Safety helmet early warning system based on artificial intelligence

Abstract

The invention discloses a safety helmet early warning system based on artificial intelligence, which comprises a safety helmet body, a radar laser height measurement sensor is mounted at the front bottom of the brim of the safety helmet body, the top of the safety helmet body is fixedly connected with a mounting shell, and a detection processing device is detachably mounted in the mounting shell; the detection processing device comprises a shell, the shell is detachably connected with the mounting shell, a micro-processor is mounted in the shell, a camera and a voice broadcast device which are connected to the micro-processor are mounted in the shell, and a battery is further mounted in the shell. The invention relates to the technical field of safety protection, in particular to a safety helmet early warning system based on artificial intelligence.

Description

Technical Field

[0001] The present invention relates to the technical field of safety protection, and specifically to a safety helmet warning system based on artificial intelligence. Background Art

[0002] In high-altitude working environments such as construction, power facility maintenance, and bridge construction, workers face serious safety threats such as stepping into empty space and falling. Traditional safety helmets mainly play a role in physical head protection, lacking effective monitoring and warning means for dynamic safety risks during the operation process.

[0003] There are some existing intelligent safety helmets. Although they introduce some monitoring functions, they have significant defects: some products only rely on simple height detection sensors with low accuracy. When the height of stepping into empty space exceeds the preset value, they can only give a single voice prompt or alarm, and the monitoring of subsequent standard operations of workers is extremely limited. In addition, some existing methods for safety rope detection often require workers to manually operate the equipment for detection, which is cumbersome and prone to detection omission or untimely detection due to human negligence, and cannot make accurate judgments and feedback on the safety status in the first time, making it difficult to meet the growing safety operation requirements. Summary of the Invention

[0004] In view of the above situation, to make up for the above existing defects, the present invention provides a safety helmet warning system based on artificial intelligence, which solves the problems of only being able to give a single voice prompt or alarm and easy detection omission in the safety equipment room.

[0005] A safety helmet warning system based on artificial intelligence proposed by the present invention includes a safety helmet body. A radar laser altimeter sensor is installed at the front bottom of the brim of the safety helmet body. An installation shell is fixedly connected to the top of the safety helmet body, and a detection and processing device is detachably installed in the installation shell;

[0006] The detection and processing device includes a housing, which is detachably connected to the installation shell. A microprocessor is installed in the housing. A camera and a voice broadcaster connected to the microprocessor are installed in the housing. A battery is also installed in the housing to supply power to each component.

[0007] Furthermore, the microprocessor includes a data acquisition module, a data processing and intelligent analysis module, and an image recognition module. The data acquisition module is responsible for collecting the data of the height of stepping into empty space measured by the radar laser altimeter sensor and the image data of the safety rope collected by the camera in the image recognition module, etc. The data processing and intelligent analysis module processes and analyzes the collected data. For the data of the height of stepping into empty space, it will compare with the preset safety value to judge whether it exceeds the safety range. For the image data of the safety rope of the image recognition module, it will use model algorithms for analysis to identify whether the state of the safety rope meets the specifications.

[0008] Further, the image recognition module uses a deep learning algorithm to construct a safety rope image recognition model. After learning and training on a large number of images of the standard state and abnormal state of safety ropes, the safety rope image recognition model can accurately identify the state of the key parts of the safety rope in the images captured by the camera and determine whether it meets the safety specification requirements.

[0009] Further, the data processing and intelligent analysis module activates the voice broadcaster through the warning execution module. The warning execution module is connected to the image recognition module, and the image recognition module stops the alarm after checking that the safety rope meets the specifications through the camera.

[0010] Further, other sensors are integrated on the housing, including environmental sensors such as temperature sensors, humidity sensors, and wind speed sensors. Each sensor is connected to the microprocessor through a data cable to collect environmental data in real time and transmit it to the microprocessor.

[0011] Further, the microprocessor is a dual-core Cortex-A53 processor.

[0012] Further, the ranging range of the radar laser altimeter sensor is 0.5 - 15m, and the accuracy is ±1cm.

[0013] The beneficial effects achieved by the present invention with the above structure are as follows: The advantages of an artificial intelligence-based safety helmet warning system of the present invention are:

[0014] 1. Through the advanced radar laser altimeter sensor, the present invention can measure the height of the worker's misstep in real time with millimeter-level accuracy. In addition to monitoring the misstep height, the system introduces an image recognition module to monitor the key parts of the safety rope. By using a deep learning algorithm to identify the state of the safety rope, potential safety hazards such as the safety rope not being fastened tightly, worn, or broken can be detected in a timely manner, expanding the safety monitoring range from a single height monitoring to the state monitoring of key safety equipment and comprehensively ensuring the safety of workers during operation.

[0015] 2. When the detected misstep height exceeds the safety value, the system immediately activates the voice broadcaster. At the same time, once the image recognition system confirms that the safety rope meets the specifications, the system automatically stops the alarm, avoiding ineffective interference, realizing efficient warning and intelligent feedback, enabling workers to focus on their work, and effectively improving work efficiency.

[0016] 3. The artificial intelligence algorithm of this system has strong environmental adaptability, can integrate data from environmental sensors such as temperature, humidity, and wind speed, comprehensively judge the impact of environmental factors on the safety of workers during operation, and provide more reliable safety protection for workers. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present invention and form a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the accompanying drawings:

[0018] Figure 1 is a schematic structural diagram of the safety helmet in the safety helmet warning system based on artificial intelligence of the present invention Figure 1 ;

[0019] Figure 2 is a schematic structural diagram of the safety helmet in the safety helmet warning system based on artificial intelligence of the present invention Figure 2 ;

[0020] Figure 3 is a structural diagram of the detection and processing device in the safety helmet warning system based on artificial intelligence of the present invention;

[0021] Figure 4 is a structural block diagram of the detection and processing device in the safety helmet warning system based on artificial intelligence of the present invention;

[0022] Figure 5 is a system block diagram of the safety helmet warning system based on artificial intelligence of the present invention.

[0023] Among them, 1. Safety helmet body, 2. Radar laser altimeter sensor, 3. Installation shell, 4. Detection and processing device, 5. Shell, 6. Microprocessor, 7. Camera, 8. Voice broadcaster, 9. Data acquisition module, 10. Data processing and intelligent analysis module, 11. Image recognition module, 12. Warning execution module, 13. Other sensors, 14. Battery. Detailed implementation manners

[0024] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0025] It should be noted that the terms "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to the directions in the accompanying drawings, and the terms "inner" and "outer" respectively refer to the directions towards or away from the geometric center of a specific component.

[0026] Such as Figures 1-5As shown in the figure, the technical solution adopted by the present invention is as follows: An artificial intelligence-based safety helmet warning system proposed by the present invention includes a safety helmet body 1. A radar laser altimeter sensor 2 is installed at the bottom in front of the brim of the safety helmet body 1. The ranging range of the radar laser altimeter sensor 2 is 0.5 - 15 m, and the accuracy is ±1 cm. A mounting shell 3 is fixedly connected to the top of the safety helmet body 1. A detection and processing device 4 is detachably installed in the mounting shell 3;

[0027] As Figure 3 , 4 As shown in the figure, the detection and processing device 4 includes a housing 5. The housing 5 is detachably connected to the mounting shell 3. A microprocessor 6 is installed in the housing 5. The microprocessor 6 is a dual-core Cortex-A53 processor. A camera 7 and a voice broadcaster 8 connected to the microprocessor 6 are installed in the housing 5. A battery 14 is also installed in the housing 5 to supply power to each component. Other sensors 13 are integrated on the housing 5, including environmental sensors such as a temperature sensor, a humidity sensor, and a wind speed sensor. Each sensor is connected to the microprocessor 6 through a data cable to collect environmental data in real time and transmit it to the microprocessor 6.

[0028] As Figure 5 As shown in the figure, the microprocessor 6 includes a data acquisition module 9, a data processing and intelligent analysis module 10, and an image recognition module 11. The data acquisition module 9 is responsible for collecting the data of the stepping height measured by the radar laser altimeter sensor 2 and the image data of the safety rope collected by the camera 7 in the image recognition module 11, etc. The data processing and intelligent analysis module 10 processes and analyzes the collected data. For the stepping height data, it will be compared with a preset safety value to judge whether it exceeds the safety range. For the image data of the safety rope in the image recognition module 11, it will be analyzed using a model algorithm to identify whether the state of the safety rope meets the specifications. The image recognition module 11 uses a deep learning algorithm to construct a safety rope image recognition model. The safety rope image recognition model, through learning and training on a large number of images of the standard state and abnormal state of the safety rope, can accurately identify the state of the key parts of the safety rope in the image taken by the camera 7 and judge whether it meets the safety specification requirements. The data processing and intelligent analysis module 10 starts the voice broadcaster 8 through the warning execution module 12. The warning execution module 12 is connected to the image recognition module 11. The image recognition module 11 stops the alarm after checking that the safety rope meets the specifications through the camera 7.

[0029] During specific use, workers wear the safety helmet body 1 and enter the operation area. The radar laser altimeter 2 in the data acquisition module 9 collects altitude data in real time. The collected data is quickly transmitted to the data processing and intelligent analysis module 10. The tripping risk assessment model analyzes the altitude data to determine whether there is a tripping risk. When there is a risk, the warning execution module 12 activates the voice broadcaster 8 for voice broadcast reminder. The staff needs to aim the camera 7 at the safety rope, and the image recognition module 11 recognizes the image data to determine whether the state of the key parts of the safety rope meets the specifications. If the safety rope does not meet the specifications, the voice broadcaster 8 continues to alarm. When it meets the specifications, the voice broadcaster 8 stops working.

[0030] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, material or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, material or device.

[0031] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An artificial intelligence-based helmet early warning system, comprising a helmet body (1), a radar laser height sensor (2) being installed at the front bottom of the brim of the helmet body (1), a mounting shell (3) being fixedly connected to the top of the helmet body (1), and a detection and processing device (4) being detachably installed in the mounting shell (3); The detection and processing device (4) comprises a shell (5), the shell (5) and the mounting shell (3) are detachably connected, a microprocessor (6) is installed in the shell (5), a camera (7) and a voice announcer (8) connected to the microprocessor (6) are installed in the shell (5), and a battery (14) is also installed in the shell (5).

2. The artificial intelligence-based helmet warning system according to claim 1 is characterized by: The microprocessor (6) comprises a data acquisition module (9), a data processing and intelligent analysis module (10) and an image recognition module (11); the data acquisition module (9) is responsible for collecting the stepping height data measured by the radar laser height measurement sensor (2) and the safety rope image data collected by the camera (7) in the image recognition module (11); The data processing and intelligent analysis module (10) processes and analyzes the collected data. For the step height data, it compares it with the preset safety value to determine whether it exceeds the safety range; for the safety rope image data of the image recognition module (11), it uses a model algorithm to analyze it to identify whether the state of the safety rope meets the specifications.

3. The artificial intelligence-based helmet warning system according to claim 2 is characterized in that: The image recognition module (11) uses a deep learning algorithm to construct a safety rope image recognition model. After learning and training a large number of safety rope standard state and abnormal state images, the safety rope image recognition model can accurately identify the state of key parts of the safety rope in the image taken by the camera (7) and judge whether it meets the safety specification requirements.

4. The artificial intelligence-based helmet warning system according to claim 3 is characterized by: The data processing and intelligent analysis module (10) starts the voice announcer (8) through the early warning execution module (12), and the early warning execution module (12) is connected to the image recognition module (11). The image recognition module (11) stops the alarm after checking that the safety rope meets the specifications through the camera (7).

5. The artificial intelligence-based helmet warning system according to claim 1 is characterized by: The housing (5) is integrated with other sensors (13), including temperature sensors, humidity sensors, wind speed sensors and other environmental sensors, each of which is connected to the microprocessor (6) via a data cable to collect environmental data in real time and transmit the data to the microprocessor (6).

6. The artificial intelligence-based helmet warning system according to claim 1 or 2, characterized in that: The microprocessor (6) is a dual-core Cortex-A53 processor.

7. The artificial intelligence-based helmet warning system according to claim 1, characterized in that: The radar laser height measuring sensor (2) has a distance measuring range of 0.5-15m and an accuracy of ±1cm.

Images