Intelligent factory network architecture construction method based on multi-modal network

Abstract

The invention provides an intelligent factory network architecture construction method based on a multi-modal network. The method comprises the following steps: constructing a data center network, a security management network, an intelligent office park network, an intelligent vision network, an AGV park network, a factory network and an exit network; each network is connected through a core-level multi-mode network element; the core-level multi-mode network element adopts dual-computer deployment to ensure the reliability of a link, adopts an architecture of an FPGA (Field Programmable Gate Array) and a special exchange chip to realize nanosecond-level data forwarding, and solidifies industrial protocol analysis logic in the FPGA to improve the protocol processing efficiency; the access-level multi-mode network element, the convergence-level multi-mode network element and the core-level multi-mode network element support loading and unloading of a custom protocol and are provided with unified control interfaces. The method is applied to intelligent factories and can support continuously evolved complex industrial services.

Description

Technical Field

[0001] The present invention relates to the field of intelligent factories, and particularly to a method for constructing an intelligent factory network architecture based on a multimodal network. Background Art

[0002] The network, as an infrastructure in the factory, is of great significance to the construction of an intelligent factory.

[0003] Currently, to adapt to various types of services in the intelligent factory while ensuring network security, there are multiple private networks in the intelligent factory. For example, to achieve remote control of industrial equipment, a device private network is established, which is not interconnected with other networks. To build an intelligent factory office network, network services provided by operators are used.

[0004] The existing methods have the following defects: currently, the factory networks are like chimneys standing separately, and the network structure is complex. With the continuous diversification of intelligent factory services, the current network structure cannot adapt to the continuously evolving services. Summary of the Invention

[0005] The purpose of the present invention is to use multimodal network technology to propose a method for constructing an intelligent factory network architecture based on a multimodal network, so as to solve the problems of complex, rigid network structure and inability to adapt to the continuously evolving complex industrial services in the existing technology.

[0006] The technical solution adopted by the present invention is as follows:

[0007] To achieve the above purpose, the present invention provides a method for constructing an intelligent factory network architecture based on a multimodal network, and the method includes:

[0008] Construct an intelligent factory network architecture including a data center network, a security management network, a smart office park network, an AGV park network, an intelligent vision network, a factory network, and an egress network; wherein:

[0009] Construct a data center network, including building business servers, a business storage cluster, a factory database, and a smart factory platform; construct a security management network, including constructing a situation awareness subsystem, an anti-virus subsystem, an operation and maintenance audit subsystem, a database subsystem, and a cloud management platform; construct a smart office park network, including constructing various office terminals, wireless access points, and Internet of Things terminals; construct terminals in the AGV park network, including various AGV vehicles accessing the intelligent factory; construct an intelligent vision network, mainly used to carry intelligent vision quality inspection services on the production line, and the network terminals mainly include cameras located at the production line positions; construct a factory network, including constructing access-level multimodal network elements and aggregation-level multimodal network elements for achieving sub-second fault convergence; construct an egress network, including constructing an internal firewall, a security gateway, switches, a load balancer, an anti-DDoS server, and an external firewall;

[0010] Each network is connected by a core-level multimodal network element; the core-level multimodal network element is deployed in a dual-machine manner to ensure reliable links. It adopts an FPGA + dedicated switching chip architecture to achieve nanosecond-level data forwarding, and the industrial protocol parsing logic is solidified in the FPGA to improve the protocol processing efficiency; the access-level multimodal network element, aggregation-level multimodal network element, and core-level multimodal network element all support the loading and unloading of custom protocols and have a unified control interface.

[0011] Further, in the data center network, the business storage cluster is used to store documents and materials related to the intelligent factory business, and is connected to the business server, factory database, and intelligent factory platform through an optical fiber switch; the business server, factory database, and intelligent factory platform are connected to the core-level multimodal network element through the aggregation-level multimodal network element and access-level multimodal network element; the aggregation-level multimodal network element and access-level multimodal network element are respectively configured with load balancing, north-south firewalls, and east-west firewalls.

[0012] Further, the data center network and intelligent office park network support addressing based on IPv4, IPv6, SRv6 protocols, and content naming identifiers to achieve a decentralized content distribution function; when a terminal in the intelligent office park network requests file content from the data center, the request is addressed by name on the multimodal network element. If the multimodal network element already stores the content corresponding to the name, the request does not need to reach the data center, and the multimodal network element directly replies to the requesting terminal, thereby improving the transmission efficiency.

[0013] Further, in the security management network, each subsystem is connected to the core-level multimodal network element through the aggregation-level multimodal network element and north-south firewalls; the aggregation-level multimodal network element and access-level multimodal network element adopt a leaf-spine network structure, are both deployed in a dual-machine manner, and use cross-device link aggregation technology to ensure service redundancy; the north-south firewalls are deployed in a primary-backup mode to ensure service redundancy and are used for policy control of network access inside and outside the region; the policy deployment method is: the outside of the firewall is a non-secure area, and the inside is a secure area; unauthorized addresses are prohibited from accessing the secure area inside the firewall, and authorized addresses are allowed to access the secure area inside the firewall.

[0014] Further, in the intelligent office park network, each device accesses the access-level multimodal network element through wired access or through a wireless access AP. The access-level multimodal network element accesses the core-level multimodal network element through the aggregation-level multimodal network element and north-south firewalls; the access-level multimodal network element and aggregation-level multimodal network element adopt a leaf-spine network architecture, and the aggregation-level multimodal network element is deployed in a dual-machine manner to ensure service redundancy; the intelligent office park network is used to carry the office business of intelligent factory employees, transmit design data through the network, and realize collaborative modification and improvement of off-site designers.

[0015] Furthermore, in the AGV campus network, the AGV vehicle accesses the access-level multimodal network element through an AP, and then is connected to the core-level multimodal network element through the access-level multimodal network element, the aggregation-level multimodal network element, and a firewall. The firewall is deployed in a primary / backup mode; the AGV vehicle is equipped with various sensors for collecting various data of on-site videos, voices, and pictures; the data collected by the AGV vehicle is monitored and analyzed in real time through the intelligent office campus network. When a danger is detected, the vehicles / pedestrians that need to be urgently evacuated from the accident site are called, the maintenance vehicles around the accident area are called, and a warning is issued to the corresponding area; the control center sends the alarm information and early warning information to the corresponding dangerous areas through the network; the geographical identification network mode is transmitted through this network to complete the point-to-point, point-to-multipoint, point-to-any point within the area, and point-to-area transmission methods addressed by geographical location, supporting communication service scenarios such as vehicle-to-vehicle and vehicle-to-AP.

[0016] Furthermore, in the intelligent vision network, the camera is connected to the core-level multimodal network element through the access-level multimodal network element, the aggregation-level multimodal network element, and a firewall; the product photos taken by the camera upload the product quality inspection data to the data center network through the core-level multimodal network element; afterwards, the intelligent office campus network requests the corresponding data from the data center as needed.

[0017] To achieve the above object, the present invention also provides an apparatus for constructing an intelligent factory network architecture based on a multimodal network, including one or more processors for implementing the above method for constructing an intelligent factory network architecture based on a multimodal network.

[0018] To achieve the above object, the present invention also provides an electronic device including a memory and a processor, and the memory is coupled to the processor; wherein, the memory is used for storing program data, and the processor is used for executing the program data to implement the above method for constructing an intelligent factory network architecture based on a multimodal network.

[0019] To achieve the above object, the present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, it implements the above method for constructing an intelligent factory network architecture based on a multimodal network.

[0020] The beneficial effects of the present invention are as follows: By utilizing the definable and programmable capabilities of multi-modal network elements, problems such as low communication efficiency, poor real-time performance, and complex deployment caused by multi-protocol heterogeneous networks in factories are solved. This method constructs a multi-modal intelligent factory network based on the same set of network infrastructure, realizes dynamic parsing of protocol identifiers at the switch chip layer, supports zero-conversion transparent transmission of mainstream transport protocols and custom protocols, solves the high latency caused by traditional industrial gateway protocol conversion, enables the intelligent factory network to be compatible with multiple different service transport protocols, and can be extended to future service protocols. This method realizes the efficient interconnection of multi-protocol devices in the intelligent factory, improves communication efficiency, reduces deployment and maintenance costs at the same time, and provides a reliable network infrastructure for industrial digital transformation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 General layout diagram of the intelligent factory network architecture provided by an embodiment of the present invention;

[0023] Figure 2 Network architecture diagram of the data center and security management area in the intelligent factory network architecture provided by an embodiment of the present invention;

[0024] Figure 3 Intelligent park office network architecture diagram provided by an embodiment of the present invention;

[0025] Figure 4 AGV network architecture diagram provided by an embodiment of the present invention;

[0026] Figure 5 Intelligent vision network architecture diagram provided by an embodiment of the present invention;

[0027] Figure 6 Factory network architecture diagram provided by an embodiment of the present invention;

[0028] Figure 7 Export network architecture diagram provided by an embodiment of the present invention;

[0029] Figure 8 Schematic diagram of the device structure provided by an embodiment of the present invention;

[0030] Figure 9 Schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0032] It should be noted that, without conflict, the features in the following embodiments and implementation manners can be combined with each other.

[0033] See Figure 1 , Figure 1 , which is the overall diagram of the intelligent factory network architecture provided by an embodiment of the present invention. The present invention provides a method for constructing an intelligent factory network architecture based on a multi-modal network, including constructing a data center network, a security management network, a smart office park network, an intelligent vision network, an AGV park network, a factory network, and an export network. Each network is connected by a core-level multi-modal network element. The core-level multi-modal network element is deployed in a dual-machine manner to ensure reliable links. In addition to supporting mainstream protocols such as IPv4, IPv6, SRv6, and MPLS, the core-level multi-modal network element also supports custom protocols. The core-level multi-modal network element uses FPGA + a dedicated switching chip (such as a programmable ASIC or NPU) to achieve nanosecond-level (<100ns) data forwarding, support a bandwidth of 100Gbps +, and meet large-traffic and low-latency scenarios such as industrial vision detection and high-speed motion control. At the same time, the core-level multi-modal network element solidifies the parsing logic of typical industrial protocols in the FPGA to improve the protocol processing efficiency. In addition, multiple FPGAs carried by the core-level multi-modal network element can support the dynamic loading of different protocol processing pipelines to adapt to future new industrial protocols and avoid hardware obsolescence. Such network elements are suitable for high-end manufacturing scenarios (such as semiconductor production lines and automotive welding), significantly reducing the real-time data stream transmission delay of devices such as industrial cameras and robots. Compared with traditional industrial switches, the throughput is significantly improved, and the protocol conversion overhead is reduced at the same time.

[0034] The access-level multi-modal network element uses a general x86 / ARM CPU + an open-source data plane (such as DPDK, P4), and supports the dynamic loading of any protocol stack in a software-defined manner to adapt to old devices (such as Modbus TCP) or private protocols. It supports remote programming by an SDN controller to achieve unified distribution of network-wide policies and improve operation and maintenance efficiency. The access-level multi-modal network element can be used in scenarios such as flexible production lines and warehousing logistics that require frequent adjustment of network policies, and the protocol adaptation time is shortened from several hours to the minute level. Compared with dedicated industrial switches, the deployment cost is reduced, and seamless upgrade of future protocols is supported at the same time.

[0035] Based on the access-level multimodal network element, the aggregation-level multimodal network element further deploys boundary security modules such as firewalls and intrusion detection for secure connection to the gateway nodes of external networks or upper-level autonomous domains.

[0036] The core-level multimodal network element, the aggregation-level multimodal network element, and the access-level multimodal network element all support the loading and unloading of custom protocols, have a unified control interface, support standard protocols such as p4runtime and netconf, and can be managed by the same network controller. The devices all have dual power supplies, support wide-temperature operation, are equipped with built-in security features to resist unknown attacks. The aggregation-level multimodal network element and the access-level multimodal network element are both deployed inside the autonomous domain.

[0037] Figure 2 It is the network architecture diagram of the data center and the security management area in the intelligent factory network architecture provided by an embodiment of the present invention.

[0038] Building the data center network includes setting up terminals such as business servers, business storage clusters, factory databases, and intelligent factory platforms. Among them, the business storage cluster is used to store documents, materials, etc. related to the intelligent factory business and is connected to business servers, factory databases, intelligent factory platforms, etc. through fiber optic switches. Business servers, factory databases, intelligent factory platforms, etc. are connected to the core-level multimodal network element through the aggregation-level multimodal network element and the access-level multimodal network element. At the same time, the aggregation-level multimodal network element and the access-level multimodal network element are respectively configured with load balancers, north-south firewalls, and east-west firewalls. In addition to supporting addressing based on typical mainstream protocols (IPv4, IPv6, SRv6), the data center network also supports content-named identifier addressing to achieve a decentralized content distribution function.

[0039] Building a security management network includes building a situation awareness subsystem, an anti-virus subsystem, an operation and maintenance audit subsystem, a database subsystem, a cloud management platform, etc. These subsystems are connected to the core-level multimodal network element through the aggregation-level multimodal network element and the north-south firewall. Among them, the load balancer uses a stacked deployment to ensure service redundancy. Physically, the load balancer includes multiple physical servers, and multiple actual servers are virtualized into a virtual server through mapping. When a user accesses the virtual server, the user's request is forwarded to the actual server through the load balancing scheduling algorithm. This can reduce the operating pressure on a single server and also ensure service redundancy. The east-west firewall uses service chain drainage. When firewall escape is required, the service chain policy can be directly deleted on the controller. The north-south firewall is deployed in a primary and standby mode to ensure service redundancy and is used for policy control of network access inside and outside the region. The policy deployment method is as follows: the outside of the firewall is a non-secure area, and the inside is a secure area. Unauthorized addresses are prohibited from accessing the secure area inside the firewall. Authorized addresses are allowed to access the secure area inside the firewall. The aggregation-level multimodal network element and the access-level multimodal network element adopt a leaf-spine network structure and are both deployed in a dual-machine mode, using cross-device link aggregation technology (such as distributed elastic network interconnection) to ensure service redundancy.

[0040] Figure 3 This is the architecture diagram of the intelligent park office network provided by an embodiment of the present invention.

[0041] Building a smart office park network includes building various office terminals, wireless access points (APs), Internet of Things terminals, etc. These devices are connected to the access-level multimodal network element through wired access or through the wireless access AP and then connected to the access-level multimodal network element. The access-level multimodal network element is connected to the core-level multimodal network element through the aggregation-level multimodal network element and the north-south firewall. The access-level multimodal network element and the aggregation-level multimodal network element adopt a leaf-spine network architecture, and the aggregation-level multimodal network element is deployed in a dual-machine manner to ensure service redundancy. This network is used to carry the office business of intelligent factory employees, such as collaborative design of digital models of industrial components, equipment, systems, environments, etc. across departments, transmitting design data through the network, and realizing collaborative modification and improvement of 2D / 3D design drawings by remote designers. Usually, such business scenarios should support mainstream network protocols, such as IPv4, IPv6, SRv6, etc. In addition, the smart office park network also supports addressing based on content naming to improve bandwidth utilization. For example, when a terminal in the smart office park network requests file content from the data center, the request is addressed by naming on the multimodal network element. If the multimodal network element already stores the content corresponding to the naming, the request does not need to reach the data center and can be directly replied to the requesting terminal by the multimodal network element, thus improving the transmission efficiency. For example, when within the smart office park network, addressing is performed by naming on the access-level modal network element and the aggregation-level modal network element; when sending to other networks such as the AGV network, it passes through the core-level multimodal network element, and addressing by naming is performed on the core-level multimodal network element for routing.

[0042] Figure 4 This is the AGV network architecture diagram provided by an embodiment of the present invention.

[0043] The terminals in the AGV (Automated Guided Vehicle) campus network include various types of AGV trolleys accessing the smart factory. The network access layer of the AGV access area adopts a ring network protection design (such as using RRPP, Rapid Ring Protection Protocol), aiming to achieve sub-second fault convergence. The AGV trolley is built-in with a wireless communication module and accesses the access-level multimodal network element through an AP. The AP supports wifi6. The access-level multimodal network element, aggregation-level multimodal network element, firewall are connected to the core-level multimodal network element. The firewall is deployed in the primary and standby mode. The AGV trolley is also equipped with various sensors, which can collect various data such as on-site videos, voices, and pictures. The network should transmit the aforementioned data in real time and keep the transmission uninterrupted during cross-regional movement. In addition, the smart office campus network monitors and analyzes the data collected by the AGV trolley in real time. When a danger is detected, it is necessary to urgently evacuate the vehicles / pedestrians at the accident site, call the maintenance vehicles around the accident area, and issue a warning to the corresponding area. The control center sends the alarm information and early warning information to the AGV campus network according to the dangerous area. Since the occurrence of accidents in the smart factory is uncertain, the network needs to be flexibly located and accurately notified according to different areas. Therefore, the network should be able to transmit the geographical identification network mode and complete the point-to-point, point-to-multipoint, point-to-any point within the area, point-to-area and other transmission methods addressed by geographical location, and support communication service scenarios such as vehicle-to-vehicle and vehicle-to-AP. It should be noted that the control center is deployed in the factory network. The control center can send device operation instructions to the industrial device terminals based on industrial protocols and remotely control the devices. The control center can also dispatch the AGV trolleys to the AGV campus network based on other protocols (such as geographical identification protocols), and can also communicate with the terminals of the smart office campus network based on the mainstream IP protocol.

[0044] Figure 5 This is the architecture diagram of the intelligent vision network provided by an embodiment of the present invention.

[0045] Building the intelligent vision network is mainly used to carry the intelligent vision quality inspection service on the production line. The network terminals mainly include cameras located at positions such as the production line. The cameras are connected to the core-level multimodal network element through the access-level multimodal network element, aggregation-level multimodal network element, and firewall. The cameras take pictures of the products and continuously upload the product quality inspection data to the data center network through the core-level multimodal network element. After that, the smart office campus network will request the corresponding data from the data center as needed.

[0046] Figure 6 This is the architecture diagram of the factory network provided by an embodiment of the present invention.

[0047] Building a factory network includes building access-level multimodal network elements and aggregation-level multimodal network elements. Its terminals include intelligent machine tools, robotic arms, control centers, edge servers, intelligent warehousing, etc. in the factory. Among them, the control center can send instructions to remotely control the start and stop of industrial equipment such as robotic arms and machine tools, and can also send scheduling instructions to schedule the movement of the small vehicles in the AGV park network according to requirements. At the same time, it also supports communication with the office network based on mainstream protocols. Each terminal accesses the core-level multimodal network element through the access-level multimodal network element, the aggregation-level multimodal network element, and the firewall. Among them, the access-level multimodal network element and the aggregation-level multimodal network element can provide redundant default gateway functions to ensure that when the active router fails, it can quickly switch to the standby router, thereby achieving sub-second fault convergence and ensuring the continuity and reliability of the network. The firewall is deployed in the primary and standby mode to ensure service redundancy. The aggregation switch is deployed virtually to ensure service redundancy.

[0048] Figure 7 This is the export network architecture diagram provided by an embodiment of the present invention.

[0049] Building an export network includes building an internal firewall, a security gateway, a switch, a load balancer, an anti-DDoS server, and an external firewall. The load balancer and the switch are both deployed virtually to ensure service redundancy. Logically, there are two switches and a load balancer, and physically only one physical machine is deployed. The internal firewall and the security gateway are deployed in the primary and standby mode. The anti-DDoS server and the external firewall are deployed in a dual-machine transparent mode. The factory export uses dual-operator access.

[0050] Corresponding to the embodiment of the method for building an intelligent factory network architecture based on a multimodal network described above, the present invention also provides an embodiment of an apparatus for building an intelligent factory network architecture based on a multimodal network.

[0051] See Figure 8 , the apparatus for building an intelligent factory network architecture based on a multimodal network provided by the embodiment of the present invention includes one or more processors for implementing the method for building an intelligent factory network architecture based on a multimodal network in the above embodiment.

[0052] The embodiment of the apparatus for building an intelligent factory network architecture based on a multimodal network of the present invention can be applied to any device with data processing capabilities, and the any device with data processing capabilities can be a device or apparatus such as a computer. The apparatus embodiment can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, as a logically meaningful apparatus, it is formed by the processor of any device with data processing capabilities reading the corresponding computer program instructions in the non-volatile memory into the memory for operation. From the hardware level, such as Figure 8As shown, it is a hardware structure diagram of any device with data processing capabilities where the intelligent factory network architecture construction device based on the multimodal network of the present invention is located. Except for Figure 8 the shown processor, memory, network interface, and non-volatile memory, any device with data processing capabilities where the device in the embodiment is located usually may further include other hardware according to the actual functions of the any device with data processing capabilities, which will not be elaborated herein.

[0053] For the specific implementation process of the functions and roles of each unit in the above device, refer to the implementation process of the corresponding steps in the above method in detail, which will not be elaborated herein.

[0054] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can be referred to the partial description of the method embodiment. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the present invention. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0055] Corresponding to the embodiment of the method for constructing an intelligent factory network architecture based on a multimodal network described above, an embodiment of the present application further provides an electronic device, including: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method for constructing an intelligent factory network architecture based on a multimodal network as described above. As Figure 9 shown, it is a hardware structure diagram of any device with data processing capabilities where the method for constructing an intelligent factory network architecture based on a multimodal network provided by the embodiment of the present application is located. Except for Figure 9 the shown processor, memory, DMA controller, disk, and non-volatile memory, any device with data processing capabilities where the device in the embodiment is located usually may further include other hardware according to the actual functions of the any device with data processing capabilities, which will not be elaborated herein.

[0056] Corresponding to the embodiment of the method for constructing an intelligent factory network architecture based on a multimodal network described above, an embodiment of the present invention further provides a computer-readable storage medium, on which a program is stored. When the program is executed by a processor, the method for constructing an intelligent factory network architecture based on a multimodal network in the above embodiment is implemented.

[0057] The computer-readable storage medium may be an internal storage unit of any data processing-capable device described in any of the foregoing embodiments, such as a hard disk or a memory. The computer-readable storage medium may also be any data processing-capable device, such as a plug-in hard disk, a Smart Media Card (SMC), an SD card, a Flash Card, etc. equipped on the device. Further, the computer-readable storage medium may also include both an internal storage unit of any data processing-capable device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by any data processing-capable device, and may also be used to temporarily store the data that has been output or will be output.

[0058] The foregoing is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the scope of protection of the present invention.

[0059] The above embodiments are only used to illustrate the design concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The scope of protection of the present invention is not limited to the above embodiments. Therefore, any equivalent changes or modifications made based on the principles and design concepts disclosed by the present invention are within the scope of protection of the present invention.

Claims

1. A method for constructing an intelligent factory network architecture based on a multi-modal network, characterized in that, The method includes: Constructing an intelligent factory network architecture including a data center network, a security management network, a smart office park network, an AGV park network, an intelligent vision network, a factory network, and an egress network; where: Constructing a data center network, including building business servers, business storage clusters, factory databases, and intelligent factory platforms; constructing a security management network, including constructing a situation awareness subsystem, an anti-virus subsystem, an operation and maintenance audit subsystem, a database subsystem, and a cloud management platform; constructing a smart office park network, including constructing various office terminals, wireless access points, and Internet of Things terminals; constructing terminals in the AGV park network, including connecting various AGV cars in the intelligent factory; constructing an intelligent vision network, mainly used to carry intelligent vision quality inspection services on the production line, and the network terminals mainly include cameras located at the production line positions; constructing a factory network, including constructing access-level multimodal network elements and aggregation-level multimodal network elements for achieving sub-second fault convergence; constructing an egress network, including constructing an internal firewall, a security gateway, switches, load balancers, anti-DDoS servers, and an external firewall; Each network is connected through core-level multimodal network elements; the core-level multimodal network elements are deployed in a dual-machine mode to ensure reliable links. They adopt an architecture of FPGA + dedicated switching chips to achieve nanosecond-level data forwarding, and industrial protocol parsing logic is solidified in the FPGA to improve protocol processing efficiency; the access-level multimodal network elements, aggregation-level multimodal network elements, and core-level multimodal network elements all support the loading and unloading of custom protocols and have a unified control interface.

2. The method for constructing an intelligent factory network architecture based on a multimodal network according to claim 1, wherein, In the data center network, the business storage cluster is used to store documents and materials related to intelligent factory operations and is connected to business servers, factory databases, and intelligent factory platforms through fiber optic switches; business servers, factory databases, and intelligent factory platforms are connected to the core-level multimodal network elements through aggregation-level multimodal network elements and access-level multimodal network elements; the aggregation-level multimodal network elements and access-level multimodal network elements are respectively configured with load balancers, north-south firewalls, and east-west firewalls.

3. The method for constructing an intelligent factory network architecture based on a multi-modal network according to claim 1, wherein The data center network and the smart office park network support addressing based on IPv4, IPv6, SRv6 protocols, and content naming identifiers to achieve a decentralized content distribution function; when a terminal in the smart office park network requests file content from the data center, the request is addressed by name on the multimodal network elements. If the multimodal network elements already store the content corresponding to the name, the request does not need to reach the data center, and the multimodal network elements directly reply to the requesting terminal, thereby improving the transmission efficiency.

4. The method for constructing an intelligent factory network architecture based on a multimodal network according to claim 1, wherein, In the described security management network, each subsystem is connected to the core multi-modal network element through the aggregation-level multi-modal network element and the north-south firewall; the aggregation-level multi-modal network element and the access-level multi-modal network element adopt a leaf-spine network structure, both are deployed in a dual-machine mode, and use cross-device link aggregation technology to ensure service redundancy; the north-south firewall is deployed in a primary-backup mode to ensure service redundancy and is used for policy control of network access inside and outside the region; the policy deployment method is: the outside of the firewall is a non-secure area and the inside is a secure area; unauthorized addresses are prohibited from accessing the secure area inside the firewall, and authorized addresses are allowed to access the secure area inside the firewall.

5. The method for constructing an intelligent factory network architecture based on a multimodal network according to claim 1, wherein In the described intelligent office park network, each device accesses the access-level multi-modal network element through wired access or through a wireless access AP, and the access-level multi-modal network element accesses the core-level multi-modal network element through the aggregation-level multi-modal network element and the north-south firewall; the access-level multi-modal network element and the aggregation-level multi-modal network element adopt a leaf-spine network architecture, and the aggregation-level multi-modal network element is deployed in a dual-machine mode to ensure service redundancy; the intelligent office park network is used to carry the office business of the employees in the intelligent factory, transmit design data through the network, and realize the collaborative modification and improvement of off-site designers.

6. The method for constructing an intelligent factory network architecture based on a multimodal network according to claim 1, wherein In the described AGV park network, the AGV cart accesses the access-level multi-modal network element through an AP, and then is connected to the core-level multi-modal network element through the access-level multi-modal network element, the aggregation-level multi-modal network element, and the firewall. The firewall is deployed in a primary-backup mode; the AGV cart is equipped with various sensors for collecting various data such as on-site videos, voices, and pictures; the data collected by the AGV cart is monitored and analyzed in real time through the intelligent office park network. When a danger is detected, vehicles / pedestrians that need to be urgently removed from the accident site are called, the maintenance vehicles around the accident area are called, and a warning is sent to the corresponding area; the control center sends the alarm information and early warning information to the corresponding areas according to the dangerous areas through the network; through this network, the geographical identification network mode is transmitted to complete the point-to-point, point-to-multipoint, point-to-any point within the area, and point-to-area transmission methods addressed by geographical location, and support communication service scenarios such as vehicle-to-vehicle and vehicle-to-AP.

7. The method for constructing an intelligent factory network architecture based on a multimodal network according to claim 1, wherein In the described intelligent vision network, the camera is connected to the core-level multi-modal network element through the access-level multi-modal network element, the aggregation-level multi-modal network element, and the firewall; the product photos taken by the camera are uploaded to the data center network for product quality inspection data through the core-level multi-modal network element; afterwards, the intelligent office park network will request the corresponding data from the data center as needed.

8. An intelligent factory network architecture construction device based on a multimodal network, characterized in that Comprising one or more processors for implementing the method for constructing an intelligent factory network architecture based on a multi-modal network according to any one of claims 1-7.

9. An electronic device, comprising a memory and a processor, characterized in that, The memory is coupled to the processor; wherein, the memory is used to store program data, and the processor is used to execute the program data to implement the method for constructing an intelligent factory network architecture based on a multi-modal network according to any one of claims 1-7 above.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for constructing an intelligent factory network architecture based on a multi-modal network according to any one of claims 1-7.

Images