A machine shutdown control method and device, electronic equipment and storage medium

Abstract

This application discloses a machine shutdown control method and apparatus, electronic device, and storage medium. The method includes: acquiring current signal data and current images of each protection device; extracting features from the current image of each protection device to obtain a current image feature matrix; loading a standard image feature matrix of the protection device from an image feature library; randomly generating multiple new current feature matrices in the feature value space corresponding to the protection device, and selecting the current central feature matrix whose deviation from the standard image feature matrix is ​​less than a preset threshold; extracting the center vector with the smallest deviation from the current image feature matrix of the protection device from the current central feature matrix to form the output vector of the protection device; determining whether to shut down the target machine based on the current signal data and output vectors of each protection device; and controlling the shutdown of the target machine if it is determined to shut down the target machine.

Description

Technical Field

[0001] This application relates to the field of machine control technology, and in particular to a machine shutdown control method and device, electronic equipment, and storage medium. Background Technology

[0002] In order to ensure the safe and stable operation of the conveyor, it is necessary to be able to detect various faults of the conveyor in a timely manner and control the conveyor to stop in time to prevent the fault or loss from escalating further, and to facilitate timely maintenance.

[0003] Currently, to ensure timely shutdown of conveyors in case of malfunctions, interlocking shutdown control is the primary method used. Specifically, the conveyor is equipped with multiple protection devices, such as pull ropes, belt misalignment switches, and tear switches. Each protection device is triggered when a different fault occurs in the conveyor, sending a shutdown signal to the conveyor's control system to stop the conveyor promptly. For example, when the belt misaligns, it contacts the belt misalignment switch, which in turn triggers the control system to send a shutdown signal, stopping the conveyor.

[0004] However, when the protection device malfunctions, it may send a stop signal to the conveyor control system even when it is not triggered, or it may be triggered by other external factors, such as accidental contact by personnel or other animals, and send a stop signal to the conveyor control system, thereby causing the conveyor to stop unnecessarily and affecting normal production. Summary of the Invention

[0005] In view of the shortcomings of the prior art, this application provides a machine shutdown control method and device, electronic equipment and storage medium to solve the problem that the prior art is prone to accidental shutdown and affects the normal production of the machine.

[0006] To achieve the above objectives, this application provides the following technical solution:

[0007] The first aspect of this application provides a machine shutdown control method, including:

[0008] Collect current signal data and current images from each protection device;

[0009] For each of the protection devices, feature extraction is performed on the current image of the protection device to obtain the current image feature matrix of the protection device;

[0010] The standard image feature matrix of the protection device is loaded from a pre-built image feature library; wherein, the standard image feature matrix of the protection device is generated based on features in images of the protection device in multiple scenarios;

[0011] In the feature space corresponding to the protection device, multiple new feature matrices are randomly generated, and the new feature matrices whose deviation from the standard image feature matrix is ​​less than a preset threshold are selected as the current center feature matrix.

[0012] Extract the center vector that has the smallest deviation from the current image feature matrix of the protection device from the current center feature matrix, and form the output vector of the protection device;

[0013] Based on the current signal data of each of the protection devices and the output vector of each of the protection devices, it is determined whether to shut down the target machine.

[0014] If it is determined that the target machine needs to be shut down, then the target machine is controlled to be shut down.

[0015] Optionally, in the above-described machine shutdown control method, before acquiring the current signal data and current image of each protection device, the method further includes:

[0016] For each of the protection devices, images of the protection device in multiple scenarios are acquired;

[0017] For each image, local feature points are extracted, and the feature values ​​of the local feature points are calculated.

[0018] The feature values ​​of the image are used to form the feature matrix of the image;

[0019] The feature matrix of the image is stored in the image feature library;

[0020] According to each of the aforementioned protection devices, the image feature matrix in the image feature library is divided into items.

