EP4185853A1 - Verfahren zur fehlererkennung bei einem antrieb - Google Patents
Verfahren zur fehlererkennung bei einem antriebInfo
- Publication number
- EP4185853A1 EP4185853A1 EP21797957.4A EP21797957A EP4185853A1 EP 4185853 A1 EP4185853 A1 EP 4185853A1 EP 21797957 A EP21797957 A EP 21797957A EP 4185853 A1 EP4185853 A1 EP 4185853A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- spectrum
- frequency
- peak
- recognized
- pattern
- 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
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/028—Acoustic or vibration analysis
-
- 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
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
Definitions
- the invention relates to a method for detecting faults in a drive.
- a drive has, for example, an electric machine, a gear, a V-belt, a power converter, etc. on .
- the drive also has one or more bearings, for example.
- the warehouse or the bearings are in particular part of the electrical machine of the transmission, etc.
- the electric machine is, for example, a high-voltage electric motor.
- Such motors are used, for example, in many manufacturing industries. Timely maintenance of these machines is a key aspect in order to ensure uninterrupted operation and service of such systems for the customer. to provide service.
- One goal can be, for example, to identify mechanical faults in the moving elements of an electric motor at an early stage and to offer the operator of a system or an engine or alert a service team in time to avoid any unplanned machine downtime or to avoid the plant.
- EP1304463B1 discloses a method for monitoring the condition of a bearing arranged at one end of a rotatable shaft, a vibration sensor monitoring the bearing being arranged at the other end of the rotatable shaft, but in the vicinity thereof.
- a broadband signal is determined by the vibration sensor, by means of which the bearing is monitored for a defect.
- a vibration sensor for monitoring the state of a rotating component is known from US7231303B2.
- Evaluation electronics available for this purpose have an analog-to-digital converter and a signal conditioning device a multiplicity of signals that were detected by the sensor element and can thus be diagnosed.
- a signal processing device for processing machine vibrations is known from US Pat. No. 5,895,857A.
- a peak detector is used to determine peaks in vibration amplitude during predetermined sampling periods.
- One object of the invention is to improve fault detection in a drive.
- a solution to the problem results from a method according to claim 1 .
- Configurations result, for example, according to claims 2 to 13 .
- the task is solved by a computer program product according to claim 14 .
- the advantages and configurations listed below in relation to the method can be transferred analogously to the computer program and the computer program product.
- a normalized spectrum is determined, a normalized frequency spectrum.
- the error detection does not only relate to an error, for example, but also wear of a component or wear of several components of a drive.
- the component is, for example, a bearing, a clutch and/or a gear. Wear and tear can also be referred to as an error, in particular above a threshold value. Not every error automatically leads to a shutdown of the drive, for example. Examples of actions in the event of a fault are reducing the maximum speed, reducing the maximum acceleration, reducing the maximum load on the bearing and/or gear, scheduling a repair and/or replacement of the faulty bearing and/or gear.
- the spectrum concerns, for example, a velocity, a derivative of the velocity (in particular a ne acceleration), a vibration (whereby a vibration can also be dependent on a speed), or . Values of the same or similar kind.
- Speed affects, for example, the speed of a bearing, a gearbox, a motor, a generator, a clutch, etc.
- the vibration concerns, for example, the vibration of a bearing, a transmission, an engine, a generator, a clutch, etc.
- the vibration is recorded, for example, by means of a vibration sensor, with the vibration being recorded in particular on a housing or within a transmission.
- the vibration is caused in particular by a movement.
- the movement relates in particular to a rotary movement, ie also to a speed (in particular a rotary speed).
- a bearing error can, for example, cause a vibration when a component rotates by means of the bearing. This vibration is therefore also dependent on a speed, the number of revolutions.
- the spectrum is advantageously standardized.
- a threshold such as e.g. B. a minimum value, independent of the place of use and/or the time of use of the method, to be changed . This applies, for example, to the use of the method in different types of bearings.
