CN110489898B - Dynamic multi-level system modeling and state prediction method based on hybrid cognition - Google Patents
Dynamic multi-level system modeling and state prediction method based on hybrid cognition Download PDFInfo
- Publication number
- CN110489898B CN110489898B CN201910787419.9A CN201910787419A CN110489898B CN 110489898 B CN110489898 B CN 110489898B CN 201910787419 A CN201910787419 A CN 201910787419A CN 110489898 B CN110489898 B CN 110489898B
- Authority
- CN
- China
- Prior art keywords
- bayesian network
- state
- dynamic
- level
- dynamic multi
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000019771 cognition Effects 0.000 title claims abstract description 9
- 238000005094 computer simulation Methods 0.000 title claims abstract description 5
- 230000003068 static effect Effects 0.000 claims abstract description 43
- 238000004458 analytical method Methods 0.000 claims abstract description 28
- 230000001149 cognitive effect Effects 0.000 claims abstract description 18
- 230000008859 change Effects 0.000 claims abstract description 13
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 230000003993 interaction Effects 0.000 claims description 6
- 230000015556 catabolic process Effects 0.000 claims description 5
- 238000006731 degradation reaction Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000004146 energy storage Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 5
- 238000013459 approach Methods 0.000 description 3
- 230000007704 transition Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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"
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The invention discloses a dynamic multi-level system modeling and state prediction method based on hybrid cognition, which comprises the following steps: firstly, carrying out system analysis by using a fault tree and static Bayesian network method; step two, analyzing the dynamic multi-level system by using the hybrid cognitive method, and constructing a static Bayesian network B ═ (B)1θ); step three, expanding the static Bayesian network into a dynamic Bayesian network to form a system state prediction model; fourthly, reasoning, evaluating and predicting the health state of the dynamic multi-level system; the invention provides a hybrid cognitive system analysis method, which can solve the problem that a fault tree and static Bayesian network method are not completely cognized to a dynamic multi-level system, and a static Bayesian network model established on the basis of hybrid cognition has higher system state prediction accuracy; the system state prediction model established by the invention can utilize the base level component data to carry out reasoning evaluation and prediction on the overall state of the system and master the change trend of the system state.
Description
Technical Field
The invention relates to a hybrid cognitive method for analyzing a dynamic multi-level system by combining a fault tree, a static Bayesian network and a STAMP (static state prediction) method aiming at data of a base-level component in the dynamic multi-level system, and a system prediction model is constructed by utilizing the dynamic Bayesian network on the basis of analysis, belonging to the technical field of system modeling and state prediction.
Background
For a dynamic multi-level system product, the development of state prediction modeling is a very necessary work, the state of the system can be evaluated by constructing a prediction model of the system, the state of the system can be mastered, accidents are avoided, and follow-up system maintenance and other works can be guided. At present, for a dynamic multi-hierarchy system, state prediction modeling is mainly realized by classical methods such as fault tree analysis, static Bayesian network, combination of fault tree and static Bayesian network, and the like. However, in the research of the classical analysis method, the model obtained by the fault tree analysis is often directly converted into a static bayesian network structure, so that the structure of the established model is completely dependent on the result of the fault tree analysis and the hidden relationship in the network cannot be found, and meanwhile, the established model cannot continuously predict the system state over time, so that the evaluation result of the established prediction model has a large deviation from the actual state in the practical application. Therefore, it is necessary to further provide a more suitable method for analyzing the complex relationship of the dynamic multi-level system and establishing a prediction model for dynamic continuous prediction.
In the aspect of state prediction modeling of a dynamic multi-level system, the dynamic Bayesian network is an effective method at present, inherits the advantages of a static Bayesian network in solving the uncertainty problem, represents the complex logic relationship in the dynamic multi-level system, and can describe the time sequence change of the system state; the construction of the model of the dynamic Bayesian network needs to perform comprehensive and accurate analysis on a dynamic multi-level system, the classical analysis method combining a fault tree and the static Bayesian network excessively depends on expert knowledge, and in order to provide a more reasonable system analysis method, STAMP analysis is introduced from the perspective of safety and risk analysis on the basis of the classical analysis method, a new hybrid cognitive method is formed by combining the fault tree with the static Bayesian network method and the STAMP analysis and utilizing data of a base-level component, a hidden relation in the static Bayesian network model is searched by utilizing the hybrid cognitive method, model parameters in the network are trained, and a more complete static Bayesian network model is established. The hybrid cognitive method and the dynamic Bayesian network modeling method can provide an effective technical approach for the problems.
Therefore, for specific problems to be solved, the patent proposes a dynamic multi-level system state prediction modeling method based on a hybrid cognition (combination of a fault tree and a static bayesian network method, STAMP analysis and data training of a base level component) method and a dynamic bayesian network, and the method has certain originality.
Disclosure of Invention
The invention aims to solve the problems and provides a method which can comprehensively and accurately recognize the internal structure of a dynamic multi-level system and establish a state prediction model of the system so as to obtain an accurate and effective dynamic multi-level system state prediction result.
The method comprises the following specific steps:
firstly, carrying out system analysis by using a fault tree and static Bayesian network method;
step two, analyzing the dynamic multi-level system by using the hybrid cognitive method, and constructing a static Bayesian network B ═ (B)1,θ)；
Step three, expanding the static Bayesian network into a dynamic Bayesian network to form a system state prediction model;
and fourthly, reasoning, evaluating and predicting the state of the dynamic multi-level system.
The invention has the advantages that:
(1) the invention provides a hybrid cognitive system analysis method, and the internal logic of the dynamic multi-level system is effectively described and modelled;
(2) the invention establishes a dynamic Bayesian network model of the dynamic multi-level system, and can evaluate and predict the state of the dynamic multi-level system in time sequence.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of a hybrid cognitive method implementation;
FIG. 3 is a fault tree diagram of an energy storage battery system;
FIG. 4 is a static Bayesian network plot derived by a classical approach;
FIG. 5 is a diagram of an energy storage battery system control process;
FIG. 6 is a static Bayesian network plot derived from a hybrid cognitive approach;
FIG. 7 is a diagram of a dynamic Bayesian network model;
FIG. 8 is a diagram of energy storage battery system state estimation and prediction;
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
The flow chart of the method is shown in fig. 1, and comprises the following steps:
step one, carrying out system analysis by utilizing fault tree and static Bayesian network method
The dynamic multi-hierarchy system is composed of a plurality of subsystems, a plurality of devices and component interaction, the degradation or failure of the subsystems, the components and the devices can directly affect the system state change, so the structural and logical relations between the components and the devices and the subsystems need to be known firstly to predict the system state change.
The failure tree analysis method can summarize the reasons causing the system failure, and for the dynamic multi-level system, the failure tree analysis method can find out the events causing the fatal failure of the complex system due to the combination of low-level failure events. The fault tree is thus first established for the multi-level system. Because the fault tree can only represent the states of occurrence and non-occurrence of events, the description accuracy of the system state is not enough, and then the established fault tree is converted into a static Bayesian network B0The method is shown in table 1.
Table 1 fault tree to bayesian network mapping table
Step two, analyzing the dynamic multi-level system by using the hybrid cognitive method, and constructing a static Bayesian network B ═ (B)1,θ)。
The hybrid cognitive analysis method provided by the patent firstly establishes a static Bayesian network B in the step one0On the basis, the multi-level system is taken as a whole by using the STAMP method, and the interaction relation R in the operation process of the internal equipment is analyzedsSearching for failure caused by interaction among subsystems and components in the system; then the interaction relation RsIs expressed as B in the step one0The network lacks directed edges, forming B1A network structure; finally, the data set D (C, t) of the base-level component is input into the network B1Training the network to obtain B1The probability relation theta among the network nodes realizes the quantitative description of the network node relation, and the construction of the static Bayesian network B (B) is completed1,θ)。
The flow of the hybrid cognitive method is shown in fig. 2.
