CN104865956A  Bayesiannetworkbased sensor fault diagnosis method in complex system  Google Patents
Bayesiannetworkbased sensor fault diagnosis method in complex system Download PDFInfo
 Publication number
 CN104865956A CN104865956A CN201510138292.XA CN201510138292A CN104865956A CN 104865956 A CN104865956 A CN 104865956A CN 201510138292 A CN201510138292 A CN 201510138292A CN 104865956 A CN104865956 A CN 104865956A
 Authority
 CN
 China
 Prior art keywords
 sensor
 bayesian network
 complication
 fault diagnosis
 bayesian
 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.)
 Granted
Links
 238000003745 diagnosis Methods 0.000 title claims abstract description 38
 238000009826 distribution Methods 0.000 claims abstract description 9
 230000004927 fusion Effects 0.000 claims description 8
 238000005312 nonlinear dynamic Methods 0.000 claims description 7
 238000004891 communication Methods 0.000 claims description 5
 238000001514 detection method Methods 0.000 claims description 4
 230000003862 health status Effects 0.000 claims description 4
 230000000875 corresponding Effects 0.000 claims description 3
 238000004364 calculation method Methods 0.000 claims description 2
 238000005516 engineering process Methods 0.000 description 3
 238000010586 diagram Methods 0.000 description 2
 230000000694 effects Effects 0.000 description 2
 238000000034 method Methods 0.000 description 2
 230000005540 biological transmission Effects 0.000 description 1
 230000001808 coupling Effects 0.000 description 1
 238000010168 coupling process Methods 0.000 description 1
 238000005859 coupling reaction Methods 0.000 description 1
 238000007689 inspection Methods 0.000 description 1
 238000004519 manufacturing process Methods 0.000 description 1
 239000011159 matrix material Substances 0.000 description 1
 239000000203 mixture Substances 0.000 description 1
 238000007500 overflow downdraw method Methods 0.000 description 1
 238000003860 storage Methods 0.000 description 1
Classifications

 G—PHYSICS
 G05—CONTROLLING; REGULATING
 G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
 G05B23/00—Testing or monitoring of control systems or parts thereof
 G05B23/02—Electric testing or monitoring
 G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
 G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
Abstract
The invention provides a bayesiannetworkbased sensor fault diagnosis method in a complex system. A sensor monitoring model is constructed in a complex system; and a dynamic Bayesian network model is applied to a sensor fault diagnosis of the complex system. To be specific, the method comprises the following steps: step one, establishing a single sensor dynamic model S<(I,q)> of a complex system according to all sensor characteristics; step two, establishing a Bayesian network model for the complex system; step three, selecting a nonlinear observer sigma <(I,q)>, constructing a sub system estimation model, and obtaining a sensor residual error; step four, estimating a residual error threshold value and determining prior probability distribution of observation node parameters; step five, carrying out updating and adjusting on a Bayesian network structure and parameters and constructing a new Bayesian model; and step six, realizing the sensor fault diagnosis method in the complex system based on the Bayesian network. According to the method, expansion is carried out based on the Bayesian network; and for the complex system, the method has obvious advantages of the complex system fault diagnosis on the condition of information incompleteness.
Description
Technical field
The present invention relates to complication system sensor fault diagnosis technology, be specifically related to a kind of based on sensor fault diagnosis method in the complication system of Bayesian network.
Background technology
Along with modernization heavy mechanical equipment day by day to maximizing, the future development of complicated and precise treatment, the structure of parts is increasingly accurate.But there is the mutual relationship of many intricate, conjunction coupling between each parts, cause its fault signature to have the feature such as model uncertainty, information incompleteness, only rely on single piece of information source to be difficult to make accurate diagnosis to fault.In actual production process, before accident occurs, control system often all can break down omen, if this omen can be detected in time and be controlled, can avoid the generation of accident completely.The reliability improving complication system that appears as of Malfunction Diagnoses & Tolerance Technology provides possibility.
Bayesian Network is that uncertain knowledge is expressed and one of effective ways of diagnostic reasoning.Complex effects relation between autobody assembly deviation can be expressed with uncertain probability model form by the one hand; Can carry out Multisource Information Fusion to the prior imformation such as engineering experience, design knowledge and current detection data on the other hand, thus under realizing incomplete information, the study of assembling deviation relational model upgrades, and improves constantly fault diagnosis accuracy.With tradition based on classical statistical theory method compared with, Bayesian network has significant advantage detecting in the Fault Diagnosis of Complex System under little, the incomplete condition of information of sample.
For complication system sensor fault diagnosis model uncertainty problem, uncertain reasoning method and Multisource Information Fusion can be adopted to deal with problems.Conventional uncertain reasoning method has the multiple methods such as Bayesian network, fuzzy set theory and evidence theory, often kind of method has its feature and the scope of application, wherein Bayesian Network is based on theory of probability, it expresses uncertain with probability, express be considered to one of most effectual way solving uncertain problem at present with uncertain reasoning ability with its powerful problem.Simultaneously Bayesian network effectively can utilize multisource informations such as detecting data, engineering experience and design information, and to the storage of above information, Unified Expression and fusion, under small sample, imperfect inspection condition, the solution of troubleshooting issue provides possibility.
Summary of the invention
In view of this, the object of the present invention is to provide a kind of based on sensor fault diagnosis method in the complication system of Bayesian network, the method adopts and sets up nonlinearities system model in complication system, sensor group dynamic model and singlesensor dynamic model, build diagnosis Bayesian network model, build subsystem estimation model, compare with abovementioned model, obtain sensor model residual error, estimate threshold residual value, determine the prior probability distribution of observer nodes parameter, the probability fusion of prior probability and sample data also carries out renewal adjustment to bayesian network structure and parameter, build new Bayesian model, realize complication system sensor fault diagnosis, the Fault Diagnosis of Complex System of the method under the incomplete condition of information has clear superiority.
For achieving the above object, the invention provides following technical scheme:
Based on a sensor fault diagnosis method in the complication system of Bayesian network, it is characterized in that comprising the steps: step one: set up singlesensor dynamic model S in complication system according to each characteristic sensor
^{(I, q)}, utilize multiple agent to realize sensing data communication, Bayesian network leaf node defined; Step 2: set up the Bayesian network model towards complication system, sets up nonlinearities systematic observation model Σ according to complication system structure
^{(I)}observation model S dynamic with sensor group
^{(I)}, Bayesian network root node is defined; Step 3: build subsystem estimation model, compare with abovementioned model, obtains sensor model residual error; Step 4: setting threshold residual value, determines the prior probability distribution of observer nodes parameter; Step 5: the probability fusion of prior probability and sample data also carries out renewal adjustment to bayesian network structure and parameter, builds new Bayesian model; Step 6: carry out reasoning diagnosis based on new Bayesian network and obtain sophisticated sensors system fault diagnosis result.
Further, specifically comprise the following steps in step one: set up singlesensor in complication system according to each characteristic sensor and dynamically carry out modeling, a jth sensor with S (I) j}, j ∈ 1 ..., m
_{i}represent, utilize multiple agent to realize sensing data communication, be defined as Bayesian network leaf node;
Further, specifically comprise the following steps in step 2: 31: define the sophisticated sensors system that comprises N number of Nonlinear Dynamic subsystem model, I ∈ 1 ..., N} Nonlinear Dynamic subsystem Σ (I) represents, Σ
^{(I)}comprise known local dynamic station characteristic, known connection dynamic perfromance and model uncertainty, as uncertain in linear error, model parameter or system disturbance etc.; ; 32: definition respective sensor group S (I) represents, is defined as Bayesian network root node, sets up the Bayesian network model towards complication system;
Further, specifically comprise the following steps in step 3: 41: choose nonlinear observer model σ
^{(I, q)}, build subsystem estimation model 42: subsystem estimation model and corresponding system model compare, obtain a jth sensor residual error
and obtain its state equation;
Further, specifically comprise the following steps in step 4: 51: be set in the threshold residual value that health status lower sensor is suitable, determine the prior probability distribution of observer nodes parameter;
Further, specifically comprise the following steps in step 5: 61: the new detection data obtaining some, utilize each conditional probability of Bayes method to node to carry out fusion calculation; 62: the conditional probability according to node is tested to internodal independence, the structure and parameter obtaining Bayesian network upgrades; 63: along with a new round detects the acquisition of data set, the new network model obtained last time constantly to circulate study as prior model, and the iteration realizing network structure and parameter upgrades, and sets up offset relation model more and more accurately.
Further, specifically comprise the following steps in step 6: based on offset relation model, improve the degree of accuracy of new Bayesian network, reasoning diagnosis obtains sophisticated sensors system fault diagnosis result.
Beneficial effect of the present invention is: the present invention is by setting up nonlinearities system model and sensor group dynamic model and singlesensor dynamic model in complication system, Bayesian network root node and leaf are defined, dynamically associating property between adjacent node is introduced in sensor model, and adopt the bayes method probability fusion method of leaf node sensors association, upgrade network structure and parameter adjustment, build new Bayesian model, realize fault diagnosis, the Fault Diagnosis of Complex System of the method under the incomplete condition of information has clear superiority.
Accompanying drawing explanation
In order to make the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, the present invention is described in further detail, wherein:
Fig. 1 is sensor fault diagnosis process flow diagram in the complication system based on Bayesian network model;
Fig. 2 is Bayesian network root node of the present invention and special node relationships figure.
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described in detail.
Fig. 1 is the process flow diagram of the method for the invention, and this method comprises the following steps:
S1: carry out modeling to each sensor in the Nonlinear Dynamic subsystem of sophisticated sensors, utilizes multiple agent to realize sensing data communication, a jth sensor with S (I) j}, j ∈ 1 ..., m
_{i}represent Bayesian network relationships between nodes as shown in Figure 2; Definition S (I) j} is as formula (1):
Wherein,
represent the output variable caused by the single fault of a jth sensor
the variable changed, definition
as formula (2):
Wherein,
represent time section,
represent in the unknown moment
the unknown failure produced;
S2: define the sophisticated sensors system that comprises N number of Nonlinear Dynamic subsystem model, I ∈ 1 ..., N} Nonlinear Dynamic subsystem Σ (I) represents, respective sensor group S (I) represents, is defined as Bayesian network root node; Definition Σ (I) is as formula (3):
Wherein, x
^{(I)}, u
^{(I)}represent state variable and the control variable of Σ (I), z
^{(I)}represent connection status variable between adjacent subsystems,
to represent between adjacent subsystems connection status variable with
nonlinear combination, constant matrices A
^{(I)}represent the linear segment of state equation, γ
^{(I)}represent known nonlinear variable, A
^{(I)}x
^{(I)}(t)+γ (x
^{(I)}(t), u
^{(I)}(t)) represent known local dynamic station characteristic, h
^{(I)}represent known connection dynamic perfromance, η
^{(I)}model uncertainty, as uncertain in linear error, model parameter or system disturbance etc.;
Definition S (I) is as formula (4):
y
^{(I)}(t)＝C
^{(I)}x
^{(I)}+d
^{(I)}(t)+f
^{(I)}(t) (4)
Wherein, y
^{(I)}represent output variable, d
^{(I)}represent the noise variance that sensor detection perform worsens, f
^{(I)}the sensor fault variable expressed possibility;
S3: choose nonlinear observer model σ
^{(I, q)}, build subsystem estimation model, subsystem estimation model and corresponding system model compare, and obtain a jth sensor residual error
and obtain its state equation, concrete steps are as follows:
S31: set up prior Bayesian network model according to the root node defined in step one and step 2 and leaf node;
S32: between sensor, information transmission is used
represent, definition
as formula 5:
Wherein,
represent sensor noise variable and fault variable;
Generate residual error based on observer, choose nonlinear observer σ
^{(I, q)}subsystem model is estimated, definition σ
^{(I, q)}as formula 6:
Wherein,
represent x
^{(I)}estimated value, L
^{(I, q)}represent observation gain matrix,
represent the information transmitted between sensor;
A definition jth sensor residual error
as formula 7:
S4: under sensor subsystem health status, setting sensor residual error
threshold value, obtain the priori conditions probability distribution of Bayesian network observer nodes parameter according to the mapping relations between threshold residual value and estimated value;
S5: combine the Bayesian network model detecting data and upgrade, concrete steps are as follows:
S51: first parameter θ will be considered as stochastic variable by the parameter learning based on Bayesian Estimation, and the priori about θ is expressed as prior probability distribution P (θ), what next will calculate is exactly after observing independent identically distributed partial data D, the Posterior probability distribution P of θ (θ  D);
S52: the conditional probability according to node is tested to internodal independence, the structure and parameter obtaining Bayesian network upgrades;
S53: along with a new round detects the acquisition of data set, the new network model obtained last time constantly to circulate study as prior model, realizes the iteration renewal of network structure and parameter.
S6: set up more and more accurate offset relation model, carries out reasoning diagnosis based on new Bayesian network and obtains sophisticated sensors system fault diagnosis result.
By above step, can realize sensor fault diagnosis in complication system.
What finally illustrate is, above preferred embodiment is only in order to illustrate technical scheme of the present invention and unrestricted, although by above preferred embodiment to invention has been detailed description, but those skilled in the art are to be understood that, various change can be made to it in the form and details, and not depart from claims of the present invention limited range.
Claims (7)
1., based on a sensor fault diagnosis method in the complication system of Bayesian network, it is characterized in that comprising the steps:
Step one: set up singlesensor dynamic model S in complication system according to each characteristic sensor
^{(I, q)}, utilize multiple agent to realize sensing data communication, Bayesian network leaf node defined;
Step 2: set up the Bayesian network model towards complication system, sets up nonlinearities systematic observation model Σ according to complication system structure and sensor parameters
^{(I)}observation model S dynamic with sensor group
^{(I)}, Bayesian network root node is defined;
Step 3: choose nonlinear observer σ
^{(I, q)}, build subsystem estimation model, estimation model and abovementioned observation model compared, obtain sensor residual error;
Step 4: under sensor subsystem health status, the prior probability distribution of setting threshold residual value determination observer nodes parameter;
Step 5: the probability fusion of prior probability and sample data also carries out renewal adjustment to bayesian network structure and parameter, builds new Bayesian model;
Step 6: based on offset relation model, improves the degree of accuracy of new Bayesian network, and reasoning diagnosis obtains sophisticated sensors system fault diagnosis result.
2. according to claim 1 a kind of based on sensor fault diagnosis method in the complication system of Bayesian network, it is characterized in that: set up singlesensor in complication system according to each characteristic sensor and dynamically carry out modeling, jth sensor S (I) { j}, j ∈ { 1, ..., m
_{i}represent, utilize multiple agent to realize sensing data communication, be defined as Bayesian network leaf node.
3. according to claim 1 a kind of based on sensor fault diagnosis method in the complication system of Bayesian network, it is characterized in that: specifically comprise the following steps in step 2: 31: define the sophisticated sensors system that comprises N number of Nonlinear Dynamic subsystem model, I ∈ { 1, ..., N} Nonlinear Dynamic subsystem Σ (I) represents, Σ
^{(I)}comprise known local dynamic station characteristic, known connection dynamic perfromance and model uncertainty, as uncertain in linear error, model parameter or system disturbance etc.; ; 32: definition respective sensor group S (I) represents, is defined as Bayesian network root node, sets up the Bayesian network model towards complication system.
4. according to claim 1 a kind of based on sensor fault diagnosis method in the complication system of Bayesian network, it is characterized in that: specifically comprise the following steps in step 3: 41: choose nonlinear observer model σ
^{(I, q)}, build subsystem estimation model 42: subsystem estimation model and corresponding system model compare, obtain a jth sensor residual error
and obtain its state equation.
5. according to claim 1 a kind of based on sensor fault diagnosis method in the complication system of Bayesian network, it is characterized in that: specifically comprise the following steps in step 4: 51: estimate, in the suitable threshold residual value of health status lower sensor, to determine the prior probability distribution of observer nodes parameter.
6. according to claim 1 a kind of based on sensor fault diagnosis method in the complication system of Bayesian network, it is characterized in that: specifically comprise the following steps in step 5: 61: the new detection data obtaining some, utilize each conditional probability of bayes method to node to carry out fusion calculation; 62: the conditional probability according to node is tested to internodal independence, the structure and parameter obtaining Bayesian network upgrades; 63: along with a new round detects the acquisition of data set, the new network model obtained last time constantly to circulate study as prior model, and the iteration realizing network structure and parameter upgrades, and sets up offset relation model more and more accurately.
7. according to claim 1 a kind of based on sensor fault diagnosis method in the complication system of Bayesian network, it is characterized in that: in step 6, set up more and more accurate offset relation model, carry out reasoning diagnosis based on new Bayesian network and obtain sophisticated sensors system fault diagnosis result.
Priority Applications (1)
Application Number  Priority Date  Filing Date  Title 

CN201510138292.XA CN104865956B (en)  20150327  20150327  Sensor fault diagnosis method in a kind of complication system based on Bayesian network 
Applications Claiming Priority (1)
Application Number  Priority Date  Filing Date  Title 

CN201510138292.XA CN104865956B (en)  20150327  20150327  Sensor fault diagnosis method in a kind of complication system based on Bayesian network 
Publications (2)
Publication Number  Publication Date 

CN104865956A true CN104865956A (en)  20150826 
CN104865956B CN104865956B (en)  20170707 
Family
ID=53911856
Family Applications (1)
Application Number  Title  Priority Date  Filing Date 

CN201510138292.XA Active CN104865956B (en)  20150327  20150327  Sensor fault diagnosis method in a kind of complication system based on Bayesian network 
Country Status (1)
Country  Link 

CN (1)  CN104865956B (en) 
Cited By (8)
Publication number  Priority date  Publication date  Assignee  Title 

CN105223945A (en) *  20150922  20160106  中国农业大学  The method for diagnosing faults of aquaculture Internet of Things equipment cluster and system 
CN105978725A (en) *  20160513  20160928  芦慧  Nonfragile distributed fault estimation method based on sensor network 
CN106792799A (en) *  20161129  20170531  德清云浩电子科技有限公司  A kind of mobile sensor network noise reduction and calibration method based on Bayesian network 
CN109062189A (en) *  20180830  20181221  华中科技大学  A kind of industrial process method for diagnosing faults for complex fault 
CN109146295A (en) *  20180828  20190104  国网湖南省电力有限公司  The Posterior probability distribution calculation method and system of power grid mountain fire disaster failure 
CN109298706A (en) *  20181102  20190201  中国航空工业集团公司西安飞机设计研究所  A kind of flight control system method for diagnosing faults based on Bayesian network 
CN109523027A (en) *  20181022  20190326  新智数字科技有限公司  A kind of boiler operatiopn data monitoring method and device based on Bayesian network 
CN110375598A (en) *  20190611  20191025  重庆大学  One kind being directed to priming system product testing system analysis method for reliability 
Citations (6)
Publication number  Priority date  Publication date  Assignee  Title 

US5434773A (en) *  19920130  19950718  Deutsche Forschungsanstalt Fur Luft  Und Raumfahrt E.V.  Method and facility for the identification of dynamic characteristic quantities 
JPH1115518A (en) *  19970623  19990122  Hitachi Ltd  Fault diagnosis system for electronic circuit substrate/ device 
CN102170648A (en) *  20110128  20110831  北京浩阳华夏科技有限公司  Passive diagnosis method of wireless sensor network 
CN102637019A (en) *  20110210  20120815  武汉科技大学  Intelligent integrated fault diagnosis method and device in industrial production process 
CN102802182A (en) *  20120809  20121128  无锡赛睿科技有限公司  Fault diagnosis device and method for wireless sensor network 
CN103941725A (en) *  20140424  20140723  淮海工学院  Fault diagnosis method of nonlinear network control system 

2015
 20150327 CN CN201510138292.XA patent/CN104865956B/en active Active
Patent Citations (6)
Publication number  Priority date  Publication date  Assignee  Title 

US5434773A (en) *  19920130  19950718  Deutsche Forschungsanstalt Fur Luft  Und Raumfahrt E.V.  Method and facility for the identification of dynamic characteristic quantities 
JPH1115518A (en) *  19970623  19990122  Hitachi Ltd  Fault diagnosis system for electronic circuit substrate/ device 
CN102170648A (en) *  20110128  20110831  北京浩阳华夏科技有限公司  Passive diagnosis method of wireless sensor network 
CN102637019A (en) *  20110210  20120815  武汉科技大学  Intelligent integrated fault diagnosis method and device in industrial production process 
CN102802182A (en) *  20120809  20121128  无锡赛睿科技有限公司  Fault diagnosis device and method for wireless sensor network 
CN103941725A (en) *  20140424  20140723  淮海工学院  Fault diagnosis method of nonlinear network control system 
NonPatent Citations (3)
Title 

刘希亮 等: ""基于多传感器信息融合的贝叶斯网络故障诊断方法研究及应用"", 《机械科学与技术》 * 
姜万录 等: ""多特征信息融合的贝叶斯网络故障诊断方法研究"", 《中国机械工程》 * 
杨昌昊 等: ""基于贝叶斯网的复杂系统故障诊断方法"", 《中国机械工程》 * 
Cited By (13)
Publication number  Priority date  Publication date  Assignee  Title 

CN105223945A (en) *  20150922  20160106  中国农业大学  The method for diagnosing faults of aquaculture Internet of Things equipment cluster and system 
CN105223945B (en) *  20150922  20180306  中国农业大学  Aquaculture Internet of Things equips the fault diagnosis method and system of cluster 
CN105978725A (en) *  20160513  20160928  芦慧  Nonfragile distributed fault estimation method based on sensor network 
CN105978725B (en) *  20160513  20170503  东北石油大学  Nonfragile distributed fault estimation method based on sensor network 
CN106792799A (en) *  20161129  20170531  德清云浩电子科技有限公司  A kind of mobile sensor network noise reduction and calibration method based on Bayesian network 
CN106792799B (en) *  20161129  20200114  德清云浩电子科技有限公司  Bayesian networkbased mobile sensor network noise reduction and calibration method 
CN109146295A (en) *  20180828  20190104  国网湖南省电力有限公司  The Posterior probability distribution calculation method and system of power grid mountain fire disaster failure 
CN109062189A (en) *  20180830  20181221  华中科技大学  A kind of industrial process method for diagnosing faults for complex fault 
CN109062189B (en) *  20180830  20200630  华中科技大学  Industrial process fault diagnosis method for complex fault 
CN109523027A (en) *  20181022  20190326  新智数字科技有限公司  A kind of boiler operatiopn data monitoring method and device based on Bayesian network 
WO2020082972A1 (en) *  20181022  20200430  新智数字科技有限公司  Method and apparatus for monitoring operating data of boiler based on bayesian network 
CN109298706A (en) *  20181102  20190201  中国航空工业集团公司西安飞机设计研究所  A kind of flight control system method for diagnosing faults based on Bayesian network 
CN110375598A (en) *  20190611  20191025  重庆大学  One kind being directed to priming system product testing system analysis method for reliability 
Also Published As
Publication number  Publication date 

CN104865956B (en)  20170707 
Similar Documents
Publication  Publication Date  Title 

CN104865956A (en)  Bayesiannetworkbased sensor fault diagnosis method in complex system  
CN106125714B (en)  In conjunction with the Failure Rate Forecasting Method of BP neural network and two parameters of Weibull  
CN102208028B (en)  Fault predicting and diagnosing method suitable for dynamic complex system  
CN106950945B (en)  A kind of fault detection method based on dimension changeable type independent component analysis model  
CN104595170A (en)  Air compressor monitoring diagnosis system and method adopting adaptive kernel Gaussian hybrid model  
Fort et al.  Hidden Markov Models approach used for life parameters estimations  
CN105700358A (en)  Modeling quality monitoring method for model predictive controller (MPC) with drift interference  
CN108960303B (en)  Unmanned aerial vehicle flight data anomaly detection method based on LSTM  
CN106960069A (en)  A kind of Bayesian network platform with selflearning function  
BarzolaMonteses et al.  Energy Consumption of a Building by using Long ShortTerm Memory Network: A Forecasting Study  
CN105117606A (en)  Method for determining element fault probability change tendency  
CN107423414A (en)  A kind of process industry complex electromechanical systems fault source tracing method based on information transmission model  
CN103712702A (en)  Electromechanical device temperature early warning method  
CN110750455B (en)  Intelligent online selfupdating fault diagnosis method and system based on system log analysis  
Leifeld et al.  Fault detection for probabilistic Boolean networks  
CN106789262A (en)  A kind of complex network community method for detecting abnormality  
Qiao et al.  Fault detection for networked systems with random delays and packet losses  
AbdulMalak et al.  Optimally replacing multiple systems in a shared environment  
Song et al.  Reliability analysis of monotone coherent multistate systems based on Bayesian networks  
CN108198268A (en)  A kind of production equipment data scaling method  
CN110531732B (en)  Random fault detection method for nonlinear networked control system  
Karaaslanli et al.  Constrained spectral clustering for dynamic community detection  
Wang et al.  Integrative probabilistic short‐term prediction and uncertainty quantification of wind power generation  
CN104168188A (en)  Internet AS deduction and router division method based on SVI  
EP3413153A1 (en)  Method and distributed control system for carrying out an automated industrial process 
Legal Events
Date  Code  Title  Description 

C06  Publication  
PB01  Publication  
EXSB  Decision made by sipo to initiate substantive examination  
SE01  Entry into force of request for substantive examination  
GR01  Patent grant  
GR01  Patent grant 