Processing center control method and system based on artificial intelligence

Abstract

The invention discloses a machining center control method and system based on artificial intelligence, and belongs to the technical field of intelligent control. The method comprises the steps that a simulation model is created, and a first track of a milling head is simulated and generated; the machining sequence and the corresponding switching track are optimized according to the switching path position of the milling head between the different machining positions and the shortest distance principle; sensing information and abrasion information of a milling head, the material of a to-be-machined workpiece and the cutting speed are collected in real time, the cutting model is input to obtain cutting parameters, and a predicted cutting track is generated in combination with the simulation model; selecting a representative position in the predicted cutting track, and judging whether correction is needed or not; when correction is needed, a correction position is calculated according to a projection area maximum principle, and a second track is generated based on the correction position, the predicted cutting track and the optimized switching track; and driving machining according to the control parameters of the second track. According to the system, through dynamic prediction and local track correction, the machining precision and efficiency are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent control, in particular to a machining center control method and system based on artificial intelligence. BACKGROUND

[0002] With the continuous development of manufacturing industry, the precision and efficiency of machining center are increasingly required. The traditional machining center control method mainly relies on preset programs and fixed trajectory planning, which is difficult to adapt to various complex situations in the machining process and has certain limitations. Similar prior art has a Chinese patent with publication number CN113885433A, which proposes a digital control method and device for an intelligent milling machine, including: monitoring the control data of the intelligent milling machine in response to the start signal, the control data including the processing control time of the control unit of the intelligent milling machine for any one processing device at the target position; generating processing path data based on the control data, the processing path data being the first processing information of all processing devices participating in processing in the intelligent milling machine from the time when the start signal is received to the current time, the first processing information including position information and time information; saving the processing path data at intervals of a preset time period; when the intelligent milling machine reaches the first preset condition, the processing path data saved at the previous nearest time is retrieved, and the processing path data is compared with the preset path data to obtain the second processing information; controlling the processing device of the intelligent milling machine based on the second processing information, which can realize intelligent control and realize the processing of semi-finished products. In addition, similar prior art has a Chinese patent with publication number CN119439883A, which proposes an intelligent numerical control machining method and system for mold manufacturing, including obtaining the mold to be cut pattern and planning the milling cutter feed route, dividing it into multiple milling cutter feed sub-routes, determining the milling cutter control trajectory composed of spline curves, clustering the milling cutter control trajectory to obtain multiple trajectory sets, and milling the mold according to the milling cutter priority order. In the milling process, real-time processing trajectories are collected, curvature deviation values are calculated, and if the preset value is exceeded, the milling cutter control trajectory is corrected. The milling cutter priority is sorted by working radius size, and suitable trajectory sets are selected for milling in turn until all trajectory sets are completed. Through intelligent path planning and real-time deviation correction, the milling cutter efficiency and processing precision are significantly improved, ensuring high quality and high stability of mold manufacturing. The above two patent documents solve the problem of machine tool machining control, but cannot effectively optimize the switching trajectory of the milling head between different machining positions, resulting in long idle path and low processing efficiency. Moreover, in the machining process, due to the lack of effective real-time monitoring and correction mechanism, once the machining deviation occurs, it is difficult to discover and correct in time, thereby affecting the final machining quality. SUMMARY

[0003] The application provides a machining center control method and system based on artificial intelligence, which significantly improves the control accuracy and efficiency of the gantry machining center through artificial intelligence technology. A simulation model is created based on the equipment information of the gantry machining equipment, the machining information of each to-be-machined position of the to-be-machined piece, the milling head information, and the first trajectory of the milling head corresponding to each to-be-machined position is simulated based on the simulation model; The machining sequence and the switching trajectory in the first trajectory are optimized according to the switching path position and the shortest distance principle of the milling head between different to-be-machined positions; The sensing information and wear information of the milling head, the material and cutting shape of the to-be-machined piece are input into a cutting model to obtain cutting parameters, and the cutting parameters are input into the simulation model to generate a predicted cutting trajectory in the first trajectory of the milling head; Representative positions in the predicted cutting trajectory are selected, and whether the representative positions need to be corrected is determined according to the polygon formed between each representative position and the adjacent representative position; When correction is needed, a correction position of the representative position is obtained according to the maximum projection area principle, and a second trajectory is generated based on the correction position, the predicted cutting trajectory and the switching trajectory; The to-be-machined piece is machined based on the control parameters corresponding to the second trajectory, and when the real-time error is greater than the error threshold, the method of obtaining the second trajectory is repeated.

