CN110318953A - Temperature monitoring method and device for wind turbine generator electric control system - Google Patents
Temperature monitoring method and device for wind turbine generator electric control system Download PDFInfo
- Publication number
- CN110318953A CN110318953A CN201810296326.1A CN201810296326A CN110318953A CN 110318953 A CN110318953 A CN 110318953A CN 201810296326 A CN201810296326 A CN 201810296326A CN 110318953 A CN110318953 A CN 110318953A
- Authority
- CN
- China
- Prior art keywords
- thermograph
- temperature
- parts
- temperature monitoring
- control system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000009826 distribution Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 238000003475 lamination Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims 1
- 238000001931 thermography Methods 0.000 abstract description 28
- 238000012360 testing method Methods 0.000 description 9
- 238000009434 installation Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000009529 body temperature measurement Methods 0.000 description 4
- 230000005611 electricity Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000012827 research and development Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004040 coloring Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Wind Motors (AREA)
Abstract
The invention provides a temperature monitoring method and equipment for an electric control system of a wind turbine generator, wherein the temperature monitoring method comprises the following steps: acquiring a thermal imaging graph of the electronic control system; determining the positions of all components in the electronic control system in the thermal imaging graph according to a pre-established component recognition model; and determining the temperature of each part according to the position of each part in the thermal imaging graph and the thermal imaging graph. According to the temperature monitoring method and the temperature monitoring equipment for the wind turbine generator electric control system, the temperature of each part can be determined only by installing the thermal imaging camera for shooting the thermal imaging picture of the electric control system and automatically determining the position of each part in the thermal imaging picture through the part recognition model.
Description
Technical field
The present invention relates to the field of equipment monitoring of wind-power electricity generation, more particularly, are related to the temperature of Wind turbines electric-control system
Spend monitoring method and equipment.
Background technique
With the fast development of wind generating technology, the installed capacity of separate unit Wind turbines is also increased with it, but wind turbine
The inner space of group has limitation.In order to preferably verify the energy density of electrical equipment, space is maximally utilized to radiate,
Guarantee that sufficient maintenance space and escape route, Wind turbines electric-control system would generally be by the pacts of overall design space requirement
Beam, therefore, the energy density that electric-control system is effectively measured by heat test, which becomes, increases in the industry unit area unit capacity
Main direction of studying.
It is directed to the heat test of Wind turbines electric-control system at present, mainly takes to tested in Wind turbines electric-control system
The mode of temperature sensor is arranged to measure the temperature of all parts in the surface or inside of component, and each temperature sensor requires
Outconnector is transferred to data acquisition equipment to data acquisition equipment, by the temperature data of acquisition.And it is directed to Wind turbines
Each unit under test mounting temperature sensor in electric-control system needs two workers fixed temperature sensor and to carry out exhausted one by one
The work such as edge protection, need higher cost of labor.For example, for the filtering inside the current transformer in Wind turbines electric-control system
Capacitor needs that temperature sensor is fixed on filter condenser surface using band, to measure the temperature of filter condenser.
Summary of the invention
The purpose of the present invention is to provide the temperature monitoring methods and equipment of a kind of Wind turbines electric-control system, existing to solve
Some thermal test methods implement problem complicated and with high labor costs.
The present invention provides a kind of temperature monitoring method of Wind turbines electric-control system, and the temperature monitoring method includes: to obtain
Take the thermograph of the electric-control system；Each portion in the electric-control system is determined according to the component identification model pre-established
Position of the part in the thermograph；It is true according to position of all parts in the thermograph and the thermograph
Determine the temperature of all parts.
Optionally, determine all parts in the electric-control system in the heat according to the component identification model pre-established
Position in image includes: that the thermograph is inputted in the component identification model pre-established, exports the automatically controlled system
Position of all parts in the thermograph in system, wherein the component identification model includes convolutional layer and full connection
Layer, convolutional layer are used to extract the characteristics of image of the thermograph, and full articulamentum is each in the thermograph for predicting
The image of position belongs to the probability of all parts.
Optionally, the component identification model is obtained according to the training of the history thermograph of predetermined quantity, wherein described pre-
The history thermograph of fixed number amount includes the history image of multiple Wind turbines electric-control systems for containing all parts,
The position of all parts is identified in each history thermograph.
Optionally, the temperature monitoring method further include: by the maximum temperature threshold of the temperature of all parts and all parts
Value compares, and carries out temperature anomaly alarm for the component beyond maximum temperature threshold.
Optionally, the temperature monitoring method further include: component names and the component that will exceed maximum temperature threshold are super
The time of big temperature threshold is recorded out.
Optionally, the temperature monitoring method further include: temperature of the record all parts in different moments, and according to each
Temperature of the component in different moments draws the temperature changing curve diagram of all parts.
Optionally, all parts include all parts in the thermograph in the position in the thermograph
The region covered, wherein the temperature monitoring method further include: covered in the thermograph according to all parts
Region and the thermograph determine the temperature of each point in the corresponding region of all parts, according to all parts pair
The temperature of each point in the region answered draws the face temperature distribution map of all parts.
Another aspect of the present invention provides a kind of temperature monitoring apparatus of Wind turbines electric-control system, and the monitoring temperature is set
Standby includes: acquiring unit, for obtaining the thermograph of the electric-control system；Position determination unit is pre-established for basis
Component identification model determine position of all parts in the thermograph in the electric-control system；Temperature determines single
Member, for determining the temperature of all parts according to position of all parts in the thermograph and the thermograph.
Optionally, the position determination unit be specifically used for inputted in the component identification model pre-established it is described heat at
As figure, position of all parts in the thermograph in the electric-control system is exported by the component identification model,
Wherein, the component identification model includes convolutional layer and full articulamentum, and the image that convolutional layer is used to extract the thermograph is special
Sign, full articulamentum are used to predict the probability that the image of each position in the thermograph belongs to all parts.
Optionally, the component identification model is obtained according to the training of the history thermograph of predetermined quantity, wherein described pre-
The history thermograph of fixed number amount includes the history image of multiple Wind turbines electric-control systems for containing all parts,
The position of all parts is identified in each history thermograph.
Optionally, the temperature monitoring apparatus further include: Alarm Unit, for by the temperature and all parts of all parts
Maximum temperature threshold compare, for beyond maximum temperature threshold component carry out temperature anomaly alarm.
Optionally, the temperature monitoring apparatus further include: recording unit, for will exceed the name of parts of maximum temperature threshold
Claim and component is recorded beyond the time of big temperature threshold.
Optionally, the temperature monitoring apparatus further include: drawing unit, for recording all parts in the temperature of different moments
Degree, and the temperature according to all parts in different moments draws the temperature changing curve diagram of all parts.
Optionally, all parts include all parts in the thermograph in the position in the thermograph
The region covered, wherein the temperature monitoring apparatus further include: drawing unit, for according to all parts it is described heat at
The temperature of each point in the corresponding region of all parts is determined as the region covered in figure and the thermograph,
The face temperature distribution map of all parts is drawn according to the temperature of each point in the corresponding region of all parts.
The temperature monitoring method and equipment of the Wind turbines electric-control system of embodiment according to the present invention, it is only necessary to which installation is used for
The thermal imaging camera of the thermograph of electric-control system is shot, and each portion in thermograph is automatically determined by component identification model
The position of part can determine the temperature of all parts, compared with prior art, greatly reduce human cost, reduce survey
The point arrangement time, implement simpler and efficient.
Part in following description is illustrated into the other aspect and/or advantage of the present invention, some is by retouching
Stating will be apparent, or can learn by implementation of the invention.
Detailed description of the invention
By the detailed description carried out below in conjunction with the accompanying drawings, above and other objects of the present invention, features and advantages will
It becomes more fully apparent, in which:
Fig. 1 is the flow chart for showing the temperature monitoring method of Wind turbines electric-control system of embodiment according to the present invention；
Fig. 2 is the block diagram for showing the temperature monitoring apparatus of Wind turbines electric-control system of embodiment according to the present invention；
Fig. 3 is the connection exemplary diagram for showing the thermal imaging camera and other component of embodiment according to the present invention.
Specific embodiment
Detailed description of the present invention embodiment with reference to the accompanying drawings.
Fig. 1 is the flow chart for showing the temperature monitoring method of Wind turbines electric-control system of embodiment according to the present invention.
The temperature monitoring method of the Wind turbines electric-control system of embodiment according to the present invention, can be used in Wind turbines electric-control system
The temperature of all parts in electric-control system is monitored during heat test.
In step S10, the thermograph of Wind turbines electric-control system is obtained.
Here, can from the cabin for being mounted on Wind turbines unobstructed position thermal imaging camera come obtain the heat at
As figure.The installation site of the thermal imaging camera also needs to meet the following conditions: the coverage of thermal imaging camera being made to cover electricity
In control system tested temperature in need component.
The basic principle of thermal imaging detection technique is analyzed by the way that the infrared external reflection light intensity to measured object is weak, according to pre-
The graph coloring scale bar first set shows thermograph, and the image of different location embodies the corresponding positions of measured object in thermograph
The temperature information set.
In step S20, determine all parts in electric-control system in thermal imaging according to the component identification model pre-established
Position in figure.
Above-mentioned all parts refer to the component that tested amount temperature is needed in electric-control system.
Component identification model includes the recognition rule for identifying above-mentioned all parts in thermograph.Can pass through by
The thermograph of acquisition is input in component identification model, and component identification model will export position of all parts in thermograph
It sets.Here, position of all parts in thermograph can quickly and accurately be determined by the component identification model pre-established
Set, in the prior art manually come by way of identifying position of all parts in thermograph compared with, the present invention is real
The temperature monitoring method for applying the Wind turbines electric-control system of example offer, which realizes, automatically determines position, more efficiently.
The position can be represented as a little or region.It is covered in thermograph for example, the position can be all parts
The region of lid.In order to simplify calculating process, which can be considered as having well-regulated shape, such as can be considered as rectangle.
In the case where the region is considered as rectangle, the region can by the height and width of the coordinate of the central point of rectangle and rectangle come
It indicates.For another example, the position can also be in region that all parts are covered in thermograph a bit, preferably centered on
Point.
As an example, above-mentioned component identification model includes convolutional layer and full articulamentum.Convolutional layer is for extracting thermal imaging
The characteristics of image of figure.Full articulamentum is used to predict the probability that the image of each position in thermograph belongs to all parts.Volume
Lamination and full articulamentum may each be at least one, wherein convolutional layer can extract the characteristics of image of thermograph by convolution, entirely
Articulamentum can belong to the probability of all parts using the image of each position in existing forecast of regression model thermograph,
This will not be repeated here.
Above-mentioned component identification model is obtained according to the training of the history thermograph of predetermined quantity.For trained every
The position of above-mentioned all parts and the mark of all parts are identified in a history thermograph.It is above-mentioned to make a reservation for for training
The history thermograph of quantity includes the history image of multiple Wind turbines electric-control systems for containing above-mentioned all parts.On
Stating multiple Wind turbines electric-control systems for containing above-mentioned all parts can be different the electric-control system of Wind turbines, thus
All parts in the thermograph for the electric-control system that above-mentioned component identification model may be used to determine different Wind turbines
Position.
It can pass through using the history thermograph of the position for identifying above-mentioned all parts of predetermined quantity as learning sample
Deep learning algorithm obtains the recognition rule for identifying above-mentioned all parts in thermograph, to obtain above-mentioned component
Identification model.
It is appreciated that the installation site and shooting angle in the thermal imaging camera for shooting thermograph do not change
In the case where, i.e., in the thermograph that obtains in step slo in the indeclinable situation in position of all parts, for it is different when
Between the thermograph that shoots, it is only necessary to the position of all parts in the thermograph obtained at first is carried out in step S20 true
It is fixed, the position phase of the position of each component in the thermograph obtained later and all parts in the thermograph obtained at first
Together, without determining again.
In step S30, the temperature of all parts is determined according to position of all parts in thermograph and thermograph
Degree.Since the image of different location in thermograph can embody the temperature of the corresponding object in the position, for any one
Component can find the corresponding image in the position, according to the position according to position of the component in thermograph in thermograph
It sets corresponding image i.e. and can determine the temperature of the component.
In the case where being represented as a little in the position, using the corresponding temperature of point as the temperature of component.
In the case where being represented as the region that each component is covered in thermograph in the position, all parts can be existed
The temperature of any one of region covered in thermograph point or the corresponding temperature of predetermined point as component.The predetermined point
It can be the highest point of temperature in all the points in the region that component is covered in thermograph or central point.
In a preferred embodiment, position of all parts in thermograph includes all parts in thermograph
Middle covered region, temperature monitoring method further include: the region covered in thermograph according to all parts and heat
Image determines the temperature of each point in the corresponding region of all parts, according to each point in the corresponding region of all parts
Temperature draw all parts face temperature distribution map.Component can be embodied in the face temperature distribution map in thermograph
The temperature of the different location in region covered, the temperature on different location that component can be embodied in certain degree.?
That is in this embodiment, the existing temperature measurement to component can be optimized for " face " measurement by spot measurement, increased
The temperature measurement range of each component allows the temperature characterisitic of component to show more comprehensive, can provide for heat test more fully warm
Degree evidence.In addition, the face temperature distribution map can be used for verifying the simulation result of the thermal design of new research and development component, heat will be emulated
The face temperature distribution map of distribution map and the new research and development component during heat test compares, and can give design optimization provider
To.
In another preferred embodiment, temperature monitoring method further include: by the temperature and all parts of all parts
Maximum temperature threshold compare, for beyond maximum temperature threshold component carry out temperature anomaly alarm.It can be achieved in this way
The temperature anomaly on-line alarm of each component of electric-control system.In addition, in order to facilitate the subsequent calling to abnormal conditions data, temperature
Monitoring method may also include that the component names that will exceed maximum temperature threshold and component are carried out beyond the time of big temperature threshold
Record.
In an additional preferred embodiment, temperature monitoring method may also include that record all parts in the temperature of different moments
Degree, and the temperature according to all parts in different moments draws the temperature changing curve diagram of all parts.In this way, user can be facilitated
The temperature variations of the component of concern are more intuitively checked.
Above-mentioned thermograph, face temperature distribution map, abnormal conditions data and temperature variation curve is storable in clothes
It is engaged in device, to facilitate user is subsequent to be called to it.
Fig. 2 is the block diagram for showing the temperature monitoring apparatus of Wind turbines electric-control system of embodiment according to the present invention.
The temperature monitoring apparatus of the Wind turbines electric-control system of embodiment according to the present invention includes acquiring unit 10, position
Determination unit 20 and temperature determining unit 30.
Acquiring unit 10 is used to obtain the thermograph of Wind turbines electric-control system.
Here, can from the cabin for being mounted on Wind turbines unobstructed position thermal imaging camera come obtain the heat at
As figure.The installation site of the thermal imaging camera also needs to meet the following conditions: the coverage of thermal imaging camera being made to cover electricity
In control system tested temperature in need component.
The basic principle of thermal imaging detection technique is analyzed by the way that the infrared external reflection light intensity to measured object is weak, according to pre-
The graph coloring scale bar first set shows thermograph, and the image of different location embodies the corresponding positions of measured object in thermograph
The temperature information set.
Position determination unit 20 is used to determine all parts in electric-control system according to the component identification model pre-established
Position in thermograph.
Above-mentioned all parts refer to the component that tested amount temperature is needed in electric-control system.
Component identification model includes the recognition rule for identifying above-mentioned all parts in thermograph.Position determines
The thermograph that unit 20 can will acquire is input in component identification model, will be exported all parts by component identification model and be existed
Position in thermograph.Here, it can quickly and accurately determine all parts in heat by the component identification model pre-established
Position in image, and in the prior art manually come phase by way of identifying position of all parts in thermograph
Than the temperature monitoring apparatus of the Wind turbines electric-control system of embodiment according to the present invention, which realizes, automatically determines position, more
It is efficient.
The position can be represented as a little or region.It is covered in thermograph for example, the position can be all parts
The region of lid.In order to simplify calculating process, which can be considered as having well-regulated shape, such as can be considered as rectangle.
In the case where the region is considered as rectangle, the region can by the height and width of the coordinate of the central point of rectangle and rectangle come
It indicates.For another example, the position can also be in region that all parts are covered in thermograph a bit, preferably centered on
Point.
As an example, above-mentioned component identification model includes convolutional layer and full articulamentum.Convolutional layer is for extracting thermal imaging
The characteristics of image of figure.Full articulamentum is used to predict the probability that the image of each position in thermograph belongs to all parts.Volume
Lamination and full articulamentum may each be at least one, wherein convolutional layer can extract the characteristics of image of thermograph by convolution, entirely
Articulamentum can belong to the probability of all parts using the image of each position in existing forecast of regression model thermograph,
This will not be repeated here.
Above-mentioned component identification model is obtained according to the training of the history thermograph of predetermined quantity.For trained every
The position of above-mentioned all parts and the mark of all parts are identified in a history thermograph.The above-mentioned predetermined number for training
The history thermograph of amount includes the history image of multiple Wind turbines electric-control systems for containing above-mentioned all parts.It is above-mentioned
Multiple Wind turbines electric-control systems for containing above-mentioned all parts can be different the electric-control system of Wind turbines, thus on
The component identification model stated may be used to determine all parts in the thermograph of the electric-control system of different Wind turbines
Position.
It can pass through using the history thermograph of the position for identifying above-mentioned all parts of predetermined quantity as learning sample
Deep learning algorithm obtains the recognition rule for identifying above-mentioned all parts in thermograph, to obtain above-mentioned component
Identification model.
It is appreciated that the installation site and shooting angle in the thermal imaging camera for shooting thermograph do not change
In the case where, i.e., in the thermograph that acquiring unit 10 obtains in the indeclinable situation in position of all parts, for difference
The thermograph of time shooting, position determination unit 20 only need to the positions of all parts in the thermograph obtained at first into
It goes and determines, the position of the position of each component in the thermograph obtained later and all parts in the thermograph obtained at first
Set it is identical, without determining again.
Temperature determining unit 30 is used to be determined according to position of all parts in thermograph and thermograph each
The temperature of component.Since the image of different location in thermograph can embody the temperature of the corresponding object in the position, for
Any one component, can find the corresponding image in the position according to position of the component in thermograph in thermograph,
It is the temperature that can determine the component according to the corresponding image in the position.
In the case where being represented as a little in the position, using the corresponding temperature of point as the temperature of component.
In the case where being represented as the region that each component is covered in thermograph in the position, all parts can be existed
The temperature of any one of region covered in thermograph point or the corresponding temperature of predetermined point as component.The predetermined point
It can be the highest point of temperature in all the points in the region that component is covered in thermograph or central point.
In a preferred embodiment, position of all parts in thermograph includes all parts in thermograph
Middle covered region, temperature monitoring apparatus may also include drawing unit (not shown).Drawing unit is according to all parts
The region and thermograph covered in thermograph determines the temperature of each point in the corresponding region of all parts, root
The face temperature distribution map of all parts is drawn according to the temperature of each point in the corresponding region of all parts.In the face temperature
The temperature that the different location in the region that component is covered in thermograph can be embodied in distribution map, can in certain degree
Embody the temperature on the different location of component.That is, in this embodiment, can by the existing temperature measurement to component by
Spot measurement is optimized for " face " measurement, increases the temperature measurement range of each component, the temperature characterisitic of component is allowed to show more
Comprehensively, more fully temperature data can be provided for heat test.In addition, the face temperature distribution map can be used for verifying new research and development component
Thermal design simulation result, the face temperature for emulating the new research and development component during thermal profile and heat test is distributed
Figure compares, and can provide direction to design optimization.
In another preferred embodiment, temperature monitoring apparatus further includes Alarm Unit (not shown).Alarm is single
Member is for comparing the maximum temperature threshold of the temperature of all parts and all parts, for beyond maximum temperature threshold
Component carries out temperature anomaly alarm.The temperature anomaly on-line alarm of each component of electric-control system can be achieved in this way.In addition, for side
Continue the calling to abnormal conditions data after an action of the bowels, temperature monitoring apparatus may also include recording unit (not shown).Recording unit
The time that component names and component for will exceed maximum temperature threshold exceed big temperature threshold is recorded.
In an additional preferred embodiment, drawing unit is also used to record all parts in the temperature of different moments, and root
Temperature according to all parts in different moments draws the temperature changing curve diagram of all parts.In this way, user can be facilitated to concern
The temperature variations of component more intuitively checked.
Above-mentioned thermograph, face temperature distribution map, abnormal conditions data and temperature variation curve is storable in clothes
It is engaged in device, to facilitate user is subsequent to be called to it.
The temperature monitoring method and equipment of the Wind turbines electric-control system of embodiment according to the present invention, it is only necessary to which installation is used for
The thermal imaging camera of the thermograph of electric-control system is shot, and each portion in thermograph is automatically determined by component identification model
The position of part can determine the temperature of all parts, compared with prior art, greatly reduce human cost, reduce survey
The point arrangement time, implement simpler and efficient.
Embodiment according to the present invention also provides a kind of computer readable storage medium.The computer readable storage medium is deposited
Contain the temperature monitoring method for making processor execute Wind turbines electric-control system as described above when being executed by a processor
Computer program.
Embodiment according to the present invention also provides a kind of computing device.The computing device includes processor and memory.It deposits
Reservoir is for storing program instruction.The program instruction is executed by processor so that processor executes Wind turbines electricity as described above
The computer program of the temperature monitoring method of control system.
The computing device can be the various calculating equipment with data-handling capacity.Such as the computing device can be work
Industry controls computer (alternatively referred to as host computer).
Above-mentioned thermal imaging camera can directly carry out data transmission between host computer, can also pass through data relay module
Carry out data transmission between host computer.In order to reduce the setting up time of heat test, thermal imaging camera can be connect by pluggable
Head is attached with host computer or data relay module.
Fig. 3 is the connection exemplary diagram for showing the thermal imaging camera and other component of embodiment according to the present invention.
As shown in figure 3, thermal imaging camera 101 is used to shoot the thermograph of electric-control system 102, thermal imaging camera
101 are connect by pluggable connector 103 with data relay module 104, and data relay module 104 is connect with host computer 105.It can insert
Pulling out the line between connector 103 and data relay module 104 can be used the stronger transmission line of function of shielding.
In addition, each program mould in the temperature monitoring apparatus of the Wind turbines electric-control system of embodiment according to the present invention
Block can be realized by hardware completely, such as field programmable gate array or specific integrated circuit；It can also be by hardware and software phase
In conjunction with mode realize；It can also be realized completely by computer program with software mode.
Although being particularly shown and describing the present invention, those skilled in the art referring to its exemplary embodiment
It should be understood that in the case where not departing from the spirit and scope of the present invention defined by claim form can be carried out to it
With the various changes in details.
Claims (16)
1. a kind of temperature monitoring method of Wind turbines electric-control system, which is characterized in that the temperature monitoring method includes:
Obtain the thermograph of the electric-control system；
Determine all parts in the electric-control system in the thermograph according to the component identification model pre-established
Position；
The temperature of all parts is determined according to position of all parts in the thermograph and the thermograph.
2. temperature monitoring method according to claim 1, which is characterized in that true according to the component identification model pre-established
Position of all parts in the thermograph in the fixed electric-control system includes: in the component identification model pre-established
The middle input thermograph, exports position of all parts in the thermograph in the electric-control system, wherein institute
Stating component identification model includes convolutional layer and full articulamentum, and convolutional layer is used to extract the characteristics of image of the thermograph, Quan Lian
Layer is connect for predicting that the image of each position in the thermograph belongs to the probability of all parts.
3. temperature monitoring method according to claim 1, which is characterized in that the component identification model is according to predetermined quantity
History thermograph training obtain, wherein the history thermograph of the predetermined quantity include it is multiple contain it is described each
The history image of the Wind turbines electric-control system of component identifies the position of all parts in each history thermograph
It sets.
4. temperature monitoring method according to claim 1, which is characterized in that the temperature monitoring method further include: will be each
The temperature of a component and the maximum temperature threshold of all parts compare, and carry out temperature for the component beyond maximum temperature threshold
Spend abnormality alarming.
5. temperature monitoring method according to claim 4, which is characterized in that the temperature monitoring method further include: will surpass
The component names and component of maximum temperature threshold are recorded beyond the time of big temperature threshold out.
6. temperature monitoring method according to claim 1, which is characterized in that the temperature monitoring method further include: record
Temperature of all parts in different moments, and the temperature according to all parts in different moments draws the temperature change of all parts
Curve graph.
7. temperature monitoring method according to claim 1, which is characterized in that all parts are in the thermograph
Position include region that all parts are covered in the thermograph,
Wherein, the temperature monitoring method further include: the region that is covered in the thermograph according to all parts and
The thermograph determines the temperature of each point in the corresponding region of all parts, according to the corresponding region of all parts
In each point temperature draw all parts face temperature distribution map.
8. a kind of temperature monitoring apparatus of Wind turbines electric-control system, which is characterized in that the temperature monitoring apparatus includes:
Acquiring unit, for obtaining the thermograph of the electric-control system；
Position determination unit, for determining that all parts in the electric-control system exist according to the component identification model pre-established
Position in the thermograph；
Temperature determining unit, it is each for being determined according to position of all parts in the thermograph and the thermograph
The temperature of a component.
9. temperature monitoring apparatus according to claim 8, which is characterized in that the position determination unit is specifically used for pre-
The thermograph is inputted in the component identification model first established, is exported in the electric-control system by the component identification model
Position of all parts in the thermograph, wherein the component identification model includes convolutional layer and full articulamentum, volume
Lamination is used to extract the characteristics of image of the thermograph, and full articulamentum is used to predict each position in the thermograph
Image belongs to the probability of all parts.
10. temperature monitoring apparatus according to claim 8, which is characterized in that the component identification model is according to predetermined number
The history thermograph training of amount obtains, wherein the history thermograph of the predetermined quantity include it is multiple contain it is described each
The history image of the Wind turbines electric-control system of a component identifies the position of all parts in each history thermograph
It sets.
11. temperature monitoring apparatus according to claim 8, which is characterized in that the temperature monitoring apparatus further include: alarm
Unit, for comparing the maximum temperature threshold of the temperature of all parts and all parts, for beyond maximum temperature threshold
The component of value carries out temperature anomaly alarm.
12. temperature monitoring apparatus according to claim 11, which is characterized in that the temperature monitoring apparatus further include: note
Unit is recorded, the time that the component names and component for will exceed maximum temperature threshold exceed big temperature threshold is recorded.
13. temperature monitoring apparatus according to claim 8, which is characterized in that the temperature monitoring apparatus further include: draw
Unit, for recording all parts in the temperature of different moments, and it is each in the temperature drafting of different moments according to all parts
The temperature changing curve diagram of component.
14. temperature monitoring apparatus according to claim 8, which is characterized in that all parts are in the thermograph
In position include region that all parts are covered in the thermograph,
Wherein, the temperature monitoring apparatus further include: drawing unit, for being covered in the thermograph according to all parts
The region of lid and the thermograph determine the temperature of each point in the corresponding region of all parts, according to each portion
The temperature of each point in the corresponding region of part draws the face temperature distribution map of all parts.
15. a kind of computer readable storage medium is stored with and processor is made to execute such as claim 1 when being executed by a processor
To the computer program of the temperature monitoring method of Wind turbines electric-control system described in any one of 7.
16. a kind of computing device, comprising:
Processor；
Memory is executed by processor for storing to work as so that processor executes as claimed in any of claims 1 to 7 in one of claims
The computer program of the temperature monitoring method of Wind turbines electric-control system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810296326.1A CN110318953B (en) | 2018-03-30 | 2018-03-30 | Temperature monitoring method and device for wind turbine generator electric control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810296326.1A CN110318953B (en) | 2018-03-30 | 2018-03-30 | Temperature monitoring method and device for wind turbine generator electric control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110318953A true CN110318953A (en) | 2019-10-11 |
| CN110318953B CN110318953B (en) | 2021-01-26 |
Family
ID=68112440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810296326.1A Active CN110318953B (en) | 2018-03-30 | 2018-03-30 | Temperature monitoring method and device for wind turbine generator electric control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110318953B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110969813A (en) * | 2019-12-24 | 2020-04-07 | 上海申瑞继保电气有限公司 | Railway substation unattended monitoring method based on edge calculation |
| CN113464387A (en) * | 2021-06-25 | 2021-10-01 | 广州市力瑞电气机械有限公司 | Water cooling control method for wind power generation, computer equipment and storage medium thereof |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567983A (en) * | 2010-12-26 | 2012-07-11 | 浙江大立科技股份有限公司 | Determining method for positions of monitored targets in instant infrared chart and application |
| CN103168467A (en) * | 2010-08-16 | 2013-06-19 | 韩国标准科学研究院 | Security camera tracking and monitoring system and method using thermal image coordinates |
| CN103234753A (en) * | 2013-04-11 | 2013-08-07 | 华北电力大学 | Gaussian process modeling based wind turbine shafting state monitoring method |
| CN103901072A (en) * | 2014-04-21 | 2014-07-02 | 国网安徽省电力公司淮南供电公司 | Method for diagnosing equipment overheating defects by utilizing infrared spectrum analysis |
| US20150043769A1 (en) * | 2013-03-15 | 2015-02-12 | Digital Wind Systems, Inc. | Method and apparatus for remote feature measurement in distorted images |
| CN107024506A (en) * | 2017-03-09 | 2017-08-08 | 深圳市朗驰欣创科技股份有限公司 | A kind of pyrogenicity defect inspection method and system |
| CN107103598A (en) * | 2017-03-28 | 2017-08-29 | 国网上海市电力公司 | A kind of power cable thermal fault detection method based on infrared image clustering processing |
| CN107271044A (en) * | 2017-05-03 | 2017-10-20 | 北京海顿中科技术有限公司 | A kind of thermal imaging device for detecting temperature and method |
| CN107290062A (en) * | 2017-06-16 | 2017-10-24 | 国网江苏省电力公司检修分公司 | A kind of power transmission and transformation equipment state analysis method based on Infrared Thermogram |
| CN107466263A (en) * | 2017-07-10 | 2017-12-12 | 深圳市艾唯尔科技有限公司 | A kind of joint of robot anticollision protection system and its method for sensing integration technology |
| CN107607207A (en) * | 2017-08-22 | 2018-01-19 | 中国科学院深圳先进技术研究院 | A kind of power equipment thermal fault detection method, system and electronic equipment |
-
2018
- 2018-03-30 CN CN201810296326.1A patent/CN110318953B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103168467A (en) * | 2010-08-16 | 2013-06-19 | 韩国标准科学研究院 | Security camera tracking and monitoring system and method using thermal image coordinates |
| CN102567983A (en) * | 2010-12-26 | 2012-07-11 | 浙江大立科技股份有限公司 | Determining method for positions of monitored targets in instant infrared chart and application |
| US20150043769A1 (en) * | 2013-03-15 | 2015-02-12 | Digital Wind Systems, Inc. | Method and apparatus for remote feature measurement in distorted images |
| CN103234753A (en) * | 2013-04-11 | 2013-08-07 | 华北电力大学 | Gaussian process modeling based wind turbine shafting state monitoring method |
| CN103901072A (en) * | 2014-04-21 | 2014-07-02 | 国网安徽省电力公司淮南供电公司 | Method for diagnosing equipment overheating defects by utilizing infrared spectrum analysis |
| CN107024506A (en) * | 2017-03-09 | 2017-08-08 | 深圳市朗驰欣创科技股份有限公司 | A kind of pyrogenicity defect inspection method and system |
| CN107103598A (en) * | 2017-03-28 | 2017-08-29 | 国网上海市电力公司 | A kind of power cable thermal fault detection method based on infrared image clustering processing |
| CN107271044A (en) * | 2017-05-03 | 2017-10-20 | 北京海顿中科技术有限公司 | A kind of thermal imaging device for detecting temperature and method |
| CN107290062A (en) * | 2017-06-16 | 2017-10-24 | 国网江苏省电力公司检修分公司 | A kind of power transmission and transformation equipment state analysis method based on Infrared Thermogram |
| CN107466263A (en) * | 2017-07-10 | 2017-12-12 | 深圳市艾唯尔科技有限公司 | A kind of joint of robot anticollision protection system and its method for sensing integration technology |
| CN107607207A (en) * | 2017-08-22 | 2018-01-19 | 中国科学院深圳先进技术研究院 | A kind of power equipment thermal fault detection method, system and electronic equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110969813A (en) * | 2019-12-24 | 2020-04-07 | 上海申瑞继保电气有限公司 | Railway substation unattended monitoring method based on edge calculation |
| CN110969813B (en) * | 2019-12-24 | 2023-06-02 | 上海申瑞继保电气有限公司 | Unmanned monitoring method for railway substation based on edge calculation |
| CN113464387A (en) * | 2021-06-25 | 2021-10-01 | 广州市力瑞电气机械有限公司 | Water cooling control method for wind power generation, computer equipment and storage medium thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110318953B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7183425B2 (en) | Machine learning system and data fusion to optimize deployment conditions for detecting corrosion under insulation | |
| JP5607772B2 (en) | Solar cell panel monitoring program, solar cell panel monitoring device, and solar cell panel monitoring method | |
| CN110567964B (en) | Method and device for detecting defects of power transformation equipment and storage medium | |
| CN108518804A (en) | A kind of machine room humiture environmental forecasting method and system | |
| US10998853B2 (en) | Internet of things-enabled solar photovoltaic health monitoring and advising related thereto | |
| KR102054163B1 (en) | Photovoltaic power generation prediction system and photovoltaic power generation apparatus having the same | |
| CN113056665A (en) | Detection and fault detection of corrosion under fire-resistant insulation using hybrid sensing system | |
| CN113820017A (en) | Generator carbon brush temperature monitoring system based on infrared image and temperature prediction method | |
| CN110318953A (en) | Temperature monitoring method and device for wind turbine generator electric control system | |
| CN117613430B (en) | New energy battery comprehensive test energy management method and system | |
| CN115878992A (en) | Monitoring method and monitoring system for comprehensive pipe rack power supply system | |
| CN111354496A (en) | Nuclear power plant accident online diagnosis and state tracking prediction method | |
| CN117538710A (en) | Intelligent early warning method and system for local dynamic discharge monitoring | |
| Olivatti et al. | Analysis of artificial intelligence techniques applied to thermographic inspection for automatic detection of electrical problems | |
| US20220215138A1 (en) | Method for Validating System Parameters of an Energy System, Method for Operating an Energy System, and Energy Management System for an Energy System | |
| KR20200102649A (en) | Guiding system and managemennt server for production maximization of renewable energy generatiors | |
| KR102635460B1 (en) | Method and apparatus for analyzing abnormal production based on phothovoltaic remote monitoring | |
| Fuhrmann et al. | X-AMINOR: A Mobile Multi-Sensor Platform for Lifecycle-Monitoring of Transformers. | |
| CN117422861A (en) | Method, device, equipment and medium for evaluating risk of maintaining power equipment | |
| CN116910491B (en) | Lightning monitoring and early warning system and method, electronic equipment and storage medium | |
| CN117452148B (en) | Intelligent monitoring method of ring main unit | |
| US20240053287A1 (en) | Probability of detection of lifecycle phases of corrosion under insulation using artificial intelligence and temporal thermography | |
| CN117724933B (en) | Data center communication thermal management detection method and system | |
| CN117670300B (en) | Distributed photovoltaic equipment detection operation and maintenance system and method | |
| KR102574002B1 (en) | Solar power plant inspection system and method using drone |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |