CN106845651A - The method of the anticipation of equipment state variation tendency, system architecture and maintenance policy optimization - Google Patents
The method of the anticipation of equipment state variation tendency, system architecture and maintenance policy optimization Download PDFInfo
- Publication number
- CN106845651A CN106845651A CN201611174646.7A CN201611174646A CN106845651A CN 106845651 A CN106845651 A CN 106845651A CN 201611174646 A CN201611174646 A CN 201611174646A CN 106845651 A CN106845651 A CN 106845651A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- equipment
- data
- fault
- failure
- 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.)
- Pending
Links
Classifications
-
- 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
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The present invention gives the method for a kind of anticipation of equipment state variation tendency, system architecture and maintenance policy optimization, equipment/systems reliability analysis and maintenance policy formulating method is integrated together, it is input to be formed with data, the closed-loop policy that self iteration for be simulated, optimizing updates.
Description
Technical field
The present invention relates to the method for a kind of anticipation of equipment state variation tendency, system architecture and maintenance policy optimization.
Background technology
The existing technology of in the market is not equipment/systems reliability analysis (RAM) and maintenance policy formulating method (RCM)
Combining for both systems, is input, simulation, the Systematization method of optimization, without real without being formed with data
Existing self iteration optimization and closed loop management.
Mainly there are following a few point defects:
Fail the driving force analyzed as equipment dependability using data, be mainly manifested in the imperfect of business data, not just
Really, the problems such as form disunity, storage dispersion;It is fail-safe analysis service not have the data base management system of specification;Without profit
System information is constantly updated with real time data so as to obtain the real-time state change of equipment;Maintenance policy could not be finger with data
Lead so as to accurately can not targetedly solve failure problems;Not the cycle to maintenance policy optimize analysis.
The content of the invention
The technical problem to be solved in the present invention be to provide a kind of anticipation of simple equipment state variation tendency, system architecture and
The method of maintenance policy optimization.
In order to solve the above technical problems, the present invention provides a kind of anticipation of equipment state variation tendency, system architecture and maintenance
The method of policy optimization, by both equipment/systems reliability analysis and maintenance policy the formulating method system integration together, forms one
Set can be input with data, the closed-loop policy that self iteration for be simulated, optimizing updates.
The method optimized as the anticipation of present device state variation tendency, system architecture and maintenance policy further changes
Enter;The equipment/systems reliability analysis step is as follows:A. data are collected;B. the data acquisition facility for being obtained by step a
And its failure pests occurrence rule of parts;C. RBD models are set up;D. it is simulated using the RBD models in step c, is optimized;e.
Result according to step d is analyzed, and obtains KPI, sends associated alarm;F. in the associated alarm and step a that step e are sent
The data of collection are collectively as the fault message with equipment as the first floor system of highest unit;G. by described in step b
The function and functional fault of equipment and its parts carry out accurate definition, realize effective judgement and identification to the system failure.
The method optimized as the anticipation of present device state variation tendency, system architecture and maintenance policy further changes
Enter;The maintenance policy formulating method is as follows:H. according to step f gained fault messages, fault mode is carried out with failure effect point
Analysis;I. maintenance policy is formulated;J. the associated alarm for being sent by step e triggers corresponding maintenance policy in step i;K. maintenance policy
Formulating method is formed and selects different maintenance policies, and formulation section for different faults with the result of fail-safe analysis to be oriented to
Maintenance work interval is learned, while determining the cycle of maintenance scheme and the spare part quantity of maintenance scheme application.
The method optimized as the anticipation of present device state variation tendency, system architecture and maintenance policy further changes
Enter;In the step a, the data of the collection include but is not limited to specification of equipment parameter, reliability data and mantenance data;With
The upper data source includes but is not limited to EAM systems, plant maintenance work order, equipment account, operational procedure, management of equipment maintenance
Paper document, enterprise accident/equipment fault analysis daily record, enterprise operation operation target, maintenance/operating standard, instrument factory quotient
According to and asset data database data, monitoring data.
The method optimized as the anticipation of present device state variation tendency, system architecture and maintenance policy further changes
Enter;In the step b, data processing step is as follows:The data obtained to step a using special algorithm are by fault mode, failure
Reason is analyzed, and show that the failure that each fault mode, failure cause, equipment are overall and packet where equipment is overall occurs
Rule, the time-consuming rule of maintenance, the time-consuming rule parameter of offline inspection;The failure pests occurrence rule, maintenance time-consuming rule, offline inspection
Time-consuming rule, the description type of Maintenance Resource consumption law parameter include and are not limited to Weibull distribution.
