CN109015111A - A kind of cutting tool state on-line monitoring method based on information fusion and support vector machines - Google Patents
A kind of cutting tool state on-line monitoring method based on information fusion and support vector machines Download PDFInfo
- Publication number
- CN109015111A CN109015111A CN201810733638.4A CN201810733638A CN109015111A CN 109015111 A CN109015111 A CN 109015111A CN 201810733638 A CN201810733638 A CN 201810733638A CN 109015111 A CN109015111 A CN 109015111A
- Authority
- CN
- China
- Prior art keywords
- support vector
- vector machines
- cutting tool
- frequency
- line monitoring
- 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
- 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
-
- 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 belongs to cutting tool for CNC machine status monitoring correlative technology fields, it discloses it is a kind of based on information fusion and support vector machines cutting tool state on-line monitoring method, method includes the following steps: S1, the multiple sensors signal of cutting tool for CNC machine is acquired, then extracts characteristic parameter of the sensor signal on time domain, frequency domain and time-frequency domain respectively；The measured value of characteristic parameter and tool wear after normalized is done Pearson came correlation analysis respectively to screen to characteristic parameter by S2, and is the health index for indicating tool wear information by the Feature Parameter Fusion screened；S3, support vector machines identification model is trained based on obtained health index, and handle the signal acquired in real time to obtain health index, and then this health index is input in the trained support vector machines identification model, to realize the on-line monitoring of cutting-tool wear state.The present invention improves accuracy and stability, and flexibility is preferable.
Description
Technical field
The invention belongs to cutting tool for CNC machine status monitoring correlative technology fields, are based on information more particularly, to one kind
The cutting tool state on-line monitoring method of fusion and support vector machines.
Background technique
Under industrial overall background, people, machine, the connection of information three classes element are even closer, the intelligence manufacture of this three composition
Equipment and intelligent manufacturing system also play increasingly important role in production application, and intelligent manufacturing equipment is to measure one
The outstanding feature of National Industrial level.According to statistics, having 70% or more in machining is machining, and cutter is machining
In valuable source, while also influence production and processing quality and efficiency.It can be greatly reduced and be set using cutter effective and reasonablely
The standby downtime, reduce production cost.Some researches show that, enterprise be added in CNC machine tool condition monitoring system it
Afterwards, the downtime that 5% can be reduced, 30% production cost is saved.If can sensor be passed through in process
The failure of cutting tool state, intelligent diagnostics cutter is monitored and identified to collected machining information on-line, makes corresponding decision, realizes 7
It processes within × 24 hours, intelligence manufacture level is promoted to new height.
When monitoring cutting tool state, the behaviour in service of cutter can be monitored using multiple sensors according to workplace, it is existing
Some methods are usually certain characteristic parameter using certain sensor signal to indicate the state of wear of cutter, monitoring it is accurate
Property be limited to the precision of a certain sensor, monitoring stability is poor, cannot effectively realize the monitoring of cutting tool state.Correspondingly,
There is the technical needs for developing a kind of preferable cutting tool state on-line monitoring method of stability for this field.
Summary of the invention
Aiming at the above defects or improvement requirements of the prior art, the present invention provides one kind based on information merge and support to
The cutting tool state on-line monitoring method of amount machine is based on existing tool condition monitoring feature, studies and devise one kind and be based on
The cutting tool state on-line monitoring method of information fusion and support vector machines.The monitoring method has merged multiple sensors signal
Effective information, and go out using the support vector machines online recognition of particle group optimizing the state of wear of cutter, it realizes to cutter shape
State stablizes on-line monitoring, and improves monitoring accuracy and flexibility, and monitoring is no longer limited by some sensor signal.
