AI project construction safety auxiliary management system based on edge calculation

Abstract

The invention relates to an AI project construction safety auxiliary management system based on edge computing, which comprises a sensing layer, a network layer, a platform layer and an application layer, and is characterized in that the sensing layer comprises an intelligent safety helmet and a field host, the intelligent safety helmet is worn on the head of a constructor and is integrated with various sensors, and the field host is connected with the network layer; the intelligent safety helmet transmits a detection signal to the host and receives an error correction prompt of the host, a safety regulation case and an operation specification file are built in the field host, an operation process and a work ticket requirement are compared in real time, the field host judges an operation specification, and the platform layer is provided with a document storage module and an analysis model. The document storage module stores a compliant engineering project construction management annotation document, the analysis model analyzes information collected by the field host and transmits a signal to the application layer in combination with the engineering project construction management annotation document, and the application layer comprises a background monitoring platform and a mobile phone terminal.

Description

Technical Field

[0001] The present invention relates to the field of safe production, and in particular to an AI project construction safety auxiliary management system based on edge computing. Background Art

[0002] In the existing technology, project construction safety is an important indicator of construction site security. The existing technology has the following shortcomings: ⑴ Due to the generally low quality of construction personnel and frequent habitual violations, the existing safety measures are to use on-site personnel supervision and smart safety video surveillance to ensure construction safety. Safety hazards cannot be discovered in time and violations cannot be corrected in time; ⑵ The workload of writing documents required for construction management, such as construction plans, budgets, quality plans, etc., is large. Construction personnel cannot write the above documents well, and it is difficult to ensure the accuracy and timeliness of the documents. Moreover, the management of these documents relies on manual labor and lacks intelligent means, resulting in untimely document updates, affecting construction progress and quality. Summary of the Invention

[0003] In view of the above-mentioned defects in the existing technology, the technical problems to be solved by the present invention are the heavy workload of compiling the documents required for construction management, such as construction plans, budgets, and quality plans, the safety hazards and habitual violations at the construction site, and the inability of on-site supervision and video surveillance to detect problems and correct violations in a timely manner. The specific technical solution is as follows:

[0004] An AI project construction safety auxiliary management system based on edge computing, including perception layer, network layer, platform layer and application layer.

[0005] The perception layer includes a smart helmet and an on-site host. The smart helmet is worn on the head of the construction worker and is integrated with multiple sensors. The smart helmet transmits detection signals to the host and receives error correction prompts from the host. The on-site host has built-in safety regulations and work specification documents, and compares the work process with the work ticket requirements in real time. The on-site host determines the work specifications.

[0006] The network layer includes 5G private network and LoRaWAN or WAP1 or WiFi hybrid network. The on-site host transmits information to the platform layer and application layer through the network layer.

[0007] The platform layer is provided with a document storage module and an analysis model. The document storage module stores compliant engineering project construction management annotation documents. The analysis model analyzes the information collected by the on-site host and transmits the signal to the application layer in combination with the engineering project construction management annotation documents.

[0008] The application layer includes the background monitoring platform and the mobile terminal. The background monitoring platform automatically generates the documents required for the construction management of the engineering project and imports the work tickets and pushes them to the on-site host. It also saves the process images and error correction records and automatically generates work logs. The mobile terminal can also import the work tickets and push them to the on-site host. It can also save the process images and error correction records and automatically generate work logs.

[0009] As a preferred solution for the AI project construction safety auxiliary management system, the smart safety helmet includes a safety helmet body and a strap. The safety helmet body is used to be put on the human head, and a strap is installed under the safety helmet body. A sensor mounting strap is installed on the outer peripheral side of the middle part of the safety helmet body. Various sensors include millimeter-wave radar, gas sensor, nine-axis attitude sensor, and infrared thermal imaging module. Communication module, millimeter-wave radar, cap camera, lighting, gas sensor, and battery are installed in the sensor mounting strap. The communication module is used to transmit wireless signals with external devices, the millimeter-wave radar is used for positioning, the cap camera is used to shoot the surrounding environment, the lighting is used for lighting, and the gas sensor is used to detect the concentration of hydrogen sulfide and oxygen in the air. A nine-axis attitude sensor is installed in the strap, and an infrared thermal imaging module is installed on the safety helmet body. The infrared thermal imaging module is used for body temperature monitoring, and the battery is used to provide power for the communication module, millimeter-wave radar, cap camera, lighting, gas sensor, and nine-axis attitude sensor.

[0010] As the preferred solution for the AI project construction safety auxiliary management system, the nine-axis attitude sensor is used to detect the hat-taking action. The nine-axis attitude sensor consists of a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer. It outputs high-precision attitude information through a data fusion algorithm. The equipment, safety tools and on-site operation scenes captured by the hat camera are transmitted to the on-site host to determine compliance.

[0011] As a preferred solution for the AI project construction safety auxiliary management system, the on-site host includes a host body, a host camera, an antenna, a tripod bracket and a power module. The host camera is installed on the host body, and the host camera collects construction scene images and personnel location information in real time. The antenna is installed on the side of the host body, and a tripod bracket is installed under the host body. The power module supplies power to the host.

[0012] As the priority solution for the AI project construction safety auxiliary management system, after the host camera recognizes the compliance of the work ticket and the operator, it will transfer the violation information detected during the construction process, such as the crane without anti-falling device and the personnel not wearing safety helmets, to the on-site smart safety helmet and the background monitoring platform and mobile phone. The background monitoring platform automatically generates the documents required for project construction management, such as construction plans, budgets, quality plans, etc., imports the work ticket and pushes it to the on-site host. It has the functions of process image storage, error correction records, and automatic generation of work logs.

[0013] As the preferred solution for the AI project construction safety auxiliary management system, the background monitoring platform and the mobile database store work tickets, images and records, use cloud services to store data processed by edge computing, and automatically generate work logs through natural language processing or template filling combined with time, location, work content and other data.

[0014] As a priority solution for the AI project construction safety auxiliary management system, when the on-site host detects a violation, it will issue an audible and visual warning through the speaker or vibration module of the smart safety helmet within 30ms, reminding workers and on-site managers to correct the violation in a timely manner, block the illegal operation process, and record the violation and blocked operation to facilitate subsequent analysis and processing.

[0015] An AI project construction safety application scenario based on edge computing applies the above-mentioned AI project construction safety auxiliary management system to the construction operation scenario. In this scenario, the on-site host monitors the operation site in real time through the camera. When violations such as "no anti-fall device" or "not wearing a safety helmet" are detected, the violation information is immediately pushed to the smart safety helmet, the background monitoring platform and the mobile phone. The management personnel can view the situation of the crane operation site in real time through the background monitoring platform or the mobile phone, and remotely monitor and direct the operation process. When violations or safety hazards are discovered, the management personnel can issue instructions in time through the background monitoring platform and the mobile phone to guide the on-site personnel to correct and deal with them.

[0016] An AI project construction safety application scenario based on edge computing applies the above-mentioned AI project construction safety auxiliary management system to high-altitude work scenarios. In high-altitude work scenarios, smart safety helmets integrate multiple sensors to monitor the physical condition of personnel in real time. When it is detected that a person is unwell or engages in dangerous behavior, it immediately reminds on-site personnel and management personnel through sound and light alarms. The millimeter-wave radar locates the position of the personnel in real time. When a person engages in dangerous behaviors such as falling or taking off a hat in a high-altitude work area, the system automatically triggers sound and light alarms, and notifies relevant personnel through the background monitoring platform and mobile phones to take rescue measures in time. The positioning and alarm functions can quickly determine the location of dangerous personnel and promptly notify rescue personnel to deal with them.

[0017] Beneficial effects:

[0018] (1) The on-site host of the perception layer compares the operation process with the work ticket requirements in real time through the built-in safety regulations and operating specifications with a camera, prompts omissions or errors, identifies the compliance of personnel identities, operating processes, safety protection facilities, tools, etc., and corrects errors;

[0019] (2) The smart helmet is integrated with a variety of sensors. The smart helmet transmits detection signals to the host and receives error correction prompts from the host. It can locate and transmit actual working conditions, monitor personnel's physical condition, hat removal, environment and other information;

[0020] (3) The background monitoring platform automatically generates the documents required for the construction management of the project and imports the work tickets and pushes them to the on-site host. It also has functions such as process image storage, error correction records, and automatic generation of work logs to achieve automation and intelligence of document management. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a layered diagram of the present invention;

[0022] Figure 2 It is a front view of the safety helmet of the present invention;

[0023] Figure 3 It is a side view of the safety helmet of the present invention;

[0024] Figure 4 It is a three-dimensional view of the safety helmet of the present invention;

[0025] Figure 5 It is a front view of the on-site host of the present invention;

[0026] Figure 6 This is a schematic diagram of the on-site host transmission signal of the present invention;

[0027] Figure 7 Schematic diagram of the application scenario of the present invention. DETAILED DESCRIPTION

[0028] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings:

[0029] In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the position or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limiting the present invention.

[0030] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediary; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0031] like Figure 1As shown in the figure, an AI project construction safety auxiliary management system based on edge computing includes the perception layer, network layer, platform layer and application layer.

[0032] The perception layer includes a smart helmet and an on-site host. The smart helmet is worn on the head of the construction worker and is integrated with multiple sensors. The smart helmet transmits detection signals to the host and receives error correction prompts from the host. The on-site host has built-in safety regulations and work specification documents, and compares the work process with the work ticket requirements in real time. The on-site host determines the work specifications.

[0033] The network layer includes 5G private network and LoRaWAN or WAP1 or WiFi hybrid network. The on-site host transmits information to the platform layer and application layer through the network layer.

[0034] The platform layer is provided with a document storage module and an analysis model. The document storage module stores compliant engineering project construction management annotation documents. The analysis model analyzes the information collected by the on-site host and transmits the signal to the application layer in combination with the engineering project construction management annotation documents. The analysis model has a built-in YOLOv7+DeepSORT multi-target tracking model.

[0035] The application layer includes the background monitoring platform and the mobile terminal. The background monitoring platform automatically generates the documents required for the construction management of the engineering project and imports the work tickets and pushes them to the on-site host. It also saves the process images and error correction records and automatically generates work logs. The mobile terminal can also import the work tickets and push them to the on-site host. It can also save the process images and error correction records and automatically generate work logs.

[0036] like Figure 2-4As shown, the smart helmet includes a helmet body 1 and a strap 2. The strap 2 is mounted below the helmet body 1. The smart helmet also includes a sensor mounting strap 3 mounted on the outer periphery of the central portion of the helmet body 1. The sensor mounting strap 3 is equipped with a communication module 4, a millimeter-wave radar 5, a camera 6, a lighting lamp 7, a gas sensor 8, and a battery 9. The communication module 4 is used for wireless signal transmission with external devices such as an on-site host. The millimeter-wave radar 5 is used for positioning. The camera 6 is used to capture the surrounding environment. The lighting lamp 7 is used for illumination. The gas sensor 8 is used to detect the concentration of hydrogen sulfide and oxygen in the air. The battery 9 is used to provide power to the communication module 4, the millimeter-wave radar 5, the camera 6, the lighting lamp 7, and the gas sensor 8. The strap 2 is equipped with a nine-axis attitude sensor 10 for detecting the action of taking off the helmet. The nine-axis attitude sensor 10 is composed of a three-axis accelerometer, a three-axis gyroscope, and a three-axis magnetometer. The nine-axis attitude sensor outputs high-precision attitude information through a data fusion algorithm. A three-axis accelerometer measures linear acceleration based on inertial force. It measures the direction of gravity when static, calculates pitch and roll angles, and detects linear motion when dynamic. A three-axis gyroscope uses Coriolis force or MEMS (microelectromechanical systems) to measure angular velocity, detecting rotational angular velocity about the X / Y / Z axes. Long-term use can lead to integral drift errors, requiring correction through data fusion with other sensors. A three-axis magnetometer measures the Earth's magnetic field strength using the Hall effect or magnetoresistive effect. Data fusion algorithms combine the data from these three sensors to compensate for the limitations of a single sensor. Common data fusion algorithms include: Kalman filtering for dynamic noise suppression; complementary filtering for low computational complexity, suitable for embedded systems; and Madgwick / Mahony algorithm for efficient attitude resolution.

[0037] Specifically, the helmet body 1 is equipped with an infrared thermal imaging module 11 for temperature monitoring and monitoring the physical condition of construction workers. A camera 6 and lighting 7 are located on the front side of the sensor mounting strap 3 for easy operation. The communication module 4 transmits wireless signals via Cat.1 and Bluetooth 5.2 dual-mode, ensuring stable signal transmission. The sensor mounting strap 3 is detachable, allowing the communication module 4, millimeter-wave radar 5, camera 6, lighting 7, gas sensor 8, battery 9, and other components to be removed from the helmet body for easy maintenance.

[0038] like Figure 5 As shown, the on-site host includes a host body 12, a host camera 13, an antenna 14, a tripod bracket 15 and a power module 16. The host camera 13 is installed on the host body 12, and the host camera 13 collects construction scene images and personnel location information in real time. The antenna 14 is installed on the side of the host body 12, and the tripod bracket 15 is installed below the host body 12. The power module 16 supplies power to the host.

[0039] like Figure 6As shown, after the host camera recognizes that the work ticket and the operator are in compliance, it transfers the violation information detected during the construction process, such as the crane without anti-falling device and the personnel not wearing safety helmets, to the on-site smart safety helmet and the background monitoring platform and mobile phone. The background monitoring platform automatically generates the documents required for project construction management, such as construction plan, budget, quality plan, etc., imports the work ticket and pushes it to the on-site host. It has the functions of process image preservation, error correction record, automatic generation of work logs, etc. The database of the background monitoring platform and the mobile phone stores work tickets, images and records, uses cloud services to store edge computing processed data, and automatically generates work logs through natural language processing, or template filling combined with time, location, work content and other data.

[0040] Specifically, when the on-site host detects a violation, it will issue an audible and visual warning through the speaker or vibration module of the smart safety helmet within 30ms, reminding workers and on-site managers to correct the violation in a timely manner, block the illegal operation process, record the violation and blocked operation, and facilitate subsequent analysis and processing.

[0041] like Figure 7 As shown, an AI project construction safety application scenario based on edge computing applies the above-mentioned AI project construction safety auxiliary management system to the crane operation scenario. In this scenario, the on-site host monitors the operation site in real time through the camera. When violations such as "no anti-fall device" or "not wearing a safety helmet" are detected, the violation information is immediately pushed to the smart safety helmet, the background monitoring platform and the mobile phone. The management personnel can view the situation of the crane operation site in real time through the background monitoring platform or the mobile phone, and remotely monitor and direct the operation process. When violations or safety hazards are found, the management personnel can issue instructions in time through the background monitoring platform and the mobile phone to guide the on-site personnel to correct and deal with them.

[0042] An AI project construction safety application scenario based on edge computing applies the above-mentioned AI project construction safety auxiliary management system to high-altitude work scenarios. In high-altitude work scenarios, smart safety helmets integrate multiple sensors to monitor the physical condition of personnel in real time. When it is detected that a person is unwell or engages in dangerous behavior, it immediately reminds on-site personnel and management personnel through sound and light alarms. The millimeter-wave radar locates the position of the personnel in real time. When a person engages in dangerous behaviors such as falling or taking off a hat in a high-altitude work area, the system automatically triggers sound and light alarms, and notifies relevant personnel through the background monitoring platform and mobile phones to take rescue measures in time. The positioning and alarm functions can quickly determine the location of dangerous personnel and promptly notify rescue personnel to deal with them.

[0043] The AI project construction safety system based on edge computing of the present invention has the following advantages:

[0044] (1) Real-time monitoring of operational compliance: Through on-site hosts and smart helmets and other equipment, construction workers' operational behavior and the use of safety equipment are monitored in real time to ensure operational compliance. AI technology is used to analyze operational scenarios in real time to promptly detect violations and issue alerts, thereby improving the real-time and effectiveness of safety management.

[0045] (2) Based on real-time data during the construction process, it automatically generates work documents such as construction plans, budgets, and quality plans, reducing the workload of manual editing and improving the accuracy and timeliness of documents. Through template filling and natural language processing technology, it combines time, location, work content and other data to generate detailed work logs, realizing the automation and intelligence of document management;

[0046] ⑶ Reduce the accident rate and improve management efficiency. Through real-time monitoring and intelligent error correction functions, timely discover and correct violations, reduce the construction accident rate, ensure the life safety of construction workers, improve the efficiency and accuracy of safety management, reduce manual management costs, and realize the digital and intelligent upgrade of construction safety management.

[0047] The above content is a further detailed description of the present invention in combination with specific preferred embodiments. It cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or replacements can be made without departing from the concept of the present invention, which should be regarded as falling within the scope of protection of the present invention.

Claims

1. An AI project construction safety auxiliary management system based on edge computing, characterized by: Including perception layer, network layer, platform layer and application layer, The perception layer includes a smart helmet and an on-site host. The smart helmet is worn on the head of the construction worker and is integrated with multiple sensors. The smart helmet transmits detection signals to the host and receives error correction prompts from the host. The on-site host has built-in safety regulations and work specification documents, and compares the work process with the work ticket requirements in real time. The on-site host determines the work specifications. The network layer includes 5G private network and LoRaWAN or WAP1 or WiFi hybrid network. The on-site host transmits information to the platform layer and application layer through the network layer. The platform layer is provided with a document storage module and an analysis model. The document storage module stores compliant engineering project construction management annotation documents. The analysis model analyzes the information collected by the on-site host and transmits the signal to the application layer in combination with the engineering project construction management annotation documents. The application layer includes the background monitoring platform and the mobile terminal. The background monitoring platform automatically generates the documents required for the construction management of the engineering project and imports the work tickets and pushes them to the on-site host. It also saves the process images and error correction records and automatically generates work logs. The mobile terminal can also import the work tickets and push them to the on-site host. It can also save the process images and error correction records and automatically generate work logs.

2. The AI project construction safety auxiliary management system based on edge computing according to claim 1 is characterized by: The smart safety helmet includes a safety helmet body and a strap. The safety helmet body is used to be put on the human head. The strap is installed under the safety helmet body. A sensor mounting strap is installed on the outer peripheral side of the middle part of the safety helmet body. Various sensors include millimeter-wave radar, gas sensor, nine-axis attitude sensor, and infrared thermal imaging module. A communication module, millimeter-wave radar, cap camera, lighting, gas sensor, and battery are installed in the sensor mounting strap. The communication module is used to transmit wireless signals with external devices, the millimeter-wave radar is used for positioning, the cap camera is used to shoot the surrounding environment, the lighting is used for lighting, and the gas sensor is used to detect the concentration of hydrogen sulfide and oxygen in the air. The nine-axis attitude sensor is installed in the strap, and the infrared thermal imaging module is installed on the safety helmet body. The infrared thermal imaging module is used for body temperature monitoring, and the battery is used to provide power for the communication module, millimeter-wave radar, cap camera, lighting, gas sensor, and nine-axis attitude sensor.

3. The AI project construction safety auxiliary management system based on edge computing according to claim 2 is characterized by: The nine-axis attitude sensor is used to detect the action of taking off the hat. The nine-axis attitude sensor consists of a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer. It outputs high-precision attitude information through a data fusion algorithm. The equipment, safety tools and on-site operation scenes captured by the hat camera are transmitted to the on-site host to judge compliance.

4. The AI project construction safety auxiliary management system based on edge computing according to claim 1 is characterized by: The on-site host includes a host body, a host camera, an antenna, a tripod bracket and a power module. The host camera is installed on the host body, and the host camera collects construction scene images and personnel location information in real time. The antenna is installed on the side of the host body, and the tripod bracket is installed below the host body. The power module supplies power to the host.

5. The AI project construction safety auxiliary management system based on edge computing according to claim 4 is characterized in that: After the host camera recognizes that the work ticket and the operator are in compliance, it will transfer the violation information detected during the construction process, such as the crane without anti-falling device and the personnel not wearing safety helmets, to the on-site smart safety helmet, the background monitoring platform and the mobile phone. The background monitoring platform automatically generates the documents required for project construction management, such as construction plans, budgets, quality plans, etc., imports the work ticket and pushes it to the on-site host. It has the functions of process image storage, error correction records, and automatic generation of work logs.

6. The AI project construction safety auxiliary management system based on edge computing according to claim 5 is characterized by: The database of the background monitoring platform and the mobile phone terminal stores work tickets, images and records, uses cloud services to store data processed by edge computing, and automatically generates work logs through natural language processing, or fills in templates with data such as time, location, and work content.

7. An edge computing-based AI project construction safety auxiliary management system according to any one of claims 1 to 6, characterized in that: When the on-site host detects a violation, it will issue an audible and visual warning through the speaker or vibration module of the smart helmet within 30ms, reminding workers and on-site managers to correct the violation in time, block the illegal operation process, record the violation and blocked operation, and facilitate subsequent analysis and processing.

8. An edge computing-based AI project construction safety application scenario, characterized by: The AI project construction safety auxiliary management system described in any one of claims 1-7 is applied to a construction operation scenario. In this scenario, the on-site host monitors the operation site in real time through a camera. When violations such as "no anti-fall device" or "no safety helmet" are detected, the violation information is immediately pushed to the smart safety helmet, the background monitoring platform and the mobile phone. The management personnel can view the situation of the crane operation site in real time through the background monitoring platform or the mobile phone, and remotely monitor and direct the operation process. When violations or safety hazards are discovered, the management personnel can issue instructions in a timely manner through the background monitoring platform and the mobile phone to guide the on-site personnel to correct and deal with them.

9. An AI project construction safety application scenario based on edge computing, characterized by: The AI project construction safety auxiliary management system described in any one of claims 1-7 is applied to high-altitude working scenarios. In high-altitude working scenarios, the smart safety helmet integrates multiple sensors to monitor the physical condition of personnel in real time. When it is detected that a person is unwell or engages in dangerous behavior, the on-site personnel and management personnel are immediately reminded through sound and light alarms. The millimeter wave radar locates the position of the personnel in real time. When a person engages in dangerous behaviors such as falling or taking off a hat in a high-altitude working area, the system automatically triggers sound and light alarms, and notifies relevant personnel through the background monitoring platform and mobile phones to take rescue measures in time. The positioning and alarm functions can quickly determine the location of dangerous personnel and promptly notify rescue personnel to deal with them.

Images