CN111371405A - Photovoltaic power station fault detection system and machine learning fault detection method - Google Patents
Photovoltaic power station fault detection system and machine learning fault detection method Download PDFInfo
- Publication number
- CN111371405A CN111371405A CN202010325655.1A CN202010325655A CN111371405A CN 111371405 A CN111371405 A CN 111371405A CN 202010325655 A CN202010325655 A CN 202010325655A CN 111371405 A CN111371405 A CN 111371405A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic
- power plant
- photovoltaic power
- fault detection
- photovoltaic panel
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000010801 machine learning Methods 0.000 title claims description 20
- 238000012549 training Methods 0.000 claims description 23
- 238000000034 method Methods 0.000 claims description 13
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 4
- 239000004576 sand Substances 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 description 7
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
- H02S50/10—Testing of PV devices, e.g. of PV modules or single PV cells
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a photovoltaic power station fault detection system, which comprises: photovoltaic board group cluster, photovoltaic inverter and host computer, every photovoltaic board group cluster corresponds a photovoltaic inverter, and every photovoltaic inverter and a photovoltaic board group cluster electrical connection, photovoltaic inverter and host computer electrical connection still include: the lower computer is electrically connected with the upper computer; the photovoltaic power plant map is marked with all photovoltaic panel group string positions; the display device is connected with the corresponding display device at the position of the photovoltaic panel group string on the photovoltaic power plant map, and the display device is electrically connected with the lower computer. The problems that fault early warning is not timely, early warning information needs to be judged by a person, an early warning mode is not visual enough and a prediction result error is large in the prior art are solved.
Description
Technical Field
The invention relates to the technical field of photovoltaic equipment, in particular to a photovoltaic power station fault detection system and a machine learning fault detection method.
Background
The photovoltaic panels of the photovoltaic power plant often break down in the operation process to cause that power cannot be generated or the generated energy is low, in order to ensure the high-efficiency operation of the photovoltaic power plant, the corresponding photovoltaic panels need to be found in time and quickly to facilitate maintenance, the number of the photovoltaic panels of the photovoltaic power plant is huge, and the photovoltaic panels with faults need to be found quickly and is not easy. The photovoltaic panel fault judging method comprises the steps that whether a photovoltaic panel breaks down or not is judged by checking the current condition of a photovoltaic inverter corresponding to each photovoltaic panel string in the prior art, the photovoltaic panel fault judging method comprises the photovoltaic panel string, the photovoltaic inverter and a host, each photovoltaic panel string corresponds to one photovoltaic inverter, the number of photovoltaic panels of each photovoltaic panel string is the same, each photovoltaic panel string comprises 12 left and right photovoltaic panels, each photovoltaic inverter is electrically connected with one photovoltaic panel string, and the photovoltaic inverters are electrically connected with the host.
However, the problems that fault early warning is not timely, early warning information needs to be judged by people, the early warning mode is not visual enough and the error of a prediction result is large exist in the prior art, so that a fault photovoltaic panel is not timely found, and a photovoltaic power plant is in a low power generation efficiency state for a long time.
1) The reason that failure early warning is not timely, and early warning information needs human judgment and the early warning mode is not intuitive enough is that the search flow is too long, for example: when a fault photovoltaic panel needs to be checked, firstly, an inverter with a smaller current value is found manually, then a corresponding fault photovoltaic panel set string is found through an inverter code, and then the position of the fault photovoltaic panel set string is found through a photovoltaic power plant map;
2) the reason why the error of the prediction result is large is that the operation and maintenance personnel only judge whether the photovoltaic panel is in fault by checking the current magnitude, but the situation is much more complicated in reality, for example, a small dark cloud just covers some group strings, the group strings may have the problem of small current at this time, but the reason is not the photovoltaic panel fault, and if the photovoltaic panel is maintained on site due to the frequently-occurring non-fault reasons, a large amount of manpower is wasted;
3) different fault types can not be judged by checking the current, for example, the photovoltaic panel is shielded by sundries, the line fault of the photovoltaic panel and the damage of the photovoltaic panel, so that operation and maintenance personnel can not quickly and accurately carry out symptomatic medicine administration and maintenance.
Disclosure of Invention
In order to overcome the defects and shortcomings of the prior art, the invention mainly aims to provide a photovoltaic power station fault detection system and a machine learning fault detection method.
The technical scheme of the invention is as follows: a photovoltaic power plant fault detection system, comprising: photovoltaic board group cluster, photovoltaic inverter and host computer, every photovoltaic board group cluster corresponds a photovoltaic inverter, and every photovoltaic inverter and a photovoltaic board group cluster electrical connection, photovoltaic inverter and host computer electrical connection still include:
the lower computer is electrically connected with the upper computer;
the photovoltaic power plant map is marked with all photovoltaic panel group string positions;
the display device, photovoltaic board group cluster position department on the map of photovoltaic power plant all is connected with corresponding display device 7, and display device is in the next electromechanical connection.
Further, the photovoltaic power plant map is a sand table or a two-dimensional plane map;
the display device is an LED lamp;
the lower computer is an Arduino circuit board.
Further, still include:
and the display device is electrically connected with the lower level machine through the displacement buffer.
Further, the lower computer is communicated with the upper computer through a serial port.
Further, still include:
the transparent cover body covers the map of the photovoltaic power plant.
A method for detecting machine learning faults of a photovoltaic power station, the method comprising the steps of:
s01, collecting current value curves of photovoltaic inverters of fault photovoltaic panel group strings and non-fault photovoltaic panel group strings of different fault types in a time period t, and accordingly obtaining a training sample set;
s02, generating a classification prediction model from the training samples by using a machine learning algorithm;
s03, classifying current curve values of each current photovoltaic panel set string by using the classification prediction model every t time periods;
s04, outputting a classification result: the failure type or the quality of the photovoltaic panel group string is good;
s07, the upper computer sends the classification result of each photovoltaic panel group string to the lower computer;
and S08, the lower computer lights or extinguishes the corresponding display device according to the classification result of each photovoltaic panel group string.
Further, the machine learning algorithm comprises the steps of:
s021, determining a convolution layer and a pooling layer of an input current value curve;
s022, performing multi-feature extraction on the training samples through the convolutional layers, and extracting time domain features and frequency domain features of the training samples;
s023, inputting the extracted features into a maximum pooling layer, and then inputting the pooled features into a full-link layer for fault type classification.
Further, the t >60 minutes.
Further, the following steps are included between step S04 and step S07:
s05, judging whether the classification result of the photovoltaic panel group string 1 reaches expectation, if so, entering a step S07, otherwise, entering a step S06;
and S06, adding the current curve value with the wrong classification result into the training sample set, and repeating the steps S01 to S05.
The invention has the beneficial effects that: compared with the prior art, the method has the advantages that,
1) according to the invention, the display device is connected to the position of each photovoltaic string on the map of the photovoltaic power plant, the display is electrically connected with the lower computer, the lower computer receives the current information of the photovoltaic inverters on the upper computer and controls the display device corresponding to each photovoltaic inverter to be turned on and off, so that the fault information of the photovoltaic string is rapidly, automatically and visually displayed on the map, operation and maintenance personnel can conveniently and rapidly find the faulty photovoltaic string, and the power generation efficiency of the photovoltaic power plant is improved;
2) according to the invention, the state and the position of the photovoltaic panel string can be visually displayed through the sand table or the two-dimensional plane, so that the fault photovoltaic panel string can be conveniently and quickly found;
3) according to the invention, the position of the fault photovoltaic panel group string is displayed through the LED lamp, so that the price is low and the energy is saved;
4) the Arduino circuit board is used as the lower computer, the peripheral circuits of the Arduino circuit board are rich, the programming language is simple, the communication with the upper computer is easy, and the LED lamp switch is easy to control;
5) the display device is electrically connected with the lower computer through the displacement buffer, so that the number of the display devices controlled by the lower computer is increased, and one lower computer can control hundreds of display devices;
6) according to the invention, the lower computer and the upper computer are communicated through the serial port, so that the programming is simple, and the development cost is reduced;
7) according to the invention, the photovoltaic power plant map is covered by the cover body, so that the photovoltaic power plant map is protected from being contaminated by the ash layer, and the service life is prolonged;
8) the invention uses the current value curves of the photovoltaic inverters of the fault photovoltaic panel group string and the non-fault photovoltaic panel group string in t time period as training samples, trains the classification prediction model by using a machine learning algorithm, classifies the current value curve of each photovoltaic panel group string by using the classification prediction model every t time period to obtain the classification result of the state of the photovoltaic panel group string, the classification result is divided into different fault types and good, because the machine learning algorithm is adopted for training, the fault types and the current curves of the false faults can be identified in the training process, the machine can accurately identify which current curve corresponds to which fault type and which current curve corresponds to which good, thereby achieving the effect of reducing the fault identification error rate, the invention has the advantages of low fault identification error rate and can identify different fault types, the operation and maintenance personnel can quickly respond and quickly overhaul;
9) according to the invention, the time domain characteristics and the frequency domain characteristics of the current curve are extracted through the convolution layer, so that the correlation degree of real faults such as photovoltaic panel damage, circuit disconnection, impurity shielding and cloud shielding and pseudo faults is high, and the identification accuracy is higher; according to the method, overfitting is reduced by maximizing the amount of the pooled layer compression data and parameters, and the invariance of translation, rotation and scale of a current curve is ensured;
10) according to the invention, t is more than 60 minutes, and various random noises can be filtered for a longer time, so that the classification prediction model is more accurate;
11) the invention checks whether the result of the classification error exists through the steps S05 and S06, if so, the current curve and the result which judge the error are added into the training sample set to train the classification prediction model, so that the precision of the system is continuously improved in use.
Drawings
FIG. 1 is a schematic structural view of example 1 of the present invention;
FIG. 2 is a top view of example 1 of the present invention;
FIG. 3 is a circuit connection block diagram of embodiment 1 of the present invention;
FIG. 4 is a schematic diagram of the detection method of embodiment 1 of the present invention.
Detailed Description
The invention will be further described with reference to the following drawings and specific embodiments:
example 1: referring to fig. 1-4, a photovoltaic power plant fault detection system includes: photovoltaic board group cluster 1, photovoltaic inverter 2 and host computer 3, every photovoltaic board group cluster 1 corresponds a photovoltaic inverter 2, and every photovoltaic inverter 2 is connected with a photovoltaic board group cluster 1 electricity, and photovoltaic inverter 2 is connected with host computer 3 electricity, still includes: the lower computer 4 is electrically connected with the upper computer 3; the photovoltaic power plant map 6 is characterized in that the positions of all photovoltaic panel group strings 1 are marked on the photovoltaic power plant map 6; the display device 7 is connected with the corresponding display device 7 at the position of the photovoltaic panel group string 1 on the map 6 of the photovoltaic power plant, and the display device 7 is electrically connected with the lower computer 4.
The upper computer 3 may be a general-purpose computer or a server. When the photovoltaic panel set string is used, if the photovoltaic panel set string 1 breaks down, the current of the photovoltaic inverters 2 changes, the upper computer 3 receives the current of all the photovoltaic inverters 2, then the upper computer 3 judges the state of the photovoltaic panel set string 1 according to the current value, and the lower computer 4 opens or closes the corresponding display device 7 according to the state.
Further, the photovoltaic power plant map 6 is a sand table or a two-dimensional plane map.
Further, the display device 7 is an LED lamp.
Further, the lower computer 4 is an Arduino circuit board.
Further, still include: the displacement buffer 5 and the display device 7 are electrically connected with the lower computer 4 through the displacement buffer 5. The shift buffer 5 may be a 74HC595 chip.
Further, the lower computer 4 is communicated with the upper computer 3 through a serial port.
Further, still include: the transparent cover body 8 covers the map 6 of the photovoltaic power plant by the transparent cover body 8.
A method for detecting machine learning faults of a photovoltaic power station, the method comprising the steps of:
s01, collecting current value curves of the photovoltaic inverters 2 of the fault photovoltaic panel group string 1 and the non-fault photovoltaic panel group string 1 of different fault types in a time period t, and accordingly obtaining a training sample set;
s02, generating a classification prediction model from the training samples by using a machine learning algorithm;
s03, classifying the current curve values of each current photovoltaic panel group string 1 by using the classification prediction model every t time periods;
s04, outputting a classification result: the fault type of the photovoltaic panel group string 1 is good;
s05, the upper computer 3 sends the classification result of each photovoltaic panel group string 1 to the lower computer 4;
s06, the lower computer 4 turns on or off the corresponding display device 7 according to the classification result of each photovoltaic panel group string 1.
The invention uses the current value curves of the photovoltaic inverter 2 of the fault photovoltaic panel group string 1 and the non-fault photovoltaic panel group string 1 in the time period t as training samples, trains a classification prediction model by using a machine learning algorithm, classifies the current value curve of each photovoltaic panel group string 1 by using the classification prediction model every time period t to obtain the classification result of the state of the photovoltaic panel group string, wherein the classification result is divided into different fault types and good, because the machine learning algorithm is adopted for training, the current curves of different fault types and false faults can be identified in the training process, the machine can accurately identify which current curve corresponds to the fault type and which current curve corresponds to the good, thereby achieving the effect of reducing the fault identification error rate, the invention has the advantages of low fault identification error rate and can identify different fault types, so that the operation and maintenance personnel can quickly respond and quickly overhaul.
Further, the machine learning algorithm comprises the steps of:
s021, determining a convolution layer and a pooling layer of an input current value curve;
s022, performing multi-feature extraction on the training samples through the convolutional layers, and extracting time domain features and frequency domain features of the training samples;
s023, inputting the extracted features into a maximum pooling layer, and then inputting the pooled features into a full-link layer for fault type classification.
According to the invention, the time domain characteristics and the frequency domain characteristics of the current curve are extracted through the convolution layer, so that the correlation degree of faults or false faults such as damage to a photovoltaic panel, disconnection of a circuit, sundry shielding and black cloud shielding is high, and the identification accuracy is higher; the invention reduces overfitting by maximizing the amount of the pooled layer compression data and parameters, and ensures the invariance of translation, rotation and scale of the current curve.
Further, the t >60 minutes.
According to the invention, t is more than 60 minutes, and various random noises can be filtered for a longer time, so that the classification prediction model is more accurate.
Further, the following steps are included between step S04 and step S07:
s05, judging whether the classification result of the photovoltaic panel group string 1 reaches expectation, if so, entering a step S07, otherwise, entering a step S06;
and S06, adding the current curve value with the wrong classification result into the training sample set, and repeating the steps S01 to S05.
The invention checks whether the result of the classification error exists through the steps S05 and S06, if so, the current curve and the result which judge the error are added into the training sample set to train the classification prediction model, so that the precision of the system is continuously improved in use.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (9)
1. A photovoltaic power plant fault detection system, comprising: photovoltaic board group cluster (1), photovoltaic inverter (2) and host computer (3), every photovoltaic board group cluster (1) corresponds a photovoltaic inverter (2), and every photovoltaic inverter (2) is connected with a photovoltaic board group cluster (1) electricity, and photovoltaic inverter (2) and host computer (3) electricity are connected, its characterized in that still includes:
the lower computer (4), the lower computer (4) is electrically connected with the upper computer (3);
the photovoltaic power plant map (6), wherein the positions of all photovoltaic panel group strings (1) are marked on the photovoltaic power plant map (6);
the display device (7) and the position of the photovoltaic panel group string (1) on the photovoltaic power plant map (6) are connected with the corresponding display device (7), and the display device (7) is electrically connected with the lower computer (4).
2. The photovoltaic power plant fault detection system of claim 1, characterized in that the photovoltaic power plant map (6) is a sand table or a two-dimensional plane map;
the display device (7) is an LED lamp;
the lower computer (4) is an Arduino circuit board.
3. The photovoltaic power plant fault detection system of claim 1 or 2, further comprising:
the displacement buffer (5) and the display device (7) are electrically connected with the lower computer (4) through the displacement buffer (5).
4. The photovoltaic power plant fault detection system of claim 3 wherein the lower computer (4) communicates with the upper computer (3) via a serial port.
5. The photovoltaic power plant fault detection system of any of claims 1, 2, or 4, further comprising:
the transparent cover body (8), the transparent cover body (8) covers photovoltaic power plant map (6).
6. A method for detecting machine learning faults of a photovoltaic power station is characterized by comprising the following steps:
s01, collecting current value curves of the photovoltaic inverters (2) of the fault photovoltaic panel group string (1) and the non-fault photovoltaic panel group string (1) with different fault types in a time period t, and accordingly obtaining a training sample set;
s02, generating a classification prediction model from the training samples by using a machine learning algorithm;
s03, classifying current curve values of each current photovoltaic panel group string (1) by using the classification prediction model every t time periods;
s04, outputting a classification result: the photovoltaic panel group string (1) is failed or good;
s07, the upper computer (3) sends the classification result of each photovoltaic panel group string (1) to the lower computer (4);
s08, the lower computer (4) lights or extinguishes the corresponding display device (7) according to the classification result of each photovoltaic panel group string (1).
7. The machine learning based photovoltaic power plant unmanned aerial vehicle inspection method according to claim 6, wherein the machine learning algorithm comprises the steps of:
s021, determining a convolution layer and a pooling layer of an input current value curve;
s022, performing multi-feature extraction on the training samples through the convolutional layers, and extracting time domain features and frequency domain features of the training samples;
s023, inputting the extracted features into a maximum pooling layer, and then inputting the pooled features into a full-link layer for fault type classification.
8. The photovoltaic power plant machine learning fault detection method of claim 6 wherein t >60 minutes.
9. The photovoltaic power plant machine learning fault detection method of claim 6 further comprising, between steps S04 and S07, the steps of:
s05, judging whether the classification result of the photovoltaic panel group string (1) reaches expectation, if so, entering a step S07, otherwise, entering a step S06;
and S06, adding the current curve value with the wrong classification result into the training sample set, and repeating the steps S01 to S05.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010325655.1A CN111371405A (en) | 2020-04-22 | 2020-04-22 | Photovoltaic power station fault detection system and machine learning fault detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010325655.1A CN111371405A (en) | 2020-04-22 | 2020-04-22 | Photovoltaic power station fault detection system and machine learning fault detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111371405A true CN111371405A (en) | 2020-07-03 |
Family
ID=71211027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010325655.1A Pending CN111371405A (en) | 2020-04-22 | 2020-04-22 | Photovoltaic power station fault detection system and machine learning fault detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111371405A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785160A (en) * | 2021-01-25 | 2021-05-11 | 杭州易达光电有限公司 | Photovoltaic operation and maintenance management information display platform |
-
2020
- 2020-04-22 CN CN202010325655.1A patent/CN111371405A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785160A (en) * | 2021-01-25 | 2021-05-11 | 杭州易达光电有限公司 | Photovoltaic operation and maintenance management information display platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108062571B (en) | Photovoltaic array fault diagnosis method based on differential evolution random forest classifier | |
| CN109801284A (en) | A kind of high iron catenary insulator breakdown detection method based on deep learning | |
| CN106712713B (en) | The monitoring system and monitoring and abnormal localization method of a kind of photovoltaic plant | |
| CN105424395B (en) | Method and device for determining equipment fault | |
| CN106202886B (en) | Track circuit red band Fault Locating Method based on fuzzy coarse central and decision tree | |
| CN109660206B (en) | Wasserstein GAN-based photovoltaic array fault diagnosis method | |
| CN106526400B (en) | The earth fault diagnostic method and device of DC600V power supply system of train | |
| CN107766879A (en) | The MLP electric network fault cause diagnosis methods of feature based information extraction | |
| CN105159283A (en) | Remote fault analysis and feedback system of urban rail transit vehicle | |
| CN103699698A (en) | Method and system for track traffic failure recognition based on improved Bayesian algorithm | |
| CN109034220A (en) | A kind of intelligent photovoltaic array method for diagnosing faults based on optimal rotation forest | |
| CN110135302A (en) | Method, apparatus, equipment and the storage medium of training Lane detection model | |
| CN112115618A (en) | Power equipment fault diagnosis method and system based on matrix chart and confidence | |
| CN108664875A (en) | Underground belt-conveying monitoring method based on image recognition | |
| CN103824092A (en) | Image classification method for monitoring state of electric transmission and transformation equipment on line | |
| CN113485432A (en) | Photovoltaic power station electroluminescence intelligent diagnosis system and method based on unmanned aerial vehicle | |
| CN104657814B (en) | Protective relaying device signal templates based on EMS system extract definition method | |
| CN113848471B (en) | Intelligent fault positioning method and system for relay protection system | |
| CN109308587A (en) | The reliability analysis system and its intelligent diagnosing method of electric automobile charging pile | |
| CN111371405A (en) | Photovoltaic power station fault detection system and machine learning fault detection method | |
| CN117612345A (en) | Power equipment state monitoring and alarming system and method | |
| CN105891679A (en) | Fault detection system and method for electric power grid | |
| CN115511367A (en) | Intelligent quality management system of production line | |
| CN106355187A (en) | Application of visual information to electrical equipment monitoring | |
| CN117635905A (en) | Intelligent monitoring method for electric energy meter attachment quality based on image recognition algorithm |
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 |