To achieve the above object, the present invention provides a kind of cutting tool state based on information fusion and support vector machines is online
Monitoring method, the monitoring method the following steps are included:
S1, acquires the multiple sensors signal of cutting tool for CNC machine, then extract respectively each sensor signal when
Characteristic parameter on domain, frequency domain and time-frequency domain, and normalized is done to the characteristic parameter extracted；
S2, respectively by the measured value of characteristic parameter and tool wear after normalized do Pearson came correlation analysis with
Characteristic parameter is screened, and uses Self-organizing Maps method by the Feature Parameter Fusion screened for expression tool wear
The health index of information；
S3 is trained support vector machines identification model based on the health index that step S2 is obtained, and will adopt in real time
The signal of collection is handled to obtain health index, and then this health index is input to the trained support vector machines and is known
In other model, to realize the on-line monitoring of cutting-tool wear state.
Further, the sensor signal includes vibration signal, current signal, acoustic emission signal and Cutting Force Signal.
It further, further include being pre-processed to the sensor signal in step S1, to remove null value and singular value
The step of.
Further, the sensor signal of extraction the characteristic parameter of time domain include mean value, mean square deviation, root amplitude,
Root, maximum value, degree of skewness, root mean square frequency, frequency variance and frequency standard are poor.
Further, sensor signal is extracted in the characteristic parameter of time domain using the complete empirical modal of adaptive noise
Decomposition method.
Further, the sensor signal of extraction includes gravity frequency, square frequency, root mean square in the characteristic parameter of time domain
Frequency, frequency variance and frequency standard are poor.
Further, when extracting characteristic parameter on frequency domain, by vibration signal by discrete Fourier transform to obtain function
Rate spectrum；Wherein, the change of the main band position of the gravity frequency, the square frequency and the root mean square frequency representation power spectrum
Change situation, the frequency variance and the frequency standard difference indicate the dispersion degree of spectrum energy.
Further, normalized, formula (17) are done to the characteristic parameter extracted using formula (17) are as follows:
In formula, x is input value；Y is normalized output value；MinValue is minimum value；MaxValue is maximum value.
Further, when screening to characteristic parameter, the Pearson correlation coefficient that Pearson came correlation analysis is obtained is big
Characteristic parameter in 0.8 remains, to represent effective wear information of cutter.
Further, when being trained to support vector machines identification model, using particle swarm optimization algorithm to supporting vector
Penalty factor and radial function radius sigma in machine identification model optimize, so that classifying quality is optimal.
In general, through the invention it is contemplated above technical scheme is compared with the prior art, base provided by the invention
It is mainly had the advantages that in the cutting tool state on-line monitoring method of information fusion and support vector machines
1. acquire cutting tool for CNC machine multiple sensors signal, then extract respectively each sensor signal when
Characteristic parameter on domain, frequency domain and time-frequency domain, and normalized is done to the characteristic parameter extracted, believed based on multiple sensors
It number realizes the monitoring of Cutter wear state, improves flexibility and monitoring accuracy.
2. using health of the Self-organizing Maps method by the Feature Parameter Fusion screened to indicate tool wear information
Index so can effectively improve the stability of monitoring.
3. being trained based on obtained health index to support vector machines identification model, and then live signal is corresponding
Health index be input in the trained support vector machines identification model, to realize the real-time online of cutting-tool wear state
Monitoring improves monitoring accuracy and timeliness, provides data support for the effective and reasonable application of cutter.
4. a pair support vector machines identification model is trained, mould is identified to support vector machines using particle swarm optimization algorithm
Penalty factor and radial function radius sigma in type optimize, so that classifying quality is optimal, and then improve state recognition
Accuracy.
5. a pair characteristic parameter screens, the Pearson correlation coefficient that Pearson came correlation analysis is obtained is greater than 0.8
Characteristic parameter remains, and to represent effective wear information of cutter, improves the efficiency of cutting tool state identification, it is ensured that cutter
The accuracy rate of state recognition.
Detailed description of the invention
Fig. 1 is the process of the cutting tool state on-line monitoring method provided by the invention based on information fusion and support vector machines
Schematic diagram.
Fig. 2 is the flow diagram of the cutting tool state on-line monitoring method based on information fusion and support vector machines in Fig. 1.
Fig. 3 is the time domain that the cutting tool state on-line monitoring method based on information fusion and support vector machines in Fig. 1 is related to
The flow diagram of feature extraction.
Fig. 4 is the feature that the cutting tool state on-line monitoring method based on information fusion and support vector machines in Fig. 1 is related to
The comparison diagram of fused health index MOE and tool wear VB.
(a), (b), (c) in Fig. 5 and (d) figure be respectively using in Fig. 1 based on information fusion and support vector machines
The result figure of training group and test group under two different operating conditions that cutting tool state on-line monitoring method obtains.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.As long as in addition, technical characteristic involved in the various embodiments of the present invention described below
Not constituting a conflict with each other can be combined with each other.
Please refer to Fig. 1 and Fig. 2, the cutting tool state on-line monitoring provided by the invention based on information fusion and support vector machines
Method mainly comprises the steps that
S1, acquires the multiple sensors signal of cutting tool for CNC machine, then extract respectively each sensor signal when
Characteristic parameter on domain, frequency domain and time-frequency domain, and normalized is done to the characteristic parameter extracted.
Specifically, a variety of monitors sensor signals of cutting tool for CNC machine are acquired, and the sensor signal are carried out pre-
Processing, the pretreatment is including going null value and going singular value.In present embodiment, the sensor signal of acquisition includes vibration letter
Number, current signal, acoustic emission signal and Cutting Force Signal.Wherein, go singular value according to Pauta criterion, using formula (1) into
Row:
In formula, xiFor sensor signal data；μ is the average value of signal data；σ is the standard deviation of signal data.
Referring to Fig. 3, then, feature ginseng is extracted on time domain, frequency domain and time-frequency domain respectively to each sensor signal
Number, and all characteristic parameters after extraction are done into normalized.In present embodiment, include in the characteristic parameter that time domain is extracted
Mean value, mean square deviation, root amplitude, root mean square, maximum value, degree of skewness, root mean square frequency, frequency variance and frequency standard are poor；?
Using the complete empirical mode decomposition method (CEEMDAN) based on adaptive noise when time domain extracts characteristic parameter, extraction when
Characteristic of field is the energy value of mode function.
Wherein, (1) mean value MV (mean value):
(2) mean square deviation MSE (mean square error):
(3) root amplitude SMR (square mean root):
(4) root mean square RMS (root mean square):
(5) maximum value MA (maximum absolute value):
MA=max | x (n) | (6)
(6) degree of skewness SF (skewness factor):
(7) kurtosis KF (kurtosis factor):
(8) peak factor CF (crest factor):
(9) nargin factor M F (margin factor):
In formula, x (n) is signal data；N is data count.
When extracting feature on frequency domain, vibration signal is obtained into power spectrum by discrete Fourier transform, extracts following five
A characteristic parameter is as frequency domain character.
(1) gravity frequency FC, gravity frequency FC are calculated using formula (11):
(2) square frequency MSF, the side frequency MSF are calculated using formula (12):
(3) root mean square frequency RMSF, the root mean square frequency RMSF are calculated using formula (13):
(4) frequency variance VF, the frequency variance VF are calculated using formula (14):
(5) frequency standard difference RVF, the frequency standard difference RVF are calculated using formula (15):
Wherein, S (f) is the power spectrum of vibration signal, and wherein gravity frequency, square frequency and root mean square frequency can describe
The situation of change of the main band position of power spectrum, and frequency variance, frequency standard difference can describe the dispersion degree of spectrum energy.
When temporal signatures extract, operator E is definedj() indicates to decompose j-th of the modal components obtained, W by EMDiIt is full
The white noise of sufficient N (0,1)；It extracts IMF function and acquires energy value, as time and frequency domain characteristics, calculation formula are as follows:
Wherein, IMFkK-th of the mode function component extracted for CEEMDAN.
It in present embodiment, is normalized using linear function method for transformation, is carried out using formula (17), it is public
Formula (17) are as follows:
In formula, x is input value；Y is normalized output value；MinValue is minimum value；MaxValue is maximum value.
S2, respectively by the measured value of characteristic parameter and tool wear after normalized do Pearson came correlation analysis with
Characteristic parameter is screened, and uses the Self-organizing Maps method of growth by the Feature Parameter Fusion screened for expression knife
Has the health index of wear information.
