CN111428987A - Artificial intelligence-based image identification method and system for relay protection device - Google Patents
Artificial intelligence-based image identification method and system for relay protection device Download PDFInfo
- Publication number
- CN111428987A CN111428987A CN202010200770.6A CN202010200770A CN111428987A CN 111428987 A CN111428987 A CN 111428987A CN 202010200770 A CN202010200770 A CN 202010200770A CN 111428987 A CN111428987 A CN 111428987A
- Authority
- CN
- China
- Prior art keywords
- image
- information
- text information
- artificial intelligence
- protection device
- 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
Images
Classifications
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/247—Aligning, centring, orientation detection or correction of the image by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Emergency Protection Circuit Devices (AREA)
Abstract
The embodiment of the invention discloses a relay protection device image identification method and a system based on artificial intelligence, wherein the method comprises the following steps: collecting an image displayed on a display screen of the protection cabinet; identifying text information and image information in the acquired image by adopting a CTPN algorithm; and outputting setting and operating data of the power line equipment according to the text information and the image information, and carrying out system safety evaluation according to the data. The technical scheme provided by the embodiment of the invention can improve the reliability and accuracy of monitoring the power line.
Description
Technical Field
The embodiment of the invention relates to the technical field of image recognition, in particular to a relay protection device image recognition method and system based on artificial intelligence.
Background
With the rapid development of power grid technology in China, the requirements on the automation level and the intelligent degree of a power system are continuously improved, and much confidence of the power system is displayed in a visual mode such as a display screen or an instrument panel.
At present, most of substations in China adopt a series of traditional instruments with glass shells, such as pressure gauges, current meters, liquid level meters, non-intelligent switches and the like, which need to record data manually. These meters are all non-digital non-intelligent devices, and only rely on human eyes to observe and record data, not only precision is low, the reliability is poor, has great potential safety hazard more, because reasons such as visual fatigue or memory illusion, may cause the omission of data or the misinterpretation of information when the manual reading display screen, causes unnecessary loss for electric power system.
Disclosure of Invention
The embodiment of the invention provides a relay protection device image identification method and system based on artificial intelligence, which are used for accurately identifying information on a non-digital relay protection device image, so that the reliability of power line protection monitoring is improved.
In a first aspect, an embodiment of the present invention provides an artificial intelligence-based image recognition method for a relay protection device, which is used for recognizing data displayed by a non-digital device, and includes: collecting an image displayed on a display screen of the protection cabinet;
identifying text information and image information in the acquired image by adopting a CTPN algorithm;
and outputting setting and operating data of the power line equipment according to the text information and the image information, and carrying out system safety evaluation according to the data.
Optionally, the outputting power line equipment setting and operating data according to the text information and the image information, and performing system safety evaluation according to the data includes:
generating a rule base according to the operation mode of the power system, and extracting factor parameters related to the safety of the power system;
generating a quantitative relationship between the factor parameter and the power system safety;
and inquiring results in the rule base according to the quantitative relation, and feeding the results back to operation and maintenance personnel.
Optionally, the data includes a voltage value, a current value, a setting value of the power line device, a soft pressing plate parameter, and a hard pressing plate parameter.
Optionally, the identifying the text information and the image information in the acquired image by using the CTPN algorithm includes:
determining the position of the text information aiming at the collected image;
cutting the text information by using prediction boxes with the same width;
and grouping and splicing the prediction frames according to the classification rule corresponding to the text information to form complete text content.
Optionally, the identifying the text information and the image information in the acquired image by using the CTPN algorithm further includes:
determining the position of the image information aiming at the acquired image;
performing edge detection on the image information;
and determining the final image content through feature comparison.
Optionally, before recognizing text information and image information in the acquired image by using the CTPN algorithm, the method includes: and preprocessing the acquired image, wherein the preprocessing comprises position correction, light spot elimination and noise reduction enhancement.
In a second aspect, an embodiment of the present invention further provides an artificial intelligence based image recognition system for an image recognition system of an artificial intelligence based relay protection device, which is used to execute the artificial intelligence based image recognition method for the relay protection device provided in the embodiment of the present invention, and includes:
the image acquisition module is used for acquiring images displayed on the display screen of the protection cabinet;
the information identification module is used for identifying text information and image information in the acquired image through a CTPN algorithm;
and the information processing module is used for outputting setting and operating data of the power line equipment according to the text information and the image information and carrying out system safety evaluation according to the data.
Optionally, the information processing module includes:
a parameter extraction unit for extracting factor parameters related to the safety of the power system;
an information determination unit for generating a quantitative relationship between the factor parameter and the power system safety;
and the result query and output unit is used for performing result query in the rule base according to the quantitative relation and feeding back the result to the operation and maintenance personnel.
Optionally, the information identification module includes a text information identification unit and an image identification unit;
the text information identification unit is used for identifying characters in the acquired image through a CTPN algorithm;
the image identification unit is used for carrying out image identification on the relay protection device in the collected image through a CTPN algorithm.
Optionally, the image acquisition module includes a camera.
According to the embodiment of the invention, the text information and the image information of the image displayed on the display screen of the protection cabinet are identified by adopting the CTPN algorithm, the setting and running data of the power line equipment are output according to the identified text information and the image information, the safety of the power system is evaluated according to the output setting and running data of the power line equipment, whether the power system has abnormal conditions or not is analyzed, so that an operator can judge the abnormal conditions, and the reliability and the accuracy of monitoring the power line can be further improved.
Drawings
Fig. 1 is a flowchart of an artificial intelligence-based image recognition method for a relay protection device according to an embodiment of the present invention;
FIG. 2 is a flowchart of a relay protection device image recognition method based on artificial intelligence according to a second embodiment of the present invention;
FIG. 3 is a flowchart of an image recognition method for an artificial intelligence-based relay protection device according to a third embodiment of the present invention;
FIG. 4 is a flowchart of an image recognition method for an artificial intelligence-based relay protection device according to a fourth embodiment of the present invention;
FIG. 5 is a flowchart of an artificial intelligence-based image recognition method for a relay protection device according to a fifth embodiment of the present invention;
fig. 6 is a block diagram of an image recognition system of an artificial intelligence-based relay protection device according to a sixth embodiment of the present invention;
FIG. 7 is a block diagram of another artificial intelligence based image recognition system for a relay protection device according to a sixth embodiment of the present invention;
fig. 8 is a block diagram of another artificial intelligence based image recognition system for a relay protection device according to a sixth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an artificial intelligence-based image recognition method for a relay protection device according to an embodiment of the present invention. The technical scheme provided by the embodiment is suitable for the condition that information on non-digital equipment needs to be extracted and identified. The method may be performed by an artificial intelligence based image recognition device, which may be implemented by hardware and/or software. Typically, the apparatus may be configured on the server side for identifying data displayed by the non-digitizing device. Referring to fig. 1, the image recognition method for an artificial intelligence-based relay protection device according to the present embodiment includes:
and 110, collecting an image displayed on a display screen of the protection cabinet.
Specifically, in a transformer substation, a relay protection device such as a pressure gauge, an ammeter, a liquid level meter and other non-intelligent switches with a glass shell is generally adopted to monitor and display the operation data of a power line in real time, a display screen of a protection cabinet can be an L ED display screen, a liquid crystal display screen or an instrument panel, the real-time operation data of a power system is displayed on the display screen of the protection cabinet, images displayed on the display screen of the protection cabinet can be shot through a high-definition camera, and the images are collected.
And step 120, recognizing text information and image information in the acquired image by adopting a CTPN algorithm.
Specifically, the CTPN algorithm is a method for extracting characters from a scene, and can detect the position of text information in a natural environment and identify corresponding text contents. When the CTPN algorithm is adopted to identify the text information, a series of prediction frames with the same width are predicted, the text content is cut by adopting the prediction frames, and then the prediction frames are connected to obtain the whole text information content, so that the text content is not lost. The image displayed on the display screen of the protection cabinet not only has text information but also image information, for example, the image displayed on the display screen of the protection cabinet is shot by a high-definition camera to be a pointer type ammeter, and the current value can be read through the position pointed by the pointer. It is necessary to recognize not only the number pointed to by the pointer but also the type of device in the captured image when image recognition is performed. Only in the case of recognition of the type of device can the meaning of the recognized text information be clearly determined. Of course, the collected images can also be non-intelligent switching devices such as a circuit breaker and a pressing plate, and at the moment, the switching state of the circuit breaker and the switching condition of the pressing plate can be visually seen only by identifying the image information by using the CTPN algorithm.
And step 130, outputting setting and operating data of the power line equipment according to the text information and the image information, and carrying out system safety evaluation according to the data.
Specifically, text information and image information in the collected image are identified through a CTPN algorithm, and the server or the computer can calculate the content of the image information and the text information to obtain setting data and operation data of the power line equipment, wherein the setting data is a specified value of the action of the relay protection device, such as a current value or a voltage value when the relay protection device acts to protect the power line from being burnt; the operation data is data such as an actual current value or a voltage value of the power line in the current state. Optionally, the setting and operating data of the power line equipment includes a voltage value, a current value, a setting value of the power line equipment, a soft pressing plate parameter, and a hard pressing plate parameter. Then, the corresponding server evaluates the operation state of the power system according to the output setting data and operation data of the power line equipment, analyzes the safety level of the power system, and transmits the evaluation result to an operator so that the operator can determine whether the current power line is abnormal. Exemplarily, it is recognized through the CTPN algorithm that an image displayed by a protection cabinet acquired by a camera is an ammeter and a current value is 10A, if a setting value of a relay protection device, such as a circuit breaker, on a current power line is 20A, it is estimated that the current power system is in a safety range and no abnormal condition exists, and an estimation result is sent to a monitoring screen of a main monitoring room, and an operator can judge the operation condition of the current power system by directly observing information on the monitoring screen. In other embodiments, the image on the display screen of the protection cabinet is a pressing plate, the image information is identified as the pressing plate through the CTPN algorithm, and the pressing plate is in a state of not being switched into the power line, so that an operator can confirm that the current power line is in an open circuit state by observing the output evaluation result and the image information.
In the actual operation process of the power system, the display screen of the protection cabinet can contain text information and image information of various relay protection devices, and when the display screen is read manually, data omission or misinterpretation of the data information can be caused, so that unnecessary loss is caused. According to the embodiment of the invention, text information and image information of the image displayed on the display screen of the protection cabinet are identified by adopting a CTPN algorithm, setting and operating data of the power line equipment are output according to the identified text information and image information, the safety of the power system is evaluated according to the output setting and operating data of the power line equipment, and whether the power system has abnormal conditions or not is analyzed so as to assist an operator to judge. Compared with the prior art, when the operation data of the power line needs to be observed, operation and maintenance personnel do not need to go to the site to manually record through a human eye observation method, the problem of low information reading precision is effectively avoided, the problems of information omission and the like caused by visual fatigue of operators can be solved, and the reliability and the accuracy of monitoring the power line can be improved.
Example two
Optionally, fig. 2 is a flowchart of an artificial intelligence-based image recognition method for a relay protection device according to a second embodiment of the present invention. Referring to fig. 2, on the basis of the above embodiment, outputting power line equipment setting and operating data according to text information and image information, and performing system safety evaluation according to the data includes:
step 210, generating a rule base according to the operation mode of the power system, and extracting factor parameters related to the safety of the power system.
Specifically, the rule base is used to determine whether the power system is operating normally under standard conditions, and the state of the power system during abnormal operation, and includes operation rules of various operating modes of the power system. The rule base can be predetermined according to various operation modes of the power system and stored in the computer, wherein the operation modes of the power system can comprise operation modes which can affect the safety and the stability of the power system, such as the change of a power line, the change of a load and the like. And identifying the text information and the image information of the acquired image on the display screen through a CTPN algorithm, and outputting an identification result to a computer. The computer extracts factor parameters related to the safety of the power system from the identification result, wherein the factor parameters can comprise a voltage value, a current value, a frequency, a phase and the like of the power system.
Step 220, generating a quantitative relationship between the factor parameters and the power system safety.
Specifically, the operating conditions of the power system can be directly reflected by the factor parameters such as the voltage value, the current value, the frequency, the phase and the like, each power line and the related relay device in the power system have rated values or action protection values, and when the value of the factor parameter on the power line or the relay device on the line reaches or exceeds the corresponding specified value, an abnormal condition may exist in the power system. Each factor parameter has a quantitative relation with the safety of the power system, for example, the current setting value of the relay protection device in the power line is 40A, and when the actual current on the power line exceeds 40A, the relay protection device acts to cut off the corresponding power line. At this time, the current value of 40A may be in a quantitative relationship.
And step 230, inquiring results in the rule base according to the quantitative relation, and feeding the results back to the operation and maintenance personnel.
Specifically, key factor parameters influencing the safe operation of the power system are determined according to text information and image information in the collected images, quantitative relations between the factor parameters and the safety of the power system are expressed to an operator, operation rules of operation modes similar to the identified factor parameters are automatically matched in a rule base generated according to the operation modes of the power system through a computer, and the safety level of the current power system is evaluated according to the matched corresponding operation rules, so that the operator is assisted in judging whether the current power system has abnormal conditions. In addition, after the information of the acquired image is identified by adopting the CTPN algorithm and is processed by a corresponding operation module, the operator can output the on-off condition of the power line, the fault warning, the power flow distribution of the power line or the solution of similar faults of the current power system according to the factor parameters, and particularly under the huge power system environment, the unnecessary loss of the power system caused by the omission of data information on a display screen due to the visual fatigue of the operator can be effectively avoided.
EXAMPLE III
Fig. 3 is a flowchart of an image recognition method for an artificial intelligence-based relay protection device according to a third embodiment of the present invention. Referring to fig. 3, on the basis of the above embodiment, the image recognition method for an artificial intelligence-based relay protection device according to an embodiment of the present invention includes:
and step 310, collecting an image displayed on a display screen of the protection cabinet.
Step 320, determining the position of the text information for the collected image.
Specifically, images displayed on a display screen of the protection cabinet can be shot through the high-definition camera, and then image data of the analog video signals are converted into digital image streams. For a digital image stream, extracting feature vectors of text information in the image from the digital image stream through convolutional layers of a VGG16 network architecture in a candidate area, wherein the extracted feature vectors form a feature map, and the size of the feature map is related to the spatial arrangement of the feature vectors and the number of the convolutional layers. And then, densely sliding on the feature map by adopting a sliding window with a preset size to obtain a feature vector with the same size as the sliding window, so that the position of the text information in the candidate area can be predicted by using the feature vector with the same size as the sliding window. For example, the first 5 convolutional layers of the VGG16 network architecture are used to extract feature vectors of 2 × 1 size from the captured image, the size of the formed feature map is 2 × 1 × 5, and then the feature map is densely slid on the feature map through a sliding window of 3 × 5 size, each time the dense sliding is performed, the feature vectors of 3 × 5 size are obtained, that is, the position of the text information in the candidate region can be determined through a plurality of feature vectors of 3 × 5.
And step 330, cutting the text information into prediction boxes with the same width.
Specifically, after a plurality of feature vectors with the same size as that of the sliding window are obtained, a sequence formed by the plurality of feature vectors with the same size as that of the sliding window is input into a bidirectional long-and-short-term memory recurrent neural network for training, and a training result is input into a 512-dimensional full-connected layer for normalization processing, so that densely predicted text candidate regions are obtained, and each text candidate region is displayed by a prediction frame with the same width, that is, a plurality of dense prediction frames are formed in the candidate regions, that is, text information in the candidate regions is cut into a plurality of feature vectors by the plurality of dense prediction frames.
And 340, grouping and splicing the prediction boxes according to the classification rules corresponding to the text information to form complete text content.
Specifically, in the candidate area, a plurality of dense prediction boxes containing text information are cut and combined into text lines by a simple text construction method, and a complete text line is the complete text content on the acquired image.
According to the technical scheme provided by the embodiment of the invention, the CTPN algorithm is adopted to extract the text features in the image collected on the display screen of the protection cabinet, then the text features are cut by using the prediction boxes with the same width, and finally the complete text line, namely the complete text information, is obtained by the text construction method, so that the accuracy of text information identification is greatly improved, and the potential safety hazard caused by the observation of operators through human eyes is effectively avoided.
Example four
Fig. 4 is a flowchart of an image recognition method for an artificial intelligence-based relay protection device according to a fourth embodiment of the present invention. Referring to fig. 4, on the basis of the above embodiment, the image recognition method for an artificial intelligence-based relay protection device according to an embodiment of the present invention includes:
and step 410, collecting images displayed on a display screen of the protection cabinet.
Step 420, determining the position of the image information for the acquired image.
Specifically, images displayed on a display screen of the protection cabinet are shot through the high-definition camera, and then image data of the analog video signals are converted into digital image streams. For a digital image stream, extracting feature vectors of image information in the image from the digital image stream through convolutional layers of a VGG16 network architecture in a candidate region, wherein the extracted feature vectors of the plurality of convolutional layers form a feature map, and the size of the feature map is related to the spatial arrangement of the feature vectors and the number of the convolutional layers. And then, performing dense sliding on the feature map by adopting a sliding window with a preset size to obtain a feature vector with the same size as the sliding window, so that the position of the image information in the candidate region can be predicted by using the feature vector with the same size as the sliding window. For example, the image displayed on the display screen of the protection cabinet is a pointer type ammeter, the feature vector of the ammeter can be extracted from the acquired image through the convolution layer of the VGG16 network architecture, a feature map is formed, and the position of the ammeter in the image is determined by adopting a sliding window with a preset size to perform dense sliding on the feature map.
And step 430, carrying out edge detection on the image information.
Specifically, after the position of the image information is determined, an edge detection method is used to determine the edge of the image information, where the edge refers to the set of pixels whose surrounding pixels have sharp gray changes, and is the most basic feature of the image. For example, the intensity of the acquired image information is determined and the first derivative or the second derivative of the intensity is determined, i.e. the edge of the image is determined by the gradient of the intensity of the image information.
And step 440, determining the final image content through feature comparison.
Specifically, after the edge detection is performed on the acquired image information to determine the edge of the image, the feature comparison is performed with other images (which may be the images of the related relay devices) to determine what the relay devices in the acquired image are. For example, a local feature alignment approach may be employed.
According to the technical scheme provided by the embodiment of the invention, the type of the specific equipment in the image is determined by positioning, edge detection and characteristic comparison of the image information in the acquired image, so that an operator can directly observe the specific information on the display screen, and the operator can rapidly judge the current state of the power system. For example, the voltages on the three-phase lines need to be observed, and if only the voltage values on the collected images are identified, it is difficult to determine which voltage corresponds to the voltage of the a-phase line, so that the voltmeter in the collected images needs to be identified, so that an operator can accurately determine the voltage of each phase on the three-phase lines.
EXAMPLE five
Fig. 5 is a flowchart of an artificial intelligence-based image recognition method for a relay protection device according to a fifth embodiment of the present invention. Referring to fig. 5, on the basis of the above embodiment, the image recognition method for an artificial intelligence-based relay protection device according to an embodiment of the present invention further includes:
and step 510, collecting an image displayed on a display screen of the protection cabinet.
And step 520, preprocessing the acquired image, wherein the preprocessing comprises position correction, light spot elimination and noise reduction enhancement.
Specifically, in the process of actual image acquisition, due to the reason of shooting angle, the image on the display screen of the protection cabinet can present the characteristics of multiple angles and multiple morphologies, and certain influence is brought to accurate identification of text information and image information in the image. Therefore, before the text information and the image information in the acquired image are identified by using the CTPN algorithm, the acquired image needs to be preprocessed to improve the accuracy of extracting the text information and the image information in the acquired image. The position correction, the light spot elimination, the noise reduction enhancement and the like can be carried out on the acquired image by adopting a conventional image preprocessing method.
Step 530, identifying text information and image information in the collected image by using a CTPN algorithm.
And 540, outputting setting and operating data of the power line equipment according to the text information and the image information, and evaluating the system safety according to the data.
According to the technical scheme provided by the embodiment of the invention, the collected image is preprocessed before the CTPN algorithm is adopted to identify the text information and the image information of the image displayed on the display screen of the protection cabinet, so that the identification precision of the text information and the image information in the image can be improved, and the accuracy of determining whether the power system has abnormal conditions by an operator can be improved.
EXAMPLE six
Fig. 6 is a block diagram of an image recognition system of an artificial intelligence-based relay protection device according to a sixth embodiment of the present invention. Referring to fig. 6, the image recognition system of the artificial intelligence-based relay protection device according to the present embodiment includes:
the image acquisition module 61 is used for acquiring images displayed on the display screen of the protection cabinet;
the information identification module 62 is configured to identify text information and image information in the acquired image through a CTPN algorithm;
and the information processing module 63 is used for outputting setting and operating data of the power line equipment according to the text information and the image information, and performing system safety evaluation according to the data.
According to the embodiment of the invention, text information and image information of the image displayed on the display screen of the protection cabinet are identified by adopting a CTPN algorithm, setting and operating data of the power line equipment are output according to the identified text information and image information, the safety of the power system is evaluated according to the output setting and operating data of the power line equipment, and whether the power system has abnormal conditions or not is analyzed so as to assist an operator to judge. Compared with the prior art, when the operation data of the power line needs to be observed, operation and maintenance personnel do not need to go to the site to manually record through a human eye observation method, the problem of low information reading precision is effectively avoided, the problems of information omission and the like caused by visual fatigue of operators can be solved, and the reliability and the accuracy of monitoring the power line can be improved.
Optionally, the image capturing module 61 includes a camera.
Optionally, fig. 7 is a block diagram of another artificial intelligence based image recognition system for a relay protection device according to a sixth embodiment of the present invention. Referring to fig. 7, on the basis of the above-described embodiment, the information processing module 63 includes:
a parameter extraction unit 631 for extracting factor parameters related to the safety of the power system;
an information determination unit 632 for generating a quantitative relationship between the factor parameters and the power system safety;
and the result query and output unit 633 is used for performing result query in the rule base according to the quantitative relationship, and feeding back the result to the operation and maintenance personnel.
Optionally, fig. 8 is a block diagram of another artificial intelligence based image recognition system for a relay protection device according to a sixth embodiment of the present invention. Referring to fig. 8, on the basis of the above-described embodiment, the information recognition module 62 includes a text information recognition unit 621 and an image recognition unit 622;
the text information identification unit 621 is configured to identify characters in the acquired image through a CTPN algorithm;
the image recognition unit 622 is configured to perform image recognition on the relay protection device in the acquired image through the CTPN algorithm.
The artificial intelligence based image recognition system for the relay protection device provided by the embodiment of the invention can execute the artificial intelligence based image recognition method for the relay protection device provided by the embodiment of the invention, so that the artificial intelligence based image recognition system for the relay protection device provided by the embodiment of the invention has corresponding functional modules and beneficial effects for executing the method, and the details are not repeated herein.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An artificial intelligence-based image recognition method for a relay protection device is used for recognizing data displayed by non-digital equipment, and is characterized by comprising the following steps of:
collecting an image displayed on a display screen of the protection cabinet;
identifying text information and image information in the acquired image by adopting a CTPN algorithm;
and outputting setting and operating data of the power line equipment according to the text information and the image information, and carrying out system safety evaluation according to the data.
2. The artificial intelligence based image recognition method for a relay protection device according to claim 1, wherein the outputting of power line equipment setting and operating data according to the text information and the image information and the performing of system safety evaluation according to the data comprises:
generating a rule base according to the operation mode of the power system, and extracting factor parameters related to the safety of the power system;
generating a quantitative relationship between the factor parameter and the power system safety;
and inquiring results in the rule base according to the quantitative relation, and feeding the results back to operation and maintenance personnel.
3. The artificial intelligence based image recognition method of a relay protection device according to claim 2, wherein the data includes a voltage value, a current value, a setting value of a power line equipment, a soft platen parameter, and a hard platen parameter.
4. The artificial intelligence based image recognition method for a relay protection device as claimed in claim 1, wherein said recognizing the text information and the image information in the collected image by using the CTPN algorithm comprises:
determining the position of the text information aiming at the collected image;
cutting the text information by using prediction boxes with the same width;
and grouping and splicing the prediction frames according to the classification rule corresponding to the text information to form complete text content.
5. The artificial intelligence based image recognition method of a relay protection device as claimed in claim 4, wherein said recognizing the text information and the image information in the collected image by using the CTPN algorithm further comprises:
determining the position of the image information aiming at the acquired image;
performing edge detection on the image information;
and determining the final image content through feature comparison.
6. The image recognition method for an artificial intelligence based relay protection device as claimed in claim 1, wherein before recognizing the text information and the image information in the collected image by using the CTPN algorithm, the method comprises: and preprocessing the acquired image, wherein the preprocessing comprises position correction, light spot elimination and noise reduction enhancement.
7. An artificial intelligence based image recognition system for a relay device for performing the method of any one of claims 1-6, comprising:
the image acquisition module is used for acquiring images displayed on the display screen of the protection cabinet;
the information identification module is used for identifying text information and image information in the acquired image through a CTPN algorithm;
and the information processing module is used for outputting setting and operating data of the power line equipment according to the text information and the image information and carrying out system safety evaluation according to the data.
8. The artificial intelligence based image recognition system for a relay protection device as claimed in claim 7, wherein said information processing module comprises:
a parameter extraction unit for extracting factor parameters related to the safety of the power system;
an information determination unit for generating a quantitative relationship between the factor parameter and the power system safety;
and the result query and output unit is used for performing result query in a rule base according to the quantitative relation and feeding back the result to the operation and maintenance personnel.
9. The artificial intelligence based image recognition system of claim 7, wherein the information recognition module comprises a text information recognition unit and an image recognition unit;
the text information identification unit is used for identifying characters in the acquired image through a CTPN algorithm;
the image identification unit is used for carrying out image identification on the relay protection device in the collected image through a CTPN algorithm.
10. The artificial intelligence based image recognition system of claim 7, wherein said image capturing module comprises a camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010200770.6A CN111428987A (en) | 2020-03-20 | 2020-03-20 | Artificial intelligence-based image identification method and system for relay protection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010200770.6A CN111428987A (en) | 2020-03-20 | 2020-03-20 | Artificial intelligence-based image identification method and system for relay protection device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111428987A true CN111428987A (en) | 2020-07-17 |
Family
ID=71553502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010200770.6A Pending CN111428987A (en) | 2020-03-20 | 2020-03-20 | Artificial intelligence-based image identification method and system for relay protection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428987A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159172A (en) * | 2021-04-20 | 2021-07-23 | 上海济辰水数字科技有限公司 | Intelligent water meter image positioning training method, intelligent water meter identification system and method |
| CN114511179A (en) * | 2021-12-28 | 2022-05-17 | 江苏东晔电气设备有限公司 | Intelligent planning method and system for processing abnormity of power distribution cabinet |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537222A (en) * | 2018-04-13 | 2018-09-14 | 湖南阳光电力科技有限公司 | A kind of image-recognizing method and system for electric instrument |
| CN109165625A (en) * | 2018-09-11 | 2019-01-08 | 国网山东省电力公司莱芜供电公司 | A kind of test report intelligent generation method based on image recognition |
| US20190311210A1 (en) * | 2018-04-05 | 2019-10-10 | Walmart Apollo, Llc | Automated extraction of product attributes from images |
| CN110334647A (en) * | 2019-07-03 | 2019-10-15 | 云南电网有限责任公司信息中心 | A kind of parameter format method based on image recognition |
-
2020
- 2020-03-20 CN CN202010200770.6A patent/CN111428987A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190311210A1 (en) * | 2018-04-05 | 2019-10-10 | Walmart Apollo, Llc | Automated extraction of product attributes from images |
| CN108537222A (en) * | 2018-04-13 | 2018-09-14 | 湖南阳光电力科技有限公司 | A kind of image-recognizing method and system for electric instrument |
| CN109165625A (en) * | 2018-09-11 | 2019-01-08 | 国网山东省电力公司莱芜供电公司 | A kind of test report intelligent generation method based on image recognition |
| CN110334647A (en) * | 2019-07-03 | 2019-10-15 | 云南电网有限责任公司信息中心 | A kind of parameter format method based on image recognition |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159172A (en) * | 2021-04-20 | 2021-07-23 | 上海济辰水数字科技有限公司 | Intelligent water meter image positioning training method, intelligent water meter identification system and method |
| CN114511179A (en) * | 2021-12-28 | 2022-05-17 | 江苏东晔电气设备有限公司 | Intelligent planning method and system for processing abnormity of power distribution cabinet |
| CN114511179B (en) * | 2021-12-28 | 2023-09-12 | 江苏东晔电气设备有限公司 | Intelligent planning method and system for processing abnormality of power distribution cabinet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10269138B2 (en) | UAV inspection method for power line based on human visual system | |
| CN110826538B (en) | Abnormal off-duty identification system for electric power business hall | |
| CN105654461B (en) | A kind of machine vision detection method of multiple fission conductor conductor spacer fracture | |
| CN109308447A (en) | The method of equipment operating parameter and operating status is automatically extracted in remote monitoriong of electric power | |
| CN109271844B (en) | Electrical cabinet electrical symbol recognition method based on OpenCV | |
| CN109271872B (en) | Device and method for judging on-off state and diagnosing fault of high-voltage isolating switch | |
| CN107563263A (en) | Video image identification method and system based on instrument | |
| CN111428987A (en) | Artificial intelligence-based image identification method and system for relay protection device | |
| CN109308448A (en) | A method of it prevents from becoming distribution maloperation using image processing techniques | |
| CN112906576B (en) | State identification method, device and equipment of isolating switch equipment and temperature measurement method thereof | |
| CN112257632A (en) | Transformer substation monitoring system based on edge calculation | |
| CN112508019A (en) | GIS isolation/grounding switch state detection method and system based on image recognition | |
| CN113794857A (en) | Non-intrusive monitoring method and device for switch cabinet and storage medium | |
| CN114694050A (en) | Power equipment running state detection method based on infrared image | |
| CN106019145A (en) | System and method for recognizing external load switches of electric energy meter | |
| CN105987665A (en) | Early warning and monitoring device of ultra high voltage transmission line sag point variation range, and method of the same | |
| CN112734637A (en) | Thermal infrared image processing method and system for monitoring temperature of lead | |
| Yang et al. | Technology of actual wind deviation monitoring for suspension insulator strings based on improved edge detection | |
| Bin et al. | Study on the method of switch state detection based on image recognition in substation sequence control | |
| CN114549822A (en) | Disconnecting switch closing state detection method based on preset position camera | |
| Yang et al. | An intelligent identification algorithm for obtaining the state of power equipment in SIFT-based environments | |
| CN113947563A (en) | Cable process quality dynamic defect detection method based on deep learning | |
| CN111768378A (en) | Crimping hardware tool live-line detection method and device | |
| Shen et al. | Transmission line safety early warning technology based on multi-source data perception | |
| CN112183194B (en) | Non-contact type convertor station workstation equipment parameter identification 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200717 |
|
| RJ01 | Rejection of invention patent application after publication |