CN111653291A - Intelligent health monitoring method for power equipment based on voiceprint - Google Patents
Intelligent health monitoring method for power equipment based on voiceprint Download PDFInfo
- Publication number
- CN111653291A CN111653291A CN202010482501.3A CN202010482501A CN111653291A CN 111653291 A CN111653291 A CN 111653291A CN 202010482501 A CN202010482501 A CN 202010482501A CN 111653291 A CN111653291 A CN 111653291A
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- data
- module
- equipment
- wireless
- 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
- 230000036541 health Effects 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 238000013500 data storage Methods 0.000 claims abstract description 32
- 238000012937 correction Methods 0.000 claims abstract description 30
- 238000004891 communication Methods 0.000 claims abstract description 24
- 238000003745 diagnosis Methods 0.000 claims abstract description 24
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 3
- 229920006351 engineering plastic Polymers 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims description 2
- 229910052744 lithium Inorganic materials 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 11
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/21—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being power information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Water Supply & Treatment (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Public Health (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of electric power, and provides an intelligent health monitoring method for electric power equipment based on voiceprints, which comprises the following steps: s1, laying a voiceprint signal collector on the site of the power equipment, and uniformly deploying a plurality of wireless sensors on each power equipment to collect voiceprint signals of each equipment of the power equipment working on the site; s2, the voiceprint signal collector is composed of a Bluetooth wireless communication module, a data packet forwarding module, a 4G communication module and a power supply module; s3, the cloud voiceprint data memory is composed of an IP communication module, a data storage module and a data processing module; and S4, periodically performing feature extraction, fault diagnosis and threshold correction on the voiceprint data stored in the disk by adopting the equipment health intelligent manager. The invention solves the problems of difficult deployment of acquisition nodes, unstable work of a data server, low fault diagnosis speed and precision, nonadjustable fault diagnosis threshold value and the like in the conventional power equipment health monitoring technology.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to an intelligent health monitoring method for electric power equipment based on voiceprints.
Background
With the expansion of the investment scale of a power grid, the rapid development of the new energy power generation industry and the vigorous transformation of the rural power grid of the urban power grid, the normal operation of the power equipment is a necessary premise for ensuring the normal operation of the whole power supply system and ensuring good power supply. However, power equipment is generally in a charged state and cannot be detected in a conventional mode, indirect judgment is mostly performed by acquiring equipment temperature data in the prior art, but the judgment is greatly influenced by the environment, the judgment accuracy is not high, and the reference significance is not large.
In the process of live operation, the power equipment can generate specific sound and vibration which can represent the state of the equipment, the sound is unique to the equipment, and the sound can be measured and analyzed through an electroacoustic instrument, so that the characteristic carried by the sound and representing the operating state of the power equipment is called as voiceprint and vibration. By utilizing the characteristic, the abnormal detection is carried out on the detection voiceprint information of the detected equipment, so that the working condition of the equipment can be prejudged, the preknown and the elimination are realized before the equipment breaks down, and the loss caused by abnormal power grid outage due to sudden failure of the power equipment is avoided.
For example, Chinese patent documents: CN 201811612080.0A fault detection method, device and system for electromechanical equipment, disclosing a fault detection method for electromechanical equipment, because the sound of the electromechanical equipment in normal operation state is generally different from the sound of the electromechanical equipment in fault, only needing to place sound collection equipment in the surrounding area of the electromechanical equipment to collect the sound of the electromechanical equipment, and determining whether the electromechanical equipment is in fault by extracting the voiceprint characteristics of the collected sound and verifying the extracted voiceprint characteristics by using a voiceprint library. The contact type sensor does not need to be installed on the electromechanical equipment, the physical characteristics of the electromechanical equipment can not interfere with the sound acquisition equipment, the limitation of fault detection on the electromechanical equipment is small, the fault detection precision of the electromechanical equipment is improved, and accidents in the area where the electromechanical equipment is located are avoided. However, the fault diagnosis is based on the existing data in the voiceprint library for verification, fault false alarm can be generated when the acquired voiceprint data is abnormal, the fault false alarm cannot be corrected when the fault false alarm occurs, meanwhile, fault diagnosis false alarm can be generated when the voiceprint data is abnormal along with the aging of equipment operation, environmental changes and the like, the monitoring effect is not ideal, and the equipment cannot be effectively and healthily monitored.
Also, for example, CN201910885692.5 is a method for identifying faults of rotating mechanical equipment based on voiceprint signals, which discloses a method for identifying faults of rotating mechanical equipment based on voiceprint signals, comprising the following steps: establishing a screen spectrum database; collecting voiceprint signals of the rotating mechanical equipment through an audio collecting assembly; converting the electric signal corresponding to the voiceprint signal into a digital signal through an audio conversion component; judging whether the rotating mechanical equipment has faults or not by comparing the frequency spectrum value of the digital signal with a spectrum screening database; judging whether the rotary mechanical equipment has faults or not through wavelet packet analysis; and comparing the states of the rotary mechanical equipment analyzed by the two modes, if the states are consistent, the rotary mechanical equipment is in a normal state or a fault state, and if the states are inconsistent, analyzing and comparing the states of the rotary mechanical equipment again until the comparison is consistent. Although the method can reduce false alarm of fault diagnosis to a certain extent by adopting two detection and analysis modes, the method only checks the existing database, and fault diagnosis false alarm can be generated when voiceprint data generated along with the aging of equipment operation, environmental change and the like are abnormal, the monitoring effect is not ideal, and the detection cost is increased by arranging the two detection modes at the same time.
Further, like the method and system for online monitoring of power equipment based on voiceprint recognition in CN201910570185.2, a method and system for online monitoring of power equipment based on voiceprint recognition are disclosed, which collect data streams in at least one preset first sound pickup and data streams in at least one preset second sound pickup. Determining that the established connection relation of the first sound pickup including the data stream and the corresponding data stream node, the at least one second sound pickup including the data stream and the corresponding data stream node and the original data of the data server are matched; and outputting a matching result. Compared with the prior art, the method and the system for monitoring the power equipment on line based on voiceprint recognition have the advantages that the running state of the transformer is monitored on line through the sound signals generated when the monitoring equipment runs, the actual running condition of the equipment is mastered from multiple aspects by matching with a transformer substation monitoring system, the management of the transformer substation system is optimized, and the method and the system have important practical significance for improving the maintenance efficiency and reliability of the equipment and prolonging the service life of the equipment. But the detection and analysis are complex and are not suitable for the overall health monitoring of various devices on the site of the power equipment.
Therefore, in the existing voiceprint-based power equipment health monitoring technology, either the deployment of collection nodes is difficult, the work of a data server is unstable, or the detection and analysis are complex and not suitable for simultaneous health monitoring of various equipment, or the fault diagnosis false alarm rate is high and low in precision, and meanwhile, the voiceprint data monitoring threshold value for fault diagnosis is not adjustable, so that various equipment on the site of the power equipment cannot be effectively and uniformly monitored.
Disclosure of Invention
Therefore, aiming at the problems, the invention provides the intelligent health monitoring method for the power equipment based on the voiceprint, which is used for uniformly monitoring the health of various devices on the site of the power equipment, is convenient for deploying the acquisition nodes, stable in work of the data server, high in fault diagnosis speed and precision and capable of adjusting the fault diagnosis threshold.
In order to solve the technical problem, the invention adopts the following scheme: a voiceprint-based intelligent health monitoring method for electrical equipment comprises the following steps:
s1, laying a voiceprint signal collector on the site of the power equipment, uniformly deploying a plurality of wireless sensors on each power equipment to collect voiceprint signals of each equipment of the power equipment working on the site, collecting voiceprint data by each wireless sensor according to a set collection frequency and transmitting the voiceprint data to the voiceprint signal collector through wireless Bluetooth;
s2, the voiceprint signal collector is composed of a Bluetooth wireless communication module, a data packet forwarding module, a 4G communication module and a power module, wherein the Bluetooth wireless communication module is in communication connection with each wireless sensor for collecting voiceprint signals, and sends voiceprint signal collecting commands to each wireless sensor for collecting voiceprint signals through wireless connection and receives voiceprint signal collecting data collected by the wireless sensors for collecting voiceprint signals; the data packet forwarding module packages voiceprint signal acquisition data received by each wireless sensor for acquiring voiceprint signals into a data packet, generates an integrity abstract by adopting an SHA algorithm, and then sends the data packet and the integrity abstract to a cloud voiceprint data memory through the 4G communication module;
s3, the cloud voiceprint data memory is composed of an IP communication module, a data storage module and a data processing module, wherein the IP communication module receives data packets and integrity abstract voiceprint data sent by a voiceprint signal collector through the Internet; the data processing module carries out data packet integrity check by using the integrity abstract of the voiceprint data and an SHA algorithm and transmits the data packet passing the integrity check to the data storage module; the data storage module stores the data packet which passes the integrity check in a disk in a file format;
s4, periodically extracting the characteristics, diagnosing faults and correcting the threshold value of the voiceprint data stored in the disk by adopting an intelligent health manager, wherein the intelligent health manager consists of a data reading module, a characteristic extraction module, a fault diagnosis module, a fault early warning module and a threshold value correction module, and the data reading module reads time-domain voiceprint data from a voiceprint data file stored on the disk periodically; the method comprises the steps that a characteristic extraction module extracts voiceprint data to calculate a time domain average energy value and a frequency domain average energy value, the time domain average energy value calculation method of the voiceprint data is that each data value in the time domain voiceprint data is respectively squared, then accumulated and summed, and finally averaged to calculate the time domain average energy value of the voiceprint data, the frequency domain average energy value calculation method of the voiceprint data is that time domain voiceprint data is firstly subjected to Fourier transform to obtain frequency domain voiceprint data, then each data value in the frequency domain voiceprint data is respectively squared, then accumulated and summed, and finally averaged to calculate the frequency domain average energy value of the voiceprint data; the fault diagnosis module compares the time domain average energy value and the frequency domain average energy value obtained by calculation with a characteristic threshold value to diagnose the fault, and when the time domain average energy value and the frequency domain average energy value are both greater than the current characteristic threshold value, the equipment is diagnosed to be in a fault state; the fault early warning module sends the fault state information detected by the fault diagnosis module, the corresponding time domain average energy value, the corresponding frequency domain average energy value and the characteristic threshold value of the equipment to a field power engineer; and a threshold correction module of the equipment health intelligent manager receives the threshold correction command and the suggested correction value sent by the field power engineer and sets the suggested correction value as a new characteristic threshold of the equipment.
Further, in the step S1, the wireless sensor is a wireless MEMS vibration sensor, the wireless MEMS vibration sensor is powered by a lithium secondary battery, and the wireless MEMS vibration sensor is integrated with a bluetooth wireless interface to perform high-security wireless data transmission; the wireless MEMS vibration sensor shell is made of high-strength engineering plastics.
Furthermore, in step S1, when the field work voiceprint signal is collected for a single large power device, a plurality of wireless sensors are deployed on the large power device in an array manner to collect voiceprint data.
By adopting the technical scheme, the invention has the beneficial effects that: the voiceprint signal data collected by the plurality of wireless sensors are collected by the voiceprint signal collector and forwarded to the cloud voiceprint data storage, deployment cost of voiceprint data collection is saved, the voiceprint data storage is used for receiving the voiceprint data sent by the voiceprint signal collector and carrying out check storage, working requirements of a data storage server are hardly met due to the fact that the working environment of the equipment is severe, such as temperature, humidity and maintenance, in the working field of the equipment are avoided, the situation that the data storage server cannot work stably is avoided, the voiceprint data storage is stored through the cloud voiceprint data storage, the cloud voiceprint data storage is often configured in a machine room meeting the working environment requirements, the server of the cloud voiceprint data storage works stably and safely, and the voiceprint data stored in a magnetic disk by the cloud voiceprint data storage are subjected to feature extraction, feature extraction and data storage by the cloud voiceprint data storage periodically through the intelligent, The method comprises the steps of fault diagnosis and threshold correction, wherein the intelligent health manager of the equipment compares a voiceprint data with a threshold value to diagnose whether the equipment has a fault or not, and when the equipment has a fault, a fault early warning module sends fault state information detected by a fault diagnosis module, a corresponding time domain average energy value, a corresponding frequency domain average energy value and a characteristic threshold value of the equipment to a field power engineer; the method comprises the steps that a field power engineer confirms and processes received fault early warning, when the field power engineer finds that a fault is mistakenly reported, a threshold correction command and a suggested correction value can be sent to an intelligent health manager of the equipment, a threshold correction module of the intelligent health manager of the equipment receives the threshold correction command and the suggested correction value sent by the field power engineer of the equipment and sets the suggested correction value as a new characteristic threshold of the equipment, and therefore the defects of high conventional static characteristic threshold and false alarm rate are overcome.
Detailed Description
The invention will now be further described with reference to specific embodiments.
Preferably, the intelligent health monitoring method for the power equipment based on the voiceprint comprises the following steps:
s1, a voiceprint signal collector is arranged on a power equipment field, a plurality of wireless sensors are uniformly deployed on each power equipment to collect voiceprint signals of each equipment of the power equipment working on the field, each wireless sensor collects voiceprint data according to set collection frequency and transmits the voiceprint data to the voiceprint signal collector through wireless Bluetooth, wherein each wireless sensor is a wireless MEMS vibration sensor, the wireless MEMS vibration sensor is powered by a lithium-ion battery, and the wireless MEMS vibration sensor is integrated with a Bluetooth wireless interface to perform high-safety wireless data transmission; the wireless MEMS vibration sensor shell is made of high-strength engineering plastics, and a plurality of wireless sensors are deployed on a large power device in an array mode to acquire voiceprint data when the voiceprint signals of the single large power device are acquired on site by the power device;
s2, the voiceprint signal collector is composed of a Bluetooth wireless communication module, a data packet forwarding module, a 4G communication module and a power module, wherein the Bluetooth wireless communication module is in communication connection with each wireless sensor for collecting voiceprint signals, and sends voiceprint signal collecting commands to each wireless sensor for collecting voiceprint signals through wireless connection and receives voiceprint signal collecting data collected by the wireless sensors for collecting voiceprint signals; the data packet forwarding module packages voiceprint signal acquisition data received by each wireless sensor for acquiring voiceprint signals into a data packet, generates an integrity abstract by adopting an SHA algorithm, and then sends the data packet and the integrity abstract to a cloud voiceprint data memory through the 4G communication module;
s3, the cloud voiceprint data memory is composed of an IP communication module, a data storage module and a data processing module, wherein the IP communication module receives data packets and integrity abstract voiceprint data sent by a voiceprint signal collector through the Internet; the data processing module carries out data packet integrity check by using the integrity abstract of the voiceprint data and an SHA algorithm and transmits the data packet passing the integrity check to the data storage module; the data storage module stores the data packet which passes the integrity check in a disk in a file format;
s4, periodically extracting the characteristics, diagnosing faults and correcting the threshold value of the voiceprint data stored in the disk by adopting an intelligent health manager, wherein the intelligent health manager consists of a data reading module, a characteristic extraction module, a fault diagnosis module, a fault early warning module and a threshold value correction module, and the data reading module reads time-domain voiceprint data from a voiceprint data file stored on the disk periodically; the method comprises the steps that a characteristic extraction module extracts voiceprint data to calculate a time domain average energy value and a frequency domain average energy value, the time domain average energy value calculation method of the voiceprint data is that each data value in the time domain voiceprint data is respectively squared, then accumulated and summed, and finally averaged to calculate the time domain average energy value of the voiceprint data, the frequency domain average energy value calculation method of the voiceprint data is that time domain voiceprint data is firstly subjected to Fourier transform to obtain frequency domain voiceprint data, then each data value in the frequency domain voiceprint data is respectively squared, then accumulated and summed, and finally averaged to calculate the frequency domain average energy value of the voiceprint data; the fault diagnosis module compares the time domain average energy value and the frequency domain average energy value obtained by calculation with a characteristic threshold value to diagnose the fault, and when the time domain average energy value and the frequency domain average energy value are both greater than the current characteristic threshold value, the equipment is diagnosed to be in a fault state; the fault early warning module sends the fault state information detected by the fault diagnosis module, the corresponding time domain average energy value, the corresponding frequency domain average energy value and the characteristic threshold value of the equipment to a field power engineer; and a threshold correction module of the equipment health intelligent manager receives the threshold correction command and the suggested correction value sent by the field power engineer and sets the suggested correction value as a new characteristic threshold of the equipment.
According to the invention, for small or medium-sized equipment, whether an array type plurality of wireless sensors need to be arranged to collect voiceprint data of the equipment or not can be seen on the site of the power equipment according to the circumstances, and the collection of the time domain voiceprint data is to sample the voiceprint data according to the set cycle time, namely to collect the time domain voiceprint data in equal duration within the set interval time period.
The voiceprint signal data collected by the plurality of wireless sensors are collected and forwarded to the cloud voiceprint data storage through the voiceprint signal collector, deployment cost of voiceprint data collection is saved, the voiceprint data storage is used for receiving the voiceprint data sent by the voiceprint signal collector and carrying out check storage, working requirements of the data storage server are hardly met due to the fact that the working site environment of the equipment is severe, such as temperature, humidity and maintenance, of the data storage server in the working site data storage, the situation that the data storage server cannot work stably is avoided, the voiceprint data storage is stored through the cloud voiceprint data storage, the cloud voiceprint data storage is often configured in a machine room meeting the working environment requirements, the server of the cloud voiceprint data storage is stable and safe in working, and the voiceprint data stored in a magnetic disk in the cloud voiceprint data storage are periodically subjected to feature extraction through the intelligent device health manager, The method comprises the steps of fault diagnosis and threshold correction, wherein the intelligent health manager of the equipment compares a voiceprint data with a threshold value to diagnose whether the equipment has a fault or not, and when the equipment has a fault, a fault early warning module sends fault state information detected by a fault diagnosis module, a corresponding time domain average energy value, a corresponding frequency domain average energy value and a characteristic threshold value of the equipment to a field power engineer; the method comprises the steps that a field power engineer confirms and processes received fault early warning, when the field power engineer finds that a fault is mistakenly reported, a threshold correction command and a suggested correction value can be sent to an intelligent health manager of the equipment, a threshold correction module of the intelligent health manager of the equipment receives the threshold correction command and the suggested correction value sent by the field power engineer of the equipment and sets the suggested correction value as a new characteristic threshold of the equipment, and therefore the defects of high conventional static characteristic threshold and false alarm rate are overcome.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (3)
1. An intelligent health monitoring method for power equipment based on voiceprints is characterized in that: the method comprises the following steps:
s1, laying a voiceprint signal collector on the site of the power equipment, uniformly deploying a plurality of wireless sensors on each power equipment to collect voiceprint signals of each equipment of the power equipment working on the site, collecting voiceprint data by each wireless sensor according to a set collection frequency and transmitting the voiceprint data to the voiceprint signal collector through wireless Bluetooth;
s2, the voiceprint signal collector is composed of a Bluetooth wireless communication module, a data packet forwarding module, a 4G communication module and a power module, wherein the Bluetooth wireless communication module is in communication connection with each wireless sensor for collecting voiceprint signals, and sends voiceprint signal collecting commands to each wireless sensor for collecting voiceprint signals through wireless connection and receives voiceprint signal collecting data collected by the wireless sensors for collecting voiceprint signals; the data packet forwarding module packages voiceprint signal acquisition data received by each wireless sensor for acquiring voiceprint signals into a data packet, generates an integrity abstract by adopting an SHA algorithm, and then sends the data packet and the integrity abstract to a cloud voiceprint data memory through the 4G communication module;
s3, the cloud voiceprint data memory is composed of an IP communication module, a data storage module and a data processing module, wherein the IP communication module receives data packets and integrity abstract voiceprint data sent by a voiceprint signal collector through the Internet; the data processing module carries out data packet integrity check by using the integrity abstract of the voiceprint data and an SHA algorithm and transmits the data packet passing the integrity check to the data storage module; the data storage module stores the data packet which passes the integrity check in a disk in a file format;
s4, periodically extracting the characteristics, diagnosing faults and correcting the threshold value of the voiceprint data stored in the disk by adopting an intelligent health manager, wherein the intelligent health manager consists of a data reading module, a characteristic extraction module, a fault diagnosis module, a fault early warning module and a threshold value correction module, and the data reading module reads time-domain voiceprint data from a voiceprint data file stored on the disk periodically; the method comprises the steps that a characteristic extraction module extracts voiceprint data to calculate a time domain average energy value and a frequency domain average energy value, the time domain average energy value calculation method of the voiceprint data is that each data value in the time domain voiceprint data is respectively squared, then accumulated and summed, and finally averaged to calculate the time domain average energy value of the voiceprint data, the frequency domain average energy value calculation method of the voiceprint data is that time domain voiceprint data is firstly subjected to Fourier transform to obtain frequency domain voiceprint data, then each data value in the frequency domain voiceprint data is respectively squared, then accumulated and summed, and finally averaged to calculate the frequency domain average energy value of the voiceprint data; the fault diagnosis module compares the time domain average energy value and the frequency domain average energy value obtained by calculation with a characteristic threshold value to diagnose the fault, and when the time domain average energy value and the frequency domain average energy value are both greater than the current characteristic threshold value, the equipment is diagnosed to be in a fault state; the fault early warning module sends the fault state information detected by the fault diagnosis module, the corresponding time domain average energy value, the corresponding frequency domain average energy value and the characteristic threshold value of the equipment to a field power engineer; and a threshold correction module of the equipment health intelligent manager receives the threshold correction command and the suggested correction value sent by the field power engineer and sets the suggested correction value as a new characteristic threshold of the equipment.
2. The intelligent health monitoring method for voiceprint-based power equipment according to claim 1, wherein the method comprises the following steps: in the step S1, the wireless sensor is a wireless MEMS vibration sensor, the wireless MEMS vibration sensor is powered by a lithium subcell, and the wireless MEMS vibration sensor is integrated with a Bluetooth wireless interface to perform high-safety wireless data transmission; the wireless MEMS vibration sensor shell is made of high-strength engineering plastics.
3. The intelligent health monitoring method for voiceprint-based power equipment according to claim 1 or 2, wherein the method comprises the following steps: in step S1, when a field work voiceprint signal is acquired for a single large power device, a plurality of wireless sensors are deployed in an array manner on the large power device to acquire voiceprint data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010482501.3A CN111653291B (en) | 2020-06-01 | 2020-06-01 | Intelligent health monitoring method for power equipment based on voiceprint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010482501.3A CN111653291B (en) | 2020-06-01 | 2020-06-01 | Intelligent health monitoring method for power equipment based on voiceprint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111653291A true CN111653291A (en) | 2020-09-11 |
| CN111653291B CN111653291B (en) | 2023-02-14 |
Family
ID=72350962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010482501.3A Active CN111653291B (en) | 2020-06-01 | 2020-06-01 | Intelligent health monitoring method for power equipment based on voiceprint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111653291B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112240909A (en) * | 2020-09-30 | 2021-01-19 | 山东大学 | Bridge inhaul cable broken wire sound signal acquisition system and method |
| CN112446309A (en) * | 2020-11-18 | 2021-03-05 | 华北电力大学 | System and method for monitoring abnormal state based on impact event |
| CN112649502A (en) * | 2020-11-18 | 2021-04-13 | 华北电力大学 | System and method for monitoring abnormal state based on voiceprint diagnosis |
| WO2022088643A1 (en) * | 2020-10-26 | 2022-05-05 | 华翔翔能科技股份有限公司 | Fault diagnosis method and apparatus for buried transformer substation, and electronic device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050262394A1 (en) * | 2004-04-21 | 2005-11-24 | Fuji Xerox Co., Ltd. | Failure diagnosis method, failure diagnosis apparatus, conveyance device, image forming apparatus, program, and storage medium |
| CN106898346A (en) * | 2017-04-19 | 2017-06-27 | 杭州派尼澳电子科技有限公司 | A kind of freeway tunnel safety monitoring system |
| US9892744B1 (en) * | 2017-02-13 | 2018-02-13 | International Business Machines Corporation | Acoustics based anomaly detection in machine rooms |
| CN109658954A (en) * | 2018-12-27 | 2019-04-19 | 广州势必可赢网络科技有限公司 | A kind of fault detection method for electromechanical equipment, apparatus and system |
| CN110782622A (en) * | 2018-07-25 | 2020-02-11 | 杭州海康威视数字技术股份有限公司 | Safety monitoring system, safety detection method, safety detection device and electronic equipment |
| US20200051419A1 (en) * | 2017-10-11 | 2020-02-13 | Analog Devices Global Unlimited Company | Cloud-based machine health monitoring |
-
2020
- 2020-06-01 CN CN202010482501.3A patent/CN111653291B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050262394A1 (en) * | 2004-04-21 | 2005-11-24 | Fuji Xerox Co., Ltd. | Failure diagnosis method, failure diagnosis apparatus, conveyance device, image forming apparatus, program, and storage medium |
| US9892744B1 (en) * | 2017-02-13 | 2018-02-13 | International Business Machines Corporation | Acoustics based anomaly detection in machine rooms |
| CN106898346A (en) * | 2017-04-19 | 2017-06-27 | 杭州派尼澳电子科技有限公司 | A kind of freeway tunnel safety monitoring system |
| US20200051419A1 (en) * | 2017-10-11 | 2020-02-13 | Analog Devices Global Unlimited Company | Cloud-based machine health monitoring |
| CN110782622A (en) * | 2018-07-25 | 2020-02-11 | 杭州海康威视数字技术股份有限公司 | Safety monitoring system, safety detection method, safety detection device and electronic equipment |
| CN109658954A (en) * | 2018-12-27 | 2019-04-19 | 广州势必可赢网络科技有限公司 | A kind of fault detection method for electromechanical equipment, apparatus and system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112240909A (en) * | 2020-09-30 | 2021-01-19 | 山东大学 | Bridge inhaul cable broken wire sound signal acquisition system and method |
| WO2022088643A1 (en) * | 2020-10-26 | 2022-05-05 | 华翔翔能科技股份有限公司 | Fault diagnosis method and apparatus for buried transformer substation, and electronic device |
| CN112446309A (en) * | 2020-11-18 | 2021-03-05 | 华北电力大学 | System and method for monitoring abnormal state based on impact event |
| CN112649502A (en) * | 2020-11-18 | 2021-04-13 | 华北电力大学 | System and method for monitoring abnormal state based on voiceprint diagnosis |
| WO2022105285A1 (en) * | 2020-11-18 | 2022-05-27 | 华北电力大学 | System and method for monitoring abnormal state on basis of impact event |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111653291B (en) | 2023-02-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111653291B (en) | Intelligent health monitoring method for power equipment based on voiceprint | |
| CN110926778B (en) | Mechanical fault diagnosis method for gas insulated switchgear assembly based on abnormal vibration | |
| US7072784B2 (en) | System for monitoring wind power plants | |
| CN113124929A (en) | Transformer substation multi-parameter signal acquisition comprehensive analysis system and method | |
| CN103487749A (en) | On-line monitoring and diagnosing system and method for mechanical state of high-voltage circuit breaker | |
| CN112201260A (en) | Transformer running state online detection method based on voiceprint recognition | |
| GB2476246A (en) | Diagnosing an operation mode of a machine | |
| CN115327369A (en) | On-line monitoring and analyzing system for opening and closing current of switch cabinet circuit breaker | |
| CN108919044B (en) | Active identification method for unit distribution power grid faults based on mutual verification mechanism | |
| CN103675354B (en) | A kind of method of anemoscope failure testing and system | |
| CN115327363B (en) | Method for carrying out live monitoring and state identification on mechanical characteristics of high-voltage circuit breaker | |
| CN114167315A (en) | Intelligent online monitoring system and method for transformer | |
| CN116359597B (en) | Method and device for measuring lightning parameters by medium-voltage switch | |
| CN116383633A (en) | Method and system for detecting faults of machine-made sand vibrating screen through multi-factor comprehensive analysis | |
| CN116449256A (en) | Transformer state fault diagnosis system and method based on voiceprint sensing | |
| CN105699866B (en) | The method for detecting rail traffic insulating element using UV corona technology | |
| CN107037314A (en) | A kind of winding deformation of power transformer on-line fault diagnosis method | |
| CN111693829A (en) | Partial discharge noise and discharge distinguishing method for non-contact ultrasonic detection | |
| CN105866645B (en) | A kind of method and device diagnosing generator discharge failure using noise characteristic frequency range | |
| CN117153193B (en) | Power equipment fault voiceprint recognition method integrating physical characteristics and data diagnosis | |
| CN118380013A (en) | Switch cabinet monitoring and fault diagnosis method based on voiceprint recognition technology | |
| CN117607598A (en) | Transformer fault detection method and system based on voiceprint characteristics | |
| CN116840631A (en) | Transformer partial discharge monitoring and positioning method based on joint diagnosis model | |
| CN116381380A (en) | Dynamic fault supervision system for intelligent substation fault recorder | |
| CN114878118A (en) | Transformer sound and vibration signal fusion detection method and system |
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 |