EP3803630A1 - Procédé de contrôle des dysfonctionnements d'un équipement et dispositifs associés - Google Patents
Procédé de contrôle des dysfonctionnements d'un équipement et dispositifs associésInfo
- Publication number
- EP3803630A1 EP3803630A1 EP19730699.6A EP19730699A EP3803630A1 EP 3803630 A1 EP3803630 A1 EP 3803630A1 EP 19730699 A EP19730699 A EP 19730699A EP 3803630 A1 EP3803630 A1 EP 3803630A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- equipment
- data
- phase
- malfunctions
- action
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/079—Root cause analysis, i.e. error or fault diagnosis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0793—Remedial or corrective actions
Definitions
- the present invention relates to a method for controlling malfunctions of the equipment.
- the present invention also relates to a computer program product and a readable medium of associated information.
- the present description relates to a method for controlling malfunctions of equipment, the equipment being suitable for use by separate installations, the method comprising a phase of data distribution in partial ontologies, the distribution phase being implemented by computer and comprising a step of providing partial ontologies, each partial ontology being relative to the equipment and being specific to one of the installations, a step of collecting a set of data relating to the equipment and from several separate installations, and a step of filling each partial ontology with the data collected.
- the method also includes a phase of gathering partial ontologies into a global ontology, the gathering phase being implemented by computer and involving the implementation of two learning techniques, the first technique being unsupervised and the second technique being supervised.
- the method further comprises an exploitation phase comprising a step of providing at least one piece of data originating from an installation, and a step of converting the data or data supplied into at least one information relating to the control of malfunctions. of equipment the conversion stage using the global ontology.
- control method comprises one or more of the following characteristics, taken in isolation or in any technically possible combination:
- the data set comprises measurements made by sensors.
- each piece of information relating to the control of malfunctions of the equipment is part of the group consisting of a probability of occurrence of a malfunction of the equipment, the cause of a malfunction of the equipment, the action or actions possible in the event of a malfunction of the equipment, the probability of success of a corrective action in the event of a malfunction of the equipment, and a maintenance action to prevent the subsequent occurrence of a malfunction of the equipment.
- each ontology comprises a set of concepts
- the collection phase comprising a subgrouping step comprising a reconciliation of the similar concepts of at least two partial ontologies to obtain groups, a group gathering a set of data relating to concepts that are considered to be close or logically related to each other, and an implementation of the first learning technique on each group to obtain subgroups of data sharing common characteristics, to obtain subgroups learned.
- the gathering phase includes a linking step in which a supervisor establishes a learning database and a test database by introducing relationships between data from the learned subgroups, and an implementation step. the second technique of learning relations from the two databases to obtain a global ontology associating with each subgroup a relation to the other subgroups.
- the distribution phase includes a preprocessing step during which the collected data is converted into a single format.
- At least one information relating to the control of malfunctions of the equipment is information relating to the maintenance or repair of at least a portion of the equipment.
- the operation phase comprises a step of implementing an action on the equipment according to at least one information relating to the control of malfunctions of the equipment.
- an information is a suggestion information of an action and the action implemented during the exploitation phase does not comply with the suggested action, the distribution and assembly phases are implemented again taking into account the action implemented during the exploitation phase.
- the present description also relates to a computer program product comprising a readable information medium, on which is memorized a computer program comprising program instructions, the computer program being loadable on a data processing unit and adapted to cause the implementation of a method as previously described when the computer program is implemented on the data processing unit.
- the present description also relates to a readable information medium on which is stored a computer program product as previously described.
- FIG. 1 a schematic view of an example of a computer that makes it possible to implement a method for controlling the malfunctions of an equipment
- FIG. 2 a schematic view of a set of facilities in which the equipment is brought to be used.
- FIG. 1 A system 10 and a computer program product 12 are shown in FIG. 1.
- the interaction of the computer program product 12 with the system 10 makes it possible to implement a method for controlling the malfunctions of an equipment.
- system 10 is an electronic calculator able to manipulate and / or transform data represented as electronic or physical quantities in computer registers and / or memories in other similar data corresponding to physical data in memories , registers or other types of display, transmission or storage devices.
- the system 10 comprises a processor 14 comprising a data processing unit 16, memories 18 and an information carrier reader 20.
- the system 10 also comprises a keyboard 22 and a display unit 24.
- the computer program product 12 comprises a readable information medium.
- a readable information medium is a support readable by the system 10, usually by the reader 20.
- the readable information medium is a medium adapted to memorize electronic instructions and capable of being coupled to a bus of a computer system .
- the readable information medium is a diskette or floppy disk ("floppy disk"), an optical disk, a CD-ROM, a magneto-optical disk, a ROM memory, a RAM memory, an EPROM memory, an EEPROM memory, a magnetic card or an optical card.
- a computer program including program instructions.
- the computer program is loadable on the data processing unit 16 and is adapted to carry out the implementation of the control method.
- the control method applies in a case where the equipment is brought during its lifetime to be used in several separate installations. Such a set of installations is shown in FIG.
- the facilities are an airport 22, a maintenance center 24, a repair center 26 and three central units 28, 30 and 32 each belonging to a respective supplier of the repair center 26.
- the set of facilities is thus a set of maintenance and operation of aircraft 34.
- Each aircraft 34 comprises a plurality of equipment 36 each comprising a plurality of parts.
- the equipment 36 is, in what follows, aircraft equipment.
- a fan, motor or wings are examples of such equipment.
- a plurality of aircraft 34 is suitable for taking off and arriving.
- the airport 22 includes sensors suitable for measuring environmental conditions.
- the sensors are suitable for measuring the temperature of the track, the amount of rain or visibility.
- Each aircraft 34, and in particular each equipment 36 of the aircraft 34, is strictly controlled in the maintenance center 24.
- Each equipment 36 is tested by a plurality of sensors.
- the plurality of sensors thus gives access, by way of illustration, to the mechanical strength of the equipment 36 or to electrical reference values of the equipment 36.
- a device 36 When a device 36 exhibits a malfunction, the equipment 36 is sent to a repair center 26.
- a repair center 26 By the expression “malfunction” is meant both a failure or a lack of operation, a non-compliant operation the expected operation of the equipment 36.
- each piece is tested to find the origin of the malfunction.
- the test comprises the establishment by sensors of the electrical response of the equipment 36, which response includes all the electrical values and not only the electrical reference values. For example, it is assumed that three pieces of equipment 36 are considered defective and that each of these parts is provided by a different supplier.
- the supplier carries out new tests of one of the pieces of equipment 36 with sensors of its own.
- the maintenance center 24, the repair center 26 and the plants 28, 30 and 32 of the three suppliers each have at their disposal relevant data for the maintenance and repair of the equipment 36 of the aircraft 34. It should be noted that it is difficult to connect the measurements of a plant 28 with the environmental conditions in which the part was used, these environmental conditions being known at the airport.
- the method of controlling malfunctions of a device 36 aims to exploit all of these data to ensure better maintenance (prevention) and better repair of malfunctions.
- the control method includes a data distribution phase in partial ontologies, a phase of gathering partial ontologies into a global ontology and an exploitation phase.
- At least the dispatching phase and the collecting phase are implemented by the system 10 interacting with the computer program product 12, that is, implemented by computer. Most stages of the operation phase are also computer-implemented, except that (s) which involve a direct intervention on the equipment 36 or part of the equipment 36.
- the distribution phase comprises a supply step, a collection step, a preprocessing step and a filling step.
- an ontology is an entity formed by a set of knowledge, facts and rules relating to a given field, scientific, cultural, administrative, industrial or commercial know-how.
- an ontology is a set of concepts, each concept being able to be related to other concepts.
- a concept groups together a set of words designating the same notion, typically synonyms.
- an aircraft is a concept that can also be referred to as a flying machine.
- synonyms is not the only possible case.
- a new concept may be the aircraft of said company.
- An ontology is representable in the form of a graph whose points are the concepts, a relation being represented by a line between two points.
- each ontology is at equipment 36, and more specifically at the maintenance and / or repair of equipment 36, and has generally been established by a supervisor.
- Each ontology is representative of the data of a specific installation, in this case, in the example described, the airport 22, the maintenance center 24, the repair center 26 or one of the three central 28, 30 and 32.
- the ontologies are qualified as "partial ontologies" insofar as each ontology takes into account only the data of the considered installation so that the concepts used in the partial ontology are relatively partial since not taking into account account all the relevant measures.
- a set of data is collected from several separate installations, and preferably from each installation.
- the data collected relates to the equipment 36 and more specifically to the maintenance and / or repair of the equipment 36.
- the data collected are data relating to the environment of the equipment 36, the origin of the equipment 36, the equipment history 36 and the malfunctions observed on the equipment 36.
- the environmental data of the equipment 36 is, for example, the temperatures or pressures of the atmosphere to which the equipment 36 has been subjected.
- the data relating to the origin of the equipment 36 are, for example, the manufacturer of the equipment 36 or the aircraft 34 in which the equipment 36 has been installed.
- the history of the equipment 36 may include data relating to the operating time of the equipment 36 or to the number of maintenances performed on the equipment 36.
- the malfunction data observed on the equipment 36 include by way of illustration all the abnormal measurements obtained during the tests of the equipment 36.
- the data collected also include the data for a device 36 of the same nature as the equipment 36 considered.
- the collected data includes measurements by sensors, whether measurements of the environment of the equipment 36 or measurements on the equipment 36 itself.
- heterogeneous it is understood that the format of each data is different, for example a history, a text or an array of a spreadsheet.
- the data is converted into a single format for data mining.
- the partial ontologies provided are filled by the ontologies collected data.
- an operator usually an expert in the field, establishes a table of correspondences between the possible data and the partial ontologies.
- the system 10 uses the look-up table to automatically fill each ontology.
- the gathering phase involves the implementation of two learning techniques, the first technique being unsupervised and the second technique being supervised.
- the gathering phase comprises a subgroup distribution step, a connection step, a learning step and a test step.
- sub-step of approximation a sub-step of learning.
- a similar concept of each partial ontology is compared to obtain groups, a group grouping together all the data associated with concepts considered to be close or logically related to one another.
- the associated data is the data that has been associated during the filling step.
- Concepts considered to be close or logically related to each other are the interesting concepts for which it is desired to learn a relationship between them.
- the supervisor can also guide or decide which concepts he wants to analyze.
- the reconciliation is done by a supervisor.
- the first learning technique on each group is implemented to obtain subgroups of data sharing common characteristics.
- Each subgroup corresponds to a concept, this concept being most often different from a concept contained in partial ontologies.
- the first learning technique is an unsupervised learning technique.
- the first learning technique is any learning technique that allows hierarchical classification. Principal component analysis is an example.
- a supervisor establishes a learning database and a test database by introducing relationships between the subgroup data.
- the distribution between the learning base and the test database is, for example, 60% to 40%.
- the second learning technique is applied on the basis of learning data to obtain a global ontology associating each subgroup with a relation to the other subgroups, that is to say - to say a relation between a concept and the other concepts.
- the second learning technique is supervised.
- the database gives the action corresponding to each test, this action will also correspond to a subgroup of actions: ai, a 2 , ..., a m .
- a relationship between the groups is established, depending on how they capture the data provided by the expert. Theoretically, thousands of relationships between two equally valid subgroups exist. Also a preference between them is used. Consequently, a selection criterion is defined according to the nature of the relationships (number of data involved in particular). The supervisor can also adjust the preference criteria based on his experience.
- a step of testing the global ontology is then implemented using the test database.
- errors can be detected, such errors coming, for example, from an incomplete model (ie lack of relationships or poorly distributed subgroups) or an error in the input Datas.
- Errors are detected using the relationships obtained in the previous step. Indeed, any data that does not respond to a relationship when the data should answer it is an error. It should be noted that the larger the number of relations to which a data item does not respond, the greater the error, so that the test makes it possible to determine several levels of error.
- the supervisor modifies the subclasses and the other steps of the collection phase are implemented.
- the operation phase comprises a supply step and a conversion step.
- At least one piece of data originating from an installation is provided.
- the global ontology is used to convert data originating from an installation into information relating to the control of malfunctions of the equipment 36.
- the information relating to the control of malfunctions of the equipment 36 is part of the group consisting of:
- the control method therefore makes it possible to better control malfunctions of the equipment 36 whether in maintenance or repair since the ontology used is a global ontology and not a partial ontology.
- the operation phase includes a step of implementing an action on the equipment 36 according to each piece of information.
- an information is a suggestion information of an action and the action implemented during the exploitation phase does not comply with the suggested action
- the distribution and assembly phases are implemented. again taking into account the action implemented during the exploitation phase.
- control method comprises a control of the equipment 36 according to at least one of the information relating to the control of malfunctions of the equipment 36.
- the method uses a so-called global ontology which makes it possible to characterize a dysfunction and / or the manner of treating such a dysfunction.
- an ontology is not a model of the function of a device to be improved but a function associating with parameters such as temperature, the test result, the manufacturer or the age of the equipment, predictions of malfunctions and the associated corrective measures.
- the method also applies to the maintenance of other equipment such as a ship or kitchen appliances provided that the equipment is brought to be used in a plurality of facilities.
- the facilities are the construction site, the maintenance center and the warehouse of the repair parts supplier while, for the kitchen, the facilities are the housing containing the kitchen and the different warehouses of the suppliers of each appliance.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Debugging And Monitoring (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FR1800546A FR3082021B1 (fr) | 2018-06-01 | 2018-06-01 | Procede de controle des dysfonctionnements d'un equipement et dispositifs associes |
| PCT/EP2019/064070 WO2019229174A1 (fr) | 2018-06-01 | 2019-05-29 | Procédé de contrôle des dysfonctionnements d'un équipement et dispositifs associés |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP3803630A1 true EP3803630A1 (fr) | 2021-04-14 |
Family
ID=65443869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP19730699.6A Ceased EP3803630A1 (fr) | 2018-06-01 | 2019-05-29 | Procédé de contrôle des dysfonctionnements d'un équipement et dispositifs associés |
Country Status (3)
| Country | Link |
|---|---|
| EP (1) | EP3803630A1 (fr) |
| FR (1) | FR3082021B1 (fr) |
| WO (1) | WO2019229174A1 (fr) |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102014208034A1 (de) * | 2014-04-29 | 2015-10-29 | Siemens Aktiengesellschaft | Verfahren zum Bereitstellen von zuverlässigen Sensordaten |
| US10460255B2 (en) * | 2016-07-29 | 2019-10-29 | Splunk Inc. | Machine learning in edge analytics |
-
2018
- 2018-06-01 FR FR1800546A patent/FR3082021B1/fr active Active
-
2019
- 2019-05-29 EP EP19730699.6A patent/EP3803630A1/fr not_active Ceased
- 2019-05-29 WO PCT/EP2019/064070 patent/WO2019229174A1/fr not_active Ceased
Non-Patent Citations (4)
| Title |
|---|
| ANONYMOUS: "Apprentissage semi-supervisé - Wikipédia", 3 July 2017 (2017-07-03), XP093060114, Retrieved from the Internet <URL:http://web.archive.org/web/20170703024046/https://fr.wikipedia.org/wiki/Apprentissage_semi-supervisé> [retrieved on 20230703] * |
| ANONYMOUS: "Ontologie (informatique) - Wikipédia", 3 October 2017 (2017-10-03), XP055940454, Retrieved from the Internet <URL:https://web.archive.org/web/20171003205455/https://fr.wikipedia.org/wiki/Ontologie_(informatique)> [retrieved on 20220708] * |
| MORGUN IVAN: "Types of machine learning algorithms | en.proft.me", 25 March 2018 (2018-03-25), XP093060118, Retrieved from the Internet <URL:https://web.archive.org/web/20180325145548/https://en.proft.me/2015/12/24/types-machine-learning-algorithms/> [retrieved on 20230703] * |
| See also references of WO2019229174A1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| FR3082021A1 (fr) | 2019-12-06 |
| WO2019229174A1 (fr) | 2019-12-05 |
| FR3082021B1 (fr) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11790256B2 (en) | Analyzing test result failures using artificial intelligence models | |
| FR2869698A1 (fr) | Procede pour le controle et le diagnostic de machines | |
| FR3013140A1 (fr) | Systeme et procede de diagnostic de panne aeronef | |
| Márquez | Digital maintenance management | |
| Marquez et al. | Digital twins in condition-based maintenance apps: A case study for train axle bearings | |
| Li et al. | Incident ticket analytics for it application management services | |
| Nicoletti | Supply Network 5.0 Life Cycle | |
| Kumar et al. | Transforming Data Analysis through AI-Powered Data Science | |
| WO2021180441A1 (fr) | Mises a jour de bases de donnees de navigation | |
| CN117194382A (zh) | 中台数据处理方法、装置、电子设备及存储介质 | |
| Urbani et al. | Maintenance-management in light of manufacturing 4.0 | |
| Shihab | An exploration of challenges limiting pragmatic software defect prediction | |
| US20220414504A1 (en) | Identifying traits of partitioned group from imbalanced dataset | |
| FR2990547A1 (fr) | Systeme de maintenance centralisee parametrable destine a un aeronef | |
| CN114265891A (zh) | 基于多源数据融合的智慧车间系统、方法及存储介质 | |
| EP3588387A1 (fr) | Procédé de test d'un système électronique de contrôle du trafic aérien, dispositif électronique et plate-forme associés | |
| EP3803630A1 (fr) | Procédé de contrôle des dysfonctionnements d'un équipement et dispositifs associés | |
| Sun | Designing Inclusive Interfaces: Accessibility Challenges and Solutions in Digital Products | |
| CN119887115A (zh) | 一种基于人工智能与大数据的项目管理系统 | |
| CN119204646A (zh) | 用于无人机研发制造企业的数字化智能管理系统及方法 | |
| Tichomirov et al. | The science of smooth driving: a taxonomy for anomaly detection in endurance run time series data | |
| EP3853784B1 (fr) | Procédé d'analyse des dysfonctionnements d'un système et dispositifs associés | |
| Xu et al. | Digital Twin technologies in enhancing supply chain resilience | |
| Salonen | On the Need for Human Centric Maintenance Technologies | |
| Fernandes et al. | Impact of Non-Fitting Cases for Remaining Time Prediction in a Multi-Attribute Process-Aware Method. |
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: 20201201 |
|
| 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 |
|
| AX | Request for extension of the european patent |
Extension state: BA ME |
|
| 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: 20220714 |
|
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R003 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED |
|
| 18R | Application refused |
Effective date: 20240119 |