3D printing equipment safety protection system

Abstract

This application relates to a safety protection system for 3D printing equipment, comprising a global perception layer, an edge decision-making layer, a control execution layer, and a human-machine interaction layer. The global perception layer includes at least one main image detection module and at least one secondary image detection module. The main image detection module is installed at a preset position at the equipment's inlet and outlet, and the secondary image detection module is installed at a preset position on the side or top of the equipment. The main and secondary image detection modules are stitched together using a calibration plate to construct a three-dimensional safety protection network for the equipment. The control execution layer includes a coprocessor, and the human-machine interaction layer integrates a warning system for displaying dynamic hazard boundaries. This solution addresses the problems of existing safety protection systems, such as incomplete spatial coverage, insufficient perception and prediction capabilities for complex dangerous behaviors, poor coupling between control execution and equipment status, and a lack of versatility and scalability.

Description

Technical Field

[0001] This utility model relates to the field of printing system technology, and in particular to a safety protection system for 3D printing equipment. Background Technology

[0002] Currently, the security of industrial printing equipment mainly relies on traditional monitoring and protection methods. In terms of monitoring, a single-point monitoring model is often used, monitoring a localized area of ​​the equipment through a single camera or sensor. This is insufficient to cover multiple hazardous points such as equipment entrances and exits, side gaps, and operating areas of critical components, creating numerous blind spots and failing to address complex scenarios involving multiple interconnected hazardous areas. At the perception and decision-making level, existing systems mostly employ simple sensor triggering mechanisms, only able to respond to obvious physical intrusions. They cannot recognize complex human behaviors (such as limbs moving towards hazardous areas or rapid movement), and are even less able to predict potential dangerous trajectories, resulting in a reactive security response.

[0003] Meanwhile, the existing safety systems have poor coupling between control execution and equipment operating status. They often take only single measures such as emergency stop when danger is detected, which can easily cause production interruptions and affect production efficiency. In addition, different types of industrial printing equipment vary greatly in structure, size, and distribution of hazardous areas. Existing safety systems lack universality and scalability, making it difficult to flexibly adapt to different equipment, which increases the safety protection costs and management difficulty for enterprises. Utility Model Content

[0004] Therefore, it is necessary to provide a 3D printing equipment safety protection system to address the problems of existing safety protection systems, such as incomplete spatial coverage, insufficient ability to perceive and predict complex dangerous behaviors, poor coupling between control execution and equipment status, and lack of versatility and scalability.

[0005] To solve the above problems, the present invention adopts the following technical solution:

[0006] This utility model discloses a safety protection system for 3D printing equipment, characterized by comprising a global perception layer, an edge decision layer, a control execution layer, and a human-machine interaction layer. The global perception layer includes at least one main image detection module and at least one secondary image detection module. The main image detection module is installed at a preset position at the equipment entrance / exit to cover the entrance / exit area and related equipment component areas. The secondary image detection module is installed at a preset position on the side or top of the equipment to cover equipment gaps and blind spots on the side. The main and secondary image detection modules are stitched together using a calibration board to construct a three-dimensional safety protection network for the equipment, and time alignment is achieved through a clock synchronization protocol. The edge decision layer is equipped with an edge computing unit that runs a fusion algorithm for target detection, cross-camera tracking, and trajectory prediction. The control execution layer includes a coprocessor that supports equipment emergency stop, component dynamic locking, and adaptive control functions for related equipment doors. The human-machine interaction layer integrates a warning system to display dynamic hazard boundaries.

[0007] In one embodiment, the global perception layer includes a main image detection module and two secondary image detection modules. The main image detection module is installed at a preset position at the inlet and outlet of the sand mold 3D printing equipment to cover the inlet and outlet of the box and the roller shutter door area. The two secondary image detection modules are installed on the top of both sides of the equipment to cover the gap of the front flip plate and the blind area of ​​the side wings of the equipment.

[0008] In one embodiment, the clock synchronization protocol is the IEEE 1588 clock synchronization protocol.

[0009] In one embodiment, the edge computing unit is an NVIDIA Jetson edge computing unit.

[0010] In one embodiment, the main image detection module and the sub-image detection module of the global perception layer construct a dynamic three-dimensional point cloud map of the device's surroundings using a stereo matching algorithm.

[0011] In one embodiment, the control execution layer can realize multi-level linkage response. When it is detected that a person's limbs are moving towards a dangerous area and the movement speed reaches a preset value, a pre-alarm mode is triggered. In the first-level response (potential risk), the warning system delineates a yellow warning zone and the sound and light alarm sounds briefly. In the second-level response (intrusion into the execution zone), if the equipment is running, the emergency stop module cuts off the power of the dangerous source and triggers mechanical self-locking. If the equipment is stationary, a pulse alarm is issued and a flashing red light illuminates.

[0012] In one embodiment, the warning system is an AR warning system, which includes a laser projector for projecting dynamic hazard boundaries onto the ground.

[0013] In one of the embodiments, the system further has an autonomous recovery mechanism. After the personnel leave, the system automatically scans and confirms the safe area, and sends a recovery instruction to the MES system through the OPCUA protocol.

[0014] The technical solution adopted by the utility model can achieve the following beneficial effects:

[0015] In the 3D printing equipment safety protection system disclosed in the embodiment of the utility model, through the collaborative work of the multi-image detection modules in the global perception layer and in combination with the fusion algorithm in the edge decision layer, comprehensive and accurate monitoring of the periphery of the equipment and risk prediction are achieved, breaking through the limitations of traditional safety protection in terms of spatial coverage and perception ability, and forming a complete safety protection closed loop from monitoring to decision-making and then to execution. The system can make multi-level linkage responses according to different dangerous situations, can not only warn of potential risks in advance, but also quickly take control measures when a danger occurs, effectively ensuring the safety of personnel and equipment during the operation of the 3D printing equipment and reducing the probability of safety accidents. At the same time, its modular structure design makes it have good adaptability and scalability, and can be applied to a variety of 3D printing equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic structural diagram of the 3D printing equipment safety protection system disclosed in the embodiment of the utility model.

[0017] Description of the reference numerals:

[0018] 100 - 3D printing equipment, 110 - rolling shutter door, 200 - global perception layer DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] For the convenience of understanding the utility model, the utility model will be described more comprehensively below with reference to the relevant drawings. The preferred embodiments of the utility model are shown in the drawings. However, the utility model can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided so that the disclosure of the utility model can be understood more thoroughly and comprehensively.

[0020] It should be noted that when an element is referred to as being "disposed on" another element, it can be directly on the other element or there can also be an intermediate element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. The terms "vertical", "horizontal", "left", "right", "top", "bottom", "bottom end", "top end" and similar expressions used herein are only for the purpose of illustration and do not represent the only embodiments.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0022] like Figure 1 As shown in the figure, this utility model embodiment discloses a 3D printing equipment safety protection system, which includes a global perception layer 200, an edge decision layer, a control execution layer, and a human-computer interaction layer.

[0023] The global perception layer 200 includes at least one main image detection module and at least one secondary image detection module. The main image detection module is installed at a preset position at the entrance and exit of the equipment to cover the entrance and exit area and related equipment component areas. The secondary image detection module is installed at a preset position on the side or top of the equipment to cover equipment gaps and blind spots on the side of the equipment. The main image detection module and the secondary image detection module achieve field-of-view stitching through a calibration board to construct a three-dimensional safety protection network for the equipment and achieve time alignment through a clock synchronization protocol.

[0024] The edge decision layer is equipped with an edge computing unit that runs fusion algorithms for target detection, cross-camera tracking, and trajectory prediction. The control execution layer includes a coprocessor that supports emergency stop of equipment, dynamic locking of components, and adaptive control of related equipment doors. The human-machine interaction layer integrates an alert system to display dynamic hazard boundaries.

[0025] When the safety protection system of this 3D printing equipment is working, the main image detection module and the secondary image detection module of the global perception layer 200 first come into play. The main image detection module monitors the entry and exit areas and related equipment component areas at preset positions at the equipment entrance and exit, while the secondary image detection module covers the gaps between the equipment and the blind spots on the sides of the equipment at preset positions on the side or top of the equipment. The two modules are stitched together through a calibration plate to form a three-dimensional safety protection network, and time alignment is ensured by a clock synchronization protocol, capturing the surrounding situation of the equipment from all directions.

[0026] Next, the edge computing unit of the edge decision layer processes the information acquired by the global perception layer 200, runs a fusion algorithm of target detection, cross-camera tracking and trajectory prediction, identifies targets such as people and tracks their trajectories, and predicts possible dangerous behaviors.

[0027] When a potential danger is detected, the coprocessor in the control execution layer starts the corresponding control function according to the judgment of the edge decision layer. If the pre-alarm mode is triggered, the warning system in the human-computer interaction layer will display a dynamic danger boundary; if a situation such as intrusion into the execution area occurs, the coprocessor will perform operations such as emergency stop of the device, dynamic locking of components, or adaptive control of the relevant device door body, to achieve multi-level linkage response.

[0028] After the personnel leave, the system starts the autonomous recovery mechanism, automatically scans and confirms the safe area, and then sends a recovery instruction to the external system through relevant protocols to make the device return to the normal operation state.

[0029] As can be seen from the above content, in the 3D printing device safety protection system disclosed in the embodiments of the present utility model, through the collaborative work of the multi-image detection modules in the global perception layer 200, combined with the fusion algorithm in the edge decision layer, comprehensive and accurate monitoring and danger prediction of the periphery of the device are achieved, breaking through the limitations of traditional safety protection in spatial coverage and perception ability, and forming a complete safety protection closed-loop from monitoring to decision-making and then to execution. This system can make multi-level linkage responses according to different dangerous situations, can not only warn potential risks in advance, but also quickly take control measures when a danger occurs, effectively ensuring the safety of personnel and equipment during the operation of the 3D printing device 100, and reducing the probability of safety accidents. At the same time, its modular structure design makes it have good adaptability and scalability, and can be applied to a variety of 3D printing devices 100.

[0030] Furthermore, the global perception layer 200 includes a main image detection module and two sub-image detection modules. The main image detection module is installed at a preset position at the inlet and outlet of the sand mold 3D printing device 100, and is used to cover the inlet and outlet of the box and the rolling shutter door area 110. The two sub-image detection modules are installed at the top of both sides of the device, and are used to cover the gap of the front flap and the blind area of the device flank. This specific design of the number and installation position of the image detection modules can accurately cover the key dangerous areas of the sand mold 3D printing device 100, effectively eliminating the blind areas such as the inlet and outlet of the device, the box opening, the rolling shutter door, the gap of the front flap, and the flank where safety accidents are likely to occur, greatly improving the specificity and comprehensiveness of the system's exclusive protection for the sand mold 3D printing device 100, and making the safety monitoring more in line with the actual structure and danger distribution characteristics of the device.

[0031] Furthermore, the clock synchronization protocol is the IEEE1588 clock synchronization protocol. The IEEE1588 clock synchronization protocol has high-precision time synchronization ability, can ensure the time consistency of the information collected by the main and sub-image detection modules, avoid problems such as target tracking confusion and inaccurate trajectory prediction caused by time deviation, provides an accurate time reference for the edge decision layer to perform fusion algorithm processing, and improves the accuracy and reliability of the data processing and decision-making of the entire system.

[0032] Furthermore, the edge computing unit is an NVIDIA Jetson edge computing unit. The NVIDIA Jetson edge computing unit possesses powerful parallel computing capabilities and efficient AI processing performance, enabling it to quickly and accurately run fusion algorithms such as object detection, cross-camera tracking, and trajectory prediction. This meets the system's real-time processing requirements, ensuring that the edge decision layer can promptly make judgments on information transmitted from the global perception layer 200, laying a solid foundation for the rapid response of the subsequent control execution layer and improving the overall operating efficiency of the system.

[0033] Furthermore, the main image detection module and the secondary image detection module of the global perception layer 200 construct a dynamic 3D point cloud map around the equipment using a stereo matching algorithm. The stereo matching algorithm, combined with the dynamic 3D point cloud map constructed by multiple image detection modules, can transform planar image information into three-dimensional spatial information, more intuitively and accurately reflecting the environment and personnel positional relationships around the equipment. This enables the edge decision layer to more accurately determine the relative positions of personnel and equipment in hazardous areas, improving the accuracy of dangerous behavior prediction and enhancing the system's perception and analysis capabilities in complex scenarios.

[0034] Furthermore, the control execution layer can achieve multi-level linkage response. When it detects that a person's limbs are moving towards a dangerous area and the movement speed reaches a preset value, a pre-alarm mode is triggered. In the first-level response (potential risk), the warning system delineates a yellow warning zone and triggers a short audible and visual alarm. In the second-level response (intrusion into the execution area), if the equipment is running, the emergency stop module cuts off the power to the dangerous source and triggers a mechanical self-locking mechanism; if the equipment is stationary, a pulse alarm is issued and a flashing red light illuminates. This multi-level linkage response mechanism can take corresponding protective measures according to different levels of danger. It not only promptly alerts personnel during the potential risk stage to avoid unnecessary production interruptions, but also quickly takes strong measures to prevent accidents when danger occurs. This achieves a balance between the flexibility and effectiveness of safety protection, minimizing the losses caused by safety accidents.

[0035] Furthermore, the warning system is an AR warning system, which includes a laser projector used to project dynamic hazard boundaries onto the ground. By projecting dynamic hazard boundaries onto the ground, the AR warning system can visually and conspicuously display dangerous areas to people. Compared to traditional warning methods, it is more likely to attract people's attention, allowing them to clearly understand the dangerous situation in their environment and thus avoid risks in a timely manner, improving the effectiveness and intuitiveness of the warning.

[0036] Furthermore, the system also features an autonomous recovery mechanism. When personnel leave, the system automatically scans and confirms the safe area, then sends a recovery command to the MES system via the OPCUA protocol. This autonomous recovery mechanism reduces manual intervention and, while ensuring safety, can quickly restore equipment from a shutdown state to normal operation, shortening production interruption time caused by safety precautions and improving production efficiency. Simultaneously, through the OPCUA protocol's integration with the MES system, it achieves collaboration between the system and the factory's production management system, enhancing the overall automation and intelligence level of the factory.

[0037] The embodiments described above are merely illustrative of several implementations of this utility model, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the utility model patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this utility model, and these all fall within the protection scope of this utility model. Therefore, the protection scope of this utility model patent should be determined by the appended claims.

Claims

1. A safety protection system for 3D printing equipment, characterized in that, It includes a global perception layer, an edge decision layer, a control execution layer, and a human-computer interaction layer. The global perception layer includes at least one main image detection module and at least one secondary image detection module. The main image detection module is installed at a preset position at the equipment entrance and exit to cover the entrance and exit area and related equipment component areas. The secondary image detection module is installed at a preset position on the side or top of the equipment to cover equipment gaps and blind spots on the side of the equipment. The main image detection module and the secondary image detection module achieve field-of-view stitching through a calibration board to construct a three-dimensional safety protection network for the equipment and achieve time alignment through a clock synchronization protocol. The edge decision layer is equipped with an edge computing unit that runs a fusion algorithm for target detection, cross-camera tracking, and trajectory prediction. The control execution layer includes a coprocessor that supports functions such as device emergency stop, component dynamic locking, and adaptive control of related device doors. The human-machine interaction layer integrates a warning system to display dynamic danger boundaries.

2. The 3D printing equipment safety protection system according to claim 1, characterized in that, The global perception layer includes a main image detection module and two secondary image detection modules. The main image detection module is installed at the preset positions of the inlet and outlet of the sand mold 3D printing equipment to cover the inlet and outlet of the box and the roller shutter door area. The two secondary image detection modules are installed on the top of both sides of the equipment to cover the gap of the front flip plate and the blind area of ​​the side wings of the equipment.

3. The 3D printing equipment safety protection system according to claim 1, characterized in that, The clock synchronization protocol is the IEEE 1588 clock synchronization protocol.

4. The 3D printing equipment safety protection system according to claim 1, characterized in that, The edge computing unit is an NVIDIA Jetson edge computing unit.

5. The 3D printing equipment safety protection system according to claim 1, characterized in that, The main image detection module and the sub-image detection module of the global perception layer construct a dynamic three-dimensional point cloud map around the device through a stereo matching algorithm.

6. The 3D printing equipment safety protection system according to claim 1, characterized in that, The control execution layer can achieve multi-level linkage response. When it detects that a person's limbs are moving towards a dangerous area and the movement speed reaches a preset value, a pre-alarm mode is triggered. In the first-level response, the warning system delineates a yellow warning zone and the sound and light alarm sounds briefly. In the second-level response, if the equipment is running, the emergency stop module cuts off the power to the dangerous source and triggers mechanical self-locking. If the equipment is stationary, a pulse alarm is issued and a flashing red light illuminates.

7. The 3D printing equipment safety protection system according to claim 1, characterized in that, The warning system is an AR warning system, which includes a laser projector for projecting dynamic danger boundaries onto the ground.

8. The 3D printing equipment safety protection system according to claim 1, characterized in that, The system also has an autonomous recovery mechanism. When personnel leave, the system automatically scans and confirms the safe area, and sends a recovery command to the MES system via the OPCUA protocol.

Images