Multi-scene limited operation space intelligent management method and system based on safety helmet

Abstract

The invention relates to the technical field of limited space operation safety, in particular to a multi-scene limited operation space intelligent management method and system based on a safety helmet, and the method comprises the steps: S1, dividing unsafe behaviors in a limited operation space according to scenes, and respectively building a multi-scene unsafe behavior database; s2, training a multi-scene unsafe behavior recognition model according to the data of the multi-scene unsafe behavior database; and S3, inputting data acquired by the safety helmet into the multi-scene unsafe behavior recognition model, and outputting early warning information of unsafe behaviors. The method provided by the invention solves the problems that the current intelligent safety helmet is insufficient in functional adaptability in a multi-scene limited operation space and is difficult to form a combined prevention and control system with safety supervision and monitoring equipment in the scene.

Description

Technical Field

[0001] This application relates to the field of confined space operation safety technology, specifically to a multi-scenario confined space intelligent management method and system based on safety helmets. Background Technology

[0002] A safety helmet is an important piece of personal protective equipment, primarily used to protect the head from accidental injuries. Its core functions include: 1. Impact protection: In construction, mining, and factory work environments, safety helmets can withstand direct impacts from falling tools, gravel, steel bars, and other hard objects, dispersing the impact force and reducing head injury. 2. Protection against falling objects: In high-altitude work or multi-story construction sites, safety helmets effectively cushion the impact of falling objects (such as bricks and tools), preventing skull fractures or concussions. 3. Protection against electric shock: Electrician-specific safety helmets typically use insulating materials (such as fiberglass and modified plastics) to prevent electric shock accidents and reduce damage to the head from current. 4. Anti-static properties: Safety helmets in certain special locations (such as petrochemical plants) have anti-static functions to prevent sparks from igniting explosions.

[0003] Since construction workers are required to wear safety helmets when entering the construction site according to regulations, the safety of the construction site can also be monitored based on the safety helmets, forming a joint prevention and control system.

[0004] Currently, smart safety helmets suffer from insufficient functional adaptability in limited work spaces across various scenarios, and are difficult to integrate with safety supervision and monitoring equipment within those scenarios to form a joint prevention and control system. Summary of the Invention

[0005] This application focuses on smart safety helmets, addressing the current limitations of smart safety helmets in limited work spaces across various scenarios and their difficulty in forming a joint prevention and control system with on-site safety supervision and monitoring equipment. It analyzes and summarizes the functional requirements and design principles of smart safety helmets in different scenarios within limited work spaces, and proposes methods for improving and optimizing smart safety helmet products suitable for different scenarios. Based on this, it focuses on the data acquisition and human-computer interaction functions of smart safety helmets to achieve safety in confined space operations and rapid detection and suppression of toxic and harmful substances.

[0006] Based on the above concept, the following technical solution is proposed: A multi-scenario, confined workspace intelligent management method based on safety helmets includes: S1, classify unsafe behaviors in a limited workspace according to scenarios and establish a database of unsafe behaviors for multiple scenarios; S2, train a multi-scenario unsafe behavior recognition model based on data from a multi-scenario unsafe behavior database; S3 inputs the data collected by the safety helmet into the unsafe behavior recognition model for multiple scenarios and outputs warning information about unsafe behaviors.

[0007] Furthermore, the limited working space includes: tunnels, sewage pipes, and deep foundation pits.

[0008] Furthermore, in tunnel scenarios, unsafe behaviors include: not wearing protective equipment or respiratory protective equipment; malfunctioning emergency lighting; entering the warning zone too early after blasting; smoke detection; smoking in violation of regulations; and not using ventilation equipment.

[0009] Furthermore, in the context of sewage pipelines, unsafe behaviors include: going down into the well without detecting gas; not wearing protective equipment; not wearing respiratory protective equipment; not wearing a five-point safety harness; working without supervision; and not using ventilation equipment.

[0010] Furthermore, in the context of deep foundation pits, unsafe behaviors include: undetected gas entering the pipe jacking area directly; not wearing protective equipment; not wearing respiratory protective equipment; not wearing a five-point safety harness; working without supervision; not wearing a five-point safety harness; smoke and fire detection; and not using ventilation equipment.

[0011] Furthermore, the data collected by the safety helmet includes vital sign sensing data, image data, and gas data. The data collected by the safety helmet is then fused into a multi-scenario unsafe behavior recognition model.

[0012] Furthermore, the multi-scenario unsafe behavior recognition model is constructed by combining machine learning, deep learning, and AI vision.

[0013] Based on the same concept, a multi-scenario confined workspace intelligent management system based on safety helmets was also proposed, including a safety helmet with a data acquisition device, a processor, and a monitoring device; The safety helmet equipped with a data acquisition device is used to collect data and input the collected data into a processor. The processor is used to output early warning information of unsafe behavior based on the unsafe behavior identification model of the collected data; Monitoring devices are used to output warning signals based on early warning information about unsafe behaviors; The unsafe behavior identification model for multiple scenarios is trained based on data from a database of unsafe behaviors in multiple scenarios. This database is established by dividing unsafe behaviors in a limited workspace into scenarios.

[0014] Furthermore, the data collected by the safety helmet equipped with the data acquisition device includes vital sign sensing data, image data, and gas data.

[0015] Furthermore, the processor centrally collects, analyzes, and automatically issues instructions for data in various scenarios; multiple safety helmets establish an interconnected safety control network to achieve joint prevention and control.

[0016] Compared with the prior art, the beneficial effects of this application are: the method of the present invention solves the problems of insufficient functional adaptability of current smart safety helmets in limited working spaces in multiple scenarios and difficulty in forming a joint prevention and control system with safety supervision and monitoring equipment in the scenario. Attached Figure Description

[0017] Figure 1 A flowchart of a multi-scenario confined workspace intelligent management method based on safety helmets; Figure 2 This is a front view of the safety helmet; Figure 3 This is a left-side view of the safety helmet; Figure 4 This is a rear view of the safety helmet; Figure 5 This is an internal view of the safety helmet. Detailed Implementation

[0018] The present application will now be described in further detail with reference to experimental examples and specific embodiments. However, this should not be construed as limiting the scope of the subject matter of the present application to the following embodiments. All technologies implemented based on the content of the present application fall within the scope of protection of the present application.

[0019] Unless otherwise specified, the terms "upper," "lower," "left," "right," "center," "inner," "outer," and "side" used in the description of specific embodiments of this application to indicate orientation or positional relationships are based on the orientation or positional relationships shown in the accompanying drawings, or the orientation or positional relationship in which the product / equipment / device is usually placed during use. These terms are merely for the purpose of facilitating the description of the solution in this application or simplifying the description in specific embodiments, so as to enable those skilled in the art to quickly understand the solution, and do not indicate or imply that a particular device / component / element must have a specific orientation, or be constructed and operated in a specific positional relationship. Therefore, they should not be construed as limitations on this application.

[0020] In the description of the embodiments of this application, technical terms such as "first" and "second" only distinguish one entity or operation from another, and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary or secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] Example 1 A multi-scenario, confined workspace intelligent management method based on safety helmets includes: S1, classify unsafe behaviors in a limited workspace according to scenarios and establish a database of unsafe behaviors for multiple scenarios; S2, train a multi-scenario unsafe behavior recognition model based on data from a multi-scenario unsafe behavior database; S3 inputs the data collected by the safety helmet into the unsafe behavior recognition model for multiple scenarios and outputs warning information about unsafe behaviors.

[0023] Furthermore, the limited working space includes: tunnels, sewage pipes, and deep foundation pits. Step S1 specifically includes the following steps: In tunnel scenarios, unsafe behaviors include: not wearing protective equipment or respiratory protective equipment; malfunctioning emergency lighting; entering the warning zone too early after blasting; smoke detection; smoking in violation of regulations; and not using ventilation equipment.

[0024] In the context of sewage pipelines, unsafe behaviors include: going down into the well without detecting gas; not wearing protective equipment; not wearing respiratory protective equipment; not wearing a five-point safety harness; working without supervision; and not using ventilation equipment.

[0025] In deep foundation pit scenarios, unsafe behaviors include: undetected gas entering the pipe jacking area directly; not wearing protective equipment; not wearing respiratory protective equipment; not wearing a five-point safety harness; working without supervision; not wearing a five-point safety harness; smoke and fire detection; and not using ventilation equipment.

[0026] To address the issues of redundant functional design and insufficient application relevance in current smart safety helmets for different scenarios, this paper analyzes the functional requirements of smart safety helmets in confined spaces under conditions of limited working space, such as tunnels, sewage pipelines, and deep foundation pits, and proposes a functional division scheme for smart safety helmets in different scenarios. The characteristics of confined working space scenarios and their corresponding functions are shown in Table 1. Table 1. Characteristics and corresponding functions of confined workspace scenarios

[0027] Furthermore, the data collected by the safety helmet includes vital sign sensing data, image data, and gas data. This data, after feature fusion, is input into a multi-scenario unsafe behavior recognition model. Taking the three functions of the smart safety helmet—gas detection, vital sign recognition, and safety helmet video recognition—as a starting point, sensor technology, machine learning and deep learning technology, multi-feature fusion technology, and AI vision technology are used to optimize these three functions, improving their usefulness and reliability, thereby achieving an overall enhancement of the smart safety helmet's functionality.

[0028] Furthermore, the multi-scenario unsafe behavior recognition model is constructed by combining machine learning, deep learning, and AI vision.

[0029] Example 2 Based on the same concept, a multi-scenario confined workspace intelligent management system based on safety helmets was also proposed, including a safety helmet with a data acquisition device, a processor, and a monitoring device; The safety helmet equipped with a data acquisition device is used to collect data and input the collected data into a processor. The processor is used to output early warning information of unsafe behavior based on the unsafe behavior identification model of the collected data; Monitoring devices are used to output warning signals based on early warning information about unsafe behaviors; The unsafe behavior identification model for multiple scenarios is trained based on data from a database of unsafe behaviors in multiple scenarios. This database is established by dividing unsafe behaviors in a limited workspace into scenarios.

[0030] Furthermore, a hardware design framework for an intelligent safety helmet is established. Through the rational design of the data acquisition unit and control unit, the product characteristics of stability, durability, lightweight, and low cost are met. The safety helmet with the data acquisition device collects data including vital sign sensing data, image data, and gas data. A schematic diagram of a specific safety helmet is shown below. Figure 2 , 3 As shown in Figures 4 and 5, taking the three functions of smart safety helmets—gas detection, vital sign recognition, and video recognition—as a starting point, this study employs sensor technology, machine learning and deep learning technology, multi-feature fusion technology, and AI vision technology to optimize these three functions, improving their usefulness and reliability, thereby achieving an overall enhancement of the smart safety helmet's functionality. Figure 1 As shown, the front of the safety helmet is equipped with a light, a camera, and an infrared laser head for collecting image and video information, such as... Figure 2 As shown, the safety helmet has a gas detection device at the back and ventilation holes at the top. Figure 4As shown, there are also warning lights on the rear to alert those in the vicinity who are wearing helmets. Figure 4 As shown, the helmet also contains a USB port, a magnetic charging port, a battery mounting component, an emergency call button, a photo / record button, a vital signs sensor, a voice intercom button, and power on / off and volume control buttons.

[0031] Furthermore, the processor centrally collects, analyzes, and automatically issues instructions for data in various scenarios; multiple safety helmets establish an interconnected safety control network to achieve joint prevention and control.

[0032] To fully leverage the data value of multi-source data collected by smart safety helmets in multi-scenario safety control, an adaptive data collection and management system was developed based on the characteristics of safety control in each scenario. This system was then interconnected with other safety supervision and monitoring equipment (voice broadcasting, video surveillance, disaster monitoring, etc.) within the scenario to establish a joint safety control management system, thereby achieving multi-device joint safety control centered on smart safety helmets.

[0033] The beneficial effects of this invention are: 1. Based on the characteristics of various confined workspace scenarios, this study analyzes the functional requirements of smart safety helmets for confined spaces in multiple scenarios. Building upon this analysis, the functional design of the smart safety helmet is optimized from hardware sensor acquisition and control units to software system implementation. This optimization effectively addresses the current problem of insufficient environmental adaptability of smart safety helmets, reduces their performance burden, and improves the reliability of functional applications. This is the first anticipated innovation of this research. Compared to current commercially available smart safety helmet products, this research demonstrates a certain degree of advancement.

[0034] 2. Unsafe behaviors in confined work spaces are categorized by scenario, and image databases of unsafe behaviors for each scenario are established. Based on these databases, unsafe behavior recognition models for each scenario are built using AI visual recognition technology. This enables intelligent recognition and real-time early warning of unsafe behaviors in confined work spaces across multiple scenarios, effectively improving the efficiency of on-site safety management. This is the second expected innovation of this research. Compared with similar technologies, this research has strong advancements and is expected to reach a leading level in China.

[0035] 3. By establishing a multi-device linkage mechanism in a confined workspace and conducting joint control based on a software system, the goal of achieving joint safety prevention and control can be realized, effectively improving the level of joint safety prevention and control in various confined workspace scenarios. This is the third expected innovation of this research. Compared with similar technologies, this research has good advanced features and is expected to reach the advanced level in China.

[0036] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for intelligent management of confined workspaces in multiple scenarios based on safety helmets, characterized in that: include: S1, classify unsafe behaviors in a limited workspace according to scenarios and establish a multi-scenario unsafe behavior database; S2, train a multi-scenario unsafe behavior recognition model based on data from a multi-scenario unsafe behavior database; S3 inputs the data collected by the safety helmet into the unsafe behavior recognition model for multiple scenarios and outputs warning information about unsafe behaviors.

2. The method according to claim 1, characterized in that, The limited working space includes: tunnels, sewage pipes, and deep foundation pits.

3. The method according to claim 2, characterized in that, In tunnel scenarios, unsafe behaviors include: not wearing protective equipment; respiratory protective equipment; malfunctioning emergency lighting; entering the warning zone too early after blasting; smoke detection; smoking in violation of regulations; and not using ventilation equipment.

4. The method according to claim 2, characterized in that, In the context of sewage pipelines, unsafe behaviors include: going down into the well without detecting gas; not wearing protective equipment; not wearing respiratory protective equipment; not wearing a five-point safety harness; working without supervision; and not using ventilation equipment.

5. The method according to claim 2, characterized in that, In deep foundation pit scenarios, unsafe behaviors include: undetected gas entering the pipe jacking area directly; not wearing protective equipment; not wearing respiratory protective equipment; not wearing a five-point safety harness; working without supervision; not wearing a five-point safety harness; smoke and fire detection; and not using ventilation equipment.

6. The method according to claim 1, characterized in that, The data collected by the safety helmet includes vital sign sensing data, image data, and gas data. After feature fusion, the data collected by the safety helmet is input into a multi-scenario unsafe behavior recognition model.

7. The method according to claim 1, characterized in that, The multi-scenario unsafe behavior recognition model is constructed by combining machine learning, deep learning, and AI vision.

8. A multi-scenario confined workspace intelligent management system based on safety helmets, characterized in that: This includes a safety helmet with a data acquisition device, a processor, and a monitoring device; The safety helmet equipped with a data acquisition device is used to collect data and input the collected data into a processor. The processor is used to output early warning information of unsafe behavior based on the unsafe behavior identification model of the collected data; Monitoring devices are used to output warning signals based on early warning information about unsafe behaviors; The unsafe behavior identification model for multiple scenarios is trained based on data from a database of unsafe behaviors in multiple scenarios. This database is established by dividing unsafe behaviors in a limited workspace into scenarios.

9. The management system as described in claim 8, characterized in that, The safety helmet equipped with a data acquisition device collects data including vital sign sensing data, image data, and gas data.

10. The management system as described in claim 8, characterized in that, The processor centrally collects and analyzes data from various scenarios and automatically issues instructions; multiple safety helmets establish an interconnected safety control network to achieve joint prevention and control.

Images