[0021] Optionally, in the above-described machine shutdown control method, the step of randomly generating multiple current new feature matrices in the feature space corresponding to the protection device, and selecting the current new feature matrices whose deviation from the standard image feature matrix is ​​less than a preset threshold as the current center feature matrix, includes:

[0022] In the eigenvalue space corresponding to the protection device, multiple new feature matrices are randomly generated.

[0023] The current new feature matrix with the smallest deviation from the standard image feature matrix is ​​selected from all the current new feature matrices;

[0024] Determine whether the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold;

[0025] If it is determined that the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​not less than a preset threshold, then return to the step of randomly generating multiple new feature matrices in the feature space corresponding to the protection device.

[0026] If it is determined that the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold, then the currently selected new feature matrix is ​​taken as the current center feature matrix.

[0027] Optionally, in the above-described machine shutdown control method, the step of extracting the center vector with the smallest deviation from the current image feature matrix of the protection device from the current center feature matrix to form the output vector of the protection device includes:

[0028] From the center vector of each row of the current center feature matrix, extract the center vector that has the smallest deviation from the feature vector of the corresponding row of the current image feature matrix of the protection device, and form the output vector of the protection device.

[0029] Optionally, in the above-described machine shutdown control method, determining whether to shut down the target machine based on the current signal data of each of the protection devices and the output vector of each of the protection devices includes:

[0030] Each of the aforementioned protection devices whose current signal data belongs to a shutdown signal is selected as the device to be analyzed;

[0031] The output vector of each device to be analyzed is compared with the current image feature matrix of the device to be analyzed to determine whether the device to be analyzed is in a triggered state and whether there are any interfering factors for the device to be analyzed.

[0032] If any of the devices to be analyzed is in a state that triggers a shutdown signal, and there are no interfering factors for the devices to be analyzed, then it is determined that the target machine should be shut down.

[0033] A second aspect of this application provides a machine shutdown control device, comprising:

[0034] The data acquisition unit is used to acquire the current signal data and current images of each protection device;

[0035] The first feature extraction unit is used to extract features from the current image of each of the protection devices to obtain the current image feature matrix of the protection device.

[0036] The loading unit is used to load the standard image feature matrix of the protection device from a pre-built image feature library; wherein the standard image feature matrix of the protection device is generated based on features in images of the protection device in multiple scenarios;

[0037] The matrix update unit is used to randomly generate multiple current new feature matrices in the feature space corresponding to the protection device, and select the current new feature matrices whose deviation from the standard image feature matrix is ​​less than a preset threshold as the current center feature matrix.

[0038] The vector filtering unit is used to extract the center vector with the smallest deviation from the current image feature matrix of the protection device from the current center feature matrix, and form the output vector of the protection device.

[0039] The result determination unit is used to determine whether to shut down the target machine based on the current signal data of each of the protection devices and the output vector of each of the protection devices.

[0040] The shutdown unit is used to control the shutdown of the target machine when it is determined that the target machine should be shut down.

[0041] Optionally, the above-mentioned machine stop control device further includes:

[0042] The image acquisition unit is used to acquire images of each of the protection devices in multiple scenarios;

[0043] The second feature extraction unit is used to extract local feature points of each image and calculate the feature values ​​of the local feature points.

[0044] A matrix composition unit is used to assemble the feature values ​​of the image into a feature matrix of the image.

[0045] A matrix storage unit is used to store the feature matrix of the image into the image feature library;

[0046] The sub-item unit is used to subdivide the image feature matrix in the image feature library according to each of the protection devices.

[0047] Optionally, in the above-described machine shutdown control device, the matrix update unit includes:

[0048] A random generation unit is used to randomly generate multiple current new feature matrices in the feature value space corresponding to the protection device;

[0049] A matrix filtering unit is used to filter out the current new feature matrix that has the smallest deviation from the standard image feature matrix among all the current new feature matrices;

[0050] The judgment unit is used to determine whether the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold.

[0051] The return unit is used to return to the random generation unit to perform the random generation of multiple new feature matrices in the feature space corresponding to the protection device when it is determined that the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​not less than a preset threshold.

[0052] The matrix determination unit is used to determine that when the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold, the currently selected new feature matrix is ​​used as the current center feature matrix.

[0053] Optionally, in the above-described machine shutdown control device, the vector filtering unit includes:

[0054] The vector filtering subunit is used to extract the center vector with the smallest deviation from the feature vector of the corresponding row of the current image feature matrix of the current center feature matrix from the center vector of each row of the current center feature matrix, and form the output vector of the protection device.

[0055] Optionally, in the above-described machine shutdown control device, the result determination unit includes:

[0056] The device filtering unit is used to filter out each of the protection devices whose current signal data belongs to a shutdown signal, as devices to be analyzed;

[0057] The comparison unit is used to compare the output vector of each of the devices to be analyzed with the current image feature matrix of the device to be analyzed, and to determine whether the device to be analyzed is in a triggered state and whether there are any interference factors affecting the device to be analyzed.

[0058] The shutdown determination unit is used to determine to shut down the target machine when any of the devices to be analyzed is in a state that triggers a shutdown signal and there are no interference factors affecting the devices to be analyzed.

[0059] A third aspect of this application provides an electronic device, comprising:

[0060] Memory and processor;

[0061] The memory is used to store programs;

[0062] The processor is used to execute the program, which, when executed, is specifically used to implement the machine shutdown control method as described in any of the above.

[0063] The fourth aspect of this application provides a computer storage medium for storing a computer program, which, when executed, implements the machine shutdown control method as described in any of the preceding claims.

[0064] This application provides a machine shutdown control method. It pre-generates feature matrices from images of each protection device in multiple scenarios and constructs an image feature library. This yields matrices for scenarios such as untriggered and normally triggered scenarios, facilitating subsequent comparative analysis to determine the scenario in which the protection device is located, and thus whether it has been truly triggered, whether the triggering is normal, and whether it has been unaffected by external factors. Specifically, it first collects current signal data and current images of each protection device, and then extracts features from the current image of each protection device to obtain its current image feature matrix. Next, it loads the standard image feature matrix of the protection device from the pre-constructed image feature library. Then, it randomly generates multiple new feature matrices in the feature space corresponding to the protection device, and selects the new feature matrix whose deviation from the standard image feature matrix is ​​less than a preset threshold as the current central feature matrix. It also extracts the center vector from the current central feature matrix that has the smallest deviation from the current image feature matrix of the protection device, forming the output vector of the protection device. This allows for the generation and selection of reasonable comparison feature values ​​based on the current scenario, resulting in more accurate comparison results. Then, based on the current signal data and output vectors of each protection device, it is determined whether to shut down the target machine. Only when it is determined that the target machine should be shut down is the machine controlled to be turned off. By comparing the features of the current field image with the pre-built image feature library, it is determined that if the current signal data is accurate, it is not a false trigger or triggered by other factors, thus avoiding false shutdown and thus avoiding affecting normal production. Attached Figure Description

[0065] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0066] Figure 1 A flowchart illustrating a machine shutdown control method provided in this application embodiment;

[0067] Figure 2 A flowchart illustrating a method for constructing an image feature library as provided in an embodiment of this application;

[0068] Figure 3 A flowchart illustrating a method for generating a current central feature matrix provided in an embodiment of this application;

[0069] Figure 4 A flowchart illustrating a method for determining whether to shut down a target machine based on signal data and output vector, provided in an embodiment of this application;

[0070] Figure 5 A schematic diagram of the architecture of a machine shutdown control device provided in this application embodiment;

[0071] Figure 6 This is a schematic diagram of the architecture of an electronic device provided in an embodiment of this application. Detailed Implementation

[0072] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0073] In this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0074] This application provides a machine shutdown control method, such as... Figure 1 As shown, the specific steps include:

[0075] S101. Collect the current signal data and current image of each protection device.

[0076] In order to ensure the accuracy of the signal data sent by each protection device and avoid false shutdowns, in this embodiment of the application, an image of the current scene of each protection device is collected, i.e., the current image of the protection device, so as to determine whether the protection device is actually triggered and whether there are other external factors affecting it based on the current image of the protection device.

[0077] S102. For each protection device, extract features from the current image of the protection device to obtain the current image feature matrix of the protection device.

[0078] Since each protection device has a different triggering method, triggering state, and potential external influences, it is necessary to analyze each protection device separately. To analyze the status of the protection device and whether it is affected by external factors based on the field image, this embodiment first extracts features from the current image of the protection device to obtain its current image feature matrix, and then performs analysis based on the extracted feature information.

[0079] Optionally, in another embodiment of this application, analyzing the current image of the protective device can involve analyzing the protective device and other objects that may exist in the current image, i.e., analyzing the objects in the current image. Therefore, when extracting features, the main focus is on extracting the contour information of the objects. Thus, a hybrid scanning method can be used to extract the feature information of the image.

[0080] Optionally, the current image can be scanned across all rows first, and the scanned information can be compared with a pre-set local threshold based on the data collected in the experiment to extract the path location information. It should be noted that if no valid path information is extracted in the first few rows during the scan, the current image can be considered invalid and unusable. For subsequent data extraction, an edge-based approach can be adopted, setting a range around the path extracted in the first few rows and performing subsequent tracking within this range. This can significantly reduce the scanning range and save system resources. Optionally, the search range of the edge tracking detection algorithm can also be configured dynamically. If the deviation is small, the search range can be appropriately reduced during subsequent tracking scans; otherwise, the search area can be expanded. It should be noted that in special cases, such as when no valid information is extracted in one row, the search area can be expanded accordingly using the position where the path information was correctly extracted in the previous step during subsequent edge tracking. This allows for accurate extraction of path information with minimal system resources.

[0081] S103. Load the standard image feature matrix of the protection device from the pre-built image feature library.

[0082] It should be noted that, in order to determine whether the protection device is actually in a triggered state and whether it is affected by external factors, an image feature library storing the features of images of each protection device in multiple scenarios is pre-constructed in this embodiment. This allows the scene in which the current protection device is located to be determined by comparing it with the standard image feature matrix in the image feature library and the image feature matrix of the current image, thereby determining whether it has been triggered and has not been affected by external factors.

[0083] The standard image feature matrix of the protection device is generated based on features from images of the protection device in multiple scenarios. These multiple scenario-specific images include at least images of the protection device when it is not triggered and images of it when it is normally triggered without being affected by external factors. By comparing the features of these two types of images, it can be determined whether the protection device is in a triggered state and whether it has been affected by external factors. Furthermore, images of the protection device triggered by different external factors can be included, allowing for more precise analysis of whether it has been affected by external factors.

[0084] Optionally, another embodiment of this application provides a method for constructing an image feature library, such as... Figure 2 As shown, it includes:

[0085] S201. For each protection device, acquire images of the protection device in multiple scenarios.

[0086] S202. For each image, extract the local feature points and calculate the feature values ​​of the local feature points.

[0087] It should be noted that content-based image retrieval mainly uses low-level visual features, such as action, color, shape, shadow, brightness, and spatial relationship between objects, when describing image content. In other words, the color, shape, shadow, and brightness features of an image reflect the attributes of the image from different perspectives, so it is possible to collect various feature information such as action, color, and shape of the image.

[0088] S203. Combine the feature values ​​of the image to form the feature matrix of the image.

[0089] Specifically, the feature values ​​of each image are represented in the form of a matrix, and the data represented by the matrix can be put into a vectorized feature library, so that the feature points of the image are represented as feature vectors, and then the feature vectors are stored in the image feature library.

[0090] S204. Store the feature matrix of the image into the image feature library.

[0091] S205. Divide the image feature matrix in the image feature library into items according to each protection device.

[0092] S104. In the feature space corresponding to the protection device, multiple new feature matrices are randomly generated, and the new feature matrices whose deviation from the standard image feature matrix is ​​less than a preset threshold are selected as the current center feature matrix.

[0093] It should be noted that, since it is impossible to consider all scenarios when constructing the image feature library, and multiple states may exist between two states, for example, for a pull-cord switch, when it is not triggered, the state of the plastic-coated steel wire rope of the pull switch is a straight line, while when it is fully triggered, it presents a slightly angled "V" shape. Between these two states, there may be multiple states, i.e., various smaller angled "V" shapes. Therefore, in this embodiment, multiple new feature matrices are randomly generated in the feature value space corresponding to the protection device, i.e., within the range of a corresponding feature value. Then, the new feature matrix whose deviation from the standard image feature matrix is ​​less than a preset threshold is selected as the current central feature matrix, which is used for comparative analysis with the image feature matrix of the current image.

[0094] Optionally, in another embodiment of this application, one specific implementation of step S104 is as follows: Figure 3 As shown, it includes:

[0095] S301. In the eigenvalue space corresponding to the protection device, randomly generate multiple current new feature matrices.

[0096] S302. Select the current new feature matrix with the smallest deviation from the standard image feature matrix among all current new feature matrices.

[0097] S303. Determine whether the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold.

[0098] If it is determined that the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​not less than a preset threshold, it indicates that the errors of the generated new feature matrices are all too large, so the process returns to step S301. If it is determined that the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold, then step S304 is executed.

[0099] S304. Use the currently selected new feature matrix as the current center feature matrix.

[0100] S105. Extract the center vector with the smallest deviation from the current image feature matrix of the protection device from the current center feature matrix, and form the output vector of the protection device.

[0101] Since the current central feature matrix is ​​composed of feature values ​​from various scenarios, it is necessary to select the central vector that deviates the least from the current image feature matrix, that is, to obtain the feature values ​​that are close to the current scene, and form the output vector of the protection device for subsequent analysis.

[0102] Optionally, in another embodiment of this application, one specific implementation of step S105 includes:

[0103] From the center vector of each row of the current center feature matrix, extract the center vector with the smallest deviation from the feature vector of the corresponding row of the current image feature matrix of the protection device, and form the output vector of the protection device.

[0104] Specifically, for each row in the current central feature matrix, the deviation between the central vector of that row in the current central feature matrix and the features of the same row in the current image feature matrix of the protection device is calculated, and the central vector with the smallest deviation is selected to form the output vector of the protection device.

[0105] S106. Based on the current signal data of each protection device and the output vector of each protection device, determine whether to shut down the target machine.

[0106] Specifically, based on the current signal data of the protection device, it can be determined whether the protection state has triggered a shutdown signal. Since the output vector of the protection device corresponds to the current scene image, this vector can be used to determine whether the protection device is in a triggered state and whether there are other external factors affecting the scene. When the current signal data of any protection device is a shutdown signal, and based on the output vector of that protection device, it is determined that the protection device has indeed been triggered, and there are no other external factors affecting it, it can be determined that the target machine should be shut down, and step S107 should be executed.

[0107] Optionally, in another embodiment of this application, one specific implementation of step S106 is as follows: Figure 4 As shown, it includes:

[0108] S401. Select the protection devices whose current signal data belongs to the shutdown signal as the devices to be analyzed.

[0109] S402. Compare the output vector of each device to be analyzed with the current image feature matrix of the device to be analyzed to determine whether the device to be analyzed is in a triggered state and whether there are any interference factors affecting the device to be analyzed.

[0110] It should be noted that the output vector of each device under analysis reflects the scene under standard conditions that is closest to the current scene of the device under analysis. However, by comparing them, it can be determined whether the difference between the two is within the allowable range, thereby determining whether it conforms to the scene, and further determining whether the device under analysis is in a triggered state and whether there are no interference factors affecting the device under analysis.

[0111] If any device to be analyzed is in a state where a shutdown signal has been triggered, and there are no interference factors affecting the device to be analyzed, then step S403 is executed.

[0112] S403. Determine to shut down the target machine.

[0113] S107, Control the shutdown of the target machine.

[0114] This application provides a machine shutdown control method. It pre-generates feature matrices from images of each protection device in multiple scenarios and constructs an image feature library. This yields matrices for scenarios such as untriggered and normally triggered scenarios, facilitating subsequent comparative analysis to determine the scenario in which the protection device is located, and thus whether it has been truly triggered, whether it was a normal trigger, and whether it was unaffected by external factors. Specifically, it first collects current signal data and current images of each protection device, and then extracts features from the current image of each protection device to obtain its current image feature matrix. Next, it loads the standard image feature matrix of the protection device from the pre-constructed image feature library. Then, it randomly generates multiple new feature matrices in the feature value space corresponding to the protection device, and selects the new feature matrix whose deviation from the standard image feature matrix is ​​less than a preset threshold as the current central feature matrix. It also extracts the center vector from the current central feature matrix that has the smallest deviation from the current image feature matrix of the protection device, forming the output vector of the protection device. This allows for the generation and selection of reasonable comparison feature values ​​based on the current scenario, resulting in more accurate comparison results. Then, based on the current signal data and output vectors of each protection device, it is determined whether to shut down the target machine. Only when it is determined that the target machine should be shut down is the machine controlled to be turned off. By comparing the features of the current field image with the pre-built image feature library, it is determined that if the current signal data is accurate, it is not a false trigger or triggered by other factors, thus avoiding false shutdown and thus avoiding affecting normal production.

[0115] Another embodiment of this application provides a machine shutdown control device, such as... Figure 5 As shown, it includes the following units:

[0116] The data acquisition unit 501 is used to acquire the current signal data and current image of each protection device.

[0117] The first feature extraction unit 502 is used to extract features from the current image of each protection device to obtain the current image feature matrix of the protection device.

[0118] The loading unit 503 is used to load the standard image feature matrix of the protection device from a pre-built image feature library.

[0119] The standard image feature matrix of the protection device is generated based on features from images of the protection device in multiple scenarios.

[0120] The matrix update unit 504 is used to randomly generate multiple new feature matrices in the feature space corresponding to the protection device, and select the new feature matrices whose deviation from the standard image feature matrix is ​​less than a preset threshold as the current center feature matrix.

[0121] The vector filtering unit 505 is used to extract the center vector with the smallest deviation from the current image feature matrix of the protection device from the current center feature matrix, and form the output vector of the protection device.

[0122] The result determination unit 506 is used to determine whether to shut down the target machine based on the current signal data of each protection device and the output vector of each protection device.

[0123] The shutdown unit 507 is used to control the shutdown of the target machine when it is determined that the target machine should be shut down.

[0124] Optionally, in another embodiment of the machine stop control device provided in this application, the following further includes:

[0125] The image acquisition unit is used to acquire images of each protection device in multiple scenarios.

[0126] The second feature extraction unit is used to extract local feature points of each image and calculate the feature values ​​of the local feature points.

[0127] Matrix composition unit, used to assemble the feature values ​​of an image into a feature matrix of the image.

[0128] The matrix storage unit is used to store the feature matrix of an image into the image feature library.

[0129] The sub-item unit is used to subdivide the image feature matrix in the image feature library according to each protection device.

[0130] Optionally, in another embodiment of the machine shutdown control device provided in this application, the matrix update unit includes:

[0131] The random generation unit is used to randomly generate multiple new feature matrices in the eigenvalue space corresponding to the protection device.

[0132] The matrix filtering unit is used to filter out the current new feature matrix that has the smallest deviation from the standard image feature matrix among all the current new feature matrices.

[0133] The judgment unit is used to determine whether the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold.

[0134] The return unit is used to return to the random generation unit when it is determined that the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​not less than a preset threshold. In this case, the random generation unit will randomly generate multiple new feature matrices in the feature space corresponding to the protection device.

[0135] The matrix determination unit is used to determine the current new feature matrix as the current center feature matrix when the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold.

[0136] Optionally, in another embodiment of the machine shutdown control device provided in this application, the vector filtering unit includes:

[0137] The vector filtering subunit is used to extract the center vector with the smallest deviation from the feature vector of the corresponding row of the current image feature matrix from the center vector of the current center feature matrix, and form the output vector of the protection device.

[0138] Optionally, in another embodiment of the machine shutdown control device provided in this application, the result determination unit includes:

[0139] The device screening unit is used to screen out the protection devices whose current signal data belongs to the shutdown signal, and select them as the devices to be analyzed.

[0140] The comparison unit is used to compare the output vector of each device to be analyzed with the current image feature matrix of the device to be analyzed, and to determine whether the device to be analyzed is in a triggered state and whether there are any interference factors affecting the device to be analyzed.

[0141] The shutdown determination unit is used to determine to shut down the target machine when any device to be analyzed is in a state that triggers a shutdown signal and there are no interference factors affecting the device to be analyzed.

[0142] It should be noted that the specific working process of each unit provided in the above embodiments of this application can be referred to the implementation process of the corresponding steps in the above method embodiments, and will not be repeated here.

[0143] Another embodiment of this application provides an electronic device, such as... Figure 6 As shown, it includes:

[0144] Memory 601 and processor 602.

[0145] The memory 601 is used to store the program.

[0146] The processor 602 is used to execute the program stored in the memory 601. When the program is executed, it is specifically used to implement the machine shutdown control method provided in any of the above embodiments.

[0147] Another embodiment of this application provides a computer storage medium for storing a computer program, which, when executed, implements the machine shutdown control method provided in any of the above embodiments.

[0148] Computer storage media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0149] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0150] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A machine shutdown control method, characterized in that, include: Collect current signal data and current images from each protection device; For each of the protection devices, feature extraction is performed on the current image of the protection device to obtain the current image feature matrix of the protection device; The standard image feature matrix of the protection device is loaded from a pre-built image feature library; wherein, the standard image feature matrix of the protection device is generated based on features in images of the protection device in multiple scenarios; In the feature space corresponding to the protection device, multiple new feature matrices are randomly generated, and the new feature matrices whose deviation from the standard image feature matrix is ​​less than a preset threshold are selected as the current center feature matrix. Extract the center vector that has the smallest deviation from the current image feature matrix of the protection device from the current center feature matrix, and form the output vector of the protection device; Based on the current signal data of each of the protection devices and the output vector of each of the protection devices, determine whether to shut down the target machine; If it is determined that the target machine needs to be shut down, then control the shutdown of the target machine; Before acquiring the current signal data and current image of each protection device, the process also includes: For each of the protection devices, images of the protection device in multiple scenarios are acquired; For each image, local feature points are extracted, and the feature values ​​of the local feature points are calculated. The feature values ​​of the image are used to form the feature matrix of the image; The feature matrix of the image is stored in the image feature library; According to each of the aforementioned protection devices, the image feature matrix in the image feature library is divided into items.

2. The method according to claim 1, characterized in that, In the eigenvalue space corresponding to the protection device, multiple new feature matrices are randomly generated, and the new feature matrices whose deviation from the standard image feature matrix is ​​less than a preset threshold are selected as the current center feature matrix, including: In the eigenvalue space corresponding to the protection device, multiple new feature matrices are randomly generated. The current new feature matrix with the smallest deviation from the standard image feature matrix is ​​selected from all the current new feature matrices; Determine whether the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold; If it is determined that the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​not less than a preset threshold, then return to the step of randomly generating multiple new feature matrices in the feature space corresponding to the protection device. If it is determined that the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold, then the currently selected new feature matrix is ​​taken as the current center feature matrix.

3. The method according to claim 1, characterized in that, The step of extracting the center vector with the smallest deviation from the current image feature matrix of the protection device from the current center feature matrix to form the output vector of the protection device includes: From the center vector of each row of the current center feature matrix, extract the center vector that has the smallest deviation from the feature vector of the corresponding row of the current image feature matrix of the protection device, and form the output vector of the protection device.

4. The method according to claim 1, characterized in that, The step of determining whether to shut down the target machine based on the current signal data of each of the protection devices and the output vector of each of the protection devices includes: Each of the aforementioned protection devices whose current signal data belongs to a shutdown signal is selected as the device to be analyzed; The output vector of each device to be analyzed is compared with the current image feature matrix of the device to be analyzed to determine whether the device to be analyzed is in a triggered state and whether there are any interfering factors for the device to be analyzed. If any of the devices to be analyzed is in a state that triggers a shutdown signal, and there are no interfering factors for the devices to be analyzed, then it is determined that the target machine should be shut down.

5. A machine stop control device, characterized in that, include: The data acquisition unit is used to acquire the current signal data and current images of each protection device; The first feature extraction unit is used to extract features from the current image of each of the protection devices to obtain the current image feature matrix of the protection device. The loading unit is used to load the standard image feature matrix of the protection device from a pre-built image feature library; wherein the standard image feature matrix of the protection device is generated based on features in images of the protection device in multiple scenarios; The matrix update unit is used to randomly generate multiple current new feature matrices in the feature space corresponding to the protection device, and select the current new feature matrices whose deviation from the standard image feature matrix is ​​less than a preset threshold as the current center feature matrix. The vector filtering unit is used to extract the center vector with the smallest deviation from the current image feature matrix of the protection device from the current center feature matrix, and form the output vector of the protection device. The result determination unit is used to determine whether to shut down the target machine based on the current signal data of each of the protection devices and the output vector of each of the protection devices. A shutdown unit is used to control the shutdown of the target machine when it is determined that the target machine should be shut down. The image acquisition unit is used to acquire images of each of the protection devices in multiple scenarios; The second feature extraction unit is used to extract local feature points of each image and calculate the feature values ​​of the local feature points. A matrix composition unit is used to assemble the feature values ​​of the image into a feature matrix of the image. A matrix storage unit is used to store the feature matrix of the image into the image feature library; The sub-item unit is used to subdivide the image feature matrix in the image feature library according to each of the protection devices.

6. The apparatus according to claim 5, characterized in that, The matrix update unit includes: A random generation unit is used to randomly generate multiple current new feature matrices in the feature value space corresponding to the protection device; A matrix filtering unit is used to filter out the current new feature matrix that has the smallest deviation from the standard image feature matrix among all the current new feature matrices; The judgment unit is used to determine whether the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold. The return unit is used to return to the random generation unit to perform the random generation of multiple new feature matrices in the feature space corresponding to the protection device when it is determined that the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​not less than a preset threshold. The matrix determination unit is used to take the currently selected new feature matrix as the current center feature matrix when it is determined that the deviation between the currently selected new feature matrix and the standard image feature matrix is ​​less than a preset threshold.

7. An electronic device, characterized in that, include: Memory and processor; The memory is used to store programs; The processor is used to execute the program, which, when executed, is specifically used to implement the machine shutdown control method as described in any one of claims 1 to 4.

8. A computer storage medium, characterized in that, Used to store a computer program, which, when executed, is used to implement the machine shutdown control method as described in any one of claims 1 to 4.

Images