CN106679847A - Electric power equipment fault diagnosing method and apparatus - Google Patents
Electric power equipment fault diagnosing method and apparatus Download PDFInfo
- Publication number
- CN106679847A CN106679847A CN201611150376.6A CN201611150376A CN106679847A CN 106679847 A CN106679847 A CN 106679847A CN 201611150376 A CN201611150376 A CN 201611150376A CN 106679847 A CN106679847 A CN 106679847A
- Authority
- CN
- China
- Prior art keywords
- temperature
- rate
- data
- current time
- difference
- 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
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention relates to an electric power equipment fault diagnosing method and an apparatus, comprising: obtaining the temperature data of a piece of to-be-diagnosed electric power equipment at the present time; obtaining the temperature data, the temperature differential value and the temperature variation rate of the previous time; calculating the temperature differential value and the temperature variation rate of the present time; conducting data integration between the temperature differential value and the temperature variation rate of the present time and those of the previous time for an integrated result; and determining whether the to-be-diagnosed electric power equipment suffers from any fault or not at the present time. The electric power equipment diagnosing method proposed by the invention is based on the data integration of three variables: the temperature data, the temperature differential value and the temperature variation rate for an electric power equipment diagnosing result, which can diagnose the fault of the equipment in real time. In addition, the entire detection process is fast and highly accurate with low erroneous fault reporting, therefore, reducing redundancy information to a large extent.
Description
Technical field
The present invention relates to Fault Diagnosis for Electrical Equipment technical field, more particularly to a kind of Fault Diagnosis for Electrical Equipment method and
Device.
Background technology
As the continuous expansion of power system scale, the power supply level of China are increasingly improved, various use are preferably met
The need for electricity at family.At the same time, requirement of the people to power supply reliability is also increasingly improved.Improve power supply reliability one is heavy
Want aspect to be to reduce the generation of electrical equipment fault and be diagnosed to be rapidly electrical equipment fault, rush to repair and extensive as early as possible so as to timely
Telegram in reply Force system normally runs.The appearance of fault diagnosis technology, is to improve the reliability powered of power equipment and safety is opened up
One new approach.
Current Fault Diagnosis for Electrical Equipment method treats the state quantity data of diagnosing electric power by obtaining, to the shape
State amount data are analyzed, and then determine whether power equipment breaks down, and provide important foundation for maintenance of equipment, wherein,
The state quantity data includes temperature or motor speed etc..For example, when when diagnosing electric power is transformator, by obtaining institute
The temperature of transformator is stated, data analysiss are carried out to the temperature, determine whether the transformator breaks down according to analysis result.
But, current method for diagnosing faults is all judging equipment according to this characteristic quantity of quantity of state of power equipment
Failure condition, information be not comprehensive, and the precision for causing Fault Diagnosis for Electrical Equipment is low, rate of false alarm is high.
The content of the invention
To overcome problem present in correlation technique, the present invention to provide a kind of Fault Diagnosis for Electrical Equipment method and device.
A kind of first aspect according to embodiments of the present invention, there is provided Fault Diagnosis for Electrical Equipment method, including：
The temperature data at diagnosing electric power current time is treated in acquisition；
The temperature data of acquisition previous moment, temperature difference, rate of temperature change, the temperature difference and temperature for calculating current time become
Rate；
Temperature data, temperature difference, the temperature data of rate of temperature change and previous moment to the current time, temperature
Difference, rate of temperature change carry out data fusion, obtain fusion results, determine
Failure.
Preferably, the temperature of the temperature data to the current time, temperature difference, rate of temperature change and previous moment
Before data, temperature difference, rate of temperature change carry out data fusion, also include：
Temperature data, temperature difference, the temperature data of rate of temperature change and previous moment to the current time, temperature
Difference, rate of temperature change carry out pretreatment, remove noise and singular point.
Preferably, the temperature difference and rate of temperature change for calculating current time, including：
By the temperature data at current time and the difference of the temperature data of previous moment, as the temperature at the current time
Difference.
Preferably, the temperature difference and rate of temperature change for calculating current time, also includes：
Draw the time dependent curve of the temperature data；
The time dependent function of temperature data is calculated according to the curve；
The function is obtained into the rate of temperature change at current time to time derivation at current time.
Preferably, the temperature of the temperature data to the current time, temperature difference, rate of temperature change and previous moment
Data, temperature difference, rate of temperature change carry out data fusion, obtain fusion results, determine that follow-up power-off power sets described in current time
It is standby whether to break down, including：
Using temperature data, temperature difference and rate of temperature change as three input nodes, will break down and not break down
As two output nodes, neural network model is set up, wherein, the hidden layer of the neural network model is set to eight nodes；
It is input into using the historical temperature data for treating diagnosing electric power, temperature difference and rate of temperature change as training sample
The neural network model is trained, and obtains the hidden layer input weights and output weights of the neural network model, wherein, institute
It is temperature data when diagnosing electric power normally runs, temperature to state historical temperature data, temperature difference and rate of temperature change
Degree difference and rate of temperature change；
By the input weights and output right value update to the neural network model；
By the temperature data of the temperature data at the current time, temperature difference, rate of temperature change and previous moment, temperature
Difference, rate of temperature change are input into the neural network model for updating and are trained as test sample, obtain the power for breaking down
Weight and the weight not broken down, determine.
A kind of second aspect according to embodiments of the present invention, there is provided Fault Diagnosis for Electrical Equipment device, including：
Temperature acquisition module, for obtaining the temperature data for treating diagnosing electric power current time；
Computing module, for obtaining the temperature data of previous moment, temperature difference, rate of temperature change, calculates current time
Temperature difference and rate of temperature change；
Fault diagnosis module, for the temperature data to the current time, temperature difference, rate of temperature change and previous moment
Temperature data, temperature difference, rate of temperature change carry out data fusion, obtain fusion results, determine
Whether power equipment breaks down.
Preferably, also include：
Pretreatment module, for the temperature data to the current time, temperature difference, rate of temperature change and previous moment
Temperature data, temperature difference, rate of temperature change carry out pretreatment, remove noise and singular point.
Preferably, the computing module includes：
Temperature difference computing unit, for by the difference of the temperature data at current time and the temperature data of previous moment, as
The temperature difference at the current time.
Preferably, the computing module also includes：
Curve plotting unit, for drawing the time dependent curve of the temperature data；
Function calculating unit, for calculating the time dependent function of temperature data according to the curve；
Rate of temperature change computing unit, for by the function at current time to time derivation, obtain current time
Rate of temperature change.
Preferably, the malfunctioning module includes：
Modeling unit, will break down as three input nodes for using temperature data, temperature difference and rate of temperature change
Do not break down as two output nodes, set up neural network model, wherein, the hidden layer of the neural network model is set to
Eight nodes；
Training unit, for being made with the historical temperature data for treating diagnosing electric power, temperature difference and rate of temperature change
The neural network model is input into for training sample to be trained, hidden layer input weights of the neural network model and defeated are obtained
Go out weights, wherein, the historical temperature data, temperature difference and rate of temperature change are described when diagnosing electric power normally runs
Temperature data, temperature difference and rate of temperature change；
Model modification unit, for by it is described input weights and output right value update to the neural network model；
Failure determining unit, for by the temperature data at the current time, temperature difference, rate of temperature change and previous moment
Temperature data, temperature difference, rate of temperature change as test sample be input into update the neural network model be trained, obtain
To the weight for breaking down and the weight not broken down, determine
Barrier.
The technical scheme that embodiments of the invention are provided can include following beneficial effect：
A kind of Fault Diagnosis for Electrical Equipment method and device provided in an embodiment of the present invention, including：Obtain follow-up power-off power
The temperature data at equipment current time；The temperature data of acquisition previous moment, temperature difference, rate of temperature change, calculate current time
Temperature difference and rate of temperature change；The temperature of temperature data, temperature difference, rate of temperature change and previous moment to the current time
Degrees of data, temperature difference, rate of temperature change carry out data fusion, obtain fusion results, determine follow-up power-off power described in current time
Whether equipment breaks down.Fault Diagnosis for Electrical Equipment method provided in an embodiment of the present invention, based on temperature data, temperature difference and
Three variables of rate of temperature change carry out data fusion, obtain Fault Diagnosis for Electrical Equipment result；Can in real time to the former of power equipment
Barrier situation is diagnosed, and whole process diagnosis speed is fast, and the degree of accuracy of fault diagnosis is high, and rate of false alarm is low, and to a great extent
Reduce redundancy.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not
The present invention can be limited.
Description of the drawings
During accompanying drawing herein is merged in description and the part of this specification is constituted, show the enforcement for meeting the present invention
Example, and be used for explaining the principle of the present invention together with description.
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, for those of ordinary skill in the art
Speech, without having to pay creative labor, can be with according to these other accompanying drawings of accompanying drawings acquisition.
Fig. 1 is a kind of schematic flow sheet of Fault Diagnosis for Electrical Equipment method provided in an embodiment of the present invention；
Fig. 2 is that the detailed process of step S300 in a kind of Fault Diagnosis for Electrical Equipment method provided in an embodiment of the present invention shows
It is intended to；
Fig. 3 is a kind of structural representation of neural network model provided in an embodiment of the present invention；
Fig. 4 is a kind of structural representation of Fault Diagnosis for Electrical Equipment device provided in an embodiment of the present invention.
Specific embodiment
Here in detail exemplary embodiment will be illustrated, its example is illustrated in the accompanying drawings.Explained below is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent and the consistent all embodiments of the present invention.Conversely, they be only with as appended by
The example of consistent apparatus and method in terms of some described in detail in claims, the present invention.
The embodiment of the present invention provides a kind of Fault Diagnosis for Electrical Equipment method, referring to Fig. 1, including：
S100：The temperature data at diagnosing electric power current time is treated in acquisition.
In specific implementation process, temperature sensor is set on diagnosing electric power is treated, it is real-time by temperature sensor
The temperature data of diagnosing electric power is treated in measurement, obtains the temperature for treating diagnosing electric power of the temperature sensor test at current time
Degrees of data.
S200：Obtain the temperature data of previous moment, temperature difference, rate of temperature change, calculate current time temperature difference and
Rate of temperature change.
The temperature data of diagnosing electric power previous moment, temperature difference, rate of temperature change are treated in acquisition, calculate current time
Temperature difference and rate of temperature change.According to the temperature data of previous moment, the temperature difference at current time is calculated, in specific implementation process
In, the temperature difference and rate of temperature change for calculating current time, including：
By the temperature data at current time and the difference of the temperature data of previous moment, as the temperature at the current time
Difference.
In specific implementation process, the temperature difference and rate of temperature change for calculating current time also includes：
S201：Draw the time dependent curve of the temperature data.
According to the temperature data for treating diagnosing electric power for obtaining, the time dependent curve of the temperature data is drawn.
S202：The time dependent function of temperature data is calculated according to the curve.
According to the time dependent curve of temperature data that step S201 is drawn, the time dependent letter of temperature data is calculated
Number.
S203：The function is obtained into the rate of temperature change at current time to time derivation at current time.
First derivative was asked to the time at current time to the functional relation that step S203 is calculated, the temperature at current time is obtained
Degree rate of change.
S300：Temperature data, temperature difference, the temperature data of rate of temperature change and previous moment to the current time,
Temperature difference, rate of temperature change carry out data fusion, obtain fusion results, determine and whether treat diagnosing electric power described in current time
Break down.
In specific implementation process, the method for data fusion has various, in embodiments of the present invention, is calculated using neutral net
Method carries out data fusion, determines.
In embodiments of the present invention, shown in Figure 2, the specific embodiment of step S300 includes：
S301：Using temperature data, temperature difference and rate of temperature change as three input nodes, will break down and not occur
Failure sets up neural network model as two output nodes, wherein, the hidden layer of the neural network model is set to eight sections
Point.
As shown in figure 3, neural network model is divided into 3 layers, respectively input layer, hidden layer and output layer, hidden layer are provided in
Intermediate layer between input layer and output layer.In specific implementation process, input layer includes 3 input nodes, respectively follow-up
The temperature data of disconnected power equipment, temperature difference and rate of temperature change；Rule of thumb and contrast, hidden layer is set to 8 nodes；Output layer
For 2 output nodes, respectively break down and do not break down.
S302：Using the historical temperature data for treating diagnosing electric power, temperature difference and rate of temperature change as training sample
This input neural network model is trained, and obtains the hidden layer input weights and output weights of the neural network model.
In specific implementation process, the historical temperature data, temperature difference and rate of temperature change are the follow-up power-off power
Temperature data, temperature difference and rate of temperature change when equipment normally runs.
Although the hidden layer of neural network model is not connected to external, change hidden layer input weights and output weights, can
To change the performance of whole neural network model, therefore, before fault diagnosis, it is thus necessary to determine that the input weights and output power
Value.
In embodiments of the present invention, with the historical temperature data for treating diagnosing electric power, temperature difference and temperature change
Rate is input into the neural network model as training sample and is trained, and calculates the input weights of the neural network model
W and output weights V, wherein, for described, the historical temperature data, temperature difference and rate of temperature change treat that diagnosing electric power is normal
Temperature data, temperature difference and rate of temperature change during operation, in specific implementation process, can obtain described in predetermined amount of time
Temperature data, temperature difference and rate of temperature change when diagnosing electric power normally runs is used as the historical temperature data, temperature
Degree difference and rate of temperature change, the predetermined amount of time include one day, one week or one month etc., in specific implementation process, technology
Personnel can be set to the predetermined amount of time according to practical situation, and here is not specifically limited.
S303：By the input weights and output right value update to the neural network model.
The input weights W calculated in step S302 and output weights V are updated to the neural network model.
S304：By the temperature data of the temperature data at the current time, temperature difference, rate of temperature change and previous moment,
Temperature difference, rate of temperature change are input into the neural network model for updating and are trained as test sample, are broken down
Weight and the weight not broken down, determine.
By the temperature data of the temperature data at the current time, temperature difference, rate of temperature change and previous moment, temperature
Difference, rate of temperature change are input into the neural network model for updating and are trained as test sample, obtain the power for breaking down
Weight and the weight not broken down, obtain the diagnostic result for treating described in current time whether diagnosing electric power breaks down, really
Determine described in current time, to treat whether diagnosing electric power breaks down.Using the temperature data at previous moment and current time, temperature
Spending poor, rate of temperature change carries out fault diagnosis as test sample, and diagnosis speed is fast, and due to being three comprising three groups of data
, used as test sample, diagnostic result degree of accuracy is high, and rate of false alarm is low for variable.
In specific implementation process, the diagnostic result of acquisition is output to user interface, points out user to be determined according to result
Whether need to safeguard or keep in repair.
In a kind of possible embodiment, the temperature data to the current time, temperature difference, rate of temperature change
Before temperature data, temperature difference, rate of temperature change with previous moment carries out data fusion, also include：
Temperature data, temperature difference, the temperature data of rate of temperature change and previous moment to the current time, temperature
Difference, rate of temperature change carry out pretreatment, remove noise and singular point.
Temperature data, temperature difference, the temperature data of rate of temperature change and previous moment to the current time, temperature
Difference, rate of temperature change carry out the process of pretreatment, can remove the noise and singular point in data；Pretreated data are entered
Row data fusion, diagnoses whether the band diagnosing electric power breaks down.The process of pretreatment can improve fault diagnosis
Degree of accuracy.
A kind of Fault Diagnosis for Electrical Equipment method provided in an embodiment of the present invention, including：Acquisition treats that diagnosing electric power is worked as
The temperature data at front moment；The temperature data of acquisition previous moment, temperature difference, rate of temperature change, calculate the temperature at current time
Difference and rate of temperature change；The temperature number of temperature data, temperature difference, rate of temperature change and previous moment to the current time
According to, temperature difference, rate of temperature change carry out data fusion, obtain fusion results, determine
Whether break down.Fault Diagnosis for Electrical Equipment method provided in an embodiment of the present invention, based on temperature data, temperature difference and temperature
Three variables of rate of change carry out data fusion, obtain Fault Diagnosis for Electrical Equipment result, failure feelings that can in real time to power equipment
Condition is diagnosed, and whole process diagnosis speed is fast, and the degree of accuracy of fault diagnosis is high, and rate of false alarm is low, and reduces to a great extent
Redundancy.
Based on identical technology design, also a kind of Fault Diagnosis for Electrical Equipment device of the embodiment of the present invention, referring to Fig. 4, bag
Include：Temperature acquisition module 100, computing module 200 and the fault diagnosis module 300 being sequentially connected.
The temperature acquisition module, treats the temperature data of diagnosing electric power for acquisition in real time.
The computing module, for calculating the temperature difference and rate of temperature change at current time, and obtains the temperature of previous moment
Degrees of data, temperature difference, rate of temperature change.
In specific implementation process, the computing module includes temperature difference computing unit.
The temperature difference computing unit, for by the difference of the temperature data at current time and the temperature data of previous moment,
As the temperature difference at the current time.
The computing module also includes：Curve plotting unit, function calculating unit and rate of temperature change computing unit.
The curve plotting unit, for drawing the time dependent curve of the temperature data；
The function calculating unit, for calculating the time dependent function of temperature data according to the curve；
The rate of temperature change computing unit, for by the function at current time to time derivation, when obtaining current
The rate of temperature change at quarter.
The fault diagnosis module, for the temperature data to the current time, temperature difference, rate of temperature change and previous
The temperature data at moment, temperature difference, rate of temperature change carry out data fusion, obtain fusion results, determine
Whether diagnosing electric power breaks down.
In specific implementation process, the malfunctioning module includes：Modeling unit, training unit, model modification unit and event
Barrier determining unit.
The modeling unit, will occur as three input nodes for using temperature data, temperature difference and rate of temperature change
Failure and do not break down as two output nodes, set up neural network model, wherein, the hidden layer of the neural network model
It is set to eight nodes；
The training unit, for the historical temperature data for treating diagnosing electric power, temperature difference and temperature change
Rate is input into the neural network model as training sample and is trained, and obtains the hidden layer input weights of the neural network model
With output weights, wherein, the historical temperature data, temperature difference and rate of temperature change treat that diagnosing electric power is normally transported for described
Temperature data, temperature difference and rate of temperature change during row；
The model modification unit, for by it is described input weights and output right value update to the neural network model；
The failure determining unit, for by the temperature data at the current time, temperature difference, rate of temperature change and previous
The temperature data at moment, temperature difference, rate of temperature change are input into the neural network model for updating and are instructed as test sample
Practice, obtain the weight for breaking down and the weight not broken down, determine
Raw failure.
In a kind of possible embodiment, described device also includes pretreatment module.
The pretreatment module, for the temperature data to the current time, temperature difference, rate of temperature change and it is previous when
The temperature data at quarter, temperature difference, rate of temperature change carry out pretreatment, remove noise and singular point.
Those skilled in the art will readily occur to its of the present invention after considering description and putting into practice disclosure of the invention here
Its embodiment.The application is intended to any modification of the present invention, purposes or adaptations, these modifications, purposes or
Person's adaptations follow the general principle of the present invention and including the undocumented common knowledge in the art of the present invention
Or conventional techniques.Description and embodiments are considered only as exemplary, and true scope and spirit of the invention are by following
Claim is pointed out.
It should be appreciated that the precision architecture for being described above and being shown in the drawings is the invention is not limited in, and
And various modifications and changes can be being carried out without departing from the scope.The scope of the present invention is limited only by appended claim.
Claims (10)
1. a kind of Fault Diagnosis for Electrical Equipment method, it is characterised in that include：
The temperature data at diagnosing electric power current time is treated in acquisition；
The temperature data of acquisition previous moment, temperature difference, rate of temperature change, calculate the temperature difference and temperature change at current time
Rate；
Temperature data, temperature difference, the temperature data of rate of temperature change and previous moment to the current time, temperature difference, temperature
Degree rate of change carries out data fusion, obtains fusion results, determines.
2. Fault Diagnosis for Electrical Equipment method according to claim 1, it is characterised in that described to the current time
The temperature data of temperature data, temperature difference, rate of temperature change and previous moment, temperature difference, rate of temperature change carry out data fusion
Before, also include：
Temperature data, temperature difference, the temperature data of rate of temperature change and previous moment to the current time, temperature difference, temperature
Degree rate of change carries out pretreatment, removes noise and singular point.
3. Fault Diagnosis for Electrical Equipment method according to claim 1, it is characterised in that the temperature at the calculating current time
Degree difference and rate of temperature change, including：
By the temperature data at current time and the difference of the temperature data of previous moment, as the temperature difference at the current time.
4. Fault Diagnosis for Electrical Equipment method according to claim 1, it is characterised in that the temperature at the calculating current time
Degree difference and rate of temperature change, also include：
Draw the time dependent curve of the temperature data；
The time dependent function of temperature data is calculated according to the curve；
The function is obtained into the rate of temperature change at current time to time derivation at current time.
5. Fault Diagnosis for Electrical Equipment method according to claim 1, it is characterised in that described to the current time
The temperature data of temperature data, temperature difference, rate of temperature change and previous moment, temperature difference, rate of temperature change carry out data fusion,
Fusion results are obtained, is determined, including：
Using temperature data, temperature difference and rate of temperature change as three input nodes, conduct of breaking down and not break down
Two output nodes, set up neural network model, wherein, the hidden layer of the neural network model is set to eight nodes；
It is described as training sample input using the historical temperature data for treating diagnosing electric power, temperature difference and rate of temperature change
Neural network model is trained, and obtains the hidden layer input weights and output weights of the neural network model, wherein, it is described to go through
History temperature data, temperature difference and rate of temperature change are temperature data when diagnosing electric power normally runs, temperature difference
And rate of temperature change；
By the input weights and output right value update to the neural network model；
By the temperature data of the temperature data at the current time, temperature difference, rate of temperature change and previous moment, temperature difference, temperature
Degree rate of change is input into the neural network model for updating and is trained as test sample, obtains the weight that breaks down and not
The weight for breaking down, determines.
6. a kind of Fault Diagnosis for Electrical Equipment device, it is characterised in that include：
Temperature acquisition module, for obtaining the temperature data for treating diagnosing electric power current time；
Computing module, for obtaining the temperature data of previous moment, temperature difference, rate of temperature change, calculates the temperature at current time
Difference and rate of temperature change；
Fault diagnosis module, for the temperature of the temperature data to the current time, temperature difference, rate of temperature change and previous moment
Degrees of data, temperature difference, rate of temperature change carry out data fusion, obtain fusion results, determine follow-up power-off power described in current time
Whether equipment breaks down.
7. Fault Diagnosis for Electrical Equipment device according to claim 6, it is characterised in that also include：
Pretreatment module, for the temperature of the temperature data to the current time, temperature difference, rate of temperature change and previous moment
Data, temperature difference, rate of temperature change carry out pretreatment, remove noise and singular point.
8. Fault Diagnosis for Electrical Equipment device according to claim 6, it is characterised in that the computing module includes：
Temperature difference computing unit, for by the difference of the temperature data at current time and the temperature data of previous moment, as described
The temperature difference at current time.
9. Fault Diagnosis for Electrical Equipment device according to claim 6, it is characterised in that the computing module also includes：
Curve plotting unit, for drawing the time dependent curve of the temperature data；
Function calculating unit, for calculating the time dependent function of temperature data according to the curve；
Rate of temperature change computing unit, for by the function at current time to time derivation, obtain the temperature at current time
Rate of change.
10. Fault Diagnosis for Electrical Equipment device according to claim 6, it is characterised in that the malfunctioning module includes：
Modeling unit, for temperature data, temperature difference and rate of temperature change, as three input nodes, breaking down and not
Break down as two output nodes, set up neural network model, wherein, the hidden layer of the neural network model is set to eight
Node；
Training unit, for using the historical temperature data for treating diagnosing electric power, temperature difference and rate of temperature change as instruction
Practice the sample input neural network model to be trained, obtain the hidden layer input weights and output power of the neural network model
Value, wherein, the historical temperature data, temperature difference and rate of temperature change are temperature when diagnosing electric power normally runs
Degrees of data, temperature difference and rate of temperature change；
Model modification unit, for by it is described input weights and output right value update to the neural network model；
Failure determining unit, for by the temperature of the temperature data at the current time, temperature difference, rate of temperature change and previous moment
Degrees of data, temperature difference, rate of temperature change are input into the neural network model for updating and are trained as test sample, are sent out
The weight and the weight not broken down of raw failure, determines.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611150376.6A CN106679847A (en) | 2016-12-14 | 2016-12-14 | Electric power equipment fault diagnosing method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611150376.6A CN106679847A (en) | 2016-12-14 | 2016-12-14 | Electric power equipment fault diagnosing method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106679847A true CN106679847A (en) | 2017-05-17 |
Family
ID=58869313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611150376.6A Pending CN106679847A (en) | 2016-12-14 | 2016-12-14 | Electric power equipment fault diagnosing method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106679847A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108871616A (en) * | 2018-09-19 | 2018-11-23 | 珠海格力电器股份有限公司 | The recognition methods of motor status and device |
| CN111352003A (en) * | 2020-05-25 | 2020-06-30 | 北京中航科电测控技术股份有限公司 | Analysis system for electrical equipment faults |
| CN111412990A (en) * | 2019-01-04 | 2020-07-14 | 苏州苏彭志盛信息科技有限公司 | Power equipment temperature monitoring system and method |
| CN111831026A (en) * | 2019-04-19 | 2020-10-27 | 宁波奥克斯高科技有限公司 | Oil temperature control method of oil-immersed transformer and transformer using same |
| CN113091949A (en) * | 2021-02-18 | 2021-07-09 | 深圳供电局有限公司 | Cable state detection method, device and equipment |
| CN113379005A (en) * | 2021-08-12 | 2021-09-10 | 新风光电子科技股份有限公司 | Intelligent energy management system and method for power grid power equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104180913A (en) * | 2014-09-17 | 2014-12-03 | 国家电网公司 | Transmission line temperature detection method and device |
| CN104279710A (en) * | 2014-10-08 | 2015-01-14 | 广东美的制冷设备有限公司 | Air conditioner control method, air conditioner control system and air conditioner |
-
2016
- 2016-12-14 CN CN201611150376.6A patent/CN106679847A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104180913A (en) * | 2014-09-17 | 2014-12-03 | 国家电网公司 | Transmission line temperature detection method and device |
| CN104279710A (en) * | 2014-10-08 | 2015-01-14 | 广东美的制冷设备有限公司 | Air conditioner control method, air conditioner control system and air conditioner |
Non-Patent Citations (1)
| Title |
|---|
| 李进 等: "基于多传感器信息融合的电力设备故障诊断方法", 《电子世界》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108871616A (en) * | 2018-09-19 | 2018-11-23 | 珠海格力电器股份有限公司 | The recognition methods of motor status and device |
| CN108871616B (en) * | 2018-09-19 | 2021-07-30 | 珠海格力电器股份有限公司 | Motor state identification method and device |
| CN111412990A (en) * | 2019-01-04 | 2020-07-14 | 苏州苏彭志盛信息科技有限公司 | Power equipment temperature monitoring system and method |
| CN111831026A (en) * | 2019-04-19 | 2020-10-27 | 宁波奥克斯高科技有限公司 | Oil temperature control method of oil-immersed transformer and transformer using same |
| CN111831026B (en) * | 2019-04-19 | 2022-11-04 | 宁波奥克斯高科技有限公司 | Oil temperature control method of oil-immersed transformer and transformer using same |
| CN111352003A (en) * | 2020-05-25 | 2020-06-30 | 北京中航科电测控技术股份有限公司 | Analysis system for electrical equipment faults |
| CN113091949A (en) * | 2021-02-18 | 2021-07-09 | 深圳供电局有限公司 | Cable state detection method, device and equipment |
| CN113379005A (en) * | 2021-08-12 | 2021-09-10 | 新风光电子科技股份有限公司 | Intelligent energy management system and method for power grid power equipment |
| CN113379005B (en) * | 2021-08-12 | 2021-10-29 | 新风光电子科技股份有限公司 | Intelligent energy management system and method for power grid power equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106679847A (en) | Electric power equipment fault diagnosing method and apparatus | |
| CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
| CN108051211B (en) | A kind of wind generator set main shaft holds temperature pre-warning diagnostic method | |
| CN106872657B (en) | A kind of multivariable water quality parameter time series data accident detection method | |
| CN108584592B (en) | A kind of shock of elevator car abnormity early warning method based on time series predicting model | |
| CN108255649B (en) | Diagnosis strategy design method based on modeling simulation cooperative analysis | |
| CN103499921B (en) | Structure changes fuzzy system sensor fault diagnosis method | |
| CN103983453B (en) | A kind of executing agency of aero-engine and the differentiating method of sensor fault diagnosis | |
| CN106006344B (en) | Staircase On-line Fault early warning system and method for diagnosing faults | |
| CN104504248B (en) | A kind of fault diagnosis modeling method analyzed based on design data | |
| CN103901882A (en) | Online monitoring fault diagnosis system and method of train power system | |
| CN106444489A (en) | Monitoring device based on digital monitoring heavy equipment engine and monitoring method thereof | |
| CN103678881B (en) | Composite fault diagnosis method based on combination of artificial immunity and evidence theory | |
| CN104615121B (en) | A kind of train fault diagnostic method and system | |
| CN108614539A (en) | AEF airborne equipment failure diagnosis and prediction model verification method | |
| CN107462425A (en) | The failure prediction method and failure predication platform of a kind of car kits system | |
| CN106707221A (en) | Fault diagnosis method and system for sensor in electric energy metering device | |
| CN104808653A (en) | Motor servo system additivity fault detection and fault tolerant control method based on slip form | |
| CN108427400A (en) | A kind of aircraft airspeed pipe method for diagnosing faults based on neural network Analysis design | |
| CN108830335A (en) | Photovoltaic plant fault early warning method and system | |
| CN107656518A (en) | A kind of system failure inference method | |
| CN108039987A (en) | Critical infrastructures fragility assessment method based on multi-layer-coupled relational network | |
| CN107036808A (en) | Gearbox of wind turbine combined failure diagnostic method based on SVMs probability Estimation | |
| CN108377209A (en) | Equipment fault detecting system based on SCADA and detection method | |
| Yan et al. | Reliability prediction of CNC machine tool spindle based on optimized cascade feedforward neural network |
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 |
Application publication date: 20170517 |
|
| RJ01 | Rejection of invention patent application after publication |