Step three, expanding the static Bayesian network into a dynamic Bayesian network to form a system state prediction model;
the static Bayesian network in the step two is extended into a dynamic Bayesian network according to time, and the dynamic Bayesian network is used (B, B)→) Denotes the initial t0Time-of-day network structure in which a probability distribution P (Z) of an initial time-of-day is given1)，B→Representing a bayesian network comprising two time slices, the conditional probability distribution between nodes between two adjacent time slices in the network structure being:
wherein,
is the ith node on the t-th time slice,
is that
The parent node of (2).
And determining the transition probability of the Bayesian network of two time slices by using an EM (expectation maximization) algorithm by means of the data set of the base level component, and completing the construction of a multi-level state prediction model, wherein the implementation tool is GeNIe software.
Fourthly, reasoning, evaluating and predicting the state of the dynamic multi-level system;
in the third step, a state prediction model of the dynamic multi-level system is established, the joint tree reasoning algorithm is used for reasoning the model, and all nodes in the model assume three states of Normal (Normal), Degraded (Degraded) and Failure (Failure). T at the existing base level component data0～iReasoning and evaluating the system state within the moment, and performing tiThe time with the probability of the three states being greater is taken as the system state, such as PNormal＞PDegraded＞PFailureThen at tiThe system is considered to be in a Normal state (Normal) at that time. T at unknown base level component datajAnd (3) predicting the system state at any moment, respectively obtaining the probability of the system in three states of Normal (Normal), Degraded (Degraded) and Failure (Failure), grasping the state change trend of the system, and guiding the system to maintain and the like.
Example (b):
the method of the present invention will now be described with reference to the application of an energy storage battery system.
Firstly, carrying out system analysis by using a fault tree and static Bayesian network method;
firstly, performing fault tree analysis on an energy storage battery pack system to obtain a basic event causing system fault, wherein a fault tree is shown in fig. 3; the fault tree model is then converted to a static bayesian network structure (DAG) as shown in fig. 4, with the parameters in the network given by the fault tree logical relationships and expert experience.
And step two, analyzing a certain energy storage battery pack system by using a hybrid cognitive method, and perfecting the static Bayesian network formed in the step one.
First, a control process model diagram obtained by performing STAMP analysis on the energy storage battery system is shown in fig. 5. Through the STAMP analysis result, it can be known that the states of the single batteries 1 and 2 in the energy storage battery system not only directly affect the branch subsystem 1, but also affect the branch subsystem 2, for example, when the single batteries 1 are obviously degraded, the current of the branch subsystem 2 is obviously increased, and the states of the single batteries 3 and 4 also indirectly affect the state change of the branch subsystem 1. Therefore, in the static bayesian network, they should have a logical relationship, so the bayesian network structure is improved, and the complete bayesian network of the energy storage battery system is shown in fig. 6.
And then, training and inputting the state data of 300 groups of single batteries into parent nodes of the Bayesian network shown in FIG. 6, training to obtain network parameters, and completing hybrid cognition on the energy storage battery as shown in Table 2.
TABLE 2 static Bayesian network node parameter Table
The bayesian network obtained by mixed cognition is reasoned and compared with the classical Bayesian Network (BN) shown in fig. 4, the remaining unused 132 groups of data are respectively input into the two network structures, and the system state is reasoned, and the inference result is shown in table 3.
TABLE 3 comparison of prediction accuracy of hybrid cognitive Bayesian networks to classical Bayesian networks
The results in the table are analyzed, and the static Bayesian network constructed by analyzing the system through the hybrid cognitive method has higher state inference accuracy than the classical Bayesian network, and the dynamic Bayesian network established on the basis can infer and predict the state change of the system more accurately in time sequence.
Step three, expanding the static Bayesian network into a dynamic Bayesian network to form a system state prediction model;
the static bayesian network of the system is expanded in time sequence, and on the basis, a network structure with n time slices can be formed as shown in fig. 7. The transition probability of C1, C2, C3 and C4 between two time slices, namely B, obtained by the EM algorithm→Inner conditional probability distribution as shown in tables 4 and 5.
TABLE 4 parameters of each C1, C2 node in the dynamic Bayesian network model
TABLE 5 parameters of each C3, C4 node in the dynamic Bayesian network model
Fourthly, reasoning, evaluating and predicting the state of the dynamic multi-level system;
for energy storage battery systems with the same type, the historical data of the node states of each component is known to be shown in table 6, the dynamic bayesian network model constructed in the third step of the invention can be applied to carry out inference estimation on the system states, the probability that the system is in three states in 20 moments can be obtained and is shown in fig. 8, the probability that the energy storage battery system is in a normal working state in the first 20 moments is 0.9281, the probability of a degradation state is 0.0677, and the probability of a failure state is 0.0042, so that the system is inferred to be in the normal working state. When the state of each component node at the subsequent time is unknown, the probability that the system is in a normal working state at about 111 time is smaller than that in a degradation state by predicting the state change conditions of the system at 200 future times, the probability of a failure state is continuously improved, the predicted system state change trend accords with the state change rule of the energy storage battery system, and the state of the system at a certain time can be known through the prediction result to guide the subsequent maintenance work.
Claims (1)
1. A dynamic multi-level system modeling and state prediction method based on hybrid cognition is characterized by comprising the following steps:
firstly, carrying out system analysis by using a fault tree and static Bayesian network method;
the dynamic multi-level system is composed of a plurality of subsystems, a plurality of devices and component interaction, the degradation or the failure of the subsystems, the components and the devices can directly influence the state change of the system, so the structure and the logic relation of the components, the devices and the subsystems are firstly known to predict the state change of the system;
the method comprises the steps of firstly summarizing reasons of faults of the dynamic multi-level system by using a fault tree analysis method, and discovering low-level fault events (x)i) Combining the events (T) causing the fatal failure of this complex system, and building a failure tree graph FTA, then converting the dynamic multi-level system FTA into a static Bayesian network B0The method is used for describing influence relations of internal components, equipment, subsystems and the system of the multi-level system, the multi-level system is mainly analyzed from a qualitative level, and the step is a premise of mixed cognition in the step two;
step two, analyzing the dynamic multi-level system by using the hybrid cognitive method, and constructing a static Bayesian network B ═ (B)1θ), specifically divided into the following steps:
1) dynamic multi-level system fault tree analysis to form static Bayesian network B based on fault tree0；
2) STAMP analysis method for analyzing internal interaction relation R of dynamic multi-hierarchy systems；
3) Will interact with RsIs represented by B in 1)0The network lacks directed edges, forming B1A network structure;
4) inputting a data set D (C, t) of a base level component into B1Training the network to obtain B1The probability relation theta among the network nodes realizes the quantitative description of the network node relation, and a static Bayesian network B (B) is constructed1，θ)；
Step three, expanding the static Bayesian network into a dynamic Bayesian network to form a system state prediction model;
in the dynamic multi-level system model construction process, a static Bayesian network B (B) obtained by a two-step hybrid cognitive method is used1θ) is an initial time (t)0) Network structure of, will t0Network structure of time B ═ B1θ) are respectively copied to t in time sequence1、t2…tnAt the moment, a dynamic Bayesian network model is formed, and the dynamic Bayesian network model is represented by (B, B →), where B represents t0Time network structure, the probability distribution of the initial time is P (Z)1) (ii) a B → represents a Bayesian network comprising two time slices, and the conditional probability distribution between nodes between two adjacent time slices in the network structure is:
wherein,
is the ith node on the t-th time slice,
is that
The father node takes the state data D (C, t) acquired by the base level component as evidence of the node, and utilizes a dynamic Bayesian network model (B, B →) to carry out reasoning evaluation and prediction on the state of the system node;
fourthly, reasoning, evaluating and predicting the state of the dynamic multi-level system;
performing inference evaluation and prediction on the state of the dynamic multi-level system through a dynamic Bayesian network model (B, B →), wherein all nodes in the dynamic Bayesian network model assume three states of normal, degraded and failed; t at the existing base level component data0～iReasoning and evaluating the system state within the moment, and performing tiThe one with the highest probability of the three states is taken as the system state PNormal＞PDegraded＞PFailureIf so, the system is considered to be in a normal state; t at unknown base level component datajAnd (4) predicting the system state at all times to respectively obtain the probability of the system in the normal state, the degradation state and the failure state, mastering the state change trend of the system and guiding the maintenance work of the system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910787419.9A CN110489898B (en) | 2019-08-26 | 2019-08-26 | Dynamic multi-level system modeling and state prediction method based on hybrid cognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910787419.9A CN110489898B (en) | 2019-08-26 | 2019-08-26 | Dynamic multi-level system modeling and state prediction method based on hybrid cognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110489898A CN110489898A (en) | 2019-11-22 |
| CN110489898B true CN110489898B (en) | 2021-05-28 |
Family
ID=68553819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910787419.9A Active CN110489898B (en) | 2019-08-26 | 2019-08-26 | Dynamic multi-level system modeling and state prediction method based on hybrid cognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110489898B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889501B (en) * | 2019-12-11 | 2023-06-23 | 北京工业大学 | Human brain effect connection network construction method based on non-stationary dynamic Bayesian network |
| JP7375556B2 (en) * | 2020-01-08 | 2023-11-08 | マツダ株式会社 | A graph structured analysis method, a graph structured analysis program, and a computer-readable storage medium storing the graph structured analysis program |
| CN111311092B (en) * | 2020-02-13 | 2024-04-19 | 辽宁石油化工大学 | Evaluation method based on dynamic risk of coal gasification equipment |
| CN111275195A (en) * | 2020-02-13 | 2020-06-12 | 辽宁石油化工大学 | Dynamic Bayesian network modeling method based on coal gasification equipment |
| CN112070325B (en) * | 2020-11-12 | 2021-02-26 | 北京交通大学 | Road network train optimization method, device, equipment and storage medium under abnormal event |
| CN112989604B (en) * | 2021-03-12 | 2022-07-05 | 北京航空航天大学 | Bayesian network-based cause scene safety quantitative evaluation method |
| CN113742195B (en) * | 2021-09-18 | 2022-03-29 | 北京航空航天大学 | Bayesian neural network-based system health state prediction method |
| CN114494819B (en) * | 2021-10-14 | 2024-03-08 | 西北工业大学 | Anti-interference infrared target identification method based on dynamic Bayesian network |
| CN116263878A (en) * | 2022-10-09 | 2023-06-16 | 北京理工大学 | Lithium ion battery thermal runaway risk prediction method and device |
| CN116501027B (en) * | 2023-06-29 | 2023-10-03 | 中南大学 | Distributed braking system health assessment method, system, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102262690A (en) * | 2011-06-07 | 2011-11-30 | 中国石油大学(北京) | Modeling method of early warning model of mixed failures and early warning model of mixed failures |
| CN105913124A (en) * | 2016-04-08 | 2016-08-31 | 北京航空航天大学 | System health state prediction method based on Bayes network and base data |
| CN107145634A (en) * | 2017-04-09 | 2017-09-08 | 北京工业大学 | A kind of shield cutter and the polymorphic dynamic reliability appraisal procedure of drive system |
| CN109934759A (en) * | 2019-03-20 | 2019-06-25 | 中国铁道科学研究院集团有限公司 | A kind of locomotive Analysis on monitoring data method and system |
| CN110008607A (en) * | 2019-04-11 | 2019-07-12 | 上海工业控制安全创新科技有限公司 | A kind of functional safety harm and information security threats analysis method based on STPA model |
| CN110059337A (en) * | 2019-02-26 | 2019-07-26 | 中国西安卫星测控中心 | Gyro system life-span prediction method based on Bayes multisource data fusion |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7774293B2 (en) * | 2005-03-17 | 2010-08-10 | University Of Maryland | System and methods for assessing risk using hybrid causal logic |
-
2019
- 2019-08-26 CN CN201910787419.9A patent/CN110489898B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102262690A (en) * | 2011-06-07 | 2011-11-30 | 中国石油大学(北京) | Modeling method of early warning model of mixed failures and early warning model of mixed failures |
| CN105913124A (en) * | 2016-04-08 | 2016-08-31 | 北京航空航天大学 | System health state prediction method based on Bayes network and base data |
| CN107145634A (en) * | 2017-04-09 | 2017-09-08 | 北京工业大学 | A kind of shield cutter and the polymorphic dynamic reliability appraisal procedure of drive system |
| CN110059337A (en) * | 2019-02-26 | 2019-07-26 | 中国西安卫星测控中心 | Gyro system life-span prediction method based on Bayes multisource data fusion |
| CN109934759A (en) * | 2019-03-20 | 2019-06-25 | 中国铁道科学研究院集团有限公司 | A kind of locomotive Analysis on monitoring data method and system |
| CN110008607A (en) * | 2019-04-11 | 2019-07-12 | 上海工业控制安全创新科技有限公司 | A kind of functional safety harm and information security threats analysis method based on STPA model |
Non-Patent Citations (5)
| Title |
|---|
| A Bayesian reliability evaluation method with different types of data from multiple sources;Wang L , Pan R , Wang X , et al.;《Reliability Engineering and System Safety》;20171231;第128-135页 * |
| Maintenance grouping optimization with system multi-level information based on BN lifetime prediction model;Wang X , Zhang Y , Wang L , et al.;《Journal of Manufacturing Systems》;20190116;第201-211页 * |
| Modeling of BN Lifetime Prediction of a System Based on Integrated Multi-Level Information;Jingbin W , Xiaohong W , Lizhi W .;《Sensors》;20170930;第1-19页 * |
| 基于ＨＨＭ－ＲＦＲＭ 的船舶航行风险评估方法研究;刘家国，崔进等;《中国管理科学》;20190531;第27卷(第5期);第174-182页 * |
| 融合加速试验及外场使用信息的寿命评估方法;王立志，姜同敏，李晓阳，王晓红;《北京航空航天大学学报》;20130731;第39卷(第7期);第947-951页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110489898A (en) | 2019-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110489898B (en) | Dynamic multi-level system modeling and state prediction method based on hybrid cognition | |
| Taleb-Berrouane et al. | Bayesian Stochastic Petri Nets (BSPN)-A new modelling tool for dynamic safety and reliability analysis | |
| Abrishami et al. | BN-SLIM: A Bayesian Network methodology for human reliability assessment based on Success Likelihood Index Method (SLIM) | |
| Knezevic et al. | Reliability modelling of repairable systems using Petri nets and fuzzy Lambda–Tau methodology | |
| Gran et al. | Evaluation of the Risk OMT model for maintenance work on major offshore process equipment | |
| CN110942086B (en) | Data prediction optimization method, device, equipment and readable storage medium | |
| Lavrov et al. | Mathematical models for reducing functional networks to ensure the reliability and cybersecurity of ergatic control systems | |
| CN104246798A (en) | Problem analysis and priority determination based on fuzzy expert systems | |
| Chen et al. | Knowledge-based support for simulation analysis of manufacturing cells | |
| CN113190457A (en) | Software reliability evaluation method for networked system | |
| Klymovych et al. | The Diagnostics Methods for Modern Communication Tools in the Armed Forces of Ukraine Based on Neural Network Approach. | |
| Attarzadeh et al. | Improving the accuracy of software cost estimation model based on a new fuzzy logic model | |
| Shivakumar et al. | A neuro fuzzy algorithm to compute software effort estimation | |
| Praynlin et al. | Performance analysis of software effort estimation models using neural networks | |
| Erkan | An integrated Fuzzy DEMATEL and Fuzzy Cognitive Maps approach for the assessing of the Industry 4.0 Model | |
| Smirnov | Intelligent decision support system for the control of complex technical systems | |
| Massel et al. | Intelligent system of semiotic type for decision-making support in Russia energy sector based on situational management conception | |
| Abulalqader et al. | Comparing different estimation methods for software effort | |
| Rodrigues et al. | Learning and diagnosis in manufacturing processes through an executable Bayesian network | |
| Jiang et al. | Bayesian networks in reliability modeling and assessment of multi-state systems | |
| Zhang et al. | Development of risk assessment model in construction project using fuzzy expert system | |
| Fang et al. | Modelling risk interactions to re-evaluate risks in project management | |
| Ghaleb et al. | Using fuzzy logic and discrete event simulation to enhance production lines performance: case study | |
| Yang et al. | Modeling assembly systems with repetitive operations | |
| Ren et al. | Fuzzy multi-state fault tree analysis based on fuzzy expert system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |