WO2022064769A1 - Système et procédé de prédiction d'état de dégradation - Google Patents

Système et procédé de prédiction d'état de dégradation Download PDF

Info

Publication number
WO2022064769A1
WO2022064769A1 PCT/JP2021/019620 JP2021019620W WO2022064769A1 WO 2022064769 A1 WO2022064769 A1 WO 2022064769A1 JP 2021019620 W JP2021019620 W JP 2021019620W WO 2022064769 A1 WO2022064769 A1 WO 2022064769A1
Authority
WO
WIPO (PCT)
Prior art keywords
deterioration
input
auxiliary
derivation unit
main
Prior art date
Application number
PCT/JP2021/019620
Other languages
English (en)
Japanese (ja)
Inventor
健一 福井
正嗣 北井
Original Assignee
国立大学法人大阪大学
Ntn株式会社
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 国立大学法人大阪大学, Ntn株式会社 filed Critical 国立大学法人大阪大学
Publication of WO2022064769A1 publication Critical patent/WO2022064769A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
    • 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N17/00—Investigating resistance of materials to the weather, to corrosion, or to light

Definitions

  • the present invention relates to a deterioration status prediction system that predicts a deterioration status indicating the degree of progress of deterioration with respect to the operation limit of an operation mechanism in which two members operate relatively in a contact state, and a deterioration status prediction method.
  • the deterioration status of the operating mechanism in which the first member and the second member operate relatively shows the degree of deterioration from the middle of use to the limit of use. , Is estimated using a regression model.
  • Patent Document 1 describes a method of estimating the remaining life, which is one of the deterioration states of bearings, based on the feature amount obtained from the vibration sensor.
  • Patent Document 2 describes a method of performing training by machine learning in association with a state variable calculated from sensor output data with a degree of failure to predict a failure.
  • Patent Document 2 describes a recursive regression model as an example of a regression model for estimating the remaining life.
  • the recursive regression model is to accurately estimate the remaining life, operating conditions are used. It is difficult to apply it to the estimation of the remaining life in actual operation because it is necessary to keep the surrounding environment constant and measure at regular intervals.
  • the present invention has been made in view of the above problems, and is a deterioration status prediction system capable of estimating the deterioration status up to the operation limit with high accuracy even in an operation mechanism in which the change tendency of the deterioration status including the remaining life is not constant, and deterioration.
  • the purpose is to provide a situation prediction method.
  • the deterioration status prediction system which is one of the present inventions, is a deterioration status indicating the degree of progress of deterioration with respect to the operation limit of the first member and the operation mechanism in which the second member operates relatively.
  • This is a deterioration status prediction system that predicts the deterioration status of multiple measurement timings.
  • a training unit that trains a multi-regression model using the deterioration status at the operation limit of the learning operation mechanism, a main input derived by the main input derivation unit based on the evaluation operation mechanism that has not reached the operation limit, and An auxiliary input derived by the auxiliary input derivation unit is used as an input, and a deterioration status derivation unit for deriving the deterioration status of the evaluation operation mechanism by the multi-regression model trained by the training unit is provided.
  • the deterioration status prediction method which is one of the present inventions, shows the degree of progress of deterioration with respect to the operation limit of the first member and the operation mechanism in which the second member operates relatively. It is a deterioration status prediction method that predicts the deterioration status.
  • the main input derivation unit derives the main input indicating the deterioration of the operating mechanism at each of multiple measurement timings, and the deterioration data related to the deterioration status at multiple measurement timings is obtained.
  • the auxiliary input derivation unit derives the auxiliary inputs arranged in time series, operates the learning operation mechanism to the operation limit, and returns the main input at multiple measurement timings up to the operation limit and the multi-input with the auxiliary input as the input.
  • the multi-regression model which is a model, is trained by the training unit using the deterioration status at the operation limit of the learning operation mechanism, and the main input derived by the main input derivation unit based on the evaluation operation mechanism that has not reached the operation limit.
  • the auxiliary input derived by the auxiliary input derivation unit is used as an input, and the deterioration status derivation unit derives the deterioration status of the evaluation operation mechanism by the multi-regression model trained by the training unit.
