CN105547717B - Lubricating system of diesel oil engine method for diagnosing faults based on Bayesian network - Google Patents
Lubricating system of diesel oil engine method for diagnosing faults based on Bayesian network Download PDFInfo
- Publication number
- CN105547717B CN105547717B CN201510883986.6A CN201510883986A CN105547717B CN 105547717 B CN105547717 B CN 105547717B CN 201510883986 A CN201510883986 A CN 201510883986A CN 105547717 B CN105547717 B CN 105547717B
- Authority
- CN
- China
- Prior art keywords
- lubricating system
- bayesian network
- performance parameter
- lubricating
- oil
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The present invention relates to the lubricating system of diesel oil engine method for diagnosing faults based on Bayesian network.The fault type of lubricating system and outward sign are abstracted as failure node layer and sign node layer by the present invention respectively, establish lubricating system of diesel oil engine Bayesian network model;The performance parameter that lubricating system of diesel oil engine is detected using data collecting system, carries out classification processing, according to the lubricating system actual working state information of acquisition using linear scale transform's method to performance parameter;Revised lubricating system Bayesian network model is converted by joint tree using Hugin Junction trees.The present invention is before implementing reasoning diagnosis, actual working state according to lubricating system, by the prior probability for resetting failure node layer, adaptability amendment has been carried out to Bayesian network model, enable the actual working state of model accurate description lubricating system, to reduce the uncertainty of model reasoning, the accuracy rate of fault diagnosis is improved.
Description
Technical field
The present invention relates to the lubricating system of diesel oil engine method for diagnosing faults based on Bayesian network.
Background technology
Diesel engine is played an important role in the every field of national economy.However, engine block is complicated, it is zero many
Part be in high temperature, high pressure, high load capacity mal-condition work so that system failure rate is higher, maintenance expense it is very big.System
Meter shows that in every cost of use of diesel engine, the expenditure in terms of maintenance reaches 15%-30%.It is another to there is statistics to show,
When carrying out equipment management repair, determine that the time used in failure accounts for the 70%-90% of total time.It can be seen that inefficient bavin
Oil machine method for diagnosing faults wastes a large amount of human and material resources resource, and great inconvenience is brought to industrial production.
Diesel Fault Diagnosis is the effective means for realizing failure early prediction and preventive maintenance, for reducing accident
Harm, it is ensured that the safe operation of diesel engine plays an important roll.The application of this technology first has to the critical issue solved just
It is that mapping between fault signature and the source of trouble is non-linear.Bayesian network is a directed acyclic graph, node on behalf therein
Stochastic variable, the directed edge between node represent the incidence relation between stochastic variable, and random become is characterized in the form of prior probability
The size of correlation degree between amount.Bayesian network has unique advantage in multistate logic expression and uncertain reasoning.It utilizes
Bayesian network needs to carry out by relevant reasoning algorithm to the diagnosis of equipment fault.Hugin Junction trees are a kind of normal
Bayesian network Accurate Reasoning algorithm.The algorithm converts Bayesian network to a primary structure first --- joint
Tree carries out probabilistic causal reasoning then by the message process being defined on joint tree to object event.In recent years
Come, has scholar that Bayesian network is applied to lubricating system of diesel oil engine fault diagnosis field, achieve certain achievement.However,
In existing research, the Bayesian network model form of lubricating system is fixed, cannot be according to the actual working state amendment of system
Institute's established model so that model is to the dynamic change bad adaptability of lubricating system, and that there are accuracys rate is relatively low for diagnostic result, and referential is not
The problems such as strong, seriously constrains further applying for this technology.Invention one kind can be according to device physical status, adaptability tune
The lubricating system of diesel oil engine method for diagnosing faults of fault type is fast and accurately identified for improving equipment in integral mould structure
The safety of operation, realization have great importance to the condition maintenarnce of diesel engine.