Specifically, the characteristic parameter of extraction and tool wear VB are done into Pearson came correlation analysis to obtain Pearson came phase relation
Number, Pearson correlation coefficient, the formula (18) are calculated using formula (18) are as follows:
In formula, X is characterized parameter；Vb is the measured value of tool wear；Cov is covariance calculating.
After obtaining Pearson correlation coefficient, the characteristic parameter by Pearson correlation coefficient greater than 0.8 is remained, to represent
Effective wear information of cutter.
Then, the characteristic parameter remained is carried out by information fusion using GSOM method, GSOM method can be according to defeated
The neuronal structure of the characteristic parameter adaptive entered mapped.Using cutter, the monitoring data in new knife are trained for selection
To a GSOM model, then neurons all in the data monitored on-line and GSOM are compared to obtain deviation, partially
Difference MQE is used to indicate the health index of cutter, its calculation formula is:
MQE=| | X- ωBMU|| (19)
In formula, X is the characteristic parameter collection that on-line monitoring obtains；ωBMUFor the weight with X apart from nearest neural unit to
Amount.
The result that the health index MQE and practical tool wear measured value VB obtained using GSOM method is compared is shown in figure
4, it can be seen that health index can preferably reflect the situation of change of cutter actual wear.
S3 is trained support vector machines identification model based on the health index that step S2 is obtained, and will adopt in real time
The signal of collection is handled to obtain health index, and then this health index is input to the trained support vector machines and is known
In other model, to realize the on-line monitoring of cutting-tool wear state.
Specifically, the health index being calculated is identified with support vector machines identification model, while by cutter
State of wear is divided into new knife-like state, state of wear, three kinds of blunt state according to the degree of wear, and by health index correspond to this three
In kind state grade, using particle swarm optimization algorithm to the penalty factor and radial direction in support vector machines identification model when training
Function radius sigma optimizes, so that the classifying quality of SVM is optimal.Wherein, choosing population population is 30, maximum number of iterations
It is 200, Inertia Weight wkFitness function is defined as the accuracy rate of svm classifier by=1, Studying factors c1=c2=2, training
Monitoring model online is obtained after the completion, i.e., trained support vector machines identification model.
When monitoring cutting-tool wear state on-line, the signal acquired in real time is referred to by same processing mode to obtain health
Number, and this obtained health index is input in trained support vector machines identification model, to realize cutting-tool wear state
Online recognition monitoring.
Referring to Fig. 5, being monitored on-line using the cutting tool state provided by the invention based on information fusion and support vector machines
Method has carried out training to the state of wear of each two groups of cutters under two kinds of operating conditions respectively and has monitored on-line, (a) figure and (b) chart
Show two groups of monitoring data under same operating, wherein (a) figure corresponds to training group, (b) figure corresponds to test group；(c) figure and (d) chart
Show the data under another operating condition, (c) figure corresponds to training group, and (d) figure corresponds to test group；From in figure it can be seen that the present invention mentions
The recognition accuracy of the on-line monitoring method of confession is higher, can achieve 100%, and can effectively supervise online under different operating conditions
Cutting tool state is surveyed, accuracy and stability are embodied.
In addition, the method for using two kinds of different acquisition information to merge is compared to be melted to provided by the invention based on information
It closes and the cutting tool state on-line monitoring method of support vector machines is verified.Wherein, both methods only joins some feature
Number is identified that comparing result is as shown in table 1, it can be seen that the accuracy rate that method provided by the invention obtains each group of data
All higher, the stability for being indicated above this method is more preferable, is better than other two methods.
1 accuracy rate comparing result of table
Cutting tool state on-line monitoring method provided by the invention based on information fusion and support vector machines, the cutter shape
State on-line monitoring method combine information fusion and support vector machines identification model, while to multiple sensors signal at
Reason, and then is trained support vector machines based on processing result, and when real-time monitoring, the signal of real-time monitoring is handled
To obtain health index, health index is thus input to support vector machines identification model to realize the real-time online of cutting tool state
Monitoring, state recognition accuracy rate can achieve 100%, and have preferable stability.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, not to
The limitation present invention, any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should all include
Within protection scope of the present invention.
