KR20210021249A - Intelligent industrial internet of things system using bidirectional channel-like neural network architecture - Google Patents

Abstract

The present invention provides an intelligent industrial internet-of-things system using a bidirectional channel-type neural network architecture which does not require a gateway. The intelligent industrial internet-of-things system using a bidirectional channel-type neural network architecture comprises: a programmable logic controller having an I/O module, a communication module, a detection database, a motion database, an edge computing module, and a first MQTT data module as a motion device and a detection device for connection of the intelligent industrial internet-of-things system; a cloud server having an MQTT agent, a big data module, a human cloud visual database, and a human cloud operation database; and a remote device having a human cloud visual interface program, a human cloud operation interface program, and a second MQTT data module. The programmable logic controller (1), the cloud server (2), and the remote device (3) are connected to each other via a network. Therefore, the present invention does not need to construct a gateway and a Netcom device, has low construction costs and short construction periods, facilitates maintenance, has low power consumption and high communication speed, allows bidirectional many-to-many transmission, stably synchronizes real-time processing, and has very high reliability.

Description

Intelligent industrial Internet of Things system using bidirectional channel type neural network architecture {INTELLIGENT INDUSTRIAL INTERNET OF THINGS SYSTEM USING BIDIRECTIONAL CHANNEL-LIKE NEURAL NETWORK ARCHITECTURE}

The present invention relates to an intelligent enterprise integration architecture for industries, industrial products and services, and more particularly, to an intelligent industrial Internet of Things system utilizing a two-way channel type neural network architecture.

The Fourth Industrial Revolution, also referred to as Industry 4.0, is the first high-tech project proposed by the German government. Its main idea is to connect and optimize, linking and optimizing manufacturing-related factors to increase the competitiveness and profits of companies. The current goal of Industry 4.0 for Japanese manufacturers is to focus on pursuing "zero downtime, zero wait", while the goal of Industry 4.0 in Germany is to achieve "maximum custom" production flexibility with an economical batch size of 1 at the same cost. Is to do.

In Industry 4.0, IIoT is an indispensable part of the transformation of network entity systems and production processes through big data and analytics.

IIoT, or Industrial Internet of Things, refers to the expansion and use of the Internet of Things (IoT) in industrial applications; IIoT focuses on machine-to-machine communication (M2M), big data and machine learning (ML) to further improve the efficiency and reliability of industrial operations; IIoT covers a full range of industrial applications including robotics, medical devices and software-defined production processes.

Real-time data from sensors and other data sources can be helpful in making decisions, making views and making concrete actions through industrial devices and infrastructure; Machines can further take over and automate tasks that were not possible in previous industrial revolutions; In a broader context, IIoT is very important for use scenarios related to the Internet ecosystem or environment, such as turning cities into smart cities or transforming factories into smart factories.

IIoT transcends the network interconnection of common consumer devices and entity devices commonly used in IoT; IIoT is different from the intersection of information technology (IT) and operational technology (OT). OT refers to a network of operational processes and industrial control systems (ICS), including human-machine interface (HMI), monitoring and data acquisition (SCADA) systems, distributed control systems (DCS) and programmable logic controllers (PLCs).

As shown in FIG. 1, the main architecture of the conventional industrial IoT communication network architecture 400 that is actually used currently is, as shown in FIG. 1, the sensor 401 is an I/O collection gateway 402, a first IIOT communication gateway 403, The existing I/O module 404 and the industrial communication gateway 405 are connected, and the I/O collection gateway 402 and the first IIOT communication gateway 403 are also connected to the edge computing server 409, The existing I/O module 404 is also connected to the PLC CPU module 407, the industrial communication gateway 405 is also connected to the existing communication module 406, and the existing communication module 406 is also connected to the The PLC CPU module 407 is connected, the PLC CPU module 407 is also connected to a second IIOT communication gateway 408, and the second IIOT communication gateway 408 is also connected to the edge computing server 409. Is connected, the edge computing server 409 is also connected to the edge gateway 410, and finally the edge gateway 410 is connected to the cloud system 411.

From the above description, it can be understood that the problem of the general architecture of the existing industrial IoT communication network architecture 400 lies in the edge gateway 410. The cost of building gateway hardware is high, and although not shown in the above description and drawings, a netcom device is further required to help the communication connection of the gateway when the gateway is used.The netcom device has a high building cost and is not only repetitive network wiring. High construction cost is increased, construction period is extended, maintenance difficulty is high after construction is completed, related maintenance and labor costs are maintained high, and operation costs are increased due to the high electrical energy consumption of gateway and netcom equipment during operation, and it is not eco-friendly. .

The biggest problem among them is that when using a gateway, the communication speed is reduced by reducing the network packet transmission speed, and the network packet transmission direction is limited, so only one-to-one transmission in a single direction is possible. It becomes impossible to do.

In view of this, an object of the present invention is to provide an intelligent industrial IoT system utilizing a two-way channel type neural network architecture capable of solving the above-described problem.

In order to solve the above problem, the present invention is implemented as follows. An intelligent industrial IoT system utilizing a two-way channel type neural network architecture capable of connecting at least one sensing device and at least one exercise device, wherein the intelligent industrial IoT system includes at least one programmable logic controller, at least one cloud server, And at least one remote device; The programmable logic controller includes at least one I/O module, at least one communication module, a sensing database, an exercise database, an edge computing module, and a first MQTT data module, wherein the I/O module and the communication module are each The corresponding sensing device is connected to the exercise device, the sensing database and the exercise database are connected to the corresponding I/O module and the communication module, respectively, and the edge computing module is the sensing database and the exercise database, respectively Is connected to, the first MQTT data module is connected to the edge computing module and also connected to the cloud server through a network; The cloud server is connected to the programmable logic controller through a network, and further includes at least an MQTT agent, a big data module, a human cloud visual database, and a human cloud operation database, and the MQTT agent is the first MQTT data through the network. Is connected to the module, the big data module is connected to the MQTT agent, the human cloud visual database is connected to the human cloud operation database, and both are connected to the MQTT agent and the big data module, respectively, and also via a network. Connected to the remote device; The remote device is connected to the cloud server through a network and has at least a human cloud visual interface program, a human cloud operation interface program, and a second MQTT data module, wherein the human cloud visual interface program and the human cloud operation interface program Are respectively connected to the second MQTT data module, the second MQTT data module is connected to the MQTT agent through a network, and simultaneously connected to the human cloud visual database and the human cloud operation database through the MQTT agent.

Furthermore, the edge computing module further includes an edge computing program and an edge computing database, wherein the edge computing program is connected to the sensing database and the exercise database, respectively, and the edge computing database is the edge computing program and the first Each connected to the MQTT data module; The first MQTT data module further includes a first conversion program, a first MQTT database, a first subscription program, and a first issuing program, and the first conversion program is connected to the edge computing database, and the first MQTT database Is connected to the first conversion program, the first subscription program is connected to the first MQTT database and the MQTT agent, respectively, and the first issuing program is connected to the first MQTT database and the MQTT agent, respectively; The big data module further includes a big data computing program and a big data database, and the big data computing program is connected to the MQTT agent and the big data database, and the big data database is the human cloud visual database and the human cloud. Each connected to the operation database; The second MQTT data module further includes a second conversion program, a second MQTT database, a second subscription program, and a second issuing program, and the second conversion program is the human cloud visual interface program, the human cloud operation interface program. Respectively, the second MQTT database is connected to the second conversion program, the second subscription program, and the second issuing program, respectively, the second subscription program is also connected to the MQTT agent, and the second The issuing program is also connected to the MQTT agent.

Furthermore, the cloud server further includes at least one of a machine learning module and an artificial intelligence module connectable to the big data module. Furthermore, the machine learning module further includes a machine learning analysis computing program and a machine learning database, and the machine learning analysis computing program is connected to the big data database, and the machine learning database is the machine learning analysis computing program, Each connected to a human cloud visual database and the human cloud manipulation database; The artificial intelligence module further includes an artificial intelligence determination computing program and an artificial intelligence database, wherein the artificial intelligence determination computing program is connected to the big data database, and the artificial intelligence database is the artificial intelligence determination computing program, the human cloud visual It is connected to the database and the human cloud operation database, respectively.

Further, when the cloud server includes the machine learning module and the artificial intelligence module at the same time, the artificial intelligence determination computing program is connected to the big data database through the machine learning analysis computing program connected thereto. Connected to the learning database.

Furthermore, the communication protocol applied between the programmable logic controller, the cloud server and the remote device is an application MQTT communication protocol.

Furthermore, the remote device is smart glasses.

Compared with the prior art, the present invention has the following effects.

1. The intelligent industrial IoT system of the present invention uses a combination of a programmable logic controller, a cloud server, and a remote device to achieve a virtual and real integration effect, effectively fuse information technology, operation technology and communication technology, and provide an open data platform. It further combines to form an intelligent enterprise integration architecture, thereby linking cloud and data analysis applications to focus on the core goals of Industry 4.0. Compared to the existing industrial IoT communication network architecture, there is no need to build a gateway hardware, and a Netcom device that supports communication connection of the gateway hardware does not need to repeat network wiring, thus saving a certain construction cost and shortening the construction period. Also, the difficulty of maintenance management is reduced, and maintenance and labor costs are reduced. In addition, electric energy consumption can be reduced, which not only reduces operating costs, but also considers eco-friendliness. Most importantly, communication speed can be faster, enabling many-to-many transmission in both directions and stable real-time processing. It synchronizes with, and is very reliable.

2. The intelligent industrial IoT system of the present invention applies the concept of a neural network architecture. The so-called sensing devices are various input devices such as various sensors, and the so-called movement devices refer to various output devices such as relays, hydraulic cylinders, cylinders, robots, motors, control valves, AGV vehicles, conveyor belts, and the like. Accordingly, insufficient data collection can be prevented, data can be effectively applied, and the problem of not being able to provide feedback to the field in real time is solved.

1 is a schematic architectural schematic diagram of an existing industrial IoT communication network.
2 is a schematic architectural schematic diagram according to the present invention.
3 is a schematic diagram of the overall architecture according to the first embodiment of the present invention.
4 is a schematic diagram of an architecture implementation for observing sensing device data according to the first embodiment of the present invention.
5 is a schematic diagram of an architecture implementation for operating the exercise device according to the first embodiment of the present invention.
6 is a schematic diagram of an overall architecture according to a second embodiment of the present invention.
7 is a schematic diagram of an overall architecture according to a third embodiment of the present invention.
8 is a schematic diagram of an overall architecture according to a fourth embodiment of the present invention.

It will be described in detail as follows with reference to the drawings below. In the drawings, the same components or members are indicated by the same reference numerals as possible. In addition, detailed descriptions of related known functions or configurations are omitted so as not to obscure the subject matter of the present invention.

As shown in FIGS. 2 to 5, the first embodiment illustrated in the figure is an intelligent system utilizing a bidirectional channel type neural network architecture capable of connecting at least one sensing device 200 and at least one exercise device 300. As an industrial IoT system 100, the intelligent industrial IoT system 100 includes at least one programmable logic controller 1, at least one cloud server 2, and at least one remote device 3, ; The programmable logic controller (1) includes at least one I/O module (11), at least one communication module (12), a sensing database (13), a motion database (14), an edge computing module (15), and a first Equipped with an MQTT data module 16, the I/O module 11 and the communication module 12 are connected to the corresponding sensing device 200 and the exercise device 300, respectively, and the sensing database ( 13) and the exercise database 14 are connected to the corresponding I/O module 11 and the communication module 12, respectively, and the edge computing module 15 is the detection database 13 and the exercise Connected to the database 14, the first MQTT data module 16 connected to the edge computing module 15, and also connected to the cloud server 2 via a network 10; The cloud server 2 is connected to the programmable logic controller 1 through a network 10, and at least an MQTT agent 21, a big data module 22, a human cloud visual database 23, and a human cloud Equipped with an operation database 24, the MQTT agent 21 is connected to the first MQTT data module 16 through the network 10, the big data module 22 is connected to the MQTT agent 21 Is connected, the human cloud visual database 23 is connected to the human cloud manipulation database 24, and both are connected to the MQTT agent 21 and the big data module 22, respectively, and the network 10 Connected to the remote device 3 through The remote device 3 is connected to the cloud server 2 via a network 10 and at least a human cloud visual interface program 31, a human cloud operation interface program 32, and a second MQTT data module 33 ), and the human cloud visual interface program 31 and the human cloud operation interface program 32 are respectively connected to the second MQTT data module 33, and the second MQTT data module 33 is a network It is characterized in that it is connected to the MQTT agent 21 through (10), and is connected to the human cloud visual database 23 and the human cloud operation database 24 through the MQTT agent 21 at the same time.

In the above, the programmable logic controller 1, the cloud server 2, and the remote device 3 are combined to form the intelligent industrial IoT system 100 of the present invention. Compared to the existing industrial IoT communication network architecture 400 shown in FIG. 1, it is possible to synchronize within a millisecond level by applying a two-way channel type neural network architecture, and the existing industrial IoT communication network with a programmable logic controller 1 It replaces the gateway of the architecture 400 and can also remove the Netcom device supporting the gateway. Accordingly, there is no need to repeat network wiring, the overall construction cost can be reduced, the construction period is shortened, the post maintenance and labor costs are reduced, the device can be simplified, and the consequent electrical energy consumption is also reduced. It is more environmentally friendly.

Next, by applying the programmable logic controller (1), it is possible to implement a high network packet transmission rate and a faster communication speed. Also, since there is no restriction on the direction of network packet transmission, it is possible to transmit many-to-many in both directions. There is no problem of losing data, so real-time processing is synchronized reliably and reliably.

Furthermore, the intelligent industrial IoT system 100 of the present invention can implement four types of removal. In other words, it prevents system virus intrusion and eliminates the need for system construction costs, system maintenance and updates, and operating systemization; Eliminates hardware construction costs, system construction costs, software maintenance and updates, and in-the-softization to prevent system virus intrusion; Eliminates gatewayization so that no hardware construction cost is required, and transmission speed and unidirectional transmission are improved; It eliminates the cost of building a machine room, building a servo, and eliminating the need for IT maintenance and updates. In addition, through virtual and real integration, convergence information, operation and communication technology, it clearly reaches the core goals of Industry 4.0.

In addition, through the application of the programmable logic controller 1, it is easy to use in cooperation with the factory, the application installation and maintenance are easy, the failure rate is low, and the application range is wide. At the same time, the intelligent industrial IoT system 100 of the present invention is independent. By collecting data, there is no fear of problems such as insufficient data volume or data error or data inconsistency.

In addition, since a bidirectional channel type neural network architecture is used, referring to FIG. 4, the programmable logic controller 1 is an I/O module 11 such as a digital input module, an analog input module, a temperature measurement module, a power measurement module, etc. Pressure sensor, temperature and humidity sensor, temperature sensor through communication module 12 such as RS-232 communication module, RS-485 communication module, EtherNet communication module, CANOpen communication module, PROFIBUS communication module, RFID communication module, GPRS communication module, etc. , Flow sensor, liquid level sensor, ultrasonic sensor, immersion sensor, illuminance sensor, differential pressure transmitter, acceleration sensor, displacement sensor, load cell, large amount of data acquired from sensing device 200 such as industrial camera, etc., first detection database 13 It can be stored in the edge computing module 15 and the first MQTT data module 16 is combined and quickly transmitted to the MQTT agent 21 of the cloud server 2 through the network 10, and the big data module ( 22) After cooperating with the data search processing of the human cloud visual database 23, the user of the remote device 3 remotely via the network 10 is sent to the MQTT agent 21 by the second MQTT data module 33. ) To receive and process the data transmitted, and to allow the user to know the current situation in real time at a remote location through the human cloud visual interface program 31. After the remote user understands the situation due to the action of the two-way synchronization, referring to FIG. 5, data is transmitted through the second MQTT data module 33 using the human cloud operation interface program 32 of the remote device 3. It transmits back to the MQTT agent 21, and similarly, the big data module 22 cooperates with the processing of the human cloud operation database 24 to transmit it back to the first MQTT data module 16 for processing, and the edge computing module 15 ) To transmit data back to the exercise database (14) in cooperation with I/O modules (11) such as digital output modules, analog output modules, pulse output modules, and RS-232 communication modules, RS-485 communication modules, EtherNet Movement such as relay, hydraulic cylinder, cylinder, robot hand, motor, control valve, AGV vehicle, conveyor belt, etc. through communication module 12 such as communication module, CANOpen communication module, PROFIBUS communication module, RFID communication module, GPRS communication module, etc. It can be delivered to the device 300. Since the reaction and accident time of the user is eliminated in the whole process, it is possible to process in near real time.

In addition, when the communication module 12 is operated, corresponding to the communication module 12, such as RFID, GPRS, TCP/IP, CANOpen, CANBus, EtherCAT, EtherNet/IP, ModBus, ModBus TCP/IP, PROFINET, PROFIBUS, etc. Industrial communication protocols can be applied.

Next, in the above description, the network 10 for connection between the programmable logic controller 1, the cloud server 2, and the remote device 3 is generally referred to as the Internet, and may be executed by wire and/or wirelessly.

Application example 1 of the intelligent industrial IoT system 100 of the present invention can be applied to an intelligent building, and collects building resource information including power, lighting, air conditioner, firefighting, access control, space, cabinet, information device, etc. Manage. This optimizes the use of resources and improves the operational efficiency of the building.

Application Example 2 of the intelligent industrial IoT system 100 of the present invention can be applied to a health diagnosis of a motor. Use programmable logic controller (1) to collect data on sensing devices (200) such as vibration sensors and to cooperate with end servers (2) to understand the operating and health status of critical devices and major components under current operating conditions. In addition, the remote device (3) can be used to immediately warn against adverse factors in the current operating conditions and monitoring of initial failure problems, thus reducing adverse factors in mechanical device operation, effectively improving the life of parts and preventing work safety accidents. It is effective in implementing life extension planning ideas and preventing expensive maintenance and operation losses due to unexpected and serious equipment failure.

Application Example 3 of the intelligent industrial IoT system 100 of the present invention can be applied to a smart factory. Using the programmable logic controller (1), data is collected on the sensing device 200 such as an air conditioner system, power monitoring system, machine stage control system, access control system, disaster prevention system, monitoring module, and environmental system, and the end server (2). ) To enable users to use remote devices (3) to track selected KPIs during production in real time, all from anywhere, and to provide flash alerts and notifications from the right people at the right time to warn of arbitrary messages during operation. . It can also accelerate site maintenance by interacting with key processes using simple virtual controls anytime, anywhere.

Referring to FIG. 3, the edge computing module 15 further includes an edge computing program 151 and an edge computing database 152, and the edge computing program 151 is the sensing database 13 and the exercise database. Each connected to (14), and the edge computing database 152 is connected to the edge computing program 151 and the first MQTT data module 16, respectively; The first MQTT data module 16 further includes a first conversion program 161, a first MQTT database 162, a first subscription program 163, and a first publication program 164, and the first conversion The program 161 is connected to the edge computing database 152, the first MQTT database 162 is connected to the first conversion program 161, and the first subscription program 163 is the first MQTT A database 162, each connected to the MQTT agent 21, the first issuing program 164 is connected to the first MQTT database 162 and the MQTT agent 21, respectively; The big data module 22 further includes a big data computing program 221 and a big data database 222, and the big data computing program 221 is the MQTT agent 21, the big data database 222 And the big data database 222 is connected to the human cloud visual database 23 and the human cloud manipulation database 24, respectively; The second MQTT data module 33 further includes a second conversion program 331, a second MQTT database 332, a second subscription program 333, and a second issuing program 334, and the second conversion The program 331 is connected to the human cloud visual interface program 31 and the human cloud operation interface program 32, respectively, and the second MQTT database 332 is the second conversion program 331 and the second Each connected to a subscription program 333 and the second issuing program 334, the second subscription program 333 is also connected to the MQTT agent 21, the second issuing program 334 is also the It is connected to the MQTT agent 21.

Here, by cooperating with the edge computing database 152 through the edge computing program 151 to allow the edge computing module 15 to process information effectively, it actually reduces the time delay and data transmission/storage cost due to the cloud, In cooperation with the intelligent industrial IoT system 100 of the present invention, a fast transmission, low delay architecture can be implemented, so that the cloud server 2 can be effectively operated.

Next, the first conversion program 161 cooperates with the first MQTT database 162, the second conversion program 331 cooperates with the second MQTT database 332 to process MQTT data, and the first subscription program ( 163), by applying the second subscription program 333, the first publication program 164 and the second publication program 334, the first MQTT data module 16 and the second MQTT data module 33 are normally subscribed and By enabling publishing and operation, it provides light, reliable and fast communication, and can be operated without the need for too large network bandwidth.

Further, by combining the big data computing program 221 and the big data database 222, the big data module 22 performs a function of organizing and analyzing a large amount of data collected from the programmable logic controller 1. It continuously improves the operational efficiency of the intelligent industrial IoT system 100 and reduces the possibility of problems.

Referring to FIG. 6, this shows a second embodiment of the present invention, wherein the cloud server 2 further includes at least a machine learning module 25 connected to the big data module 22.

In the above, the machine learning module 25 further includes a machine learning analysis computing program 251 and a machine learning database 252, and the machine learning analysis computing program 251 is connected to the big data database 222 The machine learning database 252 is connected to the machine learning analysis computing program 251, the human cloud visual database 23, and the human cloud manipulation database 24, respectively.

Here, through the application of the machine learning module 25, a large amount of data collected from the programmable logic controller 1 in cooperation with the big data module 22 can be applied to the machine learning module 25, and the machine learning analysis computing program After analyzing the data using 251, it is stored in the machine learning database 252, and learns to create an algorithm or rule set by acquiring a complex function or sample from the data, and how the machine predicts or reflects the future from the data. Let's learn. Accordingly, since the intelligent industrial IoT system 100 of the present invention can be operated more intelligently and can automatically complete data collection, the machine learning module 25 does not have enough data to learn, so the machine learning module ( 25) This can actually take place without worrying about spilling onto the surface.

Referring to FIG. 7, this shows a third embodiment of the present invention, and the cloud server 2 further includes at least an artificial intelligence module 26 connectable to the big data module 22.

In the above, the artificial intelligence module 26 further includes an artificial intelligence determination computing program 261 and an artificial intelligence database 262, and the artificial intelligence determination computing program 261 is connected to the big data database 222 The artificial intelligence database 262 is connected to the artificial intelligence decision computing program 261, the human cloud visual database 23, and the human cloud manipulation database 24, respectively.

Here, through the application of the artificial intelligence module 26, a large amount of data collected from the programmable logic controller 1 in cooperation with the big data module 22 can be applied to the artificial intelligence module 26, and artificial intelligence decision computing After analyzing the data using the program 261, it is stored in the artificial intelligence database 262 so that the artificial intelligence decision computing program 261 has sufficient data to operate the decision algorithm satisfactorily, and the intelligent industrial Internet of Things of the present invention Since the system 100 can be operated more intelligently and data collection can be completed automatically, there is no concern that the artificial intelligence module 26 leaks to the surface due to lack of knowledge engineering. The artificial intelligence module 26 can actually take place without any need.

Referring to FIG. 8, this shows a fourth embodiment of the present invention. When the cloud server 2 includes the machine learning module 25 and the artificial intelligence module 26 at the same time, the artificial intelligence The decision computing program 261 is connected to the big data database 222 through the machine learning analysis computing program 251 connected thereto, and is also connected to the machine learning database 252.

Here, by simultaneously executing the machine learning module 25 and the artificial intelligence module 26 and collecting data using the programmable logic controller 1, the intelligent industrial IoT system 100 of the present invention is more efficient and intelligent. Can be operated as By simultaneously executing the machine learning module 25 and the artificial intelligence module 26, the intelligent industrial IoT system 100 of the present invention can cover different application ranges, thereby further broadening the application range of the present invention.

In the first to fourth embodiments of the present invention, the communication protocol applied between the programmable logic controller 1, the cloud server 2, and the remote device 3 is an application MQTT communication protocol.

Here, the message content can be simplified through the application of the MQTT communication protocol, which is very suitable for IoT devices with limited processor resources and network bandwidth, and programmable logic controllers (1), cloud servers (2), and remote devices (3). To ensure smooth and smooth communication between them.

In the first to fourth embodiments of the present invention, the remote device 3 is smart glasses. In the above, the application of the remote device 3 may be more convenient through the application of smart glasses. The remote device 3 provides a new information interaction method so that the virtual world on the screen can be combined and interacted with the real scene without worrying about a problem that is inconvenient to use. Among them, the most important thing is that it can be used very intuitively, thereby reducing the difficulty of starting when the present invention is applied.

Since the description of the above embodiments is not intended to limit the scope of the claims of the present invention, modifications that are consistent with the spirit of the present invention should still fall within the scope of the claims of the present invention.

Claims (7)

An intelligent industrial IoT system 100 utilizing a two-way channel type neural network architecture capable of connecting at least one sensing device 200 and at least one exercise device 300,
The intelligent industrial IoT system 100 comprises at least one programmable logic controller (1), at least one cloud server (2), and at least one remote device (3);
The programmable logic controller (1) includes at least one I/O module (11), at least one communication module (12), a sensing database (13), a motion database (14), an edge computing module (15), and a first Equipped with an MQTT data module 16, the I/O module 11 and the communication module 12 are connected to the corresponding sensing device 200 and the exercise device 300, respectively, and the sensing database ( 13) and the exercise database 14 are connected to the corresponding I/O module 11 and the communication module 12, respectively, and the edge computing module 15 is the sensing database 13 and the exercise database Each connected to (14), the first MQTT data module (16) is connected to the edge computing module (15) and also connected to the cloud server (2) through a network (10);
The cloud server 2 is connected to the programmable logic controller 1 through a network 10, and at least an MQTT agent 21, a big data module 22, a human cloud visual database 23, and a human cloud Equipped with an operation database 24, the MQTT agent 21 is connected to the first MQTT data module 16 through the network 10, the big data module 22 is connected to the MQTT agent 21 Is connected, the human cloud visual database 23 is connected to the human cloud manipulation database 24, and both are connected to the MQTT agent 21 and the big data module 22, respectively, through the network 10 Connected to the remote device 3;
The remote device 3 is connected to the cloud server 2 via a network 10 and at least a human cloud visual interface program 31, a human cloud operation interface program 32, and a second MQTT data module 33 ), and the human cloud visual interface program 31 and the human cloud operation interface program 32 are respectively connected to the second MQTT data module 33, and the second MQTT data module 33 is a network Intelligent industrial object, characterized in that it is connected to the MQTT agent 21 through (10) and is connected to the human cloud visual database 23 and the human cloud operation database 24 through the MQTT agent 21 at the same time. Internet system. The method of claim 1, wherein the edge computing module (15) further comprises an edge computing program (151) and an edge computing database (152), and the edge computing program (151) is the sensing database (13), the exercise database Each connected to (14), and the edge computing database 152 is connected to the edge computing program 151 and the first MQTT data module 16, respectively;
The first MQTT data module 16 further includes a first conversion program 161, a first MQTT database 162, a first subscription program 163, and a first publication program 164, and the first conversion The program 161 is connected to the edge computing database 152, the first MQTT database 162 is connected to the first conversion program 161, and the first subscription program 163 is the first MQTT A database 162 and each connected to the MQTT agent 21, and the first issuing program 164 is connected to the first MQTT database 162 and the MQTT agent 21, respectively;
The big data module 22 further includes a big data computing program 221 and a big data database 222, and the big data computing program 221 is the MQTT agent 21, the big data database 222 And the big data database 222 is connected to the human cloud visual database 23 and the human cloud manipulation database 24, respectively;
The second MQTT data module 33 further includes a second conversion program 331, a second MQTT database 332, a second subscription program 333, and a second issuing program 334, and the second conversion The program 331 is connected to the human cloud visual interface program 31 and the human cloud operation interface program 32, respectively, and the second MQTT database 332 is the second conversion program 331 and the second Respectively connected to a subscription program 333 and the second issuing program 334, the second subscription program 333 is also connected to the MQTT agent 21, and the second issuing program 334 is also connected to the Intelligent industrial Internet of Things system connected to the MQTT agent (21). The intelligent industrial IoT system according to claim 2, wherein the cloud server (2) further comprises at least one of a machine learning module (25) and an artificial intelligence module (26) connectable to the big data module (22). The method of claim 3, wherein the machine learning module (25) further comprises a machine learning analysis computing program (251) and a machine learning database (252), and the machine learning analysis computing program (251) is the big data database (222). ), the machine learning database 252 is connected to the machine learning analysis computing program 251, the human cloud visual database 23, and the human cloud manipulation database 24, respectively;
The artificial intelligence module 26 further includes an artificial intelligence determination computing program 261 and an artificial intelligence database 262, and the artificial intelligence determination computing program 261 is connected to the big data database 222, and the The artificial intelligence database 262 is an intelligent industrial IoT system connected to the artificial intelligence decision computing program 261, the human cloud visual database 23, and the human cloud manipulation database 24, respectively. The machine learning analysis according to claim 4, wherein when the cloud server (2) includes the machine learning module (25) and the artificial intelligence module (26) at the same time, the artificial intelligence determination computing program (261) is connected thereto. An intelligent industrial IoT system connected to the machine learning database 252 so as to be connected to the big data database 222 through a computing program 251. 6. The intelligent industrial IoT system according to claim 5, wherein the communication protocol applied between the programmable logic controller (1), the cloud server (2) and the remote device (3) is an application MQTT communication protocol. 7. The intelligent industrial IoT system according to claim 6, wherein the remote device (3) is smart glasses.

Images