CN111339933A - Transformer substation safety monitoring method and device based on deep learning - Google Patents
Transformer substation safety monitoring method and device based on deep learning Download PDFInfo
- Publication number
- CN111339933A CN111339933A CN202010116140.0A CN202010116140A CN111339933A CN 111339933 A CN111339933 A CN 111339933A CN 202010116140 A CN202010116140 A CN 202010116140A CN 111339933 A CN111339933 A CN 111339933A
- Authority
- CN
- China
- Prior art keywords
- staff
- compliance
- training
- deep learning
- transformer substation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Abstract
The embodiment of the application provides a transformer substation safety monitoring method and device based on deep learning, wherein the method comprises the following steps: acquiring images of the staff through an image acquisition device arranged in the transformer substation to obtain a current staff image; performing compliance judgment on the current employee image according to a preset employee compliance inspection model; if the compliance judgment result is that the data fails, sending an alarm instruction to an alarm device arranged in the transformer substation; the safety monitoring efficiency and the reliability of the transformer substation can be effectively improved, and therefore the probability of safety accidents is reduced.
Description
Technical Field
The application relates to the field of deep learning, in particular to a transformer substation safety monitoring method and device based on deep learning.
Background
At present, most of domestic substations adopt an unattended or patrol management mode, and once an accident occurs to a person entering the substation, the health and even the life of the worker are easily endangered. Although the transformer substation management has clear safety regulations, for example, anyone entering a transformer substation production site must wear safety helmets and work clothes, many other personnel such as temporary workers and civil workers often have weak safety consciousness when entering the transformer substation, meanwhile, a large amount of time must be consumed for strict supervision and inspection when a transportation and inspection person enters the station by an operation on-duty person, manpower and material resources are consumed seriously, and once negligence occurs, a great potential safety hazard can be caused.
Disclosure of Invention
Aiming at the problems in the prior art, the application provides a transformer substation safety monitoring method and device based on deep learning, which can effectively improve the safety monitoring efficiency and reliability of a transformer substation, thereby reducing the probability of safety accidents.
In order to solve at least one of the above problems, the present application provides the following technical solutions:
in a first aspect, the application provides a transformer substation safety monitoring method based on deep learning, including:
acquiring images of the staff through an image acquisition device arranged in the transformer substation to obtain a current staff image;
performing compliance judgment on the current employee image according to a preset employee compliance inspection model;
and if the compliance judgment result is that the data fails, sending an alarm instruction to an alarm device arranged in the transformer substation.
Further, before the performing compliance judgment on the current employee image according to a preset employee compliance check model, the method includes:
collecting training data for training the staff compliance inspection model;
performing data decomposition on the training data;
and carrying out convolutional neural network training on the training data subjected to the data decomposition to obtain the staff compliance inspection model.
Further, the collecting training data for training the employee compliance check model includes:
collecting a sample image of the employee;
and marking the sample image, wherein the marking comprises at least one of a marking indicating whether the staff wears a safety helmet or not, a marking indicating whether the staff wears a work clothes or not and a marking indicating staff information obtained according to the staff face image.
Further, before the obtaining the employee compliance check model, the method includes:
performing convolutional neural network training on the training data to obtain an error value of the training data and the real data;
correcting the error value;
and judging whether the error value after the correction processing reaches a preset target value, if so, finishing the training, and otherwise, performing the training again.
In a second aspect, the present application provides a transformer substation safety monitoring device based on deep learning, including:
the image acquisition module is used for acquiring images of the staff through an image acquisition device arranged in the transformer substation to obtain a current staff image;
the model judgment module is used for carrying out compliance judgment on the current employee image according to a preset employee compliance inspection model;
and the abnormity warning module is used for sending a warning instruction to a warning device arranged in the transformer substation when the compliance judgment result is that the compliance judgment result does not pass.
Further, still include:
the training data acquisition unit is used for acquiring training data of the staff compliance inspection model;
the training data decomposition unit is used for carrying out data decomposition on the training data;
and the neural network training unit is used for carrying out convolutional neural network training on the training data subjected to the data decomposition to obtain the staff compliance inspection model.
Further, the training data acquisition unit includes:
the sample image acquisition subunit is used for acquiring sample images of the staff;
and the sample image labeling subunit is used for labeling the sample image, wherein the labeling comprises at least one of a label indicating whether the staff wears a safety helmet or not, a label indicating whether the staff wears a work clothes or not and a label indicating staff information obtained according to the staff face image.
Further, still include:
the error determining unit is used for carrying out convolutional neural network training on the training data to obtain an error value of the training data and the real data;
the error correction unit is used for correcting the error value;
and the error standard-reaching judging unit is used for judging whether the error value after the correction processing reaches a preset target value, if so, finishing the training, and otherwise, performing the training again.
In a third aspect, the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the deep learning-based substation security monitoring method when executing the program.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the deep learning-based substation security monitoring method.
According to the technical scheme, the transformer substation safety monitoring method and device based on deep learning are characterized in that real-time image acquisition is carried out on staff through an image acquisition device arranged in a transformer substation, the staff are subjected to compliance judgment according to the current staff image obtained through acquisition and a preset staff compliance inspection model trained through a deep learning neural network, if the staff do not pass through the compliance judgment result, an alarm instruction is sent to an alarm device arranged in the transformer substation, the non-compliance condition of the staff in the transformer substation is prompted and corrected, the reliability and the efficiency of transformer substation safety monitoring are improved, and the probability of safety accidents is further reduced.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is one of flow diagrams of a transformer substation safety monitoring method based on deep learning in an embodiment of the present application;
fig. 2 is a second schematic flowchart of a transformer substation safety monitoring method based on deep learning in the embodiment of the present application;
fig. 3 is a third schematic flowchart of a transformer substation safety monitoring method based on deep learning in the embodiment of the present application;
fig. 4 is a fourth schematic flowchart of a transformer substation safety monitoring method based on deep learning in the embodiment of the present application;
fig. 5 is a schematic view of an application scenario of a transformer substation safety monitoring method based on deep learning in an embodiment of the present application;
fig. 6 is one of structural diagrams of a deep learning-based substation safety monitoring device in an embodiment of the present application;
fig. 7 is a second structural diagram of a transformer substation safety monitoring device based on deep learning in the embodiment of the present application;
fig. 8 is a third structural diagram of a transformer substation safety monitoring device based on deep learning in the embodiment of the present application;
fig. 9 is a fourth structural diagram of a transformer substation safety monitoring device based on deep learning in the embodiment of the present application;
fig. 10 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Considering that most of the transformer substations in the prior art adopt an unattended or maintenance-patrol management mode, once an accident occurs to a person entering the transformer substation, the health and the life of the worker are easily endangered, although the transformer substation management has clear safety regulations, for example, when anyone enters a transformer substation production site, the worker must wear a safety helmet and wear a working clothes, but often, the safety consciousness is weak when other unit personnel such as temporary workers, civil workers and the like enter the transformer substation, meanwhile, a large amount of time must be consumed for strictly supervising and checking when a person on duty operates and arrives at the station, manpower and material resources are seriously consumed, and once the person is neglected, a great potential safety hazard can be caused, the transformer substation safety monitoring method and device based on deep learning are provided, and the image acquisition device arranged in the transformer substation is used for acquiring images of the worker in real time, and performing compliance judgment on the staff according to the acquired current staff image and a preset staff compliance inspection model trained by a deep learning neural network, if the staff does not pass the compliance judgment result, sending an alarm instruction to an alarm device arranged in the transformer substation, and timely prompting and correcting the non-compliance condition of the staff in the transformer substation, so that the reliability and the efficiency of transformer substation safety monitoring are improved, and the probability of safety accidents is further reduced.
In order to effectively improve the safety monitoring efficiency and reliability of the transformer substation and reduce the probability of safety accidents, the present application provides an embodiment of a transformer substation safety monitoring method based on deep learning, and referring to fig. 1 and 5, the transformer substation safety monitoring method based on deep learning specifically includes the following contents:
step S101: and acquiring images of the staff through an image acquisition device arranged in the transformer substation to obtain the current images of the staff.
It can be understood that the image acquisition device can be an existing camera device and can upload images acquired in real time to the server side of the application.
Optionally, the image acquisition device may be disposed at an inlet of the substation, or may be disposed at any position in the substation.
Step S102: and performing compliance judgment on the current employee image according to a preset employee compliance inspection model.
Optionally, in the application, a staff compliance check model is preset to perform image recognition, image analysis and judgment on the received current staff image acquired by the image acquisition device, and the staff compliance check model may be a model obtained by a convolutional neural network based on deep learning and capable of automatically recognizing the video stream of the image acquisition device.
Optionally, the staff compliance inspection model may be deployed at a server side of the application, or may be deployed locally at a substation connected to the image acquisition device.
Optionally, the compliance determination includes, but is not limited to: whether the staff wears safety helmets or not, whether the staff wears work clothes or not and whether the staff has the right of entering the station or not can be determined, in other embodiments of the application, the judgment condition of the compliance judgment can be defined as other judgment conditions, and the training data can be marked to obtain a corresponding staff compliance check model.
Step S103: and if the compliance judgment result is that the data fails, sending an alarm instruction to an alarm device arranged in the transformer substation.
Optionally, if the staff compliance checking model determines that the compliance judgment result of the current staff image does not pass the compliance judgment result, an alarm instruction may be sent to an alarm device arranged at a corresponding position (for example, a station entrance) in the substation, and the alarm device may adopt an existing sound and light alarm device.
Optionally, if the result of the compliance judgment of the current employee image is judged to be passed through the employee compliance inspection model, a brake opening instruction may be sent to a brake set at the station entrance of the substation, so that the corresponding employee enters the substation.
According to the transformer substation safety monitoring method based on deep learning, the image acquisition device arranged in the transformer substation can be used for acquiring images of the staff in real time, the staff is subjected to compliance judgment according to the acquired current staff image and a preset staff compliance inspection model trained through the deep learning neural network, if the compliance judgment result is that the staff does not pass through the image acquisition device, an alarm instruction is sent to the alarm device arranged in the transformer substation, the non-compliance condition of the staff in the transformer substation is timely prompted and corrected, the reliability and the efficiency of transformer substation safety monitoring are improved, and the probability of safety accidents is further reduced.
In order to realize automation and intellectualization of staff compliance check through a convolutional neural network of a deep learning technology, in an embodiment of the transformer substation security monitoring method based on deep learning of the present application, referring to fig. 2, the following contents are also specifically included:
step S201: training data for training the employee compliance check model is collected.
Optionally, an image acquisition device is used for acquiring images of the staff, the image acquisition device may be a high-definition camera or other devices capable of acquiring images, compliance information of the staff is customized through a system, and the customized compliance information includes: whether the employee wears a safety helmet or not, whether the employee wears a work clothes or not and whether the employee has the right to get in the station or not, in other embodiments of the application, the compliance information may also be other information related to the employee; and manually dividing the positions of the safety helmet and the work clothes in the current employee image, and marking the compliance information of the employees as training data.
Step S202: and performing data decomposition on the training data.
Optionally, the data decomposition operation may be a classification operation performed on the training data according to a preset classification rule to obtain employee category information, or may also be a region division performed on a current employee image in the training data to obtain a plurality of divided current employee images.
Step S203: and carrying out convolutional neural network training on the training data subjected to the data decomposition to obtain the staff compliance inspection model.
Optionally, performing RCNN convolutional neural network training on the training data subjected to data decomposition to obtain the staff compliance inspection model.
In order to accurately label the training data of the neural network, in an embodiment of the transformer substation safety monitoring method based on deep learning according to the present application, referring to fig. 3, the following contents are further specifically included:
step S301: a sample image of the employee is collected.
Optionally, an image acquisition device is used for acquiring images of the staff to obtain sample images of the staff, the sample images are appearance images of the staff in an actual production environment, and the image acquisition device may be a high-definition camera or other devices capable of acquiring images.
Step S302: and marking the sample image, wherein the marking comprises at least one of a marking indicating whether the staff wears a safety helmet or not, a marking indicating whether the staff wears a work clothes or not and a marking indicating staff information obtained according to the staff face image.
Optionally, the compliance condition of the sample image is pre-customized in a system database, and specifically, the customized compliance condition includes: whether the employee wears a safety helmet or not, whether the employee wears a work clothes or not and whether the employee has the right to get in the station or not, in other embodiments of the application, the compliance condition may also be other information related to the employee; positions related to the compliance conditions (such as the position of a safety helmet and the position of a work clothes) are manually classified in the sample image, and staff information of the staff is marked.
In order to obtain an effective staff compliance inspection model, in an embodiment of the transformer substation security monitoring method based on deep learning according to the present application, referring to fig. 4, the following contents are further specifically included:
step S401: and carrying out convolutional neural network training on the training data to obtain an error value of the training data and the real data.
Optionally, the RCNN neural network training is performed on the sample image to obtain a predicted value, and an error value between the predicted value and a true value of the labeled data is calculated.
Step S402: and carrying out correction processing on the error value.
Optionally, the error value is a calculation result of a loss function, the degree of inconsistency between a predicted value and a true value of a model calculated by the loss function is optimized according to the error value and the optimized parameters of the loss function, the parameters of the RCNN neural network are trained again, errors between the continuously corrected and marked data are corrected, a new error value closer to the true value is obtained, the correction is performed again, and error correction operation is performed in the RCNN neural network of the present application for approximately 3 ten thousand times.
Step S403: and judging whether the error value after the correction processing reaches a preset target value, if so, finishing the training, and otherwise, performing the training again.
Optionally, the preset target value is equivalent to a value of the label information, i.e. a real value, and is equal to or converges to the real value, and the expected value is equivalent to a degree of closeness of the real value, i.e. a magnitude of the error value.
Optionally, if it is determined that the current error value after the error correction operation is within the preset range, ending the neural network training, and obtaining the staff compliance check model according to the training result.
In order to effectively improve the safety monitoring efficiency and reliability of the transformer substation and reduce the probability of safety accidents, the application provides an embodiment of a transformer substation safety monitoring device based on deep learning, which is used for implementing all or part of the contents of the transformer substation safety monitoring method based on deep learning, and referring to fig. 6, the transformer substation safety monitoring device based on deep learning specifically includes the following contents:
and the image acquisition module 10 is used for acquiring images of the staff through an image acquisition device arranged in the transformer substation to obtain the current staff image.
And the model judgment module 20 is used for performing compliance judgment on the current employee image according to a preset employee compliance check model.
And the abnormal alarm module 30 is configured to send an alarm instruction to an alarm device arranged in the substation when the compliance judgment result is that the fault condition does not pass.
According to the transformer substation safety monitoring device based on deep learning, the image acquisition device arranged in the transformer substation can be used for acquiring images of the staff in real time, the staff is subjected to compliance judgment according to the acquired current staff image and a preset staff compliance inspection model trained through the deep learning neural network, if the compliance judgment result is that the staff does not pass through, an alarm instruction is sent to the alarm device arranged in the transformer substation, the out-of-compliance condition of the staff in the transformer substation is timely prompted and corrected, the reliability and the efficiency of transformer substation safety monitoring are improved, and the probability of safety accidents is further reduced.
In order to realize automation and intellectualization of staff compliance check through a convolutional neural network of a deep learning technology, in an embodiment of the transformer substation security monitoring device based on deep learning of the present application, referring to fig. 7, the following contents are also specifically included:
a training data collecting unit 41, configured to collect training data for training the employee compliance check model.
And a training data decomposition unit 42, configured to perform data decomposition on the training data.
And the neural network training unit 43 is configured to perform convolutional neural network training on the training data subjected to the data decomposition to obtain the staff compliance inspection model.
In order to accurately label the training data of the neural network, in an embodiment of the deep learning-based substation safety monitoring device of the present application, referring to fig. 8, the training data collecting unit 41 includes:
and the sample image acquisition subunit 411 is used for acquiring a sample image of the employee.
And the sample image labeling subunit 412 is configured to label the sample image, where the label includes at least one of a label indicating whether the employee wears a safety helmet, a label indicating whether the employee wears a work clothes, and a label indicating staff information obtained according to the staff face image.
In order to obtain an effective employee compliance check model, in an embodiment of the substation security monitoring device based on deep learning of the present application, referring to fig. 9, the method further includes:
and an error determining unit 51, configured to perform convolutional neural network training on the training data to obtain an error value between the training data and the real data.
An error correction unit 52, configured to perform correction processing on the error value.
And an error standard-reaching judging unit 53, configured to judge whether the error value after the correction processing reaches a preset target value, if so, ending the training, and otherwise, performing the training again.
An embodiment of the present application further provides a specific implementation manner of an electronic device, which is capable of implementing all steps in the transformer substation safety monitoring method based on deep learning in the foregoing embodiment, and with reference to fig. 10, the electronic device specifically includes the following contents:
a processor (processor)601, a memory (memory)602, a communication interface (communications interface)603, and a bus 604;
the processor 601, the memory 602 and the communication interface 603 complete mutual communication through the bus 604; the communication interface 603 is used for realizing information transmission among a transformer substation safety monitoring device based on deep learning, an online service system, client equipment and other participating mechanisms;
the processor 601 is configured to call a computer program in the memory 602, and when the processor executes the computer program, the processor implements all the steps in the deep learning-based substation security monitoring method in the above embodiments, for example, when the processor executes the computer program, the processor implements the following steps:
step S101: and acquiring images of the staff through an image acquisition device arranged in the transformer substation to obtain the current images of the staff.
Step S102: and performing compliance judgment on the current employee image according to a preset employee compliance inspection model.
Step S103: and if the compliance judgment result is that the data fails, sending an alarm instruction to an alarm device arranged in the transformer substation.
According to the description, the electronic equipment provided by the embodiment of the application can acquire images of the staff in real time through the image acquisition device arranged in the transformer substation, carries out compliance judgment on the staff according to the acquired current staff images and a preset staff compliance inspection model trained through a deep learning neural network, and sends an alarm instruction to the alarm device arranged in the transformer substation if the compliance judgment result is not passed, and prompts and corrects the non-compliance condition of the staff in the transformer substation, so that the reliability and the efficiency of transformer substation safety monitoring are improved, and the probability of safety accidents is further reduced.
Embodiments of the present application further provide a computer-readable storage medium capable of implementing all steps in the transformer substation safety monitoring method based on deep learning in the foregoing embodiments, where the computer-readable storage medium stores thereon a computer program, and when the computer program is executed by a processor, the computer program implements all steps of the transformer substation safety monitoring method based on deep learning in the foregoing embodiments, for example, when the processor executes the computer program, the processor implements the following steps:
step S101: and acquiring images of the staff through an image acquisition device arranged in the transformer substation to obtain the current images of the staff.
Step S102: and performing compliance judgment on the current employee image according to a preset employee compliance inspection model.
Step S103: and if the compliance judgment result is that the data fails, sending an alarm instruction to an alarm device arranged in the transformer substation.
As can be seen from the above description, the computer-readable storage medium provided in the embodiment of the present application can perform real-time image acquisition on employees through an image acquisition device disposed in a substation, and perform compliance judgment on the employees according to a current employee image obtained through acquisition and a preset employee compliance inspection model trained through a deep learning neural network, and if the compliance judgment result does not pass, send an alarm instruction to an alarm device disposed in the substation, and timely prompt and correct the non-compliance condition of the employees in the substation, thereby improving the reliability and efficiency of security monitoring of the substation, and further reducing the probability of occurrence of security accidents.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Although the present application provides method steps as described in an embodiment or flowchart, additional or fewer steps may be included based on conventional or non-inventive efforts. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or client product executes, it may execute sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the embodiments or methods shown in the figures.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, 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 technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
The embodiments of this specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The described embodiments may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of an embodiment of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and variations to the embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present specification should be included in the scope of the claims of the embodiments of the present specification.
Claims (10)
1. A transformer substation safety monitoring method based on deep learning is characterized by comprising the following steps:
acquiring images of the staff through an image acquisition device arranged in the transformer substation to obtain a current staff image;
performing compliance judgment on the current employee image according to a preset employee compliance inspection model;
and if the compliance judgment result is that the data fails, sending an alarm instruction to an alarm device arranged in the transformer substation.
2. The deep learning-based substation security monitoring method according to claim 1, before the performing compliance judgment on the current employee image according to a preset employee compliance check model, comprising:
collecting training data for training the staff compliance inspection model;
performing data decomposition on the training data;
and carrying out convolutional neural network training on the training data subjected to the data decomposition to obtain the staff compliance inspection model.
3. The deep learning-based substation security monitoring method according to claim 2, wherein the collecting training data for training the staff compliance check model comprises:
collecting a sample image of the employee;
and marking the sample image, wherein the marking comprises at least one of a marking indicating whether the staff wears a safety helmet or not, a marking indicating whether the staff wears a work clothes or not and a marking indicating staff information obtained according to the staff face image.
4. The deep learning-based substation security monitoring method according to claim 2, wherein before said obtaining the staff compliance inspection model, comprising:
performing convolutional neural network training on the training data to obtain an error value of the training data and the real data;
correcting the error value;
and judging whether the error value after the correction processing reaches a preset target value, if so, finishing the training, and otherwise, performing the training again.
5. The utility model provides a transformer substation safety monitoring device based on deep learning which characterized in that includes:
the image acquisition module is used for acquiring images of the staff through an image acquisition device arranged in the transformer substation to obtain a current staff image;
the model judgment module is used for carrying out compliance judgment on the current employee image according to a preset employee compliance inspection model;
and the abnormity warning module is used for sending a warning instruction to a warning device arranged in the transformer substation when the compliance judgment result is that the compliance judgment result does not pass.
6. The deep learning based substation safety monitoring device of claim 5, further comprising:
the training data acquisition unit is used for acquiring training data for training the staff compliance inspection model;
the training data decomposition unit is used for carrying out data decomposition on the training data;
and the neural network training unit is used for carrying out convolutional neural network training on the training data subjected to the data decomposition to obtain the staff compliance inspection model.
7. The deep learning-based substation safety monitoring device according to claim 6, wherein the training data acquisition unit comprises:
the sample image acquisition subunit is used for acquiring sample images of the staff;
and the sample image labeling subunit is used for labeling the sample image, wherein the labeling comprises at least one of a label indicating whether the staff wears a safety helmet or not, a label indicating whether the staff wears a work clothes or not and a label indicating staff information obtained according to the staff face image.
8. The deep learning based substation safety monitoring device of claim 6, further comprising:
the error determining unit is used for carrying out convolutional neural network training on the training data to obtain an error value of the training data and the real data;
the error correction unit is used for correcting the error value;
and the error standard-reaching judging unit is used for judging whether the error value after the correction processing reaches a preset target value, if so, finishing the training, and otherwise, performing the training again.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the deep learning based substation security monitoring method according to any of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the deep learning based substation security monitoring method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010116140.0A CN111339933A (en) | 2020-02-25 | 2020-02-25 | Transformer substation safety monitoring method and device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010116140.0A CN111339933A (en) | 2020-02-25 | 2020-02-25 | Transformer substation safety monitoring method and device based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111339933A true CN111339933A (en) | 2020-06-26 |
Family
ID=71183700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010116140.0A Pending CN111339933A (en) | 2020-02-25 | 2020-02-25 | Transformer substation safety monitoring method and device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111339933A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112907486A (en) * | 2021-03-18 | 2021-06-04 | 国家海洋信息中心 | Remote sensing image color matching method based on deep learning and color mapping |
| CN113392527A (en) * | 2021-06-17 | 2021-09-14 | 华南理工大学 | Method and device for evaluating applicability of manipulation sequence, computer equipment and storage medium |
| CN114299686A (en) * | 2021-12-13 | 2022-04-08 | 上海异工同智信息科技有限公司 | Chemical enterprise safety management method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358157A (en) * | 2017-06-07 | 2017-11-17 | 阿里巴巴集团控股有限公司 | A kind of human face in-vivo detection method, device and electronic equipment |
| CN109145789A (en) * | 2018-08-09 | 2019-01-04 | 炜呈智能电力科技（杭州）有限公司 | Power supply system safety work support method and system |
| CN110046574A (en) * | 2019-04-15 | 2019-07-23 | 北京易达图灵科技有限公司 | Safety cap based on deep learning wears recognition methods and equipment |
| CN110059742A (en) * | 2019-04-15 | 2019-07-26 | 北京易达图灵科技有限公司 | Safety protector wearing recognition methods and equipment based on deep learning |
| WO2019144469A1 (en) * | 2018-01-24 | 2019-08-01 | 华讯方舟科技有限公司 | Image quality classification method, system and terminal device |
| CN110163143A (en) * | 2019-05-17 | 2019-08-23 | 国网河北省电力有限公司沧州供电分公司 | Unlawful practice recognition methods, device and terminal device |
-
2020
- 2020-02-25 CN CN202010116140.0A patent/CN111339933A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358157A (en) * | 2017-06-07 | 2017-11-17 | 阿里巴巴集团控股有限公司 | A kind of human face in-vivo detection method, device and electronic equipment |
| WO2019144469A1 (en) * | 2018-01-24 | 2019-08-01 | 华讯方舟科技有限公司 | Image quality classification method, system and terminal device |
| CN109145789A (en) * | 2018-08-09 | 2019-01-04 | 炜呈智能电力科技（杭州）有限公司 | Power supply system safety work support method and system |
| CN110046574A (en) * | 2019-04-15 | 2019-07-23 | 北京易达图灵科技有限公司 | Safety cap based on deep learning wears recognition methods and equipment |
| CN110059742A (en) * | 2019-04-15 | 2019-07-26 | 北京易达图灵科技有限公司 | Safety protector wearing recognition methods and equipment based on deep learning |
| CN110163143A (en) * | 2019-05-17 | 2019-08-23 | 国网河北省电力有限公司沧州供电分公司 | Unlawful practice recognition methods, device and terminal device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112907486A (en) * | 2021-03-18 | 2021-06-04 | 国家海洋信息中心 | Remote sensing image color matching method based on deep learning and color mapping |
| CN113392527A (en) * | 2021-06-17 | 2021-09-14 | 华南理工大学 | Method and device for evaluating applicability of manipulation sequence, computer equipment and storage medium |
| CN114299686A (en) * | 2021-12-13 | 2022-04-08 | 上海异工同智信息科技有限公司 | Chemical enterprise safety management method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020259421A1 (en) | Method and apparatus for monitoring service system | |
| CN111339933A (en) | Transformer substation safety monitoring method and device based on deep learning | |
| CN110889339B (en) | Head and shoulder detection-based dangerous area grading early warning method and system | |
| CN115601905B (en) | Intelligent security alarm method and system for intelligent park | |
| CN109117526A (en) | One kind being suitable for mechanical system maintenance of equipment and guides data record and analysis system | |
| CN116151626B (en) | Risk management and control capability evaluating method, system, electronic equipment and storage medium | |
| CN112801434A (en) | Method, device, equipment and storage medium for monitoring performance index health degree | |
| CN114155614A (en) | Method and system for identifying anti-violation behaviors in operation site | |
| CN110705849A (en) | Inspection robot effect evaluation method and system, storage medium and robot | |
| CN113112216A (en) | Prejudgment analysis method for equipment defects | |
| CN112036708A (en) | Comprehensive pipe gallery inspection and maintenance method, platform and computer storage medium | |
| CN116909235A (en) | Intelligent factory monitoring method, intelligent factory monitoring system and electronic equipment | |
| CN104035342A (en) | Real-time alarm intelligent aided analysis system and real-time alarm intelligent aided analysis method based on IFIX platform | |
| CN110427387A (en) | A kind of data consistency detection and device | |
| CN115033412A (en) | Task log merging method and device | |
| CN115100592A (en) | Method and device for identifying hidden danger of external damage of power transmission channel and storage medium | |
| CN114925866A (en) | Auxiliary decision device, fault alarm method and system in low-voltage distribution network line | |
| CN112153341B (en) | Task supervision method, device and system, electronic equipment and storage medium | |
| CN112711508A (en) | Intelligent operation and maintenance service system facing large-scale client system | |
| CN111476922A (en) | Method and device for judging arrival of power transmission line inspection personnel | |
| CN112686583A (en) | Method and system for generating automatic handling flow of civil aviation event | |
| CN112764852A (en) | Operation and maintenance safety monitoring method and system for intelligent wave recording master station and computer readable storage medium | |
| Fang et al. | Design and Development of Industrial Safety APPs | |
| Dehai | Development and Research of Equipment Information Management System of Thermal Power Plant | |
| Sakrutina et al. | Using the Risk Potential Assessment of Energy Objects in the SMS System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |