WO2021100800A1 - 故障確率評価システム - Google Patents
故障確率評価システム Download PDFInfo
- Publication number
- WO2021100800A1 WO2021100800A1 PCT/JP2020/043161 JP2020043161W WO2021100800A1 WO 2021100800 A1 WO2021100800 A1 WO 2021100800A1 JP 2020043161 W JP2020043161 W JP 2020043161W WO 2021100800 A1 WO2021100800 A1 WO 2021100800A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- maintenance
- failure probability
- load
- item
- failure
- Prior art date
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 36
- 238000012423 maintenance Methods 0.000 claims abstract description 140
- 230000001186 cumulative effect Effects 0.000 claims abstract description 57
- 230000000694 effects Effects 0.000 claims abstract description 55
- 230000004083 survival effect Effects 0.000 claims abstract description 40
- 238000005457 optimization Methods 0.000 claims abstract description 13
- 239000006185 dispersion Substances 0.000 claims abstract description 12
- 238000011084 recovery Methods 0.000 claims abstract description 10
- 238000009825 accumulation Methods 0.000 claims abstract description 6
- 230000001629 suppression Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 51
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 7
- 238000012937 correction Methods 0.000 abstract description 13
- 238000004458 analytical method Methods 0.000 description 11
- 238000004140 cleaning Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000009826 distribution Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000005461 lubrication Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/219—Managing data history or versioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
Definitions
- the present invention relates to a technique for evaluating a failure probability for a device to be maintained. Failures include defects such as so-called failures. In addition, maintenance is also included before and after, and repairs are also included.
- Patent Document 1 describes an invention for identifying a failure probability function by performing survival time analysis in consideration of such a time-varying operating state. As described above, in Patent Document 1, sensor data is used for estimating the number of failures and the remaining life, and an appropriate load factor is automatically searched.
- the classification of maintenance is not limited to the distinction between preventive maintenance and post-maintenance defined by the timing of implementation.
- At least one of “cumulative operating time” and “cumulative load” is corrected in consideration of maintenance of the device or its constituent elements (hereinafter referred to as items). Perform life prediction.
- the “cumulative operating time” means the operating time during maintenance.
- correction includes pseudo-returning time, delaying deterioration, and changing the load. Further, in order to give these changes, it is also one aspect of the present invention to make corrections according to the maintenance type (maintenance method) of the maintenance to be considered.
- the maintenance to be considered includes the maintenance carried out and the planned maintenance.
- the configuration described in the claims is adopted. That is, it is a failure probability evaluation system that evaluates the failure probability of an item, and maintenance event data including the maintenance method for maintenance of the item and the time of the maintenance, the state related to the failure of the item, and the failure including the time of occurrence of the state.
- It is a failure probability evaluation system having a means for calculating a function.
- the present invention also includes a method using the present system and a program product for executing this method.
- Configuration diagram of an example of the failure probability evaluation system in the embodiment of the present invention The figure which shows the failure event data 4 and maintenance event data 3 used in the Example of this invention.
- the figure which shows the survival time data in the Example of this invention Schematic diagram showing the relationship between failure occurrence and maintenance implementation in the embodiment of the present invention and operating time. Schematic diagram illustrating the calculation of the equivalent cumulative operating time based on the residual damage amount in the embodiment of the present invention.
- Configuration diagram of an example of the display unit in the embodiment of the present invention Configuration diagram of an example of the failure probability evaluation system in the embodiment of the present invention
- FIG. 1 shows an example of the configuration of the failure probability evaluation system based on this embodiment.
- the failure event database 5 stores failure event data 4 including the time when an item failure occurs.
- the maintenance event database 6 records maintenance event data 3 in which maintenance execution time data and maintenance method data are paired. In some cases, as shown in FIG. 2, the information of the operator in charge of maintenance may also be recorded.
- the maintenance types are set as three types here, this embodiment does not impose any limitation on the number of maintenance types.
- a method may be adopted in which the operator 2 manually inputs data to both databases (5, 6) based on the item monitoring result and the maintenance implementation.
- the survival time data generation unit 7 generates the following data based on the failure event data 4 data stored in the failure event database 5 and the maintenance event data 3 stored in the maintenance event database 6. It is the survival time data 8 in which the cumulative operating time of the item, the state (outcome) after the lapse of the operating time, and the maintenance method are paired as shown in FIG.
- the outcome is a label indicating whether the item has failed or was alive at the time when a certain cumulative operating time has elapsed. If the item is operated while being maintained, it will be labeled as alive (pre-maintenance) because the item has not failed at that point when pre-maintenance is performed.
- the dataset used for normal survival analysis it is sufficient for the dataset used for normal survival analysis to include a pair of cumulative uptime and outcomes.
- the maintenance method is included in the data set at the same time. As described above, when there is a high possibility that the maintenance effect will differ depending on the operator who performed the maintenance, the information of the operator who performed the maintenance may be included as shown in FIG.
- Figure 4 schematically shows the relationship between the cumulative operating time of items and the occurrence of failures and the timing of maintenance. For example, at time t 0 , after a new item is replaced for maintenance, the life of the item can be expected to be relatively long. On the other hand, after disassembling and cleaning (t 2 ) and simple cleaning (t 1 ) as maintenance, the life of the item is expected to be relatively short.
- the failure probability density function obtained by the survival time analysis must be a probability density function with a large degree of dispersion represented by indicators such as variance, standard deviation, and fluctuation error.
- FIG. 5 schematically shows an example of a method for correcting the cumulative operating time.
- the degradation cleaning was performed at the time t 2 in FIG. 5, consider the fault that occurred subsequent time t 3.
- the damage corresponding to the operating time X 1 remains immediately after the disassembly and cleaning is performed (this is defined as the residual damage amount).
- the damage residual amount X i defined for each of the i types of maintenance methods is a parameter (maintenance effect parameter 11) that quantitatively expresses the maintenance effect.
- the equivalent cumulative operating time Te, n cannot be calculated concretely at this stage. Therefore, the corrected survival time data 10 is generated after temporarily giving an initial value set by using a random number or the like to the damage residual amount X i.
- the corrected survival time data 10 is survival time data including the corrected equivalent cumulative operating time and outcome as shown in FIG.
- the failure probability function identification unit 12 identifies the failure probability function 13 based on the method of survival time analysis.
- Survival time analysis is a statistical method for identifying a survival curve (reliability function) and a failure probability function from survival time data as shown in FIG. 3 or FIG. This can be broadly divided into non-parametric methods such as the Kaplan-Meier method and parametric methods that assume some kind of probability distribution.
- the method is not limited, but since the calculation focusing on the degree of dispersion of the failure probability function is performed, the calculation of the degree of dispersion is performed on the probability distribution using indexes such as variance, standard deviation, and coefficient of variation. It is desirable to adopt a parametric method that can be easily performed below.
- the failure probability function identification unit 12 uses the dispersion degree index calculated based on the corrected survival time data 10 as the objective function, and continuously performs the optimization calculation to minimize it. Based on the calculation result of the dispersion degree index and the optimization calculation algorithm, the damage residual amount X i , which is an unknown parameter, is changed and passed to the maintenance effect correction unit 9. Subsequently, based on the corrected survival time data obtained again from the maintenance effect correction unit 9, the failure probability function is identified again, and the dispersion degree index is calculated and evaluated.
- the effect of conservation is modeled as the residual damage amount X i , but this embodiment does not limit the modeling method.
- the calculation by the maintenance effect correction unit 9 changes accordingly, but the failure probability function identification unit 12 uses the maintenance effect parameter 11 as an explanatory variable. Since the optimized calculation is performed, the calculation flow inside it does not change.
- the maintenance effect duration is taken as an example, and the failure probability function 13 is identified while correcting the cumulative operating time as the equivalent cumulative operating time by these maintenance effect parameters. explained.
- the method of modeling the conservation effect is not limited to these. Even with a maintenance effect modeling method other than those illustrated here, according to this embodiment, it is only necessary to change the calculation inside the maintenance effect correction unit 9.
- both of the plurality of types of conservation effect parameters based on the modeling method of the plurality of types of conservation effects may be used in combination.
- the survival time data generation unit 7, the maintenance effect correction unit 9, and the failure probability function identification unit 12 described above are each implemented as a computer program, but the implementation form on a specific computer is not limited. For example, it is an example of this embodiment that these programs are stored in the main storage device of a computer and the calculation according to each program is executed by a processor such as a CPU. However, since the failure probability function identification unit 12 needs to perform calculation processing having a relatively large calculation cost while repeatedly calling the maintenance effect correction unit 9, both of them may be implemented in the same computer. Ideal.
- the display unit 14 is specifically composed of a computer and a display device on which a screen drawing program is mounted, but the computer used here is different from each of the analysis units (7, 9, 12) described above. It doesn't matter.
- FIG. 8 shows an example of the display unit 14.
- the display unit 14 includes a failure probability function display unit 18 that displays the failure probability function 13 identified by the failure probability function identification unit 12, a failure probability display unit 19 that displays the current failure probability, and maintenance for each estimated maintenance item. It is composed of a maintenance item display unit 20 that displays effect parameters, an operation information display unit 21 that displays the current cumulative operating time and the last maintenance item performed, and the like.
- the failure probability function (F (t)) is displayed to make it easier to understand the possibility of failure of the item at the present time.
- the item failure probability function is useful information not only for calculating the failure probability and reliability, but also for predicting the remaining life and managing the appropriate parts inventory. Therefore, it is also effective to connect the failure probability evaluation system based on this embodiment to the remaining life prediction system 15, the parts inventory management system 16, and the operation maintenance plan management system 17), which are lower systems having these functions. That is, it is also possible to analyze the calculation result by utilizing AI or the like and apply it to some service. For example, by connecting to the remaining life prediction system 15, it is possible to realize a service for notifying the life of an item. Further, by connecting to the parts inventory management system 16, highly accurate management of parts used for item maintenance (part replacement) becomes possible. Further, by connecting the operation maintenance plan management system 17, appropriate operation management (including maintenance schedule creation) of items becomes possible. In addition, it can also be applied to asset management of items.
- Example 1 the damage recovery effect of maintenance was reflected in the failure probability function in the form of correcting the cumulative operating time.
- the cumulative damage to the item is constant over time.
- Patent Document 1 describes an invention for identifying a failure probability function by performing survival time analysis in consideration of such a time-varying operating state.
- a system for identifying a damage model composed of each physical quantity is described so that a failure probability function with a low degree of dispersion can be obtained based on a plurality of physical quantities measured by sensors attached to the device.
- FIG. 9 shows the configuration of an example of a failure probability evaluation system that can consider both the time-varying operating state and the maintenance effect.
- the cumulative damage here is a virtual amount obtained by accumulating the damage obtained by combining the time-series measurement data obtained by the measurement by the sensor over time.
- the damage model generation unit 25 generates a damage model based on the time-series operation data 24 recorded in the time-series operation database 23, and the cumulative operation time is converted into cumulative damage.
- the survival time data generation unit 7 generates survival time data based on the cumulative damage.
- Example 1 the cumulative damage is corrected based on the maintenance effect, and then the failure probability function is identified.
- the optimization calculation for minimizing the dispersal degree index of the failure probability function 13 was carried out with the maintenance effect parameter 11 as a variable.
- the damage model parameter (load parameter) 26 that defines the damage model is also added as a variable to perform the optimization calculation. With such a configuration, it is possible to obtain a failure probability function 13 with a smaller degree of dispersion while identifying the damage model and quantifying the maintenance effect.
- wind power generator is illustrated as an item in this embodiment, the application target of the present invention is not limited to this.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
このように,単一のアイテムに対して複数種類の保全方式が適用される場合,保全方式によってアイテムの状態回復の程度(保全効果)が異なることは明らかである。或いは,同一の保全方式であっても,作業者の熟練度によっても同様に保全効果が異なることがあり得る。仮に保全効果を定量的に表現することが可能であれば,なんらかの補正を行うことによって生存時間解析を適用することも可能である。しかし,実際には状態回復効果を保全内容毎に定量的に表現することは難しい。
一方,保全として分解清掃(t2)や簡易清掃(t1)を実施した後には,アイテムの寿命は相対的には短くなると期待される。通常の生存時間解析を行う場合,故障に至る以前にどのような保全が実施されたのかは考慮されない。したがって,必然的に生存時間解析によって得られる故障確率密度関数は,分散や標準偏差,変動誤差といった指標によって表される散布度の大きい確率密度関数とならざるを得ない。
特許文献1には,このような時間変化する稼働状態を考慮した上で,生存時間解析を行って故障確率関数を同定するための発明が記載されている。この発明では,機器に取り付けられたセンサによって計測された複数の物理量に基づき,散布度の少ない故障確率関数が得られるように各物理量から構成されるダメージモデルを同定するシステムが記載されている。つまり,アイテムに対する負荷とその発生時期を含む負荷イベントデータを用いて,負荷パラメータを有するダメージモデルを生成していると表現できる。したがって,本実施例に基づく図1のシステムと,特許文献1に記載されたシステムを組み合わせれば,時々刻々変化するダメージの累積と,保全によるダメージの回復効果や蓄積抑制効果の双方を考慮した,より実用的な故障確率関数の同定が実現できる。
2…オペレータ
3…保全イベントデータ
4…故障イベントデータ
5…故障イベントデータベース
6…保全イベントデータベース
7…生存時間データ生成部
8…生存時間データ
9…保全効果補正部
10…補正済み生存時間データ
11…保全効果パラメータ
12…故障確率関数同定部
13…故障確率関数
14…表示部
15…余寿命予測システム
16…部品在庫管理システム
17…運用保全計画管理システム
18…故障確率関数表示部
19…故障確率表示部
20…保全項目表示部
21…稼働情報表示部
22…プルダウンメニュー
23…時系列稼働データベース
24…時系列稼働データ
25…ダメージモデル生成部
26…ダメージモデルパラメータ
27…風力発電機
Claims (12)
- アイテムにおける故障確率を評価する故障確率評価システムであって,
前記アイテムに対する保全の保全方式および当該保全の時期を含む保全イベントデータおよび前記アイテムの故障に関する状態および当該状態の発生時期を含む故障イベントデータを受け付ける手段と,
前記保全イベントデータおよび前記故障イベントデータを用いて,前記アイテムの保全間の稼働時間を示す累積稼働時間,前記状態および前記保全方式を関連付けた生存時間データを生成する手段と,
前記累積稼働時間を,関連付けられた保全方式に基づいて補正して等価累積稼働時間を生成し,生成された前記等価累積稼働時間および前記関連付けられた保全方式を用いて前記アイテムの故障確率関数を算出する手段とを有することを特徴とする故障確率評価システム。 - 請求項1に記載の故障確率評価システムであって,
前記故障確率関数を算出する手段は,前記保全方式での保全によるアイテムの損傷回復効果または損傷蓄積抑制効果を定義付ける保全効果パラメータを用いて,前記等価累積稼働時間を生成することを特徴とする故障確率評価システム。 - 請求項2に記載の故障確率評価システムであって,
さらに,前記故障確率関数の散布度を変化させることで,前記保全効果パラメータに対する最適化処理を実行する手段を有することを特徴とする故障確率評価システム。 - 請求項3に記載の故障確率評価システムであって,
故障イベントデータを受け付ける手段は,前記アイテムに対する負荷および当該負荷の発生時期を含む負荷イベントデータを受け付け,
前記生存時間データを生成する手段は,前記負荷イベントデータを用いて,前記アイテムに対する負荷を定義付ける負荷パラメータを有するダメージモデルを生成し,前記生存時間データとして,前記負荷イベントデータを用いて,前記アイテムに対する累積負荷と前記状態を関連付けた生存時間データを生成し,
前記最適化処理を実行する手段は,さらに前記負荷パラメータに対する最適化処理を実行することを特徴とする故障確率評価システム。 - 請求項2乃至4のいずれかに記載の故障確率評価システムであって,
前記故障確率関数を算出する手段は,前記累積稼働時間に対して,前記保全効果パラメータによって定義づけられる時間分の減算もしくは加算を行うことで等価累積稼働時間を算出することを特徴とする故障確率評価システム。 - 請求項4に記載の故障確率評価システムであって,
前記故障確率関数を算出する手段は,前記累積負荷を,前記負荷パラメータによって定義づけられる負荷の分だけ減算または加算することを特徴とする故障確率評価システム。 - アイテムにおける故障確率を評価する故障確率評価システムを用いた障確率評価方法であって,
前記アイテムに対する保全の保全方式および当該保全の時期を含む保全イベントデータおよび前記アイテムの故障に関する状態および当該状態の発生時期を含む故障イベントデータを受け付けるステップと,
前記保全イベントデータおよび前記故障イベントデータを用いて,前記アイテムの保全間の稼働時間を示す累積稼働時間,前記状態および前記保全方式を関連付けた生存時間データを生成するステップと,
前記累積稼働時間を,関連付けられた保全方式に基づいて補正して等価累積稼働時間を生成し,生成された前記等価累積稼働時間および前記関連付けられた保全方式を用いて前記アイテムの故障確率関数を算出するステップとを有することを特徴とする故障確率評価方法。 - 請求項7に記載の故障確率評価方法であって,
前記故障確率関数を算出するステップは,前記保全方式での保全によるアイテムの損傷回復効果または損傷蓄積抑制効果を定義付ける保全効果パラメータを用いて,前記等価累積稼働時間を生成することを特徴とする故障確率評価方法。 - 請求項8に記載の故障確率評価方法であって,
さらに,前記故障確率関数の散布度を変化させることで,前記保全効果パラメータに対する最適化処理を実行するステップを有することを特徴とする故障確率評価方法。 - 請求項9に記載の故障確率評価方法であって,
故障イベントデータを受け付けるステップは,前記アイテムに対する負荷および当該負荷の発生時期を含む負荷イベントデータを受け付け,
前記生存時間データを生成するステップは,前記負荷イベントデータを用いて,前記アイテムに対する負荷を定義付ける負荷パラメータを有するダメージモデルを生成し,前記生存時間データとして,前記負荷イベントデータを用いて,前記アイテムに対する累積負荷と前記状態を関連付けた生存時間データを生成し,
前記最適化処理を実行するステップは,さらに前記負荷パラメータに対する最適化処理を実行することを特徴とする故障確率評価方法。 - 請求項8乃至10のいずれかに記載の故障確率評価方法であって,
前記故障確率関数を算出するステップは,前記累積稼働時間に対して,前記保全効果パラメータによって定義づけられる時間分の減算もしくは加算を行うことで等価累積稼働時間を算出することを特徴とする故障確率評価方法。 - 請求項10に記載の故障確率評価方法であって,
前記故障確率関数を算出するステップは,前記累積負荷を,前記負荷パラメータによって定義づけられる負荷の分だけ減算または加算することを特徴とする故障確率評価方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/636,606 US12019595B2 (en) | 2019-11-21 | 2020-11-19 | Failure probability evaluation system |
AU2020389306A AU2020389306A1 (en) | 2019-11-21 | 2020-11-19 | Failure probability evaluation system |
EP20889132.5A EP4064141A4 (en) | 2019-11-21 | 2020-11-19 | FAILURE PROBABILITY ASSESSMENT SYSTEM |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2019210295A JP7339861B2 (ja) | 2019-11-21 | 2019-11-21 | 故障確率評価システム |
JP2019-210295 | 2019-11-21 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021100800A1 true WO2021100800A1 (ja) | 2021-05-27 |
Family
ID=75965321
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2020/043161 WO2021100800A1 (ja) | 2019-11-21 | 2020-11-19 | 故障確率評価システム |
Country Status (5)
Country | Link |
---|---|
US (1) | US12019595B2 (ja) |
EP (1) | EP4064141A4 (ja) |
JP (1) | JP7339861B2 (ja) |
AU (1) | AU2020389306A1 (ja) |
WO (1) | WO2021100800A1 (ja) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024106483A1 (ja) * | 2022-11-18 | 2024-05-23 | 日立建機株式会社 | 寿命予測システム |
CN117993220B (zh) * | 2024-03-18 | 2024-07-23 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | 融合加速寿命及加速退化的产品综合试验方法和装置 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005085178A (ja) * | 2003-09-11 | 2005-03-31 | Mitsubishi Electric Corp | 設備運用計画作成システム |
JP2019160128A (ja) | 2018-03-16 | 2019-09-19 | 株式会社日立製作所 | 故障確率評価システム及び方法 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7124059B2 (en) | 2000-10-17 | 2006-10-17 | Accenture Global Services Gmbh | Managing maintenance for an item of equipment |
JP2004191359A (ja) * | 2002-10-24 | 2004-07-08 | Mitsubishi Heavy Ind Ltd | リスクマネージメント装置 |
US7769568B2 (en) * | 2004-07-09 | 2010-08-03 | The United States Of America As Represented By The Secretary Of The Army | Employing a dynamic lifecycle condition index (CI) to accommodate for changes in the expected service life of an item based on observance of the item and select extrinsic factors |
WO2014118049A1 (en) * | 2013-02-01 | 2014-08-07 | Tetra Laval Holdings & Finance S.A. | A method for providing maintenance data |
US20160292652A1 (en) * | 2015-04-03 | 2016-10-06 | Chevron Pipe Line Company | Predictive analytic reliability tool set for detecting equipment failures |
US20190147413A1 (en) | 2017-11-13 | 2019-05-16 | Ge Energy Power Conversion Technology Ltd | Maintenance optimization system through predictive analysis and usage intensity |
-
2019
- 2019-11-21 JP JP2019210295A patent/JP7339861B2/ja active Active
-
2020
- 2020-11-19 WO PCT/JP2020/043161 patent/WO2021100800A1/ja unknown
- 2020-11-19 EP EP20889132.5A patent/EP4064141A4/en active Pending
- 2020-11-19 AU AU2020389306A patent/AU2020389306A1/en not_active Abandoned
- 2020-11-19 US US17/636,606 patent/US12019595B2/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005085178A (ja) * | 2003-09-11 | 2005-03-31 | Mitsubishi Electric Corp | 設備運用計画作成システム |
JP2019160128A (ja) | 2018-03-16 | 2019-09-19 | 株式会社日立製作所 | 故障確率評価システム及び方法 |
Non-Patent Citations (1)
Title |
---|
See also references of EP4064141A4 |
Also Published As
Publication number | Publication date |
---|---|
US20220300470A1 (en) | 2022-09-22 |
AU2020389306A1 (en) | 2022-03-17 |
EP4064141A4 (en) | 2023-11-29 |
JP7339861B2 (ja) | 2023-09-06 |
EP4064141A1 (en) | 2022-09-28 |
US12019595B2 (en) | 2024-06-25 |
JP2021082107A (ja) | 2021-05-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111542846B (zh) | 故障预测系统和故障预测方法 | |
JP6356304B2 (ja) | 保守有効性推定に基づく保守推奨システム | |
JP6865189B2 (ja) | 故障確率評価システム及び方法 | |
US10521490B2 (en) | Equipment maintenance management system and equipment maintenance management method | |
CN104966141B (zh) | 更新用于生成工业资产健康状况简档的模型的方法和系统 | |
US20170350789A1 (en) | Operating Wind Motors and Determining their Remaining Useful Life | |
US6684349B2 (en) | Reliability assessment and prediction system and method for implementing the same | |
KR101044744B1 (ko) | 신뢰도 기반 배전기자재 유지보수 시스템과 방법 | |
US20160292652A1 (en) | Predictive analytic reliability tool set for detecting equipment failures | |
JP7145821B2 (ja) | 故障確率評価システムおよびその方法 | |
WO2021100800A1 (ja) | 故障確率評価システム | |
US20130041783A1 (en) | System and method for dynamic spare part management | |
CN107992410B (zh) | 软件质量监测方法、装置、计算机设备和存储介质 | |
US9665842B2 (en) | Supply chain management anomaly detection | |
KR20140038265A (ko) | 고장관리장치 및 이의 고장관리방법 | |
JP2009086896A (ja) | コンピュータの障害予測システムおよび障害予測方法 | |
JP6975086B2 (ja) | 品質評価方法および品質評価装置 | |
WO2023286659A1 (ja) | 故障予測装置、故障予測方法、及びプログラム | |
Kaiser | A simulation study of predictive maintenance policies and how they impact manufacturing systems | |
JP7138727B2 (ja) | 品質管理装置、品質管理システム、品質管理方法、及び品質管理プログラム | |
JP2024057316A (ja) | 故障確率評価システムおよび故障確率評価方法 | |
CN117093504A (zh) | 一种面向缺陷度量的软件质量控制方法 | |
CN118575143A (zh) | 异常判定方法以及生产管理系统 | |
CN118541655A (zh) | 异常判定方法以及生产管理系统 | |
Babaei et al. | A new approach for constraining failure probability of a critical deteriorating system |
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: 20889132 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2020389306 Country of ref document: AU Date of ref document: 20201119 Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2020889132 Country of ref document: EP Effective date: 20220621 |