CNC control unit with learning ability for machining centers

• US 7,117,056 B2
• Filed: 05/02/2005
• Issued: 10/03/2006
• Est. Priority Date: 03/27/2002
• Status: Expired due to Fees

• Current Assignee: Joze Balic
• Original Assignee: Joze Balic
• Inventors: Balic, Joze
• Primary Examiner(s): Picard, Leo
• Assistant Examiner(s): Masinick, Michael D.
• Application Number:
  US11/120,018
• Publication Number:
  US 20050251284A1
• Time in Patent Office: 519 Days
• Field of Search: 700/95, 700/104, 706/6
• US Class Current: 700/104
• CPC Class Codes: G05B 19/4099 Surface or curve machining, making 3D objects, e.g. desktop manufacturing
• CPC Class Codes: G05B 2219/33034 Online learning, training
• CPC Class Codes: G05B 2219/45145 Milling
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

A computer numerical control unit with learning ability solves the problem of automatic and intelligent generating of numerical control programs for computer numerical control machining centers for milling, drilling and similar operations. The key module of the computer numerical control unit is a neural network (NN) device that learns to generate the numerical control programs through an neural network teaching module. Upon completion of learning process the neural network device can generate automatically, without any intervention of the operator, merely on the basis of the CAD 2D, 2,5D or 3D part models, taken from a conventional CAD/CAM system, various new numerical control programs for different parts, which have not been in the machining process before. The computer numerical control control unit with learning ability is suitable especially for machining centers intended for milling, including face milling (rough), contour milling (rough), final milling following the contour and in Z-plane, final contour 3D milling, contour final milling, milling in Z-plane, final contour milling on the equidistant, and milling of pockets; drilling, including normal drilling, deep drilling, and center drilling; and reaming, sinking and threading.

Claims

1. A computer numerical control unit for machining centers with learning ability and ability of automatic intelligent generation of control programs, comprising a neural network device, a modified microcomputer, a comparison unit, a position measuring module and an amplifier, the improvement comprising a neural network device that takes instructions from a neural network teaching module that is not a constituent part of the computer numerical control unit and operates independently taking as a basis for its operation a data package received from a conventional CAD&

CAM system, in order to operate as an intelligent programming module after a teaching process is completed and to automatically generate the numerical control program adequate for a given part to be processed in the machining centers;

the numerical control program being fed to the modified micro computer including an internal interface with its first output connected to a position memory and its second output connected to a function memory, which accepts also manual input commands fed through a manual input module and a decoding unit;

the modified microcomputer further includes a function program module, with its module input connected to the function memory and its output connected to an adaptable interface system, and an interpolation program module with its input connected to the position memory and its output connected to the comparison unit which has its other input connected to the output of the position measuring module, to which the position data are fed from a position meter, while the output of the comparison unit is connected to an amplifier which feeds geometric data to a step motor.

2. The computer numerical control unit for machining centers defined in claim 1, wherein in the mode of intelligent and automated processing of a CAD part model into a specific numerical control program the data package of the CAD part model is fed to the neural network device, which first identifies and classifies the individual geometric and technological features of the CAD part model and then builds a new CAD part model, which is transmitted to a neural network milling module, supplying on its output the numerical control program for the processed given part, the numerical control program being fed to an internal interface, which splits data in the numerical control program into a position package saved in the position memory and into function data saved in the function memory, wherein the function program module, containing the technological data, is transmitted through the adaptable interface system to a numerical control machine, while the numerical position program, generated in the interpolation program module, is sent over the comparison unit and the amplifier unit to the step motors of the numerical machine resulting in a movement either of parts support or of tools in accordance with the geometric data, wherein the position meter perceives the movement and sends a regulated size into the position measuring module, which transmits the data to the comparison unit, where the difference between the actual and the programmed position is calculated, while the geometric data are obtained from the numerical control program for each part and are treated in a position regulation circle.

3. The computer numerical control unit defined in claim 1, that can automatically generate the numerical control programs by means of an instructed neural network contained in the neural network teaching module 4 using engineering drawing module of parts, wherein in a learning phase, the neural network device is connected to the teaching module 4 which takes teaching numerical control programs for different parts defined in the engineering drawings module from a conventional CAD/CAM system, and wherein a decision on success of teaching process is taken in a decision module, subsequent to a testing module, so that in case the decision is NO, a path is active and repetition of the teaching process takes place, while on the other hand in case that the neural network device has learned enough, the path is active and a generated neural network is sent to the neural network device.

4. The computer numerical control unit for machining centers defined in claim 1, wherein the neural network device is realized in a microprocessor technique and contains an identification module that recognizes geometrical and technological features of different CAD part models, a generating module that produces a new feature based CAD models of parts, a neural network milling module, and an automatically generated numerical control program for a given part.

5. The computer numerical control unit defined in claim 1 wherein a neural network milling module enables intelligent, automatic generating of numerical control programs that enable machining operations, comprising milling, including face milling (rough), contour milling (rough), final milling following the contour and in Z-plane, final contour 3D milling, contour final milling, milling in Z-plane, final contour milling on the equidistant, and milling of pockets;

drilling, including normal drilling, deep drilling, and center drilling; and

reaming, sinking and threading;

to be executed on prismatic parts.

6. The computer numerical control unit for machining centers defined in claim 1, wherein the numerical control programs are generated in a conventional CAD/CAM system based on engineering drawings of parts, the numerical control programs serving as teaching numerical control programs in the neural network teaching module 4 that instructs the neural network device, wherein the decision on success of teaching process is taken in a decision module, subsequent to a testing module, so that in case the decision is NO, a path is active and repetition of the teaching process takes place, while on the other hand in case that the-neural network device has learned enough, the path is active and a generated neural network is sent to the neural network device.