[go: up one dir, main page]

CN118838285B - A method for the tool to quickly find the model coordinates during CNC 3-axis processing - Google Patents

A method for the tool to quickly find the model coordinates during CNC 3-axis processing Download PDF

Info

Publication number
CN118838285B
CN118838285B CN202410876456.8A CN202410876456A CN118838285B CN 118838285 B CN118838285 B CN 118838285B CN 202410876456 A CN202410876456 A CN 202410876456A CN 118838285 B CN118838285 B CN 118838285B
Authority
CN
China
Prior art keywords
tool
workpiece
model
cutter
prediction
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202410876456.8A
Other languages
Chinese (zh)
Other versions
CN118838285A (en
Inventor
恽成
李子婧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Summit Intelligent Technology Co ltd
Original Assignee
Shanghai Summit Intelligent Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Summit Intelligent Technology Co ltd filed Critical Shanghai Summit Intelligent Technology Co ltd
Priority to CN202410876456.8A priority Critical patent/CN118838285B/en
Publication of CN118838285A publication Critical patent/CN118838285A/en
Application granted granted Critical
Publication of CN118838285B publication Critical patent/CN118838285B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00Programme-control systems
    • G05B19/02Programme-control systems electric
    • G05B19/418Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/41865Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00Program-control systems
    • G05B2219/30Nc systems
    • G05B2219/32Operator till task planning
    • G05B2219/32252Scheduling production, machining, job shop
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Numerical Control (AREA)

Abstract

The invention discloses a method for quickly finding model coordinates of a cutter in a numerical control 3-axis process machining process, which relates to the relevant technical field of computer-aided machining, and comprises the steps of setting initial coordinate values and machining paths, carrying out initial positioning by using preset parameters, accurately positioning the cutter to the initial position of a workpiece, carrying out path planning by using CAD software in a path planning stage, determining the machining path of the cutter according to the geometric shape and machining requirements of the workpiece, carrying out path planning by using CAD software, and predicting coordinate points of the next cutter positioning by using preloaded workpiece model data and a prediction algorithm in a cutter motion control and prediction stage, thereby improving the precision and efficiency of cutter positioning; the process builds a prediction model, inputs the workpiece surface model and the current cutter position characteristics, outputs the predicted value of the next cutter position, dynamically adjusts the prediction model according to the real-time sensor data, and adapts to the actual condition change of the workpiece surface.

