Search

CN-121979115-A - Fine control method and system for feeding and discharging of numerical control machine tool

CN121979115ACN 121979115 ACN121979115 ACN 121979115ACN-121979115-A

Abstract

The application provides a method and a system for controlling feeding and discharging of a numerical control machine tool in a refined manner, and relates to the technical field of laser cladding processing, wherein the method comprises the steps of carrying out cladding fitting analysis based on an image and a point cloud data set, generating a first sub-stage cladding three-dimensional model, carrying out deviation comparison, and determining a second sub-stage cladding deviation data set; aiming at meeting the coating deviation data set of the second sub-stage, carrying out correction analysis on the preset powder feeding flow by combining the powder quantity of the real-time powder cylinder to obtain the optimized powder feeding flow; and generating a second sub-stage optimization control strategy to execute feeding control of a second sub-stage scanning time window. The application can solve the technical problems that the prior repeated laser cladding processing method cannot accurately analyze cladding deviation in the previous processing stage, and the cladding deviation cannot be compensated for pertinently in time in the next processing stage, so that the processing deviation is accumulated, and the overall cladding quality of the workpiece is poor, and can achieve the effect of improving the overall cladding quality of the workpiece.

Inventors

  • WEI MEIHONG

Assignees

  • 南通纳侬精密机械有限公司

Dates

Publication Date
20260505
Application Date
20251223

Claims (8)

  1. 1. A fine control method for feeding and discharging of a numerical control machine tool is characterized by comprising the following steps: Obtaining a melt processing index of a target workpiece, wherein the melt processing index comprises a preset coating thickness, a preset coating width and a preset coating shape; performing melt processing of the target workpiece according to a preset melt processing scheme, wherein the preset melt processing scheme comprises a preset laser power, a preset scanning speed, a preset powder feeding flow and a preset repetition number; dividing the melt processing index according to the preset repetition times, determining a plurality of stage melt indexes, and selecting a second stage melt index, wherein the second stage melt index comprises a second coating thickness, a second coating width and a second coating shape; in a preset period, carrying out data acquisition on the melt processing process of the target workpiece by utilizing double-source monitoring equipment to obtain a double-source monitoring data set, wherein the double-source monitoring data set comprises an image data set and a point cloud data set; Performing coating fitting analysis based on the image data set and the point cloud data set, generating a first sub-stage coating three-dimensional model, constructing a second-stage standard coating three-dimensional model according to the second coating thickness, the second coating width and the second coating shape, performing grid deviation comparison on the first sub-stage coating three-dimensional model and the second-stage standard coating three-dimensional model, and determining a second sub-stage coating deviation data set; Monitoring and obtaining the real-time powder cylinder powder quantity, and correcting and analyzing the preset powder feeding flow by combining the real-time powder cylinder powder quantity to obtain the optimized powder feeding flow with the aim of meeting the coating deviation data set in the second sub-stage; Performing second sub-stage scanning time prediction based on the preset scanning speed and the mapped workpiece area of the first sub-stage, and determining a second sub-stage scanning time window; generating a second sub-stage optimizing control strategy according to the optimized powder feeding flow and the second sub-stage scanning time window, and executing feeding control in the second sub-stage scanning time window according to the second sub-stage optimizing control strategy.
  2. 2. The method of claim 1, wherein the controlling of the feed within the second sub-phase scanning time window is performed in accordance with the second sub-phase optimization control strategy, and further comprising: sequentially executing optimization control analysis from the third sub-stage to the fourth sub-stage to the N sub-stage, and generating a third sub-stage optimization control strategy and a fourth sub-stage optimization control strategy to the N sub-stage optimization control strategy, wherein N is set based on the preset repetition times; And executing feeding control of the subsequent stage according to the third sub-stage optimizing control strategy and the fourth sub-stage optimizing control strategy in sequence until the Nth sub-stage optimizing control strategy.
  3. 3. The method of claim 1, wherein generating a first sub-stage coating three-dimensional model based on the image dataset and the point cloud dataset for coating fit analysis comprises: Setting a first data acquisition node based on the preset period, wherein the first data acquisition node is an ending node of the first preset period; Under the first data acquisition node, carrying out data acquisition on the melt processing process of the target workpiece by utilizing the dual-source monitoring equipment to obtain an image data set and a point cloud data set, wherein the image data set is formed by a plurality of pieces of image data with different angles; Performing image fusion on the image data set based on an image fusion strategy to generate a fusion coating image, and inputting the fusion coating image into a preset contour extraction channel to obtain a coating contour, wherein the preset contour extraction channel is constructed based on a convolutional neural network; and carrying out coating fitting analysis on the point cloud data set by taking the coating profile as constraint to obtain the first sub-stage coating three-dimensional model.
  4. 4. A method according to claim 3, wherein performing a coating fit analysis on the point cloud dataset with the coating profile as a constraint results in the first sub-stage coating three-dimensional model, comprising: Randomly fitting the point cloud data set by taking the coating contour as constraint to obtain a first fitting result, and calculating to obtain a first fitting convergence degree of the first fitting result, wherein the first fitting convergence degree is the ratio of the number of point cloud data falling into the coating contour to the total number of point cloud data in the point cloud data set; Judging whether the first fitting convergence degree meets a preset convergence degree or not, wherein the preset convergence degree is set based on image acquisition precision and point cloud acquisition precision; if not, carrying out iterative random fitting on the point cloud data set by taking the cladding contour as constraint again until the preset convergence or preset fitting frequency threshold is met, and outputting a current point cloud fitting result; And in the three-dimensional visualization platform, performing three-dimensional simulation modeling based on the current point cloud fitting result to generate the first sub-stage coating three-dimensional model.
  5. 5. The method of claim 1, wherein performing a corrective analysis on the predetermined powder feed flow rate in combination with the real-time powder amount of the powder cartridge for the purpose of satisfying the second sub-stage coating bias dataset, comprises: The second sub-stage coating deviation data set comprises a thickness deviation data set, a width deviation data set and a shape deviation data set, and average value calculation is respectively carried out on the thickness deviation data set and the width deviation data set to obtain a thickness deviation average value and a width deviation average value; performing primary correction analysis on the preset powder feeding flow based on the preset laser power and the preset scanning speed to obtain primary correction powder feeding flow aiming at meeting the thickness deviation average value, the width deviation average value and the shape deviation data set; and carrying out secondary correction analysis on the primary correction powder feeding flow according to the real-time powder amount of the powder cylinder, and outputting the optimized powder feeding flow.
  6. 6. The method of claim 5, wherein obtaining a corrected powder feed flow comprises: invoking a melt processing log, and acquiring a sample data set based on the melt processing log, wherein the sample data comprises a sample thickness deviation, a sample width deviation, a sample shape deviation, a sample laser power, a sample scanning speed and a sample powder feeding flow; dividing the sample data set into Q parts, randomly selecting Q times without returning, constructing a first sample set, and sequentially obtaining a second sample set until the Q sample set; taking the sample thickness deviation, the sample width deviation, the sample shape deviation, the sample laser power and the sample scanning speed as inputs, taking the sample powder feeding flow as supervision, performing supervision training on a BP neural network by utilizing Q sample sets to obtain a plurality of convergence correction units, and fusing and constructing a convergence correction channel according to the plurality of convergence correction units, wherein the output of the convergence correction channel is the mode of the plurality of convergence correction units; and inputting the thickness deviation average value, the width deviation average value, the shape deviation data set, the preset laser power and the preset scanning speed into the convergence correction channel for one-time correction analysis, and outputting the one-time correction powder feeding flow.
  7. 7. The method of claim 5, wherein performing a secondary correction analysis of the primary corrected powder feed rate based on the real-time powder amount of the powder cartridge comprises: based on a single variable analysis principle, acquiring a sample powder cylinder powder proportion set and a sample powder delivery flow set, wherein the sample powder cylinder powder proportion and the sample powder delivery flow are in one-to-one correspondence; Performing association influence analysis based on the sample powder cylinder powder proportion set and the sample powder feeding flow set, and determining an association influence curve; determining a real-time powder cylinder powder proportion based on the real-time powder cylinder powder amount, matching the real-time powder cylinder powder proportion with the association influence curve, and determining an association influence coefficient; And performing secondary correction analysis on the primary correction powder feeding flow according to the correlation influence coefficient to obtain the optimized powder feeding flow.
  8. 8. A numerically controlled machine tool feed and discharge refinement control system, characterized by the steps for implementing the method of any one of claims 1 to 7, comprising: The melt processing index acquisition module is used for acquiring the melt processing index of the target workpiece, wherein the melt processing index comprises a preset coating thickness, a preset coating width and a preset coating shape; The melt processing module is used for executing melt processing of the target workpiece according to a preset melt processing scheme, wherein the preset melt processing scheme comprises preset laser power, preset scanning speed, preset powder feeding flow and preset repetition times; The second-stage melting index selection module is used for dividing the melting processing indexes according to the preset repetition times, determining a plurality of stage melting indexes and selecting a second-stage melting index, wherein the second-stage melting index comprises a second coating thickness, a second coating width and a second coating shape; The data acquisition module is used for acquiring data of the melt processing process of the target workpiece by utilizing double-source monitoring equipment in a preset period to obtain a double-source monitoring data set, wherein the double-source monitoring data set comprises an image data set and a point cloud data set; The coating deviation data set determining module is used for carrying out coating fitting analysis based on the image data set and the point cloud data set, generating a first sub-stage coating three-dimensional model, constructing a second-stage standard coating three-dimensional model according to the second coating thickness, the second coating width and the second coating shape, carrying out grid deviation comparison on the first sub-stage coating three-dimensional model and the second-stage standard coating three-dimensional model, and determining a second sub-stage coating deviation data set; The correction analysis module is used for monitoring and acquiring the powder quantity of the real-time powder cylinder, and carrying out correction analysis on the preset powder feeding flow by combining the powder quantity of the real-time powder cylinder to obtain the optimized powder feeding flow aiming at meeting the coating deviation data set of the second sub-stage; the scanning time prediction module is used for predicting the scanning time of the second sub-stage based on the preset scanning speed and the mapping workpiece area of the first sub-stage, and determining a scanning time window of the second sub-stage; And the feeding control module is used for generating a second sub-stage optimizing control strategy according to the optimized powder feeding flow and the second sub-stage scanning time window, and executing feeding control in the second sub-stage scanning time window according to the second sub-stage optimizing control strategy.