The method optimized as the anticipation of present device state variation tendency, system architecture and maintenance policy further changes
Enter;It is as follows the step of analogue simulation in the step d:Equipment fault is added in each square frame for the RBD models that step c sets up
The data such as the load of resource, equipment or component needed for the probabilistic model of generation, corresponding different type maintenance maintenance, using spy
Determining algorithm carries out analogue simulation to the RBD of system, obtains RBD analog simulation results;The result includes following data:System
Availability, system operation time, system downtime, number of times, the number of times of preventative maintenance, the reality of the maintenance of being modified property of system
When the monitoring maintenance frequency, the maintenance frequency, the expectation of system first-time fault, the phase in system failure cycle that cause of detection that cause
Prestige, the expectation in system maintenance cycle, the system number of starts, machine stop times, start and total expend the time, shut down and total expend time, standby
Part quantity consumed;Reliability of the system in different time points;Cause the equipment failure mode ranking that system downtime is most long;System
The average utilization of the system percentage of run time, system loading under different load;System be used for different type safeguard into
Originally, the cost of human resources, the cost of spare part used, year investment in fixed assets cost, the storehouse of spare part used by all types of maintenances
Storage cost, start cost, shutdown cost, shutdown loss, operating cost, totle drilling cost, sales volume, profit on sales data;For each
The similar analysis result of equipment.
The method optimized as the anticipation of present device state variation tendency, system architecture and maintenance policy further changes
Enter;KPI in the step e includes reliability, availability, maintainability, fault rate, production capacity, Life cycle cost.
The method optimized as the anticipation of present device state variation tendency, system architecture and maintenance policy further changes
Enter;The step h's is analyzed as follows:Abort situation clearly related to each functional fault, fault mode, failure cause,
Failure effect and fault level, and take which measure to prevent event according to failure mode and the determination of fault effects analysis result
Barrier, mitigates failure effect, or helps go to monitor failure.
The method optimized as the anticipation of present device state variation tendency, system architecture and maintenance policy further changes
Enter;The formulation maintenance policy of the step i is as follows:According to determining for the factors such as security, Environmental, feature and economic influence
Plan tree is analyzed, and is formed and selects different maintenance policies for different faults, and formulates scientific maintenance operation range.
The present invention carries out the side of equipment state variation tendency anticipation, system architecture and maintenance policy optimization with data as driving
Method, solves current device manager and fails equipment/systems reliability analysis (RAM) and maintenance policy formulating method (RCM)
It can be driving with data that both system integrations are formed a set of together, not, the closed loop that self iteration for be simulated, optimizing updates
The problem of method.
Present invention solves the technical problem that:
Method is data-centered, is collected by the data being collected into, arranged, extract device name, platform number,
Device type, packet and operating scheme information, and all of equipment maintenance record in specified time range is extracted, including
Maintenance time started, maintenance end time, maintenance type, fault type, equipment downtime, maintenance are time-consuming, belonging to failure
Fault reason information belonging to fault mode and failure.
All of the above information is aggregated into a tables of data or database, each failure of all devices is drawn by analysis
Failure pests occurrence rule, the dimension of the overall probability Distribution Model description of packet where pattern, failure cause, equipment entirety and equipment
Repair time-consuming rule and the time-consuming rule parameter of offline inspection.
The failure pests occurrence rule and reliability block diagram model of equipment, the i.e. combination of RBD models are obtained by analog simulation
Multinomial KPI (reliability, availability, maintainability, fault rate, production capacity, Life cycle cost), real time data is continually entered
In system, self iteration updates and is modeled simulation, and each data more new capital will embody variation tendency, is understood according to the trend
The ruuning situation of corresponding device;KPI is set to system operation simultaneously, system equipment not up to standard sends alarm to KPI.
Resulting fault message can to instruct determination by analysis to take maintenance policy, (formation be for different events with data
The different maintenance policy of barrier selection, and formulate scientific maintenance operation range).
In terms of maintenance policy, examined for preventative maintenance and point, optimize its preventative maintenance cycle and point overhaul period, led to
Cross simulation and compare the Different Results brought using different maintenance strategies, and optimal maintenance strategy is selected with this;And repair plan
Slightly include how selecting different maintenance modes for particular device, examine again how this formulates prevention for preventive maintenance and point
Property maintenance period and point overhaul period, for different maintenances, using the selection of different human resources, preventive maintenance and point inspection whether
By some device packets.
Brief description of the drawings
Specific embodiment of the invention is described in further detail below in conjunction with the accompanying drawings.
Fig. 1 is both equipment/systems reliability analysis (RAM) of the invention and maintenance policy formulating method (RCM) systems
It is integrated together, formed it is a set of can with data for input, be simulated, optimization self iteration renewal closed-loop policy schematic diagram;
Fig. 2 is the anticipation rule of equipment state, and with multinomial KPI (reliability, availability, maintainability, fault rate, product
Can, Life cycle cost) manifestation mode provide the user associated alarm with data be drive fail-safe analysis (RAM)
Schematic diagram;
Fig. 3 is, with the result of fail-safe analysis to be oriented to, to be formed and select different maintenance policies for different faults, and made
Scientific maintenance operation range is determined, while also can determine that the maintenance plan of the cycle of maintenance scheme and the spare part quantity of maintenance scheme application
Omit formulating method (RCM) schematic diagram;
Fig. 4 be with data be input, be simulated, optimization self iteration update closed-loop policy detailed schematic.
Specific embodiment
The technical scheme that embodiment 1, the present invention are provided is to the anticipation of equipment state variation tendency, system architecture or maintenance plan
The method for slightly optimizing, it is that both equipment/systems reliability analysis (RAM) and maintenance policy formulating method (RCM) are by one kind
System is integrated together, and it can be input with data to be formed a set of, the closed-loop policy that self iteration for be simulated, optimizing updates.
Specific Implement methodology is as follows:
First, equipment/systems reliability analysis (RAM):
A. data are collected:
The data include specification of equipment parameter, reliability data and mantenance data.
The above data source includes, but are not limited to EAM systems (the EAM systems of MAXIMO, SAP or other independent researches
System), plant maintenance work order, equipment account, operational procedure, management of equipment maintenance paper document, enterprise accident/equipment fault analysis
Daily record, enterprise operation operation target, maintenance/operating standard, equipment vendors' data and asset data database data (are built containing database
If), monitoring data.
Tidal data recovering, the arrangement that will be collected into, extract device name, platform number, device type, packet, operating scheme etc.
Information, and all of equipment maintenance record in specified time range is extracted, including at the end of maintenance time started, maintenance
Between, maintenance type, fault type, equipment downtime, maintenance time, the fault mode (Failure Mode) belonging to failure,
The information such as the failure cause (Failure Cause) belonging to failure are simultaneously aggregated into a form or database.
B. the data for being obtained to step a using special algorithm are classified by fault mode, failure cause etc. and are analyzed, so that
Draw each fault mode (Failure Mode) of all devices, failure cause (Failure Cause), equipment it is overall and
Failure pests occurrence rule, the time-consuming rule of maintenance, the time-consuming rule of offline inspection of the overall Weibull distribution description of packet where equipment etc.
(Weibull distribution is a kind of wider probability Distribution Model of coverage to parameter, is commonly used to the industrial various faults distribution of description
Rule, it is possible to simulate other probability Distribution Models such as exponential distribution).The described special algorithm includes being based on MLE
The data fitting algorithms of (Maximum Likelihood Estimation), the data based on RR (Rank Regression) are intended
Hop algorithm, automatically select in both preferably algorithm and (Non-linear is planned based on Nonlinear Dynamic
Programming the data fitting algorithms of MLE) are combined.
C. the overall failure pests occurrence rule of packet where the equipment and equipment that are obtained according to step b, and each component
Dependence, sets up RBD block diagrams, come the reliability of dependence in descriptive system between each component and each component with it is whole
The relation of system reliability.For example, certain system has A, tri- equipment of B, C, while operation.Any one failure in A, B device, be
System is all continued to run with, but load down 50%, if A, B device simultaneous faults, system-down;It is if C equipment faults
System is directly shut down.
D. the probabilistic model, corresponding of equipment fault generation is added in each square frame for the RBD models that step c sets up
The data such as the load of resource (personnel, spare part, time, cost etc.), equipment or component needed for different type maintenance maintenance, utilize
Special algorithm (by Monte Carlo simulation algorithm, the special algorithm such as artificial neural network, big data algorithm, and deep learning) is right
The RBD of system carries out analogue simulation.RBD analog simulation results are obtained, described result includes availability, the system operation of system
It is time, system downtime (and the downtime caused due to variant reason), the number of times of being modified property of system maintenance, pre-
Maintenance frequency, the expectation of system first-time fault that maintenance frequency that the number of times of anti-property maintenance, real-time monitoring cause, detection cause
(MTTFF), expectation (MTBF), the expectation in system maintenance cycle (MTBM), the system number of starts, the shutdown time in system failure cycle
Number, startup total consuming time, shutdown total consuming time, spare parts consumption quantity;Reliability of the system in different time points;Cause be
System downtime equipment failure mode ranking most long;The system percentage of run time, system loading under different load
Average utilization;System is used for cost that different type safeguards, the cost of human resources used by all types of maintenances, spare part used
Cost, year investment in fixed assets cost, the warehouse cost of spare part, start cost, shut down cost, shutdown loss, operating cost,
The data such as totle drilling cost, sales volume, profit on sales;And for the similar analysis result of each equipment.For example, in the case of step c
In, according to the time range of 60000 hours, carry out 100 simulations and calculate, A is obtained, the MTBF of B, C is respectively 4000 hours,
5000 hours and 8000 hours, failure was satisfied by exponential distribution;Maintenance duration is respectively fixes 8 hours, 8 hours and 16 hours.
Simulation can be obtained, and the availability of system is about 0.998.
E. the KPI numerical value needed for the result according to step d obtains project, the KPI numerical value is such as, including reliability, available
Property, one or several in maintainability, fault rate, production capacity, Life cycle cost (detailed programs can be discussed with client and determined
It is fixed newly-increased or delete KPI), and determine, to target standard, threshold value to be set, to not reaching project standard according to project demand
KPI sends associated alarm, points out the deviation of KPI;For example, in the case of step d, factory is wished by optimizing A, B, C
Maintenance scheme reduces totle drilling cost as far as possible on the premise of being not less than 98% ensureing system availability.So availability 98% is here
Be KPI to mark standard, and reduce totle drilling cost as optimization aim.Threshold value is set to by 98%, what simulation was obtained in present case is
System availability is 99.8%, more than threshold value, therefore will not trigger alarm.
F. the data collected in the associated alarm that step e is sent and step a collectively as with equipment be highest unit
The fault message of first floor system.
G. standard is carried out by the equipment and its function of parts and functional fault described in step b according to international standard
It is determined that it is adopted, include but are not limited to collapse, height output, low output, internal leakage, external leakage, vibration, noise, overheat, blocking
Deng effective judgement and identification of the realization to the system failure.
It is the anticipation rule that the fail-safe analysis (RAM) for driving provides equipment state with data, and (can with multinomial KPI
By property, availability, maintainability, fault rate, production capacity, Life cycle cost) manifestation mode provide the user associated alarm.
2nd, maintenance policy formulating method (RCM):
H. according to step f gained fault messages, fault mode is carried out with fault effects analysis (clearly with the event of each function
Hinder related abort situation, fault mode, failure cause, failure effect and fault level, and according to failure mode and failure after
Fruit analysis result determines to take which measure to prevent failure, mitigation failure effect, or helps how to go to monitor failure);
I. maintenance policy (the decision tree point according to factors such as security, Environmental, feature and economic influences is formulated
Analysis, forms and selects different maintenance policies for different faults, and formulate scientific maintenance operation range);
J. the associated alarm for being sent by step e triggers corresponding maintenance policy in step i;
K. maintenance policy formulating method is formed and selects different for different faults with the result of fail-safe analysis to be oriented to
Maintenance policy, and formulate scientific maintenance operation range, at the same also can determine that maintenance scheme cycle and maintenance scheme application it is standby
Number of packages amount.
Therefore, integrating the two method systems, formed it is a set of can with data for input, simulation, it is excellent
The closed-loop policy that self iteration changed updates.So enterprise is in the anticipation of equipment state variation tendency, system architecture or maintenance policy
A closed loop of itself continuous loop optimization can be reached in the problem of optimization, so as to reach the equipment control side of self sustainable development
Method.
The present invention is both equipment/systems reliability analysis (RAM) and maintenance policy formulating method (RCM) system integration one
Rise, it can be input with data to be formed a set of, and the closed-loop policy that self iteration for be simulated, optimizing updates is solved not with number
According to being to drive, it is impossible to the problem that the convectional reliability analytic band of accurate anticipation equipment state comes;Plant maintenance scheme utilizes data
Support can accurately suit the remedy to the case;Plant maintenance scheme after optimization has quantitative data to support the checking with analog simulation,
Bigger improves confidence of the administrative staff to analysis result;Comprehensive analysis result brings help to critical decision;Side
One closed loop procedure of method self-forming, such fail-safe analysis can be optimized constantly and perfect;The reliability following to enterprise
Framework is set up in analysis, reaches a process of self-perfection.
Finally, in addition it is also necessary to it is noted that listed above is only a specific embodiment of the invention.Obviously, the present invention
Above example is not limited to, there can also be many deformations.One of ordinary skill in the art can be straight from present disclosure
The all deformations derived or associate are connect, protection scope of the present invention is considered as.
Claims (9)
1. the method that the anticipation of equipment state variation tendency, system architecture and maintenance policy optimize, it is characterized in that:By equipment/system
Fail-safe analysis and maintenance policy formulating method are integrated, formed with data for input, be simulated, optimize self change
The closed-loop policy that generation updates.
2. the method that equipment state variation tendency according to claim 1 anticipation, system architecture and maintenance policy optimize, its
It is characterized in:The equipment/systems reliability analysis step is as follows:
A. data are collected;
B. the data acquisition facility and its failure pests occurrence rule of parts for being obtained by step a;
C. RBD models are set up;
D. it is simulated using the RBD models in step c, is optimized;
E. the result according to step d is analyzed, and obtains KPI, sends associated alarm;
F. the data collected in the associated alarm and step a that step e are sent are collectively as the bottom with equipment as highest unit
The fault message of system;
G. by carrying out accurate definition to the equipment and its function of parts and functional fault described in step b, realize to being
Effective judgement and identification of failure of uniting.
3. the method that equipment state variation tendency according to claim 2 anticipation, system architecture and maintenance policy optimize, its
It is characterized in:The maintenance policy formulating method is as follows:
H. the fault message according to step f carries out fault mode and fault effects analysis;
I. maintenance policy is formulated;
J. the associated alarm for being sent by step e triggers corresponding maintenance policy in step i;
K. maintenance policy formulating method selects different maintenance plans with the result of fail-safe analysis to be oriented to for different faults
Omit, and formulate scientific maintenance operation range, while the spare part quantity of the cycle of Optimal Maintenance scheme and maintenance scheme application.
4. the method that equipment state variation tendency according to claim 3 anticipation, system architecture and maintenance policy optimize, its
It is characterized in:In the step a, the data of the collection include but is not limited to specification of equipment parameter, reliability data and maintenance number
According to;
The above data source includes but is not limited to EAM systems, plant maintenance work order, equipment account, operational procedure, equipment dimension
Repair management paper document, enterprise accident/equipment fault analysis daily record, enterprise operation operation target, maintenance/operating standard, equipment
Manufacturer data and asset data database data, monitoring data.
5. the method that equipment state variation tendency according to claim 4 anticipation, system architecture and maintenance policy optimize, its
It is characterized in:In the step b, data processing step is as follows:
The data that step a is obtained are analyzed by fault mode, failure cause using special algorithm, draw each fault mode,
Failure cause, equipment are overall and packet where equipment is overall failure pests occurrence rule, the time-consuming rule of maintenance, offline inspection consumption
When rule parameter;
The failure pests occurrence rule, the time-consuming rule of maintenance, offline inspection time-consuming rule, the description of Maintenance Resource consumption law parameter
Type includes and is not limited to Weibull distribution.
6. the method that equipment state variation tendency according to claim 5 anticipation, system architecture and maintenance policy optimize, its
It is characterized in:It is as follows the step of analogue simulation in the step d:
Probabilistic model, the corresponding different type for adding equipment fault to occur in each square frame for the RBD models that step c sets up
The data such as the load of resource, equipment or component needed for maintenance maintenance, emulation mould is carried out using special algorithm to the RBD of system
Intend, obtain RBD analog simulation results;
The result includes and is not limited to following data:
The availability of system, system operation time, system downtime, number of times, the preventative dimension of the maintenance of being modified property of system
Maintenance frequency that maintenance frequency that the number of times repaiied, real-time monitoring cause, detection cause, the expectation of system first-time fault, system therefore
The expectation in barrier cycle, the expectation in system maintenance cycle, the system number of starts, machine stop times, startup total consuming time, shutdown always consume
Time-consuming, spare parts consumption quantity;
Reliability of the system in different time points;
Cause the equipment failure mode ranking that system downtime is most long;
The average utilization of the system percentage of run time, system loading under different load;
System is used for cost, the cost of human resources, the cost of spare part used, the year used by all types of maintenances that different type is safeguarded
Change investment in fixed assets cost, the warehouse cost of spare part, start cost, shut down cost, shutdown loss, operating cost, totle drilling cost,
Sales volume, profit on sales data;
For the similar analysis result of each equipment.
7. the method that equipment state variation tendency according to claim 6 anticipation, system architecture and maintenance policy optimize, its
It is characterized in:KPI in the step e includes reliability, availability, maintainability, fault rate, production capacity, Life cycle cost.
8. the method that equipment state variation tendency according to claim 7 anticipation, system architecture and maintenance policy optimize, its
It is characterized in:The step h's is analyzed as follows:
Abort situation clearly related to each functional fault, fault mode, failure cause, failure effect and fault level,
And take which measure to prevent failure according to failure mode and the determination of fault effects analysis result, mitigate failure effect, or
How help goes to monitor failure.
9. the method that equipment state variation tendency according to claim 8 anticipation, system architecture and maintenance policy optimize, its
It is characterized in:The formulation maintenance policy of the step i is as follows:
According to the decision tree analysis of the factors such as security, Environmental, feature and economic influence, formed for different faults choosing
Different maintenance policies are selected, and formulates scientific maintenance operation range.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611174646.7A CN106845651A (en) | 2016-12-19 | 2016-12-19 | The method of the anticipation of equipment state variation tendency, system architecture and maintenance policy optimization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611174646.7A CN106845651A (en) | 2016-12-19 | 2016-12-19 | The method of the anticipation of equipment state variation tendency, system architecture and maintenance policy optimization |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106845651A true CN106845651A (en) | 2017-06-13 |
Family
ID=59140593
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611174646.7A Pending CN106845651A (en) | 2016-12-19 | 2016-12-19 | The method of the anticipation of equipment state variation tendency, system architecture and maintenance policy optimization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106845651A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107358299A (en) * | 2017-06-16 | 2017-11-17 | 杭州培慕科技有限公司 | Pre-emptive maintenace closed-loop policy based on fault mode |
CN108673503A (en) * | 2018-05-22 | 2018-10-19 | 佛山科学技术学院 | A kind of industrial robot real-time fault detection method and device |
CN109190958A (en) * | 2018-08-23 | 2019-01-11 | 合肥好多帮信息科技有限公司 | A kind of troublshooting Intelligentized regulating and controlling system |
CN110378592A (en) * | 2019-07-12 | 2019-10-25 | 珠海培慕科技有限公司 | A kind of method of dynamic evaluation equipment Risk |
CN110390404A (en) * | 2019-07-12 | 2019-10-29 | 杭州培慕科技有限公司 | A kind of RCM in knowledge based library and data management |
CN112365182A (en) * | 2020-11-24 | 2021-02-12 | 中国舰船研究设计中心 | Marine equipment maintenance work type analysis method and device based on tasks and functions |
CN112633617A (en) * | 2019-09-24 | 2021-04-09 | 北京国双科技有限公司 | Maintenance strategy generation method and device, computer equipment and readable storage medium |
CN117424338A (en) * | 2023-10-18 | 2024-01-19 | 国网江苏省电力有限公司南通供电分公司 | Cloud platform-based intelligent substation monitoring method and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100217638A1 (en) * | 2009-02-23 | 2010-08-26 | Bae Systems Information And Electronic Systems Integration, Inc. | In service support center and method of operation |
CN103810328A (en) * | 2014-01-16 | 2014-05-21 | 国家电网公司 | Transformer maintenance decision method based on hybrid model |
CN104636826A (en) * | 2015-01-27 | 2015-05-20 | 中国石油化工股份有限公司 | Method for optimizing reliability and maintenance strategy of chemical refining equipment |
-
2016
- 2016-12-19 CN CN201611174646.7A patent/CN106845651A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100217638A1 (en) * | 2009-02-23 | 2010-08-26 | Bae Systems Information And Electronic Systems Integration, Inc. | In service support center and method of operation |
CN103810328A (en) * | 2014-01-16 | 2014-05-21 | 国家电网公司 | Transformer maintenance decision method based on hybrid model |
CN104636826A (en) * | 2015-01-27 | 2015-05-20 | 中国石油化工股份有限公司 | Method for optimizing reliability and maintenance strategy of chemical refining equipment |
Non-Patent Citations (1)
Title |
---|
王庆锋: "基于风险和状态的智能维修决策优化系统及应用研究", 《中国博士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107358299A (en) * | 2017-06-16 | 2017-11-17 | 杭州培慕科技有限公司 | Pre-emptive maintenace closed-loop policy based on fault mode |
CN108673503A (en) * | 2018-05-22 | 2018-10-19 | 佛山科学技术学院 | A kind of industrial robot real-time fault detection method and device |
CN108673503B (en) * | 2018-05-22 | 2021-01-26 | 佛山科学技术学院 | Industrial robot real-time fault detection method and device |
CN109190958A (en) * | 2018-08-23 | 2019-01-11 | 合肥好多帮信息科技有限公司 | A kind of troublshooting Intelligentized regulating and controlling system |
CN110378592A (en) * | 2019-07-12 | 2019-10-25 | 珠海培慕科技有限公司 | A kind of method of dynamic evaluation equipment Risk |
CN110390404A (en) * | 2019-07-12 | 2019-10-29 | 杭州培慕科技有限公司 | A kind of RCM in knowledge based library and data management |
CN112633617A (en) * | 2019-09-24 | 2021-04-09 | 北京国双科技有限公司 | Maintenance strategy generation method and device, computer equipment and readable storage medium |
CN112365182A (en) * | 2020-11-24 | 2021-02-12 | 中国舰船研究设计中心 | Marine equipment maintenance work type analysis method and device based on tasks and functions |
CN117424338A (en) * | 2023-10-18 | 2024-01-19 | 国网江苏省电力有限公司南通供电分公司 | Cloud platform-based intelligent substation monitoring method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106845651A (en) | The method of the anticipation of equipment state variation tendency, system architecture and maintenance policy optimization | |
EP3362861B1 (en) | Systems and methods of hierarchical smart asset control application development and optimization | |
US8055371B2 (en) | Services portal | |
CN116862199A (en) | Building construction optimizing system based on big data and cloud computing | |
CN104574002B (en) | Asset management information processing method and processing device based on big data analysis | |
US9665090B2 (en) | Systems and methods for rule-based control system reliability | |
Galar et al. | Maintenance metrics: a hierarchical model of balanced scorecard | |
Erkoyuncu et al. | An intelligent agent-based architecture for resilient digital twins in manufacturing | |
JP2003016374A (en) | Evaluating method and drawing-up method for power generating facility plan, and program | |
CN110390404A (en) | A kind of RCM in knowledge based library and data management | |
Bülbül et al. | Exact and heuristic approaches for joint maintenance and spare parts planning | |
Basirat et al. | System dynamics meta-modelling for reliability considerations in maintenance | |
zu Wickern | Challenges and reliability of predictive maintenance | |
BRUZZONE et al. | Innovative solutions based on simulation combined with optimization techniques for maintenance service management within complex systems | |
Legutko | Industry 4.0 technologies for the sustainable management of maintenance resources | |
Ivanov et al. | Application of control theoretic tools to supply chain disruption management | |
Staron et al. | Industrial self-healing measurement systems | |
Tsarouhas | Reliability, availability, and maintainability analysis of an industrial plant based on Six Sigma approach: a case study in plastic industry | |
Burhanuddin et al. | An Efficient Failure-Based Maintenance Decision Support System for Smalland Medium Industries | |
Sardar et al. | Challenges in achieving optimal asset performance based on total cost of ownership | |
Panayiotou et al. | Designing an industrial maintenance system: a proposed methodological framework | |
Comes | Robust emergency management strategies: Supporting interdependent decisions | |
Singh et al. | Advanced Maintenance and Reliability | |
Imani et al. | Computerized Maintenance and Asset Management: Improving Quality Through Systems Integration. | |
Thaduri et al. | Evolution of Maintenance Processes in Industry 4.0 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |