KR20240076492A - Smart factory system that diagnoses conditions using artificial intelligence - Google Patents

Abstract

The present invention relates to a smart factory system that utilizes artificial intelligence to determine the status of process equipment and inspect process equipment with a high probability of failure. It collects data from process equipment installed on multiple assembly lines, and In a smart factory system that diagnoses the condition using artificial intelligence, which predicts the probability of failure using artificial intelligence, data on supply power, power consumption, operation time, temperature, humidity, and location information are collected from the process equipment and , a condition diagnosis unit that predicts the probability of failure by inputting artificial intelligence, and the condition diagnosis unit uses artificial intelligence to collect data on supply power, power consumption, operation time, temperature, humidity, and location information of the process equipment in which the failure occurred. We provide a smart factory system that learns and diagnoses conditions using artificial intelligence.

Description

Smart factory system that diagnoses conditions using artificial intelligence}

The present invention relates to a smart factory system using artificial intelligence. It relates to a smart factory system that uses artificial intelligence to determine the status of process equipment and inspect process equipment with a high probability of failure.

Factories that produce specific products have recently been operated by automated systems. Previously, the automation system of these factories was not connected to an external network and was a closed type operated by configuring an independent network for each factory automation system, but recently, these factory automation systems have been connected to an external network to control and produce There are active attempts to reuse data produced from devices for production and management.

Attempts to connect each device of this factory automation system to a network are being made in the form of industrial IoT (INDUSTRIAL IoT) due to the recent increase in interest in the Internet of Things (INTERNET OF THINGS) and the generalization of technology. This industrial IoT does not just network and automate only factory production facilities, but also involves even detailed parts of the factory system in IoT, enabling automatic control and various management, as well as using various internal and external data for factory operation. It is possible to greatly improve operational efficiency.

In particular, by applying IoT, various devices with various protocols can participate in the system, making it possible to configure an advanced system compared to the automation system used in the past.

The individual facilities that make up a large-scale smart factory interact organically with each other. For example, products pretreated in a pretreatment facility are transferred to the next processing facility during the manufacturing process using a transfer robot. In this connection structure of facilities, if a failure occurs in one facility, the entire manufacturing line including the failed facility must be stopped, so predicting facility failure is very important in the operation of a smart factory.

Typically, manufacturing facilities may have self-diagnosis functions, but as explained above, because a large amount of diverse data is shared inside and outside the smart factory, it is difficult to accurately detect abnormal signals from individual facilities.

As a prior art for smart factory control, there is one in Publication Patent No. 10-2019-0062739 (data analysis method, algorithm, and device for predicting equipment failure in the manufacturing process using multiple sensors, published on June 7, 2019). A technology is described that can predict failure of production equipment by attaching multiple sensors to production equipment and comparing the complex pattern of each sensor with an abnormal complex pattern.

The present invention was proposed to solve the above-mentioned problems, and it is possible to use artificial intelligence to determine the status of process equipment and inspect process equipment with a high probability of failure.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

One aspect of the present invention is a smart factory system that collects data from process equipment installed on a plurality of assembly lines and diagnoses the condition using artificial intelligence, which uses the data to predict the probability of failure, It includes a status diagnosis unit that collects data on supply power, power consumption, operation time, temperature, humidity and location information from the process equipment, and inputs it into artificial intelligence to predict the probability of failure, wherein the status diagnosis unit is configured to predict the probability of failure in the process where the failure occurred. We provide a smart factory system that learns data about the device's power supply, power consumption, operation time, temperature, humidity, and location information using artificial intelligence, and diagnoses the condition using artificial intelligence.

The status diagnosis unit may collect data on power supply, power consumption, operating time, temperature, humidity, and location information during normal operation.

The status diagnosis unit can learn data on supply power, power consumption, operation time, temperature, humidity, and location information of the process equipment corresponding to the normal operating range using artificial intelligence.

After completing learning, the status diagnosis unit inputs operation data (supplied power, power consumption, operation time, temperature, humidity, location information) of the process equipment into the learned artificial intelligence to calculate the probability of failure of the process equipment.

The condition diagnosis unit may send a notification to the user when the failure probability exceeds a predetermined value.

As described above, according to the present invention, artificial intelligence can be used to identify the state of the process equipment and inspect process equipment with a high probability of failure, thereby preventing failure in advance.

As described above, according to the present invention, big data can be effectively transmitted using multiple channels.

Additionally, according to the present invention, it is possible to prevent data errors and accurately analyze data.

Of course, the scope of the present invention is not limited by this effect.

Figure 1 is a block diagram of a smart factory system that diagnoses conditions using artificial intelligence according to an