Intelligent planning method and system for machining path of mechanical arm of numerical control machine tool

Abstract

The invention discloses an intelligent machining path planning method and system for a mechanical arm of a numerical control machine tool, and relates to the technical field of mechanical arm machining path planning. The method comprises the steps that a transmission mechanism is used for converting rotary motion of a motor into a linear motion mode or a rotary motion mode of a mechanical arm joint; the motor is matched with the speed reducer to carry out speed control; according to the mechanical constraint relation between the mechanical arm connecting rods, the motor and the speed reducer are matched for position control; and the preset machining path is corrected online, and an optimized machining path is determined. The technical problem that in the prior art, stability and precision are insufficient during numerical control machine tool mechanical arm machining path planning is solved, and the technical effects that intelligent optimization of the numerical control machine tool mechanical arm machining path is achieved, and the stability and precision of the machining path are improved are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of robotic arm machining path planning, and particularly to an intelligent machining path planning method and system for a numerically controlled machine tool robotic arm. Background Art

[0002] During the machining process of a numerically controlled machine tool robotic arm, the planning of the machining path is crucial for machining quality and efficiency. In the prior art, the machining path planning of a numerically controlled machine tool robotic arm often fails to fully consider the motion coupling relationship between robotic arm joints, the mechanical constraint relationship between connecting rods, and complex environmental interference factors, resulting in insufficient stability and accuracy of the machining path, making it difficult to meet the high-precision machining requirements and unable to achieve intelligent optimization of the machining path.

[0003] The technical problem of insufficient stability and accuracy in the machining path planning of a numerically controlled machine tool robotic arm in the prior art. Summary of the Invention

[0004] This application provides an intelligent machining path planning method and system for a numerically controlled machine tool robotic arm, which is used to solve the technical problem of insufficient stability and accuracy in the machining path planning of a numerically controlled machine tool robotic arm in the prior art.

[0005] In view of the above problems, this application provides an intelligent machining path planning method and system for a numerically controlled machine tool robotic arm.

[0006] In the first aspect of this application, an intelligent machining path planning method for a numerically controlled machine tool robotic arm is provided. The method includes: The numerically controlled machine tool robotic arm includes robotic arm joints and robotic arm connecting rods, and a transmission mechanism converts the rotational motion of the motor into a linear motion mode or a rotational motion mode of the robotic arm joints; according to the motion coupling relationship between the robotic arm joints, the motor and the reducer are used in cooperation for speed control to determine a first set of cooperative motion control parameters suitable for the linear motion mode and a second set of cooperative motion control parameters suitable for the rotational motion mode; according to the mechanical constraint relationship between the robotic arm connecting rods, the motor and the reducer are used in cooperation for position control to determine a third set of cooperative motion control parameters suitable for the linear motion mode and a fourth set of cooperative motion control parameters suitable for the rotational motion mode; based on the path performance index, the preset machining path is corrected online by combining the first set of cooperative motion control parameters, the second set of cooperative motion control parameters, the third set of cooperative motion control parameters, and the fourth set of cooperative motion control parameters to determine the optimized machining path.

[0007] In the second aspect of this application, an intelligent machining path planning system for a numerically controlled machine tool robotic arm is provided. The system includes: A rotational motion conversion module is used for a robotic arm of a numerically controlled machine tool, which includes robotic arm joints and robotic arm connecting rods, and converts the rotational motion of a motor into a linear motion mode or a rotational motion mode of the robotic arm joints through a transmission mechanism; a speed control module is used to perform speed control by using the cooperation of the motor and a speed reducer according to the motion coupling relationship between the robotic arm joints, and determine a first set of cooperative motion control parameters adapted to the linear motion mode and a second set of cooperative motion control parameters adapted to the rotational motion mode; a position control module is used to perform position control by using the cooperation of the motor and a speed reducer according to the mechanical constraint relationship between the robotic arm connecting rods, and determine a third set of cooperative motion control parameters adapted to the linear motion mode and a fourth set of cooperative motion control parameters adapted to the rotational motion mode; an optimized machining path determination module is used to perform online correction on a preset machining path based on path performance indicators, and combine the first set of cooperative motion control parameters, the second set of cooperative motion control parameters, the third set of cooperative motion control parameters, and the fourth set of cooperative motion control parameters to determine an optimized machining path.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: The robotic arm of a numerically controlled machine tool includes robotic arm joints and robotic arm connecting rods, and converts the rotational motion of a motor into a linear motion mode or a rotational motion mode of the robotic arm joints through a transmission mechanism; performs speed control by using the cooperation of the motor and a speed reducer, and determines a first set of cooperative motion control parameters adapted to the linear motion mode and a second set of cooperative motion control parameters adapted to the rotational motion mode; performs position control by using the cooperation of the motor and a speed reducer, and determines a third set of cooperative motion control parameters adapted to the linear motion mode and a fourth set of cooperative motion control parameters adapted to the rotational motion mode; performs online correction on a preset machining path to determine an optimized machining path. It achieves the technical effect of realizing the intelligent optimization of the machining path of the robotic arm of a numerically controlled machine tool and improving the stability and accuracy of the machining path. Description of the Drawings

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0010] Figure 1 It is a schematic flow chart of a method for intelligent planning of a machining path of a robotic arm of a numerically controlled machine tool provided by an embodiment of this application; Figure 2 It is a schematic structural diagram of a system for intelligent planning of a machining path of a robotic arm of a numerically controlled machine tool provided by an embodiment of this application.

[0011] Description of reference numerals: Rotational motion conversion module 10, speed control module 20, position control module 30, optimized machining path determination module 40. Detailed implementation manners

[0012] This application provides a method and system for intelligent planning of the machining path of a CNC machine tool robot, which is used to solve the technical problems of insufficient stability and accuracy in the machining path planning of the CNC machine tool robot in the prior art.

[0013] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the protection scope of this application.

[0014] Embodiment 1, as Figure 1 shown, this application provides a method for intelligent planning of the machining path of a CNC machine tool robot, and the method includes: Step S100: The CNC machine tool robot includes a robot joint and a robot link, and a transmission mechanism is used to convert the rotational motion of the motor into a linear motion mode or a rotational motion mode of the robot joint.

[0015] Specifically, through the structural design of the robot joint and the robot link of the CNC machine tool robot, and using transmission mechanisms such as gear transmission and ball screw nut transmission, the rotational motion of the servo motor is converted into a linear motion mode of the robot joint (such as converting the motor rotation into a joint linear displacement through a ball screw nut) or a rotational motion mode (such as transmitting the motor rotation to the joint through gear transmission to achieve angular rotation), which provides an executable hardware motion conversion basis for subsequent determination of the speed control parameter set based on the joint motion coupling relationship, determination of the position control parameter set based on the link mechanical constraint relationship, and online correction of the machining path by combining the path performance index.

[0016] Step S200: According to the motion coupling relationship between the robot joints, the motor and the reducer are used in cooperation for speed control to determine a first cooperative motion control parameter set suitable for the linear motion mode and a second cooperative motion control parameter set suitable for the rotational motion mode.

[0017] Specifically, for the motion coupling relationship between the joints of the robotic arm, by collecting motion parameters such as joint angular velocity and angular acceleration, analyzing the speed transmission and mutual influence during the motion of each joint, and using the cooperation of the servo motor and the reducer, a speed closed-loop control algorithm (such as PID control) is adopted. In the linear motion mode, according to the speed conversion relationship of the lead screw drive, the matching parameters of the motor speed and the linear motion speed of the joint are determined to form the first set of cooperative motion control parameters; in the rotational motion mode, based on the gear transmission ratio, the corresponding relationship between the motor speed and the joint rotation angle is calculated to construct the second set of cooperative motion control parameters, thereby realizing the cooperative control of the joint speed in different motion modes and providing a speed control basis for the stability of the subsequent processing path.

[0018] Step S300: According to the mechanical constraint relationship between the connecting rods of the robotic arm, use the cooperation of the motor and the reducer to perform position control, and determine the third set of cooperative motion control parameters suitable for the linear motion mode and the fourth set of cooperative motion control parameters suitable for the rotational motion mode.

[0019] Specifically, based on the mechanical constraint relationship between the connecting rods of the robotic arm, the set of cooperative motion control parameters is determined through the following specific implementation means: First, use sensors to collect the force data of the connecting rods under different loads, combine finite element analysis to construct a mechanical model of the connecting rods, and quantitatively analyze the influence of factors such as load torque, inertial force, and external vibration on the position accuracy of the connecting rods; then, with the cooperation of the servo motor and the reducer, adopt a position closed-loop control strategy. In the linear motion mode, calculate the mapping parameters of the motor position pulse and the linear displacement of the joint through the displacement-torque relationship of the lead screw drive, and compensate the parameters in combination with environmental interference factors such as thermal deformation caused by temperature changes and joint clearance to form the third set of cooperative motion control parameters; in the rotational motion mode, based on the angle-torque transmission characteristics of the gear drive, analyze the influence of the flexible deformation of the connecting rod on the joint rotation angle, and determine the correction coefficient of the motor rotation angle and the actual rotation angle of the joint through interpolation algorithm and feedback compensation to construct the fourth set of cooperative motion control parameters, so as to realize the precise control of the position of the connecting rods in different motion modes.

[0020] Step S400: Based on the path performance index, combine the first set of cooperative motion control parameters, the second set of cooperative motion control parameters, the third set of cooperative motion control parameters, and the fourth set of cooperative motion control parameters to perform online correction on the preset processing path, and determine the optimized processing path.

[0021] Specifically, based on path performance indicators (including machining path stability, machining path accuracy, etc.), the following specific implementation means are used to perform online correction on the preset machining path: First, take four sets of collaborative motion control parameter sets as decision variables, embed the tool-workpiece cutting force parameters (such as workpiece material characteristic parameters, cutting speed, etc.) using the dynamic simulation model, simulate the dynamic load during the machining process, record the speed / acceleration data and position / orientation error of the preset machining path, and quantitatively evaluate the path performance indicators; then analyze the influence weights of each parameter set on the performance indicators, configure a multi-objective optimization index with the goal of minimizing the parameter adjustment amount and maximizing the performance improvement degree, update the decision variables through an iterative algorithm, and determine the optimized motion control parameter combination; at the same time, collect joint current data in real time to determine the load torque, compare it with the preset threshold to predict the change trend of the path performance, if the online correction mechanism is triggered, then evaluate the potential failure probability in combination with the Bayesian network fault prediction model, and finally perform dynamic interpolation correction on the preset path based on multi-source data fusion to determine the optimized machining path.

[0022] In a possible implementation manner, step S100 further includes: Step S110: Introduce machining requirement information and configure the preset machining path.

[0023] Step S120: Build a dynamic simulation model of the machining process of the CNC machine tool robotic arm, perform dynamic simulation verification on the preset machining path, and evaluate the path performance indicators, where the path performance indicators include machining path stability and machining path accuracy.

[0024] Specifically, when introducing machining requirement information to configure the preset machining path, the following specific implementation means are used: Use a 3D scanner to collect the three-dimensional structure of the workpiece, and read the workpiece material properties (such as the hardness parameters of carbon steel, the ductility parameters of aluminum alloy), the machining surface roughness requirements (such as Ra3.2), and the tool parameters (such as the diameter of the end mill, the helix angle) in the machining requirement information through the data interface; Based on CAD / CAM software such as UG / NX, according to the curvature characteristics and material cutting performance of the workpiece three-dimensional structure, use the equal scallop height method to generate the initial path nodes, so that the node distribution adapts to the surface undulation; Optimize the sorting of the initial path nodes through the genetic algorithm, follow the process principle of rough machining first and then finish machining, and machining the outer contour first and then the inner cavity, and finally use the B-spline curve interpolation algorithm to connect the nodes to generate a preset machining path including process parameters such as feed speed and cutting depth.

[0025] When constructing a dynamic simulation model for the machining process of a CNC machine tool robotic arm and conducting dynamic simulation verification, the following specific implementation means are adopted: In simulation software such as ANSYS, first set environmental interference factors such as thermal deformation caused by temperature changes and external vibration interference. Based on the impact analysis of joint clearances and flexible deformation of connecting rods, use the finite element method to establish a dynamic model including the joints, connecting rods, and transmission mechanisms of the robotic arm; then configure the cutting force parameters of the tool-workpiece (including workpiece material characteristic parameters, tool geometric parameters, cutting speed, feed rate, cutting depth), perform mesh division on the tool-workpiece contact area to analyze the magnitude and direction of the cutting force, and use the multi-point constraint method to apply the cutting force as a dynamic load to the center point of the tool, forming a cutting force parameter loading strategy; then import the preset machining path into the model, simulate the dynamic load during the machining process, record the speed / acceleration data and position / orientation error of the path in real time, quantitatively evaluate the stability of the machining path through the speed fluctuation amplitude and acceleration change rate, and quantitatively evaluate the accuracy of the machining path based on the position error value and attitude deviation angle, providing data support for subsequent path correction.

[0026] In a possible implementation manner, step S110 further includes: Step S111: Collect the three-dimensional structure of the workpiece, and analyze the workpiece material properties, machining surface roughness requirements, and tool parameters in the machining requirement information.

[0027] Step S112: Generate initial path nodes that conform to the three-dimensional structure of the workpiece based on the workpiece material properties, machining surface roughness requirements, and tool parameters in the machining requirement information.

[0028] Step S113: Sort and connect the initial path nodes to generate the preset machining path.

[0029] Specifically, use a three-dimensional scanner to collect the three-dimensional structure data of the workpiece, form a three-dimensional model including information such as the geometric shape and size of the workpiece, and at the same time analyze the machining requirement information to extract the workpiece material properties (such as material type, hardness, toughness, etc.), machining surface roughness requirements (such as specific roughness numerical indicators), and tool parameters (such as tool type, diameter, edge angle, etc.).

[0030] Using the path generation module of CAD / CAM software (such as UG, MasterCAM), determine the cutting depth and feed rate thresholds based on the workpiece material properties (such as the hardness parameters of 45 steel and the cutting coefficients of aluminum alloy), and calculate the tool path step size in combination with the tool parameters (such as the diameter of the end mill and the helix angle); set the residual height constraint according to the machining surface roughness requirement (such as Ra1.6), and use the equal residual height method to generate discrete points on the surface of the workpiece three-dimensional model, so that the residual height of the tool path between adjacent points does not exceed the roughness threshold; for the curved surface area, adaptively adjust the node density through curvature analysis, and increase the number of nodes in the high curvature area to ensure machining accuracy, and finally form an initial path node set that meets the material cutting characteristics, tool process parameters and surface roughness requirements.

[0031] When sorting and connecting the initial path nodes to generate the preset machining path, first, according to the machining process rules (such as rough machining first and then finish machining, outer contour first and then inner cavity) and the three-dimensional structure characteristics of the workpiece (such as the distribution of bosses and grooves), use the genetic algorithm to sort and optimize the initial path nodes to reduce the tool idle stroke and the number of reversals; then set the feed speed and cutting depth parameters according to the tool parameters (such as diameter and number of cutting edges) and the workpiece material properties (such as hardness and thermal conductivity), and connect the sorted nodes through the B-spline curve algorithm to form a smooth and continuous tool path; at the same time, embed the dynamic constraint conditions to avoid sudden acceleration and deceleration phenomena in the path, and finally generate a preset machining path including process parameters, path trajectory and dynamic constraints, providing a basic path model for the subsequent online correction based on four groups of coordinated motion control parameter sets.

[0032] In a possible implementation manner, step S120 further includes: Step S121: Set environmental interference factors including thermal deformation caused by temperature changes and external vibration interference.

[0033] Step S122: Based on the environmental interference factors, establish a dynamic simulation model by analyzing the influence of joint clearance and flexible deformation of the connecting rod.

[0034] Specifically, when setting the environmental interference factors, simulate the thermal deformation caused by temperature changes by defining the temperature field distribution parameters (such as the local temperature rise gradient caused by the motor heating during machine tool operation and the workshop environment temperature fluctuation range) in the simulation software, and at the same time input the frequency spectrum (such as the 10~50Hz periodic vibration generated by the operation of surrounding equipment) and amplitude parameters (such as 0.01~0.1mm) of the external vibration source to simulate the external vibration interference, so as to construct environmental interference conditions close to the actual machining scenario.

[0035] Based on the environmental interference factors such as thermally induced deformation and external vibration set, the joint clearance of the robotic arm (such as the radial clearance caused by bearing wear) and the flexible deformation of the connecting rod (such as the bending amount of the aluminum alloy connecting rod under the action of cutting force) are quantitatively analyzed through finite element analysis software. The change amount of the joint clearance is converted into the equivalent stiffness matrix of the kinematic pair, and the modal parameters of the flexible deformation of the connecting rod are imported into the multi-body dynamics model. Combining the mass, moment of inertia of each component of the robotic arm and the stiffness parameters of the transmission mechanism, a dynamic simulation model including the coupling of multi-physical fields of heat-structure-vibration is established. This model can reflect in real time the influence of joint motion error and connecting rod deformation on the end trajectory of the robotic arm under environmental interference.

[0036] In a possible implementation manner, step S120 further includes: Step S123: Embed the tool-workpiece cutting force parameters into the dynamic simulation model, simulate the dynamic load during the machining process of the CNC machine tool robotic arm, and record the speed data, acceleration data, position error, and attitude error of the preset machining path.

[0037] Step S124: Quantitatively evaluate the stability of the machining path in the path performance index through the speed data and acceleration data of the preset machining path.

[0038] Step S125: Quantitatively evaluate the accuracy of the machining path in the path performance index through the position error and attitude error of the preset machining path.

[0039] Specifically, when embedding the tool-workpiece cutting force parameters into the dynamic simulation model, first configure the workpiece material characteristic parameters (such as the hardness of 45# steel and the cutting resistance of aluminum alloy), tool geometric parameters (such as the rake angle and helix angle of the end mill), cutting speed, feed rate, cutting depth and other parameters, and perform mesh division on the tool-workpiece contact area through the finite element method to analyze the magnitude and direction of the cutting force; then use the magnitude and direction of the cutting force as the dynamic load and apply it to the tool center point of the dynamic simulation model in a multi-point constraint manner to simulate the dynamic load caused by the cutting force during the machining process; at the same time, record in real time the speed data, acceleration data, position error, and attitude error of the preset machining path under the action of the dynamic load, providing data support for the subsequent evaluation of the stability and accuracy of the machining path.

[0040] When quantitatively evaluating the stability of the machining path through the preset speed data and acceleration data of the machining path, first extract the real-time speed sequence and acceleration sequence of the path recorded in the dynamic simulation, calculate the standard deviation of the speed data to characterize the speed fluctuation range, and at the same time analyze the mutation frequency and absolute peak value of the acceleration curve; then compare the speed fluctuation range with the industry standard threshold (such as ±5% rated speed), and construct a stability evaluation matrix in combination with the acceleration change rate (the amount of acceleration change per unit time). The smaller the speed fluctuation range and the smoother the acceleration change, the higher the stability index. Finally, through dimensionless processing, convert the speed and acceleration characteristic parameters into a stability score of 0-100 to achieve the quantitative evaluation of the machining path stability.

[0041] When quantitatively evaluating the machining path accuracy through the preset position error and attitude error of the machining path, first extract the deviation value between the actual position of the robot end and the preset position recorded in the dynamic simulation, and the deviation angles between the actual attitude (such as pitch angle, yaw angle, roll angle) and the ideal attitude; then decompose the position error into components in the X, Y, and Z coordinate axes directions, and compare them with the tolerance band required by the machining accuracy. At the same time, analyze whether the attitude error exceeds the allowable range; finally, convert the position error and attitude error in each direction into a comprehensive accuracy index through the weighted average method. For example, the position error accounts for 70% and the attitude error accounts for 30%, and calculate an accuracy score of 0-100 to achieve the quantitative evaluation of the machining path accuracy.

[0042] In a possible implementation manner, step S123 further includes: Step S1231: Configure the tool-workpiece cutting force parameters, where the tool-workpiece cutting force parameters include workpiece material characteristic parameters, tool geometry parameters, cutting speed, feed rate, and cutting depth.

[0043] Step S1232: Perform mesh division on the tool-workpiece contact area, and analyze the magnitude and direction of the cutting force.

[0044] Step S1233: Take the magnitude and direction of the cutting force as dynamic loads, and apply multi-point constraints to the tool center point of the dynamic simulation model to determine the cutting force parameter loading strategy of the tool-workpiece cutting force parameters.

[0045] Specifically, when configuring the tool-workpiece cutting force parameters, it is necessary to first obtain the workpiece material property parameters, such as the hardness, tensile strength, elastic modulus of the workpiece material, etc., to clarify the cutting performance of the material; at the same time, obtain the tool geometric parameters, including the tool rake angle, clearance angle, principal cutting edge angle, auxiliary cutting edge angle, tool diameter and edge radius, etc., which directly affect the distribution and magnitude of the cutting force; in addition, it is also necessary to determine the machining parameters such as cutting speed, feed rate and cutting depth. Among them, the cutting speed affects the generation of cutting heat and cutting force, the feed rate determines the material removal rate per unit time, and the cutting depth is related to the magnitude of the cutting load. By comprehensively configuring these parameters, an accurate parameter basis is provided for subsequent analysis of the cutting force and simulation of the dynamic load during the machining process.

[0046] When meshing the tool-workpiece contact area and analyzing the cutting force, using ANSYS finite element software, set the meshing rules according to the tool geometric parameters (such as rake angle, clearance angle, cutting edge radius) and workpiece material properties (such as hardness, plastic deformation coefficient). In the initial contact area between the cutting edge and the workpiece, adopt the adaptive mesh refinement technology to discretize the contact area into quadrilateral or triangular elements with a minimum size of 0.01 mm; then based on the cutting force empirical formula (such as the Merchant cutting force model) or the finite element solver, calculate the shear force, friction force and plowing force components on each mesh element, and obtain the cutting force magnitude of a single mesh through vector synthesis, and then integrate along the main cutting edge direction of the tool to obtain the total cutting force; at the same time, according to the force direction distribution of the mesh elements, determine the main direction of the cutting force relative to the tool coordinate system (such as tangential, radial, axial components), providing accurate force field distribution data for subsequent dynamic load application.

[0047] When using the cutting force magnitude and direction as the dynamic load and applying it to the center point of the tool in the dynamic simulation model by multi-point constraint, first decompose the cutting force into tangential, radial and axial components, use MATLAB or Python to write the load application script, and calculate the time-domain variation curve of each component according to the cutting speed and feed rate; in the ANSYS dynamic simulation model, couple the center point of the tool with multiple key points on the cutting edge through the multi-point constraint (MPC) algorithm to form a load transfer path, so that the dynamic load is applied to the tool model according to the force field distribution obtained by meshing; set the gradient loading rules for different machining stages (such as cutting in, cutting, cutting out), for example, in the cutting-in stage, linearly increase from zero to 80% of the rated load according to a sine curve, keep the rated load in the cutting stage and superimpose a ±5% fluctuation caused by the unevenness of the workpiece material, and decay to zero exponentially in the cutting-out stage; at the same time, consider the influence of the mechanical arm joint clearance and the flexible deformation of the connecting rod on the load transfer, calculate the dynamic response of the load in the mechanical arm system by the finite element method, and finally form a cutting force parameter loading strategy including the load magnitude, direction, loading time sequence and transfer path to ensure that the simulation model accurately reflects the stress state in actual machining operation.

[0048] In a possible implementation manner, step S400 further includes: Step S410: Using the first co-motion control parameter set, the second co-motion control parameter set, the third co-motion control parameter set, and the fourth co-motion control parameter set as decision variables, analyze the influence weights on the path performance index.

[0049] Step S420: Through the influence weights, configure a multi-objective optimization index. With the goal of minimizing the parameter adjustment amount and maximizing the path performance improvement degree, continuously iterate and update the decision variables to determine the optimized motion control parameter combination corresponding to the preset machining path.

[0050] Specifically, when analyzing the influence weights with the first to fourth co-motion control parameter sets as decision variables, build a parameter-performance mapping model in the MATLAB / Simulink environment. First, define the value ranges of the first co-motion control parameter set (linear motion speed control parameter), the second co-motion control parameter set (rotary motion speed control parameter), the third co-motion control parameter set (linear motion position control parameter), and the fourth co-motion control parameter set (rotary motion position control parameter). Then, use the Taguchi method to design an orthogonal test matrix, and conduct a dynamic simulation test with each parameter set as a factor and the path stability and accuracy indicators as response values; calculate the contribution rates of each parameter set to the performance indicators through range analysis and variance analysis. For example, it is found that the influence weight of the linear motion speed control parameter on the stability indicator is 35%, and the influence weight of the rotary motion position control parameter on the accuracy indicator is 40%. And use a neural network to train the simulation data to construct a non-linear mapping relationship between the parameter set and the performance indicator, and finally determine the influence weight coefficient matrix of each parameter set.

[0051] When configuring the multi-objective optimization index through the influence weights, first multiply the influence weights of each co-motion control parameter set by the change rate of the performance indicator to construct a multi-objective optimization function including a stability improvement coefficient and an accuracy improvement coefficient, where the optimization goals are to minimize the parameter adjustment amount (the sum of the squares of the change amplitudes of each parameter set) and maximize the path performance improvement degree (the weighted sum of the stability and accuracy indicators); then use the non-dominated sorting genetic algorithm (NSGA-II) for iterative optimization. In each generation of evolution, perform crossover and mutation operations on the decision variables (the first to fourth co-motion control parameter sets) according to the optimization index, and screen out the Pareto optimal solutions through the elitist retention strategy; finally, determine the parameter combination that maximizes the ratio of the performance improvement degree to the parameter adjustment amount (optimization efficiency index) as the optimized motion control parameter combination to achieve the goal of obtaining the maximum path performance improvement at the minimum parameter adjustment cost.

[0052] In a possible implementation manner, step S400 further includes: Step S430: Collect joint current data in real time and determine the load torque of each robotic arm joint.

[0053] Step S440: Compare the load torque of each robotic arm joint with a preset load torque threshold range. If the load torque of any robotic arm joint exceeds the preset load torque threshold range, predict the change trend of the path performance under the current motion control parameter combination configuration.

[0054] Step S450: Determine whether to trigger the online correction mechanism based on the change trend of the path performance.

[0055] Specifically, high-precision current sensors installed at each joint of the robotic arm are used to collect joint current data in real time at a sampling frequency of 1000 Hz. The current signal is converted into the load torque of each robotic arm joint through the motor torque constant. For example, for a servo motor with a rated torque of 1.5 N·m, the real-time load torque can be calculated by multiplying the current value by the torque constant (such as 0.5 N·m / A).

[0056] When comparing the load torque of each robotic arm joint with the preset load torque threshold range, first, the real-time load torque signal is compared with the preset threshold (such as a ±20% fluctuation range of the rated torque) in real time through a data acquisition card. If the load torque of a certain joint exceeds the threshold, a prediction model based on the LSTM neural network is immediately started; this model takes the current load torque deviation value, historical load-performance data, and motion control parameter combination as inputs, and outputs the change curves of the path stability index (such as the speed fluctuation amplitude) and accuracy index (such as the position error) within the next 50 ms. For example, when the load torque of the elbow joint exceeds the upper limit by 25%, it is predicted that the stability of the machining path will decrease at a rate of 0.8% / ms. At the same time, the reliability of the prediction result is verified by combining the dynamic simulation model, so as to determine the change trend of the path performance under the current parameter combination.

[0057] When determining whether to trigger the online correction mechanism based on the changing trend of path performance, first set a preset performance degradation trigger threshold. For example, when the stability index of the processing path drops by more than 10% or the position error exceeds 0.05 mm, when the change in the performance index within the future processing cycle predicted by the LSTM neural network exceeds this threshold, the online correction mechanism is automatically triggered. In specific implementation, the change rates of the predicted stability index (such as the speed fluctuation amplitude) and the accuracy index (such as the attitude error angle) are compared with the threshold in real time. If the stability index is predicted to drop by 12% and the accuracy error reaches 0.06 mm, the optimized processing path determination module is immediately activated, the multi-objective optimization algorithm is called to regenerate the combination of motion control parameters, and the improvement effect of the new parameters on the performance index is quickly verified through the dynamic simulation model to ensure that the corrected parameter combination can control the performance fluctuation within the threshold range. If the changing trend of the performance is within the threshold, the current parameter combination is maintained, and the prediction model is continuously updated at a frequency of 500 Hz to ensure real-time monitoring and dynamic adjustment of the path performance.

[0058] In a possible implementation manner, step S450 further includes: Step S451: Construct a fault prediction model based on the Bayesian network, and use the load torque exceeding the torque threshold, the current combination of motion control parameters, and the historical fault data as input variables to evaluate the occurrence probabilities of different potential fault types.

[0059] Step S452: Generate a risk assessment reminder according to the occurrence probabilities of different potential fault types and in combination with the changing trend of path performance.

[0060] Specifically, when constructing a fault prediction model based on the Bayesian network, first extract the load torque data exceeding the torque threshold, the corresponding combination of motion control parameters, and the occurred fault types (such as joint bearing wear, transmission gear slipping, etc.) from the historical processing database to form a training data set including input variables (load torque deviation value, parameter combination feature vector) and output variables (fault type); then define the node structure of the Bayesian network, including the parent nodes (abnormality degree of load torque, stability of parameter combination) and the child nodes (potential fault types), calculate the conditional probability table between the nodes through the maximum a posteriori probability estimation method, and construct the network topology structure; when the current load torque data exceeding the torque threshold, the combination of motion control parameters, and the historical fault data are input, use the Bayesian inference algorithm (such as the joint tree algorithm) to calculate the posterior probabilities of each potential fault type. For example, the occurrence probability of the motor overheating fault is obtained as 40%, and the gear meshing fault probability is 25%, so as to evaluate the possibility of different faults occurring.

[0061] When generating a risk assessment reminder based on the occurrence probabilities of different potential fault types and combined with the changing trend of path performance, first perform a correlation analysis on the occurrence probabilities of each potential fault type output by the Bayesian network (such as bearing wear 40%, gear slippage 25%) and the predicted changing trend of path performance (such as stability decrease 18%, precision error increase 0.04 mm), and construct a risk matrix based on the fault severity and occurrence probability; then divide the risk level into three levels: high (red), medium (yellow), and low (green). For example, when the occurrence probability of a certain fault exceeds 30% and may cause the machining accuracy to exceed the tolerance, it is marked as a red warning; finally, generate a visual reminder including the fault type, occurrence probability, performance impact degree, and countermeasure suggestions. For example, red warning: the occurrence probability of bearing wear is 40%, which is expected to cause a 20% decrease in the accuracy of the machining path. It is recommended to immediately stop the machine to check the joint lubrication status and adjust the position control parameters, providing intuitive risk warnings and decision-making support for operators.

[0062] Embodiment 2, based on the same inventive concept as the machining path intelligent planning method for a robotic arm of a numerically controlled machine tool in the foregoing embodiment, as Figure 2 shown, the present application provides a machining path intelligent planning system for a robotic arm of a numerically controlled machine tool. The system in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the system includes: A rotational motion conversion module 10, which is used for a robotic arm of a numerically controlled machine tool including a robotic arm joint and a robotic arm link, and converts the rotational motion of a motor into a linear motion mode or a rotational motion mode of the robotic arm joint through a transmission mechanism.

[0063] A speed control module 20, which is used to perform speed control by using the cooperation of the motor and the reducer according to the motion coupling relationship between the robotic arm joints, and determine a first set of cooperative motion control parameters adapted to the linear motion mode and a second set of cooperative motion control parameters adapted to the rotational motion mode.

[0064] A position control module 30, which is used to perform position control by using the cooperation of the motor and the reducer according to the mechanical constraint relationship between the robotic arm links, and determine a third set of cooperative motion control parameters adapted to the linear motion mode and a fourth set of cooperative motion control parameters adapted to the rotational motion mode.

[0065] An optimized machining path determination module 40, which is used to perform online correction on a preset machining path based on path performance indicators, in combination with the first set of cooperative motion control parameters, the second set of cooperative motion control parameters, the third set of cooperative motion control parameters, and the fourth set of cooperative motion control parameters, and determine an optimized machining path.

[0066] Further, the system is also used to implement the following functions: Introduce the processing requirement information and configure the preset processing path; construct a dynamic simulation model for the machining process of the CNC machine tool robotic arm, conduct dynamic simulation verification on the preset processing path, and evaluate the path performance indicators, where the path performance indicators include the stability of the processing path and the accuracy of the processing path.

[0067] Furthermore, the system is also used to implement the following functions: Collect the three-dimensional structure of the workpiece, analyze the workpiece material properties, machining surface roughness requirements, and tool parameters in the processing requirement information; generate initial path nodes that conform to the three-dimensional structure of the workpiece based on the workpiece material properties, machining surface roughness requirements, and tool parameters in the processing requirement information; sort and connect the initial path nodes to generate the preset processing path.

[0068] Furthermore, the system is also used to implement the following functions: Set environmental interference factors including thermal deformation caused by temperature changes and external vibration interference; establish a dynamic simulation model based on the environmental interference factors by analyzing the effects of joint clearances and flexible deformations of the connecting rods.

[0069] Furthermore, the system is also used to implement the following functions: Embed the tool-workpiece cutting force parameters into the dynamic simulation model, simulate the dynamic loads during the machining process of the CNC machine tool robotic arm, and record the speed data, acceleration data, position error, and attitude error of the preset processing path; quantitatively evaluate the stability of the processing path in the path performance indicators through the speed data and acceleration data of the preset processing path; quantitatively evaluate the accuracy of the processing path in the path performance indicators through the position error and attitude error of the preset processing path.

[0070] Furthermore, the system is also used to implement the following functions: Configure the tool-workpiece cutting force parameters, where the tool-workpiece cutting force parameters include workpiece material characteristic parameters, tool geometric parameters, cutting speed, feed rate, and cutting depth; perform mesh division on the tool-workpiece contact area, analyze the magnitude and direction of the cutting force; use the magnitude and direction of the cutting force as dynamic loads, and apply multi-point constraints to the tool center point of the dynamic simulation model to determine the cutting force parameter loading strategy of the tool-workpiece cutting force parameters.

[0071] Furthermore, the system is also used to implement the following functions: Taking the first co - motion control parameter set, the second co - motion control parameter set, the third co - motion control parameter set, and the fourth co - motion control parameter set as decision variables, analyze the influence weights on the path performance index; through the influence weights, configure a multi - objective optimization index, aiming to minimize the parameter adjustment amount and maximize the path performance improvement degree, continuously iterate and update the decision variables, and determine the optimized motion control parameter combination corresponding to the preset machining path.

[0072] Further, the system is also used to implement the following functions: Real - time collect joint current data to determine the load torque of each robotic arm joint; compare the load torque of each robotic arm joint with the preset load torque threshold range. If the load torque of any robotic arm joint exceeds the preset load torque threshold range, predict the path performance change trend under the current motion control parameter combination configuration; judge whether to trigger the online correction mechanism through the path performance change trend.

[0073] Further, the system is also used to implement the following functions: Construct a fault prediction model based on a Bayesian network, taking the load torque exceeding the torque threshold, the current motion control parameter combination, and historical fault data as input variables, evaluate the occurrence probability of different potential fault types; generate a risk assessment reminder according to the occurrence probability of different potential fault types and in combination with the path performance change trend.

[0074] It should be noted that the above - mentioned order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above - mentioned specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi - task processing and parallel processing are also possible or may be advantageous.

[0075] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0076] This specification and the drawings are only exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An intelligent planning method for the machining path of a robotic arm of a numerically controlled machine tool, characterized in that, The method includes: The robotic arm of the numerically controlled machine tool includes robotic arm joints and robotic arm links, and a transmission mechanism converts the rotational motion of the motor into a linear motion mode or a rotational motion mode of the robotic arm joints; According to the motion coupling relationship between the robotic arm joints, the motor and the reducer are used in cooperation for speed control to determine a first set of cooperative motion control parameters adapted to the linear motion mode and a second set of cooperative motion control parameters adapted to the rotational motion mode; According to the mechanical constraint relationship between the robotic arm links, the motor and the reducer are used in cooperation for position control to determine a third set of cooperative motion control parameters adapted to the linear motion mode and a fourth set of cooperative motion control parameters adapted to the rotational motion mode; Based on the path performance index, the preset machining path is corrected online by combining the first set of cooperative motion control parameters, the second set of cooperative motion control parameters, the third set of cooperative motion control parameters, and the fourth set of cooperative motion control parameters to determine an optimized machining path.

2. The intelligent processing path planning method for the robotic arm of a numerically controlled machine tool according to claim 1, wherein, The machining requirement information is introduced to configure the preset machining path; A dynamic simulation model of the machining process of the robotic arm of the numerically controlled machine tool is constructed to perform dynamic simulation verification on the preset machining path and evaluate the path performance index, and the path performance index includes machining path stability and machining path accuracy.

3. The intelligent planning method for the machining path of a robotic arm of a numerically controlled machine tool according to claim 2, wherein The machining requirement information is introduced to configure the preset machining path, and the method includes: Collect the three-dimensional structure of the workpiece and analyze the workpiece material properties, machining surface roughness requirements, and tool parameters in the machining requirement information; Based on the workpiece material properties, machining surface roughness requirements, and tool parameters in the machining requirement information, generate initial path nodes that conform to the three-dimensional structure of the workpiece; Sort and connect the initial path nodes to generate the preset machining path.

4. The intelligent processing path planning method for the robotic arm of a numerically controlled machine tool according to claim 2, wherein, A dynamic simulation model of the machining process of the robotic arm of the numerically controlled machine tool is constructed, and the method further includes: Set environmental interference factors including thermal deformation caused by temperature change and external vibration interference; Based on the environmental interference factors, a dynamic simulation model is established by analyzing the influence of joint clearance and flexible deformation of the links.

5. The intelligent processing path planning method for a robotic arm of a numerical control machine tool according to claim 4, wherein, Perform dynamic simulation verification on the preset machining path and evaluate the path performance index, and the method includes: Embed the tool-workpiece cutting force parameters into the dynamic simulation model, simulate the dynamic load during the machining process of the robotic arm of the numerically controlled machine tool, and record the speed data, acceleration data, position error, and attitude error of the preset machining path; Quantitatively evaluate the machining path stability in the path performance index through the speed data and acceleration data of the preset machining path; Quantitatively evaluate the machining path accuracy in the path performance index through the position error and attitude error of the preset machining path.

6. The intelligent processing path planning method for a robotic arm of a numerically controlled machine tool according to claim 5, wherein, Embed the tool-workpiece cutting force parameters into the dynamic simulation model, and the method further includes: Configure the tool-workpiece cutting force parameters, and the tool-workpiece cutting force parameters include workpiece material characteristic parameters, tool geometry parameters, cutting speed, feed rate, and cutting depth; Perform mesh division on the tool-workpiece contact area and analyze the magnitude and direction of the cutting force; Taking the magnitude and direction of the cutting force as dynamic loads, apply multi-point constraints to the tool center point of the dynamic simulation model to determine the cutting force parameter loading strategy for the tool-workpiece cutting force parameters.

7. The intelligent processing path planning method for the robotic arm of a numerically controlled machine tool according to claim 1, wherein Based on the path performance index, combine the first co-motion control parameter set, the second co-motion control parameter set, the third co-motion control parameter set, and the fourth co-motion control parameter set to perform online correction on the preset machining path. The method includes: Taking the first co-motion control parameter set, the second co-motion control parameter set, the third co-motion control parameter set, and the fourth co-motion control parameter set as decision variables, analyze the influence weights on the path performance index; Through the influence weights, configure a multi-objective optimization index, aiming to minimize the parameter adjustment amount and maximize the path performance improvement degree, continuously iterate and update the decision variables to determine the optimized motion control parameter combination corresponding to the preset machining path.

8. The intelligent processing path planning method for the robotic arm of a numerical control machine tool according to claim 7, characterized in that, After determining the optimized motion control parameter combination corresponding to the preset machining path, the method includes: Collect joint current data in real time to determine the load torque of each robotic arm joint; Compare the load torque of each robotic arm joint with the preset load torque threshold range. If the load torque of any robotic arm joint exceeds the preset load torque threshold range, predict the path performance change trend under the current motion control parameter combination configuration; Judge whether to trigger the online correction mechanism through the path performance change trend.

9. The intelligent planning method for the machining path of a robotic arm of a numerically controlled machine tool according to claim 8, wherein, The method further includes: Construct a fault prediction model based on a Bayesian network, using the load torque exceeding the torque threshold, the current motion control parameter combination, and historical fault data as input variables to evaluate the occurrence probability of different potential fault types; Generate a risk assessment reminder according to the occurrence probability of different potential fault types and in combination with the path performance change trend.

10. An intelligent processing path planning system for a robotic arm of a numerically controlled machine tool, characterized in that, The system is used to implement the intelligent planning method for the machining path of a robotic arm of a numerically controlled machine tool according to any one of claims 1-9. The system includes: A rotational motion conversion module, which is used for a robotic arm of a numerically controlled machine tool including robotic arm joints and robotic arm links, and converts the rotational motion of the motor into a linear motion mode or a rotational motion mode of the robotic arm joints through a transmission mechanism; A speed control module, which is used to perform speed control by using the cooperation of the motor and the reducer according to the motion coupling relationship between the robotic arm joints, and determine the first co-motion control parameter set adapted to the linear motion mode and the second co-motion control parameter set adapted to the rotational motion mode; A position control module, which is used to perform position control by using the cooperation of the motor and the reducer according to the mechanical constraint relationship between the robotic arm links, and determine the third co-motion control parameter set adapted to the linear motion mode and the fourth co-motion control parameter set adapted to the rotational motion mode; An optimized machining path determination module, which is used to perform online correction on the preset machining path based on the path performance index, in combination with the first co-motion control parameter set, the second co-motion control parameter set, the third co-motion control parameter set, and the fourth co-motion control parameter set, to determine the optimized machining path.

Images