[go: up one dir, main page]

WO2024143961A1 - Procédé de maintenance prédictive d'un dispositif à l'aide d'un écart absolu - Google Patents

Procédé de maintenance prédictive d'un dispositif à l'aide d'un écart absolu Download PDF

Info

Publication number
WO2024143961A1
WO2024143961A1 PCT/KR2023/019784 KR2023019784W WO2024143961A1 WO 2024143961 A1 WO2024143961 A1 WO 2024143961A1 KR 2023019784 W KR2023019784 W KR 2023019784W WO 2024143961 A1 WO2024143961 A1 WO 2024143961A1
Authority
WO
WIPO (PCT)
Prior art keywords
value
absolute
detection
detection section
absolute difference
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.)
Ceased
Application number
PCT/KR2023/019784
Other languages
English (en)
Korean (ko)
Inventor
이영규
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.)
ITS Co Ltd
Original Assignee
ITS 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 ITS Co Ltd filed Critical ITS Co Ltd
Publication of WO2024143961A1 publication Critical patent/WO2024143961A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
    • G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
    • G05B23/0227—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions
    • G05B23/0235—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
    • G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
    • G05B23/0267—Fault communication, e.g. human machine interface [HMI]
    • G05B23/027—Alarm generation, e.g. communication protocol; Forms of alarm

