CN108664010A - Generating set fault data prediction technique, device and computer equipment - Google Patents
Generating set fault data prediction technique, device and computer equipment Download PDFInfo
- Publication number
- CN108664010A CN108664010A CN201810426084.3A CN201810426084A CN108664010A CN 108664010 A CN108664010 A CN 108664010A CN 201810426084 A CN201810426084 A CN 201810426084A CN 108664010 A CN108664010 A CN 108664010A
- Authority
- CN
- China
- Prior art keywords
- data type
- data
- decision
- parameter
- row
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- 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
- G05B23/0243—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 model based detection method, e.g. first-principles knowledge model
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
This application involves a kind of generating set fault data prediction technique, device, computer equipment and storage mediums.The method includes:Acquire the operating parameter in the current operational process of generating set;Decision Classfication is carried out to operating parameter using established decision-tree model;Obtain the classification information exported after decision-tree model Decision Classfication;Fault data prediction result is exported according to classification information.Using generating set fault data prediction technique, the accuracy of accident analysis can be improved, and the generation of safety accident can be reduced, in this way, failure predication accuracy is high.
Description
Technical field
This application involves technical field of power systems, more particularly to a kind of generating set fault data prediction technique, dress
It sets, computer equipment and storage medium.
Background technology
With the development of economy, demand of the user to electricity is continuously increased, to capacity, the generator of power plants generating electricity unit
Relevance, unit complexity between group also gradually increase, and the failure rate of generating set is caused to rise.The failure of generating set will
Influence the generated energy of power plant so that the required electricity of user can not be timely completed, unavoidably caused to electric power enterprise huge
Economic loss.To ensure that power plant is timely completed power generation needs, the accident analysis of generating set just seems abnormal important.
Conventionally employed failure analysis methods are mostly two kinds:The first is by the real-time generating set of monitoring system acquisition
The data of operation judge the data comparison of the data and normal condition of monitored generating set operation according to comparing result
Whether generating set is abnormal;Second is to carry out failure point using BP (back propagation backpropagations) neural network
Analysis.It is all linked with one another between generating set since most of generating sets are the multiple coupled nonlinear systems of dynamic change, operation ginseng
Between number and dependent, the operating status of generating set are fuzzy so that and the first accident analysis mode is susceptible to misjudgment,
Accident analysis accuracy is low.And the second way there are convergence rates slow, the implicit number of plies, number of nodes choose the defects of difficult, together
Sample has that accident analysis accuracy is low.
Invention content
Based on this, it is necessary in view of the above technical problems, provide a kind of generating set event that can improve forecasting accuracy
Hinder data predication method, device, computer equipment and storage medium.
A kind of generating set fault data prediction technique, the method includes:
Acquire the operating parameter in the current operational process of generating set;
Decision Classfication, the decision-tree model characterization fortune are carried out to the operating parameter using established decision-tree model
The correspondence of row parameter and classification information;
Obtain the classification information exported after the decision-tree model Decision Classfication;
Fault data prediction result is exported according to the classification information.
A kind of generating set fault data prediction meanss, described device include:
Parameter collection module, for acquiring the operating parameter in the current operational process of generating set;
Parameter analysis module, for carrying out Decision Classfication, institute to the operating parameter using established decision-tree model
State the correspondence of decision-tree model characterization operating parameter and classification information;
Data obtaining module, for obtaining the classification information exported after the decision-tree model Decision Classfication;
As a result output module, for exporting fault data prediction result according to the classification information.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes following steps when executing the computer program:
Acquire the operating parameter in the current operational process of generating set;
Decision Classfication, the decision-tree model characterization fortune are carried out to the operating parameter using established decision-tree model
The correspondence of row parameter and classification information;
Obtain the classification information exported after the decision-tree model Decision Classfication;
Fault data prediction result is exported according to the classification information.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Following steps are realized when row:
Acquire the operating parameter in the current operational process of generating set;
Decision Classfication, the decision-tree model characterization fortune are carried out to the operating parameter using established decision-tree model
The correspondence of row parameter and classification information;
Obtain the classification information exported after the decision-tree model Decision Classfication;
Fault data prediction result is exported according to the classification information.
Above-mentioned generating set fault data prediction technique, device, computer equipment and storage medium are determined using established
Plan tree-model carries out Decision Classfication to the operating parameter of generating set, and failure is exported according to the classification information exported after Decision Classfication
Data prediction result;On the one hand, by using decision-tree model, the problem of generating set accident analysis, is reduced to a failure
Classification problem, algorithm process is simply direct, and influenced by multiple coupled non-linear factor it is small, to which the standard of accident analysis can be improved
True property.On the other hand, it is analyzed by acquiring operating parameter in generating set operational process, is not sent out in generating set failure
Number of faults is carried out it was predicted that providing detection foundation for field personnel when raw, can reduce the generation of safety accident, in this way, therefore
It is high to hinder forecasting accuracy.
Description of the drawings
Fig. 1 is the flow diagram of generating set fault data prediction technique in one embodiment;
Fig. 2 is the flow diagram of generating set fault data prediction technique in another embodiment;
Fig. 3 be one embodiment according to sample parameter and the corresponding fault category of each group sample parameter, successively from multiple
Flow diagram of the data type as optimal characteristics attribute is chosen in data type;
Fig. 4 is the structure diagram of generating set fault data prediction meanss in one embodiment;
Fig. 5 is the internal structure chart of one embodiment Computer equipment.
Specific implementation mode
It is with reference to the accompanying drawings and embodiments, right in order to make the object, technical solution and advantage of the application be more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
In one embodiment, as shown in Figure 1, providing a kind of generating set fault data prediction technique, in this way
Applied to being illustrated for terminal, terminal can be in personal computer, laptop, tablet computer and smart mobile phone
Any one.Generating set fault data prediction technique can be included the following steps:
S120:Acquire the operating parameter in the current operational process of generating set.
Operating parameter is the data in generating set operational process, may include the data types such as electric current, temperature.Specifically
Ground, can be the operating parameter for monitoring generating set in real time by monitoring system, and terminal obtains generating set from monitoring system acquisition
Operating parameter in current operational process.
S140:Decision Classfication is carried out to operating parameter using established decision-tree model.
Decision-tree model is the model that Decision Classfication is carried out using tree construction, and decision-tree model characterizes operating parameter and classification
The correspondence of information, that is, output category information can be corresponded to by inputting operating parameter, and calculating speed is fast.Wherein, classification information packet
Include the data type included by fault category and operating parameter.Specifically, decision is carried out to operating parameter using decision-tree model
Classification, specifically using the operating parameter of acquisition as the input of decision-tree model, to which decision-tree model joins the operation of input
Number carries out Decision Classfication.
S160:Obtain the classification information exported after decision-tree model Decision Classfication.
Decision-tree model can export after carrying out Decision Classfication to the data of input as result of decision classification information.For example,
Classification information can be " air-introduced machine electric current, failure ", " fault-free ".
S180:Fault data prediction result is exported according to classification information.
Fault data prediction result can be information identical with classification information, can also be for summarizing classification information
Information.Such as classification information is " air-introduced machine electric current, failure ", then it is " prediction air-introduced machine event to export fault data prediction result
Barrier ";Classification information is " fault-free ", then it is " prediction fault-free " to export fault data prediction result.Specifically, terminal can be
Output fault data prediction result to display is shown, can also be to export fault data prediction result to voice announcer
Carry out voice broadcast.
In above-mentioned generating set fault data prediction technique, the operation using established decision-tree model to generating set
Parameter carries out Decision Classfication, and fault data prediction result is exported according to the classification information exported after Decision Classfication;On the one hand, pass through
Using decision-tree model, the problem of generating set accident analysis, is reduced to a failure modes problem, algorithm process is simply straight
Connect, and influenced by multiple coupled non-linear factor it is small, to which the accuracy of accident analysis can be improved.On the other hand, by sending out
In electric unit running process acquire operating parameter analyzed, when generating set failure does not occur carry out number of faults it was predicted that
Detection foundation is provided for field personnel, the generation of safety accident can be reduced, in this way, failure predication accuracy is high.
Above-mentioned generating set fault data prediction technique is applied to realize the number of faults to generating set in electric system
It was predicted that solving the high load capacity that the growing demand of power industry is brought, the malfunction monitoring problem operated for a long time, in number
Amount and has huge promotion at quality on the time compared with manual inspection, and working efficiency can be improved.Meanwhile generating set can be found in time
Existing potential faults, the early detection sign that can be formed in failure avoid safety to there is the sufficient time to be safeguarded
Accident occurs, and improves the safety of generating set work.In addition, for electricity power enterprise, by the standard for improving accident analysis
True property, ensure generating set safe and highly efficient operation, reduce failure caused by influence, can reduce electricity power enterprise's operation cost,
Customer experience value is improved, to improve the market competitiveness and occupation rate of market of electricity power enterprise.
In one embodiment, operating parameter include air-introduced machine electric current, air-introduced machine entrance aperture, air-introduced machine entrance negative pressure,
Air-introduced machine controls oil pressure, air-introduced machine bearing axial vibration value, air-introduced machine bearing radial vibration value, air inducing main bearing first and tests
Point temperature, the second test point of air inducing main bearing temperature, air inducing main bearing third test point temperature, air inducing main bearing the 4th
Test point temperature, air-introduced machine non-drive side bearing temperature and air-introduced machine inboard bearing temperature.
Wherein, air-introduced machine entrance aperture is air-introduced machine inlet baffle aperture.The first test point of air inducing main bearing temperature is drawn
Blower fan main shaft holds the second test point temperature, air inducing main bearing third test point temperature, the 4th test point temperature of air inducing main bearing
Degree is the temperature of four test points of air inducing main bearing respectively, and the position of four test points can be specific true according to actual needs
It is fixed.
By using the operating parameter including numerous types of data, the data type of acquisition is various, to decision-tree model
Decision Classfication is carried out according to numerous types of data, the accuracy of Decision Classfication can be improved.It is appreciated that in other embodiments,
Operating parameter can also include other data types.
In one embodiment, with reference to figure 2, step S140 further includes before step S110 to step S114.The present embodiment
In, step S110 to step S114 is executed before step S120, it will be understood that in other embodiments, step S110 to step
Rapid S114 can also be after step S120, step S140 execution.
S110:Obtain multigroup sample parameter and the corresponding fault category of each group sample parameter.
Wherein, one group of sample parameter includes multiple data types, the data type and operating parameter packet that sample parameter includes
The data type included is identical.For example, sample parameter and operating parameter include air-introduced machine electric current, air-introduced machine entrance aperture, air inducing
Machine entrance negative pressure, air-introduced machine control oil pressure, air-introduced machine bearing axial vibration value, air-introduced machine bearing radial vibration value, air inducing owner
The first test point of bearing temperature, the second test point of air inducing main bearing temperature, air inducing main bearing third test point temperature, air inducing
The 4th test point temperature of main bearing, air-introduced machine non-drive side bearing temperature and air-introduced machine inboard bearing temperature.Sample parameter
Including the value of each data type be sample data, the value of the data type that operating parameter includes be the generating set acquired
Data in current operational process.
Fault category is the information for identifying failure, for example, fault category is " 1 ", is expressed as failure, and fault category is " 0 ",
Indicate fault-free.Specifically, one group of sample parameter corresponds to a fault category.
S112:According to sample parameter and the corresponding fault category of each group sample parameter, selected from multiple data types successively
Take a data type as optimal characteristics attribute.
The quantity of optimal characteristics attribute is equal to the quantity for the data type that one group of sample parameter includes.Specifically, from whole
Data type in choose a data type as first optimal characteristics attribute after, reject the data type being selected, from
A data type is chosen in remaining data type as next optimal characteristics attribute, and so on, until all numbers
It is selected and finishes according to type.
S114:According to selection sequence successively using each optimal characteristics attribute as current division node, according to each group sample
The corresponding fault category of parameter carries out decision division to the value of each group sample parameter corresponding to current division node, creates
Obtain decision-tree model.
Selection sequence is to choose to obtain the sequence of optimal characteristics attribute.According to selection sequence successively with each optimal characteristics attribute
As division node, i.e. first optimal characteristics attribute is as first division node, and second optimal characteristics attribute is as the
Two division nodes, are arranged in order.In the tree construction of decision-tree model, first division node be root node, second point
Split the child node that node is first division node.
In one group of sample parameter, there are one values for a data type correspondence;In multigroup sample parameter, for same number
According to type, each group sample parameter has respective value;For example, data type is air-introduced machine electric current, first group of sample parameter corresponds to
Value be first current value, the corresponding value of second group of sample parameter be second current value.Division node is a number
According to type, therefore for the same division node, each group sample parameter has respective value.Corresponding to current division node
The value of each group sample parameter, the value of the data type of corresponding current division node as in each group sample parameter.
Specifically, according to the corresponding fault category of each group sample parameter to each group sample corresponding to current division node
The value of parameter carries out decision division, can be when the corresponding fault category of sample parameter is expressed as fault-free, will be current
The value for dividing this group of sample parameter corresponding to node is directed toward next division node, in the corresponding fault category of sample parameter
When being expressed as failure, the value of this group of sample parameter corresponding to current division node is directed toward a leaf for being expressed as failure
Child node.In this way, when inputting operating parameter, decision division is carried out to the value of multiple data types of operating parameter, if drawing
Point be expressed as the leafy node of failure the result is that being directed toward, it is assumed that the corresponding data type of a upper node of leafy node is A,
The classification information then exported is " A, failure ".
Decision-tree model is created by using multigroup sample parameter identical with the data type that operating parameter includes, to fortune
Row Parameter analysis is more identical, result is more acurrate, to which the accuracy of fault data prediction can be improved.
In one embodiment, sample parameter is that the data during acquiring generating set machine history run obtain.By adopting
Use the data of generating set history run as sample parameter, gear to actual circumstances, to make decision-tree model that establishment obtains certainly
Plan classification is accurate, to which the accuracy of fault data prediction is high.
In one embodiment, with reference to figure 3, step S112 includes step S1121 to step S1126.
S1121:It is row with each data type that the corresponding fault category of sample parameter and sample parameter include, by each group
Sample parameter is arranged in rows, and obtains total data set, and the entropy according to collection that totalizes.
Total data set is a data form.Such as total data set shown in table 1, the group number of sample serial number sample parameter
Number, the data type of sample parameter includes air-introduced machine electric current, air-introduced machine entrance aperture etc., and fault category includes " 1 " and " 0 ", point
Failure and fault-free are not expressed as it.
Table 1
Sample serial number | Air-introduced machine electric current | Air-introduced machine entrance aperture | … | Whether break down |
1 | 100 | 5 | … | 1 |
2 | 200 | 6 | … | 1 |
3 | 130 | 5 | … | 1 |
4 | 140 | 8 | … | 0 |
5 | 100 | 9 | … | 0 |
S1122:Using in total data set under same row same value row as respective column a cell row, from total data
Concentrate extraction individual data type column, a cell row of fault category column, the data type column extracted
It is combined, obtains the corresponding training set of the cell row extracted in extracted data type.
Corresponding same row, the identical row of value are as a cell row;One cell row may include data line, can be with
Include respectively multirow data;For example, the cell row that it is 100 that the cell row of air-introduced machine electric current column, which includes value, value are 200
The cell row that the cell row and value that cell row, value are 130 are 140, wherein the cell row that value is 100 includes two line numbers
According to:Row where sample serial number 1 and sample serial number 5.For different row, the division of cell row is different.The quantity of training set has
Multiple, a cell row under a data type corresponds to a training set.For example, reference table 1, air-introduced machine electric current, sample sequence
Number 1,5 corresponding training set of sample serial number is as shown in table 2 below:
Table 2
Sample serial number | Air-introduced machine electric current | Whether break down |
1 | 100 | 1 |
5 | 100 | 0 |
S1123:Calculate the entropy of the corresponding training set of each unit row in each data type.
S1124:It is calculated pair according to the entropy of the corresponding each training set of the entropy, total data set and data type of total data set
Answer the information gain of data type.
The corresponding training set of one data type includes the corresponding training set of all cell rows under data type column.Example
Such as, if there are one the cell rows of a data type column, the corresponding training set of data type is one, if a data
The cell row of type column has multiple, then the corresponding training set of data type has multiple.
S1125:Maximum information gain is chosen from the information gain of each data type, and maximum information gain is corresponded to
Data type as optimal characteristics attribute.
S1126:The row that optimal characteristics attribute is rejected from total data set obtain new total data set, and return to step
S1122 is finished until all data types are selected.
Information gain is bigger, and the ability for distinguishing data is stronger, more representative.Therefore, by calculating each data class
The information gain of type chooses the corresponding data type of maximum information gain as optimal characteristics attribute successively, so as to get certainly
The tree construction separating capacity of plan tree-model is strong, accuracy higher, to which the accuracy of fault data prediction is high.
In one embodiment, the entropy to totalize according to collection, including:
Wherein, D indicates total data set, piThe number and total data set D occurred for the i-th class fault category in total data set D
The ratio of the group number of included sample parameter, m are the classification number for the fault category that total data set D includes, and info (D) is sum
According to the entropy of collection D.
For example, the entropy of total data set shown in table 1 is:-(3/5)*log2(3/5)-(2/5)*log2(2/5).Specifically,
Using training set as the total data set of an entropy to be calculated, equally formula (1) is used to calculate each unit row pair in each data type
The entropy for the training set answered, this will not be repeated here.
In one embodiment, step S1124 includes:
Gain (A)=info (D)-infoA(D);Formula (3)
Wherein, A indicates that data type, v are the quantity for the cell row that data type A includes, DjFor jth in data type A
The corresponding training set of a cell row, | Dj| it is training set DjThe group number of included sample parameter, | D | included by total data set
The group number of sample parameter, info (Dj) it is training set DjEntropy, infoA(D) expectation that total data set is divided for data type A
Information, gain (A) are the information gain of data type.Specifically, if current total data set is to reject an optimal characteristics category
Property the obtained new total data set of row, then | D | for the group number of sample parameter included by new total data set, infoA(D) it is number
The expectation information that new total data set is divided according to type A.
For example, as shown in Table 1 and Table 2, the corresponding training set of air-introduced machine electric current has 4, sum of the air-introduced machine electric current to table 1
It is according to the expectation information divided is collected:(2/5)*【-(1/2)*log2(1/2)-(1/2)*log2(1/2)】+(1/5)*【-(1/1)*
log2(1/1)-(0/1)*log2(0/1)】+(1/5)*【-(1/1)*log2(1/1)-(0/1)*log2(0/1)】+(1/5)*【-
(1/1)*log2(1/1)-(0/1)*log2(0/1)】。
It should be understood that although each step in the flow chart of Fig. 1-3 is shown successively according to the instruction of arrow,
These steps are not that the inevitable sequence indicated according to arrow executes successively.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 1-3
Part steps may include that either these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can either the sub-step of other steps or at least part in stage be in turn or alternately with other steps
It executes.
In one embodiment, as shown in figure 4, providing a kind of generating set fault data prediction meanss, including:Parameter
Acquisition module 120, Parameter analysis module 140, data obtaining module 160 and result output module 180, wherein:
Parameter collection module 120 is used to acquire the operating parameter in the current operational process of generating set.
Parameter analysis module 140 is used to carry out Decision Classfication to operating parameter using established decision-tree model.Wherein,
Decision-tree model characterizes the correspondence of operating parameter and classification information, that is, output category letter can be corresponded to by inputting operating parameter
Breath.
Data obtaining module 160 is for obtaining the classification information exported after decision-tree model Decision Classfication.
As a result output module 180 is used to export fault data prediction result according to classification information.
In above-mentioned generating set fault data prediction meanss, the operation using established decision-tree model to generating set
Parameter carries out Decision Classfication, and fault data prediction result is exported according to the classification information exported after Decision Classfication;On the one hand, pass through
Using decision-tree model, the problem of generating set accident analysis, is reduced to a failure modes problem, algorithm process is simply straight
Connect, and influenced by multiple coupled non-linear factor it is small, to which the accuracy of accident analysis can be improved.On the other hand, by sending out
In electric unit running process acquire operating parameter analyzed, when generating set failure does not occur carry out number of faults it was predicted that
Detection foundation is provided for field personnel, the generation of safety accident can be reduced, in this way, failure predication accuracy is high.
In one embodiment, operating parameter include air-introduced machine electric current, air-introduced machine entrance aperture, air-introduced machine entrance negative pressure,
Air-introduced machine controls oil pressure, air-introduced machine bearing axial vibration value, air-introduced machine bearing radial vibration value, air inducing main bearing first and tests
Point temperature, the second test point of air inducing main bearing temperature, air inducing main bearing third test point temperature, air inducing main bearing the 4th
Test point temperature, air-introduced machine non-drive side bearing temperature and air-introduced machine inboard bearing temperature.
By using the operating parameter including numerous types of data, the data type of acquisition is various, to decision-tree model
Decision Classfication is carried out according to numerous types of data, the accuracy of Decision Classfication can be improved.It is appreciated that in other embodiments,
Operating parameter can also include other data types.
In one embodiment, above-mentioned generating set fault data prediction meanss further include that (figure is not for model building module
Show), for obtaining multigroup sample parameter and the corresponding fault category of each group sample parameter, data type that sample parameter includes and
The data type that operating parameter includes is identical;According to sample parameter and the corresponding fault category of each group sample parameter, successively from more
A data type is chosen in a data type as optimal characteristics attribute;According to selection sequence successively with each optimal characteristics attribute
As current division node, according to the corresponding fault category of each group sample parameter to each group corresponding to current division node
The value of sample parameter carries out decision division, and establishment obtains decision-tree model.
Decision-tree model is created by using multigroup sample parameter identical with the data type that operating parameter includes, to fortune
Row Parameter analysis is more identical, result is more acurrate, to which the accuracy of fault data prediction can be improved.
In one embodiment, sample parameter is that the data during acquiring generating set machine history run obtain.By adopting
Use the data of generating set history run as sample parameter, gear to actual circumstances, to make decision-tree model that establishment obtains certainly
Plan classification is accurate, to which the accuracy of fault data prediction is high.
In one embodiment, model building module with the corresponding fault category of sample parameter and sample parameter include it is each
A data type is row, and each group sample parameter is arranged in rows, total data set is obtained, and the entropy according to collection that totalizes;With sum
According to a cell row of the row of same value under same row as respective column is concentrated, individual data type is extracted from total data set
Column, fault category column, a cell row of the data type column extracted are combined, and obtain being extracted
The corresponding training set of cell row extracted in data type;Calculate the corresponding training set of each unit row in each data type
Entropy;Corresponding data type is calculated according to the entropy of the corresponding each training set of the entropy, total data set and data type of total data set
Information gain;Maximum information gain is chosen from the information gain of each data type, maximum information gain is corresponding
Data type is as optimal characteristics attribute;The row that optimal characteristics attribute is rejected from total data set obtain new total data set, and
The row of the same value under same row using in total data set is returned as a cell row of respective column, is extracted from total data set single
A data type column, fault category column, a cell row of the data type column extracted are combined, and are obtained
To the corresponding training set of cell row extracted in the data type extracted, taken until all data types are selected
Finish.
By calculating the information gain of each data type, choosing the corresponding data type of maximum information gain successively
As optimal characteristics attribute, so as to get decision-tree model tree construction separating capacity it is strong, accuracy higher, to fault data
The accuracy of prediction is high.
In one embodiment, the entropy of total data set is calculated according to following formula for model building module:
Wherein, D indicates total data set, piThe number and total data set D occurred for the i-th class fault category in total data set D
The ratio of the group number of included sample parameter, m are the classification number for the fault category that total data set D includes, and info (D) is sum
According to the entropy of collection D.
In one embodiment, the information increasing of corresponding data type is calculated according to following formula for model building module
Benefit:
Gain (A)=info (D)-infoA(D);
Wherein, A indicates that data type, v are the quantity for the cell row that data type A includes, DjFor jth in data type A
The corresponding training set of a cell row, | Dj| it is training set DjThe group number of included sample parameter, | D | included by total data set
The group number of sample parameter, info (Dj) it is training set DjEntropy, infoA(D) expectation that total data set is divided for data type A
Information, gain (A) are the information gain of data type.
Specific restriction about generating set fault data prediction meanss may refer to above for generating set failure
The restriction of data predication method, details are not described herein.Modules in above-mentioned generating set fault data prediction meanss can be complete
Portion or part are realized by software, hardware and combinations thereof.Above-mentioned each module can be in the form of hardware embedded in or independently of calculating
In processor in machine equipment, can also in a software form it be stored in the memory in computer equipment, in order to processor
It calls and executes the corresponding operation of the above modules.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 5.The computer equipment includes the processor connected by system bus, memory, network interface, display
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate by network connection with external terminal.When the computer program is executed by processor with
Realize a kind of generating set fault data prediction technique.The display screen of the computer equipment can be liquid crystal display or electronics
The input unit of ink display screen, the computer equipment can be the touch layer covered on display screen, can also be that computer is set
Button, trace ball or the Trackpad being arranged on standby shell, can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 5, is only tied with the relevant part of application scheme
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
May include either combining certain components than more or fewer components as shown in the figure or being arranged with different components.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor realize following steps when executing computer program:
Acquire the operating parameter in the current operational process of generating set;Using established decision-tree model to operating parameter
Carry out Decision Classfication;Obtain the classification information exported after decision-tree model Decision Classfication;Fault data is exported according to classification information
Prediction result.Wherein, the correspondence of decision-tree model characterization operating parameter and classification information, that is, inputting operating parameter can be right
Answer output category information.
Above-mentioned generating set fault data prediction technique may be implemented in above computer equipment, and accident analysis similarly can be improved
Accuracy, and the generation of safety accident can be reduced, failure predication accuracy is high.
In one embodiment, when processor executes computer program, the operating parameter of acquisition includes air-introduced machine electric current, draws
Fans entrance aperture, air-introduced machine entrance negative pressure, air-introduced machine control oil pressure, air-introduced machine bearing axial vibration value, air-introduced machine bearing diameter
To vibration values, the first test point of air inducing main bearing temperature, the second test point of air inducing main bearing temperature, air inducing main bearing
Three test point temperature, the 4th test point temperature of air inducing main bearing, air-introduced machine non-drive side bearing temperature and air-introduced machine driving side
Bearing temperature.
In one embodiment, following steps are also realized when processor executes computer program:
Obtain multigroup sample parameter and the corresponding fault category of each group sample parameter;Joined according to sample parameter and each group sample
The corresponding fault category of number chooses a data type as optimal characteristics attribute from multiple data types successively;According to choosing
Take sequence successively using each optimal characteristics attribute as current division node, according to the corresponding fault category pair of each group sample parameter
The value of each group sample parameter corresponding to current division node carries out decision division, and establishment obtains decision-tree model.
In one embodiment, following steps are also realized when processor executes computer program:
It is row with each data type that the corresponding fault category of sample parameter and sample parameter include, each group sample is joined
Number is arranged in rows, and obtains total data set, and the entropy according to collection that totalizes;Made with the row of same value under same row in total data set
For a cell row of respective column, individual data type column is extracted from total data set, fault category column, is extracted
A cell row of data type column be combined, obtain the cell row extracted in extracted data type correspondence
Training set;Calculate the entropy of the corresponding training set of each unit row in each data type;According to the entropy of total data set, total data set and
The information gain of corresponding data type is calculated in the entropy of the corresponding each training set of data type;Increase from the information of each data type
Maximum information gain is chosen in benefit, using the corresponding data type of maximum information gain as optimal characteristics attribute;From sum
The row that optimal characteristics attribute is rejected according to concentration obtain new total data set, and return with same value under same row in total data set
A cell row of the row as respective column, extracted from total data set individual data type column, fault category column,
One cell row of the data type column extracted is combined, and obtains the unit extracted in extracted data type
The corresponding training set of row, finishes until all data types are selected.
In one embodiment, when processor executes computer program, total data set is calculated according to following formula
Entropy:
Wherein, D indicates total data set, piThe number and total data set D occurred for the i-th class fault category in total data set D
The ratio of the group number of included sample parameter, m are the classification number for the fault category that total data set D includes, and info (D) is sum
According to the entropy of collection D.
In one embodiment, when processor executes computer program, corresponding data class is calculated according to following formula
The information gain of type:
Gain (A)=info (D)-infoA(D);
Wherein, A indicates that data type, v are the quantity for the cell row that data type A includes, DjFor jth in data type A
The corresponding training set of a cell row, | Dj| it is training set DjThe group number of included sample parameter, | D | included by total data set
The group number of sample parameter, info (Dj) it is training set DjEntropy, infoA(D) expectation that total data set is divided for data type A
Information, gain (A) are the information gain of data type.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes following steps when being executed by processor:
Acquire the operating parameter in the current operational process of generating set;Using established decision-tree model to operating parameter
Carry out Decision Classfication;Obtain the classification information exported after decision-tree model Decision Classfication;Fault data is exported according to classification information
Prediction result.Wherein, the correspondence of decision-tree model characterization operating parameter and classification information, that is, inputting operating parameter can be right
Answer output category information.
Above-mentioned generating set fault data prediction technique may be implemented in above computer readable storage medium storing program for executing, similarly can be improved
The accuracy of accident analysis, and the generation of safety accident can be reduced, failure predication accuracy is high.
In one embodiment, when computer program is executed by processor, the operating parameter of acquisition include air-introduced machine electric current,
Air-introduced machine entrance aperture, air-introduced machine entrance negative pressure, air-introduced machine control oil pressure, air-introduced machine bearing axial vibration value, air-introduced machine bearing
Radial vibration value, the first test point of air inducing main bearing temperature, the second test point of air inducing main bearing temperature, air inducing main bearing
Third test point temperature, the 4th test point temperature of air inducing main bearing, air-introduced machine non-drive side bearing temperature and air-introduced machine driving
Side bearing temperature.
In one embodiment, following steps are also realized when computer program is executed by processor:
Obtain multigroup sample parameter and the corresponding fault category of each group sample parameter;Joined according to sample parameter and each group sample
The corresponding fault category of number chooses a data type as optimal characteristics attribute from multiple data types successively;According to choosing
Take sequence successively using each optimal characteristics attribute as current division node, according to the corresponding fault category pair of each group sample parameter
The value of each group sample parameter corresponding to current division node carries out decision division, and establishment obtains decision-tree model.
In one embodiment, following steps are also realized when computer program is executed by processor:
It is row with each data type that the corresponding fault category of sample parameter and sample parameter include, each group sample is joined
Number is arranged in rows, and obtains total data set, and the entropy according to collection that totalizes;Made with the row of same value under same row in total data set
For a cell row of respective column, individual data type column is extracted from total data set, fault category column, is extracted
A cell row of data type column be combined, obtain the cell row extracted in extracted data type correspondence
Training set;Calculate the entropy of the corresponding training set of each unit row in each data type;According to the entropy of total data set, total data set and
The information gain of corresponding data type is calculated in the entropy of the corresponding each training set of data type;Increase from the information of each data type
Maximum information gain is chosen in benefit, using the corresponding data type of maximum information gain as optimal characteristics attribute;From sum
The row that optimal characteristics attribute is rejected according to concentration obtain new total data set, and return with same value under same row in total data set
A cell row of the row as respective column, extracted from total data set individual data type column, fault category column,
One cell row of the data type column extracted is combined, and obtains the unit extracted in extracted data type
The corresponding training set of row, finishes until all data types are selected.
In one embodiment, when computer program is executed by processor, total data set is calculated according to following formula
Entropy:
Wherein, D indicates total data set, piThe number and total data set D occurred for the i-th class fault category in total data set D
The ratio of the group number of included sample parameter, m are the classification number for the fault category that total data set D includes, and info (D) is sum
According to the entropy of collection D.
In one embodiment, when computer program is executed by processor, corresponding data is calculated according to following formula
The information gain of type:
Gain (A)=info (D)-infoA(D);
Wherein, A indicates that data type, v are the quantity for the cell row that data type A includes, DjFor jth in data type A
The corresponding training set of a cell row, | Dj| it is training set DjThe group number of included sample parameter, | D | included by total data set
The group number of sample parameter, info (Dj) it is training set DjEntropy, infoA(D) expectation that total data set is divided for data type A
Information, gain (A) are the information gain of data type.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein,
Any reference to memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above example can be combined arbitrarily, to keep description succinct, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield is all considered to be the range of this specification record.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the protection domain of the application patent should be determined by the appended claims.
Claims (10)
1. a kind of generating set fault data prediction technique, the method includes:
Acquire the operating parameter in the current operational process of generating set;
Decision Classfication, the decision-tree model characterization operation ginseng are carried out to the operating parameter using established decision-tree model
The correspondence of number and classification information;
Obtain the classification information exported after the decision-tree model Decision Classfication;
Fault data prediction result is exported according to the classification information.
2. according to the method described in claim 1, it is characterized in that, the operating parameter includes air-introduced machine electric current, air-introduced machine enters
Mouth aperture, air-introduced machine entrance negative pressure, air-introduced machine control oil pressure, air-introduced machine bearing axial vibration value, air-introduced machine bearing radial vibration
Value, the test of the first test point of air inducing main bearing temperature, the second test point of air inducing main bearing temperature, air inducing main bearing third
Point temperature, the 4th test point temperature of air inducing main bearing, air-introduced machine non-drive side bearing temperature and air-introduced machine inboard bearing temperature
Degree.
3. according to the method described in claim 1, it is characterized in that, described use established decision-tree model to the operation
Before parameter carries out Decision Classfication, further include:
Obtain multigroup sample parameter and the corresponding fault category of each group sample parameter, the data type that the sample parameter includes and
The data type that the operating parameter includes is identical;
According to the sample parameter and the corresponding fault category of each group sample parameter, one is chosen from multiple data types successively
Data type is as optimal characteristics attribute;
It is corresponding according to each group sample parameter according to selection sequence successively using each optimal characteristics attribute as current division node
Fault category carries out decision division to the value of each group sample parameter corresponding to current division node, and establishment obtains decision tree
Model.
4. according to the method described in claim 3, it is characterized in that, described according to the sample parameter and each group sample parameter pair
The fault category answered chooses a data type as optimal characteristics attribute from multiple data types successively, including:
It is row with each data type that the corresponding fault category of the sample parameter and the sample parameter include, by each group sample
This parameter is arranged in rows, and obtains total data set, and calculates the entropy of the total data set;
Using under same row in the total data set row of same value as respective column a cell row, from total data set
The unit traveling of middle extraction individual data type column, fault category column, the data type column extracted
Row combination, obtains the corresponding training set of the cell row extracted in extracted data type;
Calculate the entropy of the corresponding training set of each unit row in each data type;
It is calculated according to the entropy of the entropy of the total data set, the total data set and the corresponding each training set of the data type
The information gain of corresponding data type;
Maximum information gain is chosen from the information gain of each data type, by the corresponding data type of maximum information gain
As optimal characteristics attribute;
The row that the optimal characteristics attribute is rejected from the total data set obtain new total data set, and return described with described
A cell row of the row of same value as respective column under same row in total data set is extracted single from total data set
Data type column, fault category column, a cell row of the data type column extracted are combined, and are obtained
The step of cell row extracted in the data type extracted corresponding training set, until all data types are selected
It finishes.
5. according to the method described in claim 4, it is characterized in that, the entropy for calculating the total data set, including:
Wherein, D indicates the total data set, piThe number occurred for the i-th class fault category in the total data set D with it is described total
The ratio of the group number of sample parameter included by data set D, m are the classification number for the fault category that the total data set D includes,
Info (D) is the entropy of the total data set D.
6. according to the method described in claim 5, it is characterized in that, the entropy according to the total data set, the total data
The information gain of corresponding data type is calculated in the entropy of collection each training set corresponding with the data type, including:
Gain (A)=info (D)-infoA(D);
Wherein, A indicates that data type, v are the quantity for the cell row that data type A includes, DjFor j-th of unit in data type A
The corresponding training set of row, | Dj| it is training set DjThe group number of included sample parameter, | D | for sample ginseng included by total data set
Several group numbers, info (Dj) it is training set DjEntropy, infoA(D) the expectation information that total data set is divided for data type A,
Gain (A) is the information gain of data type.
7. a kind of generating set fault data prediction meanss, which is characterized in that described device includes:
Parameter collection module, for acquiring the operating parameter in the current operational process of generating set;
Parameter analysis module, it is described to determine for carrying out Decision Classfication to the operating parameter using established decision-tree model
Plan tree-model characterizes the correspondence of operating parameter and classification information;
Data obtaining module, for obtaining the classification information exported after the decision-tree model Decision Classfication;
As a result output module, for exporting fault data prediction result according to the classification information.
8. generating set fault data prediction meanss according to claim 7, which is characterized in that further include model foundation mould
Block, for obtaining multigroup sample parameter and the corresponding fault category of each group sample parameter, the data class that the sample parameter includes
Type is identical with the data type that the operating parameter includes;According to the sample parameter and the corresponding failure classes of each group sample parameter
Not, a data type is chosen from multiple data types successively as optimal characteristics attribute;According to selection sequence successively with each
Optimal characteristics attribute is as current division node, according to the corresponding fault category of each group sample parameter to current division node
The value of corresponding each group sample parameter carries out decision division, and establishment obtains decision-tree model.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In when the processor executes the computer program the step of any one of realization claim 1 to 6 the method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method according to any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810426084.3A CN108664010A (en) | 2018-05-07 | 2018-05-07 | Generating set fault data prediction technique, device and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810426084.3A CN108664010A (en) | 2018-05-07 | 2018-05-07 | Generating set fault data prediction technique, device and computer equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108664010A true CN108664010A (en) | 2018-10-16 |
Family
ID=63778565
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810426084.3A Pending CN108664010A (en) | 2018-05-07 | 2018-05-07 | Generating set fault data prediction technique, device and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108664010A (en) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109272603A (en) * | 2018-10-26 | 2019-01-25 | 北京长城华冠汽车技术开发有限公司 | Vehicle trouble analytical database and construction method, failure prediction method, failure prediction system |
CN109359866A (en) * | 2018-10-17 | 2019-02-19 | 平安国际融资租赁有限公司 | Risk hidden danger monitoring method, device and computer equipment based on leased equipment |
CN109472372A (en) * | 2018-10-17 | 2019-03-15 | 平安国际融资租赁有限公司 | Resource data distribution method, device and computer equipment based on leased equipment |
CN109492833A (en) * | 2018-12-25 | 2019-03-19 | 洛阳中科协同科技有限公司 | A kind of bearing ring quality of production prediction technique based on decision Tree algorithms |
CN109501834A (en) * | 2018-11-28 | 2019-03-22 | 交控科技股份有限公司 | A kind of point machine failure prediction method and device |
CN110188823A (en) * | 2019-05-30 | 2019-08-30 | 北京上格云技术有限公司 | A kind of Fault Tree Diagnosis Decision method and computer-readable medium |
CN110244673A (en) * | 2019-06-11 | 2019-09-17 | 中科台达(湖州)信息技术有限公司 | A kind of metal material manufacturing enterprise equipment on-line monitoring and managing method and system |
CN110378427A (en) * | 2019-07-23 | 2019-10-25 | 上海电气风电集团有限公司 | Fault detection method, system, equipment and the medium of the blade root bolt of wind electricity blade |
CN111105063A (en) * | 2018-10-26 | 2020-05-05 | 北京国双科技有限公司 | Fault prediction method, fault prediction device, model construction method, fault prediction device, processor and readable storage medium |
CN111416442A (en) * | 2020-04-26 | 2020-07-14 | 佛山科学技术学院 | UPS power distribution cabinet monitoring method and system based on WeChat small program |
CN111611146A (en) * | 2020-06-18 | 2020-09-01 | 南方电网科学研究院有限责任公司 | Micro-service fault prediction method and device |
CN111624906A (en) * | 2020-05-11 | 2020-09-04 | 新智数字科技有限公司 | Equipment operation state determination method and device, readable medium and electronic equipment |
CN111737493A (en) * | 2020-06-23 | 2020-10-02 | 平安科技(深圳)有限公司 | Abnormal data source output method and device based on decision tree and computer equipment |
CN112330095A (en) * | 2020-10-09 | 2021-02-05 | 中车青岛四方机车车辆股份有限公司 | Quality management method based on decision tree algorithm |
CN112492630A (en) * | 2019-09-11 | 2021-03-12 | 中国电信股份有限公司 | Fault prediction method and device of base station equipment and base station |
CN112633617A (en) * | 2019-09-24 | 2021-04-09 | 北京国双科技有限公司 | Maintenance strategy generation method and device, computer equipment and readable storage medium |
CN113468818A (en) * | 2021-07-13 | 2021-10-01 | 上海电气风电集团股份有限公司 | Method and device for monitoring winding running state of wind generating set |
CN114198332A (en) * | 2021-12-03 | 2022-03-18 | 上海发电设备成套设计研究院有限责任公司 | Induced draft fan fault monitoring system and method |
CN114548326A (en) * | 2022-04-27 | 2022-05-27 | 深圳丰尚智慧农牧科技有限公司 | Fault processing method and device for feed production equipment and computer equipment |
CN116500441A (en) * | 2023-06-30 | 2023-07-28 | 无锡中基电机制造有限公司 | Motor fault detection and positioning method and system |
CN116520817A (en) * | 2023-07-05 | 2023-08-01 | 贵州宏信达高新科技有限责任公司 | ETC system running state real-time monitoring system and method based on expressway |
CN116664096A (en) * | 2022-08-23 | 2023-08-29 | 国家电投集团科学技术研究院有限公司 | Wind power bolt data processing method and device based on federal learning |
CN117520964A (en) * | 2024-01-04 | 2024-02-06 | 深圳市霆宝科技有限公司 | Motor pre-diagnosis method based on artificial intelligence |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105894177A (en) * | 2016-03-25 | 2016-08-24 | 国家电网公司 | Decision-making-tree-algorithm-based analysis and evaluation method for operation risk of power equipment |
CN105930629A (en) * | 2016-07-13 | 2016-09-07 | 大唐南京环保科技有限责任公司 | On-line fault diagnosis method based on massive amounts of operating data |
CN106054104A (en) * | 2016-05-20 | 2016-10-26 | 国网新疆电力公司电力科学研究院 | Intelligent ammeter fault real time prediction method based on decision-making tree |
CN107016404A (en) * | 2017-02-24 | 2017-08-04 | 沈阳工业大学 | Wind power generating set failure prediction method based on D S evidence fusions |
CN107220469A (en) * | 2017-07-14 | 2017-09-29 | 华北电力大学(保定) | A kind of method and system of fan condition estimation |
-
2018
- 2018-05-07 CN CN201810426084.3A patent/CN108664010A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105894177A (en) * | 2016-03-25 | 2016-08-24 | 国家电网公司 | Decision-making-tree-algorithm-based analysis and evaluation method for operation risk of power equipment |
CN106054104A (en) * | 2016-05-20 | 2016-10-26 | 国网新疆电力公司电力科学研究院 | Intelligent ammeter fault real time prediction method based on decision-making tree |
CN105930629A (en) * | 2016-07-13 | 2016-09-07 | 大唐南京环保科技有限责任公司 | On-line fault diagnosis method based on massive amounts of operating data |
CN107016404A (en) * | 2017-02-24 | 2017-08-04 | 沈阳工业大学 | Wind power generating set failure prediction method based on D S evidence fusions |
CN107220469A (en) * | 2017-07-14 | 2017-09-29 | 华北电力大学(保定) | A kind of method and system of fan condition estimation |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109359866B (en) * | 2018-10-17 | 2024-05-03 | 塔比星信息技术(深圳)有限公司 | Risk hidden danger monitoring method and device based on leasing equipment and computer equipment |
CN109359866A (en) * | 2018-10-17 | 2019-02-19 | 平安国际融资租赁有限公司 | Risk hidden danger monitoring method, device and computer equipment based on leased equipment |
CN109472372A (en) * | 2018-10-17 | 2019-03-15 | 平安国际融资租赁有限公司 | Resource data distribution method, device and computer equipment based on leased equipment |
CN109472372B (en) * | 2018-10-17 | 2024-07-05 | 塔比星信息技术(深圳)有限公司 | Resource data distribution method and device based on leasing equipment and computer equipment |
CN109272603A (en) * | 2018-10-26 | 2019-01-25 | 北京长城华冠汽车技术开发有限公司 | Vehicle trouble analytical database and construction method, failure prediction method, failure prediction system |
CN111105063A (en) * | 2018-10-26 | 2020-05-05 | 北京国双科技有限公司 | Fault prediction method, fault prediction device, model construction method, fault prediction device, processor and readable storage medium |
CN109501834A (en) * | 2018-11-28 | 2019-03-22 | 交控科技股份有限公司 | A kind of point machine failure prediction method and device |
CN109492833A (en) * | 2018-12-25 | 2019-03-19 | 洛阳中科协同科技有限公司 | A kind of bearing ring quality of production prediction technique based on decision Tree algorithms |
CN110188823A (en) * | 2019-05-30 | 2019-08-30 | 北京上格云技术有限公司 | A kind of Fault Tree Diagnosis Decision method and computer-readable medium |
CN110244673A (en) * | 2019-06-11 | 2019-09-17 | 中科台达(湖州)信息技术有限公司 | A kind of metal material manufacturing enterprise equipment on-line monitoring and managing method and system |
CN110378427A (en) * | 2019-07-23 | 2019-10-25 | 上海电气风电集团有限公司 | Fault detection method, system, equipment and the medium of the blade root bolt of wind electricity blade |
CN112492630B (en) * | 2019-09-11 | 2023-02-03 | 中国电信股份有限公司 | Fault prediction method and device of base station equipment and base station |
CN112492630A (en) * | 2019-09-11 | 2021-03-12 | 中国电信股份有限公司 | Fault prediction method and device of base station equipment and base station |
CN112633617A (en) * | 2019-09-24 | 2021-04-09 | 北京国双科技有限公司 | Maintenance strategy generation method and device, computer equipment and readable storage medium |
CN111416442A (en) * | 2020-04-26 | 2020-07-14 | 佛山科学技术学院 | UPS power distribution cabinet monitoring method and system based on WeChat small program |
CN111624906A (en) * | 2020-05-11 | 2020-09-04 | 新智数字科技有限公司 | Equipment operation state determination method and device, readable medium and electronic equipment |
CN111611146A (en) * | 2020-06-18 | 2020-09-01 | 南方电网科学研究院有限责任公司 | Micro-service fault prediction method and device |
CN111611146B (en) * | 2020-06-18 | 2023-05-16 | 南方电网科学研究院有限责任公司 | Micro-service fault prediction method and device |
CN111737493B (en) * | 2020-06-23 | 2023-05-02 | 平安科技(深圳)有限公司 | Abnormal data source output method and device based on decision tree and computer equipment |
CN111737493A (en) * | 2020-06-23 | 2020-10-02 | 平安科技(深圳)有限公司 | Abnormal data source output method and device based on decision tree and computer equipment |
CN112330095A (en) * | 2020-10-09 | 2021-02-05 | 中车青岛四方机车车辆股份有限公司 | Quality management method based on decision tree algorithm |
CN113468818A (en) * | 2021-07-13 | 2021-10-01 | 上海电气风电集团股份有限公司 | Method and device for monitoring winding running state of wind generating set |
CN114198332B (en) * | 2021-12-03 | 2024-02-20 | 上海发电设备成套设计研究院有限责任公司 | Induced draft fan fault monitoring system and method |
CN114198332A (en) * | 2021-12-03 | 2022-03-18 | 上海发电设备成套设计研究院有限责任公司 | Induced draft fan fault monitoring system and method |
CN114548326B (en) * | 2022-04-27 | 2022-09-09 | 深圳丰尚智慧农牧科技有限公司 | Fault processing method and device for feed production equipment and computer equipment |
CN114548326A (en) * | 2022-04-27 | 2022-05-27 | 深圳丰尚智慧农牧科技有限公司 | Fault processing method and device for feed production equipment and computer equipment |
CN116664096A (en) * | 2022-08-23 | 2023-08-29 | 国家电投集团科学技术研究院有限公司 | Wind power bolt data processing method and device based on federal learning |
CN116664096B (en) * | 2022-08-23 | 2024-02-13 | 国家电投集团科学技术研究院有限公司 | Wind power bolt data processing method and device based on federal learning |
CN116500441A (en) * | 2023-06-30 | 2023-07-28 | 无锡中基电机制造有限公司 | Motor fault detection and positioning method and system |
CN116500441B (en) * | 2023-06-30 | 2023-08-29 | 无锡中基电机制造有限公司 | Motor fault detection and positioning method and system |
CN116520817A (en) * | 2023-07-05 | 2023-08-01 | 贵州宏信达高新科技有限责任公司 | ETC system running state real-time monitoring system and method based on expressway |
CN116520817B (en) * | 2023-07-05 | 2023-08-29 | 贵州宏信达高新科技有限责任公司 | ETC system running state real-time monitoring system and method based on expressway |
CN117520964A (en) * | 2024-01-04 | 2024-02-06 | 深圳市霆宝科技有限公司 | Motor pre-diagnosis method based on artificial intelligence |
CN117520964B (en) * | 2024-01-04 | 2024-04-02 | 深圳市霆宝科技有限公司 | Motor pre-diagnosis method based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108664010A (en) | Generating set fault data prediction technique, device and computer equipment | |
CN105677791B (en) | For analyzing the method and system of the operation data of wind power generating set | |
CN110929918B (en) | 10kV feeder fault prediction method based on CNN and LightGBM | |
CN104794059B (en) | A kind of defect positioning method and device recorded based on function call | |
TW541448B (en) | Rotating equipment diagnostic system and adaptive controller | |
Huang et al. | Review of data-driven prognostics and health management techniques: lessions learned from PHM data challenge competitions | |
CN105354587A (en) | Fault diagnosis method for gearbox of wind generation unit | |
CN104331837B (en) | The optimal method for simplifying for cutting the search of machine control strategy of electric power system transient stability | |
CN108304567B (en) | Method and system for identifying working condition mode and classifying data of high-voltage transformer | |
CN113962259A (en) | Multi-mode double-layer fault diagnosis method for fuel cell system | |
CN111722046A (en) | Transformer fault diagnosis method based on deep forest model | |
CN110197222A (en) | A method of based on multi-category support vector machines transformer fault diagnosis | |
CN114397526A (en) | Power transformer fault prediction method and system driven by state holographic sensing data | |
CN113435759B (en) | Primary equipment risk intelligent assessment method based on deep learning | |
CN111207067A (en) | Air compressor fault diagnosis method based on fuzzy support vector machine | |
CN116562114A (en) | Power transformer fault diagnosis method based on graph convolution neural network | |
CN115614292A (en) | Vibration monitoring device and method for vertical water pump unit | |
CN106056274A (en) | Power construction main body benefit analysis method based on PCA-DEA two-dimensional comprehensive evaluation model | |
CN115407753A (en) | Industrial fault diagnosis method for multivariate weighted ensemble learning | |
CN114626433A (en) | Fault prediction and classification method, device and system for intelligent electric energy meter | |
CN117056678B (en) | Machine pump equipment operation fault diagnosis method and device based on small sample | |
CN105137238A (en) | Fault diagnosis system for gas insulation combination electric appliance | |
CN117810491A (en) | Fuel cell system fault diagnosis method and system based on deep learning | |
CN113469252A (en) | Extra-high voltage converter valve operation state evaluation method considering unbalanced samples | |
CN112748331A (en) | Circuit breaker mechanical fault identification method and device based on DS evidence fusion |
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: 20181016 |