CN106197996A - Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data - Google Patents

Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data Download PDF

Info

Publication number
CN106197996A
CN106197996A CN201610475423.8A CN201610475423A CN106197996A CN 106197996 A CN106197996 A CN 106197996A CN 201610475423 A CN201610475423 A CN 201610475423A CN 106197996 A CN106197996 A CN 106197996A
Authority
CN
China
Prior art keywords
gear
data
analysis
prediction
fault
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
CN201610475423.8A
Other languages
Chinese (zh)
Inventor
陆宝春
冯毅
徐祖康
崔益华
戴烁
高剑钊
侯俊涛
彭光玉
吴建
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.)
RAINBOW-CARGOTEC INDUSTRIES Co Ltd
Nanjing University of Science and Technology
Nantong Rainbow Heavy Machineries Co Ltd
Original Assignee
RAINBOW-CARGOTEC INDUSTRIES Co Ltd
Nanjing University of Science and Technology
Nantong Rainbow Heavy Machineries Co Ltd
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 RAINBOW-CARGOTEC INDUSTRIES Co Ltd, Nanjing University of Science and Technology, Nantong Rainbow Heavy Machineries Co Ltd filed Critical RAINBOW-CARGOTEC INDUSTRIES Co Ltd
Priority to CN201610475423.8A priority Critical patent/CN106197996A/en
Publication of CN106197996A publication Critical patent/CN106197996A/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
    • G01M13/00—Testing of machine parts
    • G01M13/02—Gearings; Transmission mechanisms
    • G01M13/021—Gearings
    • 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
    • G01M13/02—Gearings; Transmission mechanisms
    • G01M13/028—Acoustic or vibration analysis

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)

Abstract

The invention discloses a kind of offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data, device includes temperature sensor, acceleration transducer, embedded monitoring means, remotely monitoring and maintenance center, first temperature is installed, acceleration transducer, by GPRS module, the data of collection are transferred to host computer, bearing temperature trend prediction based on gray model Yu support vector regression model residual compensation is carried out further according to the temperature signal gathered, vibration signal use the method combined based on empirical mode decomposition and envelope spectrum analysis extract vibration fault feature；The most periodically extract gear-box lubricating oil oil sample and make conventional physico-chemical properties analysis and emission spectrographic analysis, carrying out wear trend analysis and fault pre-alarming according to galling content in oil sample；Three kinds of analysis results are carried out fusion ratio relatively, provides the fault diagnosis result of gear-box.The present invention can be effectively improved the fault diagnosis accuracy rate of offshore crane gear-box, makes diagnostic result more accurately and reliably.

Description

Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data
Technical field
The invention belongs to the fault diagnosis technology field of engineering machinery, a kind of marine lifting based on multivariate data Machine Fault Diagnosis of Gear Case device and method.
Background technology
Gear-box is that offshore crane performs to hoist the crucial drive disk assembly of action, and its work characteristics is low-speed heave-load, warp Often it is hit and alternate load effect, work under bad environment, it is susceptible to fault, causes gearbox failure.Currently for sea The condition monitoring and fault diagnosis method of crane gear box, it is common that the vibration signal of collection in worksite gear-box or fluid letter Cease, and the spectrum analysis or fluid composition analysis result according to vibration signal diagnoses, but this kind of method field assay parameter Single, it is impossible to further determine that fault type and position, more can not detect initial failure；On the other hand offshore crane gear-box The collection in worksite of monitoring parameter is the most relatively difficult, and remote monitoring and diagnosis is then preferable solution route.
Divide with fault as the patent of invention of Application No. CN 201110346490.7 discloses a kind of monitoring state of gear case Analysis method and device, by monitoring module monitors gear-box state and obtain vibration signal and oil information, and gather gear-box Vibration signal and oil information be analyzed process, and then will process after information carry out taxonomic revision as fault diagnosis Foundation, it is possible on the premise of not destroying gear-box, quickly realizes the switching between different faults situation and failure condition with normal The switching of situation, thus realize the fault simulation to gear-box, carry out status monitoring and accident analysis.This Patent Office is limited to scene Gathering vibration and carry out accident analysis with fluid information, vibration signal processing method is single, it is impossible to realize remote information collection with multiple Miscellaneous fault diagnosis.
As the patent of invention of application number CN200910043718.8 discloses a kind of tooth analyzed based on Multiscale Morphological Wheel method for diagnosing faults.The steps include: to utilize acceleration transducer to obtain gear vibration acceleration signal；Use EMD decomposition side The vibration acceleration signal of acquisition is decomposed into multiple IMF component by method；Choose from the IMF component decomposed and comprise fault and mainly believe Number high-frequency I MF component, utilize the IMF component reconstruction signal chosen；Reconstruction signal is carried out Multiscale Morphological demodulation analysis； Observe demodulation result spectrogram and whether at fault characteristic frequency or its frequency multiplication, there is obvious peak value, and then judge that rotating machinery is No break down.This patent is single for gear-box analytical parameters, and diagnosis object is only limitted to rotary part fault, it is impossible to sentence comprehensively Broken teeth roller box fault type and position.
Summary of the invention
It is an object of the invention to provide a kind of offshore crane Fault Diagnosis of Gear Case device based on multivariate data and Method, by gather multidimensional data and comprehensively analysis realize the fault diagnosis of offshore crane gear-box, find gear-box early Middle potential faults, improves efficiency and the accuracy of fault diagnosis.
The technical solution realizing the object of the invention is: a kind of offshore crane gearbox fault based on multivariate data The diagnostic equipment, including temperature sensor, acceleration transducer, embedded monitoring means, long-range monitoring and maintenance center, temperature sensing Device is arranged on gearbox high-speed axle bearing, and acceleration transducer is respectively arranged at each rotating shaft end cap within gear-box and casing On, described embedded monitoring means includes arm processor, multi-channel A/D acquisition interface, RS232 serial ports, GPRS module, remotely supervises Survey maintenance centre and include server, host computer；Described temperature sensor, the outfan of acceleration transducer are adopted by multi-channel A/D Collection interface accesses arm processor, and the outfan of arm processor accesses GPRS module by RS232 serial ports, and GPRS module passes through base Stand and the server communication at long-range monitoring and maintenance center, data memory module and fault diagnosis module are set in host computer；
Described temperature sensor gathers offshore crane high speed shaft of gearbox bearing temperature signal, acceleration transducer collection Gear-box internal gear, rotating shaft and bearing vibration signal；The data signal that temperature sensor and acceleration transducer gather is passed through Multi-channel A/D acquisition interface inputs the arm processor of embedded monitoring means, and arm processor passes through RS232 serial ports and GPRS module Connect；Described data signal is connected into the Internet by GPRS module after being communicated with base station, then by long-range monitoring and maintenance center Server and host computer communication, the data signal received is stored by the data memory module in host computer, fault diagnosis The module data signal to receiving carries out temperature data trend prediction and vibration signal fault signature extraction and analysis.
A kind of offshore crane Fault Diagnosis of Gear Case method based on multivariate data, temperature sensor gathers marine lifting Machine high speed shaft of gearbox bearing temperature signal, acceleration transducer gathers gear-box internal gear, rotating shaft and bearing vibration signal； The data signal that temperature sensor and acceleration transducer gather inputs embedded monitoring means through multi-channel A/D acquisition interface Arm processor, arm processor is connected with GPRS module by RS232 serial ports；Described data signal passes through GPRS module and base station It is connected into the Internet after communication, then by the server at long-range monitoring and maintenance center and host computer communication, the data in host computer are deposited The data signal received is stored by storage module, is carried by remote temperature trend prediction, remote oscillation signal fault feature Take and realize the fault diagnosis of offshore crane gear-box with crude oil sample analysis, specific as follows:
Step 1, the fault diagnosis module data signal to receiving carries out temperature data trend prediction and vibration signal event Barrier feature-extraction analysis；Meanwhile, taken at regular intervals offshore crane gear-box lubricating oil oil sample carries out oil sample Wear prediction analysis；
Step 2, judges the result of temperature data trend prediction and oil sample Wear prediction analysis:
Temperature data trend prediction, if prediction bearing temperature is maintained in secure threshold, then continues monitoring；If prediction bearing Temperature exceeds secure threshold, then prediction bearing breaks down；
Oil sample Wear prediction is analyzed, and taken at regular intervals offshore crane gear-box lubricating oil oil sample carries out conventional physico-chemical properties successively Analyze and emission spectrographic analysis, the value if parameter index breaks bounds, then judged result is that prediction is broken down；If parameter refers to Mark without departing from boundary value, then uses Data Tendency Forecast Based method that abrasive grain content is carried out Data Tendency Forecast Based, if prediction abrasive particle Content is maintained in secure threshold, then continue monitoring oil sample；If prediction abrasive grain content is beyond secure threshold, then judged result is pre- Survey is broken down；
Step 3, compares temperature data trend prediction and oil sample Wear prediction analysis result, if all predicting tooth simultaneously Roller box breaks down, then export fault diagnosis report and check gear-box comprehensively；If predicting the outcome difference, then enter step Rapid 4 carry out vibration signal fault signature extraction and analysis,
Step 4, carries out vibration signal fault signature extraction and analysis, if not comprising fault characteristic frequency, then continues monitoring；If Comprise fault characteristic frequency, then judge that gear or bearing break down and export fault diagnosis report.
Further, the temperature data trend prediction described in step 2, and the Data Tendency Forecast Based of abrasive grain content, specifically Step is as follows:
(1) from initial data, extract new time series x (t) make 53 smooth pretreatment and obtain
(2) rightSet up GM (1,1) gray model, obtain time series by modelTrend term matching sequenceAnd trend term forecasting sequence
(3) trend term matching sequenceResidual sequence is constituted with the residual error of former sequence x (t)RightBy empty mutually Between reconstruct composition residual sequence sample { n, xc, wherein:I is sample Sequence number, l is total sample number, and m is sample Embedded dimensions, by support vector regression model prediction residual sequence:
x ^ c = Σ i = 1 l - m ( α i - α i * ) K ( n t - m , x i ) + b
Wherein K () is kernel function, αi、For the solution of regression model, b is side-play amount；
(4) by anticipation trend item sequenceWith residual sequenceCombination constitutes final forecasting sequence, and for becoming afterwards Potential analysis.
Further, described in step 2, the conventional physico-chemical properties analysis indexes of oil sample Wear prediction analysis includes viscosity, sudden strain of a muscle Point, burning-point and acidity, emission spectrographic analysis includes using Fe, Cu, Al, Pb metal in wear particle detection equipment test sample fluid Content.
Further, vibration signal fault signature extraction and analysis described in step 4, specifically include following steps:
(1) the gear-box vibration signal gathered is made empirical mode decomposition, it is thus achieved that all IMF components of signal；
(2) to all IMF component Filtering Processing, remove and the incoherent high frequency noise content of gear-box vibration performance, protect Stay the frequency content relevant to gear engagement frequency band；
(3) the IMF Data Whitening after filtering and noise reduction is processed, and ask for autocorrelation matrix M；
(4) to autocorrelation matrix M singular value decomposition, and the IMF component a1 that eigenvalue of maximum is corresponding is found out；
(5) carry out a1 component asking for envelope spectrum as Fourier transformation after Hilbert transform is transformed into time-frequency domain, look for Go out whether low-frequency range comprises that amplitude is higher or the spectrum signature of frequency anomaly, and contrast gear or the bearing fault of Practical Calculation Frequency, finds out trouble location.
Compared with prior art, its remarkable advantage is the present invention: (1) crane gear box at sea monitoring field, will Scene temperature, vibration signals collecting combine with embedded monitoring means, it is possible to realize remote data acquisition, adapt to various badly Work condition environment, makes measurement more reliable, efficient；(2) use method based on gray model with SVR residual compensation that bearing temperature is become Gesture is predicted, is effectively improved trend prediction precision, accurately estimates box bearing duty, finds bearing initial failure in time； (3) method using EMD and envelope spectrum analysis to combine extracts gear-box vibration fault feature, is divided by the IMF decomposing EMD Amount filtering and noise reduction also extracts principal component analysis, effectively suppresses environment noise and improves analysis efficiency, is conducive to extracting industry existing The Weak fault feature that field is disturbed by very noisy；(4) comprehensive remote temperature trend prediction, remote oscillation fault signature extract and oil The failure condition of offshore crane gear-box is diagnosed by sample analysis result, it is to avoid single method analyzes the information office of fault Sex-limited, it is possible to effectively to analyze running state of gear box, it is simple to find that in time incipient fault also positions comprehensively, it is achieved failure prediction with Safeguard.
Accompanying drawing explanation
Fig. 1 is the structural representation of present invention offshore crane based on multivariate data Fault Diagnosis of Gear Case device.
Fig. 2 is the overview flow chart of present invention offshore crane based on multivariate data Fault Diagnosis of Gear Case method.
Fig. 3 is the Data Tendency Forecast Based flow chart of the present invention.
Fig. 4 is the vibration fault feature extraction flow chart of the present invention.
Fig. 5 is the crude oil sample analysis flow chart of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawings the present invention is described in further detail.
Present invention offshore crane based on multivariate data Fault Diagnosis of Gear Case device, including temperature sensor, acceleration Degree sensor, embedded monitoring means, long-range monitoring and maintenance center, temperature sensor is arranged on gearbox high-speed axle bearing, Acceleration transducer is respectively arranged on each rotating shaft end cap within gear-box and casing, and described embedded monitoring means includes Arm processor, multi-channel A/D acquisition interface, RS232 serial ports, GPRS module, long-range monitoring and maintenance center includes server, upper Machine；Described temperature sensor, the outfan of acceleration transducer access arm processor by multi-channel A/D acquisition interface, at ARM The outfan of reason device accesses GPRS module by RS232 serial ports, and GPRS module is by the clothes of base station with long-range monitoring and maintenance center Business device communication, arranges data memory module and fault diagnosis module in host computer；
Described temperature sensor gathers offshore crane high speed shaft of gearbox bearing temperature signal, acceleration transducer collection Gear-box internal gear, rotating shaft and bearing vibration signal；The data signal that temperature sensor and acceleration transducer gather is passed through Multi-channel A/D acquisition interface inputs the arm processor of embedded monitoring means, and arm processor passes through RS232 serial ports and GPRS module Connect；Described data signal is connected into the Internet by GPRS module after being communicated with base station, then by long-range monitoring and maintenance center Server and host computer communication, the data signal received is stored by the data memory module in host computer, fault diagnosis The module data signal to receiving carries out temperature data trend prediction and vibration signal fault signature extraction and analysis.
Present invention offshore crane based on multivariate data Fault Diagnosis of Gear Case method, temperature sensor gathers sea and rises Heavy-duty machine high speed shaft of gearbox bearing temperature signal, acceleration transducer gathers gear-box internal gear, rotating shaft and bear vibration letter Number；The data signal that temperature sensor and acceleration transducer gather is single through the embedded monitoring of multi-channel A/D acquisition interface input The arm processor of unit, arm processor is connected with GPRS module by RS232 serial ports；Described data signal by GPRS module with The Internet it is connected into after the communication of base station, then by the server at long-range monitoring and maintenance center and host computer communication, the number in host computer According to memory module, the data signal received is stored, by remote temperature trend prediction, remote oscillation signal fault spy Levy and extract and crude oil sample analysis realizes the fault diagnosis of offshore crane gear-box, specific as follows:
Step 1, the fault diagnosis module data signal to receiving carries out temperature data trend prediction and vibration signal event Barrier feature-extraction analysis；Meanwhile, taken at regular intervals offshore crane gear-box lubricating oil oil sample carries out oil sample Wear prediction analysis；
Step 2, judges the result of temperature data trend prediction and oil sample Wear prediction analysis:
Temperature data trend prediction, if prediction bearing temperature is maintained in secure threshold, then continues monitoring；If prediction bearing Temperature exceeds secure threshold, then prediction bearing breaks down；
Oil sample Wear prediction is analyzed, and taken at regular intervals offshore crane gear-box lubricating oil oil sample carries out conventional physico-chemical properties successively Analyzing and emission spectrographic analysis, the conventional physico-chemical properties analysis indexes of described oil sample Wear prediction analysis includes viscosity, flash-point, combustion Point and acidity, emission spectrographic analysis includes using Fe, Cu, Al, Pb tenor in wear particle detection equipment test sample fluid, The value if parameter index breaks bounds, then judged result is that prediction is broken down；If parameter index is without departing from boundary value, then Use Data Tendency Forecast Based method that abrasive grain content is carried out Data Tendency Forecast Based, if prediction abrasive grain content is maintained at secure threshold In, then continue monitoring oil sample；If prediction abrasive grain content is beyond secure threshold, then judged result is that prediction is broken down；
Described temperature data trend prediction, and the Data Tendency Forecast Based of abrasive grain content, specifically comprise the following steps that
(1) from initial data, extract new time series x (t) make 53 smooth pretreatment and obtain
(2) rightSet up GM (1,1) gray model, obtain time series by modelTrend term matching sequenceAnd trend term forecasting sequence
(3) trend term matching sequenceResidual sequence is constituted with the residual error of former sequence x (t)RightBy empty mutually Between reconstruct composition residual sequence sample { n, xc, wherein:I is sample Sequence number, l is total sample number, and m is sample Embedded dimensions, by support vector regression model prediction residual sequence:
x ^ c = Σ i = 1 l - m ( α i - α i * ) K ( n t - m , x i ) + b
Wherein K () is kernel function, αi、For the solution of regression model, b is side-play amount；
(4) by anticipation trend item sequenceWith residual sequenceCombination constitutes final forecasting sequence, and for becoming afterwards Potential analysis.
Step 3, compares temperature data trend prediction and oil sample Wear prediction analysis result, if all predicting tooth simultaneously Roller box breaks down, then export fault diagnosis report and check gear-box comprehensively；If predicting the outcome difference, then enter step Rapid 4 carry out vibration signal fault signature extraction and analysis,
Step 4, carries out vibration signal fault signature extraction and analysis, if not comprising fault characteristic frequency, then continues monitoring；If Comprise fault characteristic frequency, then judge that gear or bearing break down and export fault diagnosis report.
Described vibration signal fault signature extraction and analysis, specifically includes following steps:
(1) the gear-box vibration signal gathered is made empirical mode decomposition, it is thus achieved that all IMF components of signal；
(2) to all IMF component Filtering Processing, remove and the incoherent high frequency noise content of gear-box vibration performance, protect Stay the frequency content relevant to gear engagement frequency band；
(3) the IMF Data Whitening after filtering and noise reduction is processed, and ask for autocorrelation matrix M；
(4) to autocorrelation matrix M singular value decomposition, and the IMF component a1 that eigenvalue of maximum is corresponding is found out；
(5) carry out a1 component asking for envelope spectrum as Fourier transformation after Hilbert transform is transformed into time-frequency domain, look for Go out whether low-frequency range comprises that amplitude is higher or the spectrum signature of frequency anomaly, and contrast gear or the bearing fault of Practical Calculation Frequency, finds out trouble location.
Embodiment 1
In conjunction with Fig. 1, offshore crane Fault Diagnosis of Gear Case device based on multivariate data: remote supervision system mainly by Field unit and long-range monitoring and maintenance center composition.Field unit includes offshore crane gear-box, temperature sensor, acceleration Sensor group and embedded monitoring means.
Seat against nearly bearing inner race position mounting temperature sensor monitoring power shaft at gearbox high-speed shaft bearing to turn at a high speed Axle and bearing running status.Sensor is weldingly fixed on bearing block outer surface, temperature when indirect measurement axis is forwarded dynamic.
Groups of acceleration sensors prison is installed at gear-box each rotating shaft end cap and on the upside of casing near position, gear engagement place The vibration signal that when survey gear-box runs, gear engagement rotates with rotating shaft, first by point position sand papering before sensor installation Flat smooth, coats the good silicone grease of heat conductivity in order to flat contact surface installing surface, then is passed by permanent magnetism contact acceleration Sensor is placed in measuring point surface and fixes, and strengthens fixing at surrounding filling glass cement.
The temperature recorded and vibration signal incoming embedded monitoring means after conditioning module is amplified.Embedded monitoring is single Unit is made up of A/D interface, RS232 interface, ARM microprocessor and GPRS module.Temperature after conditioning is simulated with vibrating sensor Signal is by being converted into digital signal after multi-channel A/D interface input ARM microprocessor, and data packing is processed and passes through by processor The incoming GPRS module of RS232 interface, GPRS module sends data to remote maintenance center again.Remote maintenance center includes service Device and host computer.Host computer receives, by server, the packet that field unit transmits, and is stored data into by acquisition software Data base, and carry out temperature trend prediction and vibration signal fault signature extraction and analysis for Monitoring Data.
In conjunction with Fig. 2, offshore crane Fault Diagnosis of Gear Case method based on multivariate data, pre-in conjunction with remote temperature trend Survey, remote oscillation fault signature extracts and crude oil sample analysis is for the method for diagnosing faults of offshore crane cylinder reduction gear box Idiographic flow: first temperature and vibration signal to gear-box carries out Real-time Collection, and the signal after conditioning is through embedded monitoring Unit is packed, and by GPRS module general's collection data Wireless transceiver to long-range monitoring and maintenance center analysis, carries out temperature respectively and become Gesture prediction is extracted with vibration signal fault signature；If temperature trend prediction data exceeds secure threshold, judge to there is potential event Barrier, otherwise continues sampling analysis；If vibration signal fault signature extracts discovery there is typical fault characteristic frequency, then according to frequency Feature failure judgement type also exports diagnosis report, otherwise continues sampling analysis.The most periodically extract gear-box lubricating oil oil sample also Deliver to laboratory and carry out crude oil sample analysis, check that fluid has without exception by conventional physico-chemical properties analysis and emission spectrographic analysis, if Find that the parameter index value that breaks bounds then judges fluid fault；If without exceeding standard, further, by tenor in fluid is become Gesture forecast analysis carries out gear-box state of wear early diagnosis；The multivariate data result of Integrated comparative balance afterwards, becomes including temperature Gesture prediction, vibration signal fault signature extract and crude oil sample analysis, and carry out total failure diagnosis, export finally according to diagnostic result Fault diagnosis report, it is simple to further maintenance.
In conjunction with Fig. 3, the flow process of Data Tendency Forecast Based method is as follows:
(1) from up-to-date collection data, choose time series x (t) conduct that sample number is n and analyze object, by five three Secondary smooth preprocess method removes the erratic fluctuation of sequence x (t), it is thus achieved that the trend term sequence of a cubic polynomial matching
(2) to sequenceThe new sequence of Accumulating generation successivelySet up the corresponding differential equation and ask with method of least square Solution draws GM (1,1) model, successively decreases to reduce sequence by forecasting model data, and then obtains the trend of sample sequence x (t) Item matching sequenceAnd trend term forecasting sequence
(3) by trend term matching sequenceResidual sequence is constituted with the residual error of former sequence x (t)RightBy phase Space Reconstruction composition residual sequence sample:
{ n , x c | n i = n ^ ( t i ) , n ^ ( t i + 1 ) , ... , n ^ ( t i + m - 1 ) , x c i = n ^ ( t i + m ) }
Wherein, i is sample sequence number, and m is sample Embedded dimensions, chooses m=10.
By training sample { n, xcInput support vector regression model acquisition residual prediction model equation group:
x ^ c = Σ i = 1 l - m ( α i - α i * ) K ( n t - m , x i ) + b
Wherein K () is kernel function, αi、For the solution of regression model, b is side-play amount, and l is total sample number.By solving The residual sequence of working time section afterwards is predicted by residual prediction model.
(4) by anticipation trend item sequenceWith residual sequenceCombination constitutes final forecasting sequence, and according to pre-thermometric Gear case body and bearing temperature are analyzed by degree.Owing to friction generates heat when principle upper gear box bearing operates, with Time balanced by lubricating oil cooling, but bearing occurs temperature to raise when abrasion or the fault such as skew, and bearing temperature rise and rotating speed And institute's torque suspension is directly proportional, therefore high speed shaft bearing and the change of neighbouring spin manifold temperature are more apparent, easily carry out initial failure forecast. And the operating temperature threshold that box bearing allows is 60 DEG C, when predicted temperature will then judge gear beyond threshold value at short notice Axle box bearing or cooling system occur abnormal, should carry out Inspection and maintenance early.
In conjunction with Fig. 4, it is as follows that what vibration signal fault signature extracted is embodied as step:
(1) the gear-box vibration signal gathered is made EMD to decompose, first obtain analysis signal y (t) all extreme points, and Maximum point and minimum point are fitted to upper and lower envelope y respectivelymax(t) and yminT (), calculates ymax(t) and ymin(t) average M (t), by m (t) isolated decomposed signal h (t) from y (t), repeats above step until h (t) meets intrinsic mode functions bar Part, then calculated one group of IMF component lock out operation；In like manner h (t) is continued aforesaid operations and filter out all IMF components until not Till decomposing again.Now obtain the many groups IMF component under primary signal different scale.
(2) all IMF components being used FIR window function filter process, window function is selected and is improved raised cosine windows, root The cut-off frequency of low-pass filtering, stop-band frequency, logical ripple and stopband ripple is given according to the gear-box Faults by Vibrating calculated Stricture of vagina, post filtering remove with the incoherent high frequency noise content of gear-box vibration performance, retain with gear engage frequency band relevant Frequency content；
(3) to the IMF Data Whitening after filtering and noise reduction, it is specially and removes average and make normalized square mean process, then dialogue After change, IMF matrix obtains autocorrelation matrix M by being multiplied with self transposition；
(4) to matrix M singular value decomposition, it is thus achieved that all eigenvalues of matrix M.The biggest expression of eigenvalue of autocorrelation matrix This component shared component ratio in overall is the most, comprises characteristic parameter the most obvious.By eigenvalue is compared, find out maximum The IMF component a1 of eigenvalue and correspondence；
(5) further, the sideband information of a1 component medium frequency is extracted, particularly as follows: a1 component is carried out Hilbert Conversion is transformed into time-frequency domain, then asks for envelope spectrum by Fourier transformation, observes whether to comprise amplitude in low-frequency range higher or frequently The spectrum signature that rate is abnormal.If not existing, continuing monitoring, otherwise judging to break down, and with the gear of Practical Calculation or bearing Fundamental frequency or the frequency multiplication of failure-frequency compare, and find out trouble location according to frequecy characteristic.
In conjunction with Fig. 5, the main flow of oil analysis is as follows:
(1) conjunction extraction lubricating oil oil sample in application probe tube insertion gear-box distance position, bottom 1/3 to 1/2 takes to oil In the middle of sample bottle, if having been found that, existence is abnormal, should be at fluid each layer position multiple repairing weld.Offshore crane gear-box belongs to engineering Mechanical gear drive system, so the sampling interval is 300 hours, the gear-box sampling interval for running-in period can suitably contract Short.
(2) collection oil sample is made conventional physico-chemical properties analysis and emission spectrographic analysis.Conventional physico-chemical properties analysis indexes bag Including viscosity, flash-point and burning-point, acidity, corresponding measuring method canonical reference GB/T265, GB/T267 and GB/T264, if having multinomial Index exceeds normality threshold, then judge that fluid deteriorates；Carry out the gold such as Fe, Cu, Al, Pb in emission spectrographic analysis inspection fluid simultaneously Belonging to content, according to the boundary value multilevel iudge gear-box state of wear containing numerical quantity Yu setting, setting value is defined as:
N 1 = 0.8 ( Y ‾ + 2 S ) N 2 = Y ‾ + 2 S N 3 = Y ‾ + 3 S
In formula, N1 is normal limits value, and N2 is abnormal boundary value, and N3 is danger line limit value,Monitor for fluid tenor The average of data, S is standard deviation.If arbitrarily tenor is beyond danger line limit value, judge gear-box generation wear-out failure, no Then perform next step.
(3) the Data Tendency Forecast Based method shown in application drawing 3, in conjunction with history fluid tenor Monitoring Data, carry out Fe, Cu, Al, Pb content trend prediction, it was predicted that the data trend before the next sampling time.Normally transport according to each constituent content simultaneously Departure date data calculate its normal limits value, abnormal boundary value and danger line limit value, and with predictive value multilevel iudge state of wear, if Before the next sampling time puts, content is all normal then continues monitoring；Otherwise there is incipient fault in diagnosis gear-box, and according to abrasion The output diagnostic analysis report of the state order of severity.
Combine remote temperature trend prediction in conjunction with Fig. 1 explanation, remote oscillation fault signature extracts and crude oil sample analysis result pin Offshore crane gear-box is carried out Comprehensive method for diagnosing faults: owing to offshore crane gear-box operating mode is severe, because of This passes through remote supervision system Real-time Collection gearbox temperature and vibration signal.And owing to oil sample gathers difficulty, the most periodically carry Take gear crude oil sample analysis.For the temperature data monitored and fluid data based on trend prediction, gear-box will be run future State is predicted, and judges will export fault diagnosis report in advance when gear-box will appear from fault when simultaneously, carries out gear-box Maintenance in early days and maintenance, it is to avoid fault deteriorates；If predicting the outcome, difference occurs, then extract vibration signal and carry out fault signature and carry Taking, if finding typical fault characteristic frequency in analysis, can confirm that gear-box exists fault or potential crack, the most defeated The diagnosis report that is out of order keeps in repair, and otherwise continues monitoring and observes.

Claims (5)

1. an offshore crane Fault Diagnosis of Gear Case device based on multivariate data, it is characterised in that include temperature sensing Device, acceleration transducer, embedded monitoring means, long-range monitoring and maintenance center, temperature sensor is arranged at high speed shaft of gearbox On bearing, acceleration transducer is respectively arranged on each rotating shaft end cap within gear-box and casing, and described embedded monitoring is single Unit includes that arm processor, multi-channel A/D acquisition interface, RS232 serial ports, GPRS module, long-range monitoring and maintenance center include service Device, host computer；Described temperature sensor, the outfan of acceleration transducer access ARM process by multi-channel A/D acquisition interface Device, the outfan of arm processor accesses GPRS module by RS232 serial ports, and GPRS module is by base station and long-range monitoring and maintenance The server communication at center, arranges data memory module and fault diagnosis module in host computer；
Described temperature sensor gathers offshore crane high speed shaft of gearbox bearing temperature signal, and acceleration transducer gathers gear Case internal gear, rotating shaft and bearing vibration signal；The data signal that temperature sensor and acceleration transducer gather is through multichannel A/D acquisition interface inputs the arm processor of embedded monitoring means, and arm processor is by RS232 serial ports with GPRS module even Connect；Described data signal is connected into the Internet by GPRS module after being communicated with base station, then by the clothes at long-range monitoring and maintenance center Business device and host computer communication, the data signal received is stored by the data memory module in host computer, fault diagnosis mould The block data signal to receiving carries out temperature data trend prediction and vibration signal fault signature extraction and analysis.
2. an offshore crane Fault Diagnosis of Gear Case method based on multivariate data, it is characterised in that: temperature sensor is adopted Collection offshore crane high speed shaft of gearbox bearing temperature signal, acceleration transducer gathers gear-box internal gear, rotating shaft and axle Hold vibration signal；The data signal that temperature sensor and acceleration transducer gather embeds through multi-channel A/D acquisition interface input The arm processor of formula monitoring means, arm processor is connected with GPRS module by RS232 serial ports；Described data signal is passed through GPRS module is connected into the Internet with base station after communicating, then by the server at long-range monitoring and maintenance center and host computer communication, on The data signal received is stored, by remote temperature trend prediction, remote oscillation by the data memory module in the machine of position Signal fault feature extraction and crude oil sample analysis realize the fault diagnosis of offshore crane gear-box, specific as follows:
Step 1, it is special with vibration signal fault that the fault diagnosis module data signal to receiving carries out temperature data trend prediction Levy extraction and analysis；Meanwhile, taken at regular intervals offshore crane gear-box lubricating oil oil sample carries out oil sample Wear prediction analysis；
Step 2, judges the result of temperature data trend prediction and oil sample Wear prediction analysis:
Temperature data trend prediction, if prediction bearing temperature is maintained in secure threshold, then continues monitoring；If prediction bearing temperature Beyond secure threshold, then prediction bearing breaks down；
Oil sample Wear prediction is analyzed, and taken at regular intervals offshore crane gear-box lubricating oil oil sample carries out conventional physico-chemical properties analysis successively And emission spectrographic analysis, the value if parameter index breaks bounds, then judged result is that prediction is broken down；If parameter index does not has Break bounds value, then use Data Tendency Forecast Based method that abrasive grain content is carried out Data Tendency Forecast Based, if prediction abrasive grain content It is maintained in secure threshold, then continues monitoring oil sample；If prediction abrasive grain content is beyond secure threshold, then judged result is for doping Existing fault；
Step 3, compares temperature data trend prediction and oil sample Wear prediction analysis result, if all predicting gear-box simultaneously Break down, then export fault diagnosis report and gear-box is checked comprehensively；If predicting the outcome difference, then enter step 4 Carry out vibration signal fault signature extraction and analysis,
Step 4, carries out vibration signal fault signature extraction and analysis, if not comprising fault characteristic frequency, then continues monitoring；If comprising Fault characteristic frequency, then judge that gear or bearing break down and export fault diagnosis report.
3. according to the offshore crane Fault Diagnosis of Gear Case method based on multivariate data described in right 2, it is characterised in that step Temperature data trend prediction described in rapid 2, and the Data Tendency Forecast Based of abrasive grain content, specifically comprise the following steps that
(1) from initial data, extract new time series x (t) make 53 smooth pretreatment and obtain
(2) rightSet up GM (1,1) gray model, obtain time series by modelTrend term matching sequence And trend term forecasting sequence
(3) trend term matching sequenceResidual sequence is constituted with the residual error of former sequence x (t)RightBy phase space weight Structure composition residual sequence sample { n, xc, wherein:I is sample sequence Number, l is total sample number, and m is sample Embedded dimensions, by support vector regression model prediction residual sequence:
x ^ c = Σ i = 1 l - m ( α i - α i * ) K ( n t - m , x i ) + b
Wherein K () is kernel function, αi、For the solution of regression model, b is side-play amount；
(4) by anticipation trend item sequenceWith residual sequenceCombination constitutes final forecasting sequence, and divides for trend afterwards Analysis.
4. according to the offshore crane Fault Diagnosis of Gear Case method based on multivariate data described in right 2, it is characterised in that step The conventional physico-chemical properties analysis indexes of oil sample Wear prediction analysis described in rapid 2 includes viscosity, flash-point, burning-point and acidity, launches light Analysis of spectrum includes using Fe, Cu, Al, Pb tenor in wear particle detection equipment test sample fluid.
5. according to the offshore crane Fault Diagnosis of Gear Case method based on multivariate data described in right 2, it is characterised in that step Vibration signal fault signature extraction and analysis described in rapid 4, specifically includes following steps:
(1) the gear-box vibration signal gathered is made empirical mode decomposition, it is thus achieved that all IMF components of signal；
(2) to all IMF component Filtering Processing, remove with the incoherent high frequency noise content of gear-box vibration performance, retain with The frequency content that gear engagement frequency band is relevant；
(3) the IMF Data Whitening after filtering and noise reduction is processed, and ask for autocorrelation matrix M；
(4) to autocorrelation matrix M singular value decomposition, and the IMF component a1 that eigenvalue of maximum is corresponding is found out；
(5) carry out a1 component asking for envelope spectrum as Fourier transformation after Hilbert transform is transformed into time-frequency domain, find out low Whether frequency range comprise amplitude is higher or the spectrum signature of frequency anomaly, and contrasts gear or the bearing fault frequency of Practical Calculation Rate, finds out trouble location.
CN201610475423.8A 2016-06-24 2016-06-24 Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data Pending CN106197996A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610475423.8A CN106197996A (en) 2016-06-24 2016-06-24 Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610475423.8A CN106197996A (en) 2016-06-24 2016-06-24 Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data

Publications (1)

Publication Number Publication Date
CN106197996A true CN106197996A (en) 2016-12-07

Family

ID=57460818

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610475423.8A Pending CN106197996A (en) 2016-06-24 2016-06-24 Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data

Country Status (1)

Country Link
CN (1) CN106197996A (en)

Cited By (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106773988A (en) * 2016-12-30 2017-05-31 西安景辉信息科技有限公司 It is a kind of to be imaged continuous collecting system and acquisition method with gear-box wear particle
CN107270970A (en) * 2017-07-19 2017-10-20 国网新疆电力公司电力科学研究院 Towering power equipment vibration monitoring device and its method for carrying out fault diagnosis
CN107454072A (en) * 2017-07-28 2017-12-08 中国人民解放军信息工程大学 A kind of control methods of multichannel data content and device
CN108415383A (en) * 2018-02-28 2018-08-17 上海士翌测试技术有限公司 Driving intellectualizing system based on Internet of Things
CN108489540A (en) * 2018-03-15 2018-09-04 上海士翌测试技术有限公司 Intelligent Sensing System based on wifi communications
CN108507783A (en) * 2018-03-14 2018-09-07 湖南大学 A kind of combined failure of rotating machinery diagnostic method decomposed based on group
CN108597055A (en) * 2018-04-20 2018-09-28 铨宝工业股份有限公司 Intelligent machine monitoring device with custom tolerance value
CN109724760A (en) * 2018-12-21 2019-05-07 沈阳建筑大学 A kind of detection of derrick crane safe condition and evaluation system
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
CN110059775A (en) * 2019-05-22 2019-07-26 湃方科技(北京)有限责任公司 Rotary-type mechanical equipment method for detecting abnormality and device
CN110070205A (en) * 2019-03-13 2019-07-30 中交广州航道局有限公司 Trend prediction method, device, computer equipment and the storage medium of ship machine dredge pump
CN110069814A (en) * 2019-03-13 2019-07-30 中交广州航道局有限公司 Trend prediction method, device and the computer equipment of ship machine gear-box
CN110108957A (en) * 2019-05-07 2019-08-09 武汉理工大学 A kind of tractor electric fault diagnosis method based on structured analysis method
CN110657985A (en) * 2019-10-11 2020-01-07 重庆邮电大学 Gearbox fault diagnosis method and system based on singular value spectrum manifold analysis
CN110779716A (en) * 2019-11-01 2020-02-11 苏州德姆斯信息技术有限公司 Embedded mechanical fault intelligent diagnosis equipment and diagnosis method
CN110837852A (en) * 2019-10-25 2020-02-25 广州机械科学研究院有限公司 Fault diagnosis method and device for rolling mill gearbox and terminal equipment
CN110849614A (en) * 2018-07-30 2020-02-28 西安英特迈思信息科技有限公司 Intelligent monitoring unit for gearbox of running gear of high-speed locomotive
CN111981111A (en) * 2020-07-31 2020-11-24 江苏国茂减速机股份有限公司 Speed reducer linkage control system and method based on big data
CN112211845A (en) * 2020-10-12 2021-01-12 上海沃克通用设备有限公司 Fan fault diagnosis system
CN112232405A (en) * 2020-10-13 2021-01-15 中车青岛四方机车车辆股份有限公司 Fault prediction, monitoring and diagnosis method of gearbox and corresponding device
CN112393891A (en) * 2020-11-23 2021-02-23 中国农业大学 Wireless monitoring system and method for fatigue damage of key parts of agricultural operation machinery
CN112665856A (en) * 2020-12-16 2021-04-16 华东交通大学 Online monitoring system for gear box
CN113030443A (en) * 2021-02-26 2021-06-25 上海伽易信息技术有限公司 Intelligent monitoring method and judgment model for oil of metro vehicle based on dynamic self-adaptive trend analysis
CN113916531A (en) * 2021-10-26 2022-01-11 辽宁科技学院 Fault diagnosis and prediction system for on-line monitoring of vibration and oil of nuclear power gearbox
CN114184367A (en) * 2021-11-29 2022-03-15 北京唐智科技发展有限公司 Fault diagnosis method, device and equipment for rotary mechanical equipment and readable storage medium
CN114358060A (en) * 2021-12-21 2022-04-15 福建省特种设备检验研究院泉州分院 Fault detection method for crane equipment
CN115410386A (en) * 2022-09-05 2022-11-29 同盾科技有限公司 Short-time speed prediction method and device, computer storage medium and electronic equipment
CN115420501A (en) * 2022-11-04 2022-12-02 山东驰勤机械有限公司 Gearbox running management and control system based on artificial intelligence
CN116296365A (en) * 2023-03-21 2023-06-23 华能酒泉风电有限责任公司 Automatic early warning method and system for abrasion of gear box of wind generating set
CN116572502A (en) * 2023-07-12 2023-08-11 天津联维乙烯工程有限公司 Granulator set detection device
CN117407827A (en) * 2023-12-15 2024-01-16 湖南辉达净化工程有限公司 Abnormal operation data detection method for purification engineering waste gas purification equipment

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4003088B2 (en) * 2006-12-20 2007-11-07 日本精工株式会社 Rotating body abnormality diagnosis method and apparatus
CN101726413A (en) * 2009-12-18 2010-06-09 北京工业大学 Method of fault diagnosis on ball socketed bearing of steel-making converter by comprehensive analysis
CN102692449A (en) * 2012-04-12 2012-09-26 北京工业大学 Fault diagnosis method of blast furnace top gearbox through comprehensive analysis
CN103364189A (en) * 2013-07-15 2013-10-23 中国水利电力物资华南公司 Online fault diagnosis system of wind turbine generator gear case
CN203490073U (en) * 2013-09-16 2014-03-19 成都赛腾自动化工程有限公司 A real-time monitoring system of a wind-driven generator gear case
CN204142289U (en) * 2014-11-04 2015-02-04 河南柏特电气设备有限公司 Blower fan unit on-line monitoring system
CN104697787A (en) * 2015-03-20 2015-06-10 山东大学 Gearbox test bed based on multi-information fusion and detection method thereof
CN104977047A (en) * 2015-07-22 2015-10-14 中国长江三峡集团公司 Wind turbine online condition monitoring and health assessment system and method thereof based on vibration and oil

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4003088B2 (en) * 2006-12-20 2007-11-07 日本精工株式会社 Rotating body abnormality diagnosis method and apparatus
CN101726413A (en) * 2009-12-18 2010-06-09 北京工业大学 Method of fault diagnosis on ball socketed bearing of steel-making converter by comprehensive analysis
CN102692449A (en) * 2012-04-12 2012-09-26 北京工业大学 Fault diagnosis method of blast furnace top gearbox through comprehensive analysis
CN103364189A (en) * 2013-07-15 2013-10-23 中国水利电力物资华南公司 Online fault diagnosis system of wind turbine generator gear case
CN203490073U (en) * 2013-09-16 2014-03-19 成都赛腾自动化工程有限公司 A real-time monitoring system of a wind-driven generator gear case
CN204142289U (en) * 2014-11-04 2015-02-04 河南柏特电气设备有限公司 Blower fan unit on-line monitoring system
CN104697787A (en) * 2015-03-20 2015-06-10 山东大学 Gearbox test bed based on multi-information fusion and detection method thereof
CN104977047A (en) * 2015-07-22 2015-10-14 中国长江三峡集团公司 Wind turbine online condition monitoring and health assessment system and method thereof based on vibration and oil

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
张帅: "风电齿轮箱状态监测与故障诊断***研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 *
张燕: "风电机组齿轮箱故障特征提取技术的研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 *
曹劲然 等: "基于组合核函数OSVR算法的起重机减速齿轮箱磨损趋势预测", 《中国机械工程》 *

Cited By (43)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106773988A (en) * 2016-12-30 2017-05-31 西安景辉信息科技有限公司 It is a kind of to be imaged continuous collecting system and acquisition method with gear-box wear particle
CN107270970A (en) * 2017-07-19 2017-10-20 国网新疆电力公司电力科学研究院 Towering power equipment vibration monitoring device and its method for carrying out fault diagnosis
CN107454072A (en) * 2017-07-28 2017-12-08 中国人民解放军信息工程大学 A kind of control methods of multichannel data content and device
CN107454072B (en) * 2017-07-28 2020-04-17 中国人民解放军信息工程大学 Comparison method and device for multi-channel data content
CN108415383A (en) * 2018-02-28 2018-08-17 上海士翌测试技术有限公司 Driving intellectualizing system based on Internet of Things
CN108507783A (en) * 2018-03-14 2018-09-07 湖南大学 A kind of combined failure of rotating machinery diagnostic method decomposed based on group
CN108489540A (en) * 2018-03-15 2018-09-04 上海士翌测试技术有限公司 Intelligent Sensing System based on wifi communications
CN108597055A (en) * 2018-04-20 2018-09-28 铨宝工业股份有限公司 Intelligent machine monitoring device with custom tolerance value
CN110849614A (en) * 2018-07-30 2020-02-28 西安英特迈思信息科技有限公司 Intelligent monitoring unit for gearbox of running gear of high-speed locomotive
CN109724760A (en) * 2018-12-21 2019-05-07 沈阳建筑大学 A kind of detection of derrick crane safe condition and evaluation system
CN110070205A (en) * 2019-03-13 2019-07-30 中交广州航道局有限公司 Trend prediction method, device, computer equipment and the storage medium of ship machine dredge pump
CN110069814A (en) * 2019-03-13 2019-07-30 中交广州航道局有限公司 Trend prediction method, device and the computer equipment of ship machine gear-box
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
CN110070205B (en) * 2019-03-13 2024-04-26 中交广州航道局有限公司 Ship machine mud pump state prediction method and device, computer equipment and storage medium
CN110108957A (en) * 2019-05-07 2019-08-09 武汉理工大学 A kind of tractor electric fault diagnosis method based on structured analysis method
CN110059775A (en) * 2019-05-22 2019-07-26 湃方科技(北京)有限责任公司 Rotary-type mechanical equipment method for detecting abnormality and device
CN110657985A (en) * 2019-10-11 2020-01-07 重庆邮电大学 Gearbox fault diagnosis method and system based on singular value spectrum manifold analysis
CN110657985B (en) * 2019-10-11 2021-07-06 重庆邮电大学 Gearbox fault diagnosis method and system based on singular value spectrum manifold analysis
CN110837852A (en) * 2019-10-25 2020-02-25 广州机械科学研究院有限公司 Fault diagnosis method and device for rolling mill gearbox and terminal equipment
CN110779716A (en) * 2019-11-01 2020-02-11 苏州德姆斯信息技术有限公司 Embedded mechanical fault intelligent diagnosis equipment and diagnosis method
CN111981111A (en) * 2020-07-31 2020-11-24 江苏国茂减速机股份有限公司 Speed reducer linkage control system and method based on big data
CN112211845A (en) * 2020-10-12 2021-01-12 上海沃克通用设备有限公司 Fan fault diagnosis system
CN112211845B (en) * 2020-10-12 2022-07-19 上海沃克通用设备有限公司 Fan fault diagnosis system
CN112232405A (en) * 2020-10-13 2021-01-15 中车青岛四方机车车辆股份有限公司 Fault prediction, monitoring and diagnosis method of gearbox and corresponding device
CN112232405B (en) * 2020-10-13 2022-09-02 中车青岛四方机车车辆股份有限公司 Fault prediction, monitoring and diagnosis method of gearbox and corresponding device
CN112393891B (en) * 2020-11-23 2024-05-21 中国农业大学 Wireless monitoring system and method for fatigue damage of key parts of agricultural operation machinery
CN112393891A (en) * 2020-11-23 2021-02-23 中国农业大学 Wireless monitoring system and method for fatigue damage of key parts of agricultural operation machinery
CN112665856A (en) * 2020-12-16 2021-04-16 华东交通大学 Online monitoring system for gear box
CN113030443A (en) * 2021-02-26 2021-06-25 上海伽易信息技术有限公司 Intelligent monitoring method and judgment model for oil of metro vehicle based on dynamic self-adaptive trend analysis
CN113916531A (en) * 2021-10-26 2022-01-11 辽宁科技学院 Fault diagnosis and prediction system for on-line monitoring of vibration and oil of nuclear power gearbox
CN114184367A (en) * 2021-11-29 2022-03-15 北京唐智科技发展有限公司 Fault diagnosis method, device and equipment for rotary mechanical equipment and readable storage medium
CN114358060A (en) * 2021-12-21 2022-04-15 福建省特种设备检验研究院泉州分院 Fault detection method for crane equipment
CN114358060B (en) * 2021-12-21 2024-05-28 福建省特种设备检验研究院泉州分院 Crane equipment fault detection method
CN115410386B (en) * 2022-09-05 2024-02-06 同盾科技有限公司 Short-time speed prediction method and device, computer storage medium and electronic equipment
CN115410386A (en) * 2022-09-05 2022-11-29 同盾科技有限公司 Short-time speed prediction method and device, computer storage medium and electronic equipment
CN115420501B (en) * 2022-11-04 2023-01-24 山东驰勤机械有限公司 Gearbox running management and control system based on artificial intelligence
CN115420501A (en) * 2022-11-04 2022-12-02 山东驰勤机械有限公司 Gearbox running management and control system based on artificial intelligence
CN116296365B (en) * 2023-03-21 2023-10-03 华能酒泉风电有限责任公司 Automatic early warning method and system for abrasion of gear box of wind generating set
CN116296365A (en) * 2023-03-21 2023-06-23 华能酒泉风电有限责任公司 Automatic early warning method and system for abrasion of gear box of wind generating set
CN116572502B (en) * 2023-07-12 2023-09-19 天津联维乙烯工程有限公司 Granulator set detection device
CN116572502A (en) * 2023-07-12 2023-08-11 天津联维乙烯工程有限公司 Granulator set detection device
CN117407827A (en) * 2023-12-15 2024-01-16 湖南辉达净化工程有限公司 Abnormal operation data detection method for purification engineering waste gas purification equipment
CN117407827B (en) * 2023-12-15 2024-02-13 湖南辉达净化工程有限公司 Abnormal operation data detection method for purification engineering waste gas purification equipment

Similar Documents

Publication Publication Date Title
CN106197996A (en) Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data
CN111043023B (en) Fracturing pump on-line monitoring and fault diagnosis system
CN102494899B (en) Composite fault diagnosis method for diesel engine and diagnosis system
Zhe et al. Pitting damage levels estimation for planetary gear sets based on model simulation and grey relational analysis
CN102707037B (en) On-line monitoring system for diesel lubrication oil
Zhang et al. Dynamic condition monitoring for 3D printers by using error fusion of multiple sparse auto-encoders
Li et al. Bearing fault feature selection method based on weighted multidimensional feature fusion
CN101059130A (en) On-line remote state monitoring and fault analysis diagnosis system of reciprocating compressor
CN102736562B (en) Knowledge base construction method oriented to fault diagnosis and fault prediction of numerical control machine tool
CN102155988A (en) Equipment monitoring and diagnosing method
CN110398362B (en) Robot RV reducer fault diagnosis and positioning method
Cao et al. Deterioration state diagnosis and wear evolution evaluation of planetary gearbox using vibration and wear debris analysis
CN110174281A (en) A kind of electromechanical equipment fault diagnosis method and system
CN114201831A (en) Rolling bearing working condition quantitative analysis method based on vibration signal real-time acquisition
CN110056640A (en) Speed reducer wireless malfunction diagnostic method based on acceleration signal and edge calculations
CN202661269U (en) Compound fault diagnosis test platform of diesel engine
Alsalaet et al. Bearing fault diagnosis using normalized diagnostic feature-gram and convolutional neural network
CN112487709B (en) Marine diesel engine fault tracing method based on sensitivity analysis
CN112686279B (en) Gear box fault diagnosis method based on K-means clustering and evidence fusion
Li et al. Instantaneous angular speed-based fault diagnosis of multicylinder marine diesel engine using intrinsic multiscale dispersion entropy
Liu et al. An interpretable multiplication-convolution network for equipment intelligent edge diagnosis
KR100749667B1 (en) System and method for engine condition diagnosis from crankshaft angular speed
CN112380782A (en) Rotating equipment fault prediction method based on mixed indexes and neural network
CN115510914B (en) Intelligent diagnosis method and system for faults of gate and supporting running piece
CN114184375A (en) Intelligent diagnosis method for common faults of gear box

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20161207

RJ01 Rejection of invention patent application after publication