CN113032912A - Ship diesel engine fault detection method based on association rule - Google Patents
Ship diesel engine fault detection method based on association rule Download PDFInfo
- Publication number
- CN113032912A CN113032912A CN202110421987.4A CN202110421987A CN113032912A CN 113032912 A CN113032912 A CN 113032912A CN 202110421987 A CN202110421987 A CN 202110421987A CN 113032912 A CN113032912 A CN 113032912A
- Authority
- CN
- China
- Prior art keywords
- fault
- diesel engine
- association rule
- degree
- deviation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000012360 testing method Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000010586 diagram Methods 0.000 claims abstract description 8
- 238000007635 classification algorithm Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims abstract description 5
- 238000005070 sampling Methods 0.000 claims abstract description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 5
- 238000012800 visualization Methods 0.000 claims description 4
- 238000007418 data mining Methods 0.000 claims description 3
- 238000002347 injection Methods 0.000 claims description 3
- 239000007924 injection Substances 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000013138 pruning Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Abstract
A ship diesel engine fault detection method based on association rules is characterized in that a diesel engine original fault database is established by simulating a ship diesel engine fault, recording fault types and engine operation parameters; sequentially selecting characteristic variables, normalizing data, discretizing data and dividing a training set and a test set according to proportion by layering random sampling on a database; establishing a fault detection model: obtaining an association rule set between the operation parameters and the faults through an association rule classification algorithm, applying the association rule set to test a data set, predicting the fault state corresponding to the data set, obtaining fault detection precision, and performing parameter optimization; establishing a ship diesel engine fault rule base by using a fault detection model, making a correlation rule scatter diagram, extracting important rules and visualizing by using a K-means-based clustering grouping matrix and vector diagram method. The invention shortens the data processing time and improves the real-time performance of the system.
Description
Technical Field
The invention relates to a technology in the field of diesel engine fault detection, in particular to a ship diesel engine fault detection method based on association rules.
Background
The marine diesel engine is used as a power heart of a ship, is a basic guarantee for safe operation of the ship, has a complex structure and severe working conditions, and has high possibility of failure, so that the state monitoring and failure detection functions of a ship power system are very important. With the development of ship intelligence, the intelligent detection method based on data driving avoids the defects of excessive dependence on expert experience, complex object models and the like to a certain extent, and therefore the intelligent detection method is receiving increasingly wide attention. The existing ship diesel engine fault detection method based on data driving mainly takes a black box model or a gray box model, and although the accuracy can meet the requirement, the interpretability of the fault detection model is poor.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a ship diesel engine fault detection method based on association rules, and the fault is determined on the basis of meeting the detection precision.
The invention is realized by the following technical scheme:
the invention relates to a ship diesel engine fault detection method based on association rules, which comprises the following specific steps:
simulating the fault of a marine diesel engine, recording the fault type and the engine operation parameters, and establishing an original fault database of the diesel engine;
selecting operation parameters of fault categories as characteristic variables for a database by adopting a principal component analysis method, and dividing the operation parameters into a training set and a test set according to proportion through data normalization, data discretization and hierarchical random sampling;
step three, establishing a fault detection model: obtaining an association rule set between the operation parameters and the faults through an association rule classification algorithm, applying the association rule set to test the data set, predicting the fault state corresponding to the data set, determining the optimal parameter combination through a grid search method, namely repeating the step three after the minimum confidence coefficient and the minimum support degree are determined, and obtaining the final fault detection model detection precision;
and step four, establishing a ship diesel engine fault rule base by using a fault detection model, making an association rule scatter diagram, extracting rules with confidence coefficient and support degree both reaching more than a set threshold value, clustering the association rules by using a K-means-based clustering grouping matrix, converting mathematical language characters into graphs by using a vector diagram method to represent each association rule, and further analyzing the physical meaning in the association rule set so as to realize visualization.
The fault category is to air inlet, supercharger, intercooler, air valve, cylinder, exhaust and turbine, and the seven functional modules simulate air leakage of an air inlet manifold, efficiency reduction of the intercooler, pressure drop increase of the intercooler, fire catching, air leakage of an exhaust manifold, advanced opening of an exhaust valve and overlarge oil injection angle.
The engine operating parameters include: intake air temperature, intake air pressure, intake air flow, supercharger outlet temperature, supercharger outlet pressure, intercooler inlet temperature, intercooler outlet pressure, intake manifold temperature, intake manifold pressure, cylinder mean effective pressure, exhaust manifold temperature, exhaust manifold pressure, turbine intake air temperature, turbine intake air pressure, turbine outlet temperature, turbine outlet pressure, diesel engine speed, diesel engine power, and diesel engine torque.
The operating parameters include: intake air flow, supercharger outlet temperature, supercharger outlet pressure, intake manifold temperature, intake manifold pressure, exhaust manifold temperature, exhaust manifold pressure, turbine intake air temperature, turbine outlet temperature, and cylinder mean effective pressure.
The data normalization refers to: characterization under fault conditionsComparing the variable with the characteristic variable in the normal state, and converting the absolute value of the characteristic variable into the deviation degree of each characteristic variable from the normal state, namely:
wherein: sigmaiDegree of deviation, x, for each characteristic variableiThe variable is a characteristic variable in a fault state, and x is a characteristic variable in a normal state.
The data discretization refers to: converting the characteristic variables into category attributes according to the deviation degree of each characteristic variable, wherein the method specifically comprises the following steps: degree of deviation σiThe range of [ 15%, + ∞) is very high; degree of deviation σiIn the range of [ 5%, 15%) is high; degree of deviation σiRanges of [ 1%, 5%) are higher; degree of deviation σiIn the range of [ -1%, 1%) is normal; degree of deviation σiRanges of [ -5%, -1%) are lower; degree of deviation σiRanges of [ -15%, -5%) are low; degree of deviation σiIn the range of (-infinity, -15%)]Is very low.
The ratio of the training set to the test set is 7: 3.
The association rule classification algorithm is obtained by establishing an association rule set through data mining, namely, establishing an initial minimum confidence coefficient and a minimum support threshold and carrying out association rule mining on a training set by using an Apriori algorithm; and then judging the category attribute of the item set according to the category attribute value.
The Apriori algorithm is as follows: using the support degree as a standard for judging the frequent item set, and finding the maximum K frequent items by adopting an iterative method, wherein the method specifically comprises the following steps: searching out a candidate one-item set and a corresponding support degree, pruning to remove the item set lower than the support degree of the set parameters to obtain a frequent one-item set, then connecting the remaining frequent one-item sets to obtain a candidate frequent two-item set, screening to remove the candidate frequent two-item set lower than the support degree to obtain a real frequent two-item set, repeating the steps until the frequent k + 1-item set cannot be found, wherein the corresponding frequent k-item set is an output result of the algorithm.
Technical effects
The invention integrally solves the defects that the existing fault detection technology excessively depends on expert experience, is not enough for a complex object model and the like; compared with the prior art, the method has the advantages that the fault diagnosis model with high precision is established, the fault action mechanism is analyzed through knowledge discovery, and reference is provided for further fault analysis research.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a flow chart of data preprocessing of the present invention;
FIG. 3 is a flow chart of the fault detection model building and parameter optimization according to the present invention.
Detailed Description
As shown in fig. 1, the present embodiment relates to a marine diesel engine fault detection method based on association rules, and the specific steps are as follows:
step one, establishing a fault database: selecting a ship diesel engine TBD234 as an object, recording fault types and engine operation parameters, and establishing a diesel engine original fault database.
The seven functional modules simulate seven faults of air leakage of an air inlet manifold, efficiency reduction of the intercooler, pressure drop increase of the intercooler, fire, air leakage of an exhaust manifold, advanced opening of an exhaust valve and overlarge oil injection angle.
The engine operating parameters include: intake air temperature, intake air pressure, intake air flow, supercharger outlet temperature, supercharger outlet pressure, intercooler inlet temperature, intercooler outlet pressure, intake manifold temperature, intake manifold pressure, cylinder mean effective pressure, exhaust manifold temperature, exhaust manifold pressure, turbine intake air temperature, turbine intake air pressure, turbine outlet temperature, turbine outlet pressure, diesel engine speed, diesel engine power, and diesel engine torque.
Step two, preprocessing an original database: as shown in fig. 2, feature variable selection, data normalization, data discretization, and training set and test set establishment are sequentially performed on the database.
And the characteristic variable selection is to select the operation parameters of the fault category as the characteristic variables by adopting a principal component analysis method for the database.
The operating parameters include: intake air flow, supercharger outlet temperature, supercharger outlet pressure, intake manifold temperature, intake manifold pressure, exhaust manifold temperature, exhaust manifold pressure, turbine intake air temperature, turbine outlet temperature, cylinder mean effective pressure.
The data normalization is to compare the characteristic variables in the fault state with the characteristic variables in the normal state, and convert the absolute values of the characteristic variables into the deviation degrees of the characteristic variables from the normal state, namely:
wherein: sigmaiDegree of deviation, x, for each characteristic variableiThe variable is a characteristic variable in a fault state, and x is a characteristic variable in a normal state.
The data discretization is to convert the characteristic variables into category attributes according to the deviation of the characteristic variables, and specifically comprises the following steps: degree of deviation σiThe range of [ 15%, + ∞) is very high; degree of deviation σiIn the range of [ 5%, 15%) is high; degree of deviation ρiRanges of [ 1%, 5%) are higher; degree of deviation σiIn the range of [ -1%, 1%) is normal; degree of deviation σiRanges of [ -5%, -1%) are lower; degree of deviation σiRanges of [ -15%, -5%) are low; degree of deviation ρiIn the range of (-infinity, -15%)]Is very low.
The training set and the test set are established by adopting layered random sampling, and the database is divided into a training data set and a test data set according to a ratio of 7: 3.
Step three, establishing a fault detection model: and obtaining an association rule set between the operation parameters and the faults through an association rule classification algorithm, testing the data set by applying the association rule set, predicting the fault state corresponding to the data set, obtaining the fault detection precision, and optimizing the parameters.
As shown in fig. 3, the association rule set is created by setting an initial minimum confidence and a minimum support threshold and mining association rules of a training set by using Apriori algorithm.
The association rule classification algorithm is as follows: and establishing an association rule set through data mining, and judging the category attribute of the item set according to the classification attribute value.
The association rule set is established by establishing an initial minimum confidence and a minimum support threshold and carrying out association rule mining on the training set by using an Apriori algorithm.
The Apriori algorithm is: and (5) using the support degree as a standard for judging the frequent item set, and finding the maximum K frequent items by adopting an iterative method.
The maximum K frequent items are that a candidate 1 item set and a corresponding support degree are searched out, an item set lower than the support degree of the set parameters is pruned to obtain a frequent 1 item set, then the remaining frequent 1 item sets are connected to obtain a candidate frequent 2 item set, the candidate frequent 2 item set lower than the support degree is screened out to obtain a real frequent two item set, and iteration is carried out by analogy until a frequent K +1 item set cannot be found, and the corresponding frequent K item set is the output result of the algorithm.
The parameter optimization is to determine the optimal parameter combination, namely the minimum confidence and the minimum support degree, by using a grid search method.
And the fault detection precision is the best parameter combination input, and the step three is repeated to obtain the final fault detection model detection precision.
And step four, establishing a ship diesel engine fault rule base by using a fault detection model, extracting important rules and visualizing by using a K-means-based clustering grouping matrix and vector diagram method.
The important rule is that the confidence threshold of the rule is set to be 0.9, the support threshold is set to be 0.05, and the confidence and the support of each rule are both above the threshold and are the important rule.
The visualization of the grouping matrix based on the K-means clustering is to cluster the association rules by combining the idea of the K-means clustering, which is beneficial to quickly finding out the rules among the association rules and helping to understand the association rules.
The vector diagram method is to convert the mathematical language characters into the figures to represent each association rule and further analyze the physical meaning in the association rule set.
Through specific practical experiments, a marine diesel engine simulation model is established through engine simulation software GT-Power, a TBD234 marine diesel engine fault operation database is established through parameter checking and a fault simulation scheme, and the optimal parameter combination (minimum support degree and minimum confidence coefficient) is determined to be (0.01 and 0.7) by using the fault detection method based on association rule classification, so that the model fault diagnosis precision is 98.67%. The important rule visualization result obtained by mining also shows that the rule accords with the thermodynamic cycle rule of the diesel engine, and the reliability of the model is further explained.
Compared with the prior art, the ship diesel engine fault detection method based on association rule classification has the characteristics of high precision and fast operation; in addition, on the premise of ensuring high precision, the ship fault diagnosis method solves the problem of poor interpretability of the existing ship fault diagnosis model based on data driving, and the fault action mechanism is analyzed through knowledge discovery, so that reference is provided for further fault analysis research.
The foregoing embodiments may be modified in many different ways by those skilled in the art without departing from the spirit and scope of the invention, which is defined by the appended claims and all changes that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (5)
1. A ship diesel engine fault detection method based on association rules is characterized by comprising the following steps:
simulating the fault of a marine diesel engine, recording the fault type and the engine operation parameters, and establishing an original fault database of the diesel engine;
selecting operation parameters of fault categories as characteristic variables for a database by adopting a principal component analysis method, and dividing the operation parameters into a training set and a test set according to proportion through data normalization, data discretization and hierarchical random sampling;
step three, establishing a fault detection model: obtaining an association rule set between the operation parameters and the faults through an association rule classification algorithm, applying the association rule set to test the data set, predicting the fault state corresponding to the data set, determining the optimal parameter combination through a grid search method, namely repeating the step three after the minimum confidence coefficient and the minimum support degree are determined, and obtaining the final fault detection model detection precision;
establishing a ship diesel engine fault rule base by using a fault detection model, making an association rule scatter diagram, extracting rules of which the confidence coefficient and the support degree reach more than a set threshold value, clustering the association rules by using a K-means-based clustering grouping matrix, converting mathematical language characters into graphs by using a vector diagram method to represent each association rule, and further analyzing the physical meaning in the association rule set so as to realize visualization;
the seven functional modules simulate air leakage of an air inlet manifold, efficiency reduction of the intercooler, pressure drop increase of the intercooler, fire, air leakage of an exhaust manifold, advanced opening of an exhaust valve and overlarge oil injection angle;
the engine operating parameters include: intake air temperature, intake air pressure, intake air flow, supercharger outlet temperature, supercharger outlet pressure, intercooler inlet temperature, intercooler outlet pressure, intake manifold temperature, intake manifold pressure, cylinder mean effective pressure, exhaust manifold temperature, exhaust manifold pressure, turbine intake air temperature, turbine intake air pressure, turbine outlet temperature, turbine outlet pressure, diesel engine speed, diesel engine power, and diesel engine torque;
the operating parameters include: intake air flow, supercharger outlet temperature, supercharger outlet pressure, intake manifold temperature, intake manifold pressure, exhaust manifold temperature, exhaust manifold pressure, turbine intake air temperature, turbine outlet temperature, and cylinder mean effective pressure.
2. According to claimThe marine diesel engine fault detection method based on the association rule as claimed in claim 1, wherein the data normalization means: comparing the characteristic variables in the fault state with the characteristic variables in the normal state, and converting the absolute values of the characteristic variables into the deviation degrees of the characteristic variables from the normal state, namely:
wherein: sigmaiDegree of deviation, x, for each characteristic variableiThe variable is a characteristic variable in a fault state, and x is a characteristic variable in a normal state.
3. The marine diesel engine fault detection method based on the association rule as claimed in claim 1, wherein the data discretization is that: converting the characteristic variables into category attributes according to the deviation degree of each characteristic variable, wherein the method specifically comprises the following steps: degree of deviation σiThe range of [ 15%, + ∞) is very high; degree of deviation σiIn the range of [ 5%, 15%) is high; degree of deviation σiRanges of [ 1%, 5%) are higher; degree of deviation σiIn the range of [ -1%, 1%) is normal; degree of deviation σiRanges of [ 5%, -1%) are lower; degree of deviation σiRanges of [ -15%, -5%) are low; degree of deviation σiIn the range of (-infinity, -15%)]Is very low.
4. The association rule-based marine diesel engine fault detection method according to claim 1, wherein the association rule classification algorithm is obtained by establishing an association rule set through data mining, namely, by establishing an initial minimum confidence level and a minimum support threshold and performing association rule mining on a training set through an Apriori algorithm; and then judging the category attribute of the item set according to the category attribute value.
5. The method for detecting the fault of the marine diesel engine based on the association rule as claimed in claim 4, wherein the Apriori algorithm is: using the support degree as a standard for judging the frequent item set, and finding the maximum K frequent items by adopting an iterative method, wherein the method specifically comprises the following steps: searching out a candidate one-item set and a corresponding support degree, pruning to remove the item set lower than the support degree of the set parameters to obtain a frequent one-item set, then connecting the remaining frequent one-item sets to obtain a candidate frequent two-item set, screening to remove the candidate frequent two-item set lower than the support degree to obtain a real frequent two-item set, repeating the steps until the frequent k + 1-item set cannot be found, wherein the corresponding frequent k-item set is an output result of the algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110421987.4A CN113032912A (en) | 2021-04-20 | 2021-04-20 | Ship diesel engine fault detection method based on association rule |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110421987.4A CN113032912A (en) | 2021-04-20 | 2021-04-20 | Ship diesel engine fault detection method based on association rule |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113032912A true CN113032912A (en) | 2021-06-25 |
Family
ID=76457625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110421987.4A Pending CN113032912A (en) | 2021-04-20 | 2021-04-20 | Ship diesel engine fault detection method based on association rule |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113032912A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114595271A (en) * | 2022-02-24 | 2022-06-07 | 贵州具京网络科技有限公司 | Big data mining method and system |
| CN115713031A (en) * | 2022-11-11 | 2023-02-24 | 上海海事大学 | Method for optimally adjusting lubrication of marine main engine cylinder based on computer vision |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| CN108873859A (en) * | 2018-05-31 | 2018-11-23 | 浙江工业大学 | Based on the bridge-type grab ship unloader fault prediction model method for improving correlation rule |
| CN110008253A (en) * | 2019-03-28 | 2019-07-12 | 浙江大学 | The industrial data association rule mining and unusual service condition prediction technique of strategy are generated based on two stages frequent item set |
-
2021
- 2021-04-20 CN CN202110421987.4A patent/CN113032912A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| CN108873859A (en) * | 2018-05-31 | 2018-11-23 | 浙江工业大学 | Based on the bridge-type grab ship unloader fault prediction model method for improving correlation rule |
| CN110008253A (en) * | 2019-03-28 | 2019-07-12 | 浙江大学 | The industrial data association rule mining and unusual service condition prediction technique of strategy are generated based on two stages frequent item set |
Non-Patent Citations (2)
| Title |
|---|
| MICHAEL HAHSLER ET AL.: ""Visualizing association rules in hierarchical groups"", 《JOURNAL OF BUSINESS ECONOMICS》 * |
| 肖峰: ""基于梯度提升树的船舶柴油机故障诊断研究"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114595271A (en) * | 2022-02-24 | 2022-06-07 | 贵州具京网络科技有限公司 | Big data mining method and system |
| CN115713031A (en) * | 2022-11-11 | 2023-02-24 | 上海海事大学 | Method for optimally adjusting lubrication of marine main engine cylinder based on computer vision |
| CN115713031B (en) * | 2022-11-11 | 2023-12-22 | 上海海事大学 | Ship main engine cylinder lubrication optimization adjustment method based on computer vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110441065B (en) | Gas turbine on-line detection method and device based on LSTM | |
| CN110849626B (en) | Self-adaptive sparse compression self-coding rolling bearing fault diagnosis system | |
| CN109408389B (en) | Code defect detection method and device based on deep learning | |
| US7593804B2 (en) | Fixed-point virtual sensor control system and method | |
| CN111259532B (en) | Fault diagnosis method of aeroengine control system sensor based on 3DCNN-JTFA | |
| CN113032912A (en) | Ship diesel engine fault detection method based on association rule | |
| CN112016251B (en) | Nuclear power device fault diagnosis method and system | |
| CN114282579A (en) | Aviation bearing fault diagnosis method based on variational modal decomposition and residual error network | |
| CN111680788A (en) | Equipment fault diagnosis method based on deep learning | |
| CN115204368A (en) | Aircraft engine fault diagnosis method based on intelligent chip technology | |
| CN112906002A (en) | Malicious software identification method based on deep learning | |
| Yu et al. | Early fault diagnosis model design of reciprocating compressor valve based on multiclass support vector machine and decision tree | |
| CN113157732B (en) | Underground scraper fault diagnosis method based on PSO-BP neural network | |
| CN113742396A (en) | Mining method and device for object learning behavior pattern | |
| CN116502155B (en) | Safety supervision system for numerical control electric screw press | |
| CN116611580A (en) | Ocean red tide prediction method based on multi-source data and deep learning | |
| Zhu et al. | Engine fault diagnosis using probabilistic neural network | |
| CN116384224A (en) | Aero-engine life prediction method based on conditional parameter dynamic convolutional neural network | |
| CN115774847A (en) | Diesel engine performance evaluation and prediction method and system | |
| CN114710344A (en) | Intrusion detection method based on tracing graph | |
| CN115374687A (en) | Numerical-shape combined intelligent diagnosis method for working conditions of oil well | |
| CN112926400A (en) | Intelligent diagnosis method and system for leakage fault in hydraulic cylinder based on data driving | |
| CN211479145U (en) | Combustion condition image monitoring device based on flame image and deep learning | |
| CN117610274A (en) | Diesel engine variable working condition fault diagnosis method based on CNN-SE-GRU neural network | |
| CN114826764B (en) | Edge computing network attack recognition method and system based on ensemble learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210625 |