Definitions

  • the sections are arranged at unit time intervals in the overlapping arrangement step (S30) so that they overlap each other, and if the absolute difference value of each detection section corresponds to the alarm section of the absolute distribution map set in the setting step (S50), an alarm is issued. It is characterized by encouraging inspection and management of the device.
  • the setting step (S50) sets a distribution threshold for the distribution probability of the warning section in the absolute distribution map based on the information of the absolute distribution map collected and constructed in the difference value collection step (S40), and the detection step (S60) ) repeatedly divides the distribution detection section containing many absolute difference values of the detection section that are repeatedly detected in the real-time operating state of the device, and the alarm section of the real-time absolute distribution map is constructed based on the absolute difference values of the sectioned distribution detection section. If the distribution probability exceeds the distribution threshold set in the setting step (S50), inspection and management of the device is induced.
  • Figures 2 to 18 are diagrams for explaining a predictive maintenance method for equipment using the absolute deviation shown in Figure 1.
  • FIGS. 1 to 18 show a predictive maintenance method for equipment using absolute deviation according to an embodiment of the present invention.
  • Figure 1 is a block diagram of a predictive maintenance method for equipment using absolute deviation according to an embodiment of the present invention.
  • FIGS. 2 to 18 each show drawings to explain the predictive maintenance method of the device using the absolute deviation shown in FIG. 1.
  • the predictive maintenance method 100 for equipment using absolute deviation includes an information collection step (S10), a section division step (S20), and an overlapping arrangement step (S30). It includes a difference value collection step (S40), a setting step (S50), and a detection step (S60).
  • the information collection step (S10) is a step of collecting information on changes in energy level over time measured by a device in a running state, and repeatedly measuring the energy value at set unit time intervals.
  • the information collection step (S10) if information on changes in the size (value) of current consumed by the device in the driving state is collected over time, it can be collected as a current (energy) waveform as shown in FIG. 2. And the current value (energy value) is repeatedly measured and collected from this current waveform at unit time intervals.
  • the current waveform measured and collected from the device in the information collection step (S10) is in a state in which the current value continuously maintains a certain range, that is, in a state in which the device has started to operate and the operation of the device has stabilized.
  • the current waveform measured and collected from the device in the information collection step (S10) is in a state in which the current value continuously maintains a certain range, that is, in a state in which the device has started to operate and the operation of the device has stabilized.
  • the section division step (S20) repeatedly extracts a detection section of a set time that includes at least two energy values from the energy waveform showing information on changes in energy size over time collected in the information collection step (S10). This is the step.
  • the detection section repeatedly formed in the current waveform is for collecting the difference value in the difference value collection step (S40), which will be described later.
  • the unit time of the detection section is as shown in FIG. 3. is set to 10 minutes so that the detection section includes a total of 10 current values.
  • the unit time for this detection section varies depending on various factors such as the type of device, the surrounding environment in which the device is used, and conditions. Of course, it is set to allow a variety of current values to be included in the detection section.
  • the overlapping arrangement step (S30) is a step of setting a unit time interval at which the detection section is repeatedly extracted and arranging the detection section and a portion of other adjacent detection sections so that they overlap each other.
  • a unit time interval at which the detection sections are repeatedly extracted (detected) is set so that the detection sections overlap each other.
  • the set unit time interval is smaller than the unit time of the detection section, so that the detection sections are connected to each other.
  • some parts overlap naturally.
  • the unit time interval at which the detection section is extracted must be set to at least less than 10 minutes.
  • the extracted unit If the time interval is 5 minutes, the detection section is repeatedly extracted every 5 minutes. At this time, the repeatedly detected (extracted) detection section naturally overlaps with another adjacent detection section by 5 minutes.
  • the detection sections are arranged to overlap each other in this way, the current value within the detection section can be repeatedly used in other detection sections, so in the difference value collection step (S40), which will be described later, the absolute difference value based on the current value of the detection section is detected. Enables device abnormalities to be detected more effectively.
  • the abnormal current value is used repeatedly in other detection sections, so the abnormality symptoms of the device can be reflected more effectively.
  • the predictive maintenance method 100 of the device using the absolute deviation of the present invention enables very accurate detection of abnormal signs of the device.
  • the difference value collection step (S40) detects and collects the difference between each energy value included in the detection section arranged in the overlapping arrangement step (S30) with the previous energy value, and sets each collected difference value as an absolute value. Collect the absolute difference values for each detection section by adding them up, and arrange the absolute difference values of the collected detection sections sequentially according to the passage of time, and compare the placed absolute difference values with other adjacent absolute difference values. This is the step of repeatedly collecting the slope of the straight line for the absolute difference value by repeatedly connecting it with a straight line.
  • the slope threshold for the slope of the absolute difference value of the detection section is the information collection step (S10), section division step (S20), overlap arrangement step (S30), and difference value collection step (S40).
  • the slope value of the detection section that changes abnormally before device failure occurs, for example, load due to device deterioration, aging, or foreign substances caught in the device.
  • settings are made based on values that change abnormally in the device in such situations.
  • the detection step (S60) repeatedly divides detection sections at unit time intervals from the energy waveform measured in the real-time operating state of the device, and the overlap arrangement step (S30) so that some of the repeatedly sectioned detection sections overlap with each other. After arranging at unit time intervals and arranging the absolute difference value of each detection section according to the passage of time, the slope value of the straight line connecting the arranged absolute difference value and other adjacent absolute difference values is the above. This is the step to induce inspection and management of the device by sending an alarm when the inclination threshold is exceeded.
  • the detection section repeatedly divided from the current (energy) waveform measured and collected from the real-time device is 10 minutes like the detection section of the section division step (S20) so that a total of 10 current values can be included.
  • the absolute difference value is calculated based on the current value of each detection section, the calculated absolute difference values are arranged sequentially according to the passage of time, and the arranged absolute difference values are compared to each other.
  • the slope value of a straight line that repeatedly connects the absolute difference value is detected, and if the detected slope value does not exceed the slope threshold set in the setting step (S50), the device is detected as stable, and vice versa.
