PCB full-process AGV intelligent transfer system

By using image acquisition and deep learning algorithms to monitor the position of staff in the AGV intelligent transport system and sending alarm information to the AGV system, the problem of safety hazards between AGV and personnel is solved, high-precision safety monitoring and collaborative work are achieved, and the Safe and stable operation of the factory area.

CN119091414APending Publication Date: 2024-12-06HUAIAN TECHUANG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411014052.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In high-frequency working environments, there are still safety hazards in the safety and coordination of AGVs with personnel or other equipment, especially when the workload is large and there are many auxiliary workers, safety accidents are prone to occur.

Method used

A full-process AGV intelligent transport system for PCB is designed, including image acquisition module, central processing module, alarm module and communication interface. Through image processing technology and deep learning algorithms, the distance between them and the AGV working area is calculated. Trigger an alarm and send an alarm message to the AGV system to ensure a safe distance.

Benefits of technology

It realizes high-precision safety monitoring and alarms to prevent misjudgment or missed judgments, ensures the safe distance between the AGV and the staff, and improves the safe and stable operation of the factory.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091414A_ABST
    Figure CN119091414A_ABST
Patent Text Reader

Abstract

The invention discloses a PCB (Printed Circuit Board) full-process AGV (Automatic Guided Vehicle) intelligent transfer system, which relates to the technical field of AGV intelligent transfer, and is characterized in that an image acquisition module, a central processing module and an alarm module are arranged to monitor the conditions of workers in the advancing route of the AGV intelligent transfer system in a factory area; the image acquisition module is used for intermittently capturing images of a factory area, the map division unit is used for carrying out digital and grid division on the images, accurate basic data is provided for intelligent navigation and safe operation of the AGV, then the key point detection unit is used for carrying out target detection on workers in the images by adopting a deep learning algorithm, and the working efficiency is improved. And the key point coordinates of the staff are marked in real time, and then the received data are processed through the data processing unit by using a mathematical calculation library, so that safety accidents caused by misjudgment or missed judgment can be effectively prevented.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of AGV intelligent transportation, and more specifically, to a PCB full-process AGV intelligent transportation system. Background Art

[0002] PCB (Printed Circuit Board) is a printed circuit board, also known as a printed circuit board. It is an important electronic component, a support for electronic components, and a carrier for the electrical connection of electronic components. Because it is made using electronic printing technology, it is called a "printed" circuit board. PCB appears in almost every electronic device, and its main function is to provide electrical connections between the various parts on it. As electronic devices become more and more complex, more and more parts are required, and the lines and parts on PCBs are becoming more and more dense. In order to reduce production costs, improve production efficiency and reduce manual errors, the design and production of PCBs are increasingly carried out with the help of computer-aided design (CAD) and computer-aided manufacturing (CAM). In this way, not only the quality of design and production is improved, but also the production cycle is shortened and production efficiency is improved.

[0003] AGV, the full name of which is Automated Guided Vehicle, means "automatic guided transport vehicle" or "automatic guided vehicle". This is a transport vehicle equipped with electromagnetic or optical automatic guidance devices, which can travel along the specified guidance path and has safety protection and various transfer functions. AGV does not require a driver in industrial applications and uses rechargeable batteries as its power source. Generally, its travel path and behavior can be controlled by a computer, or its travel path can be established using electromagnetic tracks. The electromagnetic tracks are attached to the floor, and the unmanned transport vehicle relies on the information brought by the electromagnetic tracks to move and move. AGV can only play a real role in the automatic guided vehicle system (AGVS) formed by the automatic guidance system, automatic loading and unloading system, communication system, safety system and management system according to the requirements of material handling automation, flexibility and punctuality. The research and development of AGV integrates artificial intelligence, information processing, and image processing, involving multiple disciplines such as computers, automatic control, information communication, mechanical design and electronic technology, and has become one of the hot spots in logistics automation research.

[0004] Although the AGV intelligent transfer system has greatly facilitated the in-factory transportation requirements of many industries, it also has certain defects that need to be addressed during use. For example, although AGVs are usually equipped with safety sensors and emergency stop devices, in high-frequency working environments, the safety and coordination with personnel or other equipment still need to be paid attention to. When the workload is heavy and there are many auxiliary staff, the working areas of the staff and the AGV intersect, which is prone to safety hazards and losses.

[0005] Therefore, in order to solve the above technical problems, this application proposes a PCB full-process AGV intelligent transportation system. Summary of the invention

[0006] In view of the deficiencies in the prior art, the object of the present invention is to provide a full-process AGV intelligent transportation system for PCB.

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a full-process AGV intelligent transport system for PCB, including an AGV intelligent transport system, which is used to transport PCBs in the whole process within the factory area, and also includes:

[0008] An image acquisition module, which is used to intermittently acquire images of the entire factory area;

[0009] The central processing module receives the images of the factory area collected by the image acquisition module through an interface. The central processing module includes a map division unit, a key point detection unit and a data processing unit. The map division unit is used to digitize the factory area images collected by the image acquisition unit, and divide the obtained images into closely arranged small grids through image processing technology. Each grid represents a certain area range. According to the working route of the AGV, all the grids involved are marked as AGV working intervals, and the remaining grids are marked as safety intervals.

[0010] The key point detection unit is used to establish a coordinate system on the obtained image and mark the coordinates of the boundary line between the AGV working area and the safety area. The key point detection unit also performs target detection on the staff in the image through a deep learning algorithm, identifies the position of the staff, marks key points on the staff in the image, and marks the coordinates of the key points according to the coordinate system;

[0011] The data processing unit calculates the width of the AGV working area and the distance between the key point of the staff and the two boundaries of the AGV working area according to the coordinates of the dividing line between the AGV working area and the safety area and the coordinates of the key point of the staff, and compares the larger distance value with the width value of the AGV working area to find out whether the distance value is greater than the width value of the AGV working area. If so, it means that the key point of the staff in the image is outside the AGV working area. If not, it means that the key point of the staff in the image is inside the AGV working area.

[0012] The alarm module is connected to the central processing module through an interface, and is used to trigger an alarm when the distance value calculated in the data processing unit is less than the width value of the AGV working interval, so as to inform the staff to leave the AGV working interval.

[0013] The image processing technology used by the map division unit includes but is not limited to OpenCV and map digitization technology, as well as image denoising algorithm, grayscale conversion algorithm and edge enhancement algorithm through open source visual library to process the image.

[0014] It should be noted that the key point detection unit adopts a deep learning framework, including but not limited to TensorFlow and PyTorch, combined with a target detection model and a human posture estimation model, to monitor the position of the staff in the image in real time and mark the key points on the staff in the image.

[0015] The data processing unit receives data from the map division unit and the key point detection unit, and calculates the data using a mathematical calculation library, which includes but is not limited to NumPy and SciPy.

[0016] It is worth noting that the alarm module includes but is not limited to devices such as sound alarms, LED indicator lights and wireless signal transmitters, which are used to issue sound alarms, light up indicator lights and send wireless alarm signals to staff.

[0017] Preferably, the PCB full-process AGV intelligent transfer system also includes a communication interface, which is connected to the AGV intelligent transfer system and the alarm module through a wireless network. The communication interface is used to send alarm information to the AGV intelligent transfer system when the alarm module triggers an alarm, so that the AGV intelligent transfer system can take corresponding measures in advance and realize automatic identification of AGVs across floors.

[0018] Compared with the prior art, the present invention has the following beneficial effects:

[0019] 1. In the present invention, the image acquisition module intermittently captures the image of the factory area, and the image is digitized and gridded in combination with the map division unit, providing accurate basic data for the intelligent navigation and safe operation of the AGV. Then, the key point detection unit uses a deep learning algorithm to detect the target of the staff in the image, and marks the key point coordinates of the staff in real time. Then, the data processing unit uses a mathematical calculation library to process the received data, and calculates the distance between the key point of the staff and the boundary of the AGV working area, and compares it with the width of the AGV working area to accurately determine whether the staff has entered the AGV working area. This distance-based judgment method has high accuracy and reliability, and can effectively prevent safety accidents caused by misjudgment or missed judgment.

[0020] 2. In the present invention, the present invention also realizes seamless connection with the AGV intelligent transport system through the communication interface. When the alarm module triggers the alarm, the system can send the alarm information to the AGV in time, so that the AGV can take corresponding measures in advance, such as slowing down, stopping or changing the driving route, etc., to ensure the safe distance between the AGV and the staff. This function makes the system not only have powerful monitoring and alarm capabilities, but also can realize the coordinated work with the AGV to jointly maintain the safe and stable operation of the factory area. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0022] Figure 1 This is a system block diagram of a PCB full-process AGV intelligent transportation system of the present invention. DETAILED DESCRIPTION

[0023] As shown in the system block diagram of the present invention, the present invention provides a PCB full-process AGV intelligent transportation system, including an AGV intelligent transportation system, which is used to transport PCBs in the factory area throughout the entire process, and also includes:

[0024] The image acquisition module is used to intermittently collect images of the entire factory area. The image acquisition module uses a high-definition camera array and is distributed in key areas of the factory area, such as the starting point, intersection, and end point of the AGV work path. These cameras can automatically capture high-definition factory images according to preset time intervals or event triggers, such as AGV startup, personnel entering the detection area, etc. The image data is transmitted to the central processing module via wired or wireless methods, and the image acquisition module intermittently collects factory images to ensure that when the AGV is running, it can confirm in real time whether any staff members have entered the AGV working area.

[0025] The central processing module receives the images of the factory area collected by the image acquisition module through an interface. The central processing module includes a map division unit, a key point detection unit and a data processing unit. The map division unit is used to digitize the factory area images collected by the image acquisition unit, and divide the obtained images into closely arranged small grids through image processing technology. Each grid represents a certain area range. According to the working route of the AGV, all the grids involved are marked as AGV working intervals, and the remaining grids are marked as safety intervals.

[0026] It should be noted that the image processing technology used by the map division unit includes but is not limited to OpenCV and map digitization technology, as well as image denoising algorithm, grayscale conversion algorithm and edge enhancement algorithm through open source visual library to process the image;

[0027] The key point detection unit is used to establish a coordinate system on the obtained image and mark the coordinates of the boundary between the AGV working area and the safety area. The key point detection unit also performs target detection on the staff in the image through a deep learning algorithm, identifies the position of the staff and marks key points on the staff in the image, and marks the coordinates of the key points according to the coordinate system. The key points can be selected from the more obvious positions of the staff in the image, such as the head position;

[0028] The key point detection unit uses a deep learning framework, including but not limited to TensorFlow and PyTorch, combined with a target detection model and a human posture estimation model to monitor the position of the staff in the image in real time and mark the key points on the staff in the image.

[0029] The data processing unit calculates the width of the AGV working area and the distance between the key point of the staff and the two boundaries of the AGV working area according to the coordinates of the dividing line between the AGV working area and the safety area and the coordinates of the key point of the staff, and compares the larger distance value with the width value of the AGV working area to find out whether the distance value is greater than the width value of the AGV working area. If so, it means that the key point of the staff in the image is outside the AGV working area. If not, it means that the key point of the staff in the image is inside the AGV working area.

[0030] It is worth noting that the data processing unit receives data from the map division unit and the key point detection unit, and uses a mathematical calculation library to calculate the data, and the data calculation library includes but is not limited to NumPy and Sc iPy;

[0031] An alarm module is connected to the central processing module through an interface, and is used to trigger an alarm when the distance value calculated in the data processing unit is less than the width value of the AGV working area, and inform the staff to leave the AGV working area. The alarm module can be a bracelet issued to the staff, or a communication device that can be carried with the voice, so as to facilitate the staff to leave as soon as possible when they enter the working range of the AGV;

[0032] The alarm module includes, but is not limited to, devices such as sound alarms, LED indicators, and wireless signal transmitters, which are used to issue sound alarms, light up indicators, and send wireless alarm signals to staff;

[0033] It is worth noting that a PCB full-process AGV intelligent transport system also includes a communication interface, which is connected to the AGV intelligent transport system and the alarm module through a wireless network. The communication interface is used to send alarm information to the AGV intelligent transport system when the alarm module triggers an alarm, so that the AGV intelligent transport system can take corresponding measures in advance and realize automatic recognition of AGV across floors;

[0034] It should be noted that when the AGV is far away and the staff is in the AGV working area, the alarm module will sound the alarm too early, and it will be too early for the staff to evacuate, which will delay the work. Therefore, each image acquisition module is numbered according to the direction of the AGV, and each image acquisition module is marked in sequence with numbers 1, 2, 3, 4, 5, etc. When the staff in the image captured by one of the numbered image acquisition modules is in the AGV working area, the AGV intelligent transfer system is used to find out which numbered image acquisition module captured the image of the AGV at this time, and then the numbers of the two image acquisition modules are subtracted. When the absolute value is greater than 2, the alarm module is not triggered. When the absolute value is less than or equal to 2, the alarm is triggered to inform the staff to evacuate the AGV working area in time, thereby effectively preventing the staff from giving way to the AGV too early and delaying work.

[0035] The specific workflow of this solution is as follows: The PCB full-process AGV intelligent transport system first uses the image acquisition module to collect factory images, and will be transmitted to the central processing module for further processing. In the central processing module, the map division unit first receives the image from the image acquisition module, and uses image processing technology (such as OpenCV and map digitization technology) to denoise, grayscale convert and edge enhance the image. Then, through the image processing algorithm, the processed image is divided into closely arranged small grids, each grid represents a specific area range. According to the pre-set AGV working route, the map division unit marks all the grids involved as AGV working intervals, and the remaining grids are marked as safe intervals. At the same time, the key point detection unit establishes a coordinate system on the image and marks the boundary coordinates of the AGV working interval and the safe interval. Using deep learning algorithms (such as target detection models and human posture estimation models under the TensorFlow or PyTorch framework), the key point detection unit performs target detection on the staff in the image, identifies their positions, and marks key points on the staff (such as head, shoulders, etc.). The coordinates of these key points are also recorded in the coordinate system in real time. Then, the data processing unit starts to play a role. It receives data from the map division unit and the key point detection unit, and uses mathematical calculation libraries (such as NumPy and SciPy) to calculate the width of the AGV working area and the distance between the key points of the staff and the two boundaries of the AGV working area. By comparing these distances with the width of the AGV working area, the data processing unit can accurately determine whether the staff has entered the AGV working area. If the distance is less than the width of the AGV working area), the alarm module will be triggered. The alarm module sends an alarm signal to the staff through devices such as sound alarms, LED indicators and wireless signal transmitters, reminding them to leave the AGV working area as soon as possible. At the same time, the communication interface sends the alarm information to the AGV intelligent transportation system through the wireless network. After receiving the alarm information, the AGV intelligent transportation system can take corresponding measures in advance, such as slowing down, stopping or changing the driving route, to ensure that a safe distance is maintained with the staff, and realize automatic identification and safe transportation across floors.

[0036] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any ordinary technician in the industry can smoothly implement the present invention as shown in the drawings and described above. However, any equivalent changes, modifications and evolutions made by technicians familiar with the profession without departing from the scope of the technical solution of the present invention using the technical content disclosed above are all equivalent embodiments of the present invention. At the same time, any equivalent changes, modifications and evolutions made to the above embodiments based on the essential technology of the present invention are still within the protection scope of the technical solution of the present invention.

Claims

1. A PCB full-process AGV intelligent transport system, including an AGV intelligent transport system, which is used to transport PCBs throughout the entire process within a factory, and is characterized by: Also includes: An image acquisition module, which is used to intermittently acquire images of the entire factory area; The central processing module receives the images of the factory area collected by the image acquisition module through an interface. The central processing module includes a map division unit, a key point detection unit and a data processing unit. The map division unit is used to digitize the factory area images collected by the image acquisition unit, and divide the obtained images into closely arranged small grids through image processing technology. Each grid represents a certain area range. According to the working route of the AGV, all the grids involved are marked as AGV working intervals, and the remaining grids are marked as safety intervals. The key point detection unit is used to establish a coordinate system on the obtained image and mark the coordinates of the boundary line between the AGV working area and the safety area. The key point detection unit also performs target detection on the staff in the image through a deep learning algorithm, identifies the position of the staff, marks key points on the staff in the image, and marks the coordinates of the key points according to the coordinate system; The data processing unit calculates the width of the AGV working area and the distance between the key point of the staff and the two boundaries of the AGV working area according to the coordinates of the dividing line between the AGV working area and the safety area and the coordinates of the key point of the staff, and compares the larger distance value with the width value of the AGV working area to find out whether the distance value is greater than the width value of the AGV working area. If so, it means that the key point of the staff in the image is outside the AGV working area. If not, it means that the key point of the staff in the image is inside the AGV working area. The alarm module is connected to the central processing module through an interface, and is used to trigger an alarm when the distance value calculated in the data processing unit is less than the width value of the AGV working interval, so as to inform the staff to leave the AGV working interval.

2. According to claim 1, a PCB full-process AGV intelligent transport system is characterized by: The image processing technology used by the map division unit includes but is not limited to OpenCV and map digitization technology, as well as image denoising algorithm, grayscale conversion algorithm and edge enhancement algorithm through open source visual library to process the image.

3. A PCB full-process AGV intelligent transport system according to claim 2, characterized in that: The key point detection unit adopts a deep learning framework, including but not limited to TensorFlow and PyTorch, combined with a target detection model and a human posture estimation model, to monitor the position of the staff in the image in real time and mark the key points on the staff in the image.

4. The PCB full-process AGV intelligent transport system according to claim 3 is characterized by: The data processing unit receives data from the map division unit and the key point detection unit, and calculates the data using a mathematical calculation library, which includes but is not limited to NumPy and SciPy.

5. The PCB full-process AGV intelligent transport system according to claim 4 is characterized by: The alarm module includes but is not limited to devices such as a sound alarm, an LED indicator light and a wireless signal transmitter, and is used to issue a sound alarm, light up an indicator light and send a wireless alarm signal to the staff.

6. The PCB full-process AGV intelligent transport system according to claim 5 is characterized by: The PCB full-process AGV intelligent transfer system also includes a communication interface, which is connected to the AGV intelligent transfer system and the alarm module through a wireless network. The communication interface is used to send alarm information to the AGV intelligent transfer system when the alarm module triggers an alarm, so that the AGV intelligent transfer system can take corresponding measures in advance and realize automatic identification of AGVs across floors.