Automatic monitoring method, system and equipment for relay protection hard pressure plate
Through image processing technology, including Hough linear transformation and clustering algorithm, automated monitoring of relay protection hard pressure plates is realized, solving the problem of time-consuming and labor-intensive traditional monitoring and the inability to fully automate existing automated monitoring, and improving the robustness of monitoring and reliability.
Patent Information
- Application Number
- CN202210579484.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-05-25
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2042-05-25
AI Technical Summary
The monitoring of traditional relay protection hard plates is time-consuming and labor-intensive. The existing automation monitoring solutions cannot be fully automated, and there is a problem that requires manual comparison and confirmation during target monitoring.
By acquiring the array image of the hard press plate, the Hoff linear transformation module, the clustering processing module, the difference calculation module, the average value calculation module, the clustering screening module and the automation monitoring module are used to obtain the array image of the hard press plate and use the Hoff linear transformation and Gaussian filtering, clustering and screening coordinates to realize automated monitoring of hard press plates.
It improves the robustness of monitoring, realizes full automatic monitoring of hard press plates, avoids manual comparison and confirmation, reduces labor costs, and enhances the reliability of monitoring.
Smart Images

Figure CN114862821B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of computer vision and digital image processing, and in particular relates to an automatic monitoring method, system and equipment for a relay protection hard pressure plate. Background Art
[0002] With the development of society, traditional mechanical operation methods have been basically replaced by electrical equipment operations, and electricity has been applied to all aspects of social production and life. The power system is becoming increasingly large, and the system network is becoming more complex. At the same time, as society's dependence on the power system continues to increase, the safety and stability of the power system becomes increasingly important. Once a power system fails, it will cause a large area of production and living systems to be paralyzed, leading to serious consequences. Relay protection is an important device to ensure the safe and reliable operation of the power system. In order to ensure the safe and stable operation of the power system, many researchers have invested in the research of relay protection. Such as research on coordination issues in relay protection, research on the field of microgrids, research on electromagnetic interference, and a series of hardware designs.
[0003] However, while the power system relay protection system plays an important role in the safety and stability of the power system, it has also become increasingly large in the process of continuous development. The safe operation requirements of each link are extremely high. Often a fault or control error may leave a huge hidden danger to the power system. Research on how to ensure the safe and stable operation of the relay protection system has been carried out one after another.
[0004] In order to effectively manage the staff, many control devices are designed in the relay protection system. The automatic intelligent monitoring of these control devices is very important. Among them, the hard pressure plate is an important means to ensure the safe operation of the relay protection system. It is a visible disconnection point, which provides great convenience for the staff to manage, repair and operate the entire power system, but also leaves a disconnection point in the relay protection system that cannot be completely closed. The correctness of the hard pressure plate has a great impact. Missing or mis-applying the hard pressure plate may cause protection refusal or malfunction, bringing serious consequences. Generally, the hard pressure plate is used as a protective tripping and closing switch, and there is no auxiliary monitoring circuit, which makes the relay protection system have great hidden dangers. Although the management departments at all levels have formulated a number of management systems, business guidelines, and operation guidelines to control, although there is a certain effect, the effect is very limited. The traditional manual monitoring method relying on staff cannot achieve a high degree of reliability and has the following disadvantages: (1) It is completely dependent on the staff's sense of responsibility and professional skills, with a high error rate; (2) It requires manual repeated verification, which is time-consuming and labor-intensive, resulting in a waste of manpower costs; (3) It cannot be monitored remotely, making it difficult to detect faults in time.
[0005] In order to realize the automatic intelligent monitoring of the hard pressure plate, some researchers have tried to transform the related devices of the hard pressure plate. For example, a new device is designed by using a double-position relay instead of an electric operating mechanism; a new relay protection hard pressure plate with both a relay protection secondary circuit and an automatic remote signal monitoring circuit is created to assist in realizing automatic intelligent monitoring; and a position sensing sensor is introduced into the hard pressure plate device to realize the automatic monitoring of intelligent sensing.
[0006] However, the modification of the original device increases the complexity of the circuit on the one hand, and introduces uncertainty to the originally stable device on the other hand. In order to avoid the above shortcomings, some researchers have tried to achieve monitoring through computer vision. For example, based on the pictures obtained by the camera, the Adaboost method is used to realize the pressure plate monitoring; for example, the pressure plate pictures are collected by handheld embedded terminals, and the pressure plate monitoring is realized based on YOLO Nano; for example, the pressure plate detection is realized based on Faster R-CNN.
[0007] However, although the above methods effectively avoid introducing uncertainty into the relay protection system, when there are multiple objects in the picture, it is impossible to automatically match the object status with the real object, which results in the need for manual comparison and confirmation during target monitoring. The reason is that the monitoring results are out of order.
[0008] Based on the above analysis, the present invention proposes an automatic monitoring method for a relay protection hard pressure plate. Summary of the invention
[0009] In order to solve the above problems in the prior art, that is, to solve the problem that the traditional relay protection hard pressure plate monitoring scheme is time-consuming and labor-intensive, and the existing automatic monitoring scheme cannot achieve fully automatic monitoring, the first aspect of the present invention proposes an automatic monitoring method for a relay protection hard pressure plate, the method comprising:
[0010] S100, acquiring an array image of a hard pressing plate to be monitored as an input image;
[0011] S200, performing hard pressing plate recognition detection on the input image to obtain the coordinates and state of the hard pressing plate in the input image;
[0012] S300, using the Hough linear transformation method to transform the coordinates of the hard pressing plate into a parameter space, thereby obtaining a parameter space image; performing Gaussian filtering on the parameter space image, and after the processing, obtaining a local peak point whose median value in the parameter space is greater than a set peak threshold;
[0013] S400, clustering the ordinates of each local peak point by a clustering algorithm, and sorting the coordinates in each group of clustering results after clustering in descending order according to the size of the abscissa; after sorting, reassigning an intra-class index to the coordinates in each group of clustering results as a first index;
[0014] S500: subtract the coordinates in each group of clustering results one by one in the order of the first index, and calculate all the differences The mean Compare the difference and mean of each group of clustering results respectively. Then delete the subscript r in each group of clustering results. k The coordinates of each clustering result are reassigned to the intra-class index as the second index;
[0015] S600, obtaining a clustering result with a first number of intra-group coordinates as a first clustering result; reassigning an intra-class index to the intra-coordinates of the first clustering result as a third index, and calculating an average value of the ordinates of the first clustering result The first number is the number of hard pressing plate array columns in the input image;
[0016] S700, respectively calculating the average value of the vertical coordinates of the remaining clustering results except the first clustering result Get The clustering results that belong to the set mean value difference interval and have a second number of intra-group coordinates are used as the second clustering results, and the intra-class index is reassigned to the intra-coordinates of the second clustering results as the fourth index; the second number is the number of rows of the hard pressing plate array columns in the input image;
[0017] S800, based on the first clustering result and the second clustering result, recalculate the coordinates of the hard pressure plate in the input image as the first coordinates; respectively calculate the distance between each first coordinate and the coordinate obtained in S200, and assign the state corresponding to the coordinate with the smallest distance to the first coordinate as the first state; based on the first coordinate and its corresponding first state, compose a new detection result of each hard pressure plate to complete the automatic monitoring.
[0018] In some preferred embodiments, the input image is subjected to hard pressure plate recognition detection, and the method is: the input image is subjected to hard pressure plate recognition detection through an image detection neural network; the image detection neural network is constructed based on a deep neural network.
[0019] In some preferred embodiments, the coordinates of the hard platen are transformed into the parameter space using the Hough linear transformation method, which is as follows:
[0020] ρ=ucosθ+vsinθ
[0021] Among them, u and v represent the coordinates of the hard plate in the input image, and (ρ, θ) represents the parameters of the straight line equation in the parameter space.
[0022] In some preferred embodiments, the peak threshold is set to 0.8 min (m, n), wherein m and n are the number of rows and columns of the hard plate array in the input image, respectively.
[0023] In some preferred embodiments, the set mean value difference interval is (0.45π, 0.55π).
[0024] In some preferred implementations, based on the first clustering result and the second clustering result, the coordinates of the hard pressing plate in the input image are recalculated as the first coordinates, and the method is:
[0025]
[0026]
[0027] Among them, (u p,q , v p,q ) represents the first coordinate, ρ p ,θ p They represent the equation parameters of the p-th line, i.e., the second clustering result, ρ q ,θ q They respectively represent the equation parameters of the qth column line, that is, the first clustering result.
[0028] The second aspect of the present invention proposes an automatic monitoring system for a relay protection hard pressure plate, comprising: an image acquisition module, an image recognition module, a linear transformation module, a cluster processing module, a difference calculation module, an average value calculation module, a cluster screening module, and an automatic monitoring module;
[0029] The data acquisition module is configured to acquire an array image of the hard pressing plate to be monitored as an input image;
[0030] The image recognition module is configured to perform hard pressing plate recognition detection on the input image to obtain the coordinates and state of the hard pressing plate in the input image;
[0031] The linear transformation module is configured to transform the coordinates of the hard pressing plate into the parameter space using the Hough linear transformation method, thereby obtaining a parameter space image; performing Gaussian filtering on the parameter space image, and after processing, obtaining a local peak point whose median value in the parameter space is greater than a set peak threshold;
[0032] The cluster processing module is configured to cluster the ordinates of each local peak point by a clustering algorithm, and sort the coordinates in each group of clustering results after clustering in descending order according to the size of the abscissa; after sorting, reassign the coordinates in each group of clustering results with an intra-class index as the first index;
[0033] The difference calculation module is configured to perform difference calculation on the coordinates in each group of clustering results one by one in the order of the first index, and calculate all the difference values. The mean Compare the difference and mean of each group of clustering results respectively. Then delete the subscript r in each group of clustering results. k The coordinates of each clustering result are reassigned to the intra-class index as the second index;
[0034] The average value calculation module is configured to obtain a clustering result with a first number of coordinates in the group as a first clustering result; reassign an intra-class index to the coordinates in the first clustering result as a third index, and calculate the average value of the vertical coordinates in the first clustering result The first number is the number of hard pressing plate array columns in the input image;
[0035] The cluster screening module is configured to calculate the average value of the vertical coordinates of each group of cluster results except the first cluster result. Get The clustering results that belong to the set threshold interval and have a second number of coordinates in the group are used as the second clustering results, and the coordinates in the second clustering results are reassigned with an intra-class index as the fourth index; the second number is the number of rows of the number of columns of the hard pressing plate array in the input image;
[0036] The automatic monitoring module is configured to recalculate the coordinates of the hard pressure plate in the input image as the first coordinates based on the first clustering results and the second clustering results; respectively calculate the distance between each first coordinate and the coordinate obtained in the image recognition module, and assign the state corresponding to the coordinate with the smallest distance to the first coordinate as the first state; based on the first coordinate and its corresponding first state, form a new detection result of each hard pressure plate to complete the automatic monitoring.
[0037] The third aspect of the present invention proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to at least one of the processors; wherein the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned automated monitoring method of the relay protection hard pressure plate.
[0038] In a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned automatic monitoring method of the relay protection hard pressure plate.
[0039] Beneficial effects of the present invention:
[0040] The present invention solves the problem that the traditional monitoring method is time-consuming and labor-intensive, and the existing automated monitoring cannot be fully automated, and improves the robustness of monitoring.
[0041] The present invention converts the coordinates of the hard plate array in the image into the parameter space and then performs Gaussian filtering to obtain the coordinates of the local peak points. Then, by clustering the local peak points, the difference and average values within each group of clusters are calculated, and the coordinates in the clustering results are screened, and finally the automatic correspondence between the detection state and the object is completed, effectively realizing full automation. This solves the problem that the traditional monitoring solution is time-consuming and labor-intensive, and the existing automated monitoring solution cannot be fully automated. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings.
[0043] Figure 1 It is a flow chart of an automated monitoring method for a relay protection hard pressure plate according to an embodiment of the present invention;
[0044] Figure 2 It is a schematic diagram of the framework of an automatic monitoring system for a relay protection hard pressure plate according to an embodiment of the present invention;
[0045] Figure 3 It is a structural diagram of a computer system of an embodiment of the present invention that is suitable for implementing an electronic device of an embodiment of the present application. DETAILED DESCRIPTION
[0046] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiment is a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0047] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.
[0048] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other.
[0049] The automatic monitoring method of the relay protection hard pressure plate of the present invention is as follows: Figure 1 As shown, the following steps are included:
[0050] S100, acquiring an array image of a hard pressing plate to be monitored as an input image;
[0051] S200, performing hard pressing plate recognition detection on the input image to obtain the coordinates and state of the hard pressing plate in the input image;
[0052] S300, using the Hough linear transformation method to transform the coordinates of the hard pressing plate into a parameter space, thereby obtaining a parameter space image; performing Gaussian filtering on the parameter space image, and after the processing, obtaining a local peak point whose median value in the parameter space is greater than a set peak threshold;
[0053] S400, clustering the ordinates of each local peak point by a clustering algorithm, and sorting the coordinates in each group of clustering results after clustering in descending order according to the size of the abscissa; after sorting, reassigning an intra-class index to the coordinates in each group of clustering results as a first index;
[0054] S500: subtract the coordinates in each group of clustering results one by one in the order of the first index, and calculate all the differences The mean Compare the difference and mean of each group of clustering results respectively. Then delete the subscript r in each group of clustering results. k The coordinates of each clustering result are reassigned to the intra-class index as the second index;
[0055] S600, obtaining a clustering result with a first number of intra-group coordinates as a first clustering result; reassigning an intra-class index to the intra-coordinates of the first clustering result as a third index, and calculating an average value of the ordinates of the first clustering result The first number is the number of hard pressing plate array columns in the input image;
[0056] S700, respectively calculating the average value of the vertical coordinates of the remaining clustering results except the first clustering result Get The clustering results that belong to the set mean value difference interval and have a second number of intra-group coordinates are used as the second clustering results, and the intra-class index is reassigned to the intra-coordinates of the second clustering results as the fourth index; the second number is the number of rows of the hard pressing plate array columns in the input image;
[0057] S800, based on the first clustering result and the second clustering result, recalculate the coordinates of the hard pressure plate in the input image as the first coordinates; respectively calculate the distance between each first coordinate and the coordinate obtained in S200, and assign the state corresponding to the coordinate with the smallest distance to the first coordinate as the first state; based on the first coordinate and its corresponding first state, compose a new detection result of each hard pressure plate to complete the automatic monitoring.
[0058] In order to more clearly illustrate the automatic monitoring system of the relay protection hard pressure plate of the present invention, each step in an embodiment of the method of the present invention is described in detail below with reference to the accompanying drawings.
[0059] S100, acquiring an array image of a hard pressing plate to be monitored as an input image;
[0060] In this embodiment, an array image of the hard pressing plate is first obtained. Generally, the hard pressing plate will set array parameters m, n, h according to actual conditions, where m represents the number of rows of the hard pressing plate array, and n represents the number of columns of the hard pressing plate array. In the present invention, it is assumed that m<n, h=m×n, which represents the total number of hard pressing plates.
[0061] S200, performing hard pressing plate recognition detection on the input image to obtain the coordinates and state of the hard pressing plate in the input image;
[0062] In this embodiment, the input image is subjected to hard platen recognition detection (in the present invention, the input image is preferably subjected to hard platen recognition detection by an image detection neural network; the image detection neural network is constructed based on a deep neural network), and the coordinates and state of the hard platen in the input image are obtained; the i-th hard platen detection result is expressed as: (l i ,s i ), i∈[1,h, where l i =(u i , v i ) represents the position coordinates of the i-th hard plate detection result, s i The state data (e.g., open, closed) of the i-th hard platen test result is represented by the set of each hard platen test result {(l1, s1), (l2, s2), …, (l h ,s h )}.
[0063] S300, using the Hough linear transformation method to transform the coordinates of the hard pressing plate into a parameter space, thereby obtaining a parameter space image; performing Gaussian filtering on the parameter space image, and after the processing, obtaining a local peak point whose median value in the parameter space is greater than a set peak threshold;
[0064] In this embodiment, the coordinates (ui , v i ) is converted to parameter space. The parameters in the parameter space are the parameters of the straight line equation (ρ, θ). The form of the straight line equation is shown in formula (1):
[0065] ρ=ucosθ+vsinθ (1)
[0066] Among them, u and v represent the coordinates of the hard pressure plate in the input image.
[0067] Perform Gaussian filtering on the parameter space image, and then find the coordinates of the local peak points (ρ) for each value greater than 0.8min(m,n) in the parameter space. j ,θ j ), j∈[1,g], where j is the coordinate index, is the number of point coordinates that meet the requirements, and all coordinates form a set {(ρ1,θ1), (ρ2,θ2),…, (ρ g ,θ g )}.
[0068] S400, clustering the ordinates of each local peak point by a clustering algorithm, and sorting the coordinates in each group of clustering results after clustering in descending order according to the size of the abscissa; after sorting, reassigning an intra-class index to the coordinates in each group of clustering results as a first index;
[0069] In this embodiment, based on (ρ j ,θ j ) j The value of is clustered using a clustering algorithm to group similar coordinates into one category, and obtain c groups of clusters. Each coordinate is represented by Representing coordinates In the kth group of clustering results, j k is the index of the coordinate in the clustering result of the kth group, g k is the number of coordinates in the kth clustering result, and c is the number of clustering groups. Each clustering result is expressed as The collection of all clustering results:
[0070] The coordinates in each group of clustering results are sorted from large to small based on the value of ρ, and the intra-class index is reassigned to each coordinate in the group in order as the first index.
[0071] S500: subtract the coordinates in each group of clustering results one by one in the order of the first index, and calculate all the differences The mean Compare the difference and mean of each group of clustering results respectively. Then delete the subscript r in each group of clustering results. kThe coordinates of each clustering result are reassigned to the intra-class index as the second index;
[0072] In this embodiment, the coordinates in each group of clustering results are subtracted one by one in the order of the first index to obtain the difference value Calculate the mean of all differences Each and Compare (i.e., compare the mean of the differences within each group Compared with the difference within this group), if Remove coordinates from clustering results Then, each intra-group coordinate is reassigned the intra-class index as the second index.
[0073] S600, obtaining a clustering result with a first number of intra-group coordinates as a first clustering result; reassigning an intra-class index to the intra-coordinates of the first clustering result as a third index, and calculating an average value of the ordinates of the first clustering result The first number is the number of hard pressing plate array columns in the input image;
[0074] In this embodiment, a cluster containing n coordinates is found from each group of clustering results and is re-expressed as {(ρ1, θ1) col , (ρ2, θ2) col ,…,(ρ n ,θ n ) col} col , and calculate the average value of the intra-class coordinates θ
[0075] S700, respectively calculating the average value of the vertical coordinates of the remaining clustering results except the first clustering result Get The clustering results that belong to the set mean value difference interval and have a second number of intra-group coordinates are used as the second clustering results, and the intra-class index is reassigned to the intra-coordinates of the second clustering results as the fourth index; the second number is the number of rows of the hard pressing plate array columns in the input image;
[0076] In this embodiment, the average value of the intra-class coordinates θ of each group of clustering results except the first clustering result is calculated. Find satisfaction The cluster with m coordinates within the cluster is re-expressed as {(ρ1, θ1) row , (ρ2, θ2) row ,…,(ρ m ,θ m ) row} row .
[0077] S800, based on the first clustering result and the second clustering result, recalculate the coordinates of the hard pressure plate in the input image as the first coordinates; respectively calculate the distance between each first coordinate and the coordinate obtained in S200, and assign the state corresponding to the coordinate with the smallest distance to the first coordinate as the first state; based on the first coordinate and its corresponding first state, compose a new detection result of each hard pressure plate to complete the automatic monitoring.
[0078] In this embodiment, the new detection results (l p,q ,s p,q ), p∈[1,m],q[1,n], where the coordinate l p,q =(u p,q , v p,q ), i.e., the first coordinate, and find the detection result with the closest coordinate distance in the original overall detection result set (here, the detection result obtained in S200) make Complete the automatic correspondence between detection status and objects.
[0079] Coordinate l p,q , which is calculated as:
[0080]
[0081]
[0082] Among them, ρ p ,θ p They represent the equation parameters of the p-th line, i.e., the second clustering result, ρ q ,θ q They respectively represent the equation parameters of the qth column line, that is, the first clustering result.
[0083] As we know from the previous text, the hard pressing plates are arranged in an array, so the coordinates such as the row and column can be used for correspondence. Through the detection of the neural network, several target detection results can be obtained, including the image position and state, but lacking the array position. Through the method described above, several updated results can be obtained, including the image position and array position, which can complete the automatic correspondence, but lack the state. Searching for the latest results in the original detection results can make up for the missing state, thereby realizing automatic monitoring.
[0084] A second embodiment of the present invention is an automatic monitoring system for a relay protection hard pressure plate, such as Figure 2 As shown, it includes: an image acquisition module 100, an image recognition module 200, a straight line transformation module 300, a cluster processing module 400, a difference calculation module 500, an average value calculation module 600, a cluster screening module 700, and an automatic monitoring module 800;
[0085] The data acquisition module 100 is configured to acquire an array image of the hard pressing plate to be monitored as an input image;
[0086] The image recognition module 200 is configured to perform hard pressing plate recognition detection on the input image to obtain the coordinates and state of the hard pressing plate in the input image;
[0087] The linear transformation module 300 is configured to transform the coordinates of the hard pressing plate into the parameter space using the Hough linear transformation method, thereby obtaining a parameter space image; performing Gaussian filtering on the parameter space image, and obtaining a local peak point whose median value in the parameter space is greater than a set peak threshold after the processing;
[0088] The clustering processing module 400 is configured to cluster the ordinates of each local peak point by a clustering algorithm, and sort the coordinates in each group of clustering results after clustering in descending order according to the size of the abscissa; after sorting, reassign the coordinates in each group of clustering results with an intra-class index as the first index;
[0089] The difference calculation module 500 is configured to perform difference calculation on the coordinates in each group of clustering results one by one in the order of the first index, and calculate all the difference values. The mean Compare the difference and mean of each group of clustering results respectively. Then delete the subscript r in each group of clustering results. k The coordinates of each clustering result are reassigned to the intra-class index as the second index;
[0090] The average value calculation module 600 is configured to obtain a clustering result with a first number of coordinates in the group as a first clustering result; reassign an intra-class index to the coordinates in the first clustering result as a third index, and calculate the average value of the vertical coordinates in the first clustering result The first number is the number of hard pressing plate array columns in the input image;
[0091] The cluster screening module 700 is configured to calculate the average value of the vertical coordinates of each group of cluster results except the first cluster result. Get The clustering results that belong to the set threshold interval and have a second number of coordinates in the group are used as the second clustering results, and the coordinates in the second clustering results are reassigned with an intra-class index as the fourth index; the second number is the number of rows of the number of columns of the hard pressing plate array in the input image;
[0092] The automated monitoring module 800 is configured to recalculate the coordinates of the hard pressure plate in the input image as the first coordinates based on the first clustering results and the second clustering results; respectively calculate the distance between each first coordinate and the coordinate obtained in the image recognition module 200, and assign the state corresponding to the coordinate with the smallest distance to the first coordinate as the first state; based on the first coordinate and its corresponding first state, form a new detection result for each hard pressure plate to complete automated monitoring.
[0093] It should be noted that the automatic monitoring system for the relay protection hard pressure plate provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiments can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.
[0094] An electronic device according to the third embodiment of the present invention comprises: at least one processor; and a memory communicatively connected to at least one of the processors; wherein the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned automated monitoring method of the relay protection hard pressure plate.
[0095] A computer-readable storage medium according to a fourth embodiment of the present invention stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned automatic monitoring method of the relay protection hard pressure plate.
[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the storage device and processing device described above can refer to the corresponding process in the aforementioned method example and will not be repeated here.
[0097] Reference below Figure 3 , which shows a schematic diagram of the structure of a computer system of a server suitable for implementing the method, system, and device embodiments of the present application. Figure 3 The server shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0098] like Figure 3As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through a bus 304. Input / output (I / O) interface 305 is also connected to bus 304.
[0099] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.
[0100] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU301), the above functions defined in the method of the present application are executed. It should be noted that the computer-readable medium mentioned in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, device or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
[0101] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0102] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0103] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.
[0104] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.
[0105] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.
Claims
1. An automated monitoring method for a relay protection hard platen, characterized in that: The method comprises the following steps: S100, acquiring an array image of a hard pressing plate to be monitored as an input image; S200, performing hard pressing plate recognition detection on the input image to obtain the coordinates and state of the hard pressing plate in the input image; S300, using the Hough linear transformation method to transform the coordinates of the hard pressing plate into a parameter space, thereby obtaining a parameter space image; performing Gaussian filtering on the parameter space image, and after the processing, obtaining a local peak point whose median value in the parameter space is greater than a set peak threshold; S400, clustering the ordinates of each local peak point by a clustering algorithm, and sorting the coordinates in each group of clustering results after clustering in descending order according to the size of the abscissa; after sorting, reassigning an intra-class index to the coordinates in each group of clustering results as a first index; S500: subtract the coordinates in each group of clustering results one by one in the order of the first index, and calculate all the differences The mean Compare the difference and mean of each group of clustering results respectively. Then delete the subscript r in each group of clustering results. k The coordinates of each clustering result are reassigned to the intra-class index as the second index; S600, obtaining a clustering result with a first number of intra-group coordinates as a first clustering result; reassigning an intra-class index to the intra-coordinates of the first clustering result as a third index, and calculating an average value of the ordinates of the first clustering result The first number is the number of hard pressing plate array columns in the input image; S700, respectively calculating the average value of the vertical coordinates of the remaining clustering results except the first clustering result Get The clustering results that belong to the set mean value difference interval and have a second number of intra-group coordinates are used as the second clustering results, and the intra-class index is reassigned to the intra-coordinates of the second clustering results as the fourth index; the second number is the number of rows of the hard pressing plate array columns in the input image; S800, based on the first clustering result and the second clustering result, recalculate the coordinates of the hard pressure plate in the input image as the first coordinates; respectively calculate the distance between each first coordinate and the coordinate obtained in S200, and assign the state corresponding to the coordinate with the smallest distance to the first coordinate as the first state; based on the first coordinate and its corresponding first state, compose a new detection result of each hard pressure plate to complete the automatic monitoring.
2. The automatic monitoring method of the relay protection hard plate according to claim 1 is characterized in that: The input image is subjected to hard pressure plate recognition detection, and the method is as follows: the input image is subjected to hard pressure plate recognition detection by an image detection neural network; the image detection neural network is constructed based on a deep neural network.
3. The automatic monitoring method of the relay protection hard pressure plate according to claim 2 is characterized in that: The Hough linear transformation method is used to transform the coordinates of the hard platen into the parameter space. The method is: ρ=ucosθ+vsinθ Among them, u and v represent the coordinates of the hard plate in the input image, and (ρ, θ) represents the parameters of the straight line equation in the parameter space.
4. The automatic monitoring method of the relay protection hard plate according to claim 2 is characterized in that: The peak threshold is set to 0.8min(m,n), wherein m and n are the number of rows and columns of the hard pressing plate array in the input image, respectively.
5. The automatic monitoring method of the relay protection hard plate according to claim 4 is characterized in that: The set mean value difference interval is (0.45π, 0.55π).
6. The automatic monitoring method of the relay protection hard pressure plate according to claim 4 is characterized in that: According to the first clustering result and the second clustering result, the coordinates of the hard pressing plate in the input image are recalculated as the first coordinates, and the method is as follows: Among them, (u p,q , v p,q ) represents the first coordinate, ρ p ,θ p They represent the equation parameters of the p-th line, i.e., the second clustering result, ρ q ,θ q They respectively represent the equation parameters of the qth column line, that is, the first clustering result.
7. An automatic monitoring system for a relay protection hard pressure plate, characterized in that: The system includes: an image acquisition module, an image recognition module, a straight line transformation module, a cluster processing module, a difference calculation module, an average value calculation module, a cluster screening module, and an automatic monitoring module; The image acquisition module is configured to acquire an array image of the hard pressing plate to be monitored as an input image; The image recognition module is configured to perform hard pressing plate recognition detection on the input image to obtain the coordinates and state of the hard pressing plate in the input image; The linear transformation module is configured to transform the coordinates of the hard pressing plate into the parameter space using the Hough linear transformation method, thereby obtaining a parameter space image; performing Gaussian filtering on the parameter space image, and after processing, obtaining a local peak point whose median value in the parameter space is greater than a set peak threshold; The cluster processing module is configured to cluster the ordinates of each local peak point by a clustering algorithm, and sort the coordinates in each group of clustering results after clustering in descending order according to the size of the abscissa; after sorting, reassign the coordinates in each group of clustering results with an intra-class index as the first index; The difference calculation module is configured to perform difference on the coordinates in each group of clustering results one by one in the order of the first index, and calculate all the difference values. The mean Compare the difference and mean of each group of clustering results respectively. Then delete the subscript r in each group of clustering results. k The coordinates of each clustering result are reassigned to the intra-class index as the second index; The average value calculation module is configured to obtain a clustering result with a first number of coordinates in the group as a first clustering result; reassign an intra-class index to the coordinates in the first clustering result as a third index, and calculate the average value of the vertical coordinates in the first clustering result The first number is the number of hard pressing plate array columns in the input image; The cluster screening module is configured to calculate the average value of the vertical coordinates of each group of cluster results except the first cluster result. Get The clustering results that belong to the set threshold interval and have a second number of coordinates in the group are used as the second clustering results, and the coordinates in the second clustering results are reassigned with an intra-class index as the fourth index; the second number is the number of rows of the number of columns of the hard pressing plate array in the input image; The automatic monitoring module is configured to recalculate the coordinates of the hard pressure plate in the input image as the first coordinates based on the first clustering results and the second clustering results; respectively calculate the distance between each first coordinate and the coordinate obtained in the image recognition module, and assign the state corresponding to the coordinate with the smallest distance to the first coordinate as the first state; based on the first coordinate and its corresponding first state, form a new detection result of each hard pressure plate to complete the automatic monitoring.
8. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled to at least one of the processors; Wherein, the memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the automatic monitoring method of the relay protection hard pressure plate described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the automatic monitoring method of the relay protection hard pressure plate according to any one of claims 1-6.