Claims (10)
1. a kind of cutting tool state on-line monitoring method based on information fusion and support vector machines, it is characterised in that:
S1, acquires the multiple sensors signal of cutting tool for CNC machine, then extracts each sensor signal respectively in time domain, frequency
Characteristic parameter on domain and time-frequency domain, and normalized is done to the characteristic parameter extracted；
The measured value of characteristic parameter and tool wear after normalized is done Pearson came correlation analysis to spy respectively by S2
Sign parameter is screened, and uses Self-organizing Maps method by the Feature Parameter Fusion screened for expression tool wear information
Health index；
S3 is trained support vector machines identification model based on the health index that step S2 is obtained, and will acquire in real time
Signal is handled to obtain health index, and then this health index is input to the trained support vector machines and identifies mould
In type, to realize the on-line monitoring of cutting-tool wear state.
2. the cutting tool state on-line monitoring method based on information fusion and support vector machines as described in claim 1, feature
Be: the sensor signal includes vibration signal, current signal, acoustic emission signal and Cutting Force Signal.
3. the cutting tool state on-line monitoring method based on information fusion and support vector machines as described in claim 1, feature
It is: further includes being pre-processed to the sensor signal in step S1, the step of removes null value and singular value.
4. the cutting tool state on-line monitoring method based on information fusion and support vector machines as described in claim 1, feature
Be: the sensor signal of extraction the characteristic parameter of time domain include mean value, mean square deviation, root amplitude, root mean square, maximum value,
Degree of skewness, root mean square frequency, frequency variance and frequency standard are poor.
5. the cutting tool state on-line monitoring method based on information fusion and support vector machines as described in claim 1, feature
It is: extracts sensor signal in the characteristic parameter of time domain using the complete empirical mode decomposition method of adaptive noise.
6. the cutting tool state on-line monitoring side as described in any one in claim 1-5 based on information fusion and support vector machines
Method, it is characterised in that: the sensor signal of extraction includes gravity frequency, square frequency, root mean square frequency in the characteristic parameter of time domain
Rate, frequency variance and frequency standard are poor.
7. the cutting tool state on-line monitoring method based on information fusion and support vector machines as claimed in claim 6, feature
It is: when extracting characteristic parameter on frequency domain, by vibration signal by discrete Fourier transform to obtain power spectrum；Wherein, institute
The situation of change of the main band position of gravity frequency, the square frequency and the root mean square frequency representation power spectrum is stated, it is described
Frequency variance and the frequency standard difference indicate the dispersion degree of spectrum energy.
8. the cutting tool state on-line monitoring side as described in any one in claim 1-5 based on information fusion and support vector machines
Method, it is characterised in that: normalized, formula (17) are done to the characteristic parameter extracted using formula (17) are as follows:
In formula, x is input value；Y is normalized output value；MinValue is minimum value；MaxValue is maximum value.
9. the cutting tool state on-line monitoring method based on information fusion and support vector machines as described in claim 1, feature
Be: when screening to characteristic parameter, feature of the Pearson correlation coefficient greater than 0.8 that Pearson came correlation analysis is obtained is joined
Number remains, to represent effective wear information of cutter.
10. the cutting tool state on-line monitoring side as described in any one in claim 1-5 based on information fusion and support vector machines
Method, it is characterised in that: when being trained to support vector machines identification model, support vector machines is known using particle swarm optimization algorithm
Penalty factor and radial function radius sigma in other model optimize, so that classifying quality is optimal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810733638.4A CN109015111A (en) | 2018-07-06 | 2018-07-06 | A kind of cutting tool state on-line monitoring method based on information fusion and support vector machines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810733638.4A CN109015111A (en) | 2018-07-06 | 2018-07-06 | A kind of cutting tool state on-line monitoring method based on information fusion and support vector machines |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109015111A true CN109015111A (en) | 2018-12-18 |
Family
ID=64641356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810733638.4A Pending CN109015111A (en) | 2018-07-06 | 2018-07-06 | A kind of cutting tool state on-line monitoring method based on information fusion and support vector machines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109015111A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109724785A (en) * | 2018-12-29 | 2019-05-07 | 中铁工程装备集团有限公司 | A kind of tool condition monitoring and life prediction system based on Multi-source Information Fusion |
| CN110091216A (en) * | 2019-05-13 | 2019-08-06 | 江苏师范大学 | The monitoring of milling noise and milling vibration and its correlation analysis system and method |
| CN110103077A (en) * | 2019-05-08 | 2019-08-09 | 北京理工大学 | A kind of boring state intelligent monitoring method of boring cutter bar multiple-sensor integration |
| CN110153801A (en) * | 2019-07-04 | 2019-08-23 | 西南交通大学 | A kind of cutting-tool wear state discrimination method based on multi-feature fusion |
| CN110428020A (en) * | 2019-08-13 | 2019-11-08 | 树根互联技术有限公司 | Cutter health evaluation model training method, device and electronic equipment |
| CN110515364A (en) * | 2019-07-15 | 2019-11-29 | 北京工业大学 | A kind of cutting-tool wear state detection method based on variation mode decomposition and LS-SVM |
| CN110561193A (en) * | 2019-09-18 | 2019-12-13 | 杭州友机技术有限公司 | Cutter wear assessment and monitoring method and system based on feature fusion |
| CN110744359A (en) * | 2019-11-29 | 2020-02-04 | 湖南工业职业技术学院 | Numerical control lathe cutter wear monitoring system and method |
| CN111085898A (en) * | 2019-12-30 | 2020-05-01 | 南京航空航天大学 | Working condition self-adaptive high-speed milling process cutter monitoring method and system |
| CN111300146A (en) * | 2019-11-29 | 2020-06-19 | 上海交通大学 | Numerical control machine tool cutter abrasion loss online prediction method based on spindle current and vibration signal |
| CN112034789A (en) * | 2020-08-25 | 2020-12-04 | 国家机床质量监督检验中心 | Health assessment method, system and assessment terminal for key parts and complete machine of numerical control machine tool |
| CN112192319A (en) * | 2020-09-28 | 2021-01-08 | 上海交通大学 | Tool wear monitoring method and system of unsupervised model |
| CN112372371A (en) * | 2020-10-10 | 2021-02-19 | 上海交通大学 | Method for evaluating abrasion state of numerical control machine tool cutter |
| WO2021046738A1 (en) * | 2019-09-11 | 2021-03-18 | 大连理工大学 | Method for monitoring state of deep hole boring cutter on basis of stacked autoencoder |
| CN112720071A (en) * | 2021-01-27 | 2021-04-30 | 赛腾机电科技（常州）有限公司 | Cutter real-time state monitoring index construction method based on intelligent fusion of multi-energy domain signals |
| CN113043073A (en) * | 2021-03-22 | 2021-06-29 | 曲阜师范大学 | Cutter abrasion and service life prediction method and device |
| CN113601261A (en) * | 2021-08-10 | 2021-11-05 | 中国科学院合肥物质科学研究院 | Monitoring method of online rapid optimization model for cutter |
| CN114559297A (en) * | 2020-11-27 | 2022-05-31 | 财团法人工业技术研究院 | Cutter state evaluation system and method |
| CN115157005A (en) * | 2022-08-12 | 2022-10-11 | 华侨大学 | Cutter wear monitoring method, device, equipment and storage medium based on strain |
