CN109211548A - A kind of mechanical failure diagnostic method - Google Patents
A kind of mechanical failure diagnostic method Download PDFInfo
- Publication number
- CN109211548A CN109211548A CN201811014122.0A CN201811014122A CN109211548A CN 109211548 A CN109211548 A CN 109211548A CN 201811014122 A CN201811014122 A CN 201811014122A CN 109211548 A CN109211548 A CN 109211548A
- Authority
- CN
- China
- Prior art keywords
- equipment
- signal
- trend
- diagnostic method
- filter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
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
A kind of mechanical failure diagnostic method the steps include: (1) Signal Pretreatment；(2) signal amplitude field parameter calculates；(3) equipment of work condition abnormality is made a concrete analysis of；(4) trend analysis；(5) intelligent predicting running trend of the equipment curve.The filtering algorithm of present invention optimization pre-processes signal, compared to general fault diagnosis software, the signal-to-noise ratio of signal is significantly improved, fault signature is extracted using improved fault signature extraction algorithm, compared to general fault diagnosis software, the precision that fault signature extracts is significantly improved；The historical trend of equipment can be analyzed, help the precision for improving fault diagnosis, intelligent predicting can be carried out to the residual life of equipment.
Description
Technical field
The present invention relates to monitoring technology field more particularly to a kind of mechanical failure diagnostic methods.
Background technique
Production equipment enlargement, serialization, high speed and automation increasingly in modern enterprise, this also becomes modern large-scale enterprise
The main feature of industry production also proposes the safety and reliability of industrial processes while industrial technology develops higher
It is required that even more so especially in pillar industry in national economy.Such as Aeronautics and Astronautics, petroleum, in electric power industry for production
The security requirement of process is extremely stringent, once production development accident will will cause pole if the failure for not preventing production equipment
Huge economic loss results even in the injures and deaths of personnel and the pollution of environment.This worldwide happens occasionally, and such as 1979
U.S.'s three mile island nuclear station since equipment fault causes nuclear matter to be revealed, not only cause tens dollars of economic loss and also because
Cause the protest of citizen for the pollution of environment；Bhopal insecticide factory of India lets out because production equipment failure results in poison gas within 1984
Dew, more causes more than 2,000 people's death other than economic loss and more than 20 ten thousand people are injured.
Except when will cause outside massive losses caused by production accident when equipment fault, device fails cause equipment
The maintenance cost damaged and needed is also an enormous expenditure.At the same time, often structure is complicated for modern industry equipments, if
Mechanical overhaul can not only be wasted according to common method for maintaining a large amount of time equally can also generate high maintenance cost
With.Therefore either from equipment fault cause production accident caused by from the point of view of loss or the huge damage caused by the maintenance of equipment
The change lost and require progress primary equipment maintenance mode from the point of view of the complexity of maintenance.
Modern comfort fault diagnosis technology is the needs due to aerospace earliest, from last century early sixties in the U.S.
Grow up.Hereafter, Britain, Germany, Sweden, Japan and other countries also start the research of fault diagnosis technology in succession, and obtain
Significant effect.It must develop by more than 30 years, mechanical fault diagnosis is extended via military enterprises such as initial Aeronautics and Astronautics
It is the frontier branch of science that multidisciplinary and technology intersects, computer technology and net from the development of simple detection means to civil field
Network technology is also widely applied in fault diagnosis and has greatly facilitated the development of fault diagnosis.
Rotating machinery it is many kinds of, as speed reducer, steam turbine, gas turbine, the hydraulic turbine, generator, aero-engine,
The equipment such as centrifugal compressor, typically electric power, petroleum, petrochemical industry, metallurgy, machinery, aviation and some war industry departments
Key equipment.Rotary machinery fault diagnosis has formd many fault diagnosis technologies by continuous development, general common
Fault diagnosis technology has following several:
Vibration diagnostic method
Vibration diagnostic method is detection mesh with acceleration signal, speed signal, the displacement signal etc. in the operating status of equipment
Mark carries out characteristic quantity analysis, spectrum analysis and Time-Frequency Analysis.Wherein Time-Frequency Analysis is vibration analysis method the most mature,
The fault message of most rotors can be found in the time domain of vibration signal, frequency-domain analysis, therefore analysis of vibration signal
It is the main means of rotary machinery fault diagnosis.
Temperature analysis method
The operating status of many mechanical equipments is related with temperature, therefore according to the change of mechanical equipment and ambient temperature
Change, it can be with the variation of the operating status of identifying system.Temperature diagnostic method is also a kind of method that fault diagnosis uses earliest.Now
The measurement of industrial medium temperature degree mainly uses thermal resistance, thermocouple temperature measurement sensor, and infrared temperature-test technology has gradually developed in recent years,
It will have and be more and more widely used in future.
Oil analyzing technology
Oil analyzing technology utilizes various routines, simple, precision or neutralization using spectrum analysis and analyzing iron spectrum as representative
Lubricating oil analysis instrument and method are especially in it contained mechanical wear clast to the physicochemical property of lubricating oil and other are micro-
Grain carries out the measurement of qualitative, quantitative, to obtain the state of wear in relation to components, machine operation situation and systemic contamination journey
The important information of degree etc..
Acoustics diagnosis
Acoustics diagnosis is detection target with noise, acoustic resistance, ultrasonic sound emission, carries out sound level, the sound intensity, sound source, sound field, sound
Spectrum analysis.Ultrasonic diagnosis, sound emission diagnosis are using relatively broad.In recent years, mechanical noise blind source separate technology
(Blind Source Separation) gradually application development gets up, and the effect of acoustics and diagnosis in fault diagnosis will not
It is disconnected to reinforce.
At present in the implementation process of fault diagnosis system, signal on-line checking, being generally exactly will using suitable sensor
Complete signal in mechanical movement collects, and then uses signal processing method as tool, to collected vibration signal into
Row processing, separates the characteristic information of faults and the characteristic information unrelated with failure, finds work condition state and characteristic quantity
Relationship, judge that work condition state is normal or abnormal.But directly collected signal is analyzed, not using relevant
Signal Pre-Processing Method, the serious interferences such as noise therein influence signal characteristic abstraction precision, and the signature analysis side of signal
Method precision is limited, since current signature analysis method is mainly Time Domain Analysis and based on Fourier transformation
Signal frequency domain analysis method.Frequency-domain analysis method based on Fourier transformation is only applicable to stationary signal, and the vibration at scene
Dynamic signal is non-stationary and containing much noise signal, this feature extraction precision for allowing for signal hardly results in raising；
In addition, can only be monitored to the operating condition of equipment, simple warning function is realized, the operation trend of equipment can not be made point
Analysis can not carry out the higher running trend of the equipment analysis of precision by the calculating of relevant parameter.
Summary of the invention
The present invention provides in order to solve the above problem, provides a kind of mechanical failure diagnostic method, and this method passes through improved
Fault signature extraction algorithm realizes that the history of relevant parameter becomes in conjunction with relevant time domain parameter calculation method, Time Domain Analysis
The anticipation to equipment working condition may be implemented by the historical trending analysis of relevant parameter, using intelligence learning algorithm in the analysis of gesture
Intelligent predicting is carried out to the remaining life of equipment.
The technical solution used in the present invention:
A kind of mechanical failure diagnostic method, the steps include:
(1) Signal Pretreatment: due to inevitably containing noise in collected vibration signal, first to collected
Vibration signal carries out noise reduction pretreatment, is filtered by iir filter, reduces interference of the noise to signal, improves signal-to-noise ratio；
(2) signal amplitude field parameter calculates: carrying out the calculating of amplitude domain relevant parameter, to pretreated signal to realize
The early warning of equipment working condition, and then judge whether the operating status of equipment is normal；
(3) make a concrete analysis of to the equipment of work condition abnormality: the fault characteristic frequency by calculating equipment vibrating signal is sentenced
The abort situation of the disconnected equipment that is out of order, fault type；
(4) trend analysis: calculating kurtosis, the earthquake intensity, peak value of vibration signal, carries out trend to the relevant parameter being calculated
Analysis, the overall operation state of analytical equipment confirm the fault severity level of equipment；
(5) vibration signal and noise signal of equipment intelligent predicting running trend of the equipment curve: is obtained by calculation
Arma modeling, and intelligent predicting is carried out by operation trend of the interative least square method, that is, RLS method to equipment, it is pre- using intelligence
Method of determining and calculating predicts the remaining life of equipment, to provide reference for relevant technical staff, helps the inspection for formulating equipment
It repairs, maintenance plan.
The iir filter is Butterworth filter, Chebyshev filter, chebyshev filters inverted filter, ellipse
One of filter and Bessel filter.
