CN111566493B - Method and system for circuit breaker condition monitoring - Google Patents

Method and system for circuit breaker condition monitoring Download PDF

Info

Publication number
CN111566493B
CN111566493B CN201880085814.6A CN201880085814A CN111566493B CN 111566493 B CN111566493 B CN 111566493B CN 201880085814 A CN201880085814 A CN 201880085814A CN 111566493 B CN111566493 B CN 111566493B
Authority
CN
China
Prior art keywords
circuit breaker
image
condition
features
images
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.)
Active
Application number
CN201880085814.6A
Other languages
Chinese (zh)
Other versions
CN111566493A (en
Inventor
陈妮亚
阮佳阳
于蓉蓉
庄志坚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ABB Schweiz AG
Original Assignee
ABB Schweiz AG
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by ABB Schweiz AG filed Critical ABB Schweiz AG
Publication of CN111566493A publication Critical patent/CN111566493A/en
Application granted granted Critical
Publication of CN111566493B publication Critical patent/CN111566493B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • 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
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
    • G01R31/3271—Testing of circuit interrupters, switches or circuit-breakers of high voltage or medium voltage devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/06—Recognition of objects for industrial automation

Abstract

A method and system for circuit breaker condition monitoring is disclosed. The method comprises the following steps: acquiring (202) an image of a circuit breaker; extracting (204) one or more features related to a condition of the circuit breaker from the image; comparing (206) the extracted one or more characteristics with reference data characterizing a predetermined condition of the circuit breaker; a health state of the circuit breaker is determined (208) based on the comparison.

Description

Method and system for circuit breaker condition monitoring
Technical Field
Example embodiments of the present disclosure relate generally to circuit breaker monitoring and, more particularly, to methods and systems for circuit breaker condition monitoring.
Background
Circuit breakers are widely used in electrical networks. Circuit breakers are intended to protect electrical circuits or equipment from damage caused by excessive current flow due to overload or short circuits. Catastrophic results may occur when the circuit breaker fails to operate under such adverse electrical conditions. However, over time, the circuit breaker may suffer from various faults, which threatens the safety of the circuit. It is desirable to perform condition monitoring of circuit breakers in order to track the operational status of the circuit breakers and to be able to indicate potential fault occurrences and preventative maintenance.
Circuit breakers are typically enclosed in a housing and their status cannot be easily monitored. Conventional circuit breaker monitoring systems typically include a measurement device that measures a parameter associated with the circuit breaker. However, such systems can only monitor the limited state of the circuit breaker and do not provide for comprehensive state monitoring and diagnostics of the circuit breaker.
In some circuit breakers, a camera is provided to take a picture of the circuit breaker. However, the photographed pictures are generally transmitted to a remote control center, where a technical engineer checks and diagnoses the photographed pictures one by one for status monitoring. This is time consuming and inefficient.
Additionally, in some circuit breakers, machine vision methods are used, but these methods are not related to the state monitoring of the circuit breaker and the diagnosis of the circuit breaker. For example, CN106526467A discloses a high voltage circuit breaker that can measure closing and opening speeds of a movable contact based on machine vision. The reference point is predetermined and the position of the object in a series of images is identified, and then the closing and opening speed of the movable contact can be calculated.
Disclosure of Invention
Example embodiments of the present disclosure propose a solution for circuit breaker condition monitoring.
In a first aspect, example embodiments of the present disclosure provide a method for circuit breaker condition monitoring. The method comprises the following steps: acquiring an image of the circuit breaker; extracting one or more features related to a condition of the circuit breaker from the image; comparing the extracted one or more characteristics with reference data characterizing a predetermined condition of the circuit breaker; the health status of the circuit breaker is determined based on the comparison.
With the method for circuit breaker state monitoring, the health condition of the circuit breaker can be reliably and accurately determined in a simple manner. Also, since the state monitoring of the circuit breaker is performed by a machine vision method, any number of predetermined conditions of the circuit breaker can be monitored without adding a substantial burden. Thus, some unhealthy conditions, such as conductor corrosion, dust pollution, which are difficult to monitor using conventional methods, can be monitored in a simple manner.
In some embodiments, extracting the one or more features comprises at least one of: acquiring a binary image or a gray histogram of an image; extracting key feature points describing features of components of the circuit breaker from the image; and separating the images to identify the location and grayscale data of the components of the circuit breaker. Thus, computational complexity is simplified.
In some embodiments, the components of the circuit breaker include at least one of: a fixed contact, a movable contact and a ground contact.
In some embodiments, the comparing comprises: determining a metric, the metric comprising at least one of: a distance between the one or more features and the reference data, and a correlation coefficient between the one or more features and the reference data; and determining dissimilarity between the one or more features and the reference data based on the metric. Therefore, the health state of the circuit breaker can be determined by an image processing method.
In some embodiments, the method further comprises: acquiring a set of images, each set comprising a plurality of images for one of the predetermined conditions of the circuit breaker; for each set of images, extracting features characterizing a respective predetermined condition from the plurality of images; and training a classifier based on the extracted features. The classifier can be trained well when a set of images is provided for one of a plurality of predetermined conditions of the circuit breaker. The reliability and accuracy of the determination can be improved.
In some embodiments, the one or more extracted features are classified by a classifier. When a classifier is used, the calculations are reduced and the state of health of the circuit breaker can be determined in a convenient and efficient manner.
In some embodiments, the predetermined condition comprises at least one of: normal close, defect close, normal open, defect open, normal ground, defect ground, conductor corrosion, and dust contamination.
In a second aspect, an example embodiment of the present disclosure is a system for circuit breaker condition monitoring. The system comprises: a camera configured to photograph the circuit breaker; and at least one processor communicatively coupled to the camera and configured to perform the method of the first aspect. In some embodiments, at least one processor may be local. In some embodiments, at least one processor may be remote. With the system for circuit breaker state monitoring, the state of health of the circuit breaker can be reliably and accurately determined in a simple manner. All advantages with respect to this method can be similarly achieved.
In a third aspect, example embodiments of the present disclosure provide a computer-readable medium having instructions stored thereon, which, when executed on at least one processor, cause the at least one processor to perform the method according to any one of the first aspect.
In a fourth aspect, example embodiments of the present disclosure provide a computer program product, tangibly stored on a computer-readable storage medium, and comprising instructions that, when executed on at least one processor, cause the at least one processor to perform the method according to any one of the first aspects.
In a fifth aspect, example embodiments of the present disclosure provide an internet of things (IoT) system. The system comprises: a circuit breaker; and a system for circuit breaker condition monitoring according to the second aspect.
Drawings
The above and other objects, features and advantages of the example embodiments disclosed herein will become more apparent from the following detailed description, which proceeds with reference to the accompanying drawings. Several exemplary embodiments disclosed herein are illustrated by way of example and not by way of limitation in the figures of the accompanying drawings, in which:
figure 1 illustrates a schematic diagram of a circuit breaker according to some example embodiments of the present disclosure;
fig. 2 illustrates a flow diagram of a method for circuit breaker condition monitoring, according to some example embodiments of the present disclosure;
FIG. 3 shows a schematic diagram of a feature extraction process, according to some example embodiments of the present disclosure;
fig. 4 shows images showing various predetermined conditions of a circuit breaker, according to some example embodiments of the present disclosure;
FIG. 5 illustrates a grayscale histogram corresponding to the image in FIG. 4, according to some example embodiments of the present disclosure;