Through the literature search of existing technologies, " naval vessel diesel main engine oil system Bayesian network pushes away open file
A kind of lubricating system of diesel oil engine method for diagnosing faults that reason method for diagnosing faults " (Sichuan war industry's journal, 2015) proposes, the disclosure
File readme is:" using the diesel main engine lube pipe system in ship's powerplant as research object, for oil system failure
Diagnosis problem analyzes most common failure mechanism, establishes the fault tree synthesis of oil system most common failure, builds on this basis
It is used for the Bayesian network model of malfunction reasoning, Bayes's state for analyzing under oil system typical fault state to push away
Reason process provides a kind of new method for the rapid failure diagnosis of oil system ".Its shortcoming is:The built shellfish of this method
This network model form of leaf is fixed, and cannot be adaptively adjusted according to the dynamic change of lubricating system, can not accurate description profit
The virtual condition of sliding system, therefore cause model reasoning uncertain big, diagnostic accuracy is relatively low;And this method is to lubricating system
Fault diagnosis is a kind of static reasoning, and process can not be realized really pair not according to lubricating system of diesel oil engine actual motion information
The diagnosis of lubricating system of diesel oil engine failure, it is difficult to staff be instructed to carry out specific aim repair to equipment.
Invention content
In view of the above-mentioned deficiencies in the prior art, it is an object of the present invention to provide a kind of diesel lubrication based on Bayesian network
Diagnosis method for system fault.
The object of the present invention is achieved like this:
(1) fault type of lubricating system and outward sign are abstracted as failure node layer and sign node layer respectively, built
Vertical lubricating system of diesel oil engine Bayesian network model;
(2) performance parameter for utilizing data collecting system detection lubricating system of diesel oil engine, using linear scale transform's method pair
Performance parameter carries out classification processing, and ω indicates the actual performance parameter of lubricating system, ω*Indicate the standard value of performance parameter,
It indicates the performance parameter after transformation, and then extensive lubricating system performance parameter, obtains the actual working state information of lubricating system
e;
(3) according to the lubricating system actual working state information e of acquisition, to Bayesian network model sign node layer vj's
State π (vj) carry out binary value, (ωj) indicate to performance parameter ωjIt is extensive,Expression meets performance parameter ωjExtensive
Corresponding outward sign description;The lubricating system Bayesian network model that adaptability amendment is established;
(4) Hugin Junction trees is used to convert revised lubricating system Bayesian network model to joint tree, into
And using lubricating system actual working state information e as reasoning evidence, by calculating failure node layer siMarginalisation condition it is general
Rate p (si| e), the current failure type of lubricating system is diagnosed.
The fault type specifically includes:Piston ring packing failure S1, addition low on fuel S2, Cooler Fault S3, exceed
Service life S4, the improper S of lubricating oil oil product5, contain bubble S in lubricating oil6, pipeline oil leak S7, pipeline blockage S8。
The outward sign specifically includes:The too low V of lubricating oil liquid level1, the excessively high V of oil temperature2, into the too low V of machine lubricating oil pressure3、
Go out the too low V of machine lubricating oil pressure4, go out the too low V of machine oil flow5。
The specific method for the lubricating system Bayesian network model that the adaptability amendment is established is:According to sign node layer
vjState π (vj), reset failure node layer pa (v in lubricating system Bayesian network modelj) prior probability P (pa (vj));
pa(vj) it is sign node layer vjFather node;
Compared with prior art, the beneficial effects of the present invention are:The present invention is before implementing reasoning diagnosis, according to lube system
The actual working state of system has carried out adaptability to Bayesian network model and has repaiied by resetting the prior probability of failure node layer
Just so that model is capable of the actual working state of accurate description lubricating system, to reduce the uncertainty of model reasoning, improves
The accuracy rate of fault diagnosis;In addition, reality of the present invention to the diagnostic reasoning of lubricating system fault type according to lubricating system
Work state information is implemented, therefore diagnostic result can truly reflect lubricating system actual performance, and there is stronger reality to refer to
Lead meaning.
Description of the drawings
Fig. 1 is that the present invention is based on the lubricating system of diesel oil engine method for diagnosing faults flow charts of Bayesian network.
Fig. 2 is certain type four-cylinder diesel engine lubricating system Bayesian Network Topology Structures figure.
