CN114091524A - Inverter fault early warning system and method - Google Patents
Inverter fault early warning system and method Download PDFInfo
- Publication number
- CN114091524A CN114091524A CN202111203770.2A CN202111203770A CN114091524A CN 114091524 A CN114091524 A CN 114091524A CN 202111203770 A CN202111203770 A CN 202111203770A CN 114091524 A CN114091524 A CN 114091524A
- Authority
- CN
- China
- Prior art keywords
- inverter
- data
- signal
- fault
- early warning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 40
- 230000005540 biological transmission Effects 0.000 claims abstract description 17
- 230000015654 memory Effects 0.000 claims description 30
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 7
- 230000017525 heat dissipation Effects 0.000 abstract description 21
- 238000004140 cleaning Methods 0.000 abstract description 13
- 238000010248 power generation Methods 0.000 abstract description 13
- 230000008901 benefit Effects 0.000 abstract description 10
- 238000009423 ventilation Methods 0.000 abstract description 10
- 238000007689 inspection Methods 0.000 abstract description 8
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 17
- 239000000428 dust Substances 0.000 description 12
- 238000004891 communication Methods 0.000 description 10
- 230000008021 deposition Effects 0.000 description 10
- 238000012423 maintenance Methods 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000009434 installation Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000001816 cooling Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 108010015780 Viral Core Proteins Proteins 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention discloses a system and a method for early warning inverter faults, wherein the system comprises the following steps: the system comprises an information acquisition device, a transmission device and a signal processing device, wherein the information acquisition device is arranged at an air outlet of an inverter and used for acquiring operation data of the inverter and transmitting the operation data to the transmission device; the transmission device is used for identifying the received operation data and sending the identification data to the signal processing device; the signal processing device is used for carrying out signal processing on the received identification data, determining the characteristic signals, comparing the characteristic signals by using the prediction model and determining the early warning signals. The system has the advantages that the system is simple and convenient to install and low in cost by acquiring audio and temperature data and the like of the inverter in operation in real time, the regular inspection and cleaning modes of the traditional inverter are thoroughly changed, the real-time monitoring of the ventilation and heat dissipation state of the inverter is realized, the power generation loss caused by faults of the inverter is reduced, the fault downtime of the inverter can be effectively reduced, and the availability of the inverter is improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an inverter fault early warning system and method.
Background
Two major core devices of a grid-connected photovoltaic power station are a photovoltaic module and an inverter, the inverter is a device for converting direct current generated by the photovoltaic module into alternating current, and generally, the inverter has no redundancy capability, and if the inverter fails and stops working, the whole photovoltaic array stops generating electricity, so that serious power generation loss is caused. At present, large grid-connected photovoltaic power stations are often built in desert and unmanned areas, and due to the fact that the number of inverters is large, operation and maintenance personnel are limited, the inverters are not maintained timely, the generated energy of the photovoltaic power stations is seriously influenced, and even more serious problems are caused.
Disclosure of Invention
In view of this, embodiments of the present invention provide an inverter fault early warning system and method, which solve the problem of power generation fault caused by untimely maintenance of the existing inverter.
According to a first aspect, an embodiment of the present invention provides an inverter fault early warning system, including: information acquisition device, transmission device and signal processing device, wherein:
the information acquisition device is arranged at an air outlet of the inverter and used for acquiring the operation data of the inverter and sending the operation data to the transmission device;
the transmission device is used for identifying the received operating data and sending the identifying data to the signal processing device;
the signal processing device is used for carrying out signal processing on the received identification data, determining a characteristic signal, comparing the characteristic signal by using a prediction model and determining an early warning signal.
The inverter fault early warning system provided by the embodiment of the invention has the advantages of simple and convenient installation and low cost by acquiring the audio frequency, temperature data and the like of the inverter during operation in real time, thoroughly changes the regular inspection and cleaning mode of the traditional inverter, realizes the real-time monitoring of the ventilation and heat dissipation state of the inverter, realizes the intelligent identification of the operation fault classification and abnormal operation state of the inverter by using the difference of the audio frequency and the temperature signal before and after the fault, early warns in advance to find the potential fault of ventilation and heat dissipation of the inverter, switches the passive overhaul and the cleaning after the fault into the advanced prejudgment overhaul and the cleaning before the fault, not only can reduce the power generation loss of the inverter caused by insufficient heat dissipation due to dust deposition, and the fault downtime of the inverter can be effectively reduced, and the availability of the inverter is improved, so that the power generation benefit of the photovoltaic power station is improved.
With reference to the first aspect, in a first implementation manner of the first aspect, the information acquisition apparatus includes: an audio collector and a temperature sensor, wherein,
the audio collector is used for collecting the running audio data of the inverter;
the temperature sensor is used for acquiring the operation temperature data of the inverter.
With reference to the first embodiment of the first aspect, in a second embodiment of the first aspect, the signal processing apparatus includes: a processor, a database, and a server, wherein,
the database is used for storing the operation data and establishing a prediction model according to the operation data;
the processor is used for carrying out signal processing on the received operation data and determining a characteristic signal;
the processor is further used for calling the corresponding prediction model according to the characteristic signal, determining a prediction result and sending the prediction result to the server;
and the server determines a corresponding early warning signal according to the prediction result.
With reference to the second embodiment of the first aspect, in a third embodiment of the first aspect,
the processor is used for carrying out sound pressure conversion on the received audio data and determining an audio characteristic signal;
the processor is used for carrying out discrete rate conversion on the received temperature data and determining a temperature characteristic signal.
According to a second aspect, an embodiment of the present invention provides an inverter fault early warning method, including:
acquiring operation data of an inverter;
performing signal processing on the operating data to determine a characteristic signal;
and acquiring a prediction model, comparing the characteristic signals by using the prediction model, and determining an early warning signal.
The inverter fault early warning method provided by the embodiment of the invention has the advantages of simple and convenient installation and low cost by acquiring the audio frequency, temperature data and the like of the inverter during operation in real time, thoroughly changes the regular inspection and cleaning mode of the traditional inverter, realizes the real-time monitoring of the ventilation and heat dissipation state of the inverter, realizes the intelligent identification of the operation fault classification and abnormal operation state of the inverter by using the difference of the audio frequency and the temperature signal before and after the fault, early warns in advance to find the potential fault of ventilation and heat dissipation of the inverter, switches the passive overhaul and the cleaning after the fault into the advanced prejudgment overhaul and the cleaning before the fault, not only can reduce the power generation loss of the inverter caused by insufficient heat dissipation due to dust deposition, and the fault downtime of the inverter can be effectively reduced, and the availability of the inverter is improved, so that the power generation benefit of the photovoltaic power station is improved.
With reference to the second aspect, in a first embodiment of the second aspect, the obtaining a prediction model includes:
acquiring a standard signal of the inverter;
comparing the signature signal to the standard signal to determine a fault signature signal;
and establishing the prediction model by utilizing each fault characteristic signal.
With reference to the second aspect, in a second embodiment of the second aspect, the method further includes:
updating the signature signal with the operational data;
and updating the prediction model through the updated characteristic signal.
According to a third aspect, an embodiment of the present invention provides an electronic device, including: the inverter fault early warning method comprises a memory and a processor, wherein the memory and the processor are connected in a communication mode, the memory stores computer instructions, and the processor executes the computer instructions so as to execute the inverter fault early warning method in the second aspect or any one implementation mode of the second aspect.