fig. 6 illustrates a two-dimensional feature vector extracted from an image of a circuit breaker, according to some example embodiments of the present disclosure; and is
Fig. 7 illustrates a test image and its grayscale histogram according to some example embodiments of the present disclosure.
Fig. 8 shows a block diagram of a system 800 for circuit breaker condition monitoring, in accordance with an embodiment of the present disclosure.
Throughout the drawings, the same or corresponding reference numerals designate the same or corresponding parts.
Detailed Description
The subject matter described herein will now be discussed with reference to several exemplary embodiments. These embodiments are discussed only for the purpose of enabling those skilled in the art to better understand and thus implement the subject matter described herein, and do not imply any limitation on the scope of the subject matter.
The term "comprising" or "including" and variants thereof are to be understood as open-ended terms, which mean "including but not limited to". The term "or" should be understood as "and/or" unless the context clearly dictates otherwise. The term "based on" is to be understood as "based at least in part on". The term "operable to" means that a function, action, motion, or condition can be achieved through an operation caused by a user or an external mechanism. The terms "one embodiment" and "one embodiment" should be understood as "at least one embodiment". The term "another embodiment" should be understood as "at least one other embodiment".
Unless specified or limited otherwise, the terms "mounted," "connected," "supported," and "coupled" and variations thereof are used broadly and encompass both direct and indirect mountings, connections, supports, and couplings. Further, "connected" and "coupled" are not restricted to physical or mechanical connections or couplings. In the description below, like reference numerals and labels are used to describe the same, similar or corresponding parts in the figures. Other definitions (explicit and implicit) may be included below.
Fig. 1 illustrates a schematic diagram of a circuit breaker, according to some example embodiments of the present disclosure. The diagram shows only the main components thereof, and the other components are omitted.
As shown, the circuit breaker 10 includes a fixed contact 14, a movable contact 12, and a ground contact 16. The movable contact 12 may include a number of operating conditions. For example, the movable contact 12 may move to a first position where it contacts the fixed contact 14. In this case, the circuit including the circuit breaker 10 is closed and current may flow through the circuit breaker 10. The movable contact 12 may be moved to a second position in which it is separated from the fixed contact 14 and the ground contact 16. In this case, the circuit including the circuit breaker 10 is opened, and the current cannot flow through the circuit breaker 10. The movable contact 12 may also be moved to a third position where it contacts the ground contact 16, thereby grounding the circuit breaker 10 to protect the circuit breaker 10 from damage.
The circuit breaker 10 is important for circuit protection and therefore its operating conditions should be well monitored. As described above, some conventional condition monitoring methods can detect only a limited number of conditions of the circuit breaker, and some conventional condition monitoring methods require human involvement deeply and cannot be performed automatically, which is inefficient and inconvenient. The present disclosure presents novel solutions for circuit breaker condition monitoring and diagnostics based on image processing or analysis techniques.
Fig. 2 illustrates a flow diagram of a method 200 for circuit breaker condition monitoring, according to some example embodiments of the present disclosure. The method 200 can be implemented to effectively perform the condition monitoring of the circuit breaker in a simple manner without any impact on the operation of the circuit breaker.
At block 202, one or more images of the circuit breaker are taken. At least one camera or the like may be fixedly mounted at a suitable location within the circuit breaker. Preferably, the position of the camera may ensure that the image taken by the camera includes key features for condition monitoring or diagnosis of the circuit breaker. In some embodiments, only one camera is provided, which may meet the condition monitoring requirements. In some embodiments, two or more cameras are provided in order to provide more data for condition monitoring.
At block 204, one or more features related to the condition of the circuit breaker are extracted from the image. Typically, the picture taken by the camera is in color. In some embodiments, these pictures are recorded as 3 matrices in the computer. The data is usually very large and difficult to use directly. The pictures must be compressed or processed to extract key or necessary features related to condition monitoring or diagnostics of the circuit breaker. There are many methods for extracting features from an image, which will be described below, for example, with reference to fig. 3 and 4.
At block 206, the extracted one or more features are compared to benchmark data characterizing a predetermined condition of the circuit breaker. In a method 200 according to some example embodiments of the present disclosure, reference data is created to characterize predetermined conditions of a circuit breaker. In some embodiments, these reference data are stored in a database accessible by the processor. Before creating the benchmark data, data related to predetermined conditions of the circuit breaker needs to be collected. For example, images recording predetermined conditions of the circuit breaker are collected and these collected images are processed to extract key or essential features. These extracted features are used as reference data for characterizing predetermined conditions of the circuit breaker. In some embodiments, the method may determine at least one predetermined condition of the circuit breaker. When a plurality of predetermined conditions of the circuit breaker are to be determined, for each predetermined condition, at least one image is collected recording or describing the predetermined condition of the circuit breaker to form reference data.
At block 208, a health state of the circuit breaker may be determined based on the comparison. When the health status of the circuit breaker is determined, the health status is displayed to a user (e.g., via a display). In some embodiments, when the system includes multiple circuit breakers, the condition of the multiple circuit breakers may be checked simultaneously. In some embodiments, when the status of the circuit breaker is unhealthy, an alert is sent to the user, and appropriate action may be taken, such as replacing or maintaining the circuit breaker.
According to the method for circuit breaker state monitoring, the state of health of the circuit breaker can be reliably and accurately determined in a simple manner. Also, since the state monitoring of the circuit breaker is performed by a machine vision method, any number of predetermined conditions of the circuit breaker can be monitored without adding a substantial burden. Thus, some unhealthy conditions, such as conductor corrosion, dust pollution, which are difficult to monitor using conventional methods, can be monitored in a simple manner.
In some embodiments, pictures taken by a camera may generally be compressed or processed to extract key or necessary features. There are many ways to extract features from an image. When the picture is further processed, computational complexity is simplified and hardware burden can be reduced.
Fig. 3 illustrates a schematic diagram of feature extraction, according to some example embodiments of the present disclosure. As shown in fig. 3, an original color image 301 taken by a camera is converted to a grayscale image 302. Since a grayscale image is typically recorded in one matrix, the original color image 301 can be compressed.
In the illustrated embodiment, the grayscale image may be further compressed to reduce the computational complexity of the image processing.
In one example embodiment, the grayscale image 302 may be converted to a binary image 303 using various binarization methods. For example, Otsu method is used for binarization. In Otsu's method, the threshold that minimizes the intra-class variance (i.e., intra-class variance) is searched exhaustively. The intra-class variance is defined as the weighted sum of two class variances:
Figure BDA0002574952290000071
wherein the weight ω is0And ω1Respectively representing the probability of two classes being separated by a threshold t, and
Figure BDA0002574952290000072
and
Figure BDA0002574952290000073
the variances of the two classes are represented separately.
In another example embodiment, the grayscale image 302 may be converted to a grayscale histogram 304. A gray histogram is a histogram that is used as a graphical representation of the gray distribution in a digital image. It plots the number of pixels for each gray value. The gray level histogram for a particular image records the gray level distribution of the image. The grayscale histogram vector may then be used as a vector feature for calculation.
In some example embodiments, feature points in the image are extracted using an image processing algorithm. As an example, points of interest on objects in an image may be extracted. These characteristics may characterize the main characteristics of the circuit breaker. The characterized features may be used to identify key objects in different images and may be used for comparison with reference data. As described above, in order to perform reliable recognition, even in the case where noise and illuminance vary, features extracted from an image can be detected. For example, these points are typically located on high contrast regions of the image (such as object edges). In some example embodiments, the features include edges, corners, etc. of the component in the image. Image processing algorithms may include SIFT (scale invariant feature transform), angle detection, etc.
In some example embodiments, image segmentation methods are used to locate critical components. The position and surface condition of the critical components may reflect the condition of the circuit breaker. When the location and surface condition of critical components in the image are identified, this information can be used to determine the condition of the circuit breaker. For example, the position of the movable contact may be used to determine the open and closed condition of the circuit breaker, and the corrosion characteristics in the copper contacts may be indicative of the nature of the defect. Generally, a domain knowledge (domain knowledge) database may be created in advance. Image segmentation methods can be used in conjunction with domain knowledge to locate key components and extract corresponding portions of the map as input to a diagnostic model. For example, the movable contact may be positioned as a circle within a rectangle by image segmentation in combination with domain knowledge. The position and surface condition of the movable contact can then be used to determine the condition of the circuit breaker. The image segmentation method can be performed by using various algorithms including, but not limited to, clustering algorithm (K-means), Watershed (Watershed), image segmentation (GraphCut), and the like.
Referring to fig. 4-6, a method for creating benchmark data is described. For example, images relating to predetermined conditions of the circuit breaker are collected. From these images, reference data characterizing key features related to predetermined conditions of the circuit breaker are extracted using the extraction method described above. These reference data are then stored in a database. The predetermined conditions include, but are not limited to, normal close, defect close, normal open, defect open, normal ground, defect ground, conductor corrosion, and dust contamination.
In one example, fig. 4 shows only four predetermined conditions of a circuit breaker according to some example embodiments of the present disclosure. As shown at 401 in fig. 4, the circuit breaker is closed and the movable contact contacts the fixed contact. At 402 in fig. 4, the circuit breaker is grounded and the movable contact contacts the ground contact. At 403 in fig. 4, the circuit breaker is open and the movable contact is located between the fixed contact and the ground contact and is not in contact with any of them. At 404 in fig. 4, the circuit breaker is defectively closed and the movable contact is near or partially in contact with the fixed contact.
The collected images representing the predetermined condition of the circuit breaker may be compressed to extract key features that characterize the predetermined condition.
Fig. 5 illustrates a grayscale histogram corresponding to the image in fig. 4, according to some example embodiments of the present disclosure. The grey level histogram associated with the predetermined condition of the circuit breaker may be stored as reference data in a database. As shown in fig. 5, the grayscale histogram 501 corresponds to the closing condition of the circuit breaker in fig. 4; the grayscale histogram 502 corresponds to the grounding condition of the circuit breaker in fig. 4; the grayscale histogram 503 corresponds to the open condition of the circuit breaker in fig. 4; and the grey histogram 504 corresponds to the defect closed condition of the circuit breaker in fig. 4.
Fig. 6 illustrates a two-dimensional feature vector extracted from an image of a circuit breaker, according to some example embodiments of the present disclosure. Since the vector is two-dimensional, it can be represented as a point in a two-dimensional coordinate system. As shown, each point in the graph represents a feature vector extracted from one graph of the circuit breaker. Different types of baseline data are collected as reference data. In the example shown, three conditions and possible defective closing types of known normal circuit breakers are shown.
As shown, reference numeral 601 ("' gamma") indicates that the circuit breaker can be normally open. Reference numeral 602 (") denotes that the circuit breaker can be normally closed. Reference numeral 603 "it" indicates that the circuit breaker can be normally grounded. Reference numeral 604 ". smallcircle" denotes a defect type. For example, a circuit breaker cannot be normally closed or opened, i.e., a defective opening or a defective closing. Reference numeral 605 ". v" denotes another defect type. For example, the circuit breaker cannot be grounded normally, i.e., a defective ground. Reference numeral 606 "", denotes the extracted test feature vector. As shown, for each symbol of the reference data, a plurality of points are shown. This means that a plurality of images are collected to indicate each predetermined condition. In some embodiments, when only one image is collected for each predetermined condition, only one point is shown for each predetermined condition. The test feature vectors may be classified based on the reference data using a variety of methods, for example, K-Nearest neighbors (K-Nearest neighbors), support vector machines, classical image processing methods (such as similarity calculations), and the like.
To determine the condition of the target circuit breaker, a test image or picture is taken by a camera and features characterizing the condition of the target circuit breaker are extracted. Various methods may be used to classify the extracted test features or vectors based on the reference data. The method includes, but is not limited to, classical image processing methods and machine learning algorithms.
Embodiments of a method for determining a condition of a target circuit breaker will now be described. The main principle of these methods is to determine which reference type the test data most closely resembles.
In some example embodiments, classical image processing methods are used. For example, a metric (such as a distance between the one or more features and the reference data, a correlation coefficient between the one or more features and the reference data) is determined, and a dissimilarity (dissimilarity) between the one or more features and the reference data is determined based on the metric. The condition of the target circuit breaker may then be determined.
Fig. 7 illustrates a test image 701 and a grayscale histogram 702 thereof, according to some example embodiments of the present disclosure. The original color image 701 taken by the camera is converted into a grayscale histogram 702 using the method described above. In some example embodiments, the gray histogram shown in fig. 5 is stored as reference data.
The gray histogram is recorded as a feature vector, for example, comprising 256 elements, corresponding to the number of pixels in the image at each gray value (gray 1-256). It should be understood that the length of the gray histogram vector need not be 256, and that the length may be determined to be other values. Thus, the reference data shown in fig. 5 represents four categories of predetermined conditions of the circuit breaker, each condition represented by xj(j ═ 1,2,3,4) and the extracted feature vector of the test image is represented as xt。
In some embodiments, dissimilarity or/and distance may be calculated in order to classify the test image as one class in the reference data. A reference feature vector of the reference feature vectors that is most similar or closest to the feature vector of the test image may indicate a condition of the circuit breaker. For example, the euclidean distance between the feature vector of the test image and each of the reference feature vectors may be calculated using the following equation.
Figure BDA0002574952290000101
The euclidean distance results from the feature vectors of the test image to each of the reference feature vectors are shown in table 1:
TABLE 1
Figure BDA0002574952290000102
Figure BDA0002574952290000111
As can be seen from the above, d3 is a minimum value, and thus the test image can be classified or determined to be "disconnected".
There are a number of ways to calculate dissimilarity or distance. For example, in some example embodiments, a correlation coefficient may be calculated between the feature vector of the test image and each of the reference feature vectors.
In some example embodiments, a machine learning algorithm is used. For example, in one embodiment, groups of images are acquired, each group of images including a plurality of images for one of the predetermined conditions of the circuit breaker. For each set of images, features characterizing a respective predetermined condition are extracted from the plurality of images. A classifier based on the extracted features is trained. The condition of the target circuit breaker may then be determined by the classifier. The classifier can be trained well when a set of images is provided for one of the predetermined conditions of the circuit breaker. This may improve the reliability and accuracy of the determination. There are a variety of machine learning methods that can train classifiers based on reference data, e.g., K Nearest Neighbors (KNNs), Support Vector Machines (SVMs), neural networks, logistic regression, etc. As an example, the principle of classification using the KNN and SVM methods is explained as follows. It should be understood that the following embodiments are exemplary only.
In the KNN method, the input is the extracted test feature and the output is the class member. Test images taken by the cameras are sorted in the reference database by the majority vote of their neighbours and test data is assigned to the most common class (k being a positive integer, usually small) of their k nearest neighbours.
Suppose that the reference data is represented as (X)1，y1)，(X2，y2)，...，(Xn，yn) Wherein the condition features are represented as XiAnd y isiIs a condition characteristic XiThe status category of (1). Given a distance definition (e.g., euclidean distance), the nearest k samples in the reference dataset may be determined. The majority vote of these k samples indicates the condition or class of the test image.
In some embodiments, a threshold may be set for classification. That is, if the distance between the test feature vector and the nearest reference neighbor is greater than a threshold, the condition of the test image may be determined to be "other," meaning that no known reference is similar to the test image. This may be a new defect type. In some embodiments, in such a case, an alert may be sent to the user.
In some example embodiments, an SVM method may be used to train a classifier model, which may be based on creating a representation of fiducial points whose division is divided by as wide an apparent gap as possible.
For example, given the reference data (X)1，y2)，(X2，y2)，...，(Xn，yn) Wherein the condition features are represented as XiAnd y isiIs a condition characteristic XiThe status category of (1). The goal of training using SVMs is to obtain a classifier or model.
Figure BDA0002574952290000121
This minimizes the loss function R f.
Figure BDA0002574952290000122
So as to satisfy
Figure BDA0002574952290000123
Figure BDA0002574952290000125
Wherein
Figure BDA0002574952290000124
Represents a mapping function from a low-dimensional space to a high-dimensional space, w represents a weight of the mapping function, and b represents a deviation. By the loss function R [ f ] in equation (4)]And the constraints in equation (5), the value of w in equation (3) may be determined. Thus, a classifier or model can be obtained in equation (3).
Thus, for any test data x*Of circuit breakersThe condition is the output y calculated by the trained classifier*。
Fig. 8 shows a block diagram of a system 800 for circuit breaker condition monitoring, in accordance with an embodiment of the present disclosure. The system 800 includes a camera 805 and at least one processor 810. The camera 805 is configured to take a picture of the circuit breaker. The at least one processor 810 is communicatively coupled to the camera 805 and configured to perform the method 200 as described above. With the system for circuit breaker state monitoring, the state of health of the circuit breaker can be reliably and accurately determined in a simple manner. All advantages with respect to the method 200 may be similarly achieved and will not be repeated here.
In general, the various embodiments of the disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of the embodiments of the disclosure are illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that the blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computer device, or some combination thereof.
The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, that are executed in a device on a target real or virtual processor to perform the processes or methods described above with reference to fig. 2. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within local or distributed devices. In a distributed facility, program modules may be located in both local and remote memory storage media.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the computer, partly on the computer as a stand-alone software package, partly on the computer and partly on a remote computer or entirely on the remote computer or server.
The above program code may be embodied on a machine-readable medium, which may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous. Likewise, although the above discussion contains several specific implementation details, these should not be construed as limitations on the scope of the disclosure, but rather as descriptions of features specific to particular embodiments. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. In other instances, features which are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims (9)

1. A method for circuit breaker condition monitoring, comprising:
acquiring an image of the circuit breaker;
extracting one or more features related to a condition of the circuit breaker from the image, including obtaining a binary image or a grayscale histogram from the image;
comparing the extracted binary image or grayscale histogram to a reference feature vector characterizing a predetermined condition of the circuit breaker, wherein the comparing comprises: determining a metric, the metric comprising at least one of: a distance between the binary image or the gray level histogram and the reference feature vector, and a correlation coefficient between the binary image or the gray level histogram and the reference feature vector; and determining dissimilarity between the binary image or grayscale histogram and the reference feature vector based on the metric;
determining a health state of the circuit breaker based on the comparison.
2. The method of claim 1, wherein extracting the one or more features further comprises at least one of:
extracting key feature points from the image that describe features of components of the circuit breaker; and
the image is segmented to identify position and gray scale data of components of the circuit breaker.
3. The method of claim 2, wherein the component of the circuit breaker comprises at least one of: a fixed contact, a movable contact and a ground contact.
4. The method according to any one of claims 1-3, further comprising:
obtaining a plurality of sets of images, each set of images including a plurality of images for one of the predetermined conditions of the circuit breaker; and
for each set of images of the image group,
extracting features from the plurality of images that characterize respective predetermined conditions; and
a classifier is trained based on the extracted features.
5. The method of claim 4, wherein the one or more extracted features are classified by the classifier.
6. The method of any of claims 1-3 and 5, wherein the predetermined condition comprises at least one of: normal close, defect close, normal open, defect open, normal ground, defect ground, conductor corrosion, and dust contamination.
7. A system for circuit breaker condition monitoring, comprising:
a camera configured to take a picture of the circuit breaker; and
at least one processor communicatively coupled to the camera and configured to perform the method of any of claims 1 to 6.
8. A computer-readable medium having stored thereon instructions that, when executed on at least one processor, cause the at least one processor to perform the method according to any one of claims 1 to 6.
9. An internet of things (IoT) system, comprising:
a circuit breaker; and
the system for circuit breaker condition monitoring of claim 7.
CN201880085814.6A 2018-10-09 2018-10-09 Method and system for circuit breaker condition monitoring Active CN111566493B (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/109525 WO2020073201A1 (en) 2018-10-09 2018-10-09 Method and system for circuit breaker condition monitoring

Publications (2)

Publication Number Publication Date
CN111566493A CN111566493A (en) 2020-08-21
CN111566493B true CN111566493B (en) 2022-01-28

Family

ID=70164427

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201880085814.6A Active CN111566493B (en) 2018-10-09 2018-10-09 Method and system for circuit breaker condition monitoring

Country Status (3)

Country Link
EP (1) EP3864424A4 (en)
CN (1) CN111566493B (en)
WO (1) WO2020073201A1 (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111950606B (en) * 2020-07-28 2023-11-07 北京恒通智控机器人科技有限公司 Knife switch state identification method, device, equipment and storage medium
CN112419232A (en) * 2020-10-16 2021-02-26 国网天津市电力公司电力科学研究院 Method for detecting state of low-voltage circuit breaker by integrating YOLOv3 with attention module
CN112763904A (en) * 2020-12-29 2021-05-07 广州航天海特系统工程有限公司 Circuit breaker detection method, device, equipment and storage medium
CN113780191A (en) * 2021-09-14 2021-12-10 西安西电开关电气有限公司 Method and system for identifying opening and closing state image of starting drag switch of power station
CN114325451B (en) * 2022-01-17 2022-10-25 广州地铁集团有限公司 Method and device for estimating residual life of relay, computer equipment and medium
CN116026292B (en) * 2023-03-29 2023-07-28 国网天津市电力公司电力科学研究院 Breaker travel track reproduction device and method based on three-eye imaging principle
CN116754934B (en) * 2023-05-22 2024-02-23 杭州轨物科技有限公司 Mechanical characteristic fault diagnosis method for high-voltage circuit breaker

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6437576B2 (en) * 1996-12-10 2002-08-20 Abb Research Ltd. Method for detecting short-circuit conditions and device which uses this method
CN1845605A (en) * 2006-05-15 2006-10-11 华北电力大学（北京） Image processing and recognizing method for real-time monitoring power high voltage circuit breaker switch state
CN103698694A (en) * 2012-09-28 2014-04-02 四川奥格科技有限公司 Online monitoring system for high-voltage circuit breaker
CN104849654A (en) * 2015-04-09 2015-08-19 广州供电局有限公司 Method for online monitoring breaker
CN106093773A (en) * 2016-08-26 2016-11-09 张振堂 A kind of zone isolation on off state based on Internet of Things monitoring system
CN206057508U (en) * 2016-09-30 2017-03-29 国家电网公司 A kind of primary cut-out on-line monitoring system

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106526467B (en) * 2016-10-14 2019-07-19 西安交通大学 A kind of high-voltage circuit-breaker switching on-off speed characteristics measurement method based on machine vision
CN106371013A (en) * 2016-11-08 2017-02-01 广东电网有限责任公司电力科学研究院 Picture identification-based GIS switch fault automatic identification system
CN106840406B (en) * 2016-11-29 2019-08-16 浙江中新电力工程建设有限公司自动化分公司 Isolation switch method for diagnosing faults based on matrix neural network
CN106680705A (en) * 2017-02-20 2017-05-17 中国神华能源股份有限公司 Disconnector monitoring system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6437576B2 (en) * 1996-12-10 2002-08-20 Abb Research Ltd. Method for detecting short-circuit conditions and device which uses this method
CN1845605A (en) * 2006-05-15 2006-10-11 华北电力大学（北京） Image processing and recognizing method for real-time monitoring power high voltage circuit breaker switch state
CN103698694A (en) * 2012-09-28 2014-04-02 四川奥格科技有限公司 Online monitoring system for high-voltage circuit breaker
CN104849654A (en) * 2015-04-09 2015-08-19 广州供电局有限公司 Method for online monitoring breaker
CN106093773A (en) * 2016-08-26 2016-11-09 张振堂 A kind of zone isolation on off state based on Internet of Things monitoring system
CN206057508U (en) * 2016-09-30 2017-03-29 国家电网公司 A kind of primary cut-out on-line monitoring system

Also Published As

Publication number Publication date
EP3864424A4 (en) 2022-05-18
EP3864424A1 (en) 2021-08-18
CN111566493A (en) 2020-08-21
WO2020073201A1 (en) 2020-04-16

Similar Documents

Publication Publication Date Title
CN111566493B (en) Method and system for circuit breaker condition monitoring
CN110866891A (en) Image recognition device, image recognition method, and image recognition program
CN113111844B (en) Operation posture evaluation method and device, local terminal and readable storage medium
CN109740609B (en) Track gauge detection method and device
Jadin et al. Finding region of interest in the infrared image of electrical installation
Liao et al. A flexible PCB inspection system based on statistical learning
CN110751619A (en) Insulator defect detection method
CN111950566A (en) Rotation-invariant HOG infrared image power equipment identification method
CN116168351B (en) Inspection method and device for power equipment
KR100868884B1 (en) Flat glass defect information system and classification method
KR20220014805A (en) Generating training data usable for examination of a semiconductor specimen
CN117413292A (en) Image-based anomaly detection for object-based machine learning analysis
Bharadwaj et al. Can holistic representations be used for face biometric quality assessment?
EP2911112B1 (en) Methods for assessing image change and devices thereof
Zhang et al. An image processing approach to machine fault diagnosis based on visual words representation
Steiger et al. Automatic detection of transmission towers
CN112287905A (en) Vehicle damage identification method, device, equipment and storage medium
CN112686122A (en) Human body and shadow detection method, device, electronic device and storage medium
CN116188445A (en) Product surface defect detection and positioning method and device and terminal equipment
Jadin et al. Detecting ROIs in the thermal image of electrical installations
US11120541B2 (en) Determination device and determining method thereof
WO2015178001A1 (en) Image matching system, image matching method, and recording medium storing program
Zhang et al. Visual extraction system for insulators on power transmission lines from UAV photographs using support vector machine and color models
US11961284B2 (en) Task appropriateness determination apparatus
Nair et al. Recognition of Speed Limit from Traffic Signs Using Naive Bayes Classifier

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant