Safety monitoring method and device for converter platform
By collecting image data and PLC signals from the converter platform, and combining the YOLO deep learning model and dynamic working condition recognition technology, the problems of low recognition accuracy and slow response in the existing technology have been solved, realizing high-precision safety monitoring and real-time early warning of the converter platform, and improving the level of automation in safety management.
Patent Information
- Application Number
- CN202511078966.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-02
- Publication Date
- 2025-11-28
AI Technical Summary
Existing image recognition systems lack accuracy in complex industrial environments, have limited dynamic response capabilities, cannot distinguish the specific operating status of converters, and fail to integrate effectively with existing safety management platforms, resulting in slow safety management response and incomplete coverage.
By collecting image data and PLC signals from the converter platform, and combining the YOLO deep learning model and dynamic operating condition recognition technology, the converter operation status is identified and the safety zone is dynamically adjusted, enabling real-time monitoring and early warning of personnel behavior.
It improves the automation level of safety management on the converter platform, enabling it to accurately identify dangerous behaviors and issue timely alarms in complex environments, thus preventing safety accidents.
Smart Images
Figure CN121033751A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of image processing, and in particular to a converter platform safety monitoring method and device. BACKGROUND
[0002] With the continuous development of the steel industry, safety issues in the converter operation process are increasingly valued. Traditional safety management methods rely on manual patrols and fixed-position monitoring cameras, which have certain limitations, such as incomplete monitoring coverage, slow response, and inability to accurately judge personnel behavior in complex scenarios. In recent years, with the development of image recognition technology, it has become possible to use machine vision for safety monitoring.
[0003] However, existing image recognition systems are mostly applied to target detection in simple scenarios and cannot effectively cope with the demand for multi-condition and behavior recognition in complex industrial environments. SUMMARY
[0004] In view of the above problems, the present application provides a converter platform safety monitoring method and device, which can adapt to the complex environment of industrial sites, accurately identify dangerous behavior and timely issue alarms, in order to improve the automation level and response speed of safety management.
[0005] According to a first aspect of the present application, a converter platform safety monitoring method is provided, comprising:
[0006] Collecting image data of the converter platform and PLC signals related to converter control;
[0007] Determining the current operating state of the converter according to the PLC signals and the image data;
[0008] According to the current operating state of the converter, determining the safety area corresponding to the current operating state;
[0009] According to the image data of the converter platform and the safety area, the safety of the converter platform is monitored.
[0010] Optionally, the safety of the converter platform is monitored according to the image data of the converter platform and the safety area, comprising:
[0011] Inputting the image data into a trained target model for target recognition to detect whether there is a target person in the safety area corresponding to the image data;
[0012] If there is a target person in the safety area, an alarm information is issued.
[0013] Optionally, the method further comprises:
[0014] If the target person does not exist in the safety area, a peripheral early warning area corresponding to the current operation state is determined according to the safety area;
[0015] It is detected whether the target person exists in the peripheral early warning area;
[0016] If the target person exists in the peripheral early warning area, historical image data adjacent to the image data is acquired;
[0017] The motion trajectory of the target person in a preset time period is predicted according to the image data and the historical image data;
[0018] If the motion trajectory of the target person in the preset time period reaches the safety area, a warning information is sent.
[0019] Optionally, the preset time period is in a range of 2-5 seconds.
[0020] Optionally, the target model is a YOLO model.
[0021] Optionally, the current operation state of the converter is determined according to the PLC signal and the image data, including:
[0022] The initial operation state of the converter is determined according to the PLC signal;
[0023] The check parameter is determined according to the initial operation state;
[0024] The current operation state of the converter is determined by analyzing the image data according to the check parameter.
[0025] Optionally, the check parameter includes the duration of the target object and the light intensity of the target object.
[0026] According to a second aspect of the present application, a safety monitoring device of a converter platform is provided, including:
[0027] The acquisition unit is configured to acquire image data of the converter platform and a PLC signal related to the control of the converter;
[0028] The state determination unit is configured to determine the current operation state of the converter according to the PLC signal and the image data;
[0029] The area determination unit is configured to determine a safety area corresponding to the current operation state of the converter according to the current operation state of the converter;
[0030] The monitoring unit is configured to perform safety monitoring on the converter platform according to the image data of the converter platform and the safety area.
[0031] According to a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned safety monitoring method for a converter platform when executing the computer program.
[0032] According to a fourth aspect of the present application, a converter system is provided, comprising a converter and a control system, wherein the control system implements the above-mentioned safety monitoring method for a converter platform.