According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the inverter fault early warning method described in the second aspect or any one of the implementation manners of the second aspect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic diagram of a grid-connected photovoltaic power plant main plant connection of a centralized inverter according to an embodiment of the invention;
fig. 2 is an internal configuration diagram of a centralized inverter according to a preferred embodiment of the present invention;
fig. 3 is a diagram of an inverter compartment and an air-exhaust heat-dissipation system configuration of an inverter according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an inverter fault warning system according to an embodiment of the invention;
FIG. 5 is a front view of an acquisition device mounting location according to an embodiment of the present invention;
FIG. 6 is a top view of an acquisition device installation location according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a data transmission path according to an embodiment of the present invention;
FIG. 8 is an inverter fault warning system architecture diagram according to an embodiment of the present invention;
FIG. 9 is a diagram of an inverter fault warning system software architecture according to an embodiment of the present invention;
fig. 10 is a flowchart of an inverter fault warning method according to an embodiment of the present invention;
fig. 11 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Two major core devices of a grid-connected photovoltaic power station are a photovoltaic module and an inverter, the inverter is a device for converting direct current generated by the photovoltaic module into alternating current, wherein the inverter is further divided into a centralized inverter and a string-type inverter, the embodiment mainly takes the centralized inverter as an example for explanation, a main device connection diagram of the grid-connected photovoltaic power station adopting the centralized inverter is shown in fig. 1, and the centralized inverter generally comprises: (1) the system topology structure adopts a mode that a DC-AC primary power electronic device transforms a full-bridge inversion and a power frequency isolation transformer; (2) the power device adopts a large-current IGBT, so that the loss of the device is large, and the temperature of equipment needs to be ensured in a forced cooling mode; (3) the protection grade is generally IP20, the volume is large, and the indoor vertical installation is realized; (4) generally, single-path Maximum Power Point Tracking (MPPT) tracking is adopted, group string voltage differences caused by abnormal shielding of components, group string distance differences, component delivery power differences, inconsistent component attenuation and other reasons may generate mutual interference of group string MPPT voltage tracking, and have a certain influence on the overall power generation amount of a photovoltaic array, and the total capacity of one photovoltaic array is usually 1MW or more.
In addition to the fact that the centralized inverter is precise in design and complex in structure, the internal structure of the common centralized inverter is shown in fig. 2, once a complex fault occurs, a professional must detect and maintain, related parts of the inverter are large in size and heavy in weight, and the period from fault finding to fault positioning to fault removing is long.
The centralized inverter is generally arranged in an inverter room or a special container, the temperature rise of the centralized inverter is higher than that of a group of serial inverters, the temperature in the special container or the inverter room is always higher than 50 ℃ in hot summer, the temperature in a cabinet body of the centralized inverter (the normal operating temperature range is minus 30 ℃ to 55 ℃) is higher and worse, the service life of components of the inverter is shortened due to high temperature, the capacity of the whole inverter is reduced, and even the hidden danger of machine explosion exists in extreme cases.
Also provided in the present embodiment is an inverter fault warning system, and as used below, the term "module" may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
The present embodiment provides an inverter fault early warning system, wherein, the internal heat extraction fan that is equipped with of centralized inverter cabinet, the heat that the inverter operation produced is organized and is discharged the inverter outdoor through special wind channel to guarantee that the inverter is in normal temperature operating range all the time. The conventional inverter room and the air-discharge heat-dissipation system of the inverter are constructed as shown in fig. 3. The cooling fan of the prior centralized inverter is controlled by a special temperature control module of an inverter measurement and control system, the cooling fan is automatically started after the temperature reaches a set value, the heat of the inverter is discharged through a special air duct, an air outlet of an inverter cabinet is generally rectangular or circular, and a waterproof bend and an insect-proof net are arranged.
The large grid-connected photovoltaic power station is often built in a desert and an unmanned area, because the number of inverters is large, operation and maintenance personnel are limited, if the inverters are not cleaned timely, heat dissipation is not timely easily caused by excessive dust accumulation of IGBT modules, heat dissipation fans and the like, so that the conversion efficiency of a centralized inverter is reduced, and when the inverter is seriously stopped, the inverter is triggered to protect due to overhigh operation temperature; in addition, because the coverage area of the centralized photovoltaic power station is large, when operation and maintenance personnel observe an inverter operation temperature alarm signal through the monitoring system and go to the inverter operation site for inspection and maintenance, the inverter is likely to stop working, which will seriously affect the power generation amount of the photovoltaic power station, and in addition, the problem of high-temperature tripping caused by the early unreasonable ventilation and heat dissipation design of the centralized inverter commonly exists in old photovoltaic power stations. The following table specifies the problems and handling of the inverter.
Table 1 description of temperature protection function of centralized inverter
TABLE 2 description of the routine maintenance of the centralized inverter
TABLE 3 common Fault and handling measures for centralized inverters
According to relevant data and on-site actual operation observation statistics of the photovoltaic power station, the centralized inverter does not have large vibration or abnormal noise when normally working, if the centralized inverter is abnormal, the power failure inspection should be carried out in time, and in addition, the difference range between the temperature of an air outlet of the inverter and the operation temperature of the inverter when the centralized inverter normally works is limited, if the difference is large, the shutdown inspection should be carried out in time.
The invention discloses an inverter fault early warning system, as shown in fig. 4, comprising: an information acquisition device 1, a transmission device 3 and a signal processing device 4, wherein,
the information acquisition device 1 is arranged at an air outlet of the inverter 2 and used for acquiring the operation data of the inverter 2 and sending the operation data to the transmission device 3; the transmission device 3 is used for identifying the received operation data and sending the identification data to the signal processing device 4; the signal processing device 4 is used for performing signal processing on the received identification data, determining a characteristic signal, comparing the characteristic signal by using a prediction model, and determining an early warning signal.
Specifically, the information acquisition apparatus 1 includes: the system comprises an audio collector and a temperature sensor, wherein the audio collector (radio) is used for collecting the running audio data of the inverter 2; the temperature sensor is used to acquire operating temperature data of the inverter 2. The audio acquisition device and the temperature sensor are arranged in an embedded mode in an air outlet channel of a heat dissipation air channel of the centralized inverter 2, the installation positions are shown in a front view of fig. 5 and a top view of fig. 6, fixed acquisition of operating audio data and temperature data of the inverter 2 can be achieved, wherein 30S data (configurable) and 10M data (configurable) are acquired each time when the cooling fan operates.
In another embodiment, the signal processing device 4 includes: the system comprises a processor, a database and a server, wherein the database is used for storing operation data and establishing a prediction model according to the operation data; the processor is used for processing the received operation data to determine a characteristic signal; the processor is also used for calling the corresponding prediction model according to the characteristic signal, determining a prediction result and sending the prediction result to the server; and the server determines a corresponding early warning signal according to the prediction result. The processor is used for carrying out sound pressure conversion on the received audio data and determining an audio characteristic signal; the processor is used for carrying out discrete rate conversion on the received temperature data and determining a temperature characteristic signal.
It should be noted that transmission paths and processing manners of the operation data of the temperature sensor and the audio collector, the inverter data and the ambient temperature data read by the third transmission system are shown in fig. 7.
(1) The temperature sensor and the audio collector are used for collecting temperature information and audio information, and the intelligent processing unit is used for carrying out sound pressure conversion and band-pass filtering on audio to finish collection and primary processing of temperature and audio data.
(2) And uploading the temperature and audio data to a server of a photovoltaic power station (central control room), performing short-time Fourier transform on the target audio, and processing the corresponding audio signal into a frequency domain graph and an energy graph.
Wherein, an audio frequency domain graph and an energy graph of a large number (at least 6) of inverters 2 in the same station and the same batch in normal operation are collected as standard bases; reading the fault information of the inverter 2 and the audio frequency domain diagram and the energy diagram corresponding to the front and the back of the fault through a third-party system, taking the audio frequency domain diagram, the energy diagram and other sound characteristics before the fault occurs as early warning signals, and early warning the fault of the inverter 2 in advance once the inverter 2 acquires the similar audio frequency domain diagram and the energy diagram again; and repeating the operation until the audio signal characteristics of the common faults of the inverter 2 are extracted, and forming a fault early warning data model of the inverter 2. And reading fault information of other inverters 2 and data change conditions such as IGBT operating temperature before and after the fault, inverter 2 operating temperature, active power, inverter 2 conversion efficiency and the like from a third-party system.
(3) And related modules are deployed on a photovoltaic power station (central control room) server to complete data transmission from the photovoltaic power station to the cloud server.
(4) And calling the service of the cloud to store the processed data to a data platform, and performing deep learning of a corresponding algorithm and updating of a model based on the platform.
In the embodiment of the present invention, the system principle and the system architecture are as shown in fig. 8: collection end (terminal): intelligent processing unit, temperature sensor and audio collector. The intelligent processing unit collects real-time data of the temperature sensor and the audio collector, collects front-end data according to a plan, carries out specific data processing (such as temperature dispersion rate, band-pass filtering and the like), and correspondingly outputs temperature data of a heat dissipation air duct of the inverter 2 and operation audio data of the inverter 2 to a server of a photovoltaic power station (central control room) through communication looped network transmission of the photovoltaic power station.
The server side: the system comprises an algorithm management system, a database service system and a WEB server system. The algorithm management system manages audio processing algorithm scheduling and post-algorithm processing. And after receiving the audio data, the algorithm management system calls a corresponding algorithm to process, the audio data pre-judges common faults in advance according to a corresponding fault data model, the subsequent audio data calls a corresponding algorithm, a oscillogram, a frequency spectrum, a time domain graph and a matching model are analyzed, and the audio frequency domain graph before and after the faults and the energy graph are output to be compared.
And forming fault big data as mass fault data enter the database, and performing further modeling and deep learning by using the data again to form a more compact model database.
Wherein the audio collector is an audio collecting sensor; the intelligent processing unit is responsible for audio data acquisition, preprocessing and sending. The centralized photovoltaic inverter 2 dust deposition fault early warning system is mainly based on collected inverter 2 operation sound data, temperature data, relevant (inverter 2 operation temperature, power, environment temperature and the like) data in the process operation of the inverter 2 and other inverter 2 same type data, combines a time domain and frequency domain analysis method to perform characteristic engineering, and combines a machine learning algorithm to realize detection and classification of inverter 2 operation abnormity.
As shown in fig. 9, the centralized photovoltaic inverter 2 dust deposition fault early warning system undertakes the tasks of information interaction with the operation of the inverter 2, audio data storage and processing, real-time audio data display, pre-judgment of the dust deposition degree of the inverter 2 (when the inverter 2 has serious dust deposition, although the inverter 2 cannot report the fan operation fault, the sound of the inverter 2 operation is lower than the recorded historical normal operation sound of the inverter 2, the audio frequency domain graph and the energy graph have obvious changes, in addition, the heat dissipation capability of the inverter 2 has serious dust deposition, the conversion efficiency of the inverter 2 is also reduced due to the temperature rise of the inverter 2), equipment fault early warning and pushing, and the like, provides a friendly operation interface for users, and is a terminal for machine learning and algorithm configuration.
Through the top-level design of the software architecture, the software can control the audio collector to collect corresponding audio data according to different task requirements, continuous improvement of system functions can be realized through continuous upgrading and optimization of the fault identification module, and meanwhile, a corresponding database is established to store data for self-optimization of the system. The blade audio-visual and temperature monitoring system is used for monitoring the health state of the inverters 2, and the audio display interface can click the audio playing fixedly collected by each inverter 2 of the photovoltaic power station to listen to the running sound of the inverters 2. The audio processing results can also be viewed: a frequency domain plot and an energy plot.
The inverter fault early warning system provided by the embodiment of the invention has the advantages of simple and convenient installation and low cost by acquiring the audio frequency, temperature data and the like of the inverter during operation in real time, thoroughly changes the regular inspection and cleaning mode of the traditional inverter, realizes the real-time monitoring of the ventilation and heat dissipation state of the inverter, realizes the intelligent identification of the operation fault classification and abnormal operation state of the inverter by using the difference of the audio frequency and the temperature signal before and after the fault, early warns in advance to find the potential fault of ventilation and heat dissipation of the inverter, switches the passive overhaul and the cleaning after the fault into the advanced prejudgment overhaul and the cleaning before the fault, not only can reduce the power generation loss of the inverter caused by insufficient heat dissipation due to dust deposition, and the fault downtime of the inverter can be effectively reduced, and the availability of the inverter is improved, so that the power generation benefit of the photovoltaic power station is improved.
The embodiment provides an inverter fault early warning method, which can be used for electronic equipment such as a computer, a mobile phone, a tablet computer and the like. Fig. 10 is a flowchart of an inverter fault warning method according to an embodiment of the present invention, and as shown in fig. 10, the flowchart includes the following steps:
and S11, acquiring the operation data of the inverter.
In the embodiment, the operation audio data of the inverter is acquired through the audio collector, and the operation temperature data of the inverter is acquired by using the temperature sensor. The real-time performance and the accuracy of the data are guaranteed.
And S12, performing signal processing on the operation data to determine a characteristic signal.
In this embodiment, the sampling frequency, the data integrity, the operation condition of the inverter, and the like are mainly considered, and feature extraction is performed through time domain and frequency domain analysis based on the sound data of the inverter operation. And (5) combining a time domain and frequency domain analysis method to carry out characteristic engineering.
And S13, acquiring the prediction model, comparing the characteristic signals by using the prediction model, and determining the early warning signal.
Wherein obtaining the prediction model comprises: acquiring a standard signal of an inverter; comparing the characteristic signal with a standard signal to determine a fault characteristic signal; and establishing a prediction model by using each fault characteristic signal.
The prediction model includes: a no fault model and a fault model. A fault-free model: calculating the dust deposition degree of the inverters according to the difference of the operation sounds of the inverters in the same power station and the same batch; failure model: and training the machine learning classification model based on time domain and frequency domain characteristics, such as audio characteristic extraction and judgment before and after the occurrence of common faults of the inverter.
The audio analysis of the centralized photovoltaic inverter dust deposition fault early warning system is to convert audio data of a time domain into a frequency spectrum diagram of a frequency domain, identify frequency spectrum abnormality through an algorithm, judge an impending fault of an inverter and generate early warning. Several inverter faults can be extracted and identified at present, and table 4 shows inverter operation sound feature extraction data.
Table 4 inverter operation sound characteristic extraction table
The inverter fault early warning method provided by the embodiment has the advantages that the audio frequency, the temperature data and the like during the operation of the inverter are collected in real time, the installation is simple and convenient, the cost is low, the regular inspection and cleaning mode of the traditional inverter is thoroughly changed, the real-time monitoring of the ventilation and heat dissipation state of the inverter is realized, the intelligent identification of the inverter operation fault classification and the abnormal operation state is realized by utilizing the difference of the audio frequency and the temperature signal before and after the fault, the ventilation and heat dissipation potential fault of the inverter is found by early warning in advance, the later passive maintenance and cleaning of the fault are switched to the advanced prejudgment maintenance and cleaning before the fault occurs, the power generation loss caused by insufficient heat dissipation of accumulated dust and the fault of the inverter can be reduced, the fault downtime of the inverter can be effectively reduced, the availability of the inverter is improved, and the power generation benefit of a photovoltaic power station is improved.
An embodiment of the present invention further provides an electronic device, please refer to fig. 11, where fig. 11 is a schematic structural diagram of an electronic device according to an alternative embodiment of the present invention, and as shown in fig. 11, the electronic device may include: at least one processor 601, such as a CPU (Central Processing Unit), at least one communication interface 603, memory 604, and at least one communication bus 602. Wherein a communication bus 602 is used to enable the connection communication between these components. The communication interface 603 may include a Display (Display) and a Keyboard (Keyboard), and the optional communication interface 603 may also include a standard wired interface and a standard wireless interface. The Memory 604 may be a random access Memory (random-access Memory) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The memory 604 may optionally be at least one storage device located remotely from the processor 601. Wherein the processor 601 may be in connection with the apparatus described in fig. 5, an application program is stored in the memory 604, and the processor 601 calls the program code stored in the memory 604 for performing any of the above-mentioned method steps.
The communication bus 602 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 602 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 11, but this is not intended to represent only one bus or type of bus.
The memory 604 may include a volatile memory (RAM), such as a random-access memory (RAM); the memory may also include a non-volatile memory (english: non-volatile memory), such as a flash memory (english: flash memory), a hard disk (english: hard disk drive, abbreviated: HDD) or a solid-state drive (english: SSD); the memory 604 may also comprise a combination of the above types of memory.
The processor 601 may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of a CPU and an NP.
The processor 601 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof.
Optionally, the memory 604 is also used for storing program instructions. The processor 601 may call program instructions to implement the inverter fault warning method as shown in the embodiments of the present disclosure.
The embodiment of the invention also provides a non-transitory computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the inverter fault early warning method in any method embodiment. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (9)
1. An inverter fault early warning system, comprising: information acquisition device, transmission device and signal processing device, wherein:
the information acquisition device is arranged at an air outlet of the inverter and used for acquiring the operation data of the inverter and sending the operation data to the transmission device;
the transmission device is used for identifying the received operating data and sending the identifying data to the signal processing device;
the signal processing device is used for carrying out signal processing on the received identification data, determining a characteristic signal, comparing the characteristic signal by using a prediction model and determining an early warning signal.
2. The system of claim 1, wherein the information gathering device comprises: an audio collector and a temperature sensor, wherein,
the audio collector is used for collecting the running audio data of the inverter;
the temperature sensor is used for acquiring the operation temperature data of the inverter.
3. The system of claim 2, wherein the signal processing means comprises: a processor, a database, and a server, wherein,
the database is used for storing the operation data and establishing a prediction model according to the operation data;
the processor is used for carrying out signal processing on the received operation data and determining a characteristic signal;
the processor is further used for calling the corresponding prediction model according to the characteristic signal, determining a prediction result and sending the prediction result to the server;
and the server determines a corresponding early warning signal according to the prediction result.
4. The system of claim 3, comprising:
the processor is used for carrying out sound pressure conversion on the received audio data and determining an audio characteristic signal;
the processor is used for carrying out discrete rate conversion on the received temperature data and determining a temperature characteristic signal.
5. An inverter fault early warning method is characterized by comprising the following steps:
acquiring operation data of an inverter;
performing signal processing on the operating data to determine a characteristic signal;
and acquiring a prediction model, comparing the characteristic signals by using the prediction model, and determining an early warning signal.
6. The method of claim 5, wherein obtaining the predictive model comprises:
acquiring a standard signal of the inverter;
comparing the signature signal to the standard signal to determine a fault signature signal;
and establishing the prediction model by utilizing each fault characteristic signal.
7. The method of claim 5, further comprising:
updating the signature signal with the operational data;
and updating the prediction model through the updated characteristic signal.
8. An electronic device, comprising:
a memory and a processor, wherein the memory and the processor are communicatively connected with each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the inverter fault pre-warning method according to any one of claims 5 to 7.
9. A computer-readable storage medium storing computer instructions for causing a computer to execute the inverter fault warning method according to any one of claims 5 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111203770.2A CN114091524A (en) | 2021-10-15 | 2021-10-15 | Inverter fault early warning system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111203770.2A CN114091524A (en) | 2021-10-15 | 2021-10-15 | Inverter fault early warning system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114091524A true CN114091524A (en) | 2022-02-25 |
Family
ID=80297001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111203770.2A Pending CN114091524A (en) | 2021-10-15 | 2021-10-15 | Inverter fault early warning system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114091524A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116380176A (en) * | 2023-05-29 | 2023-07-04 | 深圳市百事泰电气有限公司 | Load early warning system of inverter based on digital signal processing |
| CN117728588A (en) * | 2024-02-07 | 2024-03-19 | 华能江苏综合能源服务有限公司 | Inverter state monitoring method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105785174A (en) * | 2016-03-11 | 2016-07-20 | 深圳茂硕电气有限公司 | Intelligent fault detection and data storage system for photovoltaic inverter |
| CN108695889A (en) * | 2018-06-04 | 2018-10-23 | 中山市厚源电子科技有限公司 | A kind of high-efficiency photovoltaic inverter for sharing O&M |
| CN108847686A (en) * | 2018-07-02 | 2018-11-20 | 国电南瑞科技股份有限公司 | A kind of photovoltaic DC-to-AC converter failure prediction method |
| CN109245305A (en) * | 2018-10-24 | 2019-01-18 | 九州能源有限公司 | A kind of photovoltaic plant automatic early-warning cloud platform and system |
| CN109389104A (en) * | 2018-11-30 | 2019-02-26 | 浙江碳银互联网科技有限公司 | A kind of family photovoltaic plant fault of converter prediction technique |
| KR20190044232A (en) * | 2017-10-20 | 2019-04-30 | 한국전력공사 | apparatus an dmethod for fault detection of power converter apparatus for controlling speed using aucoustic signals |
| CN111178423A (en) * | 2019-12-25 | 2020-05-19 | 国网电子商务有限公司 | Fault early warning method and device |
-
2021
- 2021-10-15 CN CN202111203770.2A patent/CN114091524A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105785174A (en) * | 2016-03-11 | 2016-07-20 | 深圳茂硕电气有限公司 | Intelligent fault detection and data storage system for photovoltaic inverter |
| KR20190044232A (en) * | 2017-10-20 | 2019-04-30 | 한국전력공사 | apparatus an dmethod for fault detection of power converter apparatus for controlling speed using aucoustic signals |
| CN108695889A (en) * | 2018-06-04 | 2018-10-23 | 中山市厚源电子科技有限公司 | A kind of high-efficiency photovoltaic inverter for sharing O&M |
| CN108847686A (en) * | 2018-07-02 | 2018-11-20 | 国电南瑞科技股份有限公司 | A kind of photovoltaic DC-to-AC converter failure prediction method |
| CN109245305A (en) * | 2018-10-24 | 2019-01-18 | 九州能源有限公司 | A kind of photovoltaic plant automatic early-warning cloud platform and system |
| CN109389104A (en) * | 2018-11-30 | 2019-02-26 | 浙江碳银互联网科技有限公司 | A kind of family photovoltaic plant fault of converter prediction technique |
| CN111178423A (en) * | 2019-12-25 | 2020-05-19 | 国网电子商务有限公司 | Fault early warning method and device |
Non-Patent Citations (1)
| Title |
|---|
| 柯思勤;: "永磁电机故障诊断和容错技术概述", 大功率变流技术, no. 02, 5 April 2017 (2017-04-05) * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116380176A (en) * | 2023-05-29 | 2023-07-04 | 深圳市百事泰电气有限公司 | Load early warning system of inverter based on digital signal processing |
| CN116380176B (en) * | 2023-05-29 | 2023-08-29 | 深圳市百事泰电气有限公司 | Load early warning system of inverter based on digital signal processing |
| CN117728588A (en) * | 2024-02-07 | 2024-03-19 | 华能江苏综合能源服务有限公司 | Inverter state monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111306008B (en) | Fan blade detection method, device, equipment and storage medium | |
| CN109146093B (en) | Power equipment field investigation method based on learning | |
| CN114091524A (en) | Inverter fault early warning system and method | |
| CN108011584B (en) | Photovoltaic cell on-line monitoring and intelligent management system | |
| US10337502B2 (en) | Early detection of wind turbine degradation using acoustical monitoring | |
| KR102410027B1 (en) | Method for diagnosing fault of photovoltaic system and apparatus thereof | |
| CN102434387A (en) | Draught fan detection and diagnosis system | |
| CN208459507U (en) | Arrester online monitoring system | |
| CN104821789A (en) | Method for detecting reliability of photovoltaic power generation system | |
| JP7289995B2 (en) | Method and apparatus for recognizing operating state of photovoltaic string and storage medium | |
| KR20190069213A (en) | Apparatus and method for operation and management of distributed photovoltaic energy generator based on remote monitoring | |
| CN111555776B (en) | Fusion sensing and joint diagnosis method, system and device for power transmission line | |
| CN112180865A (en) | Intelligent distribution room and equipment monitoring system | |
| CN105004967A (en) | Power grid fault detection method and system | |
| CN212539271U (en) | Condensation water immersion alarm | |
| CN113992151A (en) | Method, device and equipment for determining working state of photovoltaic array and storage medium | |
| CN114675584A (en) | Power equipment monitoring device and monitoring system based on big data analysis | |
| CN103728942A (en) | Local data collecting and processing system of wind generating set | |
| CN111400959B (en) | Blade fault diagnosis method and device for wind generating set | |
| JP2004265009A (en) | Diagnostic system | |
| CN113254301A (en) | Method and system for detecting running state of steel production equipment | |
| CN102891443A (en) | Application management system for infrared detection of electric transmission and transformation equipment | |
| CN1665088A (en) | Digital diagrammatic view switch apparatus system | |
| CN111092598A (en) | Intelligent operation and maintenance method for photovoltaic power generation system | |
| CN117252729B (en) | Photovoltaic power station management method and system based on big data |
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 |