Specific implementation mode
It elaborates below in conjunction with the accompanying drawings to the embodiment of the present invention:The present embodiment before being with technical solution of the present invention
It puts and is implemented, give detailed embodiment, but protection scope of the present invention is not limited to following embodiments.
The present invention relates to a kind of lubricating system of diesel oil engine method for diagnosing faults based on Bayesian network, belong to diesel engine therefore
Hinder diagnostic techniques field.Lubricating system fault type and outward sign are abstracted as network node first, establish lubricating system shellfish
This network model of leaf;Secondly, lubricating system performance parameter is detected, lubricating system actual working state information is obtained;Again, according to
The lubricating system actual working state information of acquisition, by resetting the prior probability of failure node layer, to lubricating system Bayes
Network model carries out adaptability amendment;Finally, it using the actual working state information of lubricating system as reasoning evidence, utilizes
Hugin Junction trees carry out probabilistic diagnosis to lubricating system failure.The present invention can be by adjusting node probabilistic information amendment
The Bayesian network model established makes model more accurately reflect lubricating system current working status, improves fault diagnosis
Accuracy, diagnostic result have higher practical guided significance.
The Bayesian network model of lubricating system of diesel oil engine is initially set up, then, according to the practical work of the lubricating system of acquisition
Make status information and adaptability amendment is carried out to Bayesian network model, so that model is capable of the practical work of accurate description lubricating system
Make state, improve the accuracy rate of fault diagnosis, finally, using lubricating system actual working state information as reasoning evidence, utilizes
Hugin Junction trees carry out diagnostic reasoning to fault type, and maintenance personnel is instructed to implement needle to lubricating system of diesel oil engine accordingly
Property is repaired, ensures equipment safety, reduces maintenance management cost.
The method of the present invention specifically includes following steps:
1, by the fault type S of lubricating systemiWith outward sign VjIt is abstracted as failure node layer s respectivelyiWith sign node layer
vj, establish lubricating system of diesel oil engine Bayesian network model;
2, the performance parameter ω of lubricating system of diesel oil engine is detected using data collecting systemi, using linear scale transform's method
To performance parameter ωiClassification processing, and then the performance parameter of extensive lubricating system are carried out, the real work shape of lubricating system is obtained
State information e;
3, according to the lubricating system actual working state information e obtained in step 2, to sign layer in Bayesian network model
Node vjState π (vj) binary value is carried out, on this basis, reset the prior probability P (pa (v of failure node layerj)), with
Correct the lubricating system Bayesian network model established;
4, revised lubricating system Bayesian network model is converted by joint tree using Hugin Junction trees, into
And using lubricating system actual working state information e as reasoning evidence, by calculating failure node layer siMarginalisation condition it is general
Rate p (si| e), the current failure type of lubricating system is diagnosed.
As shown in Figure 1, the present invention includes the following steps:The foundation of lubricating system Bayesian network model, lubricating system are real
Border work state information acquisition, the adaptability amendment of Bayesian network model and the joint tree diagnosis of lubricating system failure.Specifically
It is as follows:
1, the foundation of the lubricating system Bayesian network model is by the fault type S of lubricating systemiWith outward sign Vj
Respectively as failure node layer siWith sign node layer vj, establish the Bayesian network model of lubricating system of diesel oil engine.Bayesian network
Network model is using two tuple B<G, P>It indicates, wherein G is the topological structure of Bayesian network, and P is the probabilistic information of node.Into
The probabilistic information P of one step, node is specifically included:Prior probability p (si) and conditional probability p (vj|pa(vj)), wherein pa (vj) table
Show and sign node layer vjIn the presence of the failure node layer (father node) because of, fruit relationship.In Bayesian network model B<G, P>In, institute
There is the joint probability distribution between outward sign that can be indicated by formula (1).
The fault type specifically includes:Piston ring packing failure S1, addition low on fuel S2, Cooler Fault S3, exceed
Service life S4, the improper S of lubricating oil oil product5, contain bubble S in lubricating oil6, pipeline oil leak S7, pipeline blockage S8。
The outward sign refers to the operation situation of the performance parameter of lubricating system of diesel oil engine, is specifically included:Lubricating oil liquid level
Too low V1, the excessively high V of oil temperature2, into the too low V of machine lubricating oil pressure3, go out the too low V of machine lubricating oil pressure4, go out the too low V of machine oil flow5。
Further, the performance parameter ωiIt specifically includes:Lubricating oil liquid level ω1, oil temperature ω2, into machine lubricating oil pressure
ω3, go out machine lubricating oil pressure ω4, go out machine oil flow ω5。
2, the lubricating system actual working state acquisition of information is to utilize sensor and data collecting card detection diesel engine
The performance parameter ω at lubricating system current timei, and performance parameter ω is made as shown in formula (2) by linear scale transform's methodi
Map to specific sections ([0,1), [1,1], (1 ,+∞)), the unit to eliminate performance parameter limits, and is translated into dimensionless
Pure values.On this basis, according to the performance parameter for defining the extensive acquisition of rule arranged in 1, and as lube system
The actual working state information e of system.
In above formula, ω indicates the actual performance parameter of lubricating system;ω*Indicate the standard value of performance parameter;Indicate transformation
Performance parameter afterwards.
It is as follows to provide key definition:
Define 1:After (abstraction rule for defining performance parameter) carries out linear scale transform to collected performance parameter, profit
With high-level concept " too low ", " normal ", " excessively high " substitution performance parameter respectively section [0,1), [1,1], taking in (1 ,+∞)
Value, to describe the operation situation of performance parameter by fuzzy division.The fuzzy division method is referred to as the extensive of performance parameter, is denoted as
Q(·)。
3, the adaptability amendment of the Bayesian network model refers to, according to lubricating system actual working state, utilizing public affairs
Method shown in formula (3), to Bayesian network model sign node layer vjState π (vj) carry out binary value.In formula (3)
In, Q (ωj) indicate to performance parameter ωjIt is extensive,Expression meets performance parameter ωjExtensive correspondence outward sign description.
On the basis of this, according to sign node layer state value, the dependent failure node layer of Bayesian network model is reset using formula (4)
pa(vj) prior probability P (pa (vj)), adaptability amendment is carried out to the lubricating system Bayesian network model built, so that mould
Type can accurately reflect the actual performance feature of lubricating system.
4, the joint tree diagnosis of the lubricating system failure refers to converting Bayesian network using Hugin Junction trees
Model B<G, P>It is set for joint, and using lubricating system actual working state information e as evidence, reasoning and calculation failure node layer si
Marginalisation conditional probability p (si|e)。p(si| e) it is the failure layer under the conditions of actual working state information e of lubricating system
Node siThe probability that the fault type characterized occurs.At this point, according to maximum likelihood principle, such as formula (10), edge is chosen
Change the maximum failure node layer s of conditional probability*, the current performance state for diagnosing lubricating system is s*The fault type S characterized*,
Planned, targetedly condition maintenarnce is implemented to diesel engine accordingly.
The detailed process that marginalisation conditional probability is calculated using Hugin Junction trees is as follows:
The first step:According to set converting algorithm by Bayesian network model B<G, P>It is converted into joint tree.
Second step:Unite the potential function of point X in initialization joint treeIt is 1, and according to the item in Bayesian network model
Part probability updating potential functionUpdate method uses formula (5), wherein vj、pa(vj) ∈ X (are satisfied by this in following steps
Part).
Third walks:It will be acquired using method shown in formula (6), the actual working state information e of extensive lubricating system
As reasoning evidence, input joint tree.
4th step:By uniting the message process between point, such as formula (7), all potential functions for uniting point are updated.
In formula (7), X indicates to send the unity point of message;Y indicates the unity point of received message;Segmentations of the S between X, Y
Collection;Respectively unite the former potential function of point Y, segmentation collection S.
5th step:Using method shown in formula (8) to the potential function of unity point XIn failure node layer siOn do edge
Change is handled.
6th step:It reuses formula (9) and calculates failure node layer siMarginalisation conditional probability p (si| e), owned
The possibility that fault type occurs.
s*=argmaxp (si|e) (10)
Fig. 2 is the Bayesian Network Topology Structures figure that the present invention implements certain type four-cylinder diesel engine lubricating system.
Claims (2)
1. the lubricating system of diesel oil engine method for diagnosing faults based on Bayesian network, which is characterized in that include the following steps:
(1) fault type of lubricating system and outward sign are abstracted as failure node layer and sign node layer respectively, establish bavin
Oil machine lubricating system Bayesian network model;
(2) performance parameter for utilizing data collecting system detection lubricating system of diesel oil engine, using linear scale transform's method to performance
Parameter carries out classification processing, and ω indicates the actual performance parameter of lubricating system, ω*Indicate the standard value of performance parameter,It indicates to become
Performance parameter after changing, and then extensive lubricating system performance parameter obtain the actual working state information e of lubricating system;
(3) the lubricating system Bayesian network model that adaptability amendment is established, according to the lubricating system actual working state of acquisition
Information e, using formula (1) to Bayesian network model sign node layer vjState π (vj) carry out binary value;
Q(ωj) indicate to performance parameter ωjIt is extensive,Expression meets performance parameter ωjExtensive correspondence outward sign description;
The outward sign specifically includes:The too low V of lubricating oil liquid level1, the excessively high V of oil temperature2, into the too low V of machine lubricating oil pressure3, go out machine lubricating oil
Hypotony V4, go out the too low V of machine oil flow5;Failure layer section in lubricating system Bayesian network model is reset using formula (2)
Point pa (vj) prior probability P (pa (vj));pa(vj) it is sign node layer vjFather node;
(4) Hugin Junction trees are used to convert revised lubricating system Bayesian network model to joint tree, and then will
Lubricating system actual working state information e is as reasoning evidence, by calculating failure node layer siMarginalisation conditional probability p (si
| e), the current failure type of lubricating system is diagnosed.
2. the lubricating system of diesel oil engine method for diagnosing faults according to claim 1 based on Bayesian network, feature exist
In:The fault type specifically includes:Piston ring packing failure S1, addition low on fuel S2, Cooler Fault S3, beyond use
Service life S4, the improper S of lubricating oil oil product5, contain bubble S in lubricating oil6, pipeline oil leak S7, pipeline blockage S8。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510883986.6A CN105547717B (en) | 2015-12-04 | 2015-12-04 | Lubricating system of diesel oil engine method for diagnosing faults based on Bayesian network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510883986.6A CN105547717B (en) | 2015-12-04 | 2015-12-04 | Lubricating system of diesel oil engine method for diagnosing faults based on Bayesian network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105547717A CN105547717A (en) | 2016-05-04 |
CN105547717B true CN105547717B (en) | 2018-07-24 |
Family
ID=55827061
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510883986.6A Active CN105547717B (en) | 2015-12-04 | 2015-12-04 | Lubricating system of diesel oil engine method for diagnosing faults based on Bayesian network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105547717B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106547967B (en) * | 2016-11-01 | 2020-07-28 | 哈尔滨工程大学 | Diesel engine fuel system maintenance decision method based on cost analysis |
CN106778828B (en) * | 2016-11-28 | 2020-05-15 | 哈尔滨工程大学 | Simplified Bayesian model-based multi-fault recognition method for diesel engine fuel system |
CN107905990A (en) * | 2017-06-13 | 2018-04-13 | 武汉科技大学 | A kind of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method |
CN109815441B (en) * | 2017-11-20 | 2023-06-02 | 洛阳中科晶上智能装备科技有限公司 | Method for diagnosing and predicting engine faults by adopting Bayesian network model |
CN108388232B (en) * | 2018-03-20 | 2020-07-24 | 江南大学 | Method for monitoring operation mode fault in crude oil desalting process |
CN110286333B (en) * | 2019-06-18 | 2021-09-24 | 哈尔滨理工大学 | Fault diagnosis method for lithium power battery system |
CN110909763A (en) * | 2019-10-16 | 2020-03-24 | 中国石化青岛液化天然气有限责任公司 | Equipment fault diagnosis method based on fault knowledge base and Bayesian network |
CN110956268A (en) * | 2019-10-16 | 2020-04-03 | 中国石化青岛液化天然气有限责任公司 | Compressor fault diagnosis method based on big data |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5530020B1 (en) * | 2013-11-01 | 2014-06-25 | 株式会社日立パワーソリューションズ | Abnormality diagnosis system and abnormality diagnosis method |
CN104063586A (en) * | 2014-06-11 | 2014-09-24 | 西北工业大学 | Polymorphic failure tree-based bayesian network failure prediction method |
CN104462687A (en) * | 2014-12-05 | 2015-03-25 | 北京航空航天大学 | Repairable GO algorithm based on dynamic Bayesian network |
-
2015
- 2015-12-04 CN CN201510883986.6A patent/CN105547717B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5530020B1 (en) * | 2013-11-01 | 2014-06-25 | 株式会社日立パワーソリューションズ | Abnormality diagnosis system and abnormality diagnosis method |
CN104063586A (en) * | 2014-06-11 | 2014-09-24 | 西北工业大学 | Polymorphic failure tree-based bayesian network failure prediction method |
CN104462687A (en) * | 2014-12-05 | 2015-03-25 | 北京航空航天大学 | Repairable GO algorithm based on dynamic Bayesian network |
Non-Patent Citations (2)
Title |
---|
基于贝叶斯网络分类器的船舶柴油机冷却***故障诊断;曾谊晖 等;《中南大学学报》;20100831;第41卷(第4期);第1379-1384页 * |
舰船柴油主机滑油***贝叶斯网络推理故障诊断方法;许伟 等;《四川兵工学报》;20150331;第36卷(第3期);第86-90页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105547717A (en) | 2016-05-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105547717B (en) | Lubricating system of diesel oil engine method for diagnosing faults based on Bayesian network | |
CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
Sun et al. | Outlier data treatment methods toward smart grid applications | |
Wang et al. | Data-driven risk assessment on urban pipeline network based on a cluster model | |
Xi et al. | YDRSNet: an integrated Yolov5-Deeplabv3+ real-time segmentation network for gear pitting measurement | |
CN111817880A (en) | Oil and gas field production equipment health management system and implementation method | |
CN109359662A (en) | A kind of multilayer Bayesian network method for diagnosing faults based on causality analysis towards gigawatt extra-supercritical unit non-stationary property | |
Feng et al. | Reliability evaluation of gantry cranes based on fault tree analysis and Bayesian network | |
CN103530525B (en) | A kind of improve the tailing dam method based on the risk assessment accuracy of reservoir level | |
Li et al. | Research on the Clustering Analysis and Similarity in Factor Space. | |
US20160179936A1 (en) | Processing time-aligned, multiple format data types in industrial applications | |
CN114692875A (en) | Construction method of GIS (geographic information System) knowledge graph for fault diagnosis | |
CN109858732A (en) | A kind of urban water supply pipe network health status evaluation method | |
Liu et al. | A fault diagnosis method for rolling element bearings based on ICEEMDAN and Bayesian network | |
CN115271123A (en) | Oil mass early warning method and device for hydroelectric generating set oil system and electronic equipment | |
Kuyunani et al. | Improving voltage harmonics forecasting at a wind farm using deep learning techniques | |
CN113449120B (en) | Pipeline safety comprehensive supervision method combining spatial information | |
Yu et al. | Early fault diagnosis model design of reciprocating compressor valve based on multiclass support vector machine and decision tree | |
Jiang et al. | Fault diagnosis method of submersible screw pump based on random forest | |
Ozturk et al. | Artificial intelligence in building information modeling research: Country and document-based citation and bibliographic coupling analysis | |
CN105786635A (en) | Complex event processing system and method oriented to fault sensitive point dynamic detection | |
Lin et al. | Data-driven situation awareness of electricity-gas integrated energy system considering time series features | |
CN106342315B (en) | A kind of product test model building method based on body | |
CN105760672A (en) | Diagnosis method for mechanical equipment faults | |
CN101571931B (en) | Inference method facing to indefinite context of general fit calculation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |