CN109605128A - A kind of milling parameter online test method based on Power Spectral Entropy difference - Google Patents
A kind of milling parameter online test method based on Power Spectral Entropy difference Download PDFInfo
- Publication number
- CN109605128A CN109605128A CN201910019498.9A CN201910019498A CN109605128A CN 109605128 A CN109605128 A CN 109605128A CN 201910019498 A CN201910019498 A CN 201910019498A CN 109605128 A CN109605128 A CN 109605128A
- Authority
- CN
- China
- Prior art keywords
- signal
- power spectral
- spectral entropy
- flutter
- test method
- 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.)
- Granted
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
- B23Q17/12—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring vibration
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of milling parameter online test methods based on Power Spectral Entropy difference, and the vibration information of milling process is obtained by acceleration transducer;Using variation mode decomposition by signal decomposition at one group of Intrinsic mode functions, the signal of frequency range where taking the Intrinsic mode functions reconstruction signal of high frequency section to obtain flutter ingredient;Adaptive-filtering is carried out to reconstruction signal, calculates the Power Spectral Entropy of signal filtering front and back, carries out difference is asked to obtain that Power Spectral Entropy is poor to resulting Power Spectral Entropy, the influence filtered to flutter frequency band signals spectrum distribution is reflected with this.Compared to traditional flutter detection method, this method can efficiently separate out flutter frequency band signals, influence of the threshold value reflection filtering to different conditions signal has clear physical significance, the randomness that can be selected to avoid threshold value, the accuracy and reliability of milling parameter detection is improved, False Rate and misdetection rate are reduced.
Description
Technical field
The invention belongs to be machined the detection technique field of state, and in particular to a kind of milling based on Power Spectral Entropy difference
Flutter online test method.
Background technique
Milling Process is the most common machine-tooled method, has the advantages such as efficient, high-precision, low cost, is widely used
In manufacture fields such as Aeronautics and Astronautics, mold, automobiles.Flutter is the strong self-excited vibration of one of metal cutting process, meeting
Workpiece surface quality and size reduction are caused, the qualification rate of processing is reduced, and will cause the premature fatigue failure of machine part,
Aggravate tool wear.It selects too conservative machined parameters can be to avoid the outburst of flutter, but reduces processing efficiency.Although parsing
Method can analyze to obtain the stability lobes diagram of milling, select suitable machined parameters accordingly, however due to model error and
The time-varying characteristics of milling process, therefore still have the needs of on-line checking milling parameter.
Domestic and foreign scholars expand many researchs to milling parameter detection, such as utilize the auto-correlation system of vibration acceleration signal
The intensity of periodic component in number gauge signal, to judge chatter state;Using based on the adaptive of minimum mean square error criterion
Filter separates flutter ingredient from collected acceleration signal, and measures flutter ingredient in original signal with variance ratio
Power, realize early stage flutter detection;Filter out sensitivity IMFs therein, calculating is returned after vibration signal being decomposed using EEMD
One, which changes energy ratio, the coefficient of variation and centre frequency, realizes flutter detection;WAVELET PACKET DECOMPOSITION is carried out to collected signal and is rebuild
Flutter band signal out, extracts the energy ratio and singular spectrum entropy coefficient of the frequency band signals, and training artificial nerve network model is used for
The identification of flutter;Initial data feature is extracted by training stack self-encoding encoder, and is used for the feature extracted to train support
Vector machine realizes flutter detection.
Existing literature discovery is retrieved, the method for flutter detection can be divided into mode identification method and threshold method two major classes.Mould
Formula recognition methods needs a large amount of tape label data and is trained;And in threshold method, threshold value does not have specific physical significance,
It, which sets, needs a large amount of experience and has blindness.During milling is from steady development to flutter, signal is by the narrow of low-frequency range
Band distribution develops into broadband distribution, eventually forms the narrowband distribution of high band, causes commonly to select normalized energy than maximum
Intrinsic mode functions can not accurately filter out flutter ingredient in flutter early stage as sensitive Intrinsic mode functions.
Summary of the invention
The object of the present invention is to provide a kind of milling parameter detection methods based on Power Spectral Entropy difference, and providing one has in fact
The threshold value of border meaning, the blindness for avoiding threshold value from setting.
To achieve the goals above, the technical solution adopted by the present invention is that, a kind of milling parameter based on Power Spectral Entropy difference
Online test method comprising the steps of:
Step 1, the acceleration signal X=[x in milling process is acquired1,x2,…,xn], n indicates signal length;
Step 2, acceleration signal X collected to step 1 carries out variation mode decomposition and rebuilds flutter frequency band signals, obtains
To reconstruction signal Xrec;
Step 3, to step 2 gained reconstruction signal XrecAdaptive-filtering is carried out, reconstruction signal X is obtainedrec_filtered;
Step 4, step 2 gained signal X is calculated separatelyrecWith step 3 gained signal Xrec_filteredPower Spectral Entropy, from
M frame data start, the Power Spectral Entropy difference for differentiating flutter of present frame be include present frame preceding m frame original power spectrum entropy it is poor
Mean value, obtain Power Spectral Entropy poor index;
Step 5, chatter state is determined according to step 4 gained Power Spectral Entropy poor index.
Acceleration signal is acquired using three-dimensional acceleration signal sensor.
Three-dimensional acceleration signal sensor is mounted on the end of main shaft.
Three-dimensional acceleration signal sensor connects data collecting card, and data collecting card connects computer, three-dimensional acceleration signal
The acceleration signal monitored is transmitted to data collecting card by sensor, and data collecting card sends data to computer.
In step 2, one group of Intrinsic mode functions being distributed from low to high is obtained by variation mode decomposition, is denoted as U
=u1,u2,…,uk, wherein k is the quantity for decomposing mode;And it is rebuild using the Intrinsic mode functions of the wherein high frequency of latter half
Flutter frequency band signalsWherein [] indicates to be rounded.
In step 3, the adaptive-filtering under the flutter frequency band signals progress minimum mean square error criterion of reconstruction is filtered out and is turned
Frequency and its harmonic components, obtain filtered reconstruction signal Xrec_filtered。
In step 4, precalculated power spectrum, then the probability density function of power spectrum is calculated, then calculate the power of signal
Compose entropy.
In step 4, the calculation method of Power Spectral Entropy is as follows:
Remember that Y={ y (k), k=1,2 ..., n } is the time series that a length is n, i.e. a frame XrecAnd Xrec_filtered;
Its Fourier transformation sequenceWherein Table
Show imaginary unit;
The power spectrum s (j) of signal is calculated, j indicates j-th of value in Fourier transformation sequence:
[] indicates to be rounded, and calculates the probability density function of power spectrum:
[] indicates to be rounded, and finally calculates the Power Spectral Entropy of signal:
Step 4 gained Power Spectral Entropy is poor are as follows:
Wherein, m takes 5~11.
A, when Power Spectral Entropy difference is less than 0, flutter frequency band signals are noise and faint turn frequency and harmonic components, filter out and turn frequency
And harmonic components make the spectrum distribution of signal become uniform, the Power Spectral Entropy of signal becomes larger after the filtering, is in steady milling shape
State;
B, when Power Spectral Entropy difference is greater than 0, the signal component of flutter section is noise, turns frequency and harmonic components and flutter ingredient,
It filters out flutter ingredient while turning frequency and harmonic components to be amplified, the spectrum distribution of signal, which becomes, to be concentrated, and the Power Spectral Entropy of signal exists
Become smaller after filtering, is then in flutter milling state.
Compared with prior art, it is mixed at least to have the advantages that mode is effectively relieved in variation mode decomposition by the present invention
Folded phenomenon, the signal of frequency range where accurate reconstruction goes out flutter remove the biggish low-frequency range stable elements of amplitude, improve flutter inspection
The sensibility of survey, Power Spectral Entropy poor index measure influence of the filtering to flutter frequency band signals, and 0 is used as threshold value to have specific physics
Meaning.
Compared to traditional flutter detection method, the method for the present invention is unrelated with flutter by the signal of main reflection flutter information
Signal separator open, Testing index threshold value have clear physical significance, avoid threshold value set blindness, effectively improve flutter inspection
The sensibility and accuracy of survey.
Detailed description of the invention
The system schematic of Fig. 1 the method for the present invention.
Fig. 2 adaptive-filtering schematic diagram.
Specific embodiment
Below in conjunction with the drawings and the specific embodiments, the present invention is described in further detail.
The present invention is based on the milling parameter online test methods of Power Spectral Entropy difference to include the following steps:
(1) signal acquisition:
As shown in Figure 1, milling cutter 3 is by the clamping of knife handle 2 installation and main shaft 1, three-dimensional acceleration signal sensor 5 is mounted on master
The parameter at 1 end of axis, three-dimensional acceleration signal sensor 5 is as shown in table 1, and three-dimensional acceleration signal sensor 5 cooperates data acquisition
Card 6, the parameter of data collecting card 6 is as shown in table 2, to acceleration signal sensor 5 and data collecting card 6 for acquiring milling
Acceleration signal in journey, collected acceleration signal X=[x1,x2,…,xn] indicate, n indicates signal length, collects
Signal be transmitted in computer 4 by data line, realize the on-line checking of milling parameter.
1 acceleration transducer parameter of table
2 data collecting card parameter of table
(2) variation mode decomposition is carried out to signal X and rebuilds flutter frequency band signals:
Variation mode decomposition is carried out to collected original acceleration signal, obtains one group of base being distributed from low to high
This mode component (IMFs), is denoted as U=u1,u2,…,uk, wherein k is the quantity for decomposing mode, usually takes 10~16;And it utilizes
Wherein the Intrinsic mode functions of the high frequency of latter half rebuild flutter frequency band signalsWherein [] table
Show rounding.
(3) to reconstruction signal XrecCarry out adaptive-filtering:
Adaptive-filtering under the flutter frequency band signals progress minimum mean square error criterion of reconstruction is filtered out and turns frequently and its humorous
Wave component obtains filtered reconstruction signal Xrec_filtered。
Fig. 2 is the schematic diagram of sef-adapting filter used in the present invention,It is made of m group sinusoidal and cosine signal, often
One group of cosine and sine signal constitutes the signal component for needing to filter out.M is harmonic order, is usually taken to be sample frequency divided by a turn frequency
Smallest positive integral (i.e.fsFor the sample frequency of signal, sp is the speed of mainshaft, and unit is to turn/min), wherein the i-th order harmonics
Corresponding input signal is xi=[xci xsi]=[cos (i × w × nT) sin (i × w × nT)], w is to turn frequency angular speed, and T is to adopt
Sample period, n indicate that current time is n-th point in a frame signal;For in a frame signal at n-th of pointPower
Weight, initial value To input the inner product with weight, the ingredient for needing to filter out is indicated
Mixed signal amplitude.Xrec_filtered(n)=Xrec(n)-y (n) is filtered signal amplitude.(n+1)th is updated accordingly
Weight at a point, more new formula areWherein α is filtering
The step-length of device,
(4) difference of the Power Spectral Entropy of reconstruction signal before and after filtering is calculated:
The variation range of Power Spectral Entropy is [0,1], also reflects the uniformity of time series spectrum distribution, is distributed more uniform
Power Spectral Entropy is bigger, respectively to the X of filtering front and backrecAnd Xrec_filteredPower Spectral Entropy index is calculated, it is poor that Power Spectral Entropy is poor to make
Index, which, which reflects the signal of flutter frequency range, is influenced in spectrum distribution by filtering.
The calculation method of Power Spectral Entropy is as follows:
Remember that Y={ y (k), k=1,2 ..., n } is the time series that a length is n, in the method an as frame Xrec
And Xrec_filtered;Its Fourier transformation sequenceWherein Indicate imaginary unit.
The power spectrum s (j) of signal is calculated, j indicates j-th of value in Fourier transformation sequence:
[] indicates to be rounded
Calculate the probability density function of power spectrum:
[] indicates to be rounded
Finally calculate the Power Spectral Entropy of signal:
(6) judgement of chatter state:
A, in steady milling, flutter frequency band signals are noise and faint turn frequency and harmonic components, filter out and turn frequently and humorous
Wave component makes the spectrum distribution of signal become uniform, and the Power Spectral Entropy of signal becomes larger after the filtering;
B, when flutter occurs, the signal component of flutter section is noise, turns frequency and harmonic components and flutter ingredient, filters out and turns
Flutter ingredient is amplified while frequency and harmonic components, and the spectrum distribution of signal, which becomes, to be concentrated, and the Power Spectral Entropy of signal is after the filtering
Become smaller;
Since m frame data, present frame is the original of preceding m frame (containing present frame) for the Power Spectral Entropy difference that flutter differentiates
The mean value of Power Spectral Entropy difference, can effectively eliminate the influence of data fluctuations, i.e.,
In actual operation, m takes 5~11.
Claims (10)
1. a kind of milling parameter online test method based on Power Spectral Entropy difference, which is characterized in that comprise the steps of:
Step 1, the acceleration signal X=[x in milling process is acquired1,x2,…,xn], n indicates signal length;
Step 2, acceleration signal X collected to step 1 carries out variation mode decomposition and rebuilds flutter frequency band signals, obtains weight
Build signal Xrec;
Step 3, to step 2 gained reconstruction signal XrecAdaptive-filtering is carried out, reconstruction signal X is obtainedrec_filtered;
Step 4, step 2 gained signal X is calculated separatelyrecWith step 3 gained signal Xrec_filteredPower Spectral Entropy, from m frame
Data start, and the Power Spectral Entropy difference for differentiating flutter of present frame is the preceding m frame original power spectrum entropy difference for including present frame
Mean value obtains Power Spectral Entropy poor index;
Step 5, chatter state is determined according to step 4 gained Power Spectral Entropy poor index.
2. the milling parameter online test method according to claim 1 based on Power Spectral Entropy difference, which is characterized in that step
In 1, acceleration signal is acquired using three-dimensional acceleration signal sensor (5).
3. the milling parameter online test method according to claim 2 based on Power Spectral Entropy difference, which is characterized in that three-dimensional
Acceleration signal sensor (5) is mounted on the end of main shaft (1).
4. the milling parameter online test method according to claim 3 based on Power Spectral Entropy difference, which is characterized in that three-dimensional
Acceleration signal sensor (5) connects data collecting card (6), and data collecting card (6) connects computer (4), three-dimensional acceleration signal
The acceleration signal monitored is transmitted to data collecting card (6) by sensor (5), and data collecting card (6) sends data to electricity
Brain (4).
5. the milling parameter online test method according to claim 1 based on Power Spectral Entropy difference, which is characterized in that step
In 2, one group of Intrinsic mode functions being distributed from low to high is obtained by variation mode decomposition, is denoted as U=u1,u2,…,uk,
Wherein k is the quantity for decomposing mode;And flutter frequency band signals are rebuild using the Intrinsic mode functions of the wherein high frequency of latter halfWherein [] indicates to be rounded.
6. the milling parameter online test method according to claim 1 based on Power Spectral Entropy difference, which is characterized in that step
In 3, to the flutter frequency band signals of reconstruction carry out the adaptive-filtering under minimum mean square error criterion filter out turn frequency and its harmonic wave at
Point, obtain filtered reconstruction signal Xrec_filtered。
7. the milling parameter online test method according to claim 1 based on Power Spectral Entropy difference, which is characterized in that step
In 4, precalculated power spectrum, then the probability density function of power spectrum is calculated, then calculate the Power Spectral Entropy of signal.
8. the milling parameter online test method according to claim 7 based on Power Spectral Entropy difference, which is characterized in that step
In 4, the calculation method of Power Spectral Entropy is as follows:
Remember that Y={ y (k), k=1,2 ..., n } is the time series that a length is n, i.e. a frame XrecAnd Xrec_filtered;Its Fu
In leaf transformation sequenceWherein Indicate empty
Number unit;
The power spectrum s (j) of signal is calculated, j indicates j-th of value in Fourier transformation sequence:
[] indicates to be rounded, and calculates the probability density function of power spectrum:
[] indicates to be rounded, and finally calculates the Power Spectral Entropy of signal:
9. the milling parameter online test method according to claim 8 based on Power Spectral Entropy difference, which is characterized in that step
4 gained Power Spectral Entropies are poor are as follows:
Wherein, m takes 5~11.
10. the milling parameter online test method according to claim 1 based on Power Spectral Entropy difference, which is characterized in that
A, when Power Spectral Entropy difference is less than 0, flutter frequency band signals are noise and faint turn frequency and harmonic components, filter out and turn frequently and humorous
Wave component makes the spectrum distribution of signal become uniform, and the Power Spectral Entropy of signal becomes larger after the filtering, is in steady milling state;
B, when Power Spectral Entropy difference is greater than 0, the signal component of flutter section is noise, turns frequency and harmonic components and flutter ingredient, is filtered out
Flutter ingredient is amplified while turning frequency and harmonic components, and the spectrum distribution of signal, which becomes, to be concentrated, and the Power Spectral Entropy of signal is filtering
After become smaller, then be in flutter milling state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910019498.9A CN109605128B (en) | 2019-01-09 | 2019-01-09 | Milling chatter online detection method based on power spectrum entropy difference |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910019498.9A CN109605128B (en) | 2019-01-09 | 2019-01-09 | Milling chatter online detection method based on power spectrum entropy difference |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109605128A true CN109605128A (en) | 2019-04-12 |
CN109605128B CN109605128B (en) | 2020-03-31 |
Family
ID=66016710
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910019498.9A Active CN109605128B (en) | 2019-01-09 | 2019-01-09 | Milling chatter online detection method based on power spectrum entropy difference |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109605128B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112394642A (en) * | 2020-11-27 | 2021-02-23 | 华中科技大学 | Robot milling chatter identification method based on super-parameter optimization |
CN112496862A (en) * | 2020-11-30 | 2021-03-16 | 上海交通大学 | Milling flutter intelligent identification method based on theoretical model containing milling angle |
CN112974945A (en) * | 2021-03-19 | 2021-06-18 | 天津大学 | Milling chatter monitoring method based on variational modal decomposition and tracking threshold |
CN114800042A (en) * | 2022-04-28 | 2022-07-29 | 华中科技大学 | Method for identifying chatter type of robot milling based on power spectrum entropy difference |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE3621049A1 (en) * | 1985-06-28 | 1987-01-02 | Gen Electric | ARRANGEMENT, MONITORING DEVICE AND METHOD FOR DETECTING THE INITIAL TOUCH BETWEEN A CUTTING TOOL AND A WORKPIECE |
EP0714519A1 (en) * | 1993-08-19 | 1996-06-05 | Mallinckrodt Medical, Inc. | Entropy based signal transmission, reception and signal analysis method and apparatus |
CN103203670A (en) * | 2013-04-03 | 2013-07-17 | 同济大学 | Grinding chatter prediction method based on maximum information entropy and directional divergence |
CN104390697A (en) * | 2014-11-06 | 2015-03-04 | 西安交通大学 | C0 complexity and correlation coefficient-based milling chatter detection method |
US20150304107A1 (en) * | 2014-04-17 | 2015-10-22 | International Business Machines Corporation | Extracting Entropy from Machine Vibration |
CN105108584A (en) * | 2015-07-21 | 2015-12-02 | 上海交通大学 | Turning chatter detection method |
CN106141815A (en) * | 2016-07-15 | 2016-11-23 | 西安交通大学 | A kind of high-speed milling tremor on-line identification method based on AR model |
CN107330375A (en) * | 2017-06-05 | 2017-11-07 | 天津大学 | Lathe flutter on-line monitoring method based on empirical mode decomposition and Sample Entropy feature |
-
2019
- 2019-01-09 CN CN201910019498.9A patent/CN109605128B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE3621049A1 (en) * | 1985-06-28 | 1987-01-02 | Gen Electric | ARRANGEMENT, MONITORING DEVICE AND METHOD FOR DETECTING THE INITIAL TOUCH BETWEEN A CUTTING TOOL AND A WORKPIECE |
EP0714519A1 (en) * | 1993-08-19 | 1996-06-05 | Mallinckrodt Medical, Inc. | Entropy based signal transmission, reception and signal analysis method and apparatus |
CN103203670A (en) * | 2013-04-03 | 2013-07-17 | 同济大学 | Grinding chatter prediction method based on maximum information entropy and directional divergence |
US20150304107A1 (en) * | 2014-04-17 | 2015-10-22 | International Business Machines Corporation | Extracting Entropy from Machine Vibration |
CN104390697A (en) * | 2014-11-06 | 2015-03-04 | 西安交通大学 | C0 complexity and correlation coefficient-based milling chatter detection method |
CN105108584A (en) * | 2015-07-21 | 2015-12-02 | 上海交通大学 | Turning chatter detection method |
CN106141815A (en) * | 2016-07-15 | 2016-11-23 | 西安交通大学 | A kind of high-speed milling tremor on-line identification method based on AR model |
CN107330375A (en) * | 2017-06-05 | 2017-11-07 | 天津大学 | Lathe flutter on-line monitoring method based on empirical mode decomposition and Sample Entropy feature |
Non-Patent Citations (1)
Title |
---|
蒋永翔: "《复杂制造系统加工稳定性在线监测及寻优控制关键技术研究》", 31 January 2010 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112394642A (en) * | 2020-11-27 | 2021-02-23 | 华中科技大学 | Robot milling chatter identification method based on super-parameter optimization |
CN112496862A (en) * | 2020-11-30 | 2021-03-16 | 上海交通大学 | Milling flutter intelligent identification method based on theoretical model containing milling angle |
CN112496862B (en) * | 2020-11-30 | 2021-10-29 | 上海交通大学 | Milling flutter intelligent identification method based on theoretical model containing milling angle |
CN112974945A (en) * | 2021-03-19 | 2021-06-18 | 天津大学 | Milling chatter monitoring method based on variational modal decomposition and tracking threshold |
CN114800042A (en) * | 2022-04-28 | 2022-07-29 | 华中科技大学 | Method for identifying chatter type of robot milling based on power spectrum entropy difference |
Also Published As
Publication number | Publication date |
---|---|
CN109605128B (en) | 2020-03-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109605128A (en) | A kind of milling parameter online test method based on Power Spectral Entropy difference | |
Elbestawi et al. | In-process monitoring of tool wear in milling using cutting force signature | |
CN112304613B (en) | Wind turbine generator bearing early warning method based on feature fusion | |
CN102091972B (en) | Numerical control machine tool wear monitoring method | |
CN106141815B (en) | A kind of high-speed milling flutter on-line identification method based on AR models | |
CN109514349A (en) | Monitoring Tool Wear States in Turning based on vibration signal and Stacking integrated model | |
CN108507787A (en) | Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion and method | |
CN110263474A (en) | A kind of cutter life real-time predicting method of numerically-controlled machine tool | |
CN110000610A (en) | A kind of Tool Wear Monitoring method based on multi-sensor information fusion and depth confidence network | |
CN104794492B (en) | Machine tool processing running status ONLINE RECOGNITION method based on power features model | |
CN110333077B (en) | Rolling bearing fault diagnosis method based on approximate support vector | |
CN114619292B (en) | Milling cutter wear monitoring method based on fusion of wavelet denoising and attention mechanism with GRU network | |
CN108873813A (en) | Tool wear degree detection method based on main shaft of numerical control machine tool servo motor current signal | |
CN112781820B (en) | Hob performance degradation trend evaluation method | |
CN114346761B (en) | Cutter abrasion condition detection method based on improved condition generation countermeasure network | |
CN104390697A (en) | C0 complexity and correlation coefficient-based milling chatter detection method | |
CN112692646A (en) | Intelligent assessment method and device for tool wear state | |
CN208254802U (en) | Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion | |
CN110346130A (en) | A kind of boring flutter detection method based on empirical mode decomposition and time-frequency multiple features | |
Li et al. | Online chatter detection in milling process based on VMD and multiscale entropy | |
CN112207631B (en) | Method for generating tool detection model, method, system, device and medium for detecting tool detection model | |
CN116861313B (en) | Kalman filtering working condition identification method and system based on vibration energy trend | |
CN114580666A (en) | Multi-mode fusion motor intelligent maintenance system | |
CN106203253B (en) | A kind of grinding machine vibration based on multi-source information and vibration acoustic feature extraction method | |
CN114714157B (en) | Grinding chatter monitoring method based on time-varying filtering empirical mode decomposition and instantaneous energy ratio |
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 |