[0033] The above-mentioned one or more technical solutions in the embodiments of the present application have at least the following technical effects:
[0034] The safety monitoring method and device for a converter platform provided by the embodiments of the present application collect image data of a converter platform and PLC signals related to converter control; determine a current operation state of a converter according to the PLC signals and the image data; determine a safety area corresponding to the current operation state of the converter according to the current operation state of the converter; and perform safety monitoring on the converter platform according to the image data of the converter platform and the safety area. In this way, through a high-precision target detection algorithm and a dynamic working condition recognition technology, real-time monitoring of personnel behavior on the converter platform is realized, and in particular, when dangerous operations such as converter smelting, iron melting, and waste steel loading are performed, the system can automatically identify and issue a warning, thereby preventing safety accidents from occurring.
[0035] The above description is merely a summary of the technical solutions of the present application. In order to enable one of ordinary skill in the art to better understand the technical means of the present application and implement the same according to the contents of the description, and in order to enable the above and other purposes, features and advantages of the present application to be more apparent, the following specifically describes the embodiments of the present application. BRIEF DESCRIPTION OF DRAWINGS
[0036] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments and are not meant to limit the present application. Furthermore, the same reference numerals in different drawings indicate the same or similar components. In the drawings:
[0037] Figure 1 A flow chart of a safety monitoring method for a converter platform is shown in the embodiments of the present application.
[0038] Figure 2 A block schematic diagram of a safety monitoring device for a converter platform is shown in the embodiments of the present application. DETAILED DESCRIPTION
[0039] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.
[0040] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but only represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative labor are within the scope of protection of the present application.
[0041] It should be noted that: similar reference numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.
[0042] In the description of the present application, it should also be noted that, unless otherwise explicitly specified and limited, the terms "arrangement", "installation", "connection", "connection" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium, or it can be the communication inside two elements. For those of ordinary skill in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.
[0043] With the continuous development of the steel industry, the safety problem in the operation process of converter is paid more and more attention. The traditional safety management method depends on manual patrol and fixed position monitoring camera, and these methods have certain limitations, such as incomplete monitoring coverage, slow response, inability to accurately judge personnel behavior in complex scene, etc. In recent years, with the development of image recognition technology, it is possible to use machine vision for safety monitoring.
[0044] At present, there are some safety management systems based on video monitoring and image recognition applied in industrial production. These systems obtain live video streams through fixed cameras and use pre-trained models for target detection to realize the monitoring of personnel behavior in specific areas. For example, some systems can detect the entry or exit of personnel into specific areas to judge safety hazards and issue alarms.
[0045] However, the prior art has the following defects:
[0046] 1. Low recognition accuracy; In complex industrial environments, existing image recognition models cannot adapt to changing lighting conditions and complex backgrounds, resulting in low recognition rates.
[0047] 2. Lack of dynamic response; Existing systems are mostly passive monitoring, with slow response speed to sudden conditions, and cannot effectively warn in real time.
[0048] 3. Cannot distinguish between working conditions; Existing technologies cannot distinguish the specific operating state of the converter, such as smelting, adding molten iron, or loading scrap steel, etc., resulting in the system being unable to dynamically adjust the monitoring strategy according to the actual working conditions.
[0049] 4. Poor integration; Most systems fail to effectively integrate with the existing safety management platform of the enterprise, and the real-time and availability of data are insufficient, making it difficult to achieve comprehensive safety production management.
[0050] In combination Figure 1 The present application provides a safety monitoring method for a converter platform, which includes steps 101 to 104:
[0051] Step 101: Collecting image data of the converter platform and PLC signals related to converter control;
[0052] In this embodiment, the image data of the converter platform can be collected by a camera. The camera is installed at multiple key positions on the converter platform, covering the entire platform area, and can adjust the angle and focal length as needed to ensure no dead angle monitoring.
[0053] The camera has high dynamic range (HDR) and can obtain clear images in strong light and shadow areas, and has night vision function to ensure stable operation of the system under different lighting conditions.
[0054] It should be noted that the PLC signal of the converter control is a primary signal, which can identify the operating state of the converter, but due to being a primary signal, the accuracy is not high or the signal lags, affecting the timeliness and accuracy of obtaining the operating state of the converter. And the method of this embodiment belongs to equipment modification. In order to improve the timeliness and accuracy of obtaining the operating state of the converter, this embodiment no longer simply relies on the PLC signal of the converter control when determining the current operating state of the converter.
[0055] Step 102: According to the PLC signal and the image data, determine the current operating state of the converter;
[0056] In this embodiment, when determining the current operating state of the converter, the PLC signal and the image data are used together to determine the current operating state of the converter, and the specific steps can include:
[0057] According to the PLC signal, an initial operation state of the converter is determined;
[0058] According to the initial operation state, a verification parameter is determined;
[0059] According to the verification parameter, the image data is analyzed to determine a current operation state of the converter.
[0060] In the embodiment, the operation state of the converter is preliminarily determined according to the PLC signal to obtain the initial operation state of the converter. Then, the verification analysis is performed in combination with the image data, and the image data is recognized and analyzed through the target model.
[0061] It should be noted that the operation state of the converter mainly includes a smelting state, a molten iron adding state and a scrap steel loading state. Different operation states have different verification parameters and different verification manners.
[0062] Firstly, the verification parameter is determined according to the initial operation state. The verification parameter includes a duration of a target object and a light intensity of the target object.
[0063] Specifically, in the smelting state, the corresponding target object is a damper, and the corresponding verification parameter is a light intensity of a side gap of the damper. The change of the light intensity reflects the fluctuation of the temperature in the converter. In combination with the PLC signal, whether the converter is really in the smelting state is determined by judging the light intensity of the side gap of the damper.
[0064] In the molten iron adding state, the corresponding target object is a molten iron ladle, and the corresponding verification parameter is a duration of the molten iron ladle. In combination with the adjacent historical image data, whether the converter is really in the molten iron adding state is determined by judging the duration of the appearance of the molten iron ladle.
[0065] In the scrap steel loading state, the corresponding target object is a scrap steel bucket, and the corresponding verification parameter is a duration of the scrap steel bucket. In combination with the adjacent historical image data, whether the converter is really in the scrap steel loading state is determined by judging the duration of the appearance of the scrap steel bucket.
[0066] The duration can be 10 seconds.
[0067] Step 103: According to the current operation state of the converter, a safety area corresponding to the current operation state is determined;
[0068] In this embodiment, a safety area is defined for each converter, which is flexibly set by the operator according to the actual production environment and process requirements. The safety area can be a rectangular, circular or polygonal area, and dynamic adjustment is supported. The safety area is dynamically adjusted, specifically, the range of the safety area is dynamically adjusted according to different converter operating states (such as smelting, adding molten iron, loading scrap steel, etc.). That is, according to the current operating state of the converter, the safety area corresponding to the current operating state is determined.
[0069] Step 104: Safety monitoring of the converter platform according to the image data of the converter platform and the safety area.
[0070] Specifically, the image data is input into the trained target model for target recognition to detect whether there is a target person in the safety area corresponding to the image data.
[0071] If there is a target person in the safety area, an alarm information is issued.
[0072] In this embodiment, the target model uses a trained YOLO (You Only Look Once) deep learning model to recognize personnel, ladle, scrap steel bucket and other targets in the image data. The model considers complex industrial environment factors such as smoke, heat wave, dynamic changes of process equipment, etc. during training, to ensure the robustness of recognition.
[0073] To improve the accuracy of target recognition, the image data collected in this embodiment is preprocessed, including image denoising, gray scale adjustment and edge enhancement.
[0074] In the recognition process, if there is a target person in the safety area, it means that there is a safety risk, at which time an alarm information is issued, that is, a real-time voice alarm is issued through a loudspeaker to remind the target person on site to evacuate immediately.
[0075] Moreover, at the same time when the alarm information is issued, the current monitoring screen is automatically intercepted, and relevant information (such as time, heat number, target person position, etc.) is saved. These screenshots are stored according to date and event type, which is convenient for subsequent viewing and analysis.
[0076] It should be noted that this embodiment also designs a multi-level alarm mechanism to issue different levels of alarms according to the severity of the event. For example, when the target person only approaches the safety area, the system issues a low-level warning; when the person enters a high-risk area, the system issues an emergency alarm.
[0077] In addition, this embodiment also includes steps for personnel approach detection and behavior prediction:
[0078] If the target personnel does not exist in the safety area, a peripheral early warning area corresponding to the current operation state is determined according to the safety area;
[0079] It is detected whether the target personnel exists in the peripheral early warning area;
[0080] If the target personnel exists in the peripheral early warning area, historical image data adjacent to the image data is acquired;
[0081] The motion trajectory of the target personnel in a preset time period is predicted according to the image data and the historical image data;
[0082] If the motion trajectory of the target personnel in the preset time period reaches the safety area, an early warning information is sent.
[0083] A region in the periphery of the safety area can be used as the peripheral early warning area. In this embodiment, the motion trajectory of the personnel is analyzed, and when it is detected that the target personnel is in the peripheral early warning area, it is indicated that the target personnel approaches the safety area. The motion trajectory of the target personnel in a short time is analyzed in combination with the historical image data adjacent to the image data, so as to determine whether the target personnel is likely to enter the safety area. If the motion trajectory of the target personnel in the preset time period reaches the safety area, an early warning information is sent, that is, a voice prompt is sent through a loudspeaker to remind the target personnel to pay attention to safety. This function can effectively avoid potential dangerous behaviors. The preset time period is in the range of 2-5 seconds.
[0084] In addition, this embodiment has a behavior analysis function and can determine whether the behavior of the personnel has potential danger. For example, the system can identify abnormal behaviors such as rapid movement or wandering and send an early warning accordingly.
[0085] In summary, the safety monitoring method of the converter platform provided in this specification collects image data of the converter platform and PLC signals about converter control; determines the current operation state of the converter according to the PLC signals and the image data; determines a safety area corresponding to the current operation state according to the current operation state of the converter; and performs safety monitoring on the converter platform according to the image data of the converter platform and the safety area. In this way, through a high-precision target detection algorithm and a dynamic working condition recognition technology, real-time monitoring of the behavior of personnel on the converter platform is realized, and in particular, when dangerous operations such as converter smelting, iron water mixing, and waste steel loading are performed, the system can automatically identify and send an early warning, thereby preventing the occurrence of safety accidents.
[0086] Based on the same inventive concept, in combination Figure 2 with the converter platform safety monitoring method shown in the specification, the embodiment of the present application also provides a converter platform safety monitoring device, which comprises:
[0087] an acquisition unit configured to acquire image data of a converter platform and PLC signals related to converter control;
[0088] a state determination unit configured to determine a current operation state of the converter according to the PLC signals and the image data;
[0089] a region determination unit configured to determine a safety region corresponding to the current operation state of the converter according to the current operation state of the converter;
[0090] a monitoring unit configured to perform safety monitoring on the converter platform according to the image data of the converter platform and the safety region.
[0091] Optionally, the monitoring unit is further configured to:
[0092] input the image data into a trained target model for target recognition to detect whether there is a target person in the safety region corresponding to the image data;
[0093] if there is a target person in the safety region, issue an alarm information.
[0094] Optionally, the monitoring unit is further configured to:
[0095] if there is no target person in the safety region, determine a peripheral early warning region corresponding to the current operation state according to the safety region;
[0096] detect whether there is a target person in the peripheral early warning region;
[0097] if there is a target person in the peripheral early warning region, acquire historical image data adjacent to the image data;
[0098] predict a motion trajectory of the target person within a preset time period according to the image data and the historical image data;
[0099] if the motion trajectory of the target person within the preset time period reaches the safety region, issue an early warning information.
[0100] Optionally, the preset time period is within a range of 2-5 seconds.
[0101] Optionally, the target model is a YOLO model.
[0102] Optionally, the region determination unit is further configured to:
[0103] determine an initial operation state of the converter according to the PLC signals;
[0104] determine a verification parameter according to the initial operation state;
[0105] According to the check parameter, the image data is analyzed to determine a current operation state of the converter.
[0106] Optionally, the check parameter includes a duration of the target object and a light intensity of the target object.
[0107] To sum up, the safety monitoring device of the converter platform provided by the embodiments of the present disclosure collects image data of the converter platform and PLC signals related to the control of the converter; determines a current operation state of the converter according to the PLC signals and the image data; determines a safety area corresponding to the current operation state of the converter according to the current operation state of the converter; and performs safety monitoring on the converter platform according to the image data of the converter platform and the safety area. In this way, through a high-precision target detection algorithm and a dynamic working condition recognition technology, real-time monitoring of the behavior of personnel on the converter platform is realized, and in particular, when the converter is smelting, the converter is being filled with molten iron, and the converter is being loaded with scrap steel, the system can automatically identify and issue a warning, thereby preventing the occurrence of safety accidents.
[0108] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the safety monitoring device of the converter platform described above can refer to the corresponding process in the foregoing method, and will not be described in more detail here.
[0109] Based on the same inventive concept, the embodiments provide an electronic device including the safety monitoring device of the converter platform, a memory, a processor, and a communication unit. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through a bus. The processor executes the machine-readable instructions and performs the safety monitoring method of the converter platform.
[0110] The memory, the processor, and the communication unit are directly or indirectly electrically connected to each other to realize the transmission or interaction of signals. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines. The safety monitoring device of the converter platform includes at least one software function module stored in the memory in the form of software or firmware. The processor is configured to execute the executable modules (such as software function modules or computer programs included in the safety monitoring device of the converter platform) stored in the memory.
[0111] The memory can be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electric Erasable Programmable Read-Only Memory (EEPROM), and the like.
[0112] In some embodiments, the processor is configured to perform one or more functions described in the embodiments. In some embodiments, the processor can include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). For example only, the processor can include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction-set Processor (ASIP), a Graphics Processing Unit (GPU), a Physics Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller unit, a Reduced Instruction Set Computing (RISC), or a microprocessor, and the like, or any combination thereof.
[0113] For ease of illustration, only one processor is described in the electronic device. However, it should be noted that the electronic device in the embodiments can also include multiple processors, and thus the steps performed by one processor described in the embodiments can also be jointly performed by multiple processors or individually performed by multiple processors. For example, if the processor of the server performs steps A and B, it should be understood that steps A and B can also be jointly performed by two different processors or individually performed in one processor. For example, the processor performs step A, the second processor performs step B, or the processor and the second processor jointly perform steps A and B.
[0114] In this embodiment, the memory is configured to store a program, and the processor is configured to execute the program upon receiving an execution instruction. The flow defined method disclosed in any of the embodiments of the present embodiment can be applied in the processor or implemented by the processor.
[0115] The communication unit is configured to establish a communication connection between the electronic device and other devices through a network, and configured to transmit and receive data through the network.
[0116] In some embodiments, the network can be any type of wired or wireless network, or a combination thereof. By way of example only, the network can include a wired network, a wireless network, a fiber optic network, a telecommunications network, an intranet, the Internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Public Switched Telephone Network (PSTN), a Bluetooth network, a ZigBee network, or a Near Field Communication (NFC) network, etc., or any combination thereof.
[0117] In this embodiment, the electronic device can be, but is not limited to, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), and the like. The present embodiment does not make any limitation on the specific type of the electronic device.
[0118] Based on the same inventive concept, the present embodiment also provides a converter system, comprising a converter and a control system, wherein the control system executes the safety monitoring method of the converter platform as described above.
[0119] The control system comprises an image acquisition module, an image processing module, a safety area setting module, a state recognition module, an alarm module, a pre-warning module, and a data storage and integration module.
[0120] The image acquisition module comprises a plurality of high-definition cameras installed at a plurality of key positions of the converter platform, wherein the cameras can cover the entire platform area and can adjust the angle and focal length according to the requirements to ensure no dead angle monitoring.
[0121] The system installs high-definition cameras at a plurality of key positions of the converter platform, which can cover the entire platform area and can adjust the angle and focal length according to the requirements to ensure no dead angle monitoring.
[0122] The camera has high dynamic range (HDR) and can capture clear images in both bright light and shadow areas. It also has night vision capabilities to ensure stable operation under different lighting conditions.
[0123] Image processing module:
[0124] The system uses a trained YOLO (You Only Look Once) deep learning model to identify target personnel, ladle, scrap steel, and other targets in the image. The model takes into account complex industrial environmental factors such as smoke, heat waves, and dynamic changes in process equipment during training to ensure robustness of the identification.
[0125] To improve recognition accuracy, the system pre-processes the collected images, including image denoising, grayscale adjustment, and edge enhancement.
[0126] Safety area setting module:
[0127] The system defines a safety area for each converter, which is set by the operator according to the actual production environment and process requirements. The safety area can be a rectangular, circular, or polygonal area, and supports dynamic adjustment.
[0128] Outside the set safety area, the system creates a peripheral warning area, and any target entering this area will be monitored in real time by the system.
[0129] The system dynamically adjusts the range of the safety area according to the different current operating states of the converter (such as smelting, adding molten iron, and loading scrap steel).
[0130] State recognition module:
[0131] By analyzing the light intensity of the side gap of the converter fire door, the system can determine whether the converter is in a smelting state. Changes in light intensity reflect fluctuations in the temperature inside the furnace, and combined with PLC signals, the system can accurately determine the operating state of the converter.
[0132] The system interacts with the converter control PLC to obtain the operating state of the converter (such as smelting, adding molten iron, and loading scrap steel) in real time. These signals are combined with image recognition results to ensure the accuracy of the system's decision-making.
[0133] Alarm module:
[0134] When the system detects that a target person has entered the set safety area and the current operating state of the converter is in a dangerous operating state (such as smelting, adding molten iron, or loading scrap steel), the system will issue a real-time voice alarm through the loudspeaker to remind the on-site personnel to evacuate immediately.
[0135] The system also automatically captures the current monitoring screen and saves relevant information (such as time, furnace number, personnel location, etc.) when an alarm is issued. These screenshots are stored according to date and event type for easy subsequent viewing and analysis.
[0136] Early warning module:
[0137] The system analyzes the movement trajectory of personnel and issues a voice prompt to remind personnel to pay attention to safety when it detects that personnel may reach the safety area within a preset time period. This function can effectively prevent potential dangerous behavior.
[0138] The system also has a behavior analysis function that can determine whether a person's behavior is potentially dangerous. For example, the system can identify abnormal behaviors such as rapid movement or wandering and issue a warning accordingly.
[0139] Data storage and integration module:
[0140] Data storage: The system stores all alarm and warning event data, including screenshots, event occurrence time, and related signals, in the database of the safety production integrated management platform. These data can support subsequent accident analysis and safety improvement work.
[0141] Platform integration: The system seamlessly integrates into the existing safety production integrated management platform, allowing management personnel to view monitoring screens and alarm records in real time and remotely access historical data. In addition, the system supports multi-platform collaboration, such as linking with other safety systems in the factory area to achieve more comprehensive safety management.
[0142] Data analysis and reporting: The system provides a data analysis tool that can automatically generate safety reports, including event occurrence frequency and potential risk area analysis, to provide decision support for management.
[0143] In addition, the system is designed with an automatic self-checking function that periodically checks the running status of each module, such as whether the camera is working normally, whether the image processing module is delayed or has errors, etc. Once a problem is detected, the system will automatically notify the maintenance personnel for repair.
[0144] The system supports remote upgrades to ensure continuous updates and optimization of software to address new safety needs and technological developments.
[0145] The above is only various embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims
1. A safety monitoring method for a converter platform, characterized in that, include: Acquire image data of the converter platform and PLC signals related to converter control; The current operating status of the converter is determined based on the PLC signal and the image data. Based on the current operating status of the converter, determine the safe zone corresponding to the current operating status; Safety monitoring of the converter platform is performed based on the image data of the converter platform and the safety zone.
2. The method according to claim 1, characterized in that, The step of performing safety monitoring on the converter platform based on the image data of the converter platform and the safety zone includes: The image data is input into a trained target model for target recognition to detect whether there are target personnel within the safe area corresponding to the image data; If a target person is present within the designated safe area, an alarm will be issued.
3. The method according to claim 2, characterized in that, The method further includes: If there are no target personnel within the safe area, then the peripheral warning area corresponding to the current operation status is determined based on the safe area. Detect whether there are target personnel within the outer warning area; If a target person is present within the outer warning area, then historical image data adjacent to the image data is acquired; Based on the image data and the historical image data, predict the movement trajectory of the target person within a preset time period; If the movement trajectory of the target person reaches the safe area within a preset time period, an early warning message will be issued.
4. The method according to claim 3, characterized in that, The preset time period is taken from a range of 2-5 seconds.
5. The method according to claim 2, characterized in that, The target model is the YOLO model.
6. The method according to claim 1, characterized in that, Determining the current operating status of the converter based on the PLC signal and the image data includes: The initial operating state of the converter is determined based on the PLC signal. Based on the initial operation state, determine the verification parameters; Based on the verification parameters, the image data is analyzed to determine the current operating status of the converter.
7. The method according to claim 6, characterized in that, The verification parameters include the duration of the target object and the light intensity of the target object.
8. A safety monitoring device for a converter platform, characterized in that, include: The acquisition unit is used to acquire image data of the converter platform and PLC signals related to converter control; The status determination unit is used to determine the current operating status of the converter based on the PLC signal and the image data. The area determination unit is used to determine the safe area corresponding to the current operating state of the converter based on the current operating state of the converter. The monitoring unit is used to perform safety monitoring on the converter platform based on the image data of the converter platform and the safety area.
9. An electronic device, characterized in that, The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the safety monitoring method for the converter platform as described in any one of claims 1-7.
10. A converter system, characterized in that, It includes a converter and a control system, wherein the control system performs the safety monitoring method for the converter platform as described in any one of claims 1-7.