- the normalization also results in an advantage when considering at least one or more peak values within the spectrum.
- a normalized spectrum is determined, which depends on a speed, with peak values in the spectrum being detected, with a first peak being detected at a first frequency, with a second peak being detected at a second frequency, based on the first frequency and a pattern is detected on the second frequency. Peaks in a spectrum can also be referred to as peaks.
- this is based on the detection of frequency ratios, i.e. in particular the x Frequencies of different peak values (maxima) .
- the disadvantage of narrow bandpass filters for detecting a single maximum can thus be avoided.
- a normalized speed spectrum can therefore be determined, with a first peak value being detected and with a first pattern being detected.
- the speed is a speed, for example.
- errors can be detected.
- a peak value is detected or detected a pattern that differs from normal operation. The deviation can result from an error.
- a fault in a drive belt such as a belt misalignment, can also be detected.
- an error in a bearing in order to detect an error in a bearing, it can be stored as a function of a specific bearing and as a function of a specific error pattern, and this stored error pattern can be recognized.
- this consideration of predetermined frequency ranges succeeds, for example, through the use of bandpasses. With this approach, an error is only detected if the peak values fall within the bandpass range.
- the band-pass filters are used to identify the error pattern. So shift the frequencies, z. B. due to external influences, an error is no longer recognized.
- the pattern relates to the frequencies and/or the amplitudes of the peak values, with the frequencies in particular being multiples of one another.
- a peak value can be identified in which it exceeds a minimum value, for example.
- the so identi fi ed resp. detected peak has an associated frequency .
- a frequency of a peak value can thus be a multiple of a further frequency of a further peak value.
- Patterns result in particular from the fact that multiples of frequencies are recognized which are each associated with peak values. In this way, an error pattern can be recognized even if the pattern of this error shifts in the frequency range.
- the peak value or the peak values are recognized by exceeding a first minimum value (threshold value or limit value).
- the first minimum or other minimum values can be set, for example.
- At least one of the peak values has lateral peak values in sidebands, with the lateral peak values in particular being recognized by exceeding a second minimum value.
- the peak values of side walls can therefore contribute in particular to identifying a defect and can be part of a pattern.
- the pattern is therefore also recognized as a function of lateral peak values in sidebands. This contributes to the certainty of detecting an error since a more complex pattern can be detected.
- a large number of patterns are stored, with a large number of patterns being assigned at least one error in each case.
- different errors can be recognized by different patterns.
- a large number of errors can also be associated with a pattern.
- a large number of patterns can also be assigned to an error. This can improve the detection of the error, for example.
- a fault relates to wear. Wear of a bearing, gearing and/or a clutch can also be recognized in particular. From this, for example, an exchange or maintenance of a bearing, gear and/or a clutch can be planned.
- a normalized acceleration spectrum and/or a normalized speed spectrum is determined as the spectrum, with different patterns being recognized in particular in different spectra.
- a suitable spectrum can advantageously be considered.
- a normalized acceleration envelope curve spectrum is determined, with a second peak value being recognized and with a second pattern also being recognized. For example, a bearing error and / or an error in a transmission, or a gear element can be recognized.
- a vibration analysis is carried out in the frequency range of the spectrum using the normalized speed spectrum.
- a vibration analysis is carried out in the frequency range of the spectrum using a normalized acceleration envelope.
- a vibration analysis in the frequency range is carried out using the normalized speed spectrum.
- errors can be detected that are associated with a machine, such as e.g. B. an alignment error or loosening a fastening of the machine.
- a vibration analysis in the frequency range is carried out using a spectrum of the normalized acceleration envelope.
- the vibration analysis in the frequency domain is carried out in particular on the basis of expert knowledge (with the help of bearing information) using spectra of the normalized acceleration envelope in order to detect faults that belong to a bearing element.
- statistical inference is applied to time domain statistics such as skewness and kurtosis. In this way it is possible to detect abnormal behavior in the vibration signal.
- artificial intelligence is used to recognize a pattern.
- Such an artificial intelligence is in particular trainable.
- Information about the drive such as rated power, peak power, rated speed, maximum speed, etc., can be used for training. be used with .
- an operating state of the drive is used for error detection. For example, a distinction can be made as to whether vibrations occur at a standstill, during an acceleration phase or only at high speeds. Depending on these operating conditions, a frequency spectrum can then be analyzed.
- the vibration analysis is performed on the vibration data that is recorded by vibration sensors that are mounted on the drive side and on the operator side of the machine.
- the sensors can z. B. can be mounted in different orientations in relation to the axis of rotation of the motor: axial, vertical or horizontal.
- the vibration analysis can based on a simple thresholding of KPIs in the time domain, e.g. B. RMS value , crest factor, peak-to-peak , kurtosis and skewness . It is also possible, for example, to base the vibration analysis on a spectral analysis, with the vibration signal being transformed in the time domain into the frequency domain and analyzed.
- predefined ranges of the spectra associated with bearing failures can be monitored and if the spectral peaks of this range are above the set threshold, a failure can be detected and reported.
- Key information of the spectral ranges that belong to rolling bearing defects can be taken from rolling bearing data sheets, for example.
- a vibration analysis tool receives vibration data. Such vibration data can be evaluated in the tool by calculations.
- the vibration analysis tool is, for example, at the location of the monitored machine or at a distance from this location, so that the data required for this is transmitted to the vibration analysis tool, for example via the Internet.
- the calculation relates, for example, to vibration spectra in the frequency domain, vibration statistics in the time domain and/or operating states of the monitored machine.
- Vibration spectra in the frequency domain velocity and acceleration envelope spectra
- time-domain statistics such as expected value, variance, skewness and/or kurtosis, operating states of the machine, which are defined in particular on the basis of the speed and torque of the machine at a given point in time.
- important asset information such as storage type, application de- tails , such as B. Gear drive, belt drive, stored and used in the analysis of the measured actual values such as speed or vibration.
- engine damage detection can use this data to detect errors that belong to various moving elements of the electrical machine, such as e.g. B. Bearing elements, belts or gears.
- spectra of recorded data or Actual values normalized (normalized) in relation to amplitude and speed in order to obtain amplitude-normalized order spectra are spectra of recorded data or Actual values normalized (normalized) in relation to amplitude and speed in order to obtain amplitude-normalized order spectra.
- a normalization algorithm can be made robust with respect to different operating states.
- the amplitude normalization is based on a spectral z-weighting.
- At least two of the steps listed below are used in parallel, since they are independent of one another: a) Carrying out a vibration analysis based on expert knowledge in the frequency range using normalized speed spectra in order to detect errors that belong to the machine, such as e.g. B. Alignment error, loosening, b ) perform frequency domain vibration analysis based on expert knowledge (using bearing information) on normalized acceleration envelope spectra to detect errors associated with the bearing element c ) perform statistical inference based on time domain statistics such as Skewness and buckling to detect abnormal behavior in the vibration signal.
- Steps [a-c] are steps for detecting bearing failures in a machine using vibration analysis.
- the peak and pattern recognition module used to identify peak values and patterns is not only robust to deviations in the bearing information, but also offers the possibility of detecting bearing defects if there is no bearing information.
- the peak and pattern recognition module also enables the detection of non-bearing faults such as belt misalignment and/or a defective gear.
- the module uses the vibration spectrum as an input signal to identify peak values and patterns. In particular, it applies a threshold to the spectrum and removes smaller, less prominent peaks, since these peaks contain no information about the errors.
- one of the prominent peaks contains integer multiple harmonics. This is done with all peaks in particular. Peaks are formed which do not contain harmonics or when the peak is already a harmonic of a conspicuous lower order peak. This is how you get peaks with harmonics. Peaks with harmonics can indicate an error. Once these peaks are identified, a type of error can be narrowed down by evaluating the spectral patterns around these peaks and their harmonics.
- the results from [a-e] are compared with the help of expert knowledge or analyzed by an artificial intelligence in order to draw conclusions about a possible defect and its severity.
- engine damage detection is triggered in good time, for example, if all of the above-mentioned steps in section [ae] are carried out.
- the output can be a visual graphic for an operator. It is also possible, for example, to generate a detailed report with detailed graphics and historical analysis.
- bearing information for its functionality can be dispensed with in an automated vibration analysis in the frequency range.
- the analysis is no longer dependent on knowledge of precise bearing error frequencies.
- bearing information is inaccurate or unavailable, which could have resulted in poor performance or a complete failure to detect faulty bearing elements.
- the method described does not require a large amount of training data. The method described provides a robust technique for overcoming the dependency on inventory information.
- One of the methods described makes it possible, for example, to monitor very old machines for which the storage information is not available. Using one of the methods described, it is possible to obtain reliable information about the state of health of the system and/or to provide timely information about a potential defect.
- actual values or values derived therefrom are transmitted via the Internet and an analysis of the data is made possible using a cloud application.
- this is provided in a suitable Python environment on scalable instances by means of a cloud application, ie web-based.
- a cloud application ie web-based.
- This has the advantage of enabling process automation.
- the method is implemented, for example, by algorithms based on expert knowledge and pattern mining.
- a combination of different techniques is used.
- these are: a) statistical derivation of time-domain-based KPIs from vibration data, b) vibration analysis in the frequency domain using a predefined spectral threshold calculation based on expert knowledge (threshold calculation to define a faulty and non-faulty state) and bearing information, c) spectral thresholding of peak patterns , which were obtained from the detection of novel peak and pattern recognition, which is developed in particular on the basis of expert knowledge.
- a final decision is based on the combined results of a, b, and c.
- the algorithm in the absence of storage information, relies on (a, c) to make a decision.
- the algorithm uses (a,b,c) to make a decision.
- main maxima are detected in a spectrum.
- secondary maxima are detected, each of which represents a sideband of a main maximum. From the pattern of the main maxima and secondary maxima, an analysis device draws conclusions about a specific error. In particular, this analysis device has an artificial intelligence.
- a computer program product can be provided which has computer-executable program means and, when executed on a computer device with processor means and data storage means, is suitable for carrying out a method according to one of the types described. In this way, an underlying task can be solved by a computer program product that can also be used to simulate operating behavior.
- the computer program product is intended in particular for installation on a computing unit assigned to a control device, with the computer program product being designed to carry out the method described when it is executed on the computing unit.
- the representation according to FIG. 1 shows an electric motor 1 and a sensor 2 for recording actual values.
- the actual values are received by an analysis device 3 and a spectrum 4 is formed.
- a pattern of main maxima ie the essential maxima
- patterns of sidebands are recognized.
- errors are detected on the basis of the previous steps (pattern of the main maxima and of the sidebands).
- Such defects can be classified into types of bearing defects.
- Such guys are for example: bearing inner ring, bearing outer ring, rotating element of the bearing, cage, defective gearbox, defective drive belt.
- FIG. 2 shows a first case with a spectral analysis.
- FIG. 2 shows theoretical and practical error patterns in the event of an error in a position element.
- a spectrum is shown in three areas 10 , 11 and 12 , these areas relating to a theoretical representation 13 .
- Area 10 relates to a specific speed.
- Area 11 relates to an acceleration.
- Region 12 relates to high frequencies. This then results in a spectrum for the speed 8 and a spectrum for the acceleration 9.
- BPFO All Pass Frequency Outer Race/ball bearing outer ring frequency
- FIG. 3 shows a second case with a spectral analysis.
- FIG. 3 shows spectra and error patterns in a BPFI (Ball Pass Frequency Inner Race/ball bearing inner ring frequency). Shown are main maxima 15 and 17, ie peak values, and their associated sidebands 16 and 16' with the lateral peak values for the main maximum BPFI and sidebands 18 and 18' for the further main maximum 17 with 2 ⁇ BPFI. This makes it clear that certain errors or error sources can be inferred based on a pattern of a frequency analysis.
- BPFI Bit Pass Frequency Inner Race/ball bearing inner ring frequency
- the representation according to FIG. 4 shows a third case with a spectral analysis.
- This third case concerns the ball spin (BS), ie in particular the BSF (Ball Spin Frequency). So there may be a defect in the balls of a ball bearing. It can be seen that here through the sidebands (FT) the pattern of the maxima has experienced an additional expression.
- BS ball spin
- BSF Bit Spin Frequency
- a fault can consequently be detected by spectral pattern recognition.
- the spectral pattern recognition is based on the recognition of maxima, in particular main maxima, and the recognition of maxima next to the sidebands of the main maxima.
- defects in a bearing can be assigned to a class of defects. In particular, these are defects in the area of the outer ring, defects in the area of the inner ring and/or defects in the balls of a ball bearing. This also applies accordingly to barrel bearings or needle bearings or the like.
- the representation according to FIG. 5 shows a further spectral analysis with a frequency range 25, which can be set, for example, with a bandpass filter.
- the frequency range 25 has a lower frequency 29 and an upper frequency 30 .
- the normalized amplitude x(f) is plotted with its absolute value over the frequency f [Hz]. Peak values 34, 35, 36, 38 and 39 are shown, these being recognized when a minimum value 25 is exceeded. For example, a peak 40 does not exceed this minimum value 25 and thus does not qualify as a peak for pattern recognition.
- the peaks 34, 35, 36, 38 and 39 are assigned frequencies 21, 22, 23, 31, 32 and 33, respectively.
- Bandpass filters 26, 27 and 28 are also shown. Frequency 22 is, for example, twice the frequency of frequency 21.
- Frequency 23 is, for example, three times the frequency of frequency 21. In this way, a pattern can be recognized which is based on recognizing a multiple of a frequency .
- the band-pass filters can also be arranged in relation to a multiple. However, if the spectrum shifts, errors can no longer be detected with fixed bandpasses if the peak values are outside the observed frequency range. By avoiding these narrow bandpass filters to detect a particular peak, the error detection method is tolerable. ranter .
- the error detection can be improved by patterns which are based on the detection of frequency ratios.
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP20202126.7A EP3985377A1 (de) | 2020-10-15 | 2020-10-15 | Verfahren zur fehlererkennung bei einem antrieb |
| PCT/EP2021/078482 WO2022079185A1 (de) | 2020-10-15 | 2021-10-14 | Verfahren zur fehlererkennung bei einem antrieb |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4185853A1 true EP4185853A1 (de) | 2023-05-31 |
Family
ID=72964446
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP20202126.7A Withdrawn EP3985377A1 (de) | 2020-10-15 | 2020-10-15 | Verfahren zur fehlererkennung bei einem antrieb |
| EP21797957.4A Pending EP4185853A1 (de) | 2020-10-15 | 2021-10-14 | Verfahren zur fehlererkennung bei einem antrieb |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP20202126.7A Withdrawn EP3985377A1 (de) | 2020-10-15 | 2020-10-15 | Verfahren zur fehlererkennung bei einem antrieb |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US12379283B2 (de) |
| EP (2) | EP3985377A1 (de) |
| CN (1) | CN116438433A (de) |
| WO (1) | WO2022079185A1 (de) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102024000245A1 (de) * | 2024-01-25 | 2025-07-31 | Oerlikon Textile Gmbh & Co. Kg | Aufwickelvorrichtung zum Aufwickeln eines Spinnfadens |
Family Cites Families (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2045751C1 (ru) | 1992-11-25 | 1995-10-10 | Санкт-Петербургский опытный завод "Прибор" | Устройство для сигнализации предельных параметров вибрации |
| US5895857A (en) | 1995-11-08 | 1999-04-20 | Csi Technology, Inc. | Machine fault detection using vibration signal peak detector |
| US5852793A (en) * | 1997-02-18 | 1998-12-22 | Dme Corporation | Method and apparatus for predictive diagnosis of moving machine parts |
| US5922963A (en) * | 1997-06-13 | 1999-07-13 | Csi Technology, Inc. | Determining narrowband envelope alarm limit based on machine vibration spectra |
| US5875420A (en) * | 1997-06-13 | 1999-02-23 | Csi Technology, Inc. | Determining machine operating conditioning based on severity of vibration spectra deviation from an acceptable state |
| US6711952B2 (en) | 2001-10-05 | 2004-03-30 | General Electric Company | Method and system for monitoring bearings |
| EP1502086A2 (de) | 2002-04-13 | 2005-02-02 | I-For-T Gmbh | Schwingungssensor und verfahren zur zustands berwachung von rotierenden bauteilen und lagern |
| US6999884B2 (en) * | 2003-01-10 | 2006-02-14 | Oxford Biosignals Limited | Bearing anomaly detection and location |
| RU2379645C2 (ru) | 2007-06-19 | 2010-01-20 | Андрей Павлович Ушаков | Способ диагностики технического состояния деталей, узлов и приводных агрегатов газотурбинного двигателя и устройство для его осуществления |
| RU2475717C2 (ru) | 2009-12-28 | 2013-02-20 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Пятигорский государственный гуманитарно-технологический университет" | Способ диагностирования двигателя внутреннего сгорания и диагностический комплекс для его осуществления |
| PT2581724T (pt) * | 2011-10-13 | 2020-05-07 | Moventas Gears Oy | Método e sistema para efeitos de monitorização do estado de caixas de velocidades |
| US10416126B2 (en) * | 2013-07-02 | 2019-09-17 | Computational Systems, Inc. | Machine fault prediction based on analysis of periodic information in a signal |
| RU2578044C1 (ru) | 2014-11-14 | 2016-03-20 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Ижевский государственный технический университет имени М.Т. Калашникова" | Устройство диагностирования и оценки технического состояния мехатронных приводов |
| US20160245686A1 (en) * | 2015-02-23 | 2016-08-25 | Biplab Pal | Fault detection in rotor driven equipment using rotational invariant transform of sub-sampled 3-axis vibrational data |
| GB2543521A (en) * | 2015-10-20 | 2017-04-26 | Skf Ab | Method and data processing device for severity assessment of bearing defects using vibration energy |
| US10754334B2 (en) * | 2016-05-09 | 2020-08-25 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for industrial internet of things data collection for process adjustment in an upstream oil and gas environment |
| CN109477774A (zh) * | 2016-07-27 | 2019-03-15 | 富士通株式会社 | 异常检测程序、异常检测装置、以及异常检测方法 |
| DE102018210470A1 (de) * | 2018-06-27 | 2020-01-02 | Robert Bosch Gmbh | Verfahren zur Schadensfrüherkennung, sowie Programm und Steuergerät zum Ausführen des Verfahrens |
| JP2021532355A (ja) * | 2018-07-24 | 2021-11-25 | フルークコーポレイションFluke Corporation | 音響画像にタグを付けて関連付けるためのシステム及び方法 |
| US11506569B2 (en) * | 2019-01-15 | 2022-11-22 | Computational Systems, Inc. | Bearing and fault frequency identification from vibration spectral plots |
-
2020
- 2020-10-15 EP EP20202126.7A patent/EP3985377A1/de not_active Withdrawn
-
2021
- 2021-10-14 EP EP21797957.4A patent/EP4185853A1/de active Pending
- 2021-10-14 CN CN202180070801.3A patent/CN116438433A/zh active Pending
- 2021-10-14 WO PCT/EP2021/078482 patent/WO2022079185A1/de not_active Ceased
- 2021-10-14 US US18/031,095 patent/US12379283B2/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN116438433A (zh) | 2023-07-14 |
| WO2022079185A1 (de) | 2022-04-21 |
| US12379283B2 (en) | 2025-08-05 |
| US20230375440A1 (en) | 2023-11-23 |
| EP3985377A1 (de) | 2022-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102016105877B4 (de) | Verfahren und Vorrichtung zur Überwachung einer Maschine | |
| DE69937737T2 (de) | Beurteilung des zustands eines lagers | |
| DE102011117468B4 (de) | Verfahren, Recheneinheit und Einrichtung zur Überwachung eines Antriebstrangs | |
| EP2937560A1 (de) | Windenergieanlagen-diagnosevorrichtung für generatorkomponenten | |
| DE112017001631T5 (de) | Zustandsüberwachungssystem eines Getriebes und Zustandsüberwachungsverfahren | |
| DE19917541B4 (de) | Verfahren zur Fehlerdiagnose | |
| EP2402731A1 (de) | Verfahren zum Training eines Systems zur Klassifikation eines Wälzlagerzustands sowie Verfahren zur Klassifikation eines Wälzlagerzustands und System zur Klassifikation eines Wälzlagerzustands | |
| EP3517927B1 (de) | Verfahren und vorrichtung zur früherkennung eines risses in einem radsatz für ein schienenfahrzeug | |
| DE112019001115B4 (de) | Diagnoseunterstützungsvorrichtung, rotierendes Maschinensystem und Diagnoseunterstützungsverfahren | |
| DE112017000950T5 (de) | Abnormalitäts-Diagnosevorrichtung und Abnormalitäts-Diagnoseverfahren | |
| DE112021005667T5 (de) | Verfahren und Einrichtung zum Erkennen von Anomalien in einer mechanischen Einrichtung oder einem mechanischen Bauteil | |
| EP3100064B2 (de) | Vorrichtung sowie verfahren zur fehlererkennung in maschinen | |
| CH717054A2 (de) | Verfahren zur Diagnose eines Lagers. | |
| DE19707173C5 (de) | Maschinendiagnosesystem und Verfahren zur zustandsorientierten Betriebsüberwachung einer Maschine | |
| EP4185853A1 (de) | Verfahren zur fehlererkennung bei einem antrieb | |
| DE4017448A1 (de) | Verfahren zur diagnose der mechanischen eigenschaften von maschinen | |
| DE102013205353B4 (de) | Verfahren zum Warten einer Maschine der Tabak verarbeitenden Industrie, und entsprechend eingerichtete Maschine | |
| DE102009024981A1 (de) | Verfahren zur Ermittlung und Analyse von Schäden an umlaufenden Maschinenelementen | |
| DE102015210911A1 (de) | Verfahren und Vorrichtung zum Erkennen von Veränderungen in einem elektrisch betriebenen Antrieb | |
| DE19800217A1 (de) | Verfahren zur automatisierten Diagnose von Diagnoseobjekten | |
| DE102010005049B4 (de) | Verfahren zum Erkennen von Fehlern in hydraulischen Verdrängermaschinen | |
| LU508341B1 (de) | Verfahren zur Überwachung und/oder Analyse des Zustands eines Antriebssystems | |
| DE102021214406B3 (de) | Verfahren zum Detektieren von bekannten Fehlerursachen an EOL-Prüfständen | |
| DE112023006159T5 (de) | Wälzlager und Wälzlager-Diagnoseeinrichtung | |
| EP4323731A1 (de) | Verfahren und system zur überwachung eines vorrichtungszustands einer vorrichtung |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20230223 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: INNOMOTICS GMBH |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20251008 |