  • the deterioration status of the operation mechanism in which the reduction tendency of the deterioration status is not constant is accurately determined by using the multi-regression model by the input obtained by merging the main input and the auxiliary input considering the reduction tendency of the deterioration status. Can be estimated.
  • FIG. 1 It is a figure which shows the main part of the learning information generation apparatus which concerns on embodiment It is a side view. It is a block diagram which shows the structure of the deterioration situation prediction system which concerns on embodiment. It is a figure which shows the main input, auxiliary input, and multi-regression model which concerns on embodiment. It is a figure which shows the main input, the auxiliary input, and another 1st example of a multi-regression model. It is a figure which shows the main input, the auxiliary input, and another second example of a multi-regression model.
  • the deterioration status prediction system 100 is a system that predicts the deterioration status indicating the degree of progress of deterioration with respect to the operation limit at which the operation mechanism cannot exert a predetermined function as a mechanical element.
  • the type of the operating mechanism is not particularly limited as long as the first member and the second member operate relatively in a contact state.
  • a rolling bearing is exemplified as an operating mechanism including the first member and the second member.
  • the rolling element of the rolling bearing is exemplified as the first member
  • the inner ring of the rolling bearing is exemplified as the second member.
  • the combination of the first member and the member adopted as the second member is arbitrary.
  • the motion mechanism used for learning is referred to as a learning motion mechanism 200
  • the first member included in the learning motion mechanism 200 is referred to as a learning first member 201
  • the second member is referred to as a learning second member 202.
  • the motion mechanism to be predicted is described as an evaluation motion mechanism (not shown)
  • the first member included in the evaluation motion mechanism is referred to as an evaluation first member
  • the second member is referred to as an evaluation second member.
  • FIG. 1 is a diagram showing a main part of the learning information generator according to the embodiment, the figure shown in the part (a) is a front view of the learning information generator, and the figure shown in the part (b) is the part (a). It is a cross-sectional side view corresponding to.
  • the learning information generation device 300 includes a fixing member 305 for holding and fixing the learning operation mechanism 200, and a shaft body 301.
  • the shaft body 301 is connected to the drive device 302, and the drive device 302 is connected to the drive control device 330.
  • the fixing member 305 has a structure that supports the learning operation mechanism 200, and is independent of the shaft body 301.
  • the shaft body 301 is not particularly limited in terms of material and length as long as it has a shape that fits the inner ring of the learning motion mechanism 200, but it may be matched as much as possible to the actual usage mode of the evaluation motion mechanism. preferable.
  • the learning operation mechanism 200 is a rolling bearing to be measured.
  • the learning operation mechanism 200 is not limited as described above, but in the case of the present embodiment, the learning operation mechanism 200 is a roller bearing.
  • deterioration is caused by using an operating mechanism, and “deficiency” is described as one of “deterioration”. Further, “deterioration” includes, for example, fatigue peeling, fatigue damage, deterioration of lubricating oil, surface roughness due to sealing failure, and the like.
  • Information indicating deterioration used for the main input includes peeling, wear, indentation, flaking, seizure, etc., and the surface of the first member or the second member due to sliding between the first member and the second member, rolling sliding, etc.
  • An image showing a defect generated on the surface and data showing a defect quantitatively can be exemplified.
  • the information indicating deterioration includes vibration, sound, and the like generated in the operating mechanism during operation. Specifically, in one-dimensional information such as the length and width of the area where the defect has occurred, two-dimensional information such as the area, three-dimensional information such as the size, or information related to these, images, etc. be.
  • deterioration of members other than the operating mechanism such as grease, which deteriorates due to the sliding between the first member and the second member, which can be quantified and has a correlation with the deterioration of the operating mechanism, is the main. Can be used as input.
  • the drive device 302 is a device that rotationally drives the shaft body 301.
  • the type of the drive device 302 is not particularly limited, but in the case of the present embodiment, the drive device 302 is a servomotor, and the rotary shaft body of the servomotor is connected to the shaft body 301 via a joint. ing.
  • the drive device 302 is controlled by the drive control device 330.
  • the learning operation mechanism 200 is externally loaded via the fixing member 305. It is preferable that the load is close to the usage mode of the evaluation operation mechanism.
  • the sensor is not particularly limited, and a sensor for measuring sound, an image sensor, and the like can be exemplified.
  • the sensor is a sensor capable of acquiring vibration data caused by the learning operation mechanism 200 by rotating the shaft body 301.
  • the vibration sensor is attached to the fixing member 305, and the learning operation mechanism Not only the vibration of 200, but also the vibration generated by other factors is measured.
  • the type of sensor is not particularly limited, and it is preferable to use a sensor of the same type as the sensor attached to the actual machine 400 (see FIG. 2).
  • the sensor is a sensor that measures the vibration acceleration in the uniaxial direction.
  • the number and location of the sensors attached to the learning information generation device 300 are not limited, but in the case of the present embodiment, the sensors are added to the learning operation mechanism 200 in the radial direction with respect to the axial direction of the shaft body 301.
  • the first sensor 321 that measures the vibration in the load direction (Z-axis direction in the figure) and the radial direction that is orthogonal to the vibration direction measured by the first sensor 321 and are in the horizontal plane and outside the device. It is equipped with a second sensor 322 that measures vibration in a direction in which the binding force is weak (Y-axis direction in the figure).
  • the operating mechanism including the evaluation operating mechanism is a roller bearing, it is considered that there is no strong correlation between the vibration in the axial direction (X-axis direction in the figure) and the deterioration state, and the shaft of the shaft body 301.
  • a sensor that acquires vibration in the direction is not arranged, for example, when the operating mechanism is a ball bearing, a cross roller bearing, or the like, a third sensor that acquires vibration in the axial direction may be installed.
  • the recording device 306 is a device that records a signal from the sensor.
  • the signals from the first sensor 321 and the second sensor 322 are individually recorded.
  • the recording device 306 digitizes and records an analog signal indicating the vibration acceleration from the sensor at a sampling frequency of 50 kHz.
  • FIG. 2 is a block diagram showing the configuration of the deterioration status prediction system according to the embodiment.
  • the deterioration status prediction system 100 includes a main input derivation unit 110, an auxiliary input derivation unit 120, and a training unit 130 as processing units realized by executing a deterioration status prediction program on a processor.
  • a deterioration status derivation unit 140 and a multi-regression model 150 are provided.
  • the main input derivation unit 110 derives a main input indicating deterioration of the operating mechanism at each of a plurality of measurement timings.
  • the type of the main input is not particularly limited as described above, and may be one that can be acquired by disassembling the operation mechanism at the measurement timing, one that can be acquired by using a sensor while the operation mechanism is in operation, and the like.
  • the measurement timings do not have to be arranged at equal intervals, and the measurement may be performed at any timing.
  • the recording device 306 acquires the vibration acceleration from the first sensor 321 and the second sensor 322, respectively, and digitizes them individually.
  • the main input derivation unit 110 of the deterioration status prediction system 100 performs a short-time Fourier transform on the first digital signal 410 and the second digital signal 420 acquired from the recording device 306, and performs a first time frequency image.
  • Data 411 and second time frequency image data 412 are derived, respectively.
  • the deterioration status prediction system 100 uses the first time frequency image data 411 and the second time frequency image data 412 as main inputs for learning and evaluation.
  • the auxiliary input derivation unit 120 derives an auxiliary input which is a feature vector in which deterioration data related to deterioration status at a plurality of measurement timings are arranged in chronological order.
  • the deterioration data is not particularly limited, but in the case of the present embodiment, the auxiliary input derivation unit 120 inputs the auxiliary input based on the remaining life which is the deterioration status at each measurement timing acquired from the deterioration status acquisition device 307. Derived. Further, the auxiliary input derivation unit 120 normalizes the remaining life at each measurement timing, measures at different timings, and derives the auxiliary input in which the normalized remaining life is arranged in chronological order.
  • lim the measurement timing m at the operating limit of the operating mechanism.
  • the deterioration data at the measurement timing is R ⁇ m ⁇ (the inside of ⁇ means a subscript).
  • T ⁇ m ⁇ be the time at the measurement timing.
  • the auxiliary input derivation unit 120 derives the deterioration data using the following equation 1.
  • T ⁇ lim ⁇ -T ⁇ m ⁇ indicates the remaining life of the operating mechanism 200 at the measurement timing.
  • R ⁇ m ⁇ is a normalization of the remaining life using the life (T ⁇ lim ⁇ -T ⁇ 0 ⁇ ) which is the deterioration state at the operation limit of the operation mechanism 200.
  • the auxiliary input derivation unit 120 derives the auxiliary vector I ⁇ m ⁇ in which the following deterioration data are arranged in chronological order as the auxiliary input.
  • I ⁇ m ⁇ [R ⁇ m ⁇ , R ⁇ m-1 ⁇ , ..., R ⁇ m-k ⁇ ]
  • I ⁇ m ⁇ is an auxiliary input at the mth measurement timing
  • deterioration data is not limited to the above formula 1, and data derived using the following formulas 2 and 3 may be adopted.
  • a predetermined deterioration threshold value is set, and when the deterioration status is equal to or higher than the deterioration threshold value, the deterioration data derived by using the following formula 4 is adopted, and when the deterioration status is less than the deterioration threshold value, the following formula 5 is used.
  • the type of deterioration data may be changed according to the length of the usage period of the operating mechanism, such as using the derived deterioration data.
  • N is a predetermined natural number of 2 or more, and ⁇ is a power.
  • the auxiliary input derivation unit 120 derives the deterioration data using the above equation 1.
  • the operating mechanism has not reached T ⁇ lim ⁇ , and the true value of the remaining life is unknown.
  • the deterioration status acquisition device 307 acquires the remaining life, which is the deterioration status derived by the deterioration status prediction system 100.
  • the deterioration status acquisition device 307 may estimate T ⁇ lim ⁇ using a linear model, a nonlinear model, an expert system, or the like other than the deterioration status prediction system 100.
  • the multi-regression model 150 uses the main input derived by the main input derivation unit 110 and the auxiliary input derived by the auxiliary input derivation unit 120 as inputs, and operates the learning operation mechanism 200 to the operation limit to deteriorate the operation mechanism. It is nurtured using the lifespan that is the situation, and constitutes an artificial intelligence that derives the remaining lifespan of the evaluation operation mechanism.
  • the multi-regression model 150 includes a main regression model 151 that outputs a main intermediate input based on the main input, an auxiliary regression model 152 that outputs an auxiliary intermediate input based on the auxiliary input, and a main intermediate input. It includes a merged regression model 153, which derives the remaining life based on the auxiliary intermediate input.
  • the type of the main regression model 151 is not particularly limited, but in the case of the present embodiment, since the main input is an image, the regression model used for pattern recognition is adopted.
  • the regression model used for pattern recognition include DNN (Deep Neural Network, deep neural network), CNN (Convolutional Neural Network, convolutional neural network) and the like.
  • the main regression model 151 includes a model for the first time frequency image data 411 and a model for the second time frequency image data 412. The same type of regression model for the first time frequency image data 411 and the type of regression model for the second time frequency image data 412 are adopted.
  • the main regression model 151 may include only one type of model. Further, the main regression model 151 may include different types of models.
  • the type of the auxiliary regression model 152 is not particularly limited, but in the case of the present embodiment, since the auxiliary inputs are feature vectors arranged in a time series, the model used for the time series regression is adopted. .. Examples of the model used for time-series regression include RNN (Recurrent Neural Network) and LSTM (Long Short-Term Memory).
  • the type of the merged regression model 153 is not particularly limited, but a fully connected neural network, a perceptron, and the like can be exemplified.
  • the training unit 130 operates the learning operation mechanism 200 to the operation limit, receives the main input and the auxiliary input measured at a plurality of measurement timings up to the operation limit as inputs, and sets the initial state (unused) of the learning operation mechanism 200.
  • Each model provided in the multi-regression model 150 is cultivated by using the period (lifetime) from the state) to the operation limit as teacher data.
  • the deterioration status derivation unit 140 uses the main input derived by the main input derivation unit 110 and the auxiliary input derived by the auxiliary input derivation unit 120 based on the evaluation operation mechanism mounted on the actual machine 400 and not reaching the operation limit as inputs.
  • the deterioration status of the evaluation operation mechanism is derived from the multi-regression model 150 trained by the training unit 130. In the case of this embodiment, the deterioration status derivation unit 140 derives the remaining life as the deterioration status.
  • a main regression model in which the time-frequency image data (STFT) of vibration acceleration is the main input and a feature vector in consideration of the decreasing tendency of the remaining life are used as auxiliary inputs.
  • the multi-regression model 150 including the auxiliary regression model makes it possible to improve the estimation accuracy of the remaining life. Specifically, by adding not only the measurement data at one measurement timing, that is, the main input that does not consider the decreasing tendency of the remaining life (time series), but also the feature vector that considers the decreasing tendency of the remaining life as an auxiliary input. , It is possible to consider the progress of deterioration that is not constant, and it is possible to improve the estimation accuracy of the remaining life.
  • the normalized remaining life is vectorized in the measurement sequence as an auxiliary input, the measurement accuracy is stabilized and the accuracy is further improved even when data with irregular measurement intervals is input. It is also possible to let it.
  • the present invention is not limited to the above embodiment.
  • another embodiment realized by arbitrarily combining the components described in the present specification and excluding some of the components may be an embodiment of the present invention.
  • the present invention also includes modifications obtained by making various modifications that can be conceived by those skilled in the art within the scope of the gist of the present invention, that is, the meaning indicated by the wording described in the claims, with respect to the above-described embodiment. Will be.
  • the deterioration status prediction system 100 may predict not only the remaining life but also the allowable deterioration amount as the deterioration status.
  • the auxiliary input derivation unit 120 may derive the deterioration data using the following equation 6.
  • D ⁇ m ⁇ is not particularly limited, but is, for example, the circumferential peeling length on the raceway surface of the inner ring (second member) of the rolling bearing at the measurement timing.
  • the peeling length may be a maximum value, an average value, or the like.
  • (D ⁇ lim ⁇ -D ⁇ m ⁇ ) indicates an allowable deterioration amount indicating an allowable deterioration amount of the operation mechanism 200 in the future at the measurement timing.
  • R ⁇ m ⁇ is a normalization of the permissible deterioration amount using the total deterioration amount (D ⁇ lim ⁇ -D ⁇ 0 ⁇ ) which is the deterioration state at the operation limit of the operation mechanism 200.
  • auxiliary input I1 ⁇ m ⁇ uses the deterioration data R ⁇ m ⁇ given by the above formula 1
  • the other auxiliary input I2 ⁇ m ⁇ uses the deterioration data R ⁇ m ⁇ given by the above formula 4. It may be the one using.
  • one auxiliary input I1 ⁇ m ⁇ uses the deterioration data R ⁇ m ⁇ given by the above equations 2 and 3
  • the other auxiliary input I2 ⁇ m ⁇ is the deterioration data given by the above equation 5. It may be the one using R ⁇ m ⁇ . Further, there may be three or more types.
  • auxiliary inputs may not be constant and may change depending on the period of use of the operating mechanism.
  • the deterioration status prediction system 100 includes the training unit 130 and the deterioration status derivation unit 140 has been described, but the deterioration status prediction system 100 includes a learning device provided with the training unit 130 and training.
  • a deterioration status estimation device that does not include the unit 130 may be provided as a separate device.
  • the deterioration status estimation device acquires the multi-regression model 150 trained by the learning device and estimates the deterioration status.
  • main input derivation unit 110 may be used as data for deriving a main input such as an output torque of the drive device 302 such as a command value for the drive control device 330 to control the drive device 302.
  • the learning information generation device 300 and the actual machine 400 may be the same device.
  • the feature amount may be adopted as the feature amount. It doesn't matter.
  • the operating mechanism is not limited to rolling bearings, and may be a ball screw, a linear motion guide, or the like.
  • the signal measured by the sensor is not limited to the vibration acceleration, but may be the displacement of the vibration, the speed of the vibration, or the like. Further, not only vibration but also sound or the like may be measured and used as data for deriving the main input.
  • Deterioration status prediction system 110 Main input derivation unit 120 Auxiliary input derivation unit 130 Training unit 140 Deterioration status derivation unit 150 Multi regression model 151 Main regression model 152 Auxiliary regression model 153 Merged regression model 200 Learning operation mechanism 201 First member for learning 202 Second member for learning 300 Learning information generator 301 Axis body 302 Drive device 305 Fixing member 306 Recording device 307 Deterioration status acquisition device 321 First sensor 322 Second sensor 330 Drive control device 400 Actual machine 410 First digital signal 411 First Time frequency image data 412 Second time frequency image data 420 Second digital signal

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Analytical Chemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Environmental & Geological Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Ecology (AREA)
  • Biochemistry (AREA)
  • Environmental Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
  • Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Abstract

La présente invention concerne un système de prédiction d'état de dégradation (100) comprenant : une unité de dérivation d'entrée principale (110) qui dérive des entrées principales indiquant la dégradation d'un mécanisme de déplacement à des moments de mesure individuels; une unité de dérivation d'entrée auxiliaire (120) qui dérive des entrées auxiliaires dans lesquelles des données de dégradation aux moments de mesure sont agencées en série chronologique; une unité d'apprentissage (130) qui amène un mécanisme de déplacement à apprendre à se déplacer jusqu'à une limite de déplacement et qui entraîne un modèle par régression multiple (150) dans lequel sont introduites des entrées principales et des entrées auxiliaires à une pluralité de moments de mesure jusqu'à la limite de déplacement; et une unité de dérivation d'état de dégradation (140) qui dérive un état de dégradation au moyen du modèle par régression multiple entraîné (150) en utilisant, en tant qu'entrées, des entrées principales dérivées par l'unité de dérivation d'entrée principale (110) et des entrées auxiliaires dérivées par l'unité de dérivation d'entrée auxiliaire (120) sur la base d'un mécanisme de déplacement en vue d'une évaluation.
PCT/JP2021/019620 2020-09-24 2021-05-24 Système et procédé de prédiction d'état de dégradation WO2022064769A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020159615A JP2022053036A (ja) 2020-09-24 2020-09-24 劣化状況予測システム、および劣化状況予測方法
JP2020-159615 2020-09-24

Publications (1)

Publication Number Publication Date
WO2022064769A1 true WO2022064769A1 (fr) 2022-03-31

Family

ID=80846428

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/019620 WO2022064769A1 (fr) 2020-09-24 2021-05-24 Système et procédé de prédiction d'état de dégradation

Country Status (2)

Country Link
JP (1) JP2022053036A (fr)
WO (1) WO2022064769A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018156340A (ja) * 2017-03-16 2018-10-04 株式会社リコー 診断装置、診断システム、診断方法およびプログラム
WO2019049406A1 (fr) * 2017-09-08 2019-03-14 株式会社日立製作所 Système d'évaluation de probabilité de défaillance
WO2019187138A1 (fr) * 2018-03-30 2019-10-03 株式会社牧野フライス製作所 Dispositif de prédiction de durée de vie restante et machine-outil
WO2020162425A1 (fr) * 2019-02-05 2020-08-13 日本電気株式会社 Dispositif d'analyse, procédé d'analyse et programme
WO2020183539A1 (fr) * 2019-03-08 2020-09-17 三菱電機株式会社 Système de diagnostic de pannes, procédé de production de règles de prédiction et programme de production de règles de prédiction

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018156340A (ja) * 2017-03-16 2018-10-04 株式会社リコー 診断装置、診断システム、診断方法およびプログラム
WO2019049406A1 (fr) * 2017-09-08 2019-03-14 株式会社日立製作所 Système d'évaluation de probabilité de défaillance
WO2019187138A1 (fr) * 2018-03-30 2019-10-03 株式会社牧野フライス製作所 Dispositif de prédiction de durée de vie restante et machine-outil
WO2020162425A1 (fr) * 2019-02-05 2020-08-13 日本電気株式会社 Dispositif d'analyse, procédé d'analyse et programme
WO2020183539A1 (fr) * 2019-03-08 2020-09-17 三菱電機株式会社 Système de diagnostic de pannes, procédé de production de règles de prédiction et programme de production de règles de prédiction

Also Published As

Publication number Publication date
JP2022053036A (ja) 2022-04-05

Similar Documents

Publication Publication Date Title
US11527984B2 (en) Abnormality determination system, motor control apparatus, and abnormality determination apparatus
Ali et al. Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network
US10364840B2 (en) Failure detection device for spindle head of machine tool including a plurality of sensors
Janjarasjitt et al. Bearing condition diagnosis and prognosis using applied nonlinear dynamical analysis of machine vibration signal
JP6571704B2 (ja) 診断用データ取得システム、診断用システム、及び診断用データ取得プログラム
JP2018004473A (ja) 軸受の予測寿命を学習する機械学習装置、寿命予測装置および機械学習方法
Butler et al. Condition monitoring of machine tool feed drives: A review
TWI676752B (zh) 滾動導引裝置的狀態診斷系統
EP3855153A1 (fr) Procédé pour déterminer une durée de vie utile restante d'un palier
TW201843549A (zh) 滾動導引裝置的狀態診斷系統及狀態診斷方法
JP2019168412A (ja) 異常検出装置および異常検出方法
WO2022064769A1 (fr) Système et procédé de prédiction d'état de dégradation
Dorst et al. Influence of synchronization within a sensor network on machine learning results
Justus et al. Intelligent single-board computer for Industry 4.0: Efficient real-time monitoring system for anomaly detection in CNC machines
Abed et al. Diagnosis of bearing fault of brushless DC motor based on dynamic neural network and orthogonal fuzzy neighborhood discriminant analysis
WO2021065449A1 (fr) Système de prédiction de durée de vie résiduelle, dispositif de prédiction de durée de vie résiduelle et programme de prédiction de durée de vie résiduelle
CN116324193A (zh) 机器学习装置、滑动面诊断装置、推论装置、机器学习方法、机器学习程序、滑动面诊断方法、滑动面诊断程序、推论方法及推论程序
JP2023138012A (ja) 劣化状況予測システム、および劣化状況予測方法
Demetgul et al. Misalignment detection on linear feed axis using sensorless motor current signals
Haj Mohamad et al. Discrimination of multiple faults in bearings using density-based orthogonal functions of the time response
WO2021065448A1 (fr) Dispositif de prédiction de durée de vie restante, système de prédiction de durée de vie restante et programme de prédiction de durée de vie restante
JP7430317B2 (ja) 余寿命予測システム、余寿命予測装置、および余寿命予測プログラム
Loukopoulos et al. Reciprocating compressor prognostics
Hong et al. Bearing wear prognosis based on Hidden Markov Model
Bhavsar et al. Prediction of Remaining Useful Life (RUL) of Bearing Using Exponential Degradation Model

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21871903

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21871903

Country of ref document: EP

Kind code of ref document: A1