WO2022236443A1 - Intelligent production line failure prediction and assessment method based on hdp-hmm - Google Patents
Intelligent production line failure prediction and assessment method based on hdp-hmm Download PDFInfo
- Publication number
- WO2022236443A1 WO2022236443A1 PCT/CN2021/076657 CN2021076657W WO2022236443A1 WO 2022236443 A1 WO2022236443 A1 WO 2022236443A1 CN 2021076657 W CN2021076657 W CN 2021076657W WO 2022236443 A1 WO2022236443 A1 WO 2022236443A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- equipment
- hmm
- state
- hdp
- states
- Prior art date
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000006731 degradation reaction Methods 0.000 claims abstract description 28
- 230000015556 catabolic process Effects 0.000 claims abstract description 18
- 230000007704 transition Effects 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract 1
- 238000012423 maintenance Methods 0.000 description 7
- 230000007812 deficiency Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Definitions
- the invention relates to a HDP-HMM-based intelligent production line failure prediction method, belonging to the technical field of intelligent manufacturing failure prediction and management.
- the intelligent production lines developed and constructed by enterprises are developing rapidly, and more and more equipment are introduced into the production lines. requirements.
- the traditional "scheduled maintenance” is not suitable for the traditional scheduled maintenance mode of regular replacement because the intelligent production line involves complex maintenance techniques, high-value parts and professional high-skilled personnel, and the maintenance cost is high.
- the "post-maintenance" cannot meet modern production. Operation requirements, in the production process, the production line should have a high degree of automation. Once a certain link fails, it will immediately affect the overall production efficiency and may pose a threat to the personal safety of the staff. Therefore, in the operation of the intelligent manufacturing production system, the potential failure points in the production line can be effectively predicted, and a suitable maintenance plan can be formulated in advance. While reducing the impact on production work, the equipment can be repaired purposefully to improve the effective use of the equipment. Life expectancy, saving additional expenses for the enterprise.
- the present invention provides a fault prediction method based on HDP-HMM intelligent production line.
- a method for predicting faults in an intelligent production line based on HDP-HMM comprising the following steps:
- Step 1 Using HMM-based equipment degradation process description
- Step 2 Adopt HDP-HMM-based equipment failure prediction evaluation
- Described step one comprises:
- Step two includes:
- K is the number of states experienced in the entire life cycle of the equipment, the HMM n model corresponding to each state is trained, and the equipment degradation state identification library is established;
- T RULn is the remaining life of the equipment in the nth degradation state
- Tn is the duration of the nth degradation state of the equipment.
- the HDP-HMM-based intelligent production line failure prediction method provided by the present invention processes HMM sequence data through the HDP-HMM algorithm, overcomes the deficiency that the state number of the HMM model must be preset, and makes full use of the automatic generation of HDP. Based on the functional characteristics of the class number, the degradation state of the equipment can be obtained more accurately, and the remaining life prediction of the equipment in different degradation states of the production line is realized, and the prediction results are more effective and comprehensive.
- a method for predicting faults in an intelligent production line based on HDP-HMM comprising the following steps:
- Step 1 Using HMM-based equipment degradation process description
- Described step one comprises:
- Step 2 Adopt HDP-HMM-based equipment failure prediction evaluation
- Step two includes:
- K is the number of states experienced in the entire life cycle of the equipment, the HMM n model corresponding to each state is trained, and the equipment degradation state identification library is established;
- T RULn is the remaining life of the equipment in the nth degradation state
- Tn is the duration of the nth degradation state of the equipment.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An intelligent production line failure prediction and assessment method based on an HDP-HMM. The method comprises: step one, implementing device degradation process description based on an HMM; and step two, implementing device failure prediction and assessment based on an HDP-HMM. Sequence data of an HMM is processed by means of an HDP-HMM algorithm, thereby overcoming the defect of a state number of an HMM being necessarily set in advance, and giving play to the functional characteristics of automatically generating a cluster number by an HDP, such that a device degradation state is obtained more accurately, the remaining life of a production line device under different degradation states is predicted, and a prediction result is more effective and more comprehensive.
Description
本发明涉及一种基于HDP-HMM智能产线故障预估方法,属于智能制造故障预测与管理技术领域。 The invention relates to a HDP-HMM-based intelligent production line failure prediction method, belonging to the technical field of intelligent manufacturing failure prediction and management.
随着智能制造国家战略的推进实施,企业开发建设的智能化生产线发展迅猛,生产线中引入的设备也越来越多,其机械结构、智能化水平也越来越复杂,给维护工作提出了新的要求。传统"定时维护"因为智能生产线涉及维修技术工种复杂、高价值零部件和专业高技能人员协同,维护成本很高,不适合定期更换的传统定时维护模式,"事后维护"也不能满足现代化的生产作业要求,在生产过程中应为生产线自动化程度高,一旦某个环节发生故障,立刻会影响整体生产效率,可能会对工作人员的人身安全造成威胁。因此,在智能制造生产系统运营中能有效地预测到生产线中潜在的故障点,提前制定出合适的维护方案,在降低对生产工作影响的同时,有目的对设备进行检修,提高设备的有效使用寿命,为企业节省额外的开支。With the promotion and implementation of the national strategy of intelligent manufacturing, the intelligent production lines developed and constructed by enterprises are developing rapidly, and more and more equipment are introduced into the production lines. requirements. The traditional "scheduled maintenance" is not suitable for the traditional scheduled maintenance mode of regular replacement because the intelligent production line involves complex maintenance techniques, high-value parts and professional high-skilled personnel, and the maintenance cost is high. The "post-maintenance" cannot meet modern production. Operation requirements, in the production process, the production line should have a high degree of automation. Once a certain link fails, it will immediately affect the overall production efficiency and may pose a threat to the personal safety of the staff. Therefore, in the operation of the intelligent manufacturing production system, the potential failure points in the production line can be effectively predicted, and a suitable maintenance plan can be formulated in advance. While reducing the impact on production work, the equipment can be repaired purposefully to improve the effective use of the equipment. Life expectancy, saving additional expenses for the enterprise.
但是由于机械设备本身结构和机理的复杂性,影响系统运行的因素复杂多变,机器所表现出的状态行为具有大范围不确定性、高度非线性、动态时变性、强关联性等特征、从而造成通常难以建立精确、完备的机理模型,难以描述系统各部分之间的依赖关系,给精确预测带来更大的困难和挑战。如何有效地实现对智能生产线故障的预测,从而为设备的维护工作提供相应的依据,是一个亟待解决的问题。However, due to the complexity of the structure and mechanism of the mechanical equipment itself, the factors affecting the operation of the system are complex and changeable, and the state behavior exhibited by the machine has the characteristics of large-scale uncertainty, high nonlinearity, dynamic time-varying, and strong correlation. As a result, it is usually difficult to establish an accurate and complete mechanism model, and it is difficult to describe the dependencies between various parts of the system, which brings greater difficulties and challenges to accurate prediction. How to effectively realize the prediction of intelligent production line faults, so as to provide the corresponding basis for the maintenance of equipment, is an urgent problem to be solved.
目的:为了克服现有技术中存在的不足,本发明提供一种基于HDP-HMM智能产线故障预估方法。Purpose: In order to overcome the deficiencies in the prior art, the present invention provides a fault prediction method based on HDP-HMM intelligent production line.
技术方案:为解决上述技术问题,本发明采用的技术方案为:Technical solution: In order to solve the above-mentioned technical problems, the technical solution adopted in the present invention is:
一种基于HDP-HMM智能产线故障预估方法,包括如下步骤:A method for predicting faults in an intelligent production line based on HDP-HMM, comprising the following steps:
步骤一:采用基于HMM的设备退化过程描述;Step 1: Using HMM-based equipment degradation process description;
步骤二:采用基于HDP-HMM设备故障预测评估;Step 2: Adopt HDP-HMM-based equipment failure prediction evaluation;
所述步骤一包括:Described step one comprises:
1a:设置设备从正常状态到早期故障点P的临界点;1a: Set the critical point of the equipment from the normal state to the early failure point P;
1b:设置设备功能故障点F,监测从P点到F点的设备退化过程;1b: Set the equipment function failure point F, and monitor the equipment degradation process from point P to point F;
1c:采用HMM描述设备性能退化过程,假设HMM描述的设备全寿命周期共有S={1,2....K}个隐藏状态,{1}为设备的正常状态,{2,3....K-1}分别为设备K-2个依次严重程度的退化状,{k}为设备故障状态,到T时刻为止,产生的隐状态序列为{S1,S2.....ST},{X1,X2.....XT}是不同状态下出现的观测值X1关于状态S1条件独立,不同状态转换的转移概率矩阵决定,联合概率密度函数表示为1c: Use HMM to describe the degradation process of equipment performance, assuming that there are S={1,2...K} hidden states in the whole life cycle of the equipment described by HMM, {1} is the normal state of the equipment, {2, 3.. ..K-1} are the degradation states of equipment K-2 in order of severity respectively, {k} is the equipment failure state, until T time, the generated hidden state sequence is {S 1 , S 2 ..... S T }, {X 1 , X 2 ..... X T } is the observation value X 1 appearing in different states is conditionally independent with respect to state S 1 , and is determined by the transition probability matrix of different state transitions. The joint probability density function is expressed as
步骤二包括:Step two includes:
2a:构造HDP作为HMM参数的先验分布,以观测数据计算模型的后验概率,对HMM参数动态调整,确定设备状态数K(1为正常状态,K为故障状态);2a: Construct HDP as the prior distribution of HMM parameters, calculate the posterior probability of the model with observation data, dynamically adjust the HMM parameters, and determine the number of equipment states K (1 is normal state, K is fault state);
2b:采用不同状态对应的观测数据,对HMM进行参数基于Viterbi算法分别识别评估,K为设备全寿命周期所经历状态数,训练对应出每个状态的HMMn模型,建立设备退化状态识别库;2b: Using the observation data corresponding to different states, the parameters of the HMM are identified and evaluated based on the Viterbi algorithm. K is the number of states experienced in the entire life cycle of the equipment, the HMM n model corresponding to each state is trained, and the equipment degradation state identification library is established;
2c:利用设备全寿命数据,训练涵盖设备所有状态HMM模型,获得每个退化状态所持续时间,确定设备早起故障临界点P和功能故障点F;2c: Use the data of the whole life of the equipment to train the HMM model covering all states of the equipment, obtain the duration of each degraded state, and determine the early failure critical point P and functional failure point F of the equipment;
2d:针对当前观测序列,利用退化状态识别库计算P(O|λn),估计剩余寿命,识别设备当前状态,并提供预警评估,公式:2d: For the current observation sequence, use the degradation state identification library to calculate P(O|λ n ), estimate the remaining life, identify the current state of the equipment, and provide early warning evaluation, the formula:
式中:TRULn为设备处于第n个退化状态的剩余寿命,Tn为设备第n个退化状态的持续时间。In the formula: T RULn is the remaining life of the equipment in the nth degradation state, and Tn is the duration of the nth degradation state of the equipment.
有益效果:本发明提供的一种基于HDP-HMM智能产线故障预估方法,通过HDP-HMM算法处理HMM序列数据,克服了HMM模型状态数必须预先设定的不足,发挥了HDP自动生成聚类数目功能特点,更准确获得设备退化状态,实现了对产线设备不同退化状态下的剩余寿命预测,预估结果更有效和全面。Beneficial effects: the HDP-HMM-based intelligent production line failure prediction method provided by the present invention processes HMM sequence data through the HDP-HMM algorithm, overcomes the deficiency that the state number of the HMM model must be preset, and makes full use of the automatic generation of HDP. Based on the functional characteristics of the class number, the degradation state of the equipment can be obtained more accurately, and the remaining life prediction of the equipment in different degradation states of the production line is realized, and the prediction results are more effective and comprehensive.
下面结合附图对本发明作更进一步的说明。The present invention will be further described below in conjunction with the accompanying drawings.
一种基于HDP-HMM智能产线故障预估方法,包括如下步骤:A method for predicting faults in an intelligent production line based on HDP-HMM, comprising the following steps:
步骤一:采用基于HMM的设备退化过程描述;Step 1: Using HMM-based equipment degradation process description;
所述步骤一包括:Described step one comprises:
1a:设置设备从正常状态到早期故障点P的临界点;1a: Set the critical point of the equipment from the normal state to the early failure point P;
1b:设置设备功能故障点F,监测从P点到F点的设备退化过程;1b: Set the equipment function failure point F, and monitor the equipment degradation process from point P to point F;
1c:采用HMM描述设备性能退化过程,假设HMM描述的设备全寿命周期共有S={1,2....K}个隐藏状态,{1}为设备的正常状态,{2,3....K-1}分别为设备K-2个依次严重程度的退化状,{k}为设备故障状态,到T时刻为止,产生的隐状态序列为{S1,S2.....ST},{X1,X2.....XT}是不同状态下出现的观测值X1关于状态S1条件独立,不同状态转换的转移概率矩阵决定,联合概率密度函数表示为1c: Use HMM to describe the degradation process of equipment performance, assuming that there are S={1,2...K} hidden states in the whole life cycle of the equipment described by HMM, {1} is the normal state of the equipment, {2, 3.. ..K-1} are the degradation states of equipment K-2 in order of severity respectively, {k} is the equipment failure state, until T time, the generated hidden state sequence is {S 1 , S 2 ..... S T }, {X 1 , X 2 ..... X T } is the observation value X 1 appearing in different states is conditionally independent with respect to state S 1 , and is determined by the transition probability matrix of different state transitions. The joint probability density function is expressed as
步骤二:采用基于HDP-HMM设备故障预测评估;Step 2: Adopt HDP-HMM-based equipment failure prediction evaluation;
步骤二包括:Step two includes:
2a:构造HDP作为HMM参数的先验分布,以观测数据计算模型的后验概率,对HMM参数动态调整,确定设备状态数K(1为正常状态,K为故障状态);2a: Construct HDP as the prior distribution of HMM parameters, calculate the posterior probability of the model with observation data, dynamically adjust the HMM parameters, and determine the number of equipment states K (1 is normal state, K is fault state);
2b:采用不同状态对应的观测数据,对HMM进行参数基于Viterbi算法分别识别评估,K为设备全寿命周期所经历状态数,训练对应出每个状态的HMMn模型,建立设备退化状态识别库;2b: Using the observation data corresponding to different states, the parameters of the HMM are identified and evaluated based on the Viterbi algorithm. K is the number of states experienced in the entire life cycle of the equipment, the HMM n model corresponding to each state is trained, and the equipment degradation state identification library is established;
2c:利用设备全寿命数据,训练涵盖设备所有状态HMM模型,获得每个退化状态所持续时间,确定设备早起故障临界点P和功能故障点F;2c: Use the data of the whole life of the equipment to train the HMM model covering all states of the equipment, obtain the duration of each degraded state, and determine the early failure critical point P and functional failure point F of the equipment;
2d:针对当前观测序列,利用退化状态识别库计算P(O|λn),估计剩余寿命,识别设备当前状态,并提供预警评估,公式:2d: For the current observation sequence, use the degradation state identification library to calculate P(O|λ n ), estimate the remaining life, identify the current state of the equipment, and provide early warning evaluation, the formula:
式中:TRULn为设备处于第n个退化状态的剩余寿命,Tn为设备第n个退化状态的持续时间。In the formula: T RULn is the remaining life of the equipment in the nth degradation state, and Tn is the duration of the nth degradation state of the equipment.
以上所述仅是本发明的优选实施方式,应当指出:对于本技术领域的普通技术人员来说,在不脱离本发明原理的前提下,还可以做出若干改进和润饰,这些改进和润饰也应视为本发明的保护范围。The above is only a preferred embodiment of the present invention, it should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, some improvements and modifications can also be made, and these improvements and modifications are also possible. It should be regarded as the protection scope of the present invention.
Claims (1)
- [根据细则91更正 14.05.2021]
一种基于HDP-HMM智能产线故障预估方法,其特征在于:包括如下步骤:步骤一:采用基于HMM的设备退化过程描述;步骤二:采用基于HDP-HMM设备故障预测评估;所述步骤一包括:1a:设置设备从正常状态到早期故障点P的临界点;1b:设置设备功能故障点F,监测从P点到F点的设备退化过程;1c:采用HMM描述设备性能退化过程,假设HMM描述的设备全寿命周期共有S={1,2....K}个 隐 藏 状 态,{1}为设备的正常状态, {2,3....K-1}分别为设备K-2个依次严重程度的退化状,{k}为设备故障状态,到T时刻为止,产生的隐状态序列为{S1,S2.....ST},{X1,X2.....XT}是不同状态下出现的观测值X1关于状态S1条件独立,不同状态转换的转移概率矩阵决定,联合概率密度函数表示为 步骤二包括:2a:构造HDP作为HMM参数的先验分布,以观测数据计算模型的后验概率,对HMM参数动态调整,确定设备状态数K(1为正常状态,K为故障状态);2b:采用不同状态对应的观测数据,对HMM进行参数基于Viterbi算法分别识别评估, ,K为设备全寿命周期所经历状态数,训练对应出每个状态的HMMn模型,建立设备退化状态识别库;2c:利用设备全寿命数据,训练涵盖设备所有状态HMM模型,获得每个退化状态所持续时间,确定设备早起故障临界点P和功能故障点F;2d:针对当前观测序列,利用退化状态识别库计算P( ),估计剩余寿命,识别设备当前状态,并提供预警评估,公式: 式中: 为设备处于第n个退化状态的剩余寿命,Tn为设备第n个退化状态的持续时间。 [Corrected 14.05.2021 under Rule 91]
A method for predicting failures of intelligent production lines based on HDP-HMM, characterized in that: comprising the following steps: Step 1: using HMM-based equipment degradation process description; Step 2: using HDP-HMM-based equipment failure prediction evaluation; the steps One includes: 1a: setting the critical point from the normal state of the equipment to the early failure point P; 1b: setting the equipment function failure point F, and monitoring the equipment degradation process from point P to point F; 1c: using HMM to describe the equipment performance degradation process, Assume that there are S={1,2...K} hidden states in the whole life cycle of the equipment described by HMM, {1} is the normal state of the equipment, and {2,3...K-1} are the equipment K respectively. - 2 degenerate states in order of severity, {k} is the equipment failure state, until time T, the hidden state sequence generated is {S1, S2.....ST}, {X1, X2..... XT} is the observed value X1 appearing in different states is conditionally independent with respect to state S1, and is determined by the transition probability matrix of different state transitions. The joint probability density function is expressed as Step 2 includes: 2a: Construct HDP as the prior distribution of HMM parameters, calculate the posterior probability of the model with observed data, dynamically adjust the HMM parameters, and determine the number of equipment states K (1 is normal state, K is fault state); 2b : Using the observation data corresponding to different states, the parameters of the HMM are identified and evaluated based on the Viterbi algorithm. , K is the number of states experienced in the entire life cycle of the equipment, train the HMMn model corresponding to each state, and establish the equipment degradation state identification library; 2c: use the data of the entire life of the equipment to train the HMM model covering all states of the equipment, and obtain each degradation state Determine the critical point of early failure of the equipment P and the functional failure point F of the duration; 2d: For the current observation sequence, use the degraded state identification library to calculate P ( ), estimate the remaining life, identify the current state of the equipment, and provide an early warning assessment, the formula: In the formula: is the remaining life of the equipment in the nth degradation state, and Tn is the duration of the nth degradation state of the equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2021/076657 WO2022236443A1 (en) | 2021-05-13 | 2021-05-13 | Intelligent production line failure prediction and assessment method based on hdp-hmm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2021/076657 WO2022236443A1 (en) | 2021-05-13 | 2021-05-13 | Intelligent production line failure prediction and assessment method based on hdp-hmm |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022236443A1 true WO2022236443A1 (en) | 2022-11-17 |
Family
ID=84027794
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/076657 WO2022236443A1 (en) | 2021-05-13 | 2021-05-13 | Intelligent production line failure prediction and assessment method based on hdp-hmm |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2022236443A1 (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106885697A (en) * | 2017-03-17 | 2017-06-23 | 华东交通大学 | The performance degradation assessment method of the rolling bearing based on FCM HMM |
CN108763654A (en) * | 2018-05-03 | 2018-11-06 | 国网江西省电力有限公司信息通信分公司 | A kind of electrical equipment fault prediction technique based on Weibull distribution and hidden Semi-Markov Process |
CN110232416A (en) * | 2019-06-13 | 2019-09-13 | 中国人民解放军空军工程大学 | Equipment failure prediction technique based on HSMM-SVM |
CN112836380A (en) * | 2021-02-15 | 2021-05-25 | 苏州优它科技有限公司 | Fault estimation and maintenance method for intelligent manufacturing production line |
-
2021
- 2021-05-13 WO PCT/CN2021/076657 patent/WO2022236443A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106885697A (en) * | 2017-03-17 | 2017-06-23 | 华东交通大学 | The performance degradation assessment method of the rolling bearing based on FCM HMM |
CN108763654A (en) * | 2018-05-03 | 2018-11-06 | 国网江西省电力有限公司信息通信分公司 | A kind of electrical equipment fault prediction technique based on Weibull distribution and hidden Semi-Markov Process |
CN110232416A (en) * | 2019-06-13 | 2019-09-13 | 中国人民解放军空军工程大学 | Equipment failure prediction technique based on HSMM-SVM |
CN112836380A (en) * | 2021-02-15 | 2021-05-25 | 苏州优它科技有限公司 | Fault estimation and maintenance method for intelligent manufacturing production line |
Non-Patent Citations (2)
Title |
---|
SUN ZAIDONG; ZHANG NING: "Analysis of the Health Status of Railway Vehicle Bearings Based on Improved HDP-HMM", 2018 5TH INTERNATIONAL CONFERENCE ON SYSTEMS AND INFORMATICS (ICSAI), IEEE, 10 November 2018 (2018-11-10), pages 507 - 513, XP033490054, DOI: 10.1109/ICSAI.2018.8599488 * |
WANG HENG, ZHOU YIWEN;QU JIAMING;JI YUN: "HengA prognostic method of mechanical equipment based on HDP-HMM", JOURNAL OF VIBRATION AND SHOCK, vol. 38, no. 8, 30 April 2019 (2019-04-30), pages 173 - 179, XP093003209, DOI: 10.13465/j.cnki.jvs.2019.08.026 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20190258945A1 (en) | Fault diagnosis apparatus and machine learning device | |
Chuang et al. | Condition-based maintenance optimization for continuously monitored degrading systems under imperfect maintenance actions | |
CN101753382B (en) | Method for establishing adaptive network failure monitoring and positioning security model | |
JP2010166702A (en) | Power supply risk evaluation system of power facility | |
CN110320893B (en) | Thermal power generating unit equipment maintenance method based on RCM | |
CN111581889A (en) | Fault prediction method, system and equipment for heating equipment assembly | |
CN116308304A (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
CN112836380A (en) | Fault estimation and maintenance method for intelligent manufacturing production line | |
CN115453356A (en) | Power equipment running state monitoring and analyzing method, system, terminal and medium | |
CN115630716A (en) | Intelligent generation method and device for equipment maintenance plan | |
WO2022236443A1 (en) | Intelligent production line failure prediction and assessment method based on hdp-hmm | |
CN110427689B (en) | Method for monitoring and diagnosing gas turbine unit group based on new information technology | |
CN116468408A (en) | RPA-based automatic generation method for power outage operation ticket | |
CN113374543B (en) | Aeroengine part maintenance method based on time-varying fault rate model | |
CN104408289B (en) | A kind of modified opportunity maintenance method for introducing correction maintenance | |
CN108960669A (en) | A kind of maintenance of equipment towards reliable sexual involution and process control federation policies optimization method | |
CN113793003A (en) | Toughness improvement-oriented electric power system maintenance and operation cooperative decision method | |
Shi et al. | A Dynamic Maintenance Strategy for Multi-Component Systems Using a Genetic Algorithm. | |
CN114138621A (en) | System fault behavior double-clock simulation modeling method considering internal degradation and external impact | |
CN112944603A (en) | Air conditioner health assessment method for rail transit | |
WO2023039690A1 (en) | Vulnerability assessment-based method for determining manufacturing system health state | |
Li et al. | Arena-based modeling of the maintenance operation for a wind farm | |
CN114414938B (en) | Dynamic response method and system for power distribution network faults | |
CN111210025A (en) | Method for calculating blind detection rate for state maintenance of power transmission and transformation equipment | |
CN109543857A (en) | A kind of preventative dynamic opportunity maintenance method of the series-parallel manufacture system of value driving |
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: 21941027 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: 21941027 Country of ref document: EP Kind code of ref document: A1 |