent milling machining system of claim 1 or 2, characterized in that, The method comprises the following steps: Step one, adaptive clamping and positioning of the weak stiffness cylinder; Step two, constructing a finite element simulation-recurrent neural network global wall deformation prediction model, collecting a training set, and training and verifying the wall time sequence deformation prediction recurrent neural network; Step three, performing cutting processing, predicting the real-time deformation of the machining position according to the slight deformation of the weak stiffness cylinder through the recurrent neural network global wall deformation prediction model, adjusting the cutter cutting amount, and performing dynamic compensation for machining.

7. The self-adaptive machining method of the weak-rigidity cylindrical workpiece intelligent milling system according to claim 6, characterized in that, Step one further comprises the following steps: Step 1.1 Adaptive centering clamping of weak stiffness cylinder with auxiliary support module; Step 1.2 Set appropriate floating amount according to error characteristics of weak stiffness cylinder; Step two further comprises the following steps: Step 2.1 Import the numerical model of weak stiffness cylinder into the industrial computer, and perform simulation analysis through finite element simulation software, and generate network model data set using the output simulation results; Step 2.2 Match the deformation amount through the feature points on the outer wall of the weak stiffness cylinder to obtain the global deformation result matched with the actual clamping coordinate system; Step 2.3 Repeat steps 2.1-2.2 to obtain a training set and a verification set of sufficient size, and perform training and verification of the recurrent neural network global wall deformation prediction model; Step three further comprises the following steps: Step 3.1 The industrial computer outputs the weak stiffness cylinder outer wall machining trajectory through the numerical model, and controls the machining end effector to perform outer surface machining according to the machining path; Step 3.2 The displacement sensor detects the micro deformation displacement change of the weak stiffness cylinder, and outputs to the industrial computer through the communication control module; Step 3.3 Predict the real-time deformation amount of the machining position through the recurrent neural network global wall deformation prediction model; Step 3.4 Generate tool cutting compensation amount according to the predicted deformation amount to perform dynamic compensation of machining.

Images