CN106680011A - Printer fault diagnosis method based on acoustical signals - Google Patents

Printer fault diagnosis method based on acoustical signals Download PDF

Info

Publication number
CN106680011A
CN106680011A CN201710035487.0A CN201710035487A CN106680011A CN 106680011 A CN106680011 A CN 106680011A CN 201710035487 A CN201710035487 A CN 201710035487A CN 106680011 A CN106680011 A CN 106680011A
Authority
CN
China
Prior art keywords
printer
frequency
failure
formula
acoustical signal
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
Application number
CN201710035487.0A
Other languages
Chinese (zh)
Inventor
杨淑武
荆栓平
陈大庆
樊兴虎
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shaanxi Dafeng Printing Polytron Technologies Inc
Original Assignee
Shaanxi Dafeng Printing Polytron Technologies Inc
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shaanxi Dafeng Printing Polytron Technologies Inc filed Critical Shaanxi Dafeng Printing Polytron Technologies Inc
Priority to CN201710035487.0A priority Critical patent/CN106680011A/en
Publication of CN106680011A publication Critical patent/CN106680011A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00—Subject matter not provided for in other groups of this subclass
    • G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Abstract

The invention discloses a printer fault diagnosis method based on acoustical signals, comprising the steps of 1, acquiring acoustical signals for a printer being in normal state and faulted state; 2, processing and analyzing the acquired acoustical signals, and extracting feature values of the acoustical signals for the normal state and faulted state; 3, comparing the feature values of the acoustical signals for the normal state and faulted state, calculating fault contribution rate of each band, and determining the range of fault frequency; 4, positioning a fault of the printer according to the range of fault frequency so as to finish the fault diagnosis for the printer. According to the printer fault diagnosis method based on acoustical signals, acoustical signals of a printer are acquired and detected to know the operating state of the printer, and state monitoring and fault diagnosis are performed on the printer; the method replaces manual detection partially and has high automation level, basis is provided for printer maintenance and debugging, time is saved greatly, and operating efficiency is high.

Description

A kind of printer method for diagnosing faults based on acoustical signal
Technical field
The invention belongs to printer fault diagnosis technology field, is related to a kind of printer fault diagnosis based on acoustical signal Method.
Background technology
Printing equipment is the mainstay of printing industry, once break down that huge economic loss will be caused.So, build Vertical a set of accurate perfect printing equipment fault diagnosis system and condition monitoring system carry out accurate failure to printing equipment and determine Position and real-time monitoring are significant.
The information with a large amount of printing equipment running statuses, when system jam, can produce in printer acoustical signal The raw abnormal sound for making human ear uncomfortable, referred to as abnormal sound.Abnormal sound is not substantially caused by the intrinsic exciting source in printing equipment inside, But caused by certain failure that printing internal part is present, i.e., abnormal sound is the exterior representations of printing equipment internal fault.Cause This, by the way that printer acoustical signal is acquired, extracts and is analyzed, it will be appreciated that the running status of printing equipment, is to printing Machine carries out condition monitoring and fault diagnosis.
Existing fault diagnosis technology has had many applications on printing equipment, including the printer failure based on sound Diagnostic method, based on the printer fault diagnosis technology of vibration signal, printer method for diagnosing faults, base based on image information Printer fault diagnosis technology in expertise experience etc..Wherein, the printer method for diagnosing faults based on vibration signal, leads to Cross installed in vibrating mass acceleration transducer obtain vibrating mass vibration signal, and its vibration signal is analyzed and Process, and then judge whether this part works well.On the part of survey, the self gravitation of sensor can affect the fortune of workpiece Turn precision, use extremely inconvenient.Based on the printer method for diagnosing faults of image picture information, some bases to printer This failure has a preferable recognition effect, but extremely abundant feature set is contained in printed picture information, be related to texture, The related feature of alignment, color etc., these features reflect the result that multiparameter interacts in printing process, in feature set Containing substantial amounts of, complicated redundancy, these redundancies are only got rid of, could reasonably construction feature collection and failure mould Mapping relations between formula.In addition, the method for diagnosing faults based on image information, needs printer to print out after breaking down The failure cause of printing equipment can be just detected after image containing fault message, present press speed is very big, once therefore Barrier occurs, and will cause greatly to waste and great economic loss.Printer method for diagnosing faults based on sound is to workman Heuristicses are according to lazyness height, poor fault tolerance, and inefficiency, automaticity is low.
The content of the invention
Object of the present invention is to provide a kind of printer method for diagnosing faults based on acoustical signal, solves now The ineffective problem of printer failure diagnostic process.
The technical solution adopted in the present invention is, a kind of printer method for diagnosing faults based on acoustical signal, including with Lower step：
Acoustical signal when step 1, collection printer normal condition and malfunction；
Step 2, the acoustical signal to gathering are processed and analyzed, acoustical signal when extracting normal condition and malfunction Eigenvalue；
Step 3, the eigenvalue of acoustical signal when normal condition and malfunction is compared, calculate each frequency band failure tribute Rate is offered, the scope of failure-frequency is determined；
Step 4, according to the scope of failure-frequency, the failure of printer is positioned, examine so as to complete printer failure It is disconnected.
Of the invention the characteristics of, also resides in,
When step 1 gathers printer normal condition and malfunction by channel data acquisition system and sound transducer Acoustical signal.
Step 2 specifically includes following steps；
Step 2.1, collection printer normal condition and acoustical signal during malfunction are input in a wave filter；
Step 2.2, under Fourier transformation obtains normal condition and malfunction printer acoustical signal frequency domain letter Breath A (f),
Step 2.3, using frequency domain information A (f) by formula (1) calculate energy spectrum G (f)；
G (f)=A (f) ^2 (1)
Step 2.4, using energy spectrum G (f) according to the scramble domain information of the cepstrum transformation calculations acoustical signal of formula (2) C,
C=F-1(log(G(f))) (2)
Step 2.5, the eigenvalue for calculating acoustical signal by formula (3) using the scramble domain information C after each wave filter p；
P=sum | c | (3).
Step 3 specifically includes following steps；
Step 3.1, first the printer sound signal data for collecting by Fourier transformation, obtain printer sound The frequency domain 0Hz-fHz of signal, 0Hz-fHz m frequency band is divided into, acoustical signal by 1 to n wave filter, and Failure contribution rate F of each frequency band is calculated by formula (4) Fisher ratio methodsm, failure contribution rate maximal filter i is found out, and Calculate its frequency band (i-1) × f/m to i × f/m；
In formula (4), Xi jFor the sub-belt energy of the jth frame sample signal of i-th kind of failure, uiI-th kind of event is represented respectively with u The faulty sub-band averaging energy of barrier and institute, N is the total number of frequency band,
Step 3.2, frequency band (i-1) × f/m to i × f/m is divided into n frequency band, acoustical signal is passed through m+1 to n Number wave filter, and the failure contribution rate of each frequency band is calculated by formula (4) Fisher ratio methods, find out the maximum filter of failure contribution rate Ripple device i ', and calculate its frequency band (i ' -1) × f/mn to i ' × f/mn；
Step 3.3, frequency band division is carried out by that analogy, when the bandwidth of the frequency range that obtains less than setting, setting The a width of 2HZ of band, stop split-band, that is, obtain the frequency range of failure.
Step 4 is specially：The operating frequency of printer each part when obtaining normal condition and malfunction according to Theoretical Calculation Rate, then compares the frequency range that failure is obtained in step 3 with operating frequency, and the frequency range for seeing failure falls operating frequency That scope, you can the part for judging which position of printer breaks down.
The operating frequency of each part of printer is specifically divided into when obtaining normal condition and malfunction according to Theoretical Calculation：
Bearing outer ring failure-frequency foComputing formula is (5)：
In formula (5), Z is roller number, and d is rolling element diameter, and α is bearing pressure angle, and Dm is raceway pitch diameter, Fn is speed；
Bearing inner race failure-frequency fiComputing formula is (6)：
In formula (6), Z is roller number, and d is rolling element diameter, and α is bearing pressure angle, and Dm is raceway pitch diameter, Fn is speed；
Rolling element failure-frequency fbComputing formula is (7)：
In formula (7), d is rolling element diameter, and α is bearing pressure angle, and D is raceway pitch diameter, and fn is rotary frequency Rate；
The failure-frequency f of retainer inner ring and outer ringscComputing formula is respectively (8) or (9)：
In formula (9) and (8), Z is roller number, and d is rolling element diameter, and α is bearing pressure angle, and Dm is raceway pitch circle Diameter, fn is speed；
Rider roller, inking roller, the frequency of wavers are calculated according to the relation between the radius of formula (10) axis of rolling and turned Dynamic frequency；
In formula (10), ω 1, ω 2 are respectively driving shaft, the rotation angular frequency of driven shaft, r1, r2 driving shaft, driven shaft Radius；
The computing formula of gear meshing fault frequency fm is (11)：
fm=f1×z1=f2×z2 (11)
In formula (11), f1, f2 are respectively the rotational frequency of drivewheel, driven pulley.The tooth of z1, z2 drivewheel, driven pulley Number.
The invention has the beneficial effects as follows：A kind of printer method for diagnosing faults based on acoustical signal, to printer sound Signals collecting and detection, understand the running status of printer, and then carry out condition monitoring and fault diagnosis to printer, certain Manual detection is substituted in degree, high degree of automation provides foundation, saves substantial amounts of time, work for printer maintenance, debugging Make efficiency high.
Specific embodiment
With reference to specific embodiment, the present invention is described in detail.
The invention provides a kind of printer method for diagnosing faults based on acoustical signal, comprises the following steps：
Acoustical signal when step 1, collection printer normal condition and malfunction；
When step 1 gathers printer normal condition and malfunction by channel data acquisition system and sound transducer Acoustical signal；
Step 2, the acoustical signal to gathering are processed and analyzed, acoustical signal when extracting normal condition and malfunction Eigenvalue；
Step 2 specifically includes following steps；
Step 2.1, collection printer normal condition and acoustical signal during malfunction are input in a wave filter；
Step 2.2, under Fourier transformation obtains normal condition and malfunction printer acoustical signal frequency domain letter Breath A (f),
Step 2.3, using frequency domain information A (f) by formula (1) calculate energy spectrum G (f)；
G (f)=A (f) ^2 (1)
Step 2.4, using energy spectrum G (f) according to the scramble domain information of the cepstrum transformation calculations acoustical signal of formula (2) C,
C=F-1(log(G(f))) (2)
Step 2.5, the eigenvalue for calculating acoustical signal by formula (3) using the scramble domain information C after each wave filter p；
P=sum | c | (3)
Step 3, the eigenvalue of acoustical signal when normal condition and malfunction is compared, calculate each frequency band failure tribute Rate is offered, the scope of failure-frequency is determined；
Step 3 specifically includes following steps；
Step 3.1, first the printer sound signal data for collecting by Fourier transformation, obtain printer sound The frequency domain 0Hz-fHz of signal, 0Hz-fHz m frequency band is divided into, acoustical signal by 1 to n wave filter, and Failure contribution rate F of each frequency band is calculated by formula (4) Fisher ratio methodsm, failure contribution rate maximal filter i is found out, and Calculate its frequency band (i-1) × f/m to i × f/m；
In formula (4), Xi jFor the sub-belt energy of the jth frame sample signal of i-th kind of failure, uiI-th kind of event is represented respectively with u The faulty sub-band averaging energy of barrier and institute, N is the total number of frequency band,
Step 3.2, frequency band (i-1) × f/m to i × f/m is divided into n frequency band, acoustical signal is passed through m+1 to n Number wave filter, and the failure contribution rate of each frequency band is calculated by formula (4) Fisher ratio methods, find out the maximum filter of failure contribution rate Ripple device i ', and calculate its frequency band (i ' -1) × f/mn to i ' × f/mn；
Step 3.3, frequency band division is carried out by that analogy, when the bandwidth of the frequency range that obtains less than setting, setting The a width of 2HZ of band, stop split-band, that is, obtain the frequency range of failure；
Step 4, according to the scope of failure-frequency, the failure of printer is positioned, examine so as to complete printer failure It is disconnected；
Step 4 is specially：The operating frequency of printer each part when obtaining normal condition and malfunction according to Theoretical Calculation Rate, then compares the frequency range that failure is obtained in step 3 with operating frequency, and the frequency range for seeing failure falls operating frequency That scope, you can the part for judging which position of printer breaks down；
The operating frequency of each part of printer is specifically divided into when obtaining normal condition and malfunction according to Theoretical Calculation：
Bearing outer ring failure-frequency foComputing formula is (5)：
In formula (5), Z is roller number, and d is rolling element diameter, and α is bearing pressure angle, and Dm is raceway pitch diameter, Fn is speed；
Bearing inner race failure-frequency fiComputing formula is (6)：
In formula (6), Z is roller number, and d is rolling element diameter, and α is bearing pressure angle, and Dm is raceway pitch diameter, Fn is speed；
Rolling element failure-frequency fbComputing formula is (7)：
In formula (7), d is rolling element diameter, and α is bearing pressure angle, and D is raceway pitch diameter, and fn is rotary frequency Rate；
The failure-frequency f of retainer inner ring and outer ringscComputing formula is respectively (8) or (9)：
In formula (9) and (8), Z is roller number, and d is rolling element diameter, and α is bearing pressure angle, and Dm is raceway pitch circle Diameter, fn is speed；
Rider roller, inking roller, the frequency of wavers are calculated according to the relation between the radius of formula (10) axis of rolling and turned Dynamic frequency；
In formula (10), ω 1, ω 2 are respectively driving shaft, the rotation angular frequency of driven shaft, r1, r2 driving shaft, driven shaft Radius；
The computing formula of gear meshing fault frequency fm is (11)：
fm=f1×z1=f2×z2 (11)
In formula (11), f1, f2 are respectively the rotational frequency of drivewheel, driven pulley.The tooth of z1, z2 drivewheel, driven pulley Number.
A kind of printer method for diagnosing faults based on acoustical signal of the present invention, to printer sound signal collecting and inspection Survey, understand the running status of printer, and then condition monitoring and fault diagnosis are carried out to printer, people is substituted to a certain extent Work detects that high degree of automation provides foundation for printer maintenance, debugging, saves substantial amounts of time, high working efficiency.

Claims (6)

1. a kind of printer method for diagnosing faults based on acoustical signal, it is characterised in that comprise the following steps：
Acoustical signal when step 1, collection printer normal condition and malfunction；
Step 2, the acoustical signal to gathering are processed and analyzed, voice signal property when extracting normal condition and malfunction Value；
Step 3, the eigenvalue of acoustical signal when normal condition and malfunction is compared, calculate each frequency band failure contribution Rate, determines the scope of failure-frequency；
Step 4, according to the scope of failure-frequency, the failure of printer is positioned, so as to complete printer fault diagnosis.
2. a kind of printer method for diagnosing faults based on acoustical signal according to claim 1, it is characterised in that：It is described Step 1 gathers sound letter when printer normal condition and malfunction by channel data acquisition system and sound transducer Number.
3. a kind of printer method for diagnosing faults based on acoustical signal according to claim 1, it is characterised in that：It is described Step 2 specifically includes following steps；
Step 2.1, collection printer normal condition and acoustical signal during malfunction are input in a wave filter；
Step 2.2, under Fourier transformation obtains normal condition and malfunction printer acoustical signal frequency domain information A (f),
Step 2.3, using frequency domain information A (f) by formula (1) calculate energy spectrum G (f)；
G (f)=A (f) ∧ 2 (1)
Step 2.4, using energy spectrum G (f) according to the scramble domain information C of the cepstrum transformation calculations acoustical signal of formula (2),
C=F-1 (log (G (f))) (2)
Step 2.5, the eigenvalue p for calculating acoustical signal by formula (3) using the scramble domain information C after each wave filter；
P=sum | c | (3).
4. a kind of printer method for diagnosing faults based on acoustical signal according to claim 3, it is characterised in that：It is described Step 3 specifically includes following steps；
Step 3.1, first the printer sound signal data for collecting by Fourier transformation, obtain printer acoustical signal Frequency domain 0Hz-fHz, 0Hz-fHz is divided into m frequency band, acoustical signal by 1 to n wave filter, and pass through Formula (4) Fisher ratio methods calculate failure contribution rate F of each frequency bandm, failure contribution rate maximal filter i is found out, and calculate Its frequency band (i-1) × f/m to i × f/m；
F m = ( 1 / N ) ( X i j - u i ) ^ 2 Σ i = 1 N ( u i - u ) 2 ( 1 / N ) Σ i = 1 N Σ j = 1 T ( x i j - u i ) 2 - - - ( 4 )
In formula (4),For the sub-belt energy of the jth frame sample signal of i-th kind of failure, uiWith u represent respectively i-th kind of failure and The faulty sub-band averaging energy of institute, N is the total number of frequency band,
Step 3.2, frequency band (i-1) × f/m to i × f/m is divided into n frequency band, acoustical signal by m+1 to n number filter Ripple device, and the failure contribution rate of each frequency band is calculated by formula (4) Fisher ratio methods, find out failure contribution rate maximal filter I ', and calculate its frequency band (i ' -1) × f/mn to i ' × f/mn；
Step 3.3, frequency band division is carried out by that analogy, when the bandwidth of the frequency range that obtains less than setting, the band of setting A width of 2HZ, stops split-band, that is, obtain the frequency range of failure.
5. a kind of printer method for diagnosing faults based on acoustical signal according to claim 1, it is characterised in that：It is described Step 4 is specially：The operating frequency of printer each part when obtaining normal condition and malfunction according to Theoretical Calculation, then will The frequency range and operating frequency that failure is obtained in step 3 is compared, and the frequency range for seeing failure falls that model of operating frequency Enclose, you can the part for judging which position of printer breaks down.
6. a kind of printer method for diagnosing faults based on acoustical signal according to claim 5, it is characterised in that：It is described The operating frequency of each part of printer is specifically divided into when obtaining normal condition and malfunction according to Theoretical Calculation：
Bearing outer ring failure-frequency foComputing formula is (5)：
f 0 = 1 2 ( 1 - d D m c o s α ) f n Z - - - ( 5 )
In formula (5), Z is roller number, and d is rolling element diameter, and α is bearing pressure angle, and Dm is raceway pitch diameter, and fn is Speed；
Bearing inner race failure-frequency fiComputing formula is (6)：
f i = 1 2 ( 1 + d D m c o s α ) f n Z - - - ( 6 )
In formula (6), Z is roller number, and d is rolling element diameter, and α is bearing pressure angle, and Dm is raceway pitch diameter, and fn is Speed；
Rolling element failure-frequency fbComputing formula is (7)：
f b = D 2 d ( 1 - d 2 D 2 cos 2 α ) f n - - - ( 7 )
In formula (7), d is rolling element diameter, and α is bearing pressure angle, and D is raceway pitch diameter, and fn is speed；
The failure-frequency f of retainer inner ring and outer ringscComputing formula is respectively (8) or (9)：
f c = ( 1 + d D m c o s α ) f n 2 Z - - - ( 8 )
f c = ( 1 - d D m c o s α ) f n 2 Z - - - ( 9 )
In formula (9) and (8), Z is roller number, and d is rolling element diameter, and α is bearing pressure angle, and Dm is that raceway pitch circle is straight Footpath, fn is speed；
Rider roller, inking roller, the frequency of wavers calculate rotation frequency according to the relation between the radius of formula (10) axis of rolling Rate；
ω 1 ω 2 = r 2 r 1 - - - ( 10 )
In formula (10), ω 1, ω 2 are respectively driving shaft, the rotation angular frequency of driven shaft, r1, r2 driving shaft, the half of driven shaft Footpath；
The computing formula of gear meshing fault frequency fm is (11)：
Fm=f1 × z1=f2 × z2 (11)
In formula (11), f1, f2 are respectively the rotational frequency of drivewheel, driven pulley.The number of teeth of z1, z2 drivewheel, driven pulley.
CN201710035487.0A 2017-01-17 2017-01-17 Printer fault diagnosis method based on acoustical signals Pending CN106680011A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710035487.0A CN106680011A (en) 2017-01-17 2017-01-17 Printer fault diagnosis method based on acoustical signals

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710035487.0A CN106680011A (en) 2017-01-17 2017-01-17 Printer fault diagnosis method based on acoustical signals

Publications (1)

Publication Number Publication Date
CN106680011A true CN106680011A (en) 2017-05-17

Family

ID=58859254

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710035487.0A Pending CN106680011A (en) 2017-01-17 2017-01-17 Printer fault diagnosis method based on acoustical signals

Country Status (1)

Country Link
CN (1) CN106680011A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111755025A (en) * 2019-03-26 2020-10-09 北京君林科技股份有限公司 State detection method, device and equipment based on audio features
CN113266569A (en) * 2021-05-10 2021-08-17 广东葆德科技有限公司 Fault detection method and system of compressor based on noise
CN114954587A (en) * 2022-06-28 2022-08-30 西安英特迈思信息科技有限公司 Fault analysis system for running part of railway engineering vehicle

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101829689A (en) * 2010-03-31 2010-09-15 北京科技大学 Drift fault recognition method of hot-rolling strip steel based on sound signals
CN105527104A (en) * 2016-02-14 2016-04-27 成都柏森松传感技术有限公司 Bearing running-in abnormal sound detection system
CN106198062A (en) * 2016-07-27 2016-12-07 哈尔滨市科佳通用机电有限公司 The vehicle-mounted acoustic testing system of track vehicle fault and detection method
CN106198006A (en) * 2016-08-31 2016-12-07 中国南方电网有限责任公司超高压输电公司广州局 Extra-high voltage direct-current transmission valve cold Fault Diagnosis of Rotating Equipment Based method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101829689A (en) * 2010-03-31 2010-09-15 北京科技大学 Drift fault recognition method of hot-rolling strip steel based on sound signals
CN105527104A (en) * 2016-02-14 2016-04-27 成都柏森松传感技术有限公司 Bearing running-in abnormal sound detection system
CN106198062A (en) * 2016-07-27 2016-12-07 哈尔滨市科佳通用机电有限公司 The vehicle-mounted acoustic testing system of track vehicle fault and detection method
CN106198006A (en) * 2016-08-31 2016-12-07 中国南方电网有限责任公司超高压输电公司广州局 Extra-high voltage direct-current transmission valve cold Fault Diagnosis of Rotating Equipment Based method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LI YANYAN等: "A method of diagnosis for printing press ink roller bearing based on acoustic signal and spectrum analysis", 《2016 CHINA ACADEMIC CONFERENCE ON PRINTING, PACKAGING ENGINEERING AND MEDIA TECHNOLOGY》 *
雪花儿帅帅: "滚动轴承特征频率计算推导过程", 《CSDN博客》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111755025A (en) * 2019-03-26 2020-10-09 北京君林科技股份有限公司 State detection method, device and equipment based on audio features
CN111755025B (en) * 2019-03-26 2024-02-23 苏州君林智能科技有限公司 State detection method, device and equipment based on audio features
CN113266569A (en) * 2021-05-10 2021-08-17 广东葆德科技有限公司 Fault detection method and system of compressor based on noise
CN113266569B (en) * 2021-05-10 2023-04-28 广东葆德科技有限公司 Noise-based fault detection method and system for compressor
CN114954587A (en) * 2022-06-28 2022-08-30 西安英特迈思信息科技有限公司 Fault analysis system for running part of railway engineering vehicle

Similar Documents

Publication Publication Date Title
CN110274764B (en) Automatic diagnosis method for locomotive motor bearing based on vibration acceleration signal
EP3260836B1 (en) Vibration monitoring and diagnosing system for wind power generator
CN104535323B (en) A kind of train wheel Method for Bearing Fault Diagnosis based on angular domain time-domain and frequency-domain
CN107976304B (en) The mechanical disorder prediction analyzed based on the periodical information to signal
CN107144430B (en) A kind of Method for Bearing Fault Diagnosis based on incremental learning
CN110068462A (en) A kind of motor bearings method for diagnosing faults and device
CN113834657B (en) Bearing fault early warning and diagnosis method based on improved MSET and frequency spectrum characteristics
CN104596766B (en) Early fault determining method and device for bearing
CN103323244B (en) Bearing accuracy performance testing device and method of testing and determine the method for bearing accuracy initial failure part
CN106680011A (en) Printer fault diagnosis method based on acoustical signals
CN105806613A (en) Planetary gear case fault diagnosis method based on order complexity
CN106441896A (en) Characteristic vector extraction method for rolling bearing fault mode identification and state monitoring
CN106599794A (en) Six-axis industrial robot fault diagnosis method and system based on AR model
CN102441579B (en) The on-line monitoring method of hot tandem rolling mill running status
CN110095179A (en) A kind of detection of motor oscillating and diagnostic method
JP2017032520A (en) State monitoring device and state monitoring method
CN106248356A (en) A kind of rotary machinery fault diagnosis method based on kurtosis index
JP2013224853A (en) Method of diagnosing anomalies in low speed rotational bearing of elevator
Wang et al. A two-stage method using spline-kernelled chirplet transform and angle synchronous averaging to detect faults at variable speed
CN110056640A (en) Speed reducer wireless malfunction diagnostic method based on acceleration signal and edge calculations
CN110196165B (en) Rotary machine ball bearing fault diagnosis method based on K-means clustering and evidence reasoning
CN105303033B (en) Fault Diagnosis of Roller Bearings based on set intrinsic time Scale Decomposition algorithm
CN109484937A (en) A kind of enhancing of mine hoist state-detection is synchronous to extract transform method
Tang et al. A comparative experimental study of vibration and acoustic emission on fault diagnosis of low-speed bearing
WO2020040280A1 (en) Method and device for diagnosing abnormality in rolling bearing

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20170517