[0004] As a preferred technical solution of the application, the first trajectory of the milling head is obtained by: A simulation model is established based on the equipment information of the gantry machining equipment, the shape and material of the to-be-machined piece, and the positional relationship therebetween, the machining information corresponding to each to-be-machined position of the to-be-machined piece, the milling head information and the equipment information are input into the simulation model, and the working process of the milling head is simulated according to the preset machining program corresponding to the machining information of each to-be-machined position, thereby obtaining the first trajectory of the milling head.

[0005] As a preferred technical solution of the application, the machining sequence and the switching trajectory in the first trajectory are optimized by: The switching trajectory between the first to-be-machined position and the second to-be-machined position of the milling head is obtained, the state information of the switching trajectory after processing is simulated according to the simulation model, the first shortest distance and the second shortest distance corresponding to the switching trajectory position before and after processing are obtained based on the shortest path principle, and when the first shortest distance is greater than the second shortest distance, the processing sequence of the switching trajectory position is prior to the processing sequence of the first to-be-machined position and the second to-be-machined position, otherwise, it remains unchanged; Optimize a switching trajectory in the first trajectory according to a trajectory corresponding to a minimum value of the first shortest distance and the second shortest distance.

[0006] As a preferred technical solution of the present application, the acquisition of the predicted cutting trajectory comprises: In the process of machining the workpiece by the milling head based on the control parameters corresponding to the first trajectory, the sensing information and wear information of the milling head are collected in real time, and the sensing information, wear information, material quality and cutting shape of the workpiece are input into the cutting model to obtain cutting information, the cutting information comprising the rotating speed, rotating number, feed speed and cutting amount of the milling head, and the cutting information is input into the simulation model to obtain the predicted cutting trajectory corresponding to a future preset time period.

[0007] As a preferred technical solution of the present application, the determination of whether the representative position needs to be corrected comprises: The predicted cutting trajectory is divided into a plurality of small regions, and the center point of each small region is taken as a machining position of the milling head, any position of the milling head is taken as a first point, a point in the predicted cutting trajectory having an angle greater than a set angle with a cutting surface corresponding to the face on which the i-th point is located is selected as an i+1-th point, the i-th point is taken as the representative position, the i-th point and the adjacent other points are connected to form a non-intersecting polygonal figure, the polygonal figure is mapped onto the cutting surface on which the i-th point is located to obtain a mapped figure, the ratio of the first area of the mapped figure to the second area of the polygonal figure is calculated, and when the ratio is greater than or equal to a set value, the i-th point does not need to be corrected, and when the ratio is less than the set value, the i-th point needs to be corrected.

[0008] As a preferred technical solution of the present application, the generation of the second trajectory comprises: When the representative position needs to be corrected, the representative position is adjusted while meeting the machining conditions, so that the adjusted representative position corresponds to the maximum mapping area of the figure on the cutting surface on which the representative position corresponds, the adjusted representative position is taken as the corrected position, the corrected position replaces the representative position in the predicted cutting trajectory, and the predicted cutting trajectory after replacement and the switching trajectory are taken as the second trajectory.

[0009] As a preferred technical solution of the present application, the cutting model is a model trained by historical data, and the historical data comprises historical sensing information, historical wear information, material quality, cutting shape of the workpiece and corresponding historical cutting information.

[0010] As a preferred technical scheme of the present application, the gantry machining equipment comprises a plurality of milling heads, and the milling heads can be automatically switched.

[0011] The present application also provides a machining center control system based on artificial intelligence, which is used to realize the above method, and comprises: a modeling unit, which is used to create a simulation model, simulate a first trajectory of each machining position corresponding to the milling head based on equipment information of the gantry machining equipment, machining information of each machining position of the workpiece to be machined, milling head information and the simulation model; an optimization unit, which is used to optimize machining sequencing and switching trajectories in the first trajectory according to switching path positions of the milling head between different machining positions and the shortest distance principle; a prediction unit, which is used to input sensing information, wear information of the milling head, material and cutting shape of the workpiece to be machined into a cutting model to obtain cutting parameters, input the cutting parameters into the simulation model to generate predicted cutting trajectories in the first trajectory of the milling head; a judgment unit, which is used to select representative positions in the predicted cutting trajectories, and judge whether the representative positions need to be corrected according to a polygon formed between each representative position and adjacent representative positions; a generation unit, which is used to obtain correction positions of the representative positions according to the maximum projection area principle when correction is needed, generate a second trajectory based on the correction positions, the predicted cutting trajectories and the switching trajectories; a control unit, which is used to process the workpiece to be machined based on control parameters corresponding to the second trajectory, and repeat the method of obtaining the second trajectory when real-time error is greater than an error threshold.

