US 11,630,435 B2Granted

Method and system for monitoring tool wear to estimate RUL of tool in machining

AssigneeTata Consultancy Services Limited

InventorsAnkur Krishna, Bilal Muhammed

Life of this patent

Estimating the term…

Loading patent…

Abstract

Tool wear monitoring is critical for quality and precision of manufacturing of parts in the machining industry. Existing tool wear monitoring and prediction methods are sensor based, costly and pose challenge in ease of implementation. Embodiments herein provide method and system for monitoring tool wear to estimate Remaining Useful Life (RUL) of a tool in machining is disclosed. The method provides a tool wear model, which combines tool wear physics with data fitting, capture practical considerations of a machining system, which makes the tool wear prediction and estimated RUL more stable, reliable and robust. Further, provides cost effective and practical solution. The disclosed physics based tool wear model for RUL estimation captures privilege of physics of tool wear and easily accessible data from CNC machine to monitor and predict tool wear and RUL of the tool in real-time.

Claims6

Dependent claims

A processor implemented method for monitoring tool wear to estimate Remaining Useful Life (RUL) of a tool, the method comprising:

obtaining, by one or more hardware processors, a plurality of process parameters associated with machining process of a work piece, wherein the plurality of process parameters, comprising a spindle power (Sp), a radial depth of cut (w) of the tool, an axial depth of cut t of the tool, and a cutting velocity V, are obtained directly from a Computer Numerical Control (CNC) machine;
deriving, by the one or more hardware processors, a rate of volumetric wear loss per unit contact area of the tool in terms of a rate of change of flank wear width
(
dVB
dt
)
of the tool, wherein the rate of change of flank wear width
(
dVB
dt
)
is computed using a physics based tool wear model, wherein the physics based tool wear model is developed using the spindle power (Sp), the radial depth of cut (w), the axial depth of cut t of the tool, the cutting velocity V, predetermined constants A1 and B1 defined in accordance with a combination of the tool and material of the work piece, and a predetermined temperature wear coefficient (Kw), wherein the temperature wear coefficient Kw considers effect of temperature rise due to friction caused by a current tool wear state of the tool during the machining operation, wherein the constants A1 and B1 defined in accordance with the combination of the tool and the material of the work piece are predetermined by fitting data for a selected combination of the tool and work piece material and previous machining data using least square fitting technique, and wherein the temperature wear coefficient (Kw) is tuned from the previous machining data associated with the machining process, using a specific energy of material removal (Uc) of the work piece, the cutting velocity V, a uncut chip thickness, a thermal conductivity (K) of the tool material, a density (ρ) of the tool material, and a specific heat capacity (c) of the tool material, and
wherein the physics based tool wear model is trained using published tool wear data and a set of initial matching data in case of a new set of machining condition including change in a job and the tool thereby making a system automatic, agile, self-depend, and available in changing machining conditions;
determining, by the one or more hardware processors, a cumulative flank wear growth (VB) for a current time instant by summing the rate of change of flank wear width
(
dVB
dt
)
for a plurality of cuts performed by the tool for a plurality of parts during the machining operation;
and
estimating, by the one or more hardware processors, the RUL of the tool at the current time instant from the determined cumulative flank wear growth (VB) and a maximum allowed value for the cumulative flank tool wear predefined for the tool.

18 more elements

A system for monitoring tool wear to estimate Remaining Useful Life (RUL) of a tool, the system comprising:

a memory storing instructions;
one or more Input/Output (I/O) interfaces;
and
one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to:
obtain a plurality of process parameters associated with machining process of a work piece, wherein the plurality of process parameters, comprising a spindle power (Sp), a radial depth of cut (w) of the tool, an axial depth of cut t of the tool, and a cutting velocity V, are obtained directly from a Computer Numerical Control (CNC) machine;
derive a rate of volumetric wear loss per unit contact area of the tool in terms of a rate of change of flank wear width
(
dVB
dt
)
of the tool, wherein the rate of change of flank wear width
(
dVB
dt
)
is computed using a physics based tool wear model, wherein the physics based tool wear model is developed using the spindle power (Sp), the radial depth of cut (w), the axial depth of cut t of the tool, the cutting velocity V, predetermined constants A1 and B1 defined in accordance with a combination of the tool and material of the work piece, and a predetermined temperature wear coefficient (Kw), wherein the temperature wear coefficient Kw considers effect of temperature rise due to friction caused by a current tool wear state of the tool during the machining operation, wherein the constants A1 and B1 defined in accordance with the combination of the tool and the material of the work piece are predetermined by fitting data for a selected combination of the tool and work piece material and previous machining data using least square fitting technique, and wherein the temperature wear coefficient (Kw) is tuned from the previous machining data associated with the machining process, using a specific energy of material removal (Uc) of the work piece, the cutting velocity V, a uncut chip thickness, a thermal conductivity (K) of the tool material, a density (ρ) of the tool material, and a specific heat capacity (c) of the tool material, and
wherein the physics based tool wear model is trained using published tool wear data and a set of initial matching data in case of a new set of machining condition including change in a job and the tool thereby making a system automatic, agile, self-depend, and available in changing machining conditions;
determine a cumulative flank wear growth (VB) for a current time instant by summing the rate of change of flank wear width
(
dVB
dt
)
for a plurality of cuts performed by the tool for a plurality of parts during the machining operation;
and
estimate the RUL of the tool at the current time instant from the determined cumulative flank wear growth (VB) and a maximum allowed value for the cumulative flank tool wear predefined for the tool.

22 more elements

One or more non-transitory machine readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors causes a method for:

obtaining a plurality of process parameters associated with machining process of a work piece, wherein the plurality of process parameters, comprising a spindle power (Sp), a radial depth of cut (w) of the tool, an axial depth of cut t of the tool, and a cutting velocity V, are obtained directly from a Computer Numerical Control (CNC) machine;
deriving a rate of volumetric wear loss per unit contact area of the tool in terms of a rate of change of flank wear width
(
dVB
dt
)
the tool, wherein the rate of change of flank wear width
(
dVB
dt
)
is computed using a physics based tool wear model, wherein the physics based tool wear model is developed using the spindle power (Sp), the radial depth of cut (w), the axial depth of cut t of the tool, the cutting velocity V, predetermined constants A1 and B1 defined in accordance with a combination of the tool and material of the work piece, and a predetermined temperature wear coefficient (Kw), wherein the temperature wear coefficient Kw considers effect of temperature rise due to friction caused by a current tool wear state of the tool during the machining operation, wherein the constants A1 and B1 defined in accordance with the combination of the tool and the material of the work piece are predetermined by fitting data for a selected combination of the tool and work piece material and previous machining data using least square fitting technique, and wherein the temperature wear coefficient (Kw) is tuned from the previous machining data associated with the machining process, using a specific energy of material removal (Uc) of the work piece, the cutting velocity V, a uncut chip thickness, a thermal conductivity (K) of the tool material, a density (ρ) of the tool material, and a specific heat capacity (c) of the tool material, and
wherein the physics based tool wear model is trained using published tool wear data and a set of initial matching data in case of a new set of machining condition including change in a job and the tool thereby making a system automatic, agile, self-depend, and available in changing machining conditions;
determining a cumulative flank wear growth (VB) for a current time instant by summing the rate of change of flank wear width
(
dVB
dt
)
for a plurality of cuts performed by the tool for a plurality of parts during the machining operation;
and
estimating a Remaining Useful Life (RUL) of the tool at the current time instant from the determined cumulative flank wear growth (VB) and a maximum allowed value for the cumulative flank tool wear predefined for the tool.

18 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/976,833Filed 9 Oct 2019
Priority: IN 20182103882212 Oct 2018
Published: US 2021/0356934 A118 Nov 2021
Granted: 18 Apr 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

G05B 19/4065
Characterised by monitoring or safety: monitoring tool breakage, life or condition
G01N 3/58
Investigating strength properties of solid materials by application of mechanical stress: investigating machinability by cutting tools;…
G01N 2203/0218
Theories, calculations: calculations based on experimental data
G05B 2219/37252
Measurements: life of tool, service life, decay, wear estimation