CN109924194A - A kind of scarer and bird repellent method - Google Patents
A kind of scarer and bird repellent method Download PDFInfo
- Publication number
- CN109924194A CN109924194A CN201910193650.5A CN201910193650A CN109924194A CN 109924194 A CN109924194 A CN 109924194A CN 201910193650 A CN201910193650 A CN 201910193650A CN 109924194 A CN109924194 A CN 109924194A
- Authority
- CN
- China
- Prior art keywords
- sound
- module
- bird repellent
- birds
- data processor
- 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
Abstract
The present invention discloses a kind of scarer, and described device includes: data processor, audio playing module and sound acquisition module and/or image capture module, the sound acquisition module, and the ambient sound for treating monitoring region is acquired；Described image acquisition module, the ambient image for treating monitoring region are acquired；The data processor for carrying out birds identification according to the ambient sound and/or the ambient image, and drives the audio playing module to play audio to carry out bird repellent after selecting corresponding bird repellent mode according to the result of birds identification.In addition, the invention also discloses a kind of bird repellent methods.The characteristics of can realizing that the birds to monitoring region carry out specific aim and expel based on scarer of the invention or bird repellent method, while effectively reducing noise pollution, having both energy conservation and environmental protection.
Description
Technical field
The present invention relates to power transmission electric networks to protect field, more particularly to a kind of scarer and bird repellent method.
Background technique
Birds are movable on electric power pylon, generate bird pest tripping fault by three kinds of modes, the first, birds droppings falls in insulation
It can cause flashover on substring；Second, the junk that birds are nested on electric power pylon causes short circuit；The third, the large birds
Body is directly shorted the air gap and generates short circuit.Bird pest failure occurs for transmission line of electricity, can cause to the safe operation of electric system
Serious threat.The Bird-caused Fault of electric system drastically influence power grid safe operation and high pressure overhead power line it is normal
Operation, the economic benefit of the safe and reliable and electric power enterprise of direct relation power grid.In recent years, with the improvement of ecological environment and people
Class protects the raising of birds consciousness, and the population quantity of birds is continuously increased, so that bird trouble on transmission line tripping fault has become
One of major failure form of power grid.Large-scale group bird may be implemented in audio bird dispelling, but existing audio bird dispelling technology lacks
Specific aim can receive good effect using initial stage, reach effectively anti-bird.After long-play, birds are to implementation ring
Border generates adaptability, and then effect on driving birds is caused to decline.On the basis of analyzing the birds act of defense, suitable bird repellent mould is studied
Formula can realize that targeted, the long-time of birds effectively expel, occur for reducing under the premise of protecting birds
The probability of bird pest failure, the security reliability for promoting Operation of Electric Systems have important application value.
It is directed to bird repellent, in the prior art one: a kind of voice bird repellent method comprising following steps: (1) treat bird repellent
Region is investigated, and four seasons of record wait for the type and quantity of bird repellent region birds respectively；(2) according to note in step (1)
The type and quantity of the birds of record, record the cry of more than one natural enemies of each birds respectively, and each natural enemy is named
Sound records several grades according to the size of sound decibel respectively；(3) to bird repellent region for each birds use with
The form that machine sowing is put, according to the cry of the natural enemy of ascending more than one type for playing this kind of birds step by step.Disadvantage 1: it drives
Bird sound plays, and is lack of pertinence；Disadvantage 2: long time period plays bird repellent sound, and energy consumption is high, is not suitable for no electric power
The equipment of system power supply；Disadvantage 3: sound omnidirectional plays, to nontarget area (region for needing to drive away birds is target area)
Generate noise pollution.A kind of prior art two: power transmission line intelligent voice bird-scaring unit application number: 201520817364.9.The party
Method belongs to power grid and protects scarecrow device skill the following steps are included: the utility model relates to a kind of power transmission line intelligent voice bird-scaring unit
Art field.It is made of single-chip microcontroller, solar panels, infrared sensor etc.；Its main feature is that: the high level signal input terminal of single-chip microcontroller
It is connect with the output end of infrared sensor, acoustic control end connection audio amplifier circuit, scintillation light control terminal and light emitting diode are powered
Circuit connection, light emitting diode power supply circuit are connected in parallel two light emitting diode straps；The power source charges control terminal of single-chip microcontroller
It is connect by charge protector with lithium battery charging circuit, the input terminal of lithium battery charging circuit is connect with solar panels.It is single
Piece machine burning enters self-programming program, and realization is irregular at random to play a kind of birds natural enemy sound domestic initiation, avoids birds to list
The adaptability of one audio, efficiency time is long, and effect on driving birds is good.It solves the prior art to have adapted to imitate bird repellent using many years birds
Fruit is poor, disturbing residents because the sound is huge is on the brink of to eliminate, and the problem of involve great expense.Disadvantage 1: bird repellent sound is a kind of natural enemy sound,
It is lack of pertinence；Disadvantage 2: sound omnidirectional plays, and generates to nontarget area (region for needing to drive away birds is target area)
Noise pollution.
In summary, all orientation can not be realized while guaranteeing that generation noise pollution is effectively reduced in the prior art
With targetedly bird repellent.
Summary of the invention
The purpose of the present invention is to provide a kind of scarer and bird repellent methods, to solve to cannot achieve needle in the prior art
The problems such as to property bird repellent.
In order to achieve the above objectives, of the invention to adopt the following technical solutions:
First aspect present invention discloses a kind of scarer, and described device includes: data processor, audio broadcasting mould
Block and sound acquisition module and/or image capture module,
The sound acquisition module, the ambient sound for treating monitoring region are acquired；
Described image acquisition module, the ambient image for treating monitoring region are acquired；
The data processor, for carrying out birds identification, and root according to the ambient sound and/or the ambient image
The audio playing module is driven to play audio to be driven after selecting corresponding bird repellent mode according to the result of birds identification
Bird.
Preferably, described device further include: infrared detection module, fingerprint identification module, for detecting whether there is moving object to enter area to be monitored
Domain, if so, trigger signal then is sent to the data processor,
Wherein, the trigger signal, for triggering sound acquisition module described in the data processor controlled and/or described
Image capture module is acquired.
Preferably, using orientation playing module, the broadcasting for receiving data processor refers to the audio playing module
Audio is played to assigned direction after order.
Preferably, the data processor, for carrying out birds to the ambient sound using the first deep learning network
Identification；Birds identification is carried out to the ambient image using the second deep learning network.
Preferably, the first deep learning network includes:
The time convolution unit of time-domain information extraction is carried out to the ambient sound, maximum pond is carried out to the time-domain information
The maximum pond unit of change, to the information through maximum Chi Huahou carry out processing obtain frequency domain information frequency domain convolution unit, to institute
State frequency domain information handled with obtain two layers of shot and long term memory models LSTM of the temporal aspect between different audios and
The deep neural network DNN that identification obtains birds species is carried out to the ambient sound by the temporal aspect.
Preferably, the data processor further comprises:
Pretreatment unit, for before the ambient sound to be inputted to the time convolution unit to the ambient sound into
Row framing operation, wherein frame length is M and overlapping is not present in each frame sound.
Preferably, the second deep learning network carries out birds species to the ambient image using Resnet18 model
Identification.
Preferably, the bird repellent mode includes: different bird repellent sound, the different bird repellent sound intensitys, different playback periods and difference
The combination of playing interval.
Preferably, the orientation playing module includes: double-side band ultrasonic wave modulation, D class ultrasonic power amplifier and annular
Transducer array.
Preferably, described device further comprises power module, and the power module includes solar panel, battery
And voltage transformation module.
Second aspect of the present invention disclose a kind of bird repellent method the described method includes:
S1, detect whether region to be monitored has moving object entrance by infrared detection module, fingerprint identification module, if so, then to data processing
Device sends trigger signal；
After S2, the data processor receive trigger signal, sound acquisition module and/or image capture module pair are controlled
Region to be monitored is acquired；
S3, when the sound acquisition module acquire ambient sound and/or described image acquisition module acquisition ambient image simultaneously
After being sent to the data processor, the data processor carries out birds identification to collected data, and according to the bird
The result of class identification selects driving audio playing module after corresponding bird repellent mode to play audio to carry out bird repellent.
Beneficial effects of the present invention are as follows:
Technical solution of the present invention: one, the birds species identification based on deep learning: Embedded lightweight nerve net
Network identifies birds, promotes the accuracy rate and efficiency of birds species identification；Two, infrared acquisition and sound detection comprehensive detection bird are utilized
Whether class is close to electric power pylon, then triggers the broadcasting of bird repellent sound, energy saving；Three, the bird repellent mode based on act of defense analysis:
Causing the bird repellent sound of the act of defense has hereditary capacity, ensures that the long-time of scarecrow device is effective；Four, based on audio frequency directional
Bird repellent sound plays: high-intensitive bird repellent sound only results from target area, reduces the noise pollution of nontarget area.
Detailed description of the invention
Specific embodiments of the present invention will be described in further detail with reference to the accompanying drawing.
Fig. 1 shows the schematic diagram of electric power pylon intelligent audio scarer in the present embodiment；
Fig. 2 shows the structural schematic diagrams of the first deep learning network in the present embodiment；
Fig. 3 shows the schematic diagram of the time convolution sum frequency domain convolution process in the present embodiment in the first deep learning network；
Fig. 4 shows the schematic diagram of the orientation playing module of electric power pylon intelligent audio scarer in the present embodiment.
Specific embodiment
In order to illustrate more clearly of the present invention, the present invention is done further below with reference to preferred embodiments and drawings
It is bright.Similar component is indicated in attached drawing with identical appended drawing reference.It will be appreciated by those skilled in the art that institute is specific below
The content of description is illustrative and be not restrictive, and should not be limited the scope of the invention with this.
The invention discloses a kind of scarer, described device includes: data processor, audio playing module and sound
Acquisition module and/or image capture module, the sound acquisition module, the ambient sound for treating monitoring region are adopted
Collection；Described image acquisition module, the ambient image for treating monitoring region are acquired；The data processor is used for root
Birds identification is carried out according to the ambient sound and/or the ambient image, and is selected accordingly according to the result of birds identification
Bird repellent mode after drive the audio playing module to play audio to carry out bird repellent.The device is by data processor controlled sound
The data of acquisition module and/or image capture module carry out data acquisition, to the Data Analysis Services collected, for identification
Birds out select corresponding bird repellent mode, and control audio playing module and carry out bird repellent, so that targetedly bird repellent is realized,
Improve the effect of bird repellent.
In the scarer, further includes: infrared detection module, fingerprint identification module, for detecting whether there is moving object to enter area to be monitored
Domain, if so, then sending trigger signal to the data processor, wherein the trigger signal, for triggering the data processing
Device controls the sound acquisition module and/or described image acquisition module is acquired.It can by adding the infrared detection module, fingerprint identification module
Energy conservation further is carried out to the device.
To further illustrate, the present invention provides a more specifically case study on implementation.
As shown in Figure 1, a kind of electric power pylon intelligent audio scarer in embodiments of the present invention, comprising: infrared detection
Module, sound acquisition module, image capture module, embedded system and orientation playing module, wherein the infrared detection module, fingerprint identification module
It treats monitoring region to be detected, when having detected that moving object enters region to be monitored, can be sent out to the embedded system
Send trigger signal；The embedded system can respond the trigger signal received, can be respectively to the sound collection mould
Block and described image acquisition module send acquisition instructions.The sound acquisition module is adopted in response to the sound of the embedded system
The ambient sound that monitoring region is treated in collection instruction is acquired；Figure of the described image acquisition module in response to the embedded system
As the ambient image that acquisition instructions treat monitoring region is acquired.The ambient sound and ambient image collected is sent to institute
State embedded system.The embedded system carries out birds identifying processing to the ambient sound and the ambient image, and selects
It selects corresponding bird repellent scheme control orientation playing module and carries out bird repellent.The orientation playing module receives the embedded system
Bird repellent sound is played after the play instruction of system.
In the present embodiment, the embedded system is that one kind of heretofore described data processor is preferred, more into one
Step ground, using DSP embedded system.The DSP embedded system is utilized and is trained via the birds sound of marked mistake
The the first deep learning network arrived carries out identifying processing to the ambient sound；The birds image via marked mistake is utilized simultaneously
The second deep learning network being trained carries out identifying processing to the ambient image, has further determined whether that bird leans on
Close and bird type.As Figure 2-3, it is contemplated that between the syllable of chirm have High relevancy, proposition based on environment
Sound (i.e. original audio) carries out the first deep learning network of identifying processing (i.e. based on the bird of chirm to chirm therein
Class species identification model), as shown in Figure 2.
The first deep learning network includes: the time convolution list that time-domain information extraction is carried out to the ambient sound
Member carries out the maximum pond unit in maximum pond to the time-domain information, carries out processing acquisition to the information through maximum Chi Huahou
The frequency domain convolution unit of frequency domain information is handled the frequency domain information to obtain two of the temporal aspect between different audios
It layer shot and long term memory models LSTM and identification is carried out to the ambient sound by the temporal aspect obtains birds species
Deep neural network DNN.
As shown in figure 3, for the time convolution sum frequency domain convolution process in the first deep learning network.When collecting original sound
Frequency signal and after being sent to the DSP embedded system, (is not shown in the figure by pretreatment unit, is the DSP embedded system
In a component units) first carry out pretreatment operation, i.e., first to original audio signal carry out sub-frame processing, wherein frame length be M,
And it is not provided with being overlapped between each frame.It needs for all frames to be sequentially inputted to the birds species based on chirm in identifying processing to know
In other model, the birds species identification model based on chirm passes through time convolution list using each frame signal as input respectively
Member, maximum pond unit and frequency convolution unit.The time convolution kernel of time convolution unit total P, size are N × 1, (immediately
Between the one-dimensional of size of convolution kernel be N, 1) two dimension is, for extracting time-domain information；Time-domain information inputs behind maximum pond
Into frequency domain convolution unit, the size of the frequency domain convolution core of frequency domain convolution unit is 1 × (P-K+1), and (i.e. frequency domain convolution core is big
It is small it is one-dimensional be 1, two dimension be P-K+1).The frequency domain information obtained after frequency domain convolution is handled is output to two layers of shot and long term memory models
In LSTM, to extract the temporal aspect between different input audios, finally realize using deep neural network DNN to birds object
The classification of kind.
In the present embodiment, the birds based on ambient image identify aspect, relatively simple in view of background, therefore the second depth
Learning network can directly adopt the identification that Resnet18 model carries out birds species.(can with other image recognition models into
Row substitution, such as VGG16 etc.).
In the present embodiment, the scarer further comprises the power module for device power supply, the power module
Including solar panel, battery and voltage transformation module.
In the present embodiment, when the DSP embedded system is respectively by sound and image procossing and determining birds
After species, corresponding bird repellent mode is selected according to the type of obtained one or more of birds respectively, and play mould using audio
Block plays the bird repellent of bird repellent sound, it is preferable that plays bird repellent sound using orientation playing module.Bird repellent mode includes: bird repellent sound,
Such as the cry of similar warning, utterance of sad calls sound and natural enemy；The bird repellent sound intensity is sentenced after selecting bird repellent sound according to effect on driving birds
The disconnected sound intensity to bird repellent sound carries out multi-gear adjustment；Playback period presets the duration of every kind of bird repellent sound broadcasting, will need
For the corresponding bird repellent sound shuffle of birds driven；And playing interval, interval is followed when driving to birds
Ring plays.
Bird repellent mode is obtained by the act of defense (escaping, separate etc.) of analysis birds, is stored in advance in the embedded system of DSP
The storage section of system.Therefore this scarer more has specific aim in bird repellent.
In the present embodiment, orientation playing module uses audio frequency directional technology, its working principle is that utilizing two column ultrasonic waves
Signal generates the audible sound with high directivity from demodulation effect in air.The basic composition of the audio frequency directional system of design is such as
Shown in Fig. 4, including following 3 most of: circular transducer array works in the array of the energy converter composition of supersonic range, obtains
Highly directive；Double-side band ultrasonic wave modulation, modulates the audio signal in ultrasonic carrier, modulated signal expression are as follows: y
(t)=[Ac+f(t)]cos(ωct+φc), A in formulacFor carrier amplitude, ωcFor carrier frequency, φcFor carrier phase；D class is super
Acoustical power amplifier amplifies modulated signal, drives energy converter sounding.Bird repellent sound is oriented by transducer array and is played,
So that birds are far from target area.Scarer in the present embodiment is mountable on electric power pylon, will orient playing module pair
Quasi- target area, playing by using orientation nontarget area can be effectively reduced noise pollution, will only be registered in sound set
Structure arrangement is simplified, while the energy consumption in playing process can also be reduced in target area.
Based on above-mentioned scarer, the invention also discloses a kind of bird repellent method the described method includes: S1, by infrared
Detection module detects whether region to be monitored has moving object entrance, if so, then sending trigger signal to data processor；S2,
After the data processor receives trigger signal, controls sound acquisition module and/or image capture module treats monitoring region
It is acquired；S3, when the sound acquisition module acquire ambient sound and/or described image acquisition module acquisition ambient image simultaneously
After being sent to the data processor, the data processor carries out birds identification to collected data, and according to the bird
The result of class identification selects driving audio playing module after corresponding bird repellent mode to play audio to carry out bird repellent.
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention may be used also on the basis of the above description for those of ordinary skill in the art
To make other variations or changes in different ways, all embodiments can not be exhaustive here, it is all to belong to this hair
The obvious changes or variations that bright technical solution is extended out are still in the scope of protection of the present invention.
Claims (10)
1. a kind of scarer, which is characterized in that described device includes: data processor, audio playing module and sound collection
Module and/or image capture module,
The sound acquisition module, the ambient sound for treating monitoring region are acquired；
Described image acquisition module, the ambient image for treating monitoring region are acquired；
The data processor, for carrying out birds identification according to the ambient sound and/or the ambient image, and according to institute
The audio playing module is driven to play audio to carry out bird repellent after stating the corresponding bird repellent mode of result selection of birds identification.
2. scarer according to claim 1, which is characterized in that described device further include: infrared detection module, fingerprint identification module is used for
Detect whether that moving object enters region to be monitored, if so, trigger signal then is sent to the data processor,
Wherein, the trigger signal, for triggering sound acquisition module described in the data processor controlled and/or described image
Acquisition module is acquired.
3. scarer according to claim 1, which is characterized in that the audio playing module plays mould using orientation
Block plays audio to assigned direction after the play instruction for receiving data processor.
4. scarer according to claim 1, which is characterized in that the data processor, for utilizing the first depth
Learning network carries out birds identification to the ambient sound；Birds are carried out to the ambient image using the second deep learning network
Identification.
5. scarer according to claim 4, which is characterized in that the first deep learning network includes:
The time convolution unit of time-domain information extraction is carried out to the ambient sound, maximum pond is carried out to the time-domain information
Maximum pond unit, to the information through maximum Chi Huahou carry out processing obtain frequency domain information frequency domain convolution unit, to the frequency
Domain information handled with obtain two layers of shot and long term memory models LSTM of the temporal aspect between different audios and
The deep neural network DNN that identification obtains birds species is carried out to the ambient sound by the temporal aspect.
6. scarer according to claim 5, which is characterized in that the data processor further comprises:
Pretreatment unit, for dividing before the ambient sound is inputted the time convolution unit the ambient sound
Frame operation, wherein frame length is M and overlapping is not present in each frame sound.
7. scarer according to claim 4, which is characterized in that the second deep learning network uses Resnet18
Model carries out the identification of birds species to the ambient image.
8. scarer according to claim 1, which is characterized in that the bird repellent mode includes: different bird repellent sound, no
With the combination of the bird repellent sound intensity, different playback periods and different playing intervals.
9. scarer according to claim 1, which is characterized in that the orientation playing module includes: double-side band ultrasound
Wave modulation, D class ultrasonic power amplifier and circular transducer array.
10. a kind of bird repellent method, which is characterized in that the described method includes:
S1, detect whether region to be monitored has moving object entrance by infrared detection module, fingerprint identification module, if so, then sending out to data processor
Send trigger signal；
After S2, the data processor receive trigger signal, controls sound acquisition module and/or image capture module treats prison
Region is surveyed to be acquired；
S3, ambient sound is acquired and/or the acquisition of described image acquisition module and is sent ambient image when the sound acquisition module
After the data processor, the data processor carries out birds identification to collected data, and is known according to the birds
Other result selects driving audio playing module after corresponding bird repellent mode to play audio to carry out bird repellent.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910193650.5A CN109924194A (en) | 2019-03-14 | 2019-03-14 | A kind of scarer and bird repellent method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910193650.5A CN109924194A (en) | 2019-03-14 | 2019-03-14 | A kind of scarer and bird repellent method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109924194A true CN109924194A (en) | 2019-06-25 |
Family
ID=66987200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910193650.5A Pending CN109924194A (en) | 2019-03-14 | 2019-03-14 | A kind of scarer and bird repellent method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109924194A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110301427A (en) * | 2019-07-15 | 2019-10-08 | 国网宁夏电力有限公司石嘴山市红果子供电公司 | A kind of production method of intelligent multifunctional bird-scaring unit |
| CN110367239A (en) * | 2019-08-26 | 2019-10-25 | 华北电力大学（保定） | A kind of bird trouble on transmission line control method based on Internet of Things |
| CN110555460A (en) * | 2019-07-31 | 2019-12-10 | 国网江苏省电力有限公司 | Image slice-based bird detection method for power transmission line at mobile terminal |
| CN111191559A (en) * | 2019-12-25 | 2020-05-22 | 国网浙江省电力有限公司泰顺县供电公司 | Overhead line early warning system obstacle identification method based on time convolution neural network |
| CN111972394A (en) * | 2020-06-11 | 2020-11-24 | 广东电网有限责任公司 | DQN-based selection method for optimal frequency of ultrasonic bird repelling |
| CN112273366A (en) * | 2020-10-28 | 2021-01-29 | 玉林市农业科学院(广西农业科学院玉林分院) | Method and system for ecologically repelling birds by agricultural unmanned aerial vehicle in rice direct seeding cultivation |
| CN112335647A (en) * | 2020-10-14 | 2021-02-09 | 深圳供电局有限公司 | Ultrasonic bird repelling method and device, bird repeller and storage medium |
| CN112931482A (en) * | 2021-01-15 | 2021-06-11 | 国网山西省电力公司晋城供电公司 | Shaft tower drives bird ware |
| CN114027288A (en) * | 2020-12-29 | 2022-02-11 | 深圳国金电力新能设计院有限公司 | Multi-information-source comprehensive processing bird protection device and method based on wind power plant |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105145539A (en) * | 2015-08-21 | 2015-12-16 | 电子科技大学 | Acousto-optic bird repellent device |
| CN107969417A (en) * | 2017-12-16 | 2018-05-01 | 佛山市神风航空科技有限公司 | A kind of bird-repeller system |
| CN108509976A (en) * | 2018-02-12 | 2018-09-07 | 北京佳格天地科技有限公司 | The identification device and method of animal |
-
2019
- 2019-03-14 CN CN201910193650.5A patent/CN109924194A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105145539A (en) * | 2015-08-21 | 2015-12-16 | 电子科技大学 | Acousto-optic bird repellent device |
| CN107969417A (en) * | 2017-12-16 | 2018-05-01 | 佛山市神风航空科技有限公司 | A kind of bird-repeller system |
| CN108509976A (en) * | 2018-02-12 | 2018-09-07 | 北京佳格天地科技有限公司 | The identification device and method of animal |
Non-Patent Citations (2)
| Title |
|---|
| 李明等: ""基于PReLU的DNN-LSTM混合神经网络在语音识别中的研究"", 《福建茶叶》 * |
| 黄孝平: "《当代机器深度学习方法与应用研究》", 30 November 2017, 电子科技大学出版社 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110301427A (en) * | 2019-07-15 | 2019-10-08 | 国网宁夏电力有限公司石嘴山市红果子供电公司 | A kind of production method of intelligent multifunctional bird-scaring unit |
| CN110555460A (en) * | 2019-07-31 | 2019-12-10 | 国网江苏省电力有限公司 | Image slice-based bird detection method for power transmission line at mobile terminal |
| CN110367239A (en) * | 2019-08-26 | 2019-10-25 | 华北电力大学（保定） | A kind of bird trouble on transmission line control method based on Internet of Things |
| CN111191559A (en) * | 2019-12-25 | 2020-05-22 | 国网浙江省电力有限公司泰顺县供电公司 | Overhead line early warning system obstacle identification method based on time convolution neural network |
| CN111191559B (en) * | 2019-12-25 | 2023-07-11 | 国网浙江省电力有限公司泰顺县供电公司 | Overhead line early warning system obstacle recognition method based on time convolution neural network |
| CN111972394A (en) * | 2020-06-11 | 2020-11-24 | 广东电网有限责任公司 | DQN-based selection method for optimal frequency of ultrasonic bird repelling |
| CN112335647A (en) * | 2020-10-14 | 2021-02-09 | 深圳供电局有限公司 | Ultrasonic bird repelling method and device, bird repeller and storage medium |
| CN112273366A (en) * | 2020-10-28 | 2021-01-29 | 玉林市农业科学院(广西农业科学院玉林分院) | Method and system for ecologically repelling birds by agricultural unmanned aerial vehicle in rice direct seeding cultivation |
| CN114027288A (en) * | 2020-12-29 | 2022-02-11 | 深圳国金电力新能设计院有限公司 | Multi-information-source comprehensive processing bird protection device and method based on wind power plant |
| CN112931482A (en) * | 2021-01-15 | 2021-06-11 | 国网山西省电力公司晋城供电公司 | Shaft tower drives bird ware |
| CN112931482B (en) * | 2021-01-15 | 2022-06-07 | 国网山西省电力公司晋城供电公司 | Shaft tower drives bird ware |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109924194A (en) | A kind of scarer and bird repellent method | |
| Fenton et al. | Bats of Kootenay, Glacier, and Mount Revelstoke national parks in Canada: identification by echolocation calls, distribution, and biology | |
| Kastelein et al. | Hearing threshold shifts and recovery in harbor seals (Phoca vitulina) after octave-band noise exposure at 4 kHz | |
| KR101717045B1 (en) | Animal extirpator | |
| CN203302232U (en) | Multifunctional bird repelling device for high-voltage transmission line | |
| CN206101425U (en) | Ultrasonic bird -repellent device for transmission tower | |
| CN110730331B (en) | Bird online monitoring system and method combining image and acoustic recognition technology | |
| CN202396352U (en) | Animal ultrasound expelling device for transformer substation | |
| CN110089513A (en) | It is a kind of can be to the method that power equipment bird pest is expelled in time | |
| CN212787168U (en) | Novel transmission line unmanned aerial vehicle intelligence drive bird device | |
| CN203015727U (en) | Ultrasonic voice bird repelling device | |
| CN101833097A (en) | Underwater net cage multi-beam fish driving monitoring system and method | |
| CN102396447A (en) | Photoelectric target identification bird repeller and bird repelling method | |
| CN205756850U (en) | Electric power special-purpose ultrasonic bird-scaring unit | |
| Sabinsky et al. | Temporal and spatial variation in harbor seal (Phoca vitulina L.) roar calls from southern Scandinavia | |
| CN108157219A (en) | A kind of pet based on convolutional neural networks stops apparatus and method of barking | |
| CN201854623U (en) | Photoelectric target identification bird repeller | |
| CN108007560B (en) | Dolphin acoustic protection device based on medium-high frequency signals and protection method thereof | |
| Li et al. | Intelligent audio bird repeller for transmission line tower based on bird species variation | |
| CN102972388A (en) | Solar energy birdcall bird driving method and bird driving device | |
| CN206547166U (en) | A kind of microphone array sound pick-up of water-proof sound-transmitting | |
| CN113678797A (en) | Fishery operation sea-area broadband acoustic signal dolphin acoustic driving method and system | |
| CN210226693U (en) | Intelligent bird repelling device | |
| CN204697799U (en) | A kind of intelligence drives animal solar energy equipment | |
| CN205431753U (en) | Beastly device is driven in farmland |
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: 20190625 |
|
| RJ01 | Rejection of invention patent application after publication |