Method for analyzing and optimizing a machining process

• US 7,933,679 B1
• Filed: 10/22/2008
• Issued: 04/26/2011
• Est. Priority Date: 10/23/2007
• Status: Active Grant

• Current Assignee: Textron Innovations Incorporated (Textron Inc)
• Original Assignee: Cessna Aircraft Company (Textron Inc)
• Inventors: Konde, Parag, Kulkarni, Pravin, Deshpande, Amit, Joshi, Dhananjay, Syed, Kareem
• Primary Examiner(s): Bahta; Kidest
• Application Number:
  US12/256,257
• Time in Patent Office: 916 Days
• Field of Search: 700/175, 700/172, 700/182, 700/180, 700/177, 700/173, 703/2, 703/56, 340/683, 735/79
• US Class Current: 700/173
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G05B 2219/36252 Generate machining program based on a simulation to optimize a machine parameter

Abstract

A method for optimizing machining parameters for a cutting process performed on a work piece. Finite element analysis of cutting tool and work material interaction is initially performed. Mechanistic modeling of the cutting process, using results of the finite element analysis, is then performed to provide optimized machining parameters for improved rate of material removal and tool life. Optionally, a two-stage artificial neural network may be supplementally employed, wherein a first stage of the network provides output parameters including peak tool temperature and cutting forces in X and Y directions, for a combination of input reference parameters including tool rake angle, material cutting speed, and feed rate.

Claims

1. A method for optimizing machining parameters for a milling process performed on a work piece using a cutting tool, the method comprising:

performing finite element analysis of cutting tool and work material interaction to determine an optimized combination of the machining parameters by varying work material properties, cutting tool geometry, cutting speed and feed rate;

performing mechanistic modeling of the milling process, using results of the finite element analysis, to provide optimized machining parameters for improved rate of material removal and tool life;

using a two-stage artificial neural network, wherein a first stage of the network provides output parameters including peak tool temperature and cutting forces in X and Y directions, for a combination of input reference parameters including tool rake angle, material cutting speed, and feed rate;

wherein the output parameters obtained from the first stage are considered to be baseline parameters;

applying acceptance criteria to the baseline parameters determine acceptable baseline parameters;

using the acceptable baseline parameters as input to a second stage of the network;

obtaining optimized values of machining parameters, including surface speed and feed rate, from the second stage of the network; and

utilizing the optimized values to improve work piece material removal rate and cutting tool life.

2. The method of claim 1, wherein resonance-based vibration analysis is performed prior to the finite element analysis and the mechanistic modeling, by analyzing cutting tool operation to determine machining parameters which result in reduced tool chatter.

3. The method of claim 2, wherein the optimized combination of machining parameters include parameters selected from the set consisting of work piece material grade, set-up rigidity, cutting tool material, flute type, insert type, corner radius, and number of flutes.

4. The method of claim 1, wherein:

the finite element analysis is performed by simulating operation of the cutting tool to determine the optimized cutting speed and feed rate; and

the mechanistic modeling is performed by analyzing operation of the cutting tool to balance resultant cutting forces, temperature, and milling machine power.

5. The method of claim 1, wherein the finite element analysis is performed using information including parameters selected from the set consisting of machining parameters, work material properties and cutting tool details, to provide a prediction of parameters selected from the group consisting of cutting forces, tool temperature, tool stresses, tool pressure, and milling machine power consumption, resulting from machining the work piece.

6. The method of claim 5, wherein the finite element analysis is performed by varying cutting speed and feed rate while maintaining constant depth of cut.

7. The method of claim 1 wherein the mechanistic modeling is performed using parameters selected from the set consisting of work piece material properties, raw stock geometry, cutting tool details, and numerical control tool path to provide a prediction of cutting force, tool temperature, and milling machine power consumption, resulting from machining various features of the work piece.

8. A method for optimizing machining parameters for a turning process performed on a work piece using a cutting tool, the method comprising:

performing finite element analysis of cutting tool and work material interaction to determine an optimized combination of the machining parameters, using a finite element model, by varying work material properties, cutting tool geometry, cutting speed and feed per tooth;

performing mechanistic modeling of the turning process, using results of the finite element analysis, to provide optimized machining parameters for improved rate of material removal and tool life;

using a two-stage artificial neural network, wherein a first stage of the network provides output parameters including peak tool temperature and cutting forces in X and Y directions, for a combination of input reference parameters including tool rake angle, material cutting speed, and feed per tooth;

wherein the output parameters obtained from the first stage are considered to be baseline parameters;

applying acceptance criteria to the baseline parameters determine acceptable baseline parameters;

using the acceptable baseline parameters as input to a second stage of the network;

obtaining optimized values of machining parameters, including surface speed and feed per tooth, from the second stage of the network; and

utilizing the optimized values to improve work piece material removal rate and cutting tool life.

9. The method of claim 8, wherein the parameters to be optimized are selected from the set consisting of surface speed, feed rate, depth of cut, tool material, holder types, and insert types.

10. The method of claim 8, wherein:

the finite element analysis is performed by simulating operation of the cutting tool to determine the optimized cutting speed and feed rate; and

the mechanistic modeling is performed by analyzing operation of the cutting tool to balance resultant cutting forces, temperature, and turning machine power.

11. The method of claim 8, wherein the finite element analysis is performed using information including parameters selected from the set consisting of machining parameters, work material properties and cutting tool details, to provide a prediction of parameters selected from the group consisting of cutting forces, tool temperature, tool stresses, tool pressure, and turning machine power consumption, resulting from machining the work piece.

12. The method of claim 11, wherein the finite element analysis is performed by varying cutting speed and feed rate while maintaining constant depth of cut.

13. The method of claim 8 wherein the mechanistic modeling is performed using parameters selected from the set consisting of work piece material properties, raw stock geometry, cutting tool details, and numerical control tool path to provide a prediction of cutting force, tool temperature, and turning machine power consumption, resulting from machining various features of the work piece.

14. A method for optimizing machining parameters for a cutting process performed on a work piece using a cutting tool, the method comprising:

performing finite element analysis of cutting tool and work material interaction;

performing mechanistic modeling and analysis of the cutting process, using results of the finite element analysis, to provide machining parameters for an improved rate of material removal and tool life;

determining an optimized combination of the machining parameters, using a finite element model, by varying work material properties, cutting tool geometry, cutting speed and feed rate;

using a two-stage artificial neural network, wherein a first stage of the network provides output parameters including peak tool temperature and cutting forces in X and Y directions, for a combination of input reference parameters including tool rake angle, material cutting speed, and feed rate;

wherein the output parameters obtained from the first stage are considered to be baseline parameters;

applying acceptance criteria to the baseline parameters determine acceptable baseline parameters;

using the acceptable baseline parameters as input to a second stage of the network;

obtaining optimized values of machining parameters, including surface speed and feed rate, from the second stage of the network; and

utilizing the optimized values to improve work piece material removal rate and cutting tool life.