Safety production automatic supervision device based on edge detection technology

Abstract

The invention relates to the technical field of safety production, in particular to a safety production automatic supervision device based on an edge detection technology, and aims to solve the problems that a safety supervision system in the prior art is low in response speed, high in data privacy risk, high in cost, insufficient in adaptability and flexibility, high in false alarm rate, lack of intelligence and the like. The system comprises an external interface module used for obtaining image data in the production process, the image data are sent to an edge calculation module through a communication module, the edge calculation module identifies dangerous characteristics based on an automatic identification algorithm and disposes the dangerous characteristics, and the disposal modes at least comprise alarm information sending and disposal scheme generation. According to the method, the response speed to potential dangerous conditions is increased, measures can be taken in time to prevent accidents, data are locally processed, the risk of data leakage is reduced, deployment and maintenance cost is reduced, and different industrial environments and application requirements can be flexibly adapted.

Description

Technical Field

[0001] This document relates to the field of production safety technology, and in particular to an automatic production safety monitoring device based on edge detection technology. Background Art

[0002] With the acceleration of the industrialization process, various accidents have occurred frequently, resulting in serious personal injury and property losses. In high-risk fields such as the construction industry and the chemical industry, there are particularly many safety hazards. While pursuing efficiency and profits, enterprises are also paying more and more attention to social responsibility. Building a safe and efficient production environment is not only a requirement for corporate compliance, but also a necessary condition for achieving sustainable economic development. With the rapid development of emerging technologies such as the Internet of Things, big data, and artificial intelligence, new technical means have gradually been applied to the field of safe production, providing technical support for the realization of automated and intelligent safety supervision. The application of new technologies can not only improve the safety of production operations, but also optimize operational efficiency and management methods. Enterprises actively adopt new technologies suitable for their own development to achieve higher levels of safe production goals, so as to better protect the lives and health of employees and promote sustainable development of enterprises.

[0003] Although a variety of safety supervision methods and technologies have been applied to industrial production, these methods still have some shortcomings:

[0004] Slow response speed: Traditional security monitoring systems usually rely on centralized data processing methods. Image or video data needs to be transmitted to a remote server for analysis, and then the results are fed back to the site. This process is often accompanied by large delays and cannot meet scenarios with high real-time requirements.

[0005] Data privacy and security issues: In some existing solutions, sensitive production data may need to be uploaded to the cloud for processing, which places higher demands on data privacy protection and increases the risk of data leakage.

[0006] High cost: Deploying a comprehensive central monitoring system not only requires a large initial investment, but also requires maintenance costs. In addition, due to network bandwidth limitations, large-scale video streaming will also incur additional costs.

[0007] Lack of adaptability and flexibility: Traditional monitoring equipment and systems have limited adaptability to application scenarios in different environments, and it is difficult to quickly adjust configurations to cope with changing working conditions or new security threats.

[0008] High false alarm rate: Existing security monitoring systems based on rules or simple algorithms are easily affected by environmental interference, resulting in a large number of false alarms, which reduces the reliability and practicality of the system.

[0009] Lack of intelligence: Some existing systems can only provide basic monitoring functions and fail to make full use of advanced technologies such as artificial intelligence to achieve smarter security warnings and decision support.

[0010] Therefore, it is necessary to provide an automatic production safety supervision device based on edge detection technology. Summary of the invention

[0011] This specification provides an automatic production safety supervision device based on edge detection technology to solve the problems of slow response speed, high data privacy risk, high cost, insufficient adaptability and flexibility, high false alarm rate and lack of intelligence in the safety supervision system in the prior art, which makes it difficult to meet the real-time, efficient and intelligent production safety needs.

[0012] The present invention proposes an automatic production safety supervision device based on edge detection technology, which includes an edge computing module, a communication module and an external interface module:

[0013] The external interface module is used to obtain image data in the production process and send it to the edge computing module through the communication module. The edge computing module identifies dangerous features based on an automatic recognition algorithm and handles the dangerous features. The handling method at least includes issuing alarm information and generating a handling plan.

[0014] Furthermore, the device also includes a data storage module, which is connected to the edge computing module and is used to store recognition process data and recognition result data.

[0015] Furthermore, the device also includes a power board, which is connected to the communication module, the edge computing module and the battery management module, and the power board is used to convert the voltage of the battery management module into the voltage required by the communication module and the edge computing module.

[0016] Furthermore, the battery management module is a rechargeable lithium battery.

[0017] Furthermore, the power board is connected to a switch control module, and the switch control module is used to control the opening and closing of the power board.

[0018] Furthermore, the power board is connected to a display module, and the display module includes a display screen and an indicator light.

[0019] Furthermore, the display screen is used to display the operating status of the edge computing module, and the operating status includes at least the occupancy and temperature information of the CPU, GPU, and memory, and the indicator light is used to display alarm information through preset colors.

[0020] Furthermore, the external interface module includes at least an HDMI interface, a USB interface, an RJ45 network port, a SIM card slot, an antenna interface and a charging interface.

[0021] Furthermore, the communication module is a routing module.

[0022] Further, the power board includes a voltage stabilizer U1, a capacitor C7, a capacitor C8, a capacitor C9, a diode D2, an inductor L1, a resistor R3, a resistor R4, a resistor R5 and a capacitor C10;

[0023] The VIN pin of the voltage regulator U1 is provided with a first node Q1 and a second node Q2, the first node Q1 is connected to the battery management module and one end of the capacitor C7, the second node Q2 is connected to one end of the capacitor C8, the other end of the capacitor C7 and the other end of the capacitor C8 are connected to a third node Q3, the third node Q3 is also connected to a fourth node Q4, and the fourth node Q4 is connected to the GND_2 pin of the voltage regulator U1 and the ground line;

[0024] The PH pin of the voltage regulator U1 is connected to a fifth node Q5, the fifth node Q5 is connected to one end of the inductor L1 and a sixth node Q6, the sixth node Q6 is connected to one end of the capacitor C9 and the cathode of the diode D2, the other end of the capacitor C9 is connected to the BOOT pin of the voltage regulator U1, the anode of the diode D2 is connected to a seventh node Q7, the seventh node Q7 is respectively connected to an eighth node Q8 and one end of the resistor R5, the eighth node Q8 is respectively connected to the fourth node Q4 and the GND_1 pin of the voltage regulator U1;

[0025] The other end of the resistor R5 is connected to the ninth node Q9, and the ninth node Q9 is also connected to the VSE pin of the regulator U1 and one end of the resistor R4. The other end of the resistor R4 is connected to one end of the resistor R3. The other end of the resistor R3 is connected to the tenth node Q10. The tenth node Q10 is respectively connected to the other end of the inductor L1 and the eleventh node Q11. The eleventh node Q11 is connected to the edge computing module, the communication module and one end of the capacitor C10. The other end of the capacitor C10 is grounded.

[0026] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:

[0027] Quick response: Due to the use of edge computing technology, image or video data can be analyzed directly locally, greatly reducing the time delay from acquisition to feedback, improving the response speed to potential dangerous situations, and being able to take timely measures to prevent accidents.

[0028] Strengthen data privacy and security: By processing data locally, the need to upload sensitive information to the cloud is reduced, reducing the risk of data leakage and enhancing data security and compliance within the enterprise.

[0029] Reduce operating costs: Compared with traditional central monitoring systems, this device reduces the demand for large-scale network bandwidth, reduces deployment and maintenance costs, and uses rechargeable lithium batteries as a power source, which also saves long-term operating costs.

[0030] Enhanced adaptability and flexibility: The external interface module design allows the connection of multiple types of sensors and devices, making the device flexibly adaptable to different industrial environments and application requirements, and the configuration can be adjusted through software updates to cope with changing working conditions or new security threats.

[0031] Reduce false alarm rates: Using advanced automatic identification algorithms, such as machine learning and deep learning models, real safety hazards can be identified more accurately, reducing false alarms caused by environmental factors and improving system reliability and practicality.

[0032] Intelligent management: In addition to basic monitoring functions, the device can also provide intelligent safety warnings and decision-making support. For example, it can predict possible risk points based on historical data analysis, formulate prevention strategies in advance, and help management make more scientific and reasonable decisions.

[0033] Visual operation interface: Equipped with display components such as display screen and indicator lights, it not only allows users to intuitively understand the operating status of the equipment, but also allows users to quickly identify alarm information through color coding, which is convenient for operators to respond immediately. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0035] Figure 1 A schematic diagram of the structural connection of an automatic production safety supervision device based on edge detection technology of the present invention;

[0036] Figure 2 The present invention is a schematic diagram of the circuit connection of a power supply board of an automatic production safety supervision device based on edge detection technology. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0038] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0039] like Figure 1 As shown, the present invention proposes an automatic production safety supervision device based on edge detection technology, which includes an edge computing module, a communication module and an external interface module:

[0040] The external interface module is used to obtain image data in the production process and send it to the edge computing module through the communication module. The edge computing module identifies dangerous features based on an automatic recognition algorithm and handles the dangerous features. The handling method at least includes issuing alarm information and generating a handling plan.

[0041] Among them, the edge detection module of the present invention is an embedded AI motherboard, which adopts the Linux operating system to provide powerful computing power for the device of the present invention. The safe production identification AI is running on the AI ​​edge motherboard, and the collected video is calculated and analyzed to extract the dangerous factors therein and deal with them in time;

[0042] The edge computing module uses the NVIDIA Jetson Orin nano motherboard, which has a maximum computing power of 40TOPS, supports 8-channel 1080P video analysis, and supports mainstream deep learning algorithm programming frameworks such as TensorFlow / Caffe / PyTorch / Paddle / ONNX / MXNet / Tengine / DarkNet, which facilitates the construction and operation of algorithms with different network structures, and provides a computing environment for the identification of safety production risk factors of this device. The core performance parameter indicators of the motherboard are shown in Table 1:

[0043] Table 1:

[0044]

[0045]

[0046] The communication module in this embodiment is a 5G routing module, which adopts an industrial wireless WIFI dual-band gigabit routing unit, supports 5G communication and Ethernet communication of China Unicom, China Mobile and China Telecom networks, and the wireless network coverage range reaches 12 meters.

[0047] The 5G routing module in the present invention can provide network support for the device of the present invention. The module supports wired and wireless communications. Through the 5G routing module, multiple monitoring videos can be connected to the device of the present invention, and the collected data can communicate and interact with the background system.

[0048] The external interface module is a channel for the device to exchange data with external devices. The external interface module at least includes an HDMI interface, a USB interface, an RJ45 network port, a SIM card slot, and an antenna interface connected to the communication module and the edge detection module. The external interface also includes a charging interface, which is connected to the battery management module. The charging external interface is described in detail in Table 2 below:

[0049] Table 2:

[0050] Charging port 1 channel, DC5.5*2.1, connected to 12V / 5A charger Network communication interface 2-way, adaptive RJ45 Ethernet port USB3.0 interface 2 channels, connect to USB3.0 or USB2.0 external devices 4G / 5G antenna interface 4-way, SMA female connector 2.4GHz WiFi antenna interface 2-way, SMA female connector 5.8GHz WiFi antenna interface 2-way, SMA female connector SIM card 1, for inserting SIM card of China Mobile, China Unicom and China Telecom

[0051] Among them, all external interface modules except the charging interface are connected to the edge detection module and the communication module.

[0052] The device also includes a data storage module, which is connected to the edge computing module and is used to store recognition process data and recognition result data.

[0053] The data storage module in the present invention provides data storage capabilities for the device of the present invention, including the storage required during the operation of the AI ​​algorithm and the storage of the recognition results after the video analysis calculation is completed;

[0054] The device also includes a power board, which is connected to the communication module, the edge computing module and the battery management module. The power board is used to convert the voltage of the battery management module into the voltage required by the communication module and the edge computing module.

[0055] The battery management module is a rechargeable lithium battery. The battery management module is located at the bottom of the device and uses 12 EVE 21700, 5000mAh cells, three series and four parallels, with a voltage of 12.6V, a battery capacity of 20Ah, a continuous discharge current of 5A, and an operating temperature of -20℃-60℃. The power management module provides power for other modules. The device supports both AC and battery power supply modes. The power management module reasonably distributes power to ensure the normal operation of each module of the device.

[0056] See also Figure 2 , the circuit of the power board includes: a voltage stabilizer U1, a capacitor C7, a capacitor C8, a capacitor C9, a diode D2, an inductor L1, a resistor R3, a resistor R4, a resistor R5 and a capacitor C10;

[0057] The VIN pin of the voltage regulator U1 is provided with a first node Q1 and a second node Q2, the first node Q1 is connected to the battery management module and one end of the capacitor C7, the second node Q2 is connected to one end of the capacitor C8, the other end of the capacitor C7 and the other end of the capacitor C8 are connected to a third node Q3, the third node Q3 is also connected to a fourth node Q4, and the fourth node Q4 is connected to the GND_2 pin of the voltage regulator U1 and the ground line;

[0058] The PH pin of the voltage regulator U1 is connected to a fifth node Q5, the fifth node Q5 is connected to one end of the inductor L1 and a sixth node Q6, the sixth node Q6 is connected to one end of the capacitor C9 and the cathode of the diode D2, the other end of the capacitor C9 is connected to the BOOT pin of the voltage regulator U1, the anode of the diode D2 is connected to a seventh node Q7, the seventh node Q7 is respectively connected to an eighth node Q8 and one end of the resistor R5, the eighth node Q8 is respectively connected to the fourth node Q4 and the GND_1 pin of the voltage regulator U1;

[0059] The other end of the resistor R5 is connected to the ninth node Q9, and the ninth node Q9 is also connected to the VSE pin of the regulator U1 and one end of the resistor R4. The other end of the resistor R4 is connected to one end of the resistor R3. The other end of the resistor R3 is connected to the tenth node Q10. The tenth node Q10 is respectively connected to the other end of the inductor L1 and the eleventh node Q11. The eleventh node Q11 is connected to the edge computing module, the communication module and one end of the capacitor C10. The other end of the capacitor C10 is grounded.

[0060] The circuit in the present invention is a voltage stabilizing circuit that converts a 12V input power supply into a 5V output power supply.

[0061] The model of the voltage regulator U1 is TPS5430, which achieves a stable 5V output by adjusting its internal switching frequency and duty cycle.

[0062] Inductor L1 and diode D2 form a freewheeling circuit to ensure current continuity. Inductor L1 is a 22uH / 4A inductor.

[0063] Capacitor C7, capacitor C8, capacitor C9 and capacitor C10 are used for input filtering, output filtering and bypass filtering respectively to improve the stability of the power supply. The capacitance of capacitor C7, capacitor C8, capacitor C9 and capacitor C10 is 22uF, 10uF, 10uF and 220uF respectively.

[0064] Resistors R3, R4 and R5 are used for feedback and protection circuits. The resistance values ​​of resistors R3, R4 and R5 are 11k, 20k and 10k respectively.

[0065] The power board in the present invention is connected to a switch control module, and the switch control module is used to control the opening and closing of the power board.

[0066] The switch control key is located on the front of the device. When the button is pressed, the source and drain are turned on, and the 12V power supply is supplied to the video analysis mainboard, router and TPS5430. Then, after the microcontroller is powered on, the corresponding IO port outputs a high level, and the MMBT3904 is turned on to maintain power supply to achieve startup. In the startup state, the microcontroller detects whether the button is pressed in real time through the IO port. After anti-shake processing, the control source and drain are closed 3s after the button is pressed, and the 12V output is disconnected to achieve shutdown.

[0067] The power board of the present invention is connected to a display module, and the display module includes a display screen and an indicator light. The display screen is used to display the operating status of the edge computing module, and the operating status includes at least the CPU, GPU, and memory occupancy and temperature information. The indicator light is used to display alarm information in preset colors, that is, when a device failure occurs or an alarm message is found, the indicator light will display a reminder in different colors.

[0068] The display module uses a 3.4-inch serial port screen, a power supply of 5V, a maximum operating current of 220mA, and an operating temperature of -20°C-70°C. The display module is connected to the edge computing module, and mainly displays the occupancy of the main performance such as CPU, GPU, memory, etc. during the operation of the mainboard, as well as the temperature information of the mainboard during operation.

[0069] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. An automatic production safety monitoring device based on edge detection technology, characterized in that: The device includes an edge computing module, a communication module and an external interface module: The external interface module is used to obtain image data in the production process and send it to the edge computing module through the communication module. The edge computing module identifies dangerous features based on an automatic recognition algorithm and handles the dangerous features. The handling method at least includes issuing alarm information and generating a handling plan.

2. According to claim 1, the automatic production safety supervision device based on edge detection technology is characterized in that: The device also includes a data storage module, which is connected to the edge computing module and is used to store recognition process data and recognition result data.

3. The automatic production safety monitoring device based on edge detection technology according to claim 1 is characterized in that: The device also includes a power board, which is connected to the communication module, the edge computing module and the battery management module. The power board is used to convert the voltage of the battery management module into the voltage required by the communication module and the edge computing module.

4. The automatic production safety monitoring device based on edge detection technology according to claim 3 is characterized in that: The battery management module is a rechargeable lithium battery.

5. The automatic production safety monitoring device based on edge detection technology according to claim 3 is characterized in that: The power board is connected to a switch control module, and the switch control module is used to control the opening and closing of the power board.

6. The automatic production safety monitoring device based on edge detection technology according to claim 3 is characterized in that: The power board is connected to a display module, and the display module includes a display screen and an indicator light.

7. The automatic production safety monitoring device based on edge detection technology according to claim 6 is characterized in that: The display screen is used to display the operating status of the edge computing module, and the operating status includes at least the occupancy and temperature information of the CPU, GPU, and memory. The indicator light is used to display alarm information through a preset color.

8. The automatic production safety monitoring device based on edge detection technology according to claim 3 is characterized in that: The external interface module at least includes an HDMI interface, a USB interface, an RJ45 network port, a SIM card slot, an antenna interface and a charging interface.

9. The automatic production safety monitoring device based on edge detection technology according to claim 1 is characterized in that: The communication module is a routing module.

10. The automatic production safety monitoring device based on edge detection technology according to claim 3 is characterized in that: The power board includes a voltage stabilizer U1, a capacitor C7, a capacitor C8, a capacitor C9, a diode D2, an inductor L1, a resistor R3, a resistor R4, a resistor R5 and a capacitor C10; The VIN pin of the voltage regulator U1 is provided with a first node Q1 and a second node Q2, the first node Q1 is connected to the battery management module and one end of the capacitor C7, the second node Q2 is connected to one end of the capacitor C8, the other end of the capacitor C7 and the other end of the capacitor C8 are connected to a third node Q3, the third node Q3 is also connected to a fourth node Q4, and the fourth node Q4 is connected to the GND_2 pin of the voltage regulator U1 and the ground line; The PH pin of the voltage regulator U1 is connected to a fifth node Q5, the fifth node Q5 is connected to one end of the inductor L1 and a sixth node Q6, the sixth node Q6 is connected to one end of the capacitor C9 and the cathode of the diode D2, the other end of the capacitor C9 is connected to the BOOT pin of the voltage regulator U1, the anode of the diode D2 is connected to a seventh node Q7, the seventh node Q7 is respectively connected to an eighth node Q8 and one end of the resistor R5, the eighth node Q8 is respectively connected to the fourth node Q4 and the GND_1 pin of the voltage regulator U1; The other end of the resistor R5 is connected to the ninth node Q9, and the ninth node Q9 is also connected to the VSE pin of the regulator U1 and one end of the resistor R4. The other end of the resistor R4 is connected to one end of the resistor R3, and the other end of the resistor R3 is connected to the tenth node Q10. The tenth node Q10 is respectively connected to the other end of the inductor L1 and the eleventh node Q11. The eleventh node Q11 is connected to the edge computing module, the communication module and one end of the capacitor C10, and the other end of the capacitor C10 is grounded.

Images