  • the device If the real-time inclination value of the device exceeds the above inclination threshold, the device is detected to be in a somewhat unstable state and an alarm is issued to induce management such as replacement or repair before the device malfunctions, thereby preventing the operation of the facility due to sudden device failure. Ensure that economic losses resulting from interruptions can be prevented in advance.
  • the absolute difference value which is the sum of the difference values for each current value included in the detection section, can effectively reflect the unstable state in which the current (energy) value fluctuates somewhat slightly before the device fails, so the predictive maintenance method as above This allows abnormal signs to be detected earlier and more accurately before device failure.
  • the detection step (S60) is a slope detection section of unit time that includes at least two slopes of a straight line connecting the absolute difference values of the detection sections repeatedly detected in the real-time driving state of the device. is repeatedly divided, and when the average slope value of the straight line slopes included in the partitioned slope detection section exceeds the slope threshold set in the setting step (S50), an alarm is issued to induce inspection and management of the device.
  • the average slope value of the slope detection section is compared with the slope threshold value preset in the setting step (S50) to detect abnormal signs of the device, but a separate slope is used so that it can be applied only to the average slope value.
  • the threshold can be set and used independently in the setting step (S50).
  • the difference value collection step (S40) sequentially arranges the absolute difference values of each detection section arranged in the overlapping arrangement step (S30) according to the passage of time, and the arranged absolute difference values include at least two.
  • the area detection section of unit time is repeatedly divided, and the integrated area value of the divided area detection section is detected and collected.
  • the area inside the waveform connecting the absolute difference values included in the area detection section is measured, and the integrated area value of the area detection section is repeatedly detected and collected.
  • the integrated area value information of the area detection section collected in this way becomes the basis for the area threshold value set to detect abnormal signs of the device in the setting step (S50).
  • the setting step (S50) sets an area threshold for the integrated area value based on the integrated area value information about the absolute difference value of the area detection section collected in the difference value collection step (S40),
  • the detection step (S60) is arranged at unit time intervals of the overlapping arrangement step (S30) so that the detection sections of the unit time interval in the energy waveform measured in the real-time operation state of the device can overlap each other, and each detection arranged.
  • After arranging the absolute difference values of the section according to the passage of time if the integrated area value of the area detection section containing at least two of the arranged absolute difference values exceeds the area threshold set in the setting step (S50), an alarm is issued. This leads to inspection and management of the device.
  • area detection sections containing at least two absolute difference values of each detection section measured and collected from a real-time device are repeatedly divided, and the integrated area value of the sectioned real-time area detection section is If the area threshold value set in the setting step (S50) is exceeded, the device is detected to be in a somewhat unstable state and an alarm is issued to induce management such as replacement or repair in advance before device failure occurs. This ensures that economic losses resulting from this interruption can be prevented in advance.
  • the difference value collection step (S40) repeatedly divides distribution detection sections of unit time containing a plurality of absolute difference values of each detection section arranged in the overlapping arrangement step (S30), and divides the distribution detection sections into the divided distribution detection sections.
  • An absolute distribution map is repeatedly constructed using the included absolute difference values.
  • an absolute distribution chart as shown in FIG. 12 can be constructed.
  • a section with a high distribution probability of the absolute difference value is arbitrarily set as a safety section, and a selection is made from sections other than the set safe section. Set one section or two or more sections as a warning section.
  • the absolute difference value corresponding to the safety section with a high distribution probability in the absolute distribution diagram can be viewed as a value in which the state of the device is somewhat stable, and the absolute difference value corresponding to the alarm section with a low distribution probability can be seen as a value indicating that the state of the device is somewhat unstable.
  • the warning section is all sections other than the safety section, that is, sections on both sides of the safety section are selected as warning sections, but of course, the warning section is not limited to these selected sections.
  • the detection step (S60) is arranged at unit time intervals of the overlapping arrangement step (S30) so that the detection sections of the unit time interval in the energy waveform measured in the real-time operation state of the device overlap each other, and the arrangement is performed. If the absolute difference value of each detection section corresponds to the alarm section of the absolute distribution map set in the setting step (S50), an alarm is issued to induce inspection and management of the device.
  • the distribution detection section containing a large number of absolute difference values of the detection section that is repeatedly detected in the real-time operation state of the device is repeatedly divided, and the absolute difference values of the divided distribution detection section are used. If the distribution probability of the alarm section of the constructed real-time absolute distribution map exceeds the distribution threshold set in the setting step (S50), inspection and management of the device is induced.
  • the difference value collection step (S30) repeatedly collects only the absolute difference value of each detection section arranged in the overlapping arrangement step (S30),
  • the difference value collection step (S30) repeatedly divides the average detection section of unit time containing at least two absolute difference values of the repeatedly collected detection section, and calculates the average value of the absolute difference values of the divided average detection section. Detect and collect.
  • the average detection section containing a plurality of absolute difference values is repeatedly divided, and the average value obtained by adding the absolute difference values of the divided average detection sections is repeatedly collected.
  • the average value information of the average detection section becomes the basis for the average threshold value set to detect abnormal signs of the device in the setting step (S50).
  • the predictive maintenance method 100 of a device using the absolute deviation of the present invention which predicts abnormal signs of the device through the above process, detects a detection section containing a plurality of energy values in the energy waveform over time measured by the device. It repeats segmentation, calculates the difference between each energy value within the segmented detection section and the previous energy value, sets a threshold based on the slope information for the absolute difference value, which is added to the absolute value, and sets the real-time operating status of the device. If the slope value for the absolute difference value of each detection section exceeds the threshold, the device is detected to be in a somewhat unstable state and an alarm is issued to induce management such as replacement or repair in advance before device failure occurs, thereby preventing sudden device failure. This has the effect of preventing economic losses that occur due to facility outage.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

La présente invention se rapporte à un procédé de maintenance prédictive d'un dispositif à l'aide d'un écart absolu, une forme d'onde d'énergie dans le temps mesurée par le dispositif étant divisée de manière répétée en sections de détection comprenant une pluralité de valeurs d'énergie, une valeur de différence entre des valeurs d'énergie respectives à l'intérieur des sections de détection divisées et une valeur d'énergie précédente étant calculée, une valeur seuil étant définie sur la base d'informations de pente concernant une valeur de différence absolue, qui est obtenue en ajoutant la valeur de différence à une valeur absolue, et dans un état de fonctionnement en temps réel du dispositif, si une valeur de pente pour la valeur de différence absolue de chaque section de détection dépasse la valeur seuil, il est détecté que le dispositif est dans un état quelque peu instable et une alarme est émise. Par conséquent, en encourageant une gestion, telle que le remplacement ou la réparation, à l'avance avant qu'une défaillance ne se produise dans le dispositif, des pertes économiques résultant de l'arrêt de l'installation en raison d'une défaillance soudaine du dispositif peuvent être empêchées à l'avance.
PCT/KR2023/019784 2022-12-29 2023-12-04 Procédé de maintenance prédictive d'un dispositif à l'aide d'un écart absolu Ceased WO2024143961A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020220189576A KR20240106626A (ko) 2022-12-29 2022-12-29 절대편차를 이용한 기기의 예지 보전방법
KR10-2022-0189576 2022-12-29

Publications (1)

Publication Number Publication Date
WO2024143961A1 true WO2024143961A1 (fr) 2024-07-04

Family

ID=91718280

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2023/019784 Ceased WO2024143961A1 (fr) 2022-12-29 2023-12-04 Procédé de maintenance prédictive d'un dispositif à l'aide d'un écart absolu

Country Status (2)

Country Link
KR (1) KR20240106626A (fr)
WO (1) WO2024143961A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020169582A1 (en) * 2001-05-14 2002-11-14 Evren Eryurek Diagnostics for industrial process control and measurement systems
KR20120012766A (ko) * 2010-08-02 2012-02-10 내셔날 쳉쿵 유니버시티 의존 인덱스를 이용하는 가상 계측을 활용한 고급 공정 제어 시스템
JP2021174387A (ja) * 2020-04-28 2021-11-01 三菱重工業株式会社 モデル評価装置、モデル評価方法、及びプログラム
JP2022144024A (ja) * 2021-03-18 2022-10-03 東芝情報システム株式会社 故障検知・予知装置及び故障検知・予知用プログラム
KR102477710B1 (ko) * 2021-07-01 2022-12-14 (주)아이티공간 면적에 대한 정속 정의를 통한 기기의 예지 보전방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020169582A1 (en) * 2001-05-14 2002-11-14 Evren Eryurek Diagnostics for industrial process control and measurement systems
KR20120012766A (ko) * 2010-08-02 2012-02-10 내셔날 쳉쿵 유니버시티 의존 인덱스를 이용하는 가상 계측을 활용한 고급 공정 제어 시스템
JP2021174387A (ja) * 2020-04-28 2021-11-01 三菱重工業株式会社 モデル評価装置、モデル評価方法、及びプログラム
JP2022144024A (ja) * 2021-03-18 2022-10-03 東芝情報システム株式会社 故障検知・予知装置及び故障検知・予知用プログラム
KR102477710B1 (ko) * 2021-07-01 2022-12-14 (주)아이티공간 면적에 대한 정속 정의를 통한 기기의 예지 보전방법

Also Published As

Publication number Publication date
KR20240106626A (ko) 2024-07-08

Similar Documents

Publication Publication Date Title
WO2023277544A1 (fr) Procédé de maintenance prédictive d'un dispositif par définition de vitesse constante en fonction du temps
WO2019177239A1 (fr) Procédé de maintenance préventive de précision d'unité d'entraînement
WO2023277387A1 (fr) Procédé de maintenance prédictive de dispositif utilisant le réglage de vitesse constante de crête
WO2019177238A1 (fr) Procédé de préservation d'une partie d'entraînement par prédiction précise
WO2023277388A1 (fr) Procédé de maintenance préventive de dispositif par définition de vitesse aréolaire constante
WO2019177236A1 (fr) Procédé de maintenance prédictive précise pour unité d'entraînement
WO2019031683A1 (fr) Procédé de maintenance prédictive précise pour unité d'entraînement
WO2019177237A1 (fr) Procédé de maintenance prédictive précise d'une unité de fonctionnement
WO2019031682A1 (fr) Procédé de maintenance prédictive précise pour unité d'entraînement
WO2019177234A1 (fr) Procédé de maintenance prédictive précise pour unité d'entraînement
WO2021075842A1 (fr) Procédé de maintenance prédictive d'équipement au moyen d'une carte de distribution
WO2017010821A1 (fr) Procédé de contrôle d'unité d'entraînement de chaîne de montage de carrosserie de véhicule, et dispositif associé
WO2020262843A1 (fr) Procédé de maintenance prédictive pour dispositif par l'intermédiaire d'un signal de sortie de commande
WO2019177235A1 (fr) Procédé de maintenance prédictive précise pour unité d'entraînement
WO2021075845A1 (fr) Procédé de maintenance prédictive d'équipement par l'intermédiaire d'un diagramme de distribution
WO2019177233A1 (fr) Procédé de maintenance prédictive précise pour unité de fonctionnement
WO2022154207A1 (fr) Commutateur manuel pouvant prédire des défaillances par analyse comparative de tendances de changement de température
WO2020262844A2 (fr) Méthode de maintenance prédictive pour dispositif par l'intermédiaire d'un signal de sortie de commande multiple
WO2019177240A1 (fr) Procédé de maintenance préventive de précision d'unité d'entraînement
WO2019177241A1 (fr) Procédé de maintenance prédictive précise d'une unité d'entraînement
WO2019177232A1 (fr) Procédé de maintenance prédictive précise d'une unité d'entraînement
WO2021075855A1 (fr) Procédé de maintenance prédictive d'équipement par l'intermédiaire d'un diagramme de distribution
WO2024143961A1 (fr) Procédé de maintenance prédictive d'un dispositif à l'aide d'un écart absolu
WO2024143932A1 (fr) Procédé de maintenance prédictive d'un dispositif à l'aide d'un écart absolu
WO2024143934A1 (fr) Procédé utilisant un écart absolu pour la maintenance prédictive d'un dispositif

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: 23912636

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE