CN105563234A - Twist drill abrasion monitoring method - Google Patents
Twist drill abrasion monitoring method Download PDFInfo
- Publication number
- CN105563234A CN105563234A CN201610042351.8A CN201610042351A CN105563234A CN 105563234 A CN105563234 A CN 105563234A CN 201610042351 A CN201610042351 A CN 201610042351A CN 105563234 A CN105563234 A CN 105563234A
- Authority
- CN
- China
- Prior art keywords
- neutral net
- drill
- wear
- fluted drill
- bit
- 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.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/09—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/09—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool
- B23Q17/0952—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool during machining
- B23Q17/0957—Detection of tool breakage
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a twist drill abrasion monitoring method. Firstly, four parameters such as drilling force, torque, electric current of a spindle motor and electric current of a feed motor in the different abrasion states are collected under the same cutting parameter; the four parameters are subjected to wavelet packet decomposition to obtain energy spectrums of eight frequency bands; and the energy spectrums of the second frequency band, the third frequency band, the fourth frequency band and the fifth frequency band are used as characteristic values serving as conditional attributes, the three abrasion states of a drill bit of a twist drill are used as decision attributes, a decision table is established, and the characteristic values are used as input neurons of a BP neural network for training and learning. The abrasion state recognition of the twist drill is performed through the established BP neural network, and the recognition rate is high.
Description
Technical field
The present invention relates to the Study On Intelligent Monitoring Techniques field of machine cut machining tool, particularly a kind of fluted drill wear monitoring method.
Background technology
On automated machine machining production line, the fluted drill wearing and tearing of drilling power head can have influence on crudy and the production efficiency of workpiece.In existing Tool Wear Monitoring device; the classification of Cutter wear state or too coarse; too meticulous, easily there is cutter time too coarse and lost efficacy because of wearing and tearing, cause processed workpiece size deviation excessive or shut down; monitoring complexity is improve time too meticulous; real-time decreases, and monitoring exists certain hysteresis quality, and monitoring result is often inconsistent with the actual wear state of cutter; cause cutter inordinate wear, and then affect the machining accuracy of workpiece.
Summary of the invention
The object of the invention is to solve the classification of current Tool Wear Monitoring device Cutter wear state or too coarse, otherwise too meticulous, cause the technical problem that processed workpiece size deviation is excessive.
For realizing above goal of the invention, the invention provides a kind of fluted drill wear monitoring method, jointly driving described fluted drill to carry out workpiece cutting by spindle motor and feeding motor, comprising the steps:
(1) cutting parameter is set: set the rotating speed of described spindle motor as n; If when described spindle motor rotates a circle, the amount of feeding of described feeding motor is f;
(2) when described spindle motor and described feeding motor work with cutting parameter described in step (1), following four parameters of drill bit under normal wear, excessive wear and tipping three kinds of state of wear of described fluted drill are gathered respectively: the electric current of the drill thrust of described fluted drill drill bit, the moment of torsion of described fluted drill drill bit, the electric current of described spindle motor and described feeding motor;
(3) by db4 wavelet packet, three layers of WAVELET PACKET DECOMPOSITION are carried out to described four parameters of step (2), obtain 8 frequency band energy spectrums, the energy spectrum getting four frequency ranges of wherein the 2nd, 3,4 and 5 as characteristic value as conditional attribute, using described three kinds of state of wear of the drill bit of described fluted drill as decision attribute, set up decision table;
(4) using the input vector of the energy spectrum of described for step (3) four frequency ranges as BP neutral net, described three kinds of state of wear of the drill bit of described fluted drill are as the output vector of described BP neutral net, the often group input vector of described BP neutral net and output vector form one group of data sample, choose data sample described in 40 groups and training study is carried out to described BP neutral net, to determine the neuronic coefficient of each layer of described BP neutral net;
(5) predict with the state of wear of described BP neutral net to the drill bit of described fluted drill trained.
Further, the sample frequency of described four parameters of step (2) is 1kHz.
Further, the drill thrust of step (2) described fluted drill drill bit and the moment of torsion of described fluted drill drill bit are gathered by four component piezoelectric transducers.
Further, the electric current of step (2) described spindle motor and the electric current of described feeding motor are gathered by three-phase alternating current transformer.
Further, described BP neutral net selects 3 layers, and input neuron is 4 nodes, and output neuron is 1 node.
Further, by the node in hidden layer progressively changing described BP neutral net, BP neutral net is trained, corresponding node in hidden layer time minimum for the output error of described BP neutral net is defined as the node in hidden layer of the described BP neutral net after training.
Further, the step of carrying out training study to described BP neutral net is as follows:
A () initialization weights and threshold value are the random value in (-1,1) interval;
B () enters circulation, calculate the constrained input of each node of hidden layer and each node of output layer;
C () calculates the error of hidden layer and each node of output layer;
D () uses the gradient descent method correction threshold having adaptive logic to return;
E () completes a circulation, judge whether global error is less than designated value; If so, then exit circulation, forward step (f) to; If not, then step (b) is returned;
F () calculates output layer;
G () training terminates.
Further, when predicting by the bit wear state of described BP neutral net to described fluted drill trained, when the output valve of described BP neutral net is in [0.5,1.499] scope, then the bit wear state of described fluted drill is normal wear; When the output valve of described BP neutral net is in [1.5,2.499] scope, then the bit wear state of described fluted drill is excessive wear; When the output valve of described BP neutral net is in [2.5,3.499] scope, then the bit wear state of described fluted drill is tipping.
Compared with prior art, the invention has the beneficial effects as follows:
The present invention proposes the wear monitoring method based on wavelet packet analysis feature extraction and BP neutral net Intelligent Recognition, analysis method of wavelet packet can convert signal time-domain information to frequency domain information, extracting characteristic value can the feature of reflected signal well, and can ignore a large amount of redundancies; BP neural network algorithm study precision is high, and can be used as general functional simulation device, any nonlinear function of programmable single-chip system, the speed of service is exceedingly fast.The characteristic value that WAVELET PACKET DECOMPOSITION obtains is after BP neural network classification, resolution is very high, improve real-time and the validity of the abrasion of cutting tool status monitorings such as fluted drill, the inordinate wear of fluted drill can be found as early as possible, thus the fluted drill of very first time replacing inordinate wear or tipping, improve quality and the efficiency of batch workpiece processing.
Accompanying drawing explanation
Fig. 1 is the structural representation gathering fluted drill drill thrust and torque signal;
Fig. 2 is the principle schematic gathering current of electric.
In figure, drilling power head 1; Spindle motor 2; Fluted drill 3; Workpiece 4; Drill thrust and torque sensor 5; Three-phase alternating current transformer 6.
Detailed description of the invention
Below in conjunction with the drawings and specific embodiments, the invention will be further described.
As illustrated in fig. 1 and 2, fluted drill wear monitoring method of the present invention, step is as follows:
(1) cutting parameter is set: set the rotating speed of spindle motor 2 as n; If when spindle motor 2 rotates a circle, the amount of feeding of feeding motor is f;
(2) when spindle motor 2 and feeding motor work with cutting parameter in step (1), following four parameters of drill bit under normal wear, excessive wear and tipping three kinds of state of wear of fluted drill 3 are gathered respectively: the electric current of the drill thrust of fluted drill 3 drill bit, the moment of torsion of fluted drill 3 drill bit, the electric current of spindle motor 2 and feeding motor with sample frequency 1kHz, wherein the drill thrust of fluted drill 3 drill bit and moment of torsion are gathered by four component piezoelectric transducers, and the electric current of spindle motor 2 and feeding motor is gathered by three-phase alternating current transformer 6;
(3) by db4 wavelet packet, three layers of WAVELET PACKET DECOMPOSITION are carried out to step (2) four parameters, obtain 8 frequency band energy spectrums, the energy spectrum getting four frequency ranges of wherein the 2nd, 3,4 and 5 as characteristic value as conditional attribute, using three of the drill bit of fluted drill 3 kinds of state of wear as decision attribute, set up decision table;
(4) using the input vector of the energy spectrum of step (3) four frequency ranges as BP neutral net, three kinds of state of wear of the drill bit of fluted drill 3 are as the output vector of BP neutral net, the often group input vector of BP neutral net and output vector form one group of data sample, choose 40 groups of data samples and training study is carried out to BP neutral net, to determine the neuronic coefficient of each layer of BP neutral net; Preferably, BP neutral net selects 3 layers, and input neuron is 4 nodes, and output neuron is 1 node;
(5) predict with the state of wear of BP neutral net to the drill bit of fluted drill 3 trained.
Preferably, by the node in hidden layer progressively changing BP neutral net, BP neutral net is trained, node in hidden layer corresponding time minimum for the output error of BP neutral net is defined as the node in hidden layer of the BP neutral net after training.
Preferably, the step of training study carried out to BP neutral net as follows:
A () initialization weights and threshold value are the random value in (-1,1) interval;
B () enters circulation, calculate the constrained input of each node of hidden layer and each node of output layer;
C () calculates the error of hidden layer and each node of output layer;
D () uses the gradient descent method correction threshold having adaptive logic to return;
E () completes a circulation, judge whether global error is less than designated value; If so, then exit circulation, forward step (f) to; If not, then step (b) is returned;
F () calculates output layer;
G () training terminates.
Preferably, when predicting by the bit wear state of the BP neutral net trained to fluted drill,
When the output valve of BP neutral net is in [0.5,1.499] scope, then the bit wear state of fluted drill is normal wear;
When the output valve of BP neutral net is in [1.5,2.499] scope, then the bit wear state of fluted drill is excessive wear;
When the output valve of BP neutral net is in [2.5,3.499] scope, then the bit wear state of fluted drill is tipping.
With above-mentioned according to desirable embodiment of the present invention for enlightenment, by above-mentioned description, relevant staff in the scope not departing from this invention technological thought, can carry out various change and amendment completely.The technical scope of this invention is not limited to the content on description, must determine its technical scope according to right.
Claims (8)
1. fluted drill wear monitoring method, jointly drives described fluted drill to carry out workpiece cutting by spindle motor and feeding motor, it is characterized in that, comprise the steps:
(1) cutting parameter is set: set the rotating speed of described spindle motor as n; If when described spindle motor rotates a circle, the amount of feeding of described feeding motor is f;
(2) when described spindle motor and described feeding motor work with cutting parameter described in step (1), following four parameters of drill bit under normal wear, excessive wear and tipping three kinds of state of wear of described fluted drill are gathered respectively: the electric current of the drill thrust of described fluted drill drill bit, the moment of torsion of described fluted drill drill bit, the electric current of described spindle motor and described feeding motor;
(3) by db4 wavelet packet, three layers of WAVELET PACKET DECOMPOSITION are carried out to described four parameters of step (2), obtain 8 frequency band energy spectrums, the energy spectrum getting four frequency ranges of wherein the 2nd, 3,4 and 5 as characteristic value as conditional attribute, using described three kinds of state of wear of the drill bit of described fluted drill as decision attribute, set up decision table;
(4) using the input vector of the energy spectrum of described for step (3) four frequency ranges as BP neutral net, described three kinds of state of wear of the drill bit of described fluted drill are as the output vector of described BP neutral net, the often group input vector of described BP neutral net and output vector form one group of data sample, choose data sample described in 40 groups and training study is carried out to described BP neutral net, to determine the neuronic coefficient of each layer of described BP neutral net;
(5) predict with the state of wear of described BP neutral net to the drill bit of described fluted drill trained.
2. the method for claim 1, is characterized in that, the sample frequency of described four parameters of step (2) is 1kHz.
3. method as claimed in claim 1 or 2, it is characterized in that, the drill thrust of step (2) described fluted drill drill bit and the moment of torsion of described fluted drill drill bit are gathered by four component piezoelectric transducers.
4. method as claimed in claim 1 or 2, it is characterized in that, the electric current of step (2) described spindle motor and the electric current of described feeding motor are gathered by three-phase alternating current transformer.
5. the method for claim 1, is characterized in that, described BP neutral net selects 3 layers, and input neuron is 4 nodes, and output neuron is 1 node.
6. method as claimed in claim 5, it is characterized in that, by the node in hidden layer progressively changing described BP neutral net, BP neutral net is trained, corresponding node in hidden layer time minimum for the output error of described BP neutral net is defined as the node in hidden layer of the described BP neutral net after training.
7. method as claimed in claim 6, it is characterized in that, the step of carrying out training study to described BP neutral net is as follows:
A () initialization weights and threshold value are the random value in (-1,1) interval;
B () enters circulation, calculate the constrained input of each node of hidden layer and each node of output layer;
C () calculates the error of hidden layer and each node of output layer;
D () uses the gradient descent method correction threshold having adaptive logic to return;
E () completes a circulation, judge whether global error is less than designated value; If so, then exit circulation, forward step (f) to; If not, then step (b) is returned;
F () calculates output layer;
G () training terminates.
8. method as claimed in claim 7, is characterized in that, when predicting by the bit wear state of described BP neutral net to described fluted drill trained,
When the output valve of described BP neutral net is in [0.5,1.499] scope, then the bit wear state of described fluted drill is normal wear;
When the output valve of described BP neutral net is in [1.5,2.499] scope, then the bit wear state of described fluted drill is excessive wear;
When the output valve of described BP neutral net is in [2.5,3.499] scope, then the bit wear state of described fluted drill is tipping.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610042351.8A CN105563234A (en) | 2016-01-22 | 2016-01-22 | Twist drill abrasion monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610042351.8A CN105563234A (en) | 2016-01-22 | 2016-01-22 | Twist drill abrasion monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105563234A true CN105563234A (en) | 2016-05-11 |
Family
ID=55874146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610042351.8A Pending CN105563234A (en) | 2016-01-22 | 2016-01-22 | Twist drill abrasion monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105563234A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107378779A (en) * | 2017-06-29 | 2017-11-24 | 西安交通大学 | A kind of grinding trembling detection method based on axis feeding motor current signal |
| CN107627152A (en) * | 2017-10-19 | 2018-01-26 | 电子科技大学 | Numerical control machining chip control method based on BP neural network |
| CN108897281A (en) * | 2018-06-06 | 2018-11-27 | 苏州领裕电子科技有限公司 | A kind of tool monitoring system and method |
| CN109719564A (en) * | 2018-12-30 | 2019-05-07 | 扬州市方圆机电制造有限公司 | A kind of bench drill of detectable drill bit sharpness |
| CN109719565A (en) * | 2018-12-30 | 2019-05-07 | 扬州市方圆机电制造有限公司 | Bench drill that is a kind of removable and having detection function |
| CN110458824A (en) * | 2019-08-08 | 2019-11-15 | 中国石油集团川庆钻探工程有限公司 | Drill bit wear detection method |
| CN110480045A (en) * | 2019-09-03 | 2019-11-22 | 莆田市城厢区星华电子模具有限公司 | A kind of mold through-hole aperture expansion processing method |
| CN111716150A (en) * | 2020-06-30 | 2020-09-29 | 大连理工大学 | Evolution learning method for intelligently monitoring cutter state |
| CN111890124A (en) * | 2019-05-05 | 2020-11-06 | 深圳市玄羽科技有限公司 | On-line cutter monitoring system and method |
| CN111975450A (en) * | 2020-08-18 | 2020-11-24 | 山东理工大学 | Horizontal one-way torque adjusting device for cutting |
| CN114871850A (en) * | 2022-04-22 | 2022-08-09 | 浙江大学 | Cutter wear state evaluation method based on vibration signal and BP neural network |
| CN117884951A (en) * | 2024-03-14 | 2024-04-16 | 常州苏美精密切削技术有限公司 | Size detection tool for metal cutting tool |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS60255354A (en) * | 1984-05-29 | 1985-12-17 | Omron Tateisi Electronics Co | Tool-breakage detector |
| CN102091972A (en) * | 2010-12-28 | 2011-06-15 | 华中科技大学 | Numerical control machine tool wear monitoring method |
| CN103465107A (en) * | 2013-09-24 | 2013-12-25 | 沈阳利笙电子科技有限公司 | Tool wear monitoring method |
| CN104723171A (en) * | 2015-03-17 | 2015-06-24 | 洛阳理工学院 | Cutter wear monitoring method based on current and acoustic emission compound signals |
| CN105196114A (en) * | 2015-11-05 | 2015-12-30 | 西安科技大学 | Real-time online tool wear monitoring method based on wavelet analysis and neural network |
-
2016
- 2016-01-22 CN CN201610042351.8A patent/CN105563234A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS60255354A (en) * | 1984-05-29 | 1985-12-17 | Omron Tateisi Electronics Co | Tool-breakage detector |
| CN102091972A (en) * | 2010-12-28 | 2011-06-15 | 华中科技大学 | Numerical control machine tool wear monitoring method |
| CN103465107A (en) * | 2013-09-24 | 2013-12-25 | 沈阳利笙电子科技有限公司 | Tool wear monitoring method |
| CN104723171A (en) * | 2015-03-17 | 2015-06-24 | 洛阳理工学院 | Cutter wear monitoring method based on current and acoustic emission compound signals |
| CN105196114A (en) * | 2015-11-05 | 2015-12-30 | 西安科技大学 | Real-time online tool wear monitoring method based on wavelet analysis and neural network |
Non-Patent Citations (3)
| Title |
|---|
| 崔亚新: "基于双神经网络的微孔钻削在线监测研究", 《中国博士学位论文全文数据库》 * |
| 谌鑫: "基于人工神经网络对刀具磨损状态监测的技术研究", 《中国优秀博硕士学位论文全文数据库》 * |
| 郗长青: "基于钻削力信号的钻头磨损状态监测技术的研究", 《中国优秀博硕士学位论文全文数据库》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107378779A (en) * | 2017-06-29 | 2017-11-24 | 西安交通大学 | A kind of grinding trembling detection method based on axis feeding motor current signal |
| CN107627152A (en) * | 2017-10-19 | 2018-01-26 | 电子科技大学 | Numerical control machining chip control method based on BP neural network |
| CN107627152B (en) * | 2017-10-19 | 2019-04-30 | 电子科技大学 | Numerical control machining chip control method based on BP neural network |
| CN108897281A (en) * | 2018-06-06 | 2018-11-27 | 苏州领裕电子科技有限公司 | A kind of tool monitoring system and method |
| CN109719565B (en) * | 2018-12-30 | 2021-07-09 | 山东金增精密机械有限公司 | Movable bench drill with detection function |
| CN109719565A (en) * | 2018-12-30 | 2019-05-07 | 扬州市方圆机电制造有限公司 | Bench drill that is a kind of removable and having detection function |
| CN109719564A (en) * | 2018-12-30 | 2019-05-07 | 扬州市方圆机电制造有限公司 | A kind of bench drill of detectable drill bit sharpness |
| CN111890124A (en) * | 2019-05-05 | 2020-11-06 | 深圳市玄羽科技有限公司 | On-line cutter monitoring system and method |
| CN110458824A (en) * | 2019-08-08 | 2019-11-15 | 中国石油集团川庆钻探工程有限公司 | Drill bit wear detection method |
| CN110458824B (en) * | 2019-08-08 | 2023-04-18 | 中国石油集团川庆钻探工程有限公司 | Drill bit wear detection method |
| CN110480045A (en) * | 2019-09-03 | 2019-11-22 | 莆田市城厢区星华电子模具有限公司 | A kind of mold through-hole aperture expansion processing method |
| CN110480045B (en) * | 2019-09-03 | 2020-11-27 | 莆田市城厢区星华电子模具有限公司 | Die through hole diameter expansion processing method |
| CN111716150A (en) * | 2020-06-30 | 2020-09-29 | 大连理工大学 | Evolution learning method for intelligently monitoring cutter state |
| CN111975450A (en) * | 2020-08-18 | 2020-11-24 | 山东理工大学 | Horizontal one-way torque adjusting device for cutting |
| CN114871850A (en) * | 2022-04-22 | 2022-08-09 | 浙江大学 | Cutter wear state evaluation method based on vibration signal and BP neural network |
| CN117884951A (en) * | 2024-03-14 | 2024-04-16 | 常州苏美精密切削技术有限公司 | Size detection tool for metal cutting tool |
| CN117884951B (en) * | 2024-03-14 | 2024-05-28 | 常州苏美精密切削技术有限公司 | Size detection tool for metal cutting tool |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105563234A (en) | Twist drill abrasion monitoring method | |
| CN107584334B (en) | A kind of complex structural member numerical control machining cutter status real time monitor method based on deep learning | |
| CN102091972B (en) | Numerical control machine tool wear monitoring method | |
| CN111716150B (en) | Evolution learning method for intelligently monitoring cutter state | |
| CN104723171B (en) | Cutter wear monitoring method based on current and acoustic emission compound signals | |
| CN109158953B (en) | A kind of cutting-tool wear state on-line monitoring method and system | |
| CN105108584A (en) | Turning chatter detection method | |
| CN105312965B (en) | Breakage monitoring method for milling tool | |
| CN111085898A (en) | Working condition self-adaptive high-speed milling process cutter monitoring method and system | |
| CN110263474A (en) | A kind of cutter life real-time predicting method of numerically-controlled machine tool | |
| EP1927830A3 (en) | Device for overall machine tool monitoring | |
| CN108747590A (en) | A kind of tool wear measurement method based on rumble spectrum and neural network | |
| CN113378725A (en) | Cutter fault diagnosis method, equipment and storage medium based on multi-scale-channel attention network | |
| CN113752089B (en) | Cutter state monitoring method based on singular Lev index | |
| CN109262368A (en) | A kind of tool failure determination method | |
| CN110561192A (en) | Deep hole boring cutter state monitoring method based on stacking self-encoder | |
| CN105700477A (en) | Machining chatter intelligent suppression method based on chatter frequency | |
| CN111136509A (en) | Cutter state monitoring method based on ELM-SDAE algorithm | |
| CN107505850A (en) | A kind of cutter tool changing determination methods | |
| CN111958321B (en) | Numerical control machine tool cutter wear degree identification method based on deep neural network | |
| CN204525045U (en) | A kind of Tool Wear Monitoring system based on electric current and sound emission composite signal | |
| CN111390648A (en) | Turning tool abrasion judging method based on antagonistic neural network | |
| CN108956783B (en) | HDP-HSMM-based grinding sound grinding wheel passivation state detection method | |
| CN113043073A (en) | Cutter abrasion and service life prediction method and device | |
| CN113369994A (en) | Cutter state monitoring method in high-speed milling process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160511 |