CN108907895A - A kind of milling cutter breakage on-line monitoring method - Google Patents
A kind of milling cutter breakage on-line monitoring method Download PDFInfo
- Publication number
- CN108907895A CN108907895A CN201810328343.9A CN201810328343A CN108907895A CN 108907895 A CN108907895 A CN 108907895A CN 201810328343 A CN201810328343 A CN 201810328343A CN 108907895 A CN108907895 A CN 108907895A
- Authority
- CN
- China
- Prior art keywords
- frequency
- signal
- time
- value
- sample
- 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.)
- Withdrawn
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
- B23Q17/0957—Detection of tool breakage
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The present invention provides a kind of milling cutter breakage on-line monitoring methods, the method acquires the acoustic emission signal in process as monitoring signals, extract the characteristic values such as rise time, counting, the amplitude of acoustic emission signal, characteristic value is detected using pattern recognition model, judges whether cutter occurs breakage.Using monitoring method of the present invention, tool failure can be detected at tool failure initial stage, take reduces the measures such as feed speed, the underproof problem of surface quality of workpieces caused by avoiding because of cutter serious damage in time.
Description
Technical field
The present invention relates to Milling Process Cutting tools to monitor field on-line, and in particular, to a kind of milling based on acoustic emission signal
Cut process tool damage monitoring method.
Background technique
With the development of science and technology, there are the brittleness such as the range of work wide, the ceramics of high production efficiency advantage, hard alloy
Cutter, blade are widely applied in production, and the hardness of these cutter materials is high, heat-resist, but toughness is insufficient, causes milling
Cut etc. during interrupted cuts easily occur it is damaged.Tool failure has become the main reason for this kind of tool failures, in steamer
Such cutter is largely used in the Milling Processes of the high value zero part such as machine rotor, generator amature, these parts do not allow
The problem of now causing surface quality of workpieces to be affected because of cutter serious damage, it is therefore desirable to study tool failure on-line monitoring side
Method.
Domestic and foreign scholars have done a lot of research work in terms of Condition Monitoring of Tool Breakage, retrieve by prior art document
It was found that patent CN105312965B, application number 201510900583.8, applicant:The Central China University of Science and Technology discloses a kind of " milling
The technical solution of process tool damage monitoring method ", the patent is:Spindle motor of machine tool three-phase current signal is acquired, is calculated every
The signal root-mean-square value in a sampling period as monitoring tool failure characteristic value, then calculate a period of time in upper threshold value and
Lower threshold value thinks that cutting tool state is good if new characteristic value falls into the coverage area of upper lower threshold value, thinks if exceeding
Tool failure.
The technology that the patent is related to has the following disadvantages:Above-mentioned technology is broken as cutter using the current signal of machine tool chief axis
The monitoring signals of damage, current signal reflection is machine tool chief axis power, reflects the cutting force of main shaft indirectly, is occurred in cutter serious
Damaged, cutting force can just detect tool failure after dramatically increasing, and the surface quality of workpiece has been affected at this time,
It is not used to the milling process monitoring of high level part.
Therefore, it is necessary to study one kind can monitor before cutter damaged initial stage occurs, also do not influence processing quality
Occurs damaged method to cutter.
Summary of the invention
It for the defects in the prior art, can the object of the present invention is to provide a kind of milling cutter breakage on-line monitoring method
Tool failure is detected at tool failure initial stage, and take reduces the measures such as feed speed in time, avoids leading because of cutter serious damage
The underproof problem of the surface quality of workpieces of cause.
In order to achieve the above object, the present invention provides a kind of milling cutter breakage on-line monitoring method, the method acquisition is processed
Acoustic emission signal (Acoustic Emission) in journey, the acoustic emission signal acquired using process are mentioned as monitoring signals
The characteristic value for taking acoustic emission signal is detected using characteristic value of the pattern recognition model to extraction, judges whether cutter occurs
It is damaged.
Specifically, described method includes following steps:
S1:Acoustic emission signal obtains
The acoustic emission signal sample of Milling Processes is acquired, it is corresponding that acoustic emission signal sample covers cutter serviceable condition
There is damaged corresponding acoustic emission signal in acoustic emission signal and cutter;
S2:Sound emission signal characteristic value is extracted
Characteristic value is divided into temporal signatures value and frequency domain character value two major classes, wherein:Temporal signatures value include rise time RT,
Count C, amplitude A, root-mean-square value RMS, average signal level ASL, peak counting CP, signal strength SS, absolute energy ABE;Frequently
Domain signal includes average frequency AF, inverse frequency RF, original frequency IF, centre frequency FC, crest frequency PF;
S3:Select sample
Using the method for Short Time Fourier Transform, corresponding sound emission signal characteristic value when cutter occurs damaged is filtered out,
By carrying out Short Time Fourier Transform to original signal, the time-frequency distributions of original signal are obtained, searching out is being more than 200kHz's
The high instantaneous energy signal occurred in frequency range extracts the acoustic emission signal at the moment at the time of determining that tool failure occurs
Characteristic value to get arrive the corresponding sound emission signal characteristic value of tool failure;
S4:It trains and tests supporting vector machine model
Tool Broken Detect is carried out using supporting vector machine model, the input vector of supporting vector machine model is sound emission letter
Number eigenmatrix:
Wherein:N=67 indicates the sample size for training or identification, xi=(RTi *,Ci *,Ai *,AFi *,RMSi *,
ASLi *,CPi *,RFi *,IF* i,SSi *,ABEi *,FCi *,PFi *)TIndicate the corresponding feature vector of a sample, totally 13 features;It is defeated
Outgoing vector is the target vector of training or identification, the i.e. corresponding label of input sample;
S5:Model optimization
It is deleted by adjusting the nuclear parameter γ and penalty factor of supporting vector machine model, with recursive feature Elimination Algorithms
The method Support Vector Machines Optimized model of uncorrelated features, makes the failure evaluation rate of supporting vector machine model reach highest;
S6:Breakage on-line monitoring
It acquires acoustic emission signal in real time in Milling Processes and extracts characteristic value, the support vector machines obtained using S5
Model detects characteristic value, judges whether tool failure occur.
Preferably, there are two the acoustic emission signal sources:
(1) it is generated when workpiece is plastically deformed in metal cutting process;
(2) generating when micro-crack and crack propagation occurs in cutter.
Preferably, in S1, the sample frequency of the acoustic emission signal is higher than 1MHz.
Preferably, in S2, in the temporal signatures value:
-- the rise time RT reaches interval time between amplitude peak from more than threshold value for signal;
-- the C that counts is the number that signal vibrates more than threshold value;
-- the amplitude A is the amplitude peak that signal reaches in primary hit, and unit is decibel (dB);The amplitude A's
Calculation method is A=120logVmax- P, wherein:P is preposition amplification factor;
-- the root-mean-square value RMS is that hit in corresponding period be effective voltage value;The root-mean-square value RMS's
Calculation method isWherein:xiFor ith sample point, N is the number of sampled point;
-- the average signal level ASL is the mean value of signal level in collision time, and unit is decibel (dB);It is described flat
The calculation method of equal signal level ASL is
-- the peak counting CP is the number that signal vibrates within the rise time;
-- the signal strength SS is integral of the rectified voltage signal to the time, and the time of integration is the time more than threshold;
The calculation method of the signal strength SS isWherein:xiFor ith sample point, N is sampled point
Number, f are sample frequency;
-- the absolute energy ABE is that signal voltage is that signal energy is hit in sound emission to the integral of time in collision time
The true reflection of amount, unit is joule (J);The calculation method of the absolute energy ABE isIts
In:xiFor ith sample point, N is the number of sampled point, and f is sample frequency.
Preferably, in S2, in the frequency domain character value:
-- the average frequency AF is the signal frequency in collision time, and the calculation method of the average frequency AF is AF=
C/HT, wherein:HT is collision time;
-- the inverse frequency RF is to the signal frequency after reach to peak value, and the calculation method of the inverse frequency RF is
-- the original frequency IF is the frequency that since signal reach this period of time of peak value hitting, the initial frequency
The calculation method of rate IF is
-- the centre frequency FC is the center of the frequency obtained by real time fourier processing, the centre frequency FC's
Calculation method is FC=∑ XF/ ∑ X, wherein:F, X is DFT result;
-- the crest frequency PF is the corresponding frequency of frequency maximum intensity point in Fourier transformation.
Compared with prior art, the present invention has following beneficial effect:
The present invention uses acoustic emission signal as monitoring signals, with sensor is easy for installation, does not interfere original processing work
The advantages of process system;The sound hair different from normal process can be generated when tool failure initial stage, tool surface just micro-crack occur
Signal is penetrated, therefore can detect that cutter is broken before cutter occurs influencing the serious damage of surface quality using this method
Damage avoids the occurrence of quality problems to take and reduce the measures such as feed speed;Damage testing is carried out using supporting vector machine model,
And the mode by adjusting parameter, deletion uncorrelated features optimizes, and realizes accurately identifying for tool failure.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is the method flow schematic diagram of one embodiment of the invention;
Fig. 2 is in the method for one embodiment of the invention to the Short Time Fourier Transform knot of the acoustic emission signal of normal process
Fruit;
Fig. 3 is in the method for one embodiment of the invention to the Short Time Fourier Transform knot of the acoustic emission signal of tool failure
Fruit.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, various modifications and improvements can be made.These belong to the present invention
Protection scope.
As shown in Figure 1, an a kind of embodiment process of the Milling Process Cutting tool damage monitoring method based on acoustic emission signal
Figure mainly includes six steps:Signal acquisition, signal characteristic abstraction, selection sample, training and test supporting vector machine model,
Model optimization, damaged on-line monitoring.
Specific step is as follows for the method:
S1:The acoustic emission signal sample of Milling Processes is acquired, in a preferred embodiment acoustic emission signal sample
There is the acoustic emission signal sample of the generator amature line embedding groove Milling Process acquisition of fluctuation, sample for 6 individual material properties
In contain No. 8 cutters and damaged corresponding acoustic emission signals occur, the sample frequency of acoustic emission signal is set as 2MHz;
S2:Characteristic value is divided into temporal signatures value and frequency domain character value two major classes, wherein:When the temporal signatures value has rising
Between RT, count C, amplitude A, root-mean-square value RMS, average signal level ASL, peak counting CP, signal strength SS, absolute energy
ABE;The frequency-region signal has average frequency AF, inverse frequency RF, original frequency IF, centre frequency FC, crest frequency PF;Each spy
The meaning of value indicative is as follows:
The rise time RT reaches interval time between amplitude peak from more than threshold value for signal;
The C that counts is the number that signal vibrates more than threshold value;
The amplitude A is the amplitude peak that signal reaches in primary hit, and unit is decibel (dB);The calculating side of amplitude A
Method is A=120log Vmax- P, wherein:P is preposition amplification factor;
The root-mean-square value RMS is that hit in corresponding period be effective voltage value;The calculating side of root-mean-square value RMS
Method isWherein:xiFor ith sample point, N is the number of sampled point;
The average signal level ASL is the mean value of signal level in collision time, and unit is decibel (dB);Average signal
The calculation method of level ASL is
The peak counting CP is the number that signal vibrates within the rise time;
The signal strength SS is integral of the rectified voltage signal to the time, and the time of integration is the time more than threshold;Letter
The calculation method of number intensity SS isWherein:xiFor ith sample point, N is the number of sampled point, f
For sample frequency;
The absolute energy ABE is that signal voltage is that signal energy is hit in sound emission to the integral of time in collision time
True reflection, unit is joule (J);The calculation method of absolute energy ABE isWherein:xiFor
Ith sample point, N are the number of sampled point, and f is sample frequency;
The average frequency AF is the signal frequency in collision time;The calculation method of average frequency AF is AF=C/HT,
Wherein:HT is collision time;
The inverse frequency RF is to the signal frequency after reach to peak value, and the calculation method of inverse frequency RF is
The original frequency IF is the frequency that since signal reach this period of time of peak value hitting, original frequency IF's
Calculation method is
The centre frequency FC is the center of the frequency obtained by real time fourier processing, the meter of the centre frequency FC
Calculation method is FC=∑ XF/ ∑ X, wherein:F, X is DFT result;
The crest frequency PF is the corresponding frequency of frequency maximum intensity point in Fourier transformation;
S3:Using the method for Short Time Fourier Transform, corresponding sound emission signal characteristic when cutter occurs damaged is filtered out
Value obtains the time-frequency distributions of original signal, searches out more than 200kHz by carrying out Short Time Fourier Transform to original signal
Frequency range in occur high instantaneous energy signal, determine tool failure occur at the time of, extract the moment sound emission letter
Number characteristic value is to get arriving the corresponding sound emission signal characteristic value of tool failure;As shown in Figure 2 and Figure 3, wherein:Fig. 2 is to normal
The Short Time Fourier Transform result of the acoustic emission signal of processing;Fig. 3 is the Fourier in short-term to the acoustic emission signal of tool failure
Transformation results.
S4:Tool Broken Detect is carried out using supporting vector machine model, the input vector of model is sound emission signal characteristic
Matrix:
Wherein:N=67 indicates the sample size for training or identification, xi=(RTi *,Ci *,Ai *,AFi *,RMSi *,
ASLi *,CPi *,RFi *,IF* i,SSi *,ABEi *,FCi *,PFi *)TIndicate the corresponding feature vector of a sample, totally 13 features;It is defeated
Outgoing vector is the target vector of training or identification, the i.e. corresponding label of input sample;
In a preferred embodiment, is there is into the damaged corresponding output valve of input vector in cutter and is set as " 1 ", by cutter
The output valve of normal input vector is set as " -1 ", and model is the support vector machines mould using gaussian radial basis function as kernel function
Type;
S5:It is deleted by adjusting the nuclear parameter γ and penalty factor of supporting vector machine model, with recursive feature Elimination Algorithms
Except the method Support Vector Machines Optimized model of uncorrelated features, the failure evaluation rate of supporting vector machine model is made to reach highest;
In a preferred embodiment, using the nuclear parameter γ and penalty factor of Box junction verification method Optimized model, really
Determine best parameter group, and calculate the different degree of feature using recursive feature Elimination Algorithms, removes a least relevant feature
Crest frequency;
S6:Acquire acoustic emission signal in real time in Milling Processes and extract characteristic value, the support obtained using S5 to
Amount machine model detects characteristic value, judges whether tool failure occur.
After above-mentioned specific implementation step, accurately identifying for tool failure may be implemented.
It is discussed in detail although the contents of the present invention have passed through above preferred embodiment, but it should be appreciated that above-mentioned
Description is not considered as limitation of the present invention.After those skilled in the art have read above content, for of the invention
A variety of modifications and substitutions all will be apparent, and these are all within the scope of protection of the present invention.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make various deformations or amendments within the scope of the claims, this not shadow
Ring substantive content of the invention.
Claims (5)
1. a kind of milling cutter breakage on-line monitoring method, which is characterized in that including:
S1:Acoustic emission signal obtains
The acoustic emission signal sample of Milling Processes is acquired, acoustic emission signal sample covers the corresponding sound hair of cutter serviceable condition
It penetrates signal and damaged corresponding acoustic emission signal occurs in cutter;
S2:Sound emission signal characteristic value is extracted
Characteristic value is divided into temporal signatures value and frequency domain character value two major classes, wherein:Temporal signatures value includes rise time RT, counts
C, amplitude A, root-mean-square value RMS, average signal level ASL, peak counting CP, signal strength SS, absolute energy ABE;Frequency domain letter
Number include average frequency AF, inverse frequency RF, original frequency IF, centre frequency FC, crest frequency PF;
S3:Select sample
Using the method for Short Time Fourier Transform, corresponding sound emission signal characteristic value when cutter occurs damaged is filtered out, is passed through
Short Time Fourier Transform is carried out to original signal, obtains the time-frequency distributions of original signal, searching out is being more than the frequency of 200kHz
The high instantaneous energy signal occurred in range extracts the sound emission signal characteristic at the moment at the time of determining that tool failure occurs
It is worth to get the corresponding sound emission signal characteristic value of tool failure is arrived;
S4:It trains and tests supporting vector machine model
Tool Broken Detect is carried out using supporting vector machine model, the input vector of supporting vector machine model is that acoustic emission signal is special
Levy matrix:
Wherein:N=67 indicates the sample size for training or identification,
It indicates the corresponding feature vector of a sample, shares 13 features;Output vector is the target vector of training or identification, that is, is inputted
The corresponding label of sample;
S5:Model optimization
Not phase is deleted by adjusting the nuclear parameter γ and penalty factor of supporting vector machine model, with recursive feature Elimination Algorithms
The method Support Vector Machines Optimized model for closing feature, makes the failure evaluation rate of supporting vector machine model reach highest;
S6:Breakage on-line monitoring
It acquires acoustic emission signal in real time in Milling Processes and extracts characteristic value, the supporting vector machine model obtained using S5
Characteristic value is detected, judges whether tool failure occur.
2. a kind of milling cutter breakage on-line monitoring method according to claim 1, which is characterized in that the acoustic emission signal is come
There are two sources:
(1) it is generated when workpiece is plastically deformed in metal cutting process;
(2) generating when micro-crack and crack propagation occurs in cutter.
3. a kind of milling cutter breakage on-line monitoring method according to claim 1, which is characterized in that in S1, the sound emission
The sample frequency of signal is higher than 1MHz.
4. a kind of milling cutter breakage on-line monitoring method according to claim 1, which is characterized in that in S2, the time domain is special
In value indicative:
-- the rise time RT reaches interval time between amplitude peak from more than threshold value for signal;
-- the C that counts is the number that signal vibrates more than threshold value;
-- the amplitude A is the amplitude peak that signal reaches in primary hit, and unit is decibel (dB);The calculating of the amplitude A
Method is A=120logVmax- P, wherein:P is preposition amplification factor;
-- the root-mean-square value RMS is that hit in corresponding period be effective voltage value;The calculating of the root-mean-square value RMS
Method isWherein:xiFor ith sample point, N is the number of sampled point;
-- the average signal level ASL is the mean value of signal level in collision time, and unit is decibel (dB);The average letter
The calculation method of number level ASL is
-- the peak counting CP is the number that signal vibrates within the rise time;
-- the signal strength SS is integral of the rectified voltage signal to the time, and the time of integration is the time more than threshold;It is described
The calculation method of signal strength SS isWherein:xiFor ith sample point, N is the number of sampled point,
F is sample frequency;
-- the absolute energy ABE is that signal voltage is that signal energy is hit in sound emission to the integral of time in collision time
True reflection, unit is joule (J);The calculation method of the absolute energy ABE isWherein:xi
For ith sample point, N is the number of sampled point, and f is sample frequency.
5. a kind of milling cutter breakage on-line monitoring method according to claim 1, which is characterized in that in S2, the frequency domain is special
In value indicative:
-- the average frequency AF is the signal frequency in collision time, and the calculation method of the average frequency AF is AF=C/
HT, wherein:HT is collision time;
-- the inverse frequency RF is to the signal frequency after reach to peak value, and the calculation method of the inverse frequency RF is
-- the original frequency IF is the frequency that since signal reach this period of time of peak value hitting, the original frequency IF
Calculation method be
-- the centre frequency FC is the center of the frequency obtained by real time fourier processing, the calculating of the centre frequency FC
Method is FC=∑ XF/ ∑ X, wherein:F, X is DFT result;
-- the crest frequency PF is the corresponding frequency of frequency maximum intensity point in Fourier transformation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810328343.9A CN108907895A (en) | 2018-04-13 | 2018-04-13 | A kind of milling cutter breakage on-line monitoring method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810328343.9A CN108907895A (en) | 2018-04-13 | 2018-04-13 | A kind of milling cutter breakage on-line monitoring method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108907895A true CN108907895A (en) | 2018-11-30 |
Family
ID=64402999
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810328343.9A Withdrawn CN108907895A (en) | 2018-04-13 | 2018-04-13 | A kind of milling cutter breakage on-line monitoring method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108907895A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109941860A (en) * | 2019-03-22 | 2019-06-28 | 西人马(西安)测控科技有限公司 | Elevator internal contracting brake fault monitoring method, device and system |
CN110153799A (en) * | 2019-05-14 | 2019-08-23 | 华中科技大学 | A kind of milling cutter damage testing method, apparatus and application based on permanent magnetism disturbance probe |
CN110222650A (en) * | 2019-06-10 | 2019-09-10 | 华北水利水电大学 | A kind of acoustie emission event classification method based on sound emission all band acquisition parameter |
CN112091727A (en) * | 2020-08-12 | 2020-12-18 | 上海交通大学 | Cutter damage identification method and device based on virtual sample generation and terminal |
CN117252873A (en) * | 2023-11-16 | 2023-12-19 | 江苏京创先进电子科技有限公司 | Grooving cutter damage detection method, grooving cutter damage detection system and cutting equipment |
CN117409306A (en) * | 2023-10-31 | 2024-01-16 | 江苏南高智能装备创新中心有限公司 | Fault monitoring method in milling cutter cutting-in process based on vibration and sound emission sensor |
-
2018
- 2018-04-13 CN CN201810328343.9A patent/CN108907895A/en not_active Withdrawn
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109941860A (en) * | 2019-03-22 | 2019-06-28 | 西人马(西安)测控科技有限公司 | Elevator internal contracting brake fault monitoring method, device and system |
CN110153799A (en) * | 2019-05-14 | 2019-08-23 | 华中科技大学 | A kind of milling cutter damage testing method, apparatus and application based on permanent magnetism disturbance probe |
CN110222650A (en) * | 2019-06-10 | 2019-09-10 | 华北水利水电大学 | A kind of acoustie emission event classification method based on sound emission all band acquisition parameter |
CN112091727A (en) * | 2020-08-12 | 2020-12-18 | 上海交通大学 | Cutter damage identification method and device based on virtual sample generation and terminal |
CN117409306A (en) * | 2023-10-31 | 2024-01-16 | 江苏南高智能装备创新中心有限公司 | Fault monitoring method in milling cutter cutting-in process based on vibration and sound emission sensor |
CN117409306B (en) * | 2023-10-31 | 2024-05-17 | 江苏南高智能装备创新中心有限公司 | Fault monitoring method in milling cutter cutting-in process based on vibration and sound emission sensor |
CN117252873A (en) * | 2023-11-16 | 2023-12-19 | 江苏京创先进电子科技有限公司 | Grooving cutter damage detection method, grooving cutter damage detection system and cutting equipment |
CN117252873B (en) * | 2023-11-16 | 2024-02-02 | 江苏京创先进电子科技有限公司 | Grooving cutter damage detection method, grooving cutter damage detection system and cutting equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108907895A (en) | A kind of milling cutter breakage on-line monitoring method | |
Liu et al. | Chatter detection in milling process based on VMD and energy entropy | |
CN107560851B (en) | Rolling bearing Weak fault feature early stage extracting method | |
CN109352416B (en) | Alarming method and device for clamping chips of machine tool spindle and/or winding chips of cutter | |
CN110044623A (en) | The rolling bearing fault intelligent identification Method of empirical mode decomposition residual signal feature | |
Sharifzadeh et al. | Detection of steel defect using the image processing algorithms | |
CN107350900B (en) | A kind of tool condition monitoring method extracted based on the chip breaking time | |
NO335107B1 (en) | Method and apparatus for one-piece acoustic impeller inspection | |
Wang et al. | Early chatter identification of robotic boring process using measured force of dynamometer | |
CN103941722B (en) | By component feature frequency multiplication amplitude Data Trend Monitor and the method for diagnostic device fault | |
CN109605127A (en) | A kind of cutting-tool wear state recognition methods and system | |
Li et al. | Surface quality monitoring based on time-frequency features of acoustic emission signals in end milling Inconel-718 | |
CN106771598B (en) | A kind of Adaptive spectra kurtosis signal processing method | |
Yan et al. | Early chatter detection in thin-walled workpiece milling process based on multi-synchrosqueezing transform and feature selection | |
CN104390697A (en) | C0 complexity and correlation coefficient-based milling chatter detection method | |
CN112417763A (en) | Defect diagnosis method, device and equipment for power transmission line and storage medium | |
EP4237922A1 (en) | Diagnostic apparatus, machining system, diagnostic method, and recording medium | |
CN113790911A (en) | Abnormal sound detection method based on sound frequency spectrum statistical law | |
CN208147865U (en) | A kind of sound recognition system applied to robot used for intelligent substation patrol | |
Yungong et al. | A fault feature extraction method for rotor rubbing based on load identification and measured impact response | |
CN106482912B (en) | A kind of vacuum equipment leak detection and localization method | |
CN107271543A (en) | A kind of engine compressor three-level disk seam Zone R domain high-sensitivity eddy current detection method | |
CN114528868A (en) | Crack fault detection method for compressor blade | |
Song et al. | Rolling Bearing Fault Diagnosis Under Different Severity Based on Statistics Detection Index and Canonical Discriminant Analysis | |
CN112091727A (en) | Cutter damage identification method and device based on virtual sample generation and terminal |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181130 |