Real-time monitoring and early warning method, system and equipment for operation safety measures in power industry

Abstract

The invention relates to the technical field of power industry operation safety, in particular to a power industry operation safety measure real-time monitoring and early warning method, system and equipment, and the method comprises the steps: firstly, collecting video stream data in a worker operation area in a power operation site in real time; analyzing and identifying the video stream data through a preset deep learning model to determine whether the worker correctly wears the protective equipment; when the worker does not correctly wear the protective equipment, an alarm is given out. Therefore, whether the worker regularly wears the safety protection equipment or not in the operation process can be automatically monitored, early warning is given out in time, the monitoring range and efficiency are improved, and the safety of the electric power worker is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of power industry operation safety, and in particular to a method, system and equipment for real-time monitoring and early warning of power industry operation safety measures. Background Art

[0002] The working environment of the power industry is complex and high-risk, especially in scenes such as high-altitude work and live-line work. Workers must strictly follow the regulations to wear protective equipment such as safety helmets, insulating gloves, safety belts and work clothes. At present, safety monitoring of the work site mainly relies on manual supervision or traditional video monitoring methods, but such methods have problems such as limited monitoring range and low manual management efficiency, and cannot achieve comprehensive, real-time and accurate supervision.

[0003] For example, Chinese invention patent CN114240316A discloses a safety monitoring and control method and system for power engineering construction, which divides the power engineering construction into multiple construction areas and sets a geographical fence for each construction area; one or more inspection drones that have passed identity authentication are configured in the construction area, and the inspection drones collect video images of the construction area and send them to the supervision platform, so that the staff can supervise through the video images. Although it does not require the staff to check on site, it still requires manual supervision, which is inefficient and has the problem of limited monitoring range. Another example is Chinese invention patent CN208875469U discloses a smart bracelet for power construction, which monitors the operators by producing smart bracelets for operators to wear. Although it can achieve monitoring to a certain extent, it is costly and may produce various cheating methods during specific implementation, and the accuracy of monitoring cannot be guaranteed. Therefore, there is an urgent need for an intelligent and automated method for achieving comprehensive, real-time and accurate supervision of the operation site of the power industry, so as to improve the safety protection level of the power operation site. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a real-time monitoring and early warning method, system and equipment for safety measures in power industry operations, so as to overcome the problem of small safety monitoring range and low efficiency in the current power industry operations.

[0005] To achieve the above objectives, the present invention adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for real-time monitoring and early warning of safety measures in power industry operations, including:

[0007] Real-time collection of video stream data in the worker operation area at the power operation site;

[0008] Analyze and identify the video stream data through a preset deep learning model to determine whether the worker is wearing protective equipment correctly;

[0009] An alarm is sounded when the worker is not wearing protective equipment correctly.

[0010] Furthermore, in some embodiments of the present application, analyzing and identifying the video stream data by using a preset deep learning model includes:

[0011] The target object in the video stream is monitored by a convolutional neural network to identify whether the worker is wearing protective equipment correctly and obtain a monitoring result;

[0012] The monitoring results are analyzed by a preset classifier to generate a determination result on whether the worker wears the protective equipment correctly.

[0013] Furthermore, in some embodiments of the present application, the preset deep learning model is generated based on the YOLOv8 deep learning algorithm.

[0014] Furthermore, in some embodiments of the present application, the protective equipment includes a safety helmet, insulating gloves and a safety belt.

[0015] Furthermore, in some embodiments of the present application, issuing an alarm when the worker does not correctly wear protective equipment includes: issuing an alarm sound and an alarm light when the worker does not correctly wear protective equipment.

[0016] Furthermore, in some embodiments of the present application, it also includes: recording the time, location and type of the violation and generating a safety behavior report; wherein the violation includes workers not wearing protective equipment correctly.

[0017] In a second aspect, the embodiment of the present application provides a real-time monitoring and early warning system for safety measures in power industry operations, including:

[0018] A data acquisition module is used to collect real-time video stream data in the worker operation area at the power operation site;

[0019] A deep learning model is used to analyze and identify the video stream data to determine whether the worker is wearing protective equipment correctly;

[0020] The early warning module is used to issue an alarm when the worker does not wear protective equipment correctly.

[0021] Furthermore, in some embodiments of the present application, a data storage module is also included;

[0022] The data storage module is used to record the time, location and type of illegal behavior and generate a safety behavior report; wherein the illegal behavior includes workers not wearing protective equipment correctly.

[0023] Furthermore, in some embodiments of the present application, the data acquisition module, the early warning module and the data storage module communicate and exchange data through a standard interface.

[0024] In a third aspect, an embodiment of the present application provides a real-time monitoring and early warning device for safety measures in power industry operations, including a processor and a memory, wherein the processor is connected to the memory:

[0025] Wherein, the processor is used to call and execute the program stored in the memory;

[0026] The memory is used to store the program, and the program is at least used to execute the above-mentioned real-time monitoring and early warning method for safety measures in power industry operations.

[0027] The present invention relates to the technical field of power industry operation safety, and specifically to a method, system and device for real-time monitoring and early warning of power industry operation safety measures. The method comprises: first, real-time acquisition of video stream data in the worker operation area at the power operation site; then, analysis and identification of the video stream data by a preset deep learning model to determine whether the worker wears protective equipment correctly; and alarming when the worker does not wear protective equipment correctly. In this way, it is possible to automatically monitor whether the worker wears safety protection equipment in a standardized manner during the operation process, and issue an early warning in time, thereby improving the monitoring scope and efficiency and ensuring the safety of power workers. Its beneficial effects are specifically embodied in the following aspects: 1. Video stream data can be directly obtained using existing cameras and other equipment, which is easy to deploy and low in cost. 2. Real-time monitoring can be achieved through a deep learning model, and the monitoring and early warning efficiency is high. 3. The wearing conditions of various protective equipment of workers can be monitored more comprehensively through a deep learning model. 4. The monitoring accuracy can be greatly improved through a deep learning model. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 It is a flow chart of a method for real-time monitoring and early warning of safety measures for power industry operations provided by an embodiment of the present application;

[0030] Figure 2 It is a structural diagram of a real-time monitoring and early warning system for safety measures in power industry operations provided by an embodiment of the present application;

[0031] Figure 3 It is a structural diagram of the real-time monitoring and early warning equipment for safety measures in power industry operations provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0033] Figure 1 : is a flow chart of a real-time monitoring and early warning method for safety measures in power industry operations provided by an embodiment of the present application, such as Figure 1 As shown, the real-time monitoring and early warning method for power industry operation safety measures provided by this application may at least include:

[0034] S101. Collect video stream data in the worker operation area at the power operation site in real time.

[0035] Specifically, a data acquisition module, such as a camera deployed at a power operation site, can be used to collect video stream data in the worker's operation area in real time. The module can then transmit the collected video stream data to the central processing unit of the real-time monitoring and early warning system for power industry operation safety measures for subsequent image processing and analysis.

[0036] S102. Analyze and identify the video stream data through a preset deep learning model to determine whether the workers are wearing protective equipment correctly.

[0037] S103. Issue an alarm when a worker does not wear protective equipment correctly.

[0038] Specifically, after the deep learning model completes the analysis, if it detects that the worker is not wearing protective equipment correctly during the operation, the early warning module in the real-time monitoring and early warning system for power industry operation safety measures can immediately issue an alarm. The early warning method includes sound and light to quickly attract the attention of the workers and prompt the on-site managers to take necessary measures.

[0039] The real-time monitoring and early warning method for power industry operation safety measures provided by the present invention first collects video stream data in the worker operation area at the power operation site in real time; then analyzes and identifies the video stream data through a preset deep learning model to determine whether the worker is wearing protective equipment correctly; and issues an alarm when the worker is not wearing protective equipment correctly. In this way, the video stream data of the on-site operation is obtained through the data acquisition module, and the deep learning model identifies the status of the worker wearing safety equipment. When a violation is found, an audible and visual warning can be automatically and timely issued to ensure the safety of the workers. Real-time monitoring, accurate identification, and intelligent early warning can be achieved, which significantly improves the safety management efficiency of the power operation site.

[0040] Furthermore, in the present application, the video stream data is analyzed and identified through a preset deep learning model, including: monitoring the target objects in the video stream through a convolutional neural network, identifying whether the workers are wearing protective equipment correctly, and obtaining monitoring results; and analyzing the monitoring results through a preset classifier to generate a judgment result on whether the workers are wearing protective equipment correctly.

[0041] Specifically, in this application, the deep learning model can use the YOLOv8 deep learning algorithm as the core technology to process the video stream data through a convolutional neural network (CNN). Among them, YOLOv8 has efficient target detection capabilities and can complete the identification and positioning of multiple targets in a single forward propagation. This application applies the YOLOv8 algorithm to power operation scenarios to monitor whether workers are correctly wearing protective equipment such as safety helmets, insulating gloves, safety belts and work clothes. Among them, the YOLOv8 model has undergone a lot of pre-training and optimization, and can achieve accurate detection and classification in complex operating environments.

[0042] In practical applications, the YOLOv8 algorithm is used as the core technology for image feature extraction and target detection. The YOLOv8 model uses a convolutional neural network (CNN) to quickly and efficiently monitor target objects in video frames. After identifying whether workers are wearing protective equipment such as safety helmets, insulating gloves and safety belts, the classifier can be used to analyze the monitoring results and generate judgment results on the status of workers wearing safety equipment.

[0043] Furthermore, in the present application, it also includes: recording the time, location and type of violation and generating a safety behavior report; wherein the violation includes workers not wearing protective equipment correctly.

[0044] Specifically, the data storage module in the preset real-time monitoring and early warning system for power industry operation safety measures can be used to record the monitored violations. This module records the time, location and type of each violation in detail and generates a safety behavior report. It is understandable that these data can not only be used for daily safety management, but also provide an important basis for post-analysis and worker training, making it easier for managers to conduct post-analysis and rectification.

[0045] Based on the same inventive concept, the present application also provides a real-time monitoring and early warning system for safety measures in power industry operations. Figure 2 Schematic diagram of the structure of the real-time monitoring and early warning system for power industry operation safety measures provided by the embodiment of the present application, such as Figure 2 As shown, the system may include:

[0046] The data collection module 21 is used to collect video stream data in the worker operation area at the power operation site in real time; the deep learning model 22 is used to analyze and identify the video stream data to determine whether the worker wears the protective equipment correctly; the early warning module 23 is used to issue an alarm when the worker does not wear the protective equipment correctly. And it can also include a data storage module 24, which is used to record the time, location and type of violation and generate a safety behavior report; wherein the violation includes the worker not wearing the protective equipment correctly.

[0047] It should be noted that in the real-time monitoring and early warning system for power industry operation safety measures of this application, modular design can facilitate rapid deployment and integration at the power operation site. Each module can communicate and exchange data through a standard interface to ensure the stability and efficiency of the system operation. At the same time, the system also supports the backtracking and analysis of historical data, further improving the safety management capabilities of power operation sites.

[0048] In actual applications, the real-time monitoring and early warning system for safety measures in power industry operations also includes a central processing unit for receiving video stream data collected by the data acquisition module 21, and analyzing and identifying the video stream data through the deep learning model 22, as well as controlling the early warning module 23 to issue an alarm when workers do not wear protective equipment correctly, and controlling the data storage module 24 to record and generate safety behavior reports.

[0049] Regarding the real-time monitoring and early warning system for safety measures in power industry operations in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the real-time monitoring and early warning method for safety measures in power industry operations, and will not be elaborated here.

[0050] The application also provides a real-time monitoring and early warning system for power industry operation safety measures, which is suitable for various high-risk operation scenarios in the power industry and has the advantages of easy deployment, real-time monitoring and intelligent early warning. Through the YOLOv8 algorithm, the system can achieve efficient target detection and recognition in complex environments, ensuring that the monitoring of the wearing of safety equipment is highly accurate and real-time.

[0051] Based on the same inventive concept, the present application also provides a real-time monitoring and early warning device for safety measures in power industry operations. Figure 3 Schematic diagram of the structure of the real-time monitoring and early warning device for power industry operation safety measures provided by the embodiment of the present application, such as Figure 3 As shown, the device may include: a processor 31 and a memory 32, wherein the processor 31 is connected to the memory 32: wherein the processor 31 is used to call and execute a program stored in the memory 32; the memory 32 is used to store a program, which is at least used to execute the above-mentioned real-time monitoring and early warning method for safety measures in power industry operations.

[0052] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0053] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0054] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0055] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0056] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0057] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0058] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0059] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0060] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A real-time monitoring and early warning method for safety measures in power industry operations, characterized in that: include: Real-time collection of video stream data in the worker operation area at the power operation site; Analyze and identify the video stream data through a preset deep learning model to determine whether the worker is wearing protective equipment correctly; An alarm is sounded when the worker is not wearing protective equipment correctly.

2. The real-time monitoring and early warning method for safety measures in power industry operations according to claim 1 is characterized in that: The analyzing and identifying the video stream data by using a preset deep learning model includes: The target object in the video stream is monitored by a convolutional neural network to identify whether the worker is wearing protective equipment correctly and obtain a monitoring result; The monitoring results are analyzed by a preset classifier to generate a determination result on whether the worker wears the protective equipment correctly.

3. The real-time monitoring and early warning method for safety measures in power industry operations according to claim 1 is characterized in that: The preset deep learning model is generated based on the YOLOv8 deep learning algorithm.

4. The real-time monitoring and early warning method for safety measures in power industry operations according to claim 1 is characterized in that: The protective equipment includes a safety helmet, insulating gloves and a safety belt.

5. The real-time monitoring and early warning method for safety measures in power industry operations according to claim 1 is characterized in that: The issuing of an alarm when the worker does not wear the protective equipment correctly includes: issuing an alarm sound and an alarm light when the worker does not wear the protective equipment correctly.

6. The real-time monitoring and early warning method for safety measures in power industry operations according to claim 1 is characterized in that: Also includes: Record the time, location and type of violations and generate safety behavior reports; Among them, the violations included workers not wearing protective equipment properly.

7. A real-time monitoring and early warning system for safety measures in power industry operations, characterized in that: include: A data acquisition module is used to collect real-time video stream data in the worker operation area at the power operation site; A deep learning model is used to analyze and identify the video stream data to determine whether the worker is wearing protective equipment correctly; The early warning module is used to issue an alarm when the worker does not wear protective equipment correctly.

8. The real-time monitoring and early warning system for safety measures in power industry operations according to claim 7 is characterized in that: Also included is a data storage module; The data storage module is used to record the time, location and type of illegal behavior and generate a safety behavior report; wherein the illegal behavior includes workers not wearing protective equipment correctly.

9. The real-time monitoring and early warning system for safety measures in power industry operations according to claim 8 is characterized in that: The data acquisition module, the early warning module and the data storage module communicate and exchange data through a standard interface.

10. A real-time monitoring and early warning device for safety measures in power industry operations, characterized in that: The invention comprises a processor and a memory, wherein the processor is connected to the memory: Wherein, the processor is used to call and execute the program stored in the memory; The memory is used to store the program, and the program is at least used to execute the real-time monitoring and early warning method for safety measures in power industry operations as described in any one of claims 1-6.

Images