CN1869967A - Discrimination method of machine tool type based on voice signal property - Google Patents
Discrimination method of machine tool type based on voice signal property Download PDFInfo
- Publication number
- CN1869967A CN1869967A CNA2005100402231A CN200510040223A CN1869967A CN 1869967 A CN1869967 A CN 1869967A CN A2005100402231 A CNA2005100402231 A CN A2005100402231A CN 200510040223 A CN200510040223 A CN 200510040223A CN 1869967 A CN1869967 A CN 1869967A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- lathe
- eigenwert
- mentioned
- domain
- 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
- 238000012850 discrimination method Methods 0.000 title 1
- 238000000034 method Methods 0.000 claims abstract description 53
- 230000005236 sound signal Effects 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims description 39
- 238000001228 spectrum Methods 0.000 claims description 37
- 238000001914 filtration Methods 0.000 claims description 10
- 238000002405 diagnostic procedure Methods 0.000 claims description 7
- 230000004069 differentiation Effects 0.000 claims description 7
- 230000000295 complement effect Effects 0.000 claims description 6
- 238000013459 approach Methods 0.000 claims description 2
- 230000008676 import Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000003745 diagnosis Methods 0.000 abstract description 2
- 238000005553 drilling Methods 0.000 description 11
- 238000003801 milling Methods 0.000 description 11
- 230000003595 spectral effect Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000005520 cutting process Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000003754 machining Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000002386 leaching Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005309 stochastic process Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
A method of identifying machine type based on sound signal character picks up sound character value of machine when machine runs idly and collects sound character value of machine when it is operated at site then utilizes these two sound character values to identify out machine type used on site. The computer software control can be applied in said method for realizing automatic calculation and identification used in machine fault diagnosis.
Description
Technical field
The present invention relates to a kind of method of discrimination of machine tool type, especially a kind of by thereby the voice signal when unloaded carries out the method for discrimination that collection analysis draws its eigenwert to lathe, specifically a kind of diagnostic method of the machine tool type based on the voice signal property value.
Background technology
At present, applied research in machining mainly comprises about voice recognition technology both at home and abroad: (1) is in the wear process of cutter, utilize the sound of cutting and the signal of vibration cutting to carry out online detection, feature by the signal that notes abnormalities, compare with normal signal again, thereby determine the depth of the degree of wear, the principle that wherein applies to mainly is an acoustic emission; (2) utilize in the metal cutting noise signal of flutter that flutter is monitored, see whether detected signal surpasses a certain predetermined threshold value, thereby determine the degree of flutter, wherein used the wavelet parameter estimation technique to extract corresponding proper vector; (3) by analysis, draw the operating condition of processing equipment and the state of cutting tool to annular saw cutting noise, thus the life-span and the operation danger of precognition cutting tool; (4) how research determines the voice signal property in the machining, apply to relevant signal processing technologies such as spectrum analysis, auto-correlation, relevant and artificial neural network, be primarily aimed at a kind of lathe and certain cut condition, extract the audio signal characteristics vector that it produces in process.Or the like.
In tut identification and the judgement research, major part is to concentrate on the state in the process is studied, and differentiates machining state by the proper vector that obtains, thereby is used for instructing actual production.But because its method of mainly using relates to image recognition, Ultrasonic Detection etc., its equipment investment is big, and condition of work requires high, and data processing cycle is long, has therefore influenced its practicality and has applied.
The applicant finds that the voice signal during its zero load of any a machine tool all has the characteristics of himself, dissimilar lathes, and the Welch power spectrum of the sound that it is produced when unloaded and amplitude domain eigenwert are inevitable inequality.The applicant effectively analyzes through a large amount of Welch power spectrum and amplitude domain eigenwerts of adopting economic MP3 to record at the scene when can be to lathe unloaded of experiment showed.Welch power spectrum frequency band and amplitude domain eigenwert during its zero load of any lathe all drop in the certain value scope, as long as determine the Welch power spectrum and the amplitude domain eigenwert of voice signal when institute's detection lathe is unloaded, each lathe eigenwert in itself and the given data storehouse is compared and can make correct differentiation to the type of this lathe, and the report that does not still have this respect at present comes out.
Summary of the invention
The diagnostic method that the purpose of this invention is to provide a kind of machine tool type based on voice signal property, it by gather lathe when unloaded voice signal and utilize Welch method and the amplitude analysis in the time-domain analysis (also claiming the amplitude domain analysis) method in the known frequency-domain analysis that this voice signal is handled, voice signal is in the eigenwert of frequency domain and time domain when drawing this lathe zero load, the absolute value average that comprises amplitude in pairing frequency range of peak-peak in the power spectrum and the time domain, mean square value and variance scope (below be referred to as above-mentioned eigenwert), above-mentioned eigenwert with the known lathe stored in itself and the database compares again, thereby differentiate the type of lathe, for equipment control and intelligent control provide foundation.
Technical scheme of the present invention is:
A kind of diagnostic method of the machine tool type based on voice signal property is characterized in that may further comprise the steps:
A, at first utilize sound collection equipment to gather the voice signal of certain lathe when separately unloaded, with this voice signal input computing machine, and utilize Welch method in the frequency-domain analysis and the amplitude analysis method in the time-domain analysis that this voice signal is handled, draw this lathe when unloaded voice signal in the eigenwert of frequency domain and time domain, stand-by in the above-mentioned eigenwert input database with gained;
B, repeat above-mentioned steps, the above-mentioned eigenwert of the voice signal of all kinds of lathes that obtain required differentiation when unloaded is separately also imported in the above-mentioned database stand-by;
C, import computing machine after utilizing sound collection equipment with the unloaded sound signal collecting of on-the-spot lathe, carry out the filtering of 20Hz～10kHz frequency range by the bandpass filter in the Butterworth wave filter, to cross low and too high frequency part in the filtered signal, and with Welch method in the power spectrum and amplitude domain analytical approach the voice signal of filtering gained is handled respectively, draw its corresponding eigenwert, if the above-mentioned eigenwert of certain type of lathe is complementary in this eigenwert and the database, then can judge the lathe that there is the type in the scene.
Described sound collection equipment can be the MP3 player with external microphone location, and it links to each other with computing machine by USB interface.
Above-mentioned eigenwert comprises absolute value average, mean square value and the variance scope of amplitude in pairing frequency range of peak-peak in the power spectrum and the time domain.
Beneficial effect of the present invention:
1, the revolutionary character that has at first realized signal collecting device breaks through, and utilizes MP3 player with low cost to have small investment, outstanding advantage easy to use as sound collection, conversion equipment.
2, give full play to and utilized Welch method and the powerful advantages of the amplitude analysis method in the time-domain analysis aspect the sound characteristic processing in the frequency-domain analysis, by to calculating required Parameter Optimization, can draw the frequency range with clear and definite power spectrum peak-peak at characteristic parameter place of associated machine tool and the statistical value scope of amplitude domain respectively, for the differentiation of machine tool type provides very clear and definite foundation.
3, computing method that the present invention relates to and database technology are common technology, all are easy to realize.
4, the present invention successfully is applied to the Butterworth wave filter technology in the leaching process of above-mentioned eigenwert, can effectively sudden factor be got rid of, and has improved the accuracy of data computation and differentiation.
5, the pre-job training for multimedia teaching and office worker provides image auditory effect true to nature.
6, can be used for all types of lathe factory inspections and whether its light condition works well when producing in the manufacturing shop basis for estimation.
7, provide a kind of for the fault diagnosis in next step lathe operational process for using for reference and efficient ways.
Description of drawings
Fig. 1 is signals collecting of the present invention and above-mentioned eigenwert leaching process process flow diagram.
Welch power spectrum figure line signal when Fig. 2 is the different reciprocating speed of the planer in the embodiment of the invention.
Welch power spectrum figure line signal when Fig. 3 is a milling machine different main rotating speed in the embodiment of the invention.
Welch power spectrum figure line signal when Fig. 4 is a lathe different main rotating speed in the embodiment of the invention.
Welch power spectrum figure line signal when Fig. 5 is a drilling machine different main rotating speed in the embodiment of the invention.
Embodiment
The present invention is further illustrated below in conjunction with drawings and Examples.
The concrete steps flow process as shown in Figure 1.
A, at first utilize MP3 player (no serious outside noise interference under laboratory condition with external microphone location, and be single device no-load running) gather the normal voice signal when unloaded of lathe, this voice signal is imported computing machine by USB interface, utilize Welch method in the frequency-domain analysis and the amplitude analysis method in the time-domain analysis that this voice signal is handled, the above-mentioned eigenwert of the voice signal when drawing its zero load, and with stand-by in its input database;
B, repeat above-mentioned steps respectively with each lathe of required differentiation such as planer, milling machine, lathe, drilling machine etc. when unloaded in the above-mentioned database of the above-mentioned eigenwert input of voice signal; Because the model difference of all kinds of lathes, therefore the different model of same class lathe should be tested respectively, draws the corresponding above-mentioned eigenwert of its voice signal;
C, utilize behind the unloaded sound signal collecting of the lathe that the scene need be differentiated with the MP3 player of external microphone location by USB interface input computing machine again, carry out designated frequency band (20Hz to 10kHz) filtering by the bandpass filter in the Butterworth wave filter, to cross low and too high frequency part in the filtered signal.Afterwards, utilize Welch method in the frequency-domain analysis and the amplitude analysis method in the time-domain analysis that the voice signal of filtering gained is handled respectively, draw its above-mentioned eigenwert, above-mentioned characteristic value data during such lathe light condition in this band limits of storing in the above-mentioned eigenwert of gained and the database is compared, draws as drawing a conclusion:
(1) if original signal is calculated the above-mentioned eigenwert of the planer of the one model in all planers in the above-mentioned eigenwert of gained and the database to be complementary (the above-mentioned eigenwert that is gained drops in the above-mentioned range of characteristic values of planer), then can judge the planer of on-the-spot lathe after designated frequency band filtering for this model.Otherwise, then show non-this model planer of on-the-spot lathe.
(2) if original signal is calculated the above-mentioned eigenwert of the milling machine of the one model in all milling machines in the above-mentioned eigenwert of gained and the database to be complementary (the above-mentioned eigenwert that is gained drops in the above-mentioned range of characteristic values of milling machine), then can judge the milling machine of on-the-spot lathe after designated frequency band filtering for this model.Otherwise, then show non-this model milling machine of on-the-spot lathe.
(3) if original signal is calculated the above-mentioned eigenwert of the lathe of the one model in all lathes in the above-mentioned eigenwert of gained and the database to be complementary (the above-mentioned eigenwert that is gained drops in the above-mentioned range of characteristic values of lathe), then can judge the lathe of on-the-spot lathe after designated frequency band filtering for this model.Otherwise, then show non-this model lathe of on-the-spot lathe.
(4) if original signal is calculated the above-mentioned eigenwert of the drilling machine of the one model in all drilling machines in the above-mentioned eigenwert of gained and the database to be complementary (the above-mentioned eigenwert that is gained drops in the above-mentioned range of characteristic values of drilling machine), then can judge the drilling machine of on-the-spot lathe after designated frequency band filtering for this model.Otherwise, then show non-this model drilling machine of on-the-spot lathe.
Specifically:
Above-mentioned eigenwert in the database of B690-I type hydraulic shaper is: in the frequency-domain analysis, in 180Hz～210Hz frequency range, the peak-peak (as shown in Figure 2) of clear and definite Welch power spectrum is arranged; In the time-domain analysis, each statistical value scope of amplitude is as shown in table 1.
Adopting uses the same method can learn:
Above-mentioned eigenwert in the database of S5040 type milling machine is: in the frequency-domain analysis, in 390Hz～420Hz frequency range, the peak-peak (as shown in Figure 3) of clear and definite Welch power spectrum is arranged; In the time-domain analysis, each statistical value scope of amplitude is as shown in table 2.
Above-mentioned eigenwert in the database of C630-2 type lathe is: in the frequency-domain analysis, in 590Hz～620Hz or 680Hz～710Hz frequency range, the peak-peak (as shown in Figure 4) of clear and definite Welch power spectrum is arranged; In the time-domain analysis, each statistical value scope of amplitude is as shown in table 3.
Above-mentioned eigenwert in the database of Z5125 type drilling machine is: in the frequency-domain analysis, in 600Hz～630Hz frequency range, the peak-peak (as shown in Figure 5) of clear and definite Welch power spectrum is arranged; In the time-domain analysis, each statistical value scope of amplitude is as shown in table 4.
Like this, the Welch method in the frequency-domain analysis is mutually comprehensive with the amplitude analysis method in the time-domain analysis, just can draw the above-mentioned eigenwert of all types of lathes, thereby be differentiated.
The present invention is further illustrated below in conjunction with the extraction of the voice signal property amount of planer.
1, classical power Spectral Estimation Welch method brief introduction in the frequency-domain analysis:
The power spectrum density of a static random process is the discrete Fourier transform (DFT) of this process autocorrelation sequence r (m), as shown in the formula:
P in the formula
Xx(ω) be power spectrum density, subscript xx is the original figure sequence xx (n) of this stochastic process.
The method of estimation of power spectrum density has two kinds of nonparametric model and parameter models.The nonparametric model method has Welch method, MIM (Multitaper) method and MUSIC (Multiple Signal Classification); The Welch method is a kind of period map method of improved average windowing; The MIM method is each the approximate uncorrelated estimation that at first obtains power spectrum with one group of quadrature window, it is combined produce the estimation of an overall power spectrum then; MUSIC generally is used for the linear spectral signal.The parameter model method mainly is MEM (Maximum Entropy Method) method, and it is a kind of autoregression technology of estimating for spectral density, the uncertainty of holding signal autocorrelation sequence (being entropy) maximum.In this paper research, we adopt the Welch method of nonparametric model.
General period map method estimating power spectral density is: at first a stochastic process being sampled obtains sequence xx (n), carries out Discrete Fourier Transform then.And the frequency spectrum that obtains taken absolute value square, at last with the data window norm square carry out normalized, to guarantee that it is asymptotically unbiased estimating, promptly along with the increase of sampled data, the expectation value of the estimation of periodogram is near real power spectrum density.The shortcoming of utilizing a kind of periodogram estimating power spectral density is that variance is bigger, and this variance yields does not reduce with the increase of number of samples.
The Welch method is just in order to reduce the variance that general period map method is estimated, and improves signal to noise ratio (S/N ratio), reduces and measure variability and propose.It is divided into not several parts of mutual superposition with sampled signal, averages then, and average hop count is many more, and variance is more little.But it is general because the limited length of signal, divisible signal data section hop count is less, in order to increase divisible data hop count, between the section section certain stack amount can be arranged, but since between section and the section data stack can the section of making and section between produce statistical dependence, this causes the variance increase of power spectrum density to a certain extent again.To this, by the method that adopts non-rectangle data window (as the Hamming window, Hanning window or Kaiser window) this key issue has been given solution in the Welch method.Because edge at these windows. its value decays to zero, the data dependence between the section of greatly reducing and the section.So, use the non-rectangle window, not only reduce the variance of spectrum estimation greatly, and can eliminate because the secondary lobe at frequency spectrum edge disturbs the influence of the crest width increase that makes spectrum estimation.
2, the application of Welch method in planer.
Adopt the Welch method of classical power Spectral Estimation, the main eigenwert of extracting is a power spectrum peak-peak frequency value corresponding.Here, we have adopted the programming tool of MATLAB and the signal Processing tool box that carries (SPTOOL BOX) respectively, and signal is carried out analyzing and processing.In programming process, we have mainly called [Pxx, f]=pwelch (xx, the window among the MATLAB, noverlap, nfft, fs) function, wherein Pxx is a power spectrum, f is frequency one to one with it, xx is the Serial No. of original signal, obtained Pxx, f after, we just can directly draw power spectrum chart with plot () drawing command; When utilization signal Processing tool box (SPTOOL BOX), we have used the spectrum of Welch method wherein to estimate, it is exactly that a series of parameter is integrated with the difference part of programming, provided a user interface, wherein comprise a drawing area, directly can draw power spectrum chart behind the input relevant parameter, and the demonstration of coordinate figure in length and breadth, read-out power peak-peak frequency value corresponding are easily arranged.
We can see from the function that calls, and the utilization of Welch method relates to definite problem of Several Parameters, i.e. overlapping number (noverlap) and FFT conversion count (nfft) between the length (nwin) of window function (window), window function, adjacent windows.Find by analyzing relatively, in the Welch of this research utilization:
(1) window function window () adopts hamming window (hamming ()) and Hanning window (hanning ()) almost less than big difference too, so adopted the hamming window in this research, i.e. window=hamming ();
(2) the length nwin when window changes from small to big (as by nwin=400 → nwin=800) time, the peak value number of power spectrum can increase thereupon, numerical value also becomes big slightly to some extent simultaneously, but the position that peak-peak occurs is almost constant, promptly Dui Ying frequency remains unchanged, therefore the length of window is to the not significantly influence of extraction of basic frequency of signal, and we get window length nwin=400 here;
(3) along with the increase of overlapping several noverlap, the peak number order of power spectrum can be along with minimizing, and promptly spectral line becomes comparatively level and smooth, but the frequency of peak-peak correspondence still remains unchanged, so we get overlapping several noverlap=80 in analyzing;
(4) the FFT conversion nfft that counts has directly determined frequency resolution Δ f and the low-limit frequency f in the frequency field
Min, and have:
Δ f=f
Min=f
s/ nfft (f
sBe sample frequency)
So consider actual frequency resolution and low-limit frequency, we get the FFT conversion nfft=2 that counts
12=4096.Δ f=f is so promptly arranged
Min=f
s/ nfft=22050/4096=5.3833Hz
With window, nwin, noverlap, nfft, five parameters of fs just can use the Welch method that signal has been carried out frequency-domain analysis after determining one by one.Fig. 2 is the planer drawn with the method for the programming power spectrum figure line under different gears when unloaded.
3, the application of Welch method in lathes such as milling machine, lathe and drilling machine is identical with planer.
4, the application of the amplitude analysis method in the time-domain analysis in various lathe eigenwerts are extracted.
The amplitude analysis method is exactly the knowwhy of utilization mathematical statistics, and the Serial No. of signal is carried out statistical study, absolute value average X, the mean square value of main abstraction sequence
And variances sigma (, only providing computing formula as follows) at this because of principle, formula are simple.Have for burst x (n):
Judge according to the different range of amplitude separately.The amplitude analysis method can not be differentiated machine tool type separately, need distinguish differentiation jointly in conjunction with the classical power Spectral Estimation Welch method in the above-mentioned frequency-domain analysis.
Subordinate list (all types of lathe amplitude statistical value scope):
The result of each statistical value of amplitude domain during table 1 planer difference reciprocating speed
| 1 gear | 2 gears | Planer | The absolute value average | Mean square value | Variance |
| 1 | I | Bao 01 | 0.1340 | 0.027452 | 0.09738 |
| II | Bao 02 | 0.1649 | 0.042381 | 0.12330 | |
| III | Bao 03 | 0.1947 | 0.057702 | 0.14065 | |
| IV | Bao 04 | 0.2477 | 0.081982 | 0.14359 | |
| 5 | I | Bao 01 | 0.1110 | 0.019165 | 0.08268 |
| II | Bao 02 | 0.1453 | 0.033464 | 0.11117 | |
| III | Bao 03 | 0.1801 | 0.045051 | 0.11237 | |
| IV | Bao 04 | 0.1214 | 0.023377 | 0.09295 | |
| I | Bao 01 | 0.2126 | 0.068690 | 0.15329 |
| 9 | II | Bao 02 | 0.1704 | 0.046755 | 0.13314 |
| III | Bao 03 | 0.2301 | 0.074362 | 0.14633 | |
| IV | Bao 04 | 0.3163 | 0.129714 | 0.17215 |
The result of each statistical value of amplitude domain during table 2 milling machine different main rotating speed
| Milling machine | Rotating speed (rpm) | The absolute value average | Mean square value | Variance |
| Xi 01 | 80rpm | 0.0614 | 0.005818 | 0.045262 |
| Xi 02 | 160rpm | 0.0651 | 0.006576 | 0.048417 |
| Xi 03 | 250rpm | 0.0752 | 0.008807 | 0.056105 |
| Xi 04 | 400rpm | 0.0720 | 0.008018 | 0.053238 |
| Xi 05 | 630rpm | 0.0872 | 0.011877 | 0.065426 |
| Xi 06 | 800rpm | 0.0843 | 0.011092 | 0.063165 |
| Xi 07 | 1000rpm | 0.1021 | 0.016402 | 0.077342 |
The result of each statistical value of amplitude domain during table 3 lathe different main rotating speed
| Lathe | Rotating speed (rpm) | The absolute value average | Mean square value | Variance |
| Che 01 | 67rpm | 0.0744 | 0.008708 | 0.056335 |
| Che 02 | 132rpm | 0.1506 | 0.035691 | 0.114065 |
| Che 03 | 212rpm | 0.1092 | 0.019183 | 0.120345 |
| Che 04 | 335rpm | 0.1538 | 0.038124 | 0.085160 |
| Che 05 | 425rpm | 0.1895 | 0.055831 | 0.165430 |
| Che 06 | 530rpm | 0.2336 | 0.081935 | 0.141091 |
The result of each statistical value of amplitude domain during table 4 drilling machine different main rotating speed
| Drilling machine | Rotating speed (rpm) | The absolute value average | Mean square value | Variance |
| Zuan01 | 80rpm | 0.037203 | 0.002117 | 0.027077 |
| Zuan02 | 200rpm | 0.038925 | 0.002344 | 0.028791 |
| Zuan03 | 315rpm | 0.043747 | 0.002999 | 0.032945 |
| Zuan04 | 500rpm | 0.059689 | 0.005786 | 0.047155 |
| Zuan05 | 800rpm | 0.062692 | 0.006163 | 0.047256 |
| Zuan06 | 1250rpm | 0.079298 | 0.009940 | 0.060427 |
| Zuan07 | 2000rpm | 0.144415 | 0.032827 | 0.109415 |
Claims (3)
1, a kind of diagnostic method of the machine tool type based on voice signal property is characterized in that may further comprise the steps:
A, at first utilize sound collection equipment to gather the voice signal of certain lathe when separately unloaded, with this voice signal input computing machine, and utilize Welch method in the frequency-domain analysis and the amplitude analysis method in the time-domain analysis that this voice signal is handled, draw this lathe when unloaded voice signal in the eigenwert of frequency domain and time domain, stand-by in the above-mentioned eigenwert input database with gained;
B, repeat above-mentioned steps, the above-mentioned eigenwert of the voice signal of all kinds of lathes that obtain required differentiation when unloaded is separately also imported in the above-mentioned database stand-by;
C, import computing machine after utilizing sound collection equipment with the unloaded sound signal collecting of on-the-spot lathe, carry out the filtering of 20Hz～10kHz frequency range by the bandpass filter in the Butterworth wave filter, to cross low and too high frequency part in the filtered signal, and with Welch method in the power spectrum and amplitude domain analytical approach the voice signal of filtering gained is handled respectively, draw its corresponding eigenwert, if the above-mentioned eigenwert of certain type of lathe is complementary in this eigenwert and the database, then can judge the lathe that there is the type in the scene.
2, the diagnostic method of the machine tool type based on voice signal property according to claim 1 is characterized in that described sound collection equipment is the MP3 player with external microphone location, and it links to each other with computing machine by USB interface.
3, the diagnostic method of the machine tool type based on voice signal property according to claim 1 is characterized in that described eigenwert comprises absolute value average, mean square value and the variance scope of amplitude in pairing frequency range of peak-peak in the power spectrum and the time domain.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100402231A CN100371925C (en) | 2005-05-25 | 2005-05-25 | Discrimination method of machine tool type based on voice signal property |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2005100402231A CN100371925C (en) | 2005-05-25 | 2005-05-25 | Discrimination method of machine tool type based on voice signal property |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1869967A true CN1869967A (en) | 2006-11-29 |
| CN100371925C CN100371925C (en) | 2008-02-27 |
Family
ID=37443634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2005100402231A Expired - Fee Related CN100371925C (en) | 2005-05-25 | 2005-05-25 | Discrimination method of machine tool type based on voice signal property |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100371925C (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100465609C (en) * | 2006-12-30 | 2009-03-04 | 北京航空航天大学 | System for measuring and analyzing digital-controlled machine-tool dynamic characteristic |
| CN102032942B (en) * | 2009-09-25 | 2012-07-25 | 上海宝钢工业检测公司 | Equipment vibration signal full frequency band characteristic extraction and alarm method based on Gaussian smoothing |
| CN102706560A (en) * | 2012-05-25 | 2012-10-03 | 华锐风电科技(江苏)有限公司 | State monitoring method and device of wind turbine generator set |
| CN102790933A (en) * | 2011-05-17 | 2012-11-21 | 芬德乐器公司 | Audio system and method using adaptive intelligence to distinguish information content of audio signals and to control signal processing function |
| CN102790932A (en) * | 2011-05-17 | 2012-11-21 | 芬德乐器公司 | Audio system and method using adaptive intelligence to distinguish information content of audio signals and to control signal processing function |
| CN106371407A (en) * | 2015-07-20 | 2017-02-01 | 陈益民 | Statistic method for machining working state and machining robot |
| CN106568500A (en) * | 2016-10-12 | 2017-04-19 | 上海大学 | Processing abnormality alarm system based on processing noise |
| CN106767986A (en) * | 2015-11-24 | 2017-05-31 | 中国科学院沈阳自动化研究所 | Instrument fault inline diagnosis method based on noise analysis |
| CN106873440A (en) * | 2015-12-14 | 2017-06-20 | 富士施乐株式会社 | Diagnostic device, diagnostic system, equipment and diagnostic method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4462080A (en) * | 1981-11-27 | 1984-07-24 | Kearney & Trecker Corporation | Voice actuated machine control |
| DE19933796A1 (en) * | 1999-07-19 | 2001-02-01 | Huber & Grimme Bearbeitungssys | Machine tool guidance system or multi-axis robot for a large number of tools |
| DE10049703A1 (en) * | 2000-10-07 | 2002-04-18 | Hdm Metalldrueckmaschinen Inst | Linear longitudinal seam edge processing machine for sound absorber housings etc. has tool carriage and processing towers moveable along various axis for adaptation to different work piece shapes |
-
2005
- 2005-05-25 CN CNB2005100402231A patent/CN100371925C/en not_active Expired - Fee Related
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100465609C (en) * | 2006-12-30 | 2009-03-04 | 北京航空航天大学 | System for measuring and analyzing digital-controlled machine-tool dynamic characteristic |
| CN102032942B (en) * | 2009-09-25 | 2012-07-25 | 上海宝钢工业检测公司 | Equipment vibration signal full frequency band characteristic extraction and alarm method based on Gaussian smoothing |
| CN102790933A (en) * | 2011-05-17 | 2012-11-21 | 芬德乐器公司 | Audio system and method using adaptive intelligence to distinguish information content of audio signals and to control signal processing function |
| CN102790932A (en) * | 2011-05-17 | 2012-11-21 | 芬德乐器公司 | Audio system and method using adaptive intelligence to distinguish information content of audio signals and to control signal processing function |
| CN102790932B (en) * | 2011-05-17 | 2015-10-07 | 芬德乐器公司 | Distinguish audio system and the method for signal message content and control signal processing capacity |
| CN102706560A (en) * | 2012-05-25 | 2012-10-03 | 华锐风电科技(江苏)有限公司 | State monitoring method and device of wind turbine generator set |
| CN102706560B (en) * | 2012-05-25 | 2017-12-12 | 华锐风电科技(江苏)有限公司 | The state monitoring method and device of a kind of wind power generating set |
| CN106371407A (en) * | 2015-07-20 | 2017-02-01 | 陈益民 | Statistic method for machining working state and machining robot |
| CN106767986A (en) * | 2015-11-24 | 2017-05-31 | 中国科学院沈阳自动化研究所 | Instrument fault inline diagnosis method based on noise analysis |
| CN106873440A (en) * | 2015-12-14 | 2017-06-20 | 富士施乐株式会社 | Diagnostic device, diagnostic system, equipment and diagnostic method |
| CN106568500A (en) * | 2016-10-12 | 2017-04-19 | 上海大学 | Processing abnormality alarm system based on processing noise |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100371925C (en) | 2008-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1869967A (en) | Discrimination method of machine tool type based on voice signal property | |
| CN104634571B (en) | A kind of Fault Diagnosis of Roller Bearings based on LCD MF | |
| CN111037365B (en) | Cutter state monitoring data set enhancing method based on generative countermeasure network | |
| CN102937522B (en) | Composite fault diagnosis method and system of gear case | |
| CN104723171A (en) | Cutter wear monitoring method based on current and acoustic emission compound signals | |
| CN110160765B (en) | Impact characteristic identification method and system based on sound or vibration signal | |
| CN101879690B (en) | Batch drilling process quality monitoring method based on multiple sensor signals | |
| CN105058165A (en) | Tool abrasion loss monitoring system based on vibration signals | |
| CN103962888A (en) | Tool abrasion monitoring method based on wavelet denoising and Hilbert-Huang transformation | |
| CN102765010A (en) | Cutter damage and abrasion state detecting method and cutter damage and abrasion state detecting system | |
| CN110561195B (en) | Method for monitoring flutter in machining process | |
| CN107194427A (en) | A kind of milling cutter malfunction monitoring and recognition methods and system | |
| CN108629864B (en) | Vibration-based electric spindle radial precision characterization method and system | |
| CN110346130B (en) | Boring flutter detection method based on empirical mode decomposition and time-frequency multi-feature | |
| Kulkarni et al. | Investigations on mother wavelet selection for health assessment of lathe bearings | |
| CN107350900A (en) | A kind of tool condition monitoring method based on the extraction of chip breaking time | |
| Zheng et al. | Exploring the effectiveness of using internal CNC system signals for chatter detection in milling process | |
| CN104708497A (en) | Tool wear monitoring system based on current and sound emission composite signals | |
| CN204525045U (en) | A kind of Tool Wear Monitoring system based on electric current and sound emission composite signal | |
| CN106441843A (en) | Rotating machinery fault waveform recognition method | |
| CN115890366A (en) | Online monitoring method for early flutter of inner circle of bearing ring during plunge grinding | |
| TW201925648A (en) | Pre-pressure diagnosis method of ball transmission assembly calculating a similarity of the test samples and a plurality of reference samples prepared in advance for determining whether the ball transmission assembly having a pre-pressure | |
| CN111599348B (en) | Automatic segmentation method and system for machine tool machining process monitoring signals | |
| CN116816338A (en) | Three-component electronic compass vibration monitoring-based rock stratum while drilling identification method | |
| CN114638265B (en) | Milling chatter judging method based on signal convolution neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20080227 Termination date: 20130525 |