Description

Fine control method and system for feeding and discharging of numerical control machine tool Technical Field The application relates to the technical field of laser cladding processing, in particular to a method and a system for controlling feeding and discharging of a numerical control machine tool in a refined mode. Background Laser cladding processing is an advanced material surface modification technique that utilizes a high energy laser beam to melt and deposit a powder material onto the surface of a substrate material to form a coating having specific properties. The technology has a plurality of advantages, such as high precision, high speed, low heat affected zone, good material compatibility and controllability, and the like, and can be widely applied to the industrial fields of aerospace, automobile manufacturing, energy sources and the like. At present, when the existing technology carries out repeated laser cladding processing, cladding deviation in the previous processing stage cannot be accurately analyzed, so that the cladding deviation cannot be timely compensated in the next processing stage, and the processing deviation is accumulated, so that the technical problem of poor overall cladding quality of a workpiece is caused. Disclosure of Invention The application aims to provide a fine control method and a system for feeding and discharging of a numerical control machine tool, which are used for solving the technical problem that when the existing technology is used for carrying out repeated laser cladding processing, cladding deviation in the previous processing stage cannot be accurately analyzed, so that the cladding deviation cannot be compensated in time in the next processing stage, the processing deviation is accumulated, and the whole cladding quality of a workpiece is poor. In view of the problems, the application provides a method and a system for controlling feeding and discharging of a numerical control machine tool in a refined manner. The application provides a method for controlling the fine feeding and discharging of a numerical control machine tool, which is realized by a fine feeding and discharging control system of the numerical control machine tool, wherein the method comprises the steps of obtaining a melt processing index of a target workpiece, wherein the melt processing index comprises a preset coating thickness, a preset coating width and a preset coating shape, executing the melt processing of the target workpiece according to a preset melt processing scheme, wherein the preset melt processing scheme comprises a preset laser power, a preset scanning speed, a preset powder feeding flow and a preset repetition number, dividing the melt processing index according to the preset repetition number, determining a plurality of stages of melt indexes, selecting a second stage melt index, wherein the second stage melt index comprises a second coating thickness, a second coating width and a second coating shape, acquiring data of the melt processing process of the target workpiece by using a double-source monitoring device in a preset period to obtain a double-source monitoring data set, wherein the double-source monitoring data set comprises an image data set and a point cloud data set, performing coating three-dimensional coating layer forming a first stage, a three-dimensional coating model, and a second stage coating, and a three-dimensional coating model, wherein the three-dimensional coating is formed by a three-dimensional coating model is calculated according to the first stage coating thickness, the second stage coating thickness is determined, the second stage coating width is determined, and the second coating shape is calculated by the second stage coating shape is calculated, the method comprises the steps of carrying out correction analysis on the preset powder feeding flow by combining the real-time powder amount of the powder cylinder to obtain optimized powder feeding flow, carrying out second sub-stage scanning time prediction on the basis of the preset scanning speed and a mapping workpiece area of a first sub-stage, determining a second sub-stage scanning time window, generating a second sub-stage optimizing control strategy according to the optimized powder feeding flow and the second sub-stage scanning time window, and executing feeding control in the second sub-stage scanning time window according to the second sub-stage optimizing control strategy. In a second aspect, the application also provides a refined control system for feeding and discharging of a numerical control machine tool, which is used for executing the refined control method for feeding and discharging of the numerical control machine tool according to the first aspect, wherein the system comprises a melt processing index acquisition module, a control module and a control module, wherein the melt processing index acquisition module is used for acquiring a melt processing index of a targ