Description

Method for quickly finding model coordinates by cutter in numerical control 3-axis technical processing process
Technical Field
The invention relates to the technical field of computer-aided machining, in particular to a method for quickly finding model coordinates by a cutter in a numerical control 3-axis technological machining process.
Background
Numerical control machining processes include most commonly milling and turning, and secondarily grinding, electric discharge machining, etc., where a rotating tool is used for the surface of a workpiece, and moving along 3,4, or 5 axes, and milling essentially cuts or trims the workpiece, and can rapidly machine complex geometries and precision parts from metal or thermoplastic, and turning is the use of lathes to manufacture parts that contain cylindrical features.
For example, patent publication No. CN110096034B discloses a reconstruction method of three-axis tool path curved surface transverse information based on a projection algorithm, which comprises the following steps of (1) recording indexes of each tool position point according to a tool position file and storing the indexes according to a KD-Tree structure, (2) searching adjacent track projection points of each tool position point based on the data stored in the step (1), and pairing and storing the adjacent track projection points with corresponding tool position points, so that transverse information of a tool path curved surface formed by pairing all the tool position points with the corresponding adjacent track projection points is obtained, wherein the adjacent track projection points are closest points to seed points on adjacent tool paths, the tool path curved surface is the curved surface containing all the tool position points in the tool path, the invention does not need to reconstruct the curved surface, reduces calculation load, considers the transverse information of the tool path, and has good optimization effect and strong applicability.
Although the above-mentioned solution has the advantages as described above, the conventional method for quickly finding the model coordinates by the tool during the machining process of the numerical control 3-axis process is limited in manual adjustment accuracy and low in efficiency, and once the positioning of the tool is completed, when the path adjustment is required during the machining stage, the real-time monitoring and adjustment mechanism is often lacking, and the change of the workpiece surface cannot be timely dealt with, so that a method for quickly finding the model coordinates by the tool during the machining process of the numerical control 3-axis process is needed to solve the problems.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method for quickly finding the model coordinates by a cutter in the machining process of a numerical control 3-axis process, which solves the problems that the traditional method for quickly finding the model coordinates by the cutter in the machining process of the numerical control 3-axis process in the prior art is limited in manual adjustment precision and low in efficiency, and once the positioning of the cutter is finished, when path adjustment is needed in the machining stage, a real-time monitoring and adjusting mechanism is often lacking, and the change of the surface of a workpiece cannot be timely dealt with.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
The invention provides a method for quickly finding model coordinates by a cutter in a numerical control 3-axis technical processing process, which comprises the following steps:
Step 1, initial positioning, namely setting an initial coordinate value and a machining path of a cutter, and utilizing preset parameters to perform initial positioning to position the cutter to an initial position of a workpiece;
step 2, path planning, namely pre-designing and generating a cutter path in CAD software, and determining a machining path of the cutter according to the geometric shape and machining requirements of a workpiece, wherein the machining path comprises a cutting path, a cutting direction and cutting depth parameters;
Step 3, initial tool motion control and prediction, namely controlling the motion trail and speed of a tool, including control of X, Y, Z axis coordinates of the tool, preloading a workpiece model into a numerical control system before machining;
step 4, monitoring and positioning and adjusting the workpiece in real time in the processing stage, deploying a displacement sensor and a camera, monitoring the surface condition of the workpiece in real time, collecting sensor data, dynamically adjusting a prediction model according to the real-time data, and adjusting the position and the posture of a cutter in real time according to the actual condition of the surface of the workpiece and the sensor data so as to accurately align the cutter with the surface of the workpiece;
and 5, redundancy control, deploying a system architecture with high redundancy and fault tolerance, and providing multiple backup and redundancy control mechanisms, and automatically switching to a standby mode under abnormal conditions.
The invention is further arranged that the initial positioning step in step 1 comprises:
Setting an initial coordinate value and a processing path of a tool, wherein the initial coordinate value of the tool is set in a numerical control system and comprises X, Y, Z axis coordinates;
setting a machining path of a cutter, wherein the machining path comprises a cutting path, a cutting direction and cutting depth parameters;
initial positioning is carried out by using preset parameters, and a cutter is positioned in a numerical control system according to preset initial coordinate values;
Moving the cutter to a preset initial position by using a motion control function provided by a numerical control system;
Determining an initial machining position according to the CAD model of the workpiece, converting a coordinate system by using a numerical control system, and positioning the cutter to the initial position of the workpiece;
simultaneously recording a cutter coordinate value and a machining path parameter used for initial positioning;
the invention further provides that the path planning mode in the step 2 is as follows:
Importing a CAD model file of the workpiece by using CAD software;
determining basic requirements of a processing path, including surface smoothness and dimensional accuracy, according to the geometric shape and the processing requirements of a workpiece;
according to the workpiece material, the processing requirement and the cutter performance, adopting a corresponding processing technology, and drawing a cutting path in CAD software by using a corresponding technology function;
Determining the trend, shape and spacing of a cutting path according to the machining requirements and the geometric shape of a workpiece;
setting a cutting direction, including a feed direction and a cutting direction, based on the determined trend, shape, and pitch of the cutting path;
the invention is further arranged that the work piece model construction step comprises:
Scanning the surface of the workpiece by using a three-dimensional laser scanner to obtain three-dimensional point cloud data of the surface;
Processing the scanned point cloud data, including filtering and point cloud registration, to obtain a three-dimensional model of the surface of the workpiece;
generating a three-dimensional surface model of the workpiece by using point cloud data and adopting a grid-based reconstruction algorithm;
constructing a predictive model, the input parameters including And,
Wherein, Representing three-dimensional grid data for a three-dimensional model of the surface of the workpiece,Is the characteristic vector of the current position of the cutter, comprising position coordinates, cutting speed and acceleration,A predicted value indicating a next tool position;
The input of the prediction model is AndOutput as a value;
Training the prediction model and the processing data, learning the relation between the workpiece surface and the tool motion, and adopting back propagationThe algorithm and the optimizer optimize model parameters and reduce prediction errors;
The invention further provides that in the step 3, the construction mode of the prediction algorithm is as follows:
preparing training set and verification set, constructing prediction model based on long-short-term memory network LSTM, defining input parameters including ,AndWherein, the method comprises the steps of, wherein,Representing three-dimensional grid data for a three-dimensional model of the surface of the workpiece,Is the characteristic vector of the current position of the cutter, comprising position coordinates, cutting speed and acceleration,A predicted value indicating a next tool position;
Training the neural network model by using a back propagation algorithm and a gradient descent optimization algorithm, wherein an optimization loss function formula is as follows: Wherein For the actual tool position,For the number of samples to be taken,Representing a time step;
verifying the trained neural network model by using a verification set, and adjusting the model structure and the super parameters;
before machining, the characteristic vector of the current position of the cutter is calculated And a three-dimensional model of the surface of the workpieceInputting a trained neural network model;
The model outputs the predicted value of the next cutter position ;
The invention further provides that the real-time monitoring and positioning adjustment steps of the workpiece in the step 4 comprise the following steps:
the displacement sensor and the camera are arranged on processing equipment to monitor the condition of the surface of the workpiece in real time, and continuously monitor the condition of the surface of the workpiece, including the surface shape, the roughness and the temperature;
the method comprises the steps of collecting sensor data, processing and analyzing, dynamically adjusting a prediction model according to the real-time sensor data to predict the position of a cutter at the next step;
the invention is further provided that the step of real-time monitoring, positioning and adjusting the workpiece in the step 4 further comprises the following steps:
updating model parameters according to new data by adopting a self-adaptive algorithm, and adapting to actual condition changes of the surface of the workpiece;
according to the cutter position predicted value output by the prediction model and the real-time sensor data, the position and the posture of the cutter are adjusted in real time;
the control function provided by the numerical control system is used for adjusting the processing path and the movement track of the cutter, so that the cutter is accurately aligned with the surface of the workpiece;
According to the position and the gesture of the cutter after the real-time adjustment, the cutter is accurately aligned with the surface of the workpiece, and the position and the gesture of the cutter are adjusted to be completely attached to the surface of the workpiece;
The invention is further arranged that in the step 4, the mode of predicting the position of the cutter in the next step is as follows:
Continuously monitoring the surface condition of a workpiece by using a displacement sensor and a camera, collecting related sensor data, and preprocessing the collected data, wherein the preprocessing comprises noise filtering, data alignment and calibration;
Using a neural network model based on deep learning, taking real-time sensor data as input characteristics of the model, and predicting an output value of a next cutter position;
Updating model parameters according to actual prediction errors by using a gradient descent method;
Defining a difference between a predicted value and an actual value of a loss function measurement model;
According to the cutter position predicted value output by the updated prediction model, the position and the posture of the cutter are adjusted by combining with real-time sensor data;
the invention is further arranged that the redundant control system architecture comprises:
the main control module is responsible for monitoring the running state of the processing equipment, controlling the processing process and processing various instructions;
The redundant main control module is used for performing main-standby switching and fault-tolerant control;
The backup control module is used as a backup of the main control module, keeps synchronous with the main control module, prepares to take over control right at any time, and communicates with the main control module in real time through a redundant communication link;
The power supply module is used for providing power supply required by equipment, is provided with a redundant power supply module and can be automatically switched to a standby power supply when the main power supply fails;
the invention is further arranged that the redundant control system architecture further comprises:
The sensor module is responsible for monitoring parameters of workpieces and equipment, including temperature, pressure and speed, is provided with a redundant sensor module, and can continuously acquire data when the sensor fails;
The execution module is used for controlling the movement and the gesture of the cutter;
The communication module is responsible for communicating with external equipment and systems, and comprises an industrial personal computer and a monitoring system;
And the fault detection and automatic switching module is used for implementing abnormality detection and automatic switching logic, monitoring the running states of all modules of the system and automatically switching to a standby mode when a fault is detected.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, through preloading the workpiece model and utilizing a prediction algorithm, accurate prediction of the cutter position is realized, and the positioning precision and efficiency are improved;
According to the invention, by arranging the displacement sensor and the camera, the surface condition of the workpiece is monitored in real time, sensor data are collected, and the real-time adjustment of the position and the posture of the cutter is realized according to the dynamic adjustment of the real-time data, so that the accurate alignment of the cutter and the surface of the workpiece is ensured;
The invention is provided with multiple backup and redundancy control mechanisms, so that the system is ensured to be automatically switched to a standby mode under abnormal conditions, and the stability and the safety of the processing process are improved;
The invention sets an initial coordinate value and a processing path and utilizes preset parameters to perform initial positioning, a cutter is accurately positioned to an initial position of a workpiece, a path planning stage utilizes CAD software to predesign and generate a cutter path, the processing path of the cutter is determined according to the geometric shape and the processing requirement of the workpiece, path planning is performed through the CAD software, and a coordinate point of the next cutter positioning is predicted by utilizing preloaded workpiece model data and a prediction algorithm in a cutter motion control and prediction stage, so that the precision and efficiency of cutter positioning are improved;
In the real-time monitoring and adjusting stage, a displacement sensor and a camera are deployed, the surface condition of a workpiece is monitored in real time, sensor data are collected, a prediction model is dynamically adjusted according to the real-time data, a cutter is accurately aligned with the surface of the workpiece, and the position and the gesture of the cutter are dynamically adjusted according to a cutter position prediction value output by the prediction model and combined with the real-time sensor data, so that the accurate alignment of the cutter with the surface of the workpiece is realized;
And finally, in the redundancy control and safety guarantee stage, deploying a system architecture with strong redundancy and high fault tolerance, and providing a multiple backup and redundancy control mechanism, wherein the system architecture can be automatically switched to a standby mode or a safety state under an abnormal condition, so that the stability and safety of the processing process are ensured.
Drawings
FIG. 1 is a flow chart of a method for quickly finding model coordinates by a cutter in the numerical control 3-axis technical processing process.
Detailed Description
In order that those skilled in the art will better understand the present invention, a detailed description of embodiments of the present invention will be provided below, with reference to the accompanying drawings, wherein it is apparent that the described embodiments are only some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above-described drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention is described in further detail below with reference to the attached drawing figures:
Example 1
Referring to fig. 1, the invention provides a method for quickly finding model coordinates by a cutter in a numerical control 3-axis technical processing process, which comprises the following steps:
Step 1, initial positioning, namely setting an initial coordinate value and a machining path of a cutter, and utilizing preset parameters to perform initial positioning to position the cutter to an initial position of a workpiece;
the initial positioning step in the step 1 comprises the following steps:
Setting an initial coordinate value and a processing path of a tool, wherein the initial coordinate value of the tool is set in a numerical control system and comprises X, Y, Z axis coordinates;
setting a machining path of a cutter, wherein the machining path comprises a cutting path, a cutting direction and cutting depth parameters;
initial positioning is carried out by using preset parameters, and a cutter is positioned in a numerical control system according to preset initial coordinate values;
Moving the cutter to a preset initial position by using a motion control function provided by a numerical control system;
Determining an initial machining position according to the CAD model of the workpiece, converting a coordinate system by using a numerical control system, and positioning the cutter to the initial position of the workpiece;
simultaneously recording a cutter coordinate value and a machining path parameter used for initial positioning;
The initial positioning is implemented through the step 1, so that the cutter is accurately positioned to the initial position of the workpiece;
step 2, path planning, namely pre-designing and generating a cutter path in CAD software, and determining a machining path of the cutter according to the geometric shape and machining requirements of a workpiece, wherein the machining path comprises a cutting path, a cutting direction and cutting depth parameters;
the path planning method in the step 2 is as follows:
Importing a CAD model file of the workpiece by using CAD software;
determining basic requirements of a processing path, including surface smoothness and dimensional accuracy, according to the geometric shape and the processing requirements of a workpiece;
according to the workpiece material, the processing requirement and the cutter performance, adopting a corresponding processing technology, and drawing a cutting path in CAD software by using a corresponding technology function;
Determining the trend, shape and spacing of a cutting path according to the machining requirements and the geometric shape of a workpiece;
setting a cutting direction, including a feed direction and a cutting direction, based on the determined trend, shape, and pitch of the cutting path;
Path planning is carried out in CAD software so as to determine the machining path of the tool;
Step 3, initial tool motion control and prediction, namely controlling the motion trail and speed of a tool, including control of X, Y, Z axis coordinates of the tool, preloading a workpiece model into a numerical control system before machining;
the work piece model construction step includes:
Scanning the surface of the workpiece by using a three-dimensional laser scanner to obtain three-dimensional point cloud data of the surface;
Processing the scanned point cloud data, including filtering and point cloud registration, to obtain a three-dimensional model of the surface of the workpiece;
generating a three-dimensional surface model of the workpiece by using point cloud data and adopting a grid-based reconstruction algorithm;
constructing a predictive model, the input parameters including ,And,
Wherein, Representing three-dimensional grid data for a three-dimensional model of the surface of the workpiece,Is the characteristic vector of the current position of the cutter, comprising position coordinates, cutting speed and acceleration,A predicted value indicating a next tool position;
The input of the prediction model is AndThe output is a value, and the output is a value,;
Training a prediction model and processing data, learning the relation between the surface of a workpiece and the movement of a cutter, and optimizing model parameters by adopting a back propagation algorithm and an optimizer;
In step 3, the prediction algorithm is constructed in the following manner:
preparing training set and verification set, constructing prediction model based on long-short-term memory network LSTM, defining input parameters including ,AndWherein, the method comprises the steps of, wherein,Representing three-dimensional grid data for a three-dimensional model of the surface of the workpiece,Is the characteristic vector of the current position of the cutter, comprising position coordinates, cutting speed and acceleration,A predicted value indicating a next tool position;
Training the neural network model by using a back propagation algorithm and a gradient descent optimization algorithm, wherein an optimization loss function formula is as follows: Wherein For the actual tool position,For the number of samples to be taken,Representing a time step;
verifying the trained neural network model by using a verification set, and adjusting the model structure and the super parameters;
before machining, the characteristic vector of the current position of the cutter is calculated And a three-dimensional model of the surface of the workpieceInputting a trained neural network model;
The model outputs the predicted value of the next cutter position ;
Constructing a prediction model by using a deep learning technology, and realizing accurate prediction of the next cutter positioning;
step 4, monitoring and positioning and adjusting the workpiece in real time in the processing stage, deploying a displacement sensor and a camera, monitoring the surface condition of the workpiece in real time, collecting sensor data, dynamically adjusting a prediction model according to the real-time data, and adjusting the position and the posture of a cutter in real time according to the actual condition of the surface of the workpiece and the sensor data so as to accurately align the cutter with the surface of the workpiece;
The method comprises installing displacement sensor and camera on processing equipment, monitoring the surface condition of workpiece in real time, continuously monitoring the surface condition of workpiece, including surface shape, roughness, and temperature,
The method comprises the steps of collecting sensor data, processing and analyzing, dynamically adjusting a prediction model according to the real-time sensor data to predict the position of a cutter at the next step;
Updating model parameters according to new data by adopting a self-adaptive algorithm, adapting to the actual condition change of the surface of a workpiece, adjusting the position and the gesture of a cutter in real time according to a cutter position predicted value output by a predicted model and real-time sensor data, adjusting the processing path and the motion track of the cutter by using a control function provided by a numerical control system to enable the cutter to be accurately aligned with the surface of the workpiece, and accurately aligning the cutter with the surface of the workpiece according to the position and the gesture of the cutter after the real-time adjustment, and adjusting the position and the gesture of the cutter to enable the cutter to be completely attached with the surface of the workpiece;
the mode of predicting the position of the cutter in the next step is as follows:
Continuously monitoring the surface condition of a workpiece by using a displacement sensor and a camera, collecting related sensor data, and preprocessing the collected data, wherein the preprocessing comprises noise filtering, data alignment and calibration;
Using a neural network model based on deep learning, taking real-time sensor data as input characteristics of the model, and predicting an output value of a next cutter position;
Updating model parameters according to actual prediction errors by using a gradient descent method;
Defining a difference between a predicted value and an actual value of a loss function measurement model;
According to the cutter position predicted value output by the updated prediction model, the position and the posture of the cutter are adjusted by combining with real-time sensor data;
step 5, redundancy control, deploying a system architecture with high redundancy and fault tolerance, and providing multiple backup and redundancy control mechanisms, and automatically switching to a standby mode under abnormal conditions;
The redundant control system architecture includes:
the main control module is responsible for monitoring the running state of the processing equipment, controlling the processing process and processing various instructions;
The redundant main control module is used for performing main-standby switching and fault-tolerant control;
The backup control module is used as a backup of the main control module, keeps synchronous with the main control module, prepares to take over control right at any time, and communicates with the main control module in real time through a redundant communication link;
The power supply module is used for providing power supply required by equipment, is provided with a redundant power supply module and can be automatically switched to a standby power supply when the main power supply fails;
The redundant control system architecture further includes:
The sensor module is responsible for monitoring parameters of workpieces and equipment, including temperature, pressure and speed, is provided with a redundant sensor module, and can continuously acquire data when the sensor fails;
The execution module is used for controlling the movement and the gesture of the cutter;
The communication module is responsible for communicating with external equipment and systems, and comprises an industrial personal computer and a monitoring system;
And the fault detection and automatic switching module is used for implementing abnormality detection and automatic switching logic, monitoring the running states of all modules of the system and automatically switching to a standby mode when a fault is detected.
The invention sets an initial coordinate value and a processing path and utilizes preset parameters to perform initial positioning, a cutter is accurately positioned to an initial position of a workpiece, a path planning stage utilizes CAD software to predesign and generate a cutter path, the processing path of the cutter is determined according to the geometric shape and the processing requirement of the workpiece, path planning is performed through the CAD software, and a coordinate point of the next cutter positioning is predicted by utilizing preloaded workpiece model data and a prediction algorithm in a cutter motion control and prediction stage, so that the precision and efficiency of cutter positioning are improved;
In the real-time monitoring and adjusting stage, a displacement sensor and a camera are deployed, the surface condition of a workpiece is monitored in real time, sensor data are collected, a prediction model is dynamically adjusted according to the real-time data, a cutter is accurately aligned with the surface of the workpiece, and the position and the gesture of the cutter are dynamically adjusted according to a cutter position prediction value output by the prediction model and combined with the real-time sensor data, so that the accurate alignment of the cutter with the surface of the workpiece is realized;
And finally, in the redundancy control and safety guarantee stage, deploying a system architecture with strong redundancy and high fault tolerance, and providing a multiple backup and redundancy control mechanism, wherein the system architecture can be automatically switched to a standby mode or a safety state under an abnormal condition, so that the stability and safety of the processing process are ensured.
The above is only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited by this, and any modification made on the basis of the technical scheme according to the technical idea of the present invention falls within the protection scope of the claims of the present invention.

Claims (3)

1.一种数控3轴工艺加工过程中刀具快速找到模型坐标的方法,其特征在于,包括:1. A method for a tool to quickly find model coordinates during a CNC 3-axis process, characterized in that it includes: 步骤1.初始定位,设定刀具初始坐标值和加工路径;利用预设参数进行初始定位,将刀具定位到工件的初始位置;Step 1. Initial positioning: set the initial coordinate value of the tool and the processing path; use the preset parameters for initial positioning to position the tool to the initial position of the workpiece; 初始定位步骤包括:The initial positioning steps include: 设定刀具初始坐标值和加工路径,在数控系统中设定刀具的初始坐标值,包括X、Y、Z轴坐标;Set the initial coordinate value of the tool and the processing path, and set the initial coordinate value of the tool in the CNC system, including the X, Y, and Z axis coordinates; 设定刀具的加工路径,包括切削路径、切削方向和切削深度参数;Set the tool processing path, including cutting path, cutting direction and cutting depth parameters; 利用预设参数进行初始定位,根据预设的初始坐标值,在数控系统中对刀具进行定位;Use preset parameters for initial positioning, and position the tool in the CNC system according to the preset initial coordinate values; 使用数控系统提供的运动控制功能,将刀具移动到预设初始位置;Use the motion control function provided by the CNC system to move the tool to the preset initial position; 根据工件CAD模型,确定初始加工位置,使用数控系统进行坐标系转换,将刀具定位到工件的初始位置;According to the workpiece CAD model, determine the initial processing position, use the CNC system to convert the coordinate system, and position the tool to the initial position of the workpiece; 同时记录初始定位所使用的刀具坐标值和加工路径参数;At the same time, record the tool coordinate values and machining path parameters used for initial positioning; 步骤2.路径规划,在CAD软件中预先设计和生成刀具路径,根据工件的几何形状和加工要求,确定刀具的加工路径,包括切削路径、切削方向和切削深度参数;Step 2. Path planning: pre-design and generate tool paths in CAD software, and determine the tool processing path according to the workpiece geometry and processing requirements, including cutting path, cutting direction and cutting depth parameters; 路径规划方式为:The path planning method is: 使用CAD软件导入工件的CAD模型文件;Use CAD software to import the CAD model file of the workpiece; 根据工件的几何形状和加工要求,确定加工路径的基本要求,包括表面光滑度、尺寸精度;According to the geometric shape and processing requirements of the workpiece, determine the basic requirements of the processing path, including surface smoothness and dimensional accuracy; 根据工件材料、加工要求和刀具性能,采用对应加工工艺,同样在CAD软件中用对应工艺功能,绘制切削路径;According to the workpiece material, processing requirements and tool performance, the corresponding processing technology is adopted, and the corresponding process function is used in the CAD software to draw the cutting path; 根据加工要求和工件几何形状,确定切削路径的走向、形状和间距;Determine the direction, shape and spacing of the cutting path according to the processing requirements and workpiece geometry; 基于确定的切削路径的走向、形状和间距设定切削方向,包括进给方向和切削方向;Setting the cutting direction, including the feed direction and the cutting direction, based on the determined cutting path direction, shape and spacing; 步骤3.初始刀具运动控制和预测,控制刀具的运动轨迹和速度,包括刀具的X、Y、Z轴坐标的控制,加工前预加载工件模型到数控系统中;利用预加载的模型数据和预测算法,预测下一次刀具定位的坐标点,将预测结果作为初始定位;Step 3. Initial tool motion control and prediction, control the tool motion trajectory and speed, including the control of the tool's X, Y, and Z axis coordinates, preload the workpiece model into the CNC system before processing; use the preloaded model data and prediction algorithm to predict the coordinate point of the next tool positioning, and use the prediction result as the initial positioning; 工件模型构建步骤包括:The steps of building the artifact model include: 使用三维激光扫描仪对工件表面进行扫描,获取表面的三维点云数据;Use a 3D laser scanner to scan the surface of the workpiece to obtain 3D point cloud data of the surface; 对扫描得到的点云数据进行处理,包括滤波、点云配准,获取工件表面三维模型;Process the scanned point cloud data, including filtering and point cloud registration, to obtain a three-dimensional model of the workpiece surface; 利用点云数据,采用基于网格的重建算法生成工件的三维表面模型;Using point cloud data, a grid-based reconstruction algorithm is used to generate a three-dimensional surface model of the workpiece; 构建预测模型,输入参数包括以及Construct a prediction model, the input parameters include , as well as , 其中,为工件表面的三维模型,表示三维网格数据,为刀具当前位置的特征向量,包括位置坐标、切削速度、加速度,表示下一次刀具位置的预测值;in, is the three-dimensional model of the workpiece surface, representing the three-dimensional grid data. is the characteristic vector of the current position of the tool, including position coordinates, cutting speed, and acceleration. Indicates the predicted value of the next tool position; 预测模型的输入为,输出为值The input of the prediction model is and , the output is the value ; 将预测模型与加工数据进行训练,学习工件表面和刀具运动间关系,采用反向传播算法和优化器,优化模型参数;The prediction model is trained with machining data to learn the relationship between the workpiece surface and tool motion, and the model parameters are optimized using the back propagation algorithm and optimizer; 步骤3中,预测算法的构建方式为:In step 3, the prediction algorithm is constructed as follows: 准备训练集和验证集,基于长短期记忆网络LSTM构建预测模型,定义输入参数,包括以及,其中,为工件表面的三维模型,表示三维网格数据,为刀具当前位置的特征向量,包括位置坐标、切削速度、加速度,表示下一次刀具位置的预测值;Prepare training sets and validation sets, build a prediction model based on the long short-term memory network LSTM, and define input parameters, including , as well as ,in, is the three-dimensional model of the workpiece surface, representing the three-dimensional grid data. is the characteristic vector of the current position of the tool, including position coordinates, cutting speed, and acceleration. Indicates the predicted value of the next tool position; 使用反向传播算法和梯度下降优化算法,对神经网络模型进行训练,优化损失函数公式为:,其中为实际刀具位置,为样本数量,表示时间步;Use the back propagation algorithm and gradient descent optimization algorithm to train the neural network model, and the optimization loss function formula is: ,in is the actual tool position, is the sample size, represents the time step; 使用验证集对训练的神经网络模型进行验证,调整模型结构和超参数;Use the validation set to validate the trained neural network model and adjust the model structure and hyperparameters; 在加工前,将刀具当前位置的特征向量和工件表面的三维模型输入训练好的神经网络模型;Before machining, the feature vector of the tool’s current position is and 3D model of the workpiece surface Input the trained neural network model; 模型输出下一次刀具位置的预测值The model outputs the predicted value of the next tool position ; 步骤4.