[0012] The present application also provides a computer readable storage medium, which stores instructions, and the instructions are executed by a processor to realize the above method.

[0013] The present application has the following advantages: The application patent significantly improves the control accuracy and efficiency of the gantry machining center through artificial intelligence technology. The simulation model established by equipment information, processing information and milling head information can generate the above-mentioned first trajectory corresponding to each to-be-processed position, and the cutting parameters are dynamically updated through real-time sensing data and wear information, so that the predicted cutting trajectory always matches the actual state of the physical system, solving the problem that the theoretical model is disconnected with the real-time working condition in traditional numerical control machining. Secondly, the unique "projection area ratio" correction mechanism, namely the representative position correction, intelligently identifies the position needing correction by analyzing the projection area ratio of the polygon formed by the discrete points on the cutting plane, and optimizes the spatial pose with the goal of maximizing the projection area, reduces the machining error of complex surfaces, reduces the radial cutting force, and prolongs the tool life. Thirdly, the switching trajectory optimization algorithm dynamically adjusts the processing sequence and shortens the idle path by simulating and predicting the spatial changes before and after the processing of the passing position. Finally, the system adopts the "local correction instead of global re-planning" strategy to meet the real-time demand of high-speed machining, and forms a closed-loop control of "sensing monitoring-AI prediction-dynamic correction", which greatly improves the machining quality stability of precision parts such as large structural parts. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor based on these drawings.

[0015] Figure 1 The flow chart of the machining center control method based on artificial intelligence in the embodiment of the present application; Figure 2 The method flow chart of optimizing processing sequence and switching trajectory in the embodiment of the present application; Figure 3 The method flow chart of judging whether the representative position needs to be corrected in the embodiment of the present application; Figure 4 The structure diagram of the machining center control system based on artificial intelligence in the embodiment of the present application. DETAILED DESCRIPTION

[0016] The embodiments of the present application provide a machining center control method and system based on artificial intelligence. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0017] For ease of understanding, the specific procedures of the embodiments of the present application are described as follows, as shown in the drawings, a machining center control method based on artificial intelligence in the embodiments of the present application comprises: Figure 1 Step S1: creating a simulation model, based on the equipment information of the gantry machining equipment, the machining information of each to-be-machined position of the to-be-machined piece, the milling head information and the simulation model simulating the first trajectory of the milling head corresponding to each to-be-machined position; Specifically, the equipment information of the gantry machining equipment includes the machine tool type, shape and structure of the gantry machining equipment, and based on the above-mentioned equipment information of the gantry machining equipment, the shape and material of the to-be-machined piece, and also according to the positional relationship between the gantry machining equipment and the to-be-machined piece, a simulation model is established, the machining information corresponding to each to-be-machined position on the to-be-machined piece, the milling head information corresponding to each to-be-machined position and the equipment information are input into the simulation model, wherein the machining information includes the machining shape and cutting amount of the to-be-machined position, and the milling head information is the size and material of the milling head, and an initial machining trajectory, i.e. the first trajectory, is generated in combination with a preset machining program, the first trajectory includes a switching path between the cutting path and different to-be-machined positions, the technical solution can obtain a high-precision simulation model, and the first trajectory of the milling head corresponding to each to-be-machined position is obtained according to the simulation model, which lays a foundation for subsequent high-precision and high-efficiency machining of the to-be-machined piece.

[0018] Step S2: optimizing the machining sequence and the switching trajectory in the first trajectory according to the switching path position of the milling head between different to-be-machined positions and the shortest distance principle; ​Specifically, for the multi-position machining scene, an optimization mechanism based on "path position state prediction" is proposed. For example: when the milling head switches from position A to position B, if the area C passed through is a to-be-machined area, the spatial topography after material removal in area C is simulated through the simulation model, such as the height change after the milling of a boss, and the shortest collision-free path before and after material removal is calculated: compare the current path length L1 with the path length L2 after C area machining, if L1>L2, then advance the C area machining sequence, and use the physical property of "material removal creates space" to shorten the idle travel; at the same time, update the switching trajectory with the trajectory corresponding to the minimum value of L1 and L2, this optimization shortens the idle travel path, especially for complex box-shaped parts, the efficiency is improved significantly, and the defect of ignoring the dynamic environmental changes in traditional TSP (Traveling Salesman Problem) algorithm is avoided.

[0019] Step S3: input the real-time collected sensing information of the milling head, wear information, material and cutting shape of the to-be-machined part into the cutting model to obtain cutting parameters, and input the cutting parameters into the simulation model to generate a predicted cutting trajectory in the first trajectory of the milling head; Specifically, in the initial trajectory execution, multi-source real-time data such as the temperature, friction, vibration data of the milling head and the wear information of the above milling head are synchronously collected, the above data is input into a cutting model trained by historical machining data, such as an LSTM neural network, and dynamic cutting information is output, including the above cutting information including the rotation speed, rotation number, feed speed and cutting amount of the above milling head. The model compensates for the stiffness decay, material local hardening and other nonlinear factors caused by tool wear through online learning, and the updated parameters drive the simulation model to regenerate the predicted cutting trajectory in the future period, such as the next 200ms, realize the transition from "preset theoretical path" to "working condition adaptive path", and reduce the machining precision fluctuation by more than 30%.

[0020] Step S4: select a representative position in the predicted cutting trajectory, and determine whether the representative position needs to be corrected according to a polygon formed between each representative position and an adjacent representative position; Specifically, the predicted trajectory is discretized into a dense point cloud, that is, the continuous predicted cutting trajectory is divided into multiple small regions, the center point of each region is regarded as the theoretical machining position of the milling head, and a representative position, that is, the i-th position, is selected to ensure that the selected position is located in a region where the curvature of the trajectory changes, but the change is not too large. The i-th position and its adjacent positions are connected to form a non-intersecting polygonal graph. The polygonal graph is projected onto the tangent plane corresponding to the i-th position to generate a two-dimensional mapping graph. The ratio of the area of the mapping graph, that is, the first area S1, to the area of the original polygonal graph, that is, the second area S2, is calculated. When the above ratio is greater than or equal to the above set value, no correction is needed. Otherwise, when the above ratio is less than the above set value, it indicates that the local surface is highly twisted or steeply fluctuating, and the tool will cause overcutting or undercutting if it is machined according to the original path, so the correction needs to be triggered. The above technical solution breaks through the limitations of the traditional curvature threshold-based method, quantifies the "surface developability" through the area ratio, and improves the accuracy of overcutting / undercutting identification in free-form surface machining to 92%.

[0021] Step S5: When correction is needed, a correction position of the representative position is obtained according to the principle of maximum projection area of the graph, and a second trajectory is generated based on the correction position, the predicted cutting trajectory and the switching trajectory; Specifically, for the representative position that needs to be corrected, an optimization problem is solved in a constraint space, which can be a tool-workpiece collision envelope or a machine tool stroke limit. The spatial coordinates of the representative position are adjusted to maximize the mapping area of the corresponding polygonal graph on the tangent plane corresponding to the representative position, and a correction position is obtained. The correction point replaces the representative position in the original trajectory, and the trajectory of the non-correction region remains unchanged. Finally, the second trajectory is synthesized with the optimized switching trajectory. This local correction strategy controls the calculation time within 5 ms, avoiding the real-time interruption caused by global re-planning. The above technical solution reduces the machining error of complex surfaces while ensuring machining efficiency.

[0022] Step S6: Based on the control parameters corresponding to the second trajectory, the workpiece to be machined is machined, and when the real-time error is greater than the error threshold, the method of repeatedly obtaining the second trajectory is repeated.

[0023] Specifically, the second trajectory is converted into machine tool executable instructions after processing, such as speed look-ahead control and acceleration smoothing processing, to drive multiple milling heads to cooperate in machining. The system continuously monitors the deviation between the actual trajectory and the second trajectory. When the error exceeds the error threshold, the correction cycle of re-prediction-S5, that is, the method of repeatedly obtaining the second trajectory, is triggered from step S3. This closed-loop architecture combines "feedforward prediction" (step S3) and "feedback correction" (steps S4-S5) to form a real-time control loop with small response delay, reducing the full-process precision fluctuation range of long-period machining of large structural parts.

[0024] Further, the first trajectory of the milling head is obtained by: The simulation model is established based on the equipment information of the gantry machining device, the shape and material of the workpiece to be machined, and the positional relationship therebetween. The machining information corresponding to each machining position on the workpiece to be machined, the milling head information, and the equipment information are input into the simulation model. The working process of each milling head is simulated according to the preset machining program corresponding to the machining information of each machining position, and the first trajectory of the milling head is obtained.

[0025] Specifically, the equipment information of the gantry machining device includes the machine tool model, the shape, and the structure of the gantry machining device. The simulation model is established based on the equipment information of the gantry machining device, the shape and material of the workpiece to be machined, and the positional relationship therebetween. The machining information corresponding to each machining position on the workpiece to be machined, the milling head information corresponding to each machining position, and the equipment information are input into the simulation model. The machining information includes the machining shape and the cutting amount of the machining position. The milling head information includes the size and the material of the milling head. The working process of each milling head is simulated based on the preset machining program corresponding to the machining information of each position through each simulation model, and the first trajectory of each milling head is obtained. The preset machining program is a control program corresponding to the milling head. The first trajectory includes the switching trajectory between different machining positions and the cutting trajectory at the machining position. The technical solution can obtain the ideal machining path of the milling head corresponding to each machining position, i.e., the first path.

[0026] Further, the machining sequence is optimized, and the switching trajectory in the first trajectory is optimized, as shown in Figure 2 The technical solution is shown in According to the switching trajectory of the milling head between the first machining position and the second machining position, the state information of the approach position after machining is simulated according to the simulation model. The first shortest distance and the second shortest distance corresponding to the approach position before and after machining are obtained based on the shortest path principle. When the first shortest distance is greater than the second shortest distance, the machining sequence of the approach position is prior to the machining sequence of the first machining position and the second machining position. Otherwise, the machining sequence remains unchanged. The switching trajectory in the first trajectory is optimized according to the trajectory corresponding to the minimum value of the first shortest distance and the second shortest distance.

[0027] Specifically, when the milling head switches from the first machining position to the second machining position for machining, the switching trajectory between the first machining position and the second machining position may pass through a machining position, and the switching trajectory may need to bypass the machining position before machining, so that the switching trajectory may be shortened after machining the machining position, for example, the space change caused by material removal, so that the state of the machining position after machining, that is, the state of the machining position after the excess material is removed, is simulated by the simulation model, and the first shortest distance and the second shortest distance are calculated based on the shortest distance principle, that is, the milling head needs to maintain a predetermined distance from the surface of the workpiece when switching from the first machining position to the second machining position, so that the path is the shortest when the milling head switches from the first machining position to the second machining position. When the first shortest distance is greater than the second shortest distance, it indicates that the path can be shortened after machining the machining position, so the machining order of the machining position is set before the first machining position and the second machining position, otherwise, the machining order of the machining position is still after the first machining position and the second machining position, and the switching trajectory is optimized according to the trajectory corresponding to the minimum value of the first shortest distance and the second shortest distance. The technical scheme can obtain a switching trajectory with shorter path, thereby improving the machining efficiency.

[0028] Further, the acquisition of the predicted cutting trajectory comprises: In the process of machining the workpiece by the milling head based on the control parameters corresponding to the first trajectory, the sensing information and wear information of the milling head are collected in real time, and the sensing information, wear information, material quality and cutting shape of the workpiece are input into the cutting model to obtain cutting information, the cutting information includes the rotating speed, rotating number, feeding speed and cutting amount of the milling head, and the cutting information is input into the simulation model to obtain the predicted cutting trajectory corresponding to a future preset time period.

[0029] Specifically, since the milling head changes with the working conditions during the working process, the performance of the milling head changes, and then the cutting accuracy is affected. Therefore, during the process of machining the workpiece by the milling head based on the control parameters corresponding to the first trajectory, the mechanical properties of the milling head are captured by collecting the sensing information and the wear information of the milling head in real time, wherein the sensing information includes the temperature, friction, vibration data and wear information of the milling head, and the sensing information, wear information and material and cutting shape of the workpiece are input into the cutting model to obtain the cutting information, wherein the cutting information includes the rotating speed, rotating number, feed speed and cutting amount of the milling head, the rotating number is the rotating number corresponding to a single feed, and the cutting information is input into the simulation model to obtain the predicted cutting trajectory corresponding to a future preset time period. The technical scheme can dynamically obtain the predicted cutting trajectory according to the real-time state of the milling head, cooperate with the above steps, and realize the improvement of the cutting efficiency and the cutting accuracy.

[0030] Further, it is determined whether the representative position needs to be corrected, such as Figure 3 As shown, comprising: The predicted cutting trajectory is divided into a plurality of small regions, and the center point of the small region is taken as the machining position of the milling head, any position of the milling head is taken as the first point, and the point in the predicted cutting trajectory which has an angle greater than a set angle with the cutting surface corresponding to the surface where the i-th point is located is selected as the i+1-th point. The i-th point is taken as the representative position, and the i-th point and the surrounding adjacent other points are connected, and the i-th point and the adjacent other points form a non-intersecting polygonal figure. The polygonal figure is mapped to the cutting surface where the i-th point is located to obtain a mapping figure. The ratio of the first area of the mapping figure to the second area of the polygonal figure is calculated. When the ratio is greater than or equal to a set value, the i-th point does not need to be corrected. When the ratio is less than the set value, the i-th point needs to be corrected.

[0031] Specifically, the continuous predicted cutting trajectory is divided into multiple small regions, and the center point of each region is regarded as the theoretical machining position of the milling head. This discretization converts the complex three-dimensional path into a quantifiable point set for analysis, with any starting point as the i-th position, which represents the position. Based on spatial geometric constraints, adjacent points with an angle greater than a set threshold with the tangent plane where the i-th position is located are selected as the i+1-th position. The set threshold can be 10°, ensuring that the selected position is located in a region where the curvature of the trajectory changes, but the change is not too large. These regions may be caused by milling head or gantry machining equipment vibration leading to machining deviation. Connecting the i-th position and its adjacent positions forms a non-intersecting polygonal graph (usually a triangle or quadrilateral). The polygonal graph is an approximate geometric representation of the local surface of the workpiece to be machined. Projecting the polygonal graph grid onto the tangent plane (ideal machining plane) corresponding to the i-th position generates a two-dimensional mapping graph. Calculate the ratio of the area of the mapping graph (first area S1) to the area of the original polygonal graph (second area S2), and compare the ratio with the set value. When the ratio is greater than or equal to the set value, it indicates that the actual surface has high adhesion to the ideal tangent plane, and no correction is needed. Conversely, when the ratio is less than the set value, it indicates that the local surface has high distortion or steep fluctuations, and the milling head will cause overcut or undercut if it follows the original path, so correction is needed. The above technical solution can accurately identify whether there is cutting unsmoothness at each of the representative positions, facilitating subsequent calibration processing, thereby laying the foundation for improving cutting precision.

[0032] Further, the generation of the second trajectory includes: When the representative position needs to be corrected, the representative position is adjusted while meeting the machining conditions, so that the adjusted representative position corresponds to the maximum mapping area of the graph on the tangent plane at the representative position. The adjusted representative position is taken as the correction position, the correction position replaces the representative position in the predicted cutting trajectory, and the replaced predicted cutting trajectory and the switching trajectory are taken as the second trajectory.

[0033] Specifically, when it is detected that the projection area ratio, i.e., the mapping area / original polygon area, of the representative position, i.e., the above-mentioned i-th point, is lower than a set value, it is indicated that the cutting of the point has possibly caused errors leading to insufficient smoothness, triggering the correction mechanism, and the correction unit iteratively adjusts the three-dimensional coordinates of the point in the spatial range meeting the machining constraints (such as tool length, workpiece boundary, collision avoidance, etc.) with the representative position as the center. The optimization objective is to maximize the mapping area of the polygon composed of the representative position and adjacent points on the current cutting plane, and the corrected position after optimization is used to replace the representative position in the original predicted trajectory, and is integrated with the switching trajectory generated by the optimization unit to generate a second trajectory that can directly drive the equipment. The process retains the trajectory data of the non-correction section and only reconstructs the local path. The above technical solution significantly improves the machining quality under the premise of ensuring real-time performance, and the technical essence is to make the milling head cutting state approach the ideal effect through spatial pose optimization.

[0034] Further, the cutting model is a model trained through historical data, and the historical data includes historical sensing information of the milling head, historical wear information, material of the workpiece, cutting shape, and corresponding historical cutting information.

[0035] Further, the gantry machining equipment includes multiple milling heads, and the different milling heads can be automatically switched.

[0036] The application also provides a machining center control system based on artificial intelligence, which is used to implement the above method, as shown in Figure 4 The system includes: A modeling unit is configured to create a simulation model, simulate a first trajectory of each milling head based on equipment information of the gantry machining equipment, machining information of each to-be-machined position of a to-be-machined workpiece, and milling head information of the simulation model; An optimization unit is configured to optimize machining sequencing and switching trajectories in the first trajectory according to switching path positions of the milling heads between different to-be-machined positions and the shortest distance principle; A prediction unit is configured to input real-time collected sensing information and wear information of the milling head, material and cutting shape of the to-be-machined workpiece into a cutting model to obtain cutting parameters, and input the cutting parameters into the simulation model to generate a predicted cutting trajectory in the first trajectory of the milling head; A judgment unit is configured to select a representative position in the predicted cutting trajectory, and determine whether the representative position needs to be corrected according to a polygonal figure composed of each representative position and adjacent representative positions; A correction unit is configured to, when correction is needed, obtain a corrected position of the representative position according to the maximum projection area principle of the figure, and generate a second trajectory based on the corrected position, the predicted cutting trajectory, and the switching trajectory; The control unit is configured to process the workpiece based on the control parameter corresponding to the second trajectory, and repeatedly acquire the second trajectory when the real-time error is greater than the error threshold.

[0037] The application further provides a computer readable storage medium, wherein instructions are stored on the computer readable storage medium, and the instructions are executed by a processor to implement the method.

[0038] To sum up, the patent application significantly improves the control accuracy and efficiency of the gantry machining center through artificial intelligence technology. The simulation model established by equipment information, machining information and milling head information can generate the first trajectory corresponding to each machining position. The cutting parameters are dynamically updated through real-time sensing data and wear information, so that the predicted cutting trajectory always matches the actual state of the physical system, solving the problem of disconnection between the theoretical model and the real-time working condition in traditional numerical control machining. Secondly, the unique "projection area ratio" correction mechanism, which represents the position correction, intelligently identifies the position to be corrected by analyzing the projection area ratio of the polygon formed by the discrete points on the cutting plane, and optimizes the spatial pose with the goal of maximizing the projection area, reducing the machining error of complex surfaces, reducing the radial cutting force and prolonging the tool life. Thirdly, the switching trajectory optimization algorithm dynamically adjusts the machining sequence and shortens the idle path by simulating and predicting the spatial changes before and after the machining of the passing position. Finally, the system adopts the "local correction instead of global re-planning" strategy to meet the real-time demand of high-speed machining, and forms a closed-loop control of "sensing monitoring-AI prediction-dynamic correction", which greatly improves the machining quality stability of precision parts such as large structural parts.

[0039] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, system and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0040] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the application or the whole or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0041] The above-described and above-embodied examples are merely used to illustrate the technical solutions of the present application, but not to limit the same; although the present application has been described in detail with reference to the foregoing examples, those ordinarily skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement to some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A machining center control method based on artificial intelligence, characterized in that: The method comprises: Creating a simulation model to simulate a first trajectory of the milling head corresponding to each position to be processed based on equipment information of the gantry processing equipment, processing information of each position to be processed of the workpiece, milling head information, and the simulation model; Optimizing the processing sequence and the switching trajectory in the corresponding first trajectory according to the switching path position of the milling head between different positions to be processed and the shortest distance principle; Inputting sensor information, wear information of the milling head, material and cutting shape of the workpiece to be processed collected in real time into a cutting model to obtain cutting parameters, and inputting the cutting parameters into the simulation model to generate a predicted cutting trajectory in the first trajectory of the milling head; Selecting a representative position in the predicted cutting trajectory, and determining whether the representative position needs to be corrected based on a polygonal figure formed between each representative position and adjacent representative positions; When correction is required, obtaining a correction position of the representative position according to the principle of maximum graphic projection area, and generating a second trajectory based on the correction position, the predicted cutting trajectory and the switching trajectory; The workpiece to be processed is processed based on the control parameters corresponding to the second trajectory, and when the real-time error is greater than the error threshold, the method of repeatedly obtaining the second trajectory is adopted.

2. The method according to claim 1, characterized in that The motion trajectory of each milling head and the generation of related control instructions include: A simulation model is established based on the equipment information of the gantry processing equipment, the shape and material of the workpiece to be processed, and the positional relationship between the two. The processing information, milling head information and equipment information corresponding to each position to be processed are input into the simulation model, and the working process of each milling head is simulated according to the preset program corresponding to the processing information of each position to be processed to obtain the first path of each milling head.

3. The method according to claim 1, characterized in that Optimizing the processing sequence and the switching trajectory corresponding to the first trajectory includes: According to the switching trajectory of the milling head between the first position to be processed and the second position to be processed, and simulating state information of the path position of the switching trajectory after processing according to the simulation model, and obtaining the first shortest distance and the second shortest distance corresponding to the path position before and after processing based on the shortest path principle, when the first shortest distance is greater than the second shortest distance, the processing order of the path position is prior to the processing order of the first position to be processed and the second position to be processed, and otherwise, it remains unchanged; The switching trajectory in the first trajectory is optimized according to the trajectory corresponding to the minimum value between the first shortest distance and the second shortest distance.

4. The method according to claim 1, wherein The acquisition of the predicted cutting trajectory includes: During the process of the milling head processing the workpiece to be processed based on the control parameters corresponding to the first trajectory, the sensor information and wear information of the milling head are collected in real time, and the sensor information, wear information and the material and cutting shape of the workpiece to be processed are input into the cutting model to obtain cutting information. The cutting information includes the rotation speed, number of rotations, feed speed and cutting amount of the milling head, and the cutting information is input into the simulation model to obtain the predicted cutting trajectory corresponding to the preset time period in the future.

5. The method according to claim 1, wherein Determining whether the representative position needs to be corrected includes: The predicted cutting trajectory is divided into multiple small areas, and the center point of the small area is used as the processing position of the milling head, and any position of the milling head is used as the first point, and the point in the predicted cutting trajectory whose angle with the section corresponding to the surface where the i-th site is located is greater than the set angle is selected as the i+1-th site, and the i-th site is used as the representative position, and the i-th site is connected with other adjacent sites around it, and the i-th site and other adjacent sites form a non-intersecting polygon, and the polygon is mapped to the section where the i-th site is located, and the mapping figure is obtained, and the ratio of the first area of ​​the mapping figure to the second area of ​​the polygon is calculated. When the ratio is greater than or equal to the set value, the i-th site does not need to be corrected, and when the ratio is less than the set value, the i-th site needs to be corrected.

6. The method according to claim 1, characterized in that The generation of the second trajectory includes: When the representative position needs to be corrected, the representative position is adjusted so that the mapping area of ​​the graphic corresponding to the adjusted representative position on the cross-section of the surface corresponding to the representative position is maximized while satisfying the processing conditions. The adjusted representative position is used as the correction position, and the correction position replaces the representative position in the predicted cutting trajectory. The replaced predicted cutting trajectory and the switching trajectory are used as the second trajectory.

7. The method according to claim 1, characterized in that The cutting model is a model trained with historical data, and the historical data includes historical sensing information of the milling head, historical wear information, workpiece material, cutting shape and corresponding historical cutting information.

8. The method according to claim 1, characterized in that The gantry processing equipment includes multiple milling heads, and different milling heads can be automatically switched.

9. A machining center control system based on artificial intelligence, used to implement the method according to any one of claims 1 to 8, characterized in that: The system comprises: a modeling unit, configured to create a simulation model, and simulate a first trajectory of the milling head corresponding to each position to be processed based on equipment information of the gantry processing equipment, processing information of each position to be processed of the workpiece, milling head information, and the simulation model; An optimization unit, configured to optimize the processing sequence and the switching trajectory corresponding to the first trajectory according to the switching path position of the milling head between different positions to be processed and the shortest distance principle; a prediction unit, configured to input sensor information, wear information, the material and cutting shape of the workpiece collected in real time from the milling head into a cutting model to obtain cutting parameters, and input the cutting parameters into the simulation model to generate a predicted cutting trajectory in the first trajectory of the milling head; a judgment unit, configured to select a representative position in the predicted cutting trajectory and judge whether the representative position needs to be corrected based on a polygonal figure formed between each representative position and adjacent representative positions; a generating unit, configured to, when correction is required, obtain a correction position of the representative position according to a principle of maximizing the projection area of ​​the graphic, and generate a second trajectory based on the correction position, the predicted cutting trajectory, and the switching trajectory; A control unit is configured to process the workpiece based on the control parameters corresponding to the second trajectory, and to repeat the method of acquiring the second trajectory when the real-time error is greater than an error threshold.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images