| CN115415851A (en) * | 2022-10-08 | 2022-12-02 | 清华大学 | Cutter health monitoring method based on functional data principal component analysis |
| WO2023217178A1 (en) * | 2022-05-13 | 2023-11-16 | 浙江工业大学 | Rolling workpiece surface quality prediction method |
| CN117111568A (en) * | 2023-10-24 | 2023-11-24 | 安联奇智(安徽)科技有限公司 | Equipment monitoring method, device, equipment and storage medium based on Internet of things |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH091430A (en) * | 1995-06-19 | 1997-01-07 | Sumitomo Electric Ind Ltd | Method and apparatus for detecting damage of assembled part |
| KR20140089700A (en) * | 2013-01-07 | 2014-07-16 | 제이윈 주식회사 | Cutting machine facility possible to measure quality |
| CN106126827A (en) * | 2016-06-28 | 2016-11-16 | 华中科技大学 | A kind of monitoring method of numerical control equipment health index |
-
2018
- 2018-07-06 CN CN201810733638.4A patent/CN109015111A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH091430A (en) * | 1995-06-19 | 1997-01-07 | Sumitomo Electric Ind Ltd | Method and apparatus for detecting damage of assembled part |
| KR20140089700A (en) * | 2013-01-07 | 2014-07-16 | 제이윈 주식회사 | Cutting machine facility possible to measure quality |
| CN106126827A (en) * | 2016-06-28 | 2016-11-16 | 华中科技大学 | A kind of monitoring method of numerical control equipment health index |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109724785A (en) * | 2018-12-29 | 2019-05-07 | 中铁工程装备集团有限公司 | A kind of tool condition monitoring and life prediction system based on Multi-source Information Fusion |
| CN110103077A (en) * | 2019-05-08 | 2019-08-09 | 北京理工大学 | A kind of boring state intelligent monitoring method of boring cutter bar multiple-sensor integration |
| CN110091216A (en) * | 2019-05-13 | 2019-08-06 | 江苏师范大学 | The monitoring of milling noise and milling vibration and its correlation analysis system and method |
| CN110091216B (en) * | 2019-05-13 | 2021-06-01 | 江苏师范大学 | Milling noise and milling vibration monitoring and correlation analysis system and method |
| CN110153801A (en) * | 2019-07-04 | 2019-08-23 | 西南交通大学 | A kind of cutting-tool wear state discrimination method based on multi-feature fusion |
| CN110515364A (en) * | 2019-07-15 | 2019-11-29 | 北京工业大学 | A kind of cutting-tool wear state detection method based on variation mode decomposition and LS-SVM |
| CN110515364B (en) * | 2019-07-15 | 2021-06-11 | 北京工业大学 | Cutter wear state detection method based on variational modal decomposition and LS-SVM |
| CN110428020A (en) * | 2019-08-13 | 2019-11-08 | 树根互联技术有限公司 | Cutter health evaluation model training method, device and electronic equipment |
| WO2021046738A1 (en) * | 2019-09-11 | 2021-03-18 | 大连理工大学 | Method for monitoring state of deep hole boring cutter on basis of stacked autoencoder |
| CN110561193A (en) * | 2019-09-18 | 2019-12-13 | 杭州友机技术有限公司 | Cutter wear assessment and monitoring method and system based on feature fusion |
| CN110744359A (en) * | 2019-11-29 | 2020-02-04 | 湖南工业职业技术学院 | Numerical control lathe cutter wear monitoring system and method |
| CN111300146A (en) * | 2019-11-29 | 2020-06-19 | 上海交通大学 | Numerical control machine tool cutter abrasion loss online prediction method based on spindle current and vibration signal |
| CN111085898A (en) * | 2019-12-30 | 2020-05-01 | 南京航空航天大学 | Working condition self-adaptive high-speed milling process cutter monitoring method and system |
| CN112034789A (en) * | 2020-08-25 | 2020-12-04 | 国家机床质量监督检验中心 | Health assessment method, system and assessment terminal for key parts and complete machine of numerical control machine tool |
| CN112192319A (en) * | 2020-09-28 | 2021-01-08 | 上海交通大学 | Tool wear monitoring method and system of unsupervised model |
| CN112372371A (en) * | 2020-10-10 | 2021-02-19 | 上海交通大学 | Method for evaluating abrasion state of numerical control machine tool cutter |
| CN114559297A (en) * | 2020-11-27 | 2022-05-31 | 财团法人工业技术研究院 | Cutter state evaluation system and method |
| CN114559297B (en) * | 2020-11-27 | 2023-09-19 | 财团法人工业技术研究院 | Tool state evaluation system and method |
| CN112720071A (en) * | 2021-01-27 | 2021-04-30 | 赛腾机电科技（常州）有限公司 | Cutter real-time state monitoring index construction method based on intelligent fusion of multi-energy domain signals |
| CN112720071B (en) * | 2021-01-27 | 2021-11-30 | 赛腾机电科技（常州）有限公司 | Cutter real-time state monitoring index construction method based on intelligent fusion of multi-energy domain signals |
| CN113043073A (en) * | 2021-03-22 | 2021-06-29 | 曲阜师范大学 | Cutter abrasion and service life prediction method and device |
| CN113601261A (en) * | 2021-08-10 | 2021-11-05 | 中国科学院合肥物质科学研究院 | Monitoring method of online rapid optimization model for cutter |
| WO2023217178A1 (en) * | 2022-05-13 | 2023-11-16 | 浙江工业大学 | Rolling workpiece surface quality prediction method |
| CN115157005A (en) * | 2022-08-12 | 2022-10-11 | 华侨大学 | Cutter wear monitoring method, device, equipment and storage medium based on strain |
| CN115157005B (en) * | 2022-08-12 | 2023-12-05 | 华侨大学 | Method, device, equipment and storage medium for monitoring tool wear based on strain |
| CN115415851A (en) * | 2022-10-08 | 2022-12-02 | 清华大学 | Cutter health monitoring method based on functional data principal component analysis |
| CN115415851B (en) * | 2022-10-08 | 2023-09-26 | 清华大学 | Cutter health monitoring method based on functional data principal component analysis |
| CN117111568A (en) * | 2023-10-24 | 2023-11-24 | 安联奇智(安徽)科技有限公司 | Equipment monitoring method, device, equipment and storage medium based on Internet of things |
| CN117111568B (en) * | 2023-10-24 | 2024-01-19 | 安联奇智(安徽)科技有限公司 | Equipment monitoring method, device, equipment and storage medium based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109015111A (en) | A kind of cutting tool state on-line monitoring method based on information fusion and support vector machines | |
| JP2019023937A5 (en) | ||
| CN113572625B (en) | Fault early warning method, early warning device, equipment and computer medium | |
| CN104933444B (en) | A kind of design method of the multi-level clustering syncretizing mechanism towards multidimensional property data | |
| CN104866831B (en) | The face recognition algorithms of characteristic weighing | |
| CN113225359A (en) | Safety flow analysis system based on brain-like calculation | |
| CN105424395A (en) | Method and device for determining equipment fault | |
| CN106271881B (en) | A kind of Condition Monitoring of Tool Breakage method based on SAEs and K-means | |
| Kan et al. | Dynamic network monitoring and control of in situ image profiles from ultraprecision machining and biomanufacturing processes | |
| CN109547251B (en) | Service system fault and performance prediction method based on monitoring data | |
| CN111860692A (en) | Abnormal data detection method based on K-media in Internet of things environment | |
| CN112905671A (en) | Time series exception handling method and device, electronic equipment and storage medium | |
| CN116244765A (en) | Equipment maintenance management method based on industrial Internet | |
| CN116541782A (en) | Power marketing data anomaly identification method | |
| CN117782198B (en) | Highway electromechanical equipment operation monitoring method and system based on cloud edge architecture | |
| CN111598700A (en) | Financial wind control system and method | |
| CN111600878A (en) | Low-rate denial of service attack detection method based on MAF-ADM | |
| CN117118810B (en) | Network communication abnormity early warning method and system | |
| CN114416423A (en) | Root cause positioning method and system based on machine learning | |
| CN112699921B (en) | Stack denoising self-coding-based power grid transient fault data clustering cleaning method | |
| CN113726558A (en) | Network equipment flow prediction system based on random forest algorithm | |
| CN116308295A (en) | Industrial production data management method and system | |
| CN110837953A (en) | Automatic abnormal entity positioning analysis method | |
| CN114663698A (en) | Production violation event detection method and device | |
| CN110543908B (en) | Control chart pattern recognition method based on dynamic observation window |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |