CN115510265A - Method and system for judging animal hazard distribution of pole tower in power transmission line - Google Patents
Method and system for judging animal hazard distribution of pole tower in power transmission line Download PDFInfo
- Publication number
- CN115510265A CN115510265A CN202110630962.5A CN202110630962A CN115510265A CN 115510265 A CN115510265 A CN 115510265A CN 202110630962 A CN202110630962 A CN 202110630962A CN 115510265 A CN115510265 A CN 115510265A
- Authority
- CN
- China
- Prior art keywords
- animal
- risk
- data
- tower
- voiceprint data
- 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
- 241001465754 Metazoa Species 0.000 title claims abstract description 170
- 230000005540 biological transmission Effects 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004891 communication Methods 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 11
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 4
- 241000283984 Rodentia Species 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
- G06F16/636—Filtering based on additional data, e.g. user or group profiles by using biological or physiological data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/141—Discrete Fourier transforms
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Optimization (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Algebra (AREA)
- Discrete Mathematics (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Physiology (AREA)
- Catching Or Destruction (AREA)
Abstract
The invention discloses a method and a system for judging animal hazard distribution of a tower in a power transmission line, which belong to the technical field of electric power.
Description
Technical Field
The invention belongs to the technical field of electric power, and relates to a method and a system for judging animal hazard distribution of towers in a power transmission line.
Background
The damage of the small animals is one of the important causes of the damage of the transmission line, and comprises bird damage, rodent damage and the like.
At present, aiming at the problem of small animal hazard, the establishment of an animal hazard distribution map of a power transmission line is very urgent and necessary, and the key problem of drawing the animal hazard distribution map is how to scientifically determine the animal hazard grade and the vulnerable area.
Disclosure of Invention
The invention aims to provide a method and a system for judging animal hazard distribution of towers in a power transmission line, and solves the technical problem of obtaining animal hazard grades in the power transmission line in an audio recognition mode.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for judging animal hazard distribution of poles and towers in a power transmission line comprises the steps of establishing identity lists for all the poles and towers in the power transmission line;
acquiring animal sound audio data acquired on any one tower M;
preprocessing animal voice data to generate voiceprint data;
establishing an animal sound data identification library for storing reference audios of the cry of various animals, and in the animal sound data identification library, dividing the danger grades of various animals into high-risk animals and low-risk animals;
traversing the animal voice data recognition database, comparing the voiceprint data with all reference audios in the animal voice data recognition database one by one, judging whether the voiceprint data belong to the cry audio of the high-risk animal, and executing the following judgment:
when the high-risk animal is judged to be the sound calling audio: marking the voiceprint data as high-risk animal audio frequency and storing the voiceprint data to generate high-risk voiceprint data ID, meanwhile, a high-risk animal emergence data set used for storing high-risk voiceprint data ID is established, and whether the voiceprint data are repeated or not is counted after multiple times of collection within preset time: if yes, marking the dangerous grade of the tower M as a high-risk tower, establishing a high-risk tower set for storing an identity list of the high-risk towers; if not, marking the danger level of the tower M as a non-dangerous tower;
when the low-risk animal is judged not to be the sound calling audio: marking the voiceprint data as low-risk animal audio frequency and storing, generating low-risk voiceprint data ID, establishing a low-risk animal presence and absence data set for storing the low-risk voiceprint data ID, and counting whether the voiceprint data is repeated after being collected for multiple times in preset time: if yes, marking the danger level of the tower M as a non-dangerous tower, a low-dangerous tower or a high-dangerous tower according to the occurrence frequency of the voiceprint data in the preset time, and establishing a low-dangerous tower set for storing an identity list of the high-dangerous tower;
setting preset time, updating the voiceprint data set and the low-risk animal appearing and disappearing data set of the high-risk animals according to the preset time, updating the danger level of the corresponding pole tower, and updating the low-risk pole tower set and the high-risk pole tower set at the same time;
and drawing a tower hazard distribution map in the power transmission line according to the low-risk tower set and the high-risk tower set.
Preferably, the first and second liquid crystal materials are, the pretreatment of animal sound data comprises the following steps:
step A1: after the animal sound audio data are obtained, the animal sound audio data are subjected to frame-by-frame windowing, cutting the long-time frame audio of the animal sound audio data into a plurality of short-time frame audio;
step A2: the time interval between two adjacent short-time frame audios is recorded, generating a frame time difference;
step A3: a short period of time frame audio is acquired, filtering the short-time frame audio to generate voiceprint data;
step (ii) of A4: and repeating the step A3 until all the short-time frame audio data are filtered, so as to obtain the voiceprint data of all the short-time frame audio.
Preferably, when step A3 is executed, the filtering processing on the short-time frame audio includes performing fast fourier transform on the short-time frame audio to obtain energy distribution of the short-time frame audio on a frequency domain, then obtaining an energy coefficient after preset band-pass filtering by using a Mel filtering method, performing logarithmic conversion on the energy coefficient to obtain corresponding audio power, then converting the audio power back to a time threshold by using discrete cosine transform to obtain MFCC characteristic parameters, and storing the MFCC characteristic parameters as voiceprint data.
Preferably, after the high-risk animal is judged to be the sound calling audio, the following steps are specifically executed:
step B1: after obtaining the voiceprint data, comparing the voiceprint data with the high-risk animal presence and absence data set to find out whether the voiceprint data is recorded: if not, marking the voiceprint data as a first record, recording the voiceprint data into a high-risk animal presence and absence data set, and executing the step B2; if so, marking the voiceprint data as repeated appearance, and marking the tower for collecting the voiceprint data as a high-risk tower;
and step B2: updating the high-risk animal birth and death data set every 1 week, deleting the voiceprint data which do not repeatedly appear in 1 week, and storing the voiceprint data which are marked to repeatedly appear;
and step B3: if the voiceprint data which repeatedly appear in the high-risk animal presence and absence data set exist, continuously marking the tower which collects the voiceprint data as a high-risk tower; and otherwise, marking the tower for collecting the voiceprint data as a non-dangerous tower.
Preferably, after the low-risk animal is judged to be the sound calling audio, the following steps are specifically executed:
step C1: after obtaining the voiceprint data, comparing the voiceprint data with a low-risk animal presence and absence data set to find out whether the voiceprint data is recorded: if not, marking the voiceprint data as a first record, recording the voiceprint data into a low-risk animal presence and absence data set, and executing the step C2; if so, marking the voiceprint data as repeated occurrence, and recording the repeated occurrence times;
and step C2: and traversing the repeated occurrence times of all voiceprint data in the low-risk animal presence and absence data set:
when the repeated occurrence frequency of any voiceprint data reaches a preset upper limit value, marking the tower which collects the voiceprint data as a high-risk tower;
when the repeated occurrence times of all the voiceprint data do not reach the preset upper limit value, when the repeated occurrence frequency of any voiceprint data reaches a preset early warning value, marking the tower for collecting the voiceprint data as a low-risk tower;
when the repeated occurrence frequency of all the voiceprint data does not reach a preset early warning value, marking the tower which collects the voiceprint data as a non-dangerous tower;
and C3: updating the low-risk animal birth and death data set every 1 week, and deleting the voiceprint data which do not repeatedly appear within 1 week, and storing the voiceprint data marked to repeatedly appear.
An animal hazard distribution judgment system for poles and towers in a power transmission line comprises a pickup device, a wireless communication base station and a central server, wherein the pickup device is used for collecting animal sound audio data, the pickup device communicates with a wireless communication base station through a wireless communication network, and the wireless communication base station communicates with a central server through the internet.
Preferably, the sound pickup apparatus comprises an array microphone for picking up sound and a wireless LORA module, the pickup equipment transmits animal sound audio data to a wireless communication base station through a wireless LORA module.
Preferably, an animal sound data identification database, an audio database, a high-risk animal presence and absence data set database and a low-risk animal presence and absence data set database are established in the central server;
the audio database is used for caching audio data of all animals;
the high-risk animal submergence data set database and the low-risk animal submergence data set database are respectively used for storing a high-risk animal submergence data set and a low-risk animal submergence data set.
The invention has the beneficial effects that:
the method and the system for judging the animal hazard distribution of the pole tower in the power transmission line solve the technical problem of acquiring the animal hazard grade in the power transmission line in an audio recognition mode.
Drawings
FIG. 1 is a main flow diagram of the present invention;
FIG. 2 is a flow chart of the present invention for pre-processing animal acoustic data;
FIG. 3 is a flow chart of the present invention when the high-risk animal is determined to be the cry voice of the high-risk animal;
FIG. 4 is a flow chart of the present invention when the low-risk animal is determined to be the cry tone;
FIG. 5 is a flowchart illustrating the process of determining whether voiceprint data is repeated according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Example 1:
as shown in fig. 1 to 5, a method for determining animal hazard distribution of towers in a power transmission line includes establishing an identity list for all towers in the power transmission line;
in this embodiment, the identity list of the tower includes a tower ID, a tower name, a tower number, a team to which the tower belongs, a tower coordinate, a voltage level, a tower state, a fault time, a fault type, a terrain and landform, a surrounding environment, and a tower risk level.
Acquiring animal sound audio data acquired on any one tower M;
in this embodiment, the animal audio data is bird data or rodent data, where the bird data includes high-risk birds, low-risk birds, and harmless birds, the high-risk birds are tree-inhabited birds, the low-risk birds are large non-tree-inhabited birds, the wingspan of the bird is greater than 1 meter and less than 1.5 meters, and the harmless birds are small non-tree-inhabited birds, and the wingspan of the bird is less than 1 meter.
Rodents are classified as high risk animals.
Preprocessing animal voice data to generate voiceprint data;
establishing an animal sound data recognition base for storing reference audios of the sounds of various animals, and dividing the danger grades of various animals into high-risk animals and low-risk animals in the animal sound data recognition base;
traversing the animal voice data identification library, comparing the voiceprint data with all reference audios in the animal voice data identification library one by one, judging whether the voiceprint data belong to the cry audio of the high-risk animal, and executing the following judgment:
when the high-risk animal is judged to be the sound calling audio: marking the voiceprint data as high-risk animal audio frequency and storing, generating high-risk voiceprint data ID, establishing a high-risk animal presence and absence data set for storing the high-risk voiceprint data ID, and counting whether the voiceprint data is repeated after being collected for multiple times in preset time: if yes, marking the danger level of the tower M as a high-risk tower, and establishing a high-risk tower set for storing an identity list of the high-risk tower; if not, marking the danger level of the tower M as a non-dangerous tower;
when the low-risk animal is judged not to be the sound calling audio: marking the voiceprint data as low-risk animal audio frequency and storing, generating low-risk voiceprint data ID, establishing a low-risk animal presence and absence data set for storing the low-risk voiceprint data ID, and counting whether the voiceprint data is repeated after being collected for multiple times in preset time: if yes, marking the danger level of the tower M as a non-dangerous tower, a low-dangerous tower or a high-dangerous tower according to the occurrence frequency of the voiceprint data in the preset time, and establishing a low-dangerous tower set for storing an identity list of the high-dangerous tower;
setting preset time, updating the voiceprint data set and the low-risk animal appearing and disappearing data set of the high-risk animals according to the preset time, updating the danger level of the corresponding pole tower, and updating the low-risk pole tower set and the high-risk pole tower set at the same time;
and drawing a tower hazard distribution map in the power transmission line according to the low-risk tower set and the high-risk tower set.
Preferably, the pretreatment of the animal sound data comprises the following steps:
step A1: after the animal sound audio data are obtained, performing framing and windowing processing on the animal sound audio data, and cutting the long-time frame audio of the animal sound audio data into a plurality of sections of short-time frame audio;
step A2: recording a time interval between two adjacent short-time frame audios to generate a frame time difference;
step A3: acquiring a short-time frame audio, and performing filtering processing on the short-time frame audio to generate voiceprint data;
step A4: and repeating the step A3 until all the short-time frame audio data are filtered, thereby acquiring the voiceprint data of all the short-time frame audio.
Preferably, in the step A3, the filtering process for the short-time frame audio includes performing fast fourier transform on the short-time frame audio, acquiring energy distribution of the short-time frame audio in a frequency domain, then acquiring preset band-pass filtered energy coefficients by using Mel filtering method, and carrying out logarithmic conversion on the energy coefficient to obtain corresponding audio power, then converting the audio power back to a time threshold by discrete cosine transform to obtain an MFCC characteristic parameter, and storing the MFCC characteristic parameter as voiceprint data.
Preferably, after the high-risk animal is judged to be the sound calling audio, the following steps are specifically executed:
step B1: after obtaining the voiceprint data, comparing the voiceprint data with the high-risk animal presence and absence data set to find out whether the voiceprint data is recorded: if not, marking the voiceprint data as a first record, recording the voiceprint data into a high-risk animal presence and absence data set, and executing the step B2; if yes, marking the voiceprint data as repeated appearance, and marking the tower for collecting the voiceprint data as a high-risk tower;
and step B2: updating the high-risk animal birth and death data set every 1 week, deleting the voiceprint data which do not repeatedly appear in 1 week, and storing the voiceprint data which are marked to repeatedly appear;
and step B3: if the voiceprint data which repeatedly appear exist in the high-risk animal presence and absence data set, continuously marking the tower which collects the voiceprint data as a high-risk tower; and otherwise, marking the tower for collecting the voiceprint data as a non-dangerous tower.
Preferably, after the low-risk animal is judged to be the sound calling audio, the following steps are specifically executed:
step C1: after obtaining the voiceprint data, comparing the voiceprint data with the low-risk animal presence and absence data set to find out whether the voiceprint data is recorded: if not, marking the voiceprint data as a first record, recording the voiceprint data into a low-risk animal presence and absence data set, and executing the step C2; if so, marking the voiceprint data as repeated occurrence, and recording the repeated occurrence times;
and step C2: and traversing the repeated occurrence times of all voiceprint data in the low-risk animal presence and absence data set:
when the repeated occurrence frequency of any voiceprint data reaches a preset upper limit value, marking the tower which collects the voiceprint data as a high-risk tower;
when the repeated occurrence frequency of all the voiceprint data does not reach a preset upper limit value and the repeated occurrence frequency of any voiceprint data reaches a preset early warning value, marking the tower for collecting the voiceprint data as a low-risk tower;
when the repeated occurrence frequency of all voiceprint data does not reach a preset early warning value, marking the tower for collecting the voiceprint data as a non-dangerous tower;
and C3: and updating the low-risk animal appearance data set every 1 week, deleting the voiceprint data which do not repeatedly appear in 1 week, and storing the voiceprint data which are marked to repeatedly appear.
In this embodiment, as shown in fig. 5, when determining whether voiceprint data is repeated, the following method is adopted:
step S1: acquiring new voiceprint data and acquiring a frame time difference;
step S2: the comparison is carried out according to the frame time difference or the voiceprint data, when the comparison is carried out through the frame time difference, due to the fact that the cry of birds has the characteristic of being high in repeatability, the comparison is carried out according to the similarity of the frame time difference, when the frame time difference is within the set error range, the voiceprint data are judged to be the repeated data, and the judgment efficiency is accelerated.
Example 2:
the system for determining animal hazard distribution of towers in power transmission lines described in embodiment 2 is a system which is matched with the method for determining animal hazard distribution of towers in power transmission lines described in embodiment 1, and comprises a pickup device, a wireless communication base station and a central server, wherein the pickup device is used for collecting animal sound audio data, the pickup device is communicated with the wireless communication base station through a wireless communication network, and the wireless communication base station is communicated with the central server through the internet.
Preferably, the sound pickup equipment comprises an array microphone for picking up sound and a wireless LORA module, and the sound pickup equipment transmits animal sound audio data to the wireless communication base station through the wireless LORA module.
Preferably, an animal sound data identification database, an audio database, a high-risk animal presence and absence data set database and a low-risk animal presence and absence data set database are established in the central server;
the audio database is used for caching sound and audio data of all animals;
the high-risk animal presence and absence data set database and the low-risk animal presence and absence data set database are respectively used for storing a high-risk animal presence and absence data set and a low-risk animal presence and absence data set.
The invention has the beneficial effects that:
the method and the system for judging the animal hazard distribution of the tower in the power transmission line solve the technical problem of obtaining the animal hazard grade in the power transmission line in an audio recognition mode, determine the type of the animal by recognizing the animal sound, thereby distinguishing the high-risk animal, mark the tower where the high-risk animal exists, draw a hazard distribution map in a standardized mode, and facilitate popularization.
Any process or method descriptions herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing custom logical functions or steps of a process, and the scope of the preferred embodiments of the present invention includes additional implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.
The logic and/or steps described in this specification, for example, as an ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (ePROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: discrete logic circuits with logic gates for implementing logic functions on data blocks, application specific integrated circuits with appropriate combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), etc.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (8)
1. A method for judging animal hazard distribution of towers in a power transmission line is characterized by comprising the following steps: establishing an identity list for all towers in the power transmission line;
acquiring animal sound audio data acquired on any one tower M;
preprocessing animal voice data to generate voiceprint data;
establishing an animal sound data identification library for storing reference audio of the cry of various animals, and dividing the danger grades of various animals into high-risk animals and low-risk animals in the animal sound data identification library;
traversing the animal voice data identification library, comparing the voiceprint data with all reference audios in the animal voice data identification library one by one, judging whether the voiceprint data belong to the cry audio of the high-risk animal, and executing the following judgment:
when the high-risk animal is judged to be the cry voice frequency of the high-risk animal: marking the voiceprint data as high-risk animal audio frequency and storing, generating high-risk voiceprint data ID, establishing a high-risk animal presence and absence data set for storing the high-risk voiceprint data ID, and counting whether the voiceprint data is repeated after being collected for multiple times in preset time: if yes, marking the danger level of the tower M as a high-risk tower, and establishing a high-risk tower set for storing an identity list of the high-risk tower; if not, marking the danger level of the tower M as a non-dangerous tower;
when the low-risk animal is judged not to be the cry voice frequency of the low-risk animal: marking the voiceprint data as low-risk animal audio frequency and storing, generating low-risk voiceprint data ID, establishing a low-risk animal presence and absence data set for storing the low-risk voiceprint data ID, and counting whether the voiceprint data is repeated after being collected for multiple times in preset time: if yes, marking the danger level of the tower M as a non-dangerous tower, a low-dangerous tower or a high-dangerous tower according to the occurrence frequency of the voiceprint data in the preset time, and establishing a low-dangerous tower set for storing an identity list of the high-dangerous tower;
setting preset time, updating the voiceprint data set and the low-risk animal presence and absence data set of the high-risk animals according to the preset time, updating the danger level of the corresponding pole tower, and updating the low-risk pole tower set and the high-risk pole tower set at the same time;
and drawing a tower hazard distribution map in the power transmission line according to the low-risk tower set and the high-risk tower set.
2. The method for judging the animal hazard distribution of the towers in the power transmission line according to claim 1, which is characterized in that: the method for preprocessing the animal sound data comprises the following steps:
step A1: after animal sound audio data are obtained, performing frame windowing on the animal sound audio data, and cutting a long-time frame audio of the animal sound audio data into a plurality of sections of short-time frame audio;
step A2: recording the time interval between two adjacent short-time frame audios, and generating a frame time difference;
step A3: acquiring a short-time frame audio, and filtering the short-time frame audio to generate voiceprint data;
step A4: and repeating the step A3 until all the short-time frame audio data are filtered, so as to obtain the voiceprint data of all the short-time frame audio.
3. The method for judging the animal hazard distribution of the towers in the power transmission line according to claim 2, characterized by comprising the following steps: when the step A3 is executed, the filtering processing of the short-time frame audio includes performing fast fourier transform on the short-time frame audio to obtain energy distribution of the short-time frame audio on a frequency domain, then obtaining an energy coefficient after preset band-pass filtering by using a Mel filtering method, performing logarithmic conversion on the energy coefficient to obtain corresponding audio power, then converting the audio power back to a time threshold by using discrete cosine transform to obtain MFCC characteristic parameters, and storing the MFCC characteristic parameters as voiceprint data.
4. The method for judging the animal hazard distribution of the towers in the power transmission line according to claim 1, characterized by comprising the following steps: when the high-risk animal is judged to be the sound calling audio, the following steps are specifically executed:
step B1: after obtaining the voiceprint data, comparing the voiceprint data with the high-risk animal presence and absence data set to find out whether the voiceprint data is recorded: if not, marking the voiceprint data as a first record, recording the voiceprint data into a high-risk animal presence and absence data set, and executing the step B2; if so, marking the voiceprint data as repeated appearance, and marking the tower for collecting the voiceprint data as a high-risk tower;
and step B2: updating the high-risk animal appearance data set every 1 week, deleting the voiceprint data which do not repeatedly appear in 1 week, and storing the voiceprint data which are marked to repeatedly appear;
and step B3: if the voiceprint data which repeatedly appear in the high-risk animal presence and absence data set exist, continuously marking the tower which collects the voiceprint data as a high-risk tower; and otherwise, marking the tower for collecting the voiceprint data as a non-dangerous tower.
5. The method for judging the animal hazard distribution of the towers in the power transmission line according to claim 1, which is characterized in that: when the low-risk animal is judged to be the sound calling audio, the following steps are specifically executed:
step C1: after obtaining the voiceprint data, comparing the voiceprint data with a low-risk animal presence and absence data set to find out whether the voiceprint data is recorded: if not, marking the voiceprint data as a first record, recording the voiceprint data into a low-risk animal presence and absence data set, and executing the step C2; if yes, marking the voiceprint data as repeated occurrence, and recording the repeated occurrence times;
and C2: and traversing the repeated occurrence times of all voiceprint data in the low-risk animal presence and absence data set:
when the repeated occurrence frequency of any voiceprint data reaches a preset upper limit value, marking the tower which collects the voiceprint data as a high-risk tower;
when the repeated occurrence frequency of all the voiceprint data does not reach a preset upper limit value and the repeated occurrence frequency of any voiceprint data reaches a preset early warning value, marking the tower for collecting the voiceprint data as a low-risk tower;
when the repeated occurrence frequency of all voiceprint data does not reach a preset early warning value, marking the tower for collecting the voiceprint data as a non-dangerous tower;
step C3: and updating the low-risk animal birth and death data set every 1 week, deleting the voiceprint data which do not repeatedly appear in 1 week, and storing the voiceprint data which are marked to repeatedly appear.
6. The utility model provides an animal harm distribution decision system of shaft tower among transmission line which characterized in that: the animal sound collecting system comprises sound collecting equipment, a wireless communication base station and a central server, wherein the sound collecting equipment is used for collecting animal sound audio data, the sound collecting equipment is communicated with the wireless communication base station through a wireless communication network, and the wireless communication base station is communicated with the central server through the Internet.
7. The system for determining animal hazard distribution of towers in power transmission line according to claim 6, characterized in that: the pickup equipment comprises an array microphone and a wireless LORA module, wherein the array microphone is used for picking up sound, and the pickup equipment transmits animal sound audio data to the wireless communication base station through the wireless LORA module.
8. The system for determining animal hazard distribution of towers in power transmission line according to claim 6, characterized in that: establishing an animal sound data identification database, an audio database, a high-risk animal presence and absence data set database and a low-risk animal presence and absence data set database in a central server;
the audio database is used for caching audio data of all animals;
the high-risk animal submergence data set database and the low-risk animal submergence data set database are respectively used for storing a high-risk animal submergence data set and a low-risk animal submergence data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110630962.5A CN115510265A (en) | 2021-06-07 | 2021-06-07 | Method and system for judging animal hazard distribution of pole tower in power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110630962.5A CN115510265A (en) | 2021-06-07 | 2021-06-07 | Method and system for judging animal hazard distribution of pole tower in power transmission line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115510265A true CN115510265A (en) | 2022-12-23 |
Family
ID=84499689
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110630962.5A Pending CN115510265A (en) | 2021-06-07 | 2021-06-07 | Method and system for judging animal hazard distribution of pole tower in power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115510265A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665381A (en) * | 2023-07-28 | 2023-08-29 | 国网山东省电力公司济宁市任城区供电公司 | Method and system for identifying and early warning external broken source of power transmission line |
| CN117095695A (en) * | 2023-10-19 | 2023-11-21 | 国网山西省电力公司超高压变电分公司 | Wide-area voiceprint compression acquisition method and system for transformer body |
-
2021
- 2021-06-07 CN CN202110630962.5A patent/CN115510265A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665381A (en) * | 2023-07-28 | 2023-08-29 | 国网山东省电力公司济宁市任城区供电公司 | Method and system for identifying and early warning external broken source of power transmission line |
| CN116665381B (en) * | 2023-07-28 | 2023-11-03 | 国网山东省电力公司济宁市任城区供电公司 | Method and system for identifying and early warning external broken source of power transmission line |
| CN117095695A (en) * | 2023-10-19 | 2023-11-21 | 国网山西省电力公司超高压变电分公司 | Wide-area voiceprint compression acquisition method and system for transformer body |
| CN117095695B (en) * | 2023-10-19 | 2023-12-22 | 国网山西省电力公司超高压变电分公司 | Wide-area voiceprint compression acquisition method and system for transformer body |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108198562A (en) | A kind of method and system for abnormal sound in real-time positioning identification animal house | |
| CN103117061B (en) | A kind of voice-based animals recognition method and device | |
| CN109087655A (en) | A kind of monitoring of traffic route sound and exceptional sound recognition system | |
| CN115510265A (en) | Method and system for judging animal hazard distribution of pole tower in power transmission line | |
| CN102522084B (en) | Method and system for converting voice data into text files | |
| Evans et al. | Monitoring grassland birds in nocturnal migration | |
| CN109817227B (en) | Abnormal sound monitoring method and system for farm | |
| CN110797031A (en) | Voice change detection method, system, mobile terminal and storage medium | |
| CN102945675A (en) | Intelligent sensing network system for detecting outdoor sound of calling for help | |
| CN111306010B (en) | Method and system for detecting lightning damage of fan blade | |
| CN105118511A (en) | Thunder identification method | |
| Lapp et al. | Automated detection of frog calls and choruses by pulse repetition rate | |
| CN111414832A (en) | Real-time online recognition and classification system based on whale dolphin low-frequency underwater acoustic signals | |
| CN111626093B (en) | Method for identifying related bird species of power transmission line based on sound power spectral density | |
| CN115048984A (en) | Sow oestrus recognition method based on deep learning | |
| Patti et al. | Methods for classification of nocturnal migratory bird vocalizations using Pseudo Wigner-Ville Transform | |
| CN101950564A (en) | Remote digital voice acquisition, analysis and identification system | |
| Zhang et al. | A novel insect sound recognition algorithm based on MFCC and CNN | |
| CN116168727A (en) | Transformer abnormal sound detection method, system, equipment and storage medium | |
| Cosentino et al. | Porpoise click classifier (PorCC): A high-accuracy classifier to study harbour porpoises (Phocoena phocoena) in the wild | |
| Anđelić et al. | Sound-based logging detection using deep learning | |
| CN107548007B (en) | Detection method and device of audio signal acquisition equipment | |
| CN114372513A (en) | Training method, classification method, equipment and medium of bird sound recognition model | |
| CN111863031B (en) | Audio monitoring device loaded on existing camera network and monitoring method thereof | |
| CN114387991A (en) | Audio data processing method, apparatus, and medium for recognizing field environmental sounds |
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 |