The amplitude domain relevant parameter include: root-mean-square value, average value, waveform index, pulse index, margin index,
Peak index, peak swing, kurtosis index.
The fault characteristic frequency includes FFT amplitude spectrum, power spectrum, cepstrum, envelope spectrum, resonance and demodulation spectrum.
The predicting residual useful life of the equipment passes through vibration severity parameter variation tendency figure and vibration severity curve prediction
As a result it shows.
The Signal Pretreatment is according to the different operating conditions of equipment, the suitable filter of different selections of collected vibration signal
Wave algorithm.
The vibration signal arma modeling:
First item is trend term in formula, and Section 2 is periodic term, and remainder is the part ARMA (p, q), wherein ARMA (p, q)
Model:
The interative least square method, that is, RLS method carries out intelligent predicting to the operation trend of equipment,It is pre- to need
The filter weight vector measured out, the iterative formula of weight vector are as follows:Wherein e (t) be error because
Son, k (t) are Kalman gain vector, and k (t) is acquired according to the following formula:
P (t)=λ-1P(t-1)-λ-1k(t)xT(t)P(t-1)。
Beneficial effects of the present invention: the present invention first pre-processes signal with iir filter, compared to general failure
The signal-to-noise ratio of diagnostic software, signal is significantly improved, and extracts fault signature using improved fault signature extraction algorithm, compares
In general fault diagnosis software, the precision that fault signature extracts is significantly improved；The historical trend of equipment can be carried out
Analysis helps the precision for improving fault diagnosis, can carry out intelligent predicting to the residual life of equipment.
Detailed description of the invention
Fig. 1 is algorithm flow schematic diagram of the invention.
Specific embodiment
A kind of mechanical failure diagnostic method, the steps include:
(1) Signal Pretreatment: due to inevitably containing noise in present collected vibration signal, first to acquisition
The vibration signal arrived carries out noise reduction pretreatment, is filtered by iir filter, reduces interference of the noise to signal, improves letter
It makes an uproar ratio；
(2) signal amplitude field parameter calculates: carrying out the calculating of amplitude domain relevant parameter, to pretreated signal to realize
The early warning of equipment working condition, and then judge whether the operating status of equipment is normal, which can calculate the operating parameter of equipment
And make early warning；
(3) make a concrete analysis of to the equipment of work condition abnormality: the fault characteristic frequency by calculating equipment vibrating signal is sentenced
The abort situation of the disconnected equipment that is out of order, fault type；
(4) trend analysis: calculating kurtosis, the earthquake intensity, peak value of vibration signal, carries out trend to the relevant parameter being calculated
Analysis, the overall operation state of analytical equipment confirm the fault severity level of equipment；
(5) vibration signal and noise signal of equipment intelligent predicting running trend of the equipment curve: is obtained by calculation
Arma modeling, and intelligent predicting is carried out by operation trend of the interative least square method, that is, RLS method to equipment, it is pre- using intelligence
Method of determining and calculating predicts the remaining life of equipment, to provide reference for relevant technical staff, helps the inspection for formulating equipment
It repairs, maintenance plan.
The iir filter is Butterworth filter, Chebyshev filter, chebyshev filters inverted filter, ellipse
One of filter and Bessel filter.
The amplitude domain relevant parameter include: root-mean-square value, average value, waveform index, pulse index, margin index,
Peak index, peak swing, kurtosis index.
The fault characteristic frequency includes FFT amplitude spectrum, power spectrum, cepstrum, envelope spectrum, resonance and demodulation spectrum.
The predicting residual useful life of the equipment passes through vibration severity parameter variation tendency figure and vibration severity curve prediction
As a result it shows.
The Signal Pretreatment is according to the different operating conditions of equipment, the suitable filter of different selections of collected vibration signal
Wave algorithm.
The Signal Pretreatment is according to the different operating conditions of equipment, the suitable filter of different selections of collected vibration signal
Wave algorithm.
The vibration signal arma modeling:
First item is trend term in formula, and Section 2 is periodic term, and remainder is the part ARMA (p, q), wherein ARMA (p, q)
Model:
The interative least square method, that is, RLS method carries out intelligent predicting to the operation trend of equipment,To need
Predict the filter weight vector obtained, the iterative formula of weight vector are as follows:
Wherein e (t) is error factor, and k (t) is Kalman gain vector, k (t) basis
Following formula acquires:
P (t)=λ-1P(t-1)-λ-1k(t)xT(t)P(t-1)。
Below with reference to specific embodiment, the present invention will be described:
Noise reduction pretreatment is carried out to collected vibration signal first, interference of the noise to signal is reduced, improves signal-to-noise ratio,
After the store path load document of selection analysis file, demand can be analyzed according to signal and different filter class is set
The key parameters such as type, order, cutoff frequency and passband, stopband attenuation, the parameter after signal data input filter, according to setting
Node-by-node algorithm is carried out to data, achieve the purpose that filter out specific frequency ingredient in data or extracts specific frequency ingredient；Then root
Corresponding Time-domain Statistics parameter is calculated according to the signal after filtering processing and different threshold values can be set for parameters, works as meter
When calculating threshold value of the parameter higher or lower than setting, equipment early warning is carried out；Vibration signal after calculating filtering processing, will acquire
Time-domain information be transformed into frequency domain, thus the fault characteristic frequency of extract equipment, and be out of order according to the judgement of these characteristic frequencies
The abort situation of equipment, fault type, SKF6205 deep groove ball bearing, the outer ring failure-frequency 108hz in envelope spectrum calculate filter
The parameters such as kurtosis, earthquake intensity, the peak value of wave treated vibration signal, and the rule that these parameters convert at any time is extracted, to phase
Close parameter and carry out trend analysis, can grasp the situation of change of equipment overall operation state with this, SKF6205 deep groove ball bearing it is high and steep
Angle value is worth degree to judge the severity of failure, the vibration of equipment is obtained by calculation generally 3 or so according to this is deviateed
The arma modeling of signal and noise signal, and intelligence is carried out by operation trend of the interative least square method, that is, RLS method to equipment
Can prediction, accurately predicted using remaining life of the intelligent prediction algorithms to equipment, vibration fault sequence for containing
The non-stationary random series of trend term and periodic term can be indicated by the canonical correlation formula of time series:
Xt=mt+st+Yt
In formula: mtIt is slowly varying trend term；stIt is the function that known periods are d, referred to as periodic term；YtFor steadily with
Machine noise item must carry out necessary pretreatment to dynamic data before settling time sequence arma modeling, i.e., --- it rejects
Trend term and periodic term, and test to the basic statistics feature for the noise item for rejecting trend term and periodic term, to ensure
The reliability and confidence level of the time series arma modeling of foundation.Reject the canonical correlation Formula X of time seriest=mt+st+YtIn
Trend term and periodic term, using S1 method, wherein EYt=0, st,d=stAndSo the unbiased esti-mator of trend term is
Periodic term stEstimation be then given by:
G is the number in period in formula, and meetsThe noise item of j-th of period kth point estimation is
To the random noise item for rejecting trend term and periodic term, using the stationary time series for being approximately a zero-mean,
The condition of arma modeling is established to meet sequence, if being still not able to meet the condition that time series establishes model, Ke Yigen
According to S3 method repeated action difference operatorApproaching random noise item as much as possible is the stationary time series of zero-mean.We
It can be described with following ARMA (p, q) model: yt+φ1yt-1+Λ+φpyt-p=at+θ1at-1+Λ+θqat-q
In formula: p and q is the order of autoregression part and sliding average part respectively；φi(i=1,2, Λ, p), θj(j=
1,2, Λ, q) it is autoregressive coefficient and sliding average coefficient respectively；T=1,2, Λ, it is white noise sequence, σa
For white noise variance.Therefore ARMA (p, q) model has p+q+1 unknown parameter.If determining these unknown parameters, it is necessary to first
Determine the order of model, i.e. p and q value.Identification model order has multiple criteria, such as AIC criterion, BIC criterion.
Unknown parameter φ is determined according to criterioni、θjAndSo far, random noise item can be established as follows
ARMA (p, q) model:
In conclusion obtaining vibration signal prediction model
First item is trend term in formula, and Section 2 is periodic term, and remainder is the part ARMA (p, q).Due to formulaTime series is comprehensively considered
Periodic term, trend term and random noise item feature, therefore have preferable fitting precision and outside forecast performance.
Interative least square method, that is, RLS method carries out intelligent predicting, recurrence least square (RLS) to the operation trend of equipment
Algorithm is a kind of adaptive recursive algorithm, and with its fast convergence rate, signal non-stationary adaptability is good, has quick tracking ability
The advantages that be widely used in adaptive prediction identification, prediction, filtering etc..IfTo need the filter for predicting to obtain
Weight vector, then in RLS algorithm, the iterative formula of weight vector are as follows:
Wherein e (t) is error factor, and k (t) is Kalman gain vector.Assuming that x (t) is input letter in discrete point t
Number, y (t) is by channel by the output signal after noise jamming,It is defeated by the expectation after noise jamming by channel
Signal out, n (t) are that mean value is zero and variance is σ2White noise, P (t) be covariance matrix, then error factor e (t) and
Kalman gain vector k (t) can be acquired according to the following formula:
P (t)=λ-1P(t-1)-λ-1k(t)xT(t)P(t-1)
It is iterated and can find out by the one-dimension array in ARMA (p, q) modelThe estimation knot needed
Fruit.
One embodiment of the present invention has been described in detail above, but the content is only preferable implementation of the invention
Example, should not be considered as limiting the scope of the invention.It is all according to all the changes and improvements made by the present patent application range
Deng should still be within the scope of the patent of the present invention.
Claims (8)
1. a kind of mechanical failure diagnostic method, which is characterized in that diagnostic method step are as follows:
(1) Signal Pretreatment: due to inevitably containing noise in collected vibration signal, first to collected vibration
Signal carries out noise reduction pretreatment, is filtered by iir filter, reduces interference of the noise to signal, improves signal-to-noise ratio；
(2) signal amplitude field parameter calculates: carrying out the calculating of amplitude domain relevant parameter, to pretreated signal to realize equipment
The early warning of operating condition, and then judge whether the operating status of equipment is normal；
(3) make a concrete analysis of to the equipment of work condition abnormality: the fault characteristic frequency by calculating equipment vibrating signal is judged
The abort situation of faulty equipment, fault type；
(4) trend analysis: calculating kurtosis, the earthquake intensity, peak value of vibration signal, carries out trend point to the relevant parameter being calculated
Analysis, the overall operation state of analytical equipment confirm the fault severity level of equipment；
(5) vibration signal of equipment and the ARMA mould of noise signal intelligent predicting running trend of the equipment curve: is obtained by calculation
Type, and intelligent predicting is carried out by operation trend of the interative least square method, that is, RLS method to equipment, using intelligent prediction algorithms
The remaining life of equipment is predicted, to provide reference for relevant technical staff, helps to formulate the maintenance of equipment, maintenance
Plan.
2. mechanical failure diagnostic method according to claim 1, which is characterized in that the iir filter is fertile for Bart
One of this filter, Chebyshev filter, chebyshev filters inverted filter, elliptic filter and Bessel filter.
3. mechanical failure diagnostic method according to claim 1, which is characterized in that the amplitude domain relevant parameter packet
It includes: root-mean-square value, average value, waveform index, pulse index, margin index, peak index, peak swing, kurtosis index.
4. mechanical failure diagnostic method according to claim 1, which is characterized in that the fault characteristic frequency includes
FFT amplitude spectrum, power spectrum, cepstrum, envelope spectrum, resonance and demodulation spectrum.
5. mechanical failure diagnostic method according to claim 1, which is characterized in that the predicting residual useful life of the equipment
It is shown by vibration severity parameter variation tendency figure and vibration severity curve prediction result.
6. mechanical failure diagnostic method according to claim 1, which is characterized in that the Signal Pretreatment is according to equipment
Different operating conditions, the difference of collected vibration signal select suitable filtering algorithm.
7. mechanical failure diagnostic method according to claim 1, which is characterized in that the vibration signal arma modeling:
First item is trend term in formula, and Section 2 is periodic term, and remainder is the part ARMA (p, q), wherein ARMA (p, q) mould
Type:
8. mechanical failure diagnostic method according to claim 1, which is characterized in that the interative least square method is
RLS method carries out intelligent predicting to the operation trend of equipment,To need the filter weight vector for predicting to obtain, weight vector
Iterative formula are as follows:Wherein e (t) is error factor, and k (t) is Kalman gain vector, k (t)
It acquires according to the following formula:
P (t)=λ-1P(t-1)-λ-1k(t)xT(t)P(t-1)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811014122.0A CN109211548A (en) | 2018-08-31 | 2018-08-31 | A kind of mechanical failure diagnostic method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811014122.0A CN109211548A (en) | 2018-08-31 | 2018-08-31 | A kind of mechanical failure diagnostic method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109211548A true CN109211548A (en) | 2019-01-15 |
Family
ID=64985641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811014122.0A Pending CN109211548A (en) | 2018-08-31 | 2018-08-31 | A kind of mechanical failure diagnostic method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109211548A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109738058A (en) * | 2019-02-15 | 2019-05-10 | 江苏弘冉智能科技有限公司 | A kind of self study vibrating failure diagnosis method |
| CN110044586A (en) * | 2019-03-13 | 2019-07-23 | 中交广州航道局有限公司 | Ship machine equipment failure judgment method, device, system and storage medium |
| CN110177017A (en) * | 2019-06-04 | 2019-08-27 | 沃德(天津)智能技术有限公司 | A kind of speed reducer intelligent Fault Diagnose Systems and its diagnostic method |
| CN110440909A (en) * | 2019-07-31 | 2019-11-12 | 安徽智寰科技有限公司 | A kind of vibration signal signal-noise ratio computation method based on noise self-adapting estimation |
| CN110672332A (en) * | 2019-09-10 | 2020-01-10 | 上海电力大学 | Gas turbine fault early warning system based on SARIMA model |
| CN110718231A (en) * | 2019-09-12 | 2020-01-21 | 深圳市铭华航电工艺技术有限公司 | Monitoring method, device, terminal and storage medium based on acoustic network |
| CN110991055A (en) * | 2019-12-08 | 2020-04-10 | 中国航空综合技术研究所 | Residual life prediction system for rotary mechanical products |
| CN111504450A (en) * | 2020-04-28 | 2020-08-07 | 郑州恩普特科技股份有限公司 | Equipment fault alarm method and device |
| CN111599033A (en) * | 2019-12-20 | 2020-08-28 | 深圳市鸿捷源自动化***有限公司 | Processing method for diagnosing cigarette machine fault |
| CN112014094A (en) * | 2020-09-03 | 2020-12-01 | 盾构及掘进技术国家重点实验室 | Shield tunneling machine main driving performance monitoring and repairing method |
| CN112124162A (en) * | 2020-09-23 | 2020-12-25 | 江苏徐工工程机械研究院有限公司 | Cab active vibration reduction method and system and engineering vehicle |
| CN112610330A (en) * | 2020-12-08 | 2021-04-06 | 孚创动力控制技术（启东）有限公司 | System and method for monitoring and analyzing running state of internal combustion engine |
| CN113155469A (en) * | 2021-03-19 | 2021-07-23 | 黑龙江机智通智能科技有限公司 | Engine fault diagnosis alarm system and device |
| CN113203797A (en) * | 2021-05-31 | 2021-08-03 | 郑州磨料磨具磨削研究所有限公司 | Diamond piece crack detection method and device |
| CN114046968A (en) * | 2021-10-04 | 2022-02-15 | 北京化工大学 | Two-step fault positioning method for process equipment based on acoustic signals |
| CN114295365A (en) * | 2022-03-09 | 2022-04-08 | 深圳市信润富联数字科技有限公司 | Method, system, equipment and storage medium for monitoring pin inserting machine precision abnormity |
| CN114383654A (en) * | 2021-12-14 | 2022-04-22 | 浙江华章科技有限公司 | Motor temperature, vibration, current analysis and life prediction circuit |
| CN114543982A (en) * | 2022-03-11 | 2022-05-27 | 珠海格力电器股份有限公司 | Method and device for detecting vibration of equipment, vibration detection equipment and storage medium |
| WO2023000532A1 (en) * | 2021-03-17 | 2023-01-26 | 江苏中科君达物联网股份有限公司 | New vibration noise test method |
| CN116448404A (en) * | 2023-06-15 | 2023-07-18 | 安徽容知日新科技股份有限公司 | Abnormality monitoring method, abnormality monitoring device, electronic device, and computer-readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6532454B1 (en) * | 1998-09-24 | 2003-03-11 | Paul J. Werbos | Stable adaptive control using critic designs |
| WO2007019708A1 (en) * | 2005-08-18 | 2007-02-22 | Societe De Commercialisation Des Produits De La Recherche Appliquee - Socpra | Digital identification and vector quantization methods and systems for detector crystal recognition in radiation detection machines |
| CN107576488A (en) * | 2017-08-30 | 2018-01-12 | 沃德传动（天津）股份有限公司 | A kind of method that diagnosis is monitored to equipment running status using vibration algorithm |
| CN108052528A (en) * | 2017-11-09 | 2018-05-18 | 华中科技大学 | A kind of storage device sequential classification method for early warning |
-
2018
- 2018-08-31 CN CN201811014122.0A patent/CN109211548A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6532454B1 (en) * | 1998-09-24 | 2003-03-11 | Paul J. Werbos | Stable adaptive control using critic designs |
| WO2007019708A1 (en) * | 2005-08-18 | 2007-02-22 | Societe De Commercialisation Des Produits De La Recherche Appliquee - Socpra | Digital identification and vector quantization methods and systems for detector crystal recognition in radiation detection machines |
| CN107576488A (en) * | 2017-08-30 | 2018-01-12 | 沃德传动（天津）股份有限公司 | A kind of method that diagnosis is monitored to equipment running status using vibration algorithm |
| CN108052528A (en) * | 2017-11-09 | 2018-05-18 | 华中科技大学 | A kind of storage device sequential classification method for early warning |
Non-Patent Citations (3)
| Title |
|---|
| 孙建: "滚动轴承振动故障特征提取与寿命研究", 《中国优秀硕士学位论文全文数据库 工程科学II辑》 * |
| 梁平 等: "基于ARMA及神经网络的汽轮机振动故障诊断研究", 《热能动力工程》 * |
| 闻邦椿: "《高等转子动力学：理论、技术及应用》", 31 January 2000, 机械工业出版社 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109738058A (en) * | 2019-02-15 | 2019-05-10 | 江苏弘冉智能科技有限公司 | A kind of self study vibrating failure diagnosis method |
| CN110044586A (en) * | 2019-03-13 | 2019-07-23 | 中交广州航道局有限公司 | Ship machine equipment failure judgment method, device, system and storage medium |
| CN110177017A (en) * | 2019-06-04 | 2019-08-27 | 沃德(天津)智能技术有限公司 | A kind of speed reducer intelligent Fault Diagnose Systems and its diagnostic method |
| CN110177017B (en) * | 2019-06-04 | 2023-09-19 | 沃德(天津)智能技术有限公司 | Intelligent fault diagnosis system and diagnosis method for speed reducer |
| CN110440909B (en) * | 2019-07-31 | 2021-07-13 | 安徽智寰科技有限公司 | Vibration signal-to-noise ratio calculation method based on noise adaptive identification |
| CN110440909A (en) * | 2019-07-31 | 2019-11-12 | 安徽智寰科技有限公司 | A kind of vibration signal signal-noise ratio computation method based on noise self-adapting estimation |
| CN110672332A (en) * | 2019-09-10 | 2020-01-10 | 上海电力大学 | Gas turbine fault early warning system based on SARIMA model |
| CN110718231A (en) * | 2019-09-12 | 2020-01-21 | 深圳市铭华航电工艺技术有限公司 | Monitoring method, device, terminal and storage medium based on acoustic network |
| CN110991055A (en) * | 2019-12-08 | 2020-04-10 | 中国航空综合技术研究所 | Residual life prediction system for rotary mechanical products |
| CN110991055B (en) * | 2019-12-08 | 2022-09-16 | 中国航空综合技术研究所 | Residual life prediction system for rotary mechanical products |
| CN111599033A (en) * | 2019-12-20 | 2020-08-28 | 深圳市鸿捷源自动化***有限公司 | Processing method for diagnosing cigarette machine fault |
| CN111504450A (en) * | 2020-04-28 | 2020-08-07 | 郑州恩普特科技股份有限公司 | Equipment fault alarm method and device |
| CN112014094A (en) * | 2020-09-03 | 2020-12-01 | 盾构及掘进技术国家重点实验室 | Shield tunneling machine main driving performance monitoring and repairing method |
| CN112124162A (en) * | 2020-09-23 | 2020-12-25 | 江苏徐工工程机械研究院有限公司 | Cab active vibration reduction method and system and engineering vehicle |
| CN112610330A (en) * | 2020-12-08 | 2021-04-06 | 孚创动力控制技术（启东）有限公司 | System and method for monitoring and analyzing running state of internal combustion engine |
| CN112610330B (en) * | 2020-12-08 | 2023-05-09 | 孚创动力控制技术（启东）有限公司 | Monitoring and analyzing system and method for running state of internal combustion engine |
| WO2023000532A1 (en) * | 2021-03-17 | 2023-01-26 | 江苏中科君达物联网股份有限公司 | New vibration noise test method |
| CN113155469A (en) * | 2021-03-19 | 2021-07-23 | 黑龙江机智通智能科技有限公司 | Engine fault diagnosis alarm system and device |
| CN113203797A (en) * | 2021-05-31 | 2021-08-03 | 郑州磨料磨具磨削研究所有限公司 | Diamond piece crack detection method and device |
| CN114046968A (en) * | 2021-10-04 | 2022-02-15 | 北京化工大学 | Two-step fault positioning method for process equipment based on acoustic signals |
| CN114383654A (en) * | 2021-12-14 | 2022-04-22 | 浙江华章科技有限公司 | Motor temperature, vibration, current analysis and life prediction circuit |
| CN114295365A (en) * | 2022-03-09 | 2022-04-08 | 深圳市信润富联数字科技有限公司 | Method, system, equipment and storage medium for monitoring pin inserting machine precision abnormity |
| CN114543982A (en) * | 2022-03-11 | 2022-05-27 | 珠海格力电器股份有限公司 | Method and device for detecting vibration of equipment, vibration detection equipment and storage medium |
| CN114543982B (en) * | 2022-03-11 | 2023-09-08 | 珠海格力电器股份有限公司 | Vibration detection method and device for equipment, vibration detection equipment and storage medium |
| CN116448404A (en) * | 2023-06-15 | 2023-07-18 | 安徽容知日新科技股份有限公司 | Abnormality monitoring method, abnormality monitoring device, electronic device, and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109211548A (en) | A kind of mechanical failure diagnostic method | |
| CN109506921B (en) | Fault diagnosis and early warning method for rotary machine | |
| Huo et al. | Incipient fault diagnosis of roller bearing using optimized wavelet transform based multi-speed vibration signatures | |
| Jaw | Recent advancements in aircraft engine health management (EHM) technologies and recommendations for the next step | |
| Zhang et al. | A probabilistic fault detection approach: Application to bearing fault detection | |
| CN113469060A (en) | Multi-sensor fusion convolution neural network aeroengine bearing fault diagnosis method | |
| Camci et al. | Feature evaluation for effective bearing prognostics | |
| US7027953B2 (en) | Method and system for diagnostics and prognostics of a mechanical system | |
| CN113834657B (en) | Bearing fault early warning and diagnosis method based on improved MSET and frequency spectrum characteristics | |
| KR101316486B1 (en) | Error detection method and system | |
| CN109033930B (en) | Equipment fault diagnosis method based on fault mechanism and statistical model online learning | |
| CN103115789B (en) | Second generation small-wave support vector machine assessment method for damage and remaining life of metal structure | |
| CN107576488A (en) | A kind of method that diagnosis is monitored to equipment running status using vibration algorithm | |
| CN109238455B (en) | A kind of characteristic of rotating machines vibration signal monitoring method and system based on graph theory | |
| Meng et al. | Health indicator of bearing constructed by rms-CUMSUM and GRRMD-CUMSUM with multifeatures of envelope spectrum | |
| Wang et al. | Weighted K-NN classification method of bearings fault diagnosis with multi-dimensional sensitive features | |
| CN106441843B (en) | A kind of rotating machinery fault method for waveform identification | |
| CN113053171A (en) | Civil aircraft system risk early warning method and system | |
| Zhang et al. | Remaining Useful Life Prediction of Rolling Bearings Using Electrostatic Monitoring Based on Two‐Stage Information Fusion Stochastic Filtering | |
| Feng et al. | Gas turbine blade fracturing fault diagnosis based on broadband casing vibration | |
| Adamowicz et al. | Advanced gas turbines health monitoring systems | |
| Zhang et al. | Anomaly detection: A robust approach to detection of unanticipated faults | |
| CN112380782A (en) | Rotating equipment fault prediction method based on mixed indexes and neural network | |
| Bediaga et al. | An integrated system for machine tool spindle head ball bearing fault detection and diagnosis | |
| Abdelrhman et al. | Diagnosis model for bearing faults in rotating machinery by using vibration signals and binary logistic regression |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |
|
| RJ01 | Rejection of invention patent application after publication |