加工阶段工件实时监测与定位调整,部署位移传感器、摄像头,实时监测工件表面情况并采集传感器数据,根据实时数据动态调整预测模型,根据工件表面实际情况和传感器数据实时调整刀具的位置和姿态,将刀具与工件表面对齐;Step 4. Real-time monitoring and positioning adjustment of the workpiece during the processing phase: deploy displacement sensors and cameras to monitor the surface of the workpiece in real time and collect sensor data. Dynamically adjust the prediction model based on the real-time data, adjust the position and posture of the tool in real time based on the actual situation of the workpiece surface and sensor data, and align the tool with the workpiece surface. 具体的:将位移传感器和摄像头安装在加工设备上,实时监测工件表面的情况,连续地监测工件表面的情况,包括表面形状、粗糙度、温度,采集传感器数据,并进行处理和分析,根据实时传感器数据,动态调整预测模型,使其预测下一步刀具位置,Specifically: Install displacement sensors and cameras on processing equipment to monitor the surface of the workpiece in real time and continuously monitor the surface of the workpiece, including surface shape, roughness, and temperature. Collect sensor data, process and analyze it. According to real-time sensor data, dynamically adjust the prediction model to predict the next tool position. 采用自适应算法根据新的数据更新模型参数,适应工件表面的实际情况变化,根据预测模型输出的刀具位置预测值,以及实时传感器数据,实时调整刀具的位置和姿态,使用数控系统提供的控制功能,调整刀具的加工路径和运动轨迹,使刀具与工件表面对齐,根据实时调整后的刀具位置和姿态,将刀具与工件表面对齐,调整刀具的位置和姿态,使其与工件表面完全贴合;Adopting adaptive algorithms to update model parameters according to new data, adapting to the actual changes of the workpiece surface, adjusting the position and posture of the tool in real time according to the tool position prediction value output by the prediction model and real-time sensor data, using the control function provided by the CNC system to adjust the processing path and motion trajectory of the tool so that the tool is aligned with the workpiece surface, and adjusting the position and posture of the tool so that it fits the workpiece surface completely according to the real-time adjusted tool position and posture; 预测下一步刀具位置的方式为:The way to predict the next tool position is: 使用位移传感器和摄像头连续地监测工件表面情况,并采集相关传感器数据,对采集的数据进行预处理,包括噪声滤波、数据对齐和校准,Use displacement sensors and cameras to continuously monitor the surface of the workpiece, collect relevant sensor data, and pre-process the collected data, including noise filtering, data alignment and calibration. 采用基于深度学习的神经网络模型,将实时传感器数据作为模型的输入特征,预测下一步刀具位置的输出值,使用梯度下降法根据实际的预测误差更新模型参数,定义损失函数衡量模型预测值与实际值之间的差异,根据更新后的预测模型输出的刀具位置预测值,结合实时传感器数据,调整刀具的位置和姿态;A neural network model based on deep learning is used, and real-time sensor data is used as the input feature of the model to predict the output value of the next tool position. The gradient descent method is used to update the model parameters according to the actual prediction error. A loss function is defined to measure the difference between the model prediction value and the actual value. The tool position and posture are adjusted based on the tool position prediction value output by the updated prediction model and combined with the real-time sensor data. 步骤5.冗余控制,部署高冗余性、容错性的系统架构,配备多重备份和冗余控制机制,异常情况下自动切换到备用模式。Step 5. Redundant control: deploy a highly redundant and fault-tolerant system architecture, equipped with multiple backup and redundant control mechanisms, and automatically switch to backup mode under abnormal circumstances. 2.根据权利要求1所述的一种数控3轴工艺加工过程中刀具快速找到模型坐标的方法,其特征在于,冗余控制系统架构包括:2. According to a method for a tool to quickly find model coordinates during a CNC three-axis process according to claim 1, it is characterized in that the redundant control system architecture includes: 主控制模块,负责监控加工设备的运行状态、控制加工过程以及处理各种指令;The main control module is responsible for monitoring the operating status of the processing equipment, controlling the processing process, and processing various instructions; 冗余主控制模块,进行主备切换和容错控制;Redundant main control module for active/standby switching and fault-tolerant control; 备份控制模块,作为主控制模块的备份,与主控制模块保持同步,随时准备接管控制权,与主控制模块通过冗余通信链路实时通信;The backup control module, as a backup of the main control module, keeps in sync with the main control module, is ready to take over control at any time, and communicates with the main control module in real time through a redundant communication link; 电源模块,提供设备所需的电源供应,配备冗余电源模块,在主电源故障时能够自动切换到备用电源。The power supply module provides the power supply required by the equipment. It is equipped with a redundant power supply module, which can automatically switch to the backup power supply when the main power supply fails. 3.根据权利要求2所述的一种数控3轴工艺加工过程中刀具快速找到模型坐标的方法,其特征在于,冗余控制系统架构还包括:3. The method for a tool to quickly find model coordinates during a CNC three-axis process according to claim 2, wherein the redundant control system architecture further comprises: 传感器模块,负责监测工件和设备参数,包括温度、压力、速度;配备冗余传感器模块,在传感器故障时能够继续获取数据;Sensor modules are responsible for monitoring workpiece and equipment parameters, including temperature, pressure, and speed; they are equipped with redundant sensor modules to continue to acquire data in the event of a sensor failure; 执行模块,控制刀具的运动和姿态;The execution module controls the movement and posture of the tool; 通信模块,负责与外部设备和系统进行通信,包括工控机、监控系统;The communication module is responsible for communicating with external devices and systems, including industrial computers and monitoring systems; 故障检测与自动切换模块,实施异常检测和自动切换逻辑,监测系统各个模块的运行状态,当检测到故障时自动切换到备用模式。The fault detection and automatic switching module implements abnormality detection and automatic switching logic, monitors the operating status of each module of the system, and automatically switches to the backup mode when a fault is detected.
CN202410876456.8A 2024-07-02 2024-07-02 A method for the tool to quickly find the model coordinates during CNC 3-axis processing Active CN118838285B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410876456.8A CN118838285B (en) 2024-07-02 2024-07-02 A method for the tool to quickly find the model coordinates during CNC 3-axis processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410876456.8A CN118838285B (en) 2024-07-02 2024-07-02 A method for the tool to quickly find the model coordinates during CNC 3-axis processing

Publications (2)

Publication Number Publication Date
CN118838285A CN118838285A (en) 2024-10-25
CN118838285B true CN118838285B (en) 2025-01-28

Family

ID=93138037

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410876456.8A Active CN118838285B (en) 2024-07-02 2024-07-02 A method for the tool to quickly find the model coordinates during CNC 3-axis processing

Country Status (1)

Country Link
CN (1) CN118838285B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119596847A (en) * 2025-02-10 2025-03-11 晨和晨智能装备(江苏)有限责任公司 Dynamics control method for five-axis numerical control machining cutter vector of complex curved surface

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109318051A (en) * 2018-10-17 2019-02-12 芜湖常瑞汽车部件有限公司 A kind of curved surface part numerical control processing localization method
CN117718831A (en) * 2024-01-16 2024-03-19 浙江万丰科技开发股份有限公司 Off-line programming method of full six-axis CNC rough machining polishing equipment

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003033219A2 (en) * 2001-10-15 2003-04-24 Hermann Tropf Correction of the relative motion between gripping or machining tools and work pieces
JP2005034934A (en) * 2003-07-18 2005-02-10 Yamazaki Mazak Corp Numerically controlled apparatus, machine tool equipped with the same, and method for calculating coordinate of workpiece
CN111347292B (en) * 2020-02-21 2023-04-11 青岛理工大学 System and method for monitoring and controlling state of cutter of numerical control machine tool
EP4590468A1 (en) * 2022-09-21 2025-07-30 3M Innovative Properties Company Systems and techniques for workpiece modification
CN118081428A (en) * 2024-03-20 2024-05-28 哈尔滨理工大学 A fixture for machining shallow holes and straight cooling holes and a method for determining the cutting point thereof

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109318051A (en) * 2018-10-17 2019-02-12 芜湖常瑞汽车部件有限公司 A kind of curved surface part numerical control processing localization method
CN117718831A (en) * 2024-01-16 2024-03-19 浙江万丰科技开发股份有限公司 Off-line programming method of full six-axis CNC rough machining polishing equipment

Also Published As

Publication number Publication date
CN118838285A (en) 2024-10-25

Similar Documents

Publication Publication Date Title
US11656614B2 (en) In-process digital twinning
Dittrich et al. Self-optimizing tool path generation for 5-axis machining processes
JP6959278B2 (en) Chatter vibration judgment device, machine learning device and system
CN101477351B (en) Intelligent NC method with self-optimization function of three-level machining
CN118838285B (en) A method for the tool to quickly find the model coordinates during CNC 3-axis processing
CN118897511B (en) Contour error prediction compensation control method for high-precision complex aluminum member processing
CN110405532A (en) Tool selecting apparatus and machine learning device
CN116501005B (en) Digital twin linkage factory operation management method and system
EP4121829A1 (en) Morphic manufacturing
Mansour et al. Feedrate optimization for computer numerically controlled machine tools using modeled and measured process constraints
CN112872435A (en) AC type double-swing-head five-axis linkage machine tool multi-axis servo matching method and device
CN118778543A (en) A method, system and program product for intelligent control of numerical control machining process
Dittrich et al. Autonomous machining–Recent advances in process planning and control
CN119644917A (en) Machine tool self-adaptive control system based on digital twin and implementation method thereof
CN119426675A (en) Multi-axis PCB milling synchronous control method, device, equipment and storage medium
Vasileva et al. Optimization of the CNC machining process using digital twins
CN108776459B (en) Process method for improving machining precision of five-axis numerical control machine tool
CN119105404B (en) Pole processing method in tool great circle interpolation process in numerical control system
CN119871091B (en) A high-precision multi-axis machining composite CNC machine tool control system
CN119210263B (en) Motor accurate stop control method and system applied to horizontal inverted combined tool magazine
CN115657598B (en) Machine tool simulation optimization design method and system based on fuzzy evaluation
Pivkin et al. Digital cyber-physical system for designing and manufacturing of conical end mill
Zhou Research on Digital Engineering Modeling System under Computer Virtual Reality Technology
CN119758875A (en) A CNC machine tool adaptive control system and method
CN119973726A (en) A digital twin tool wear life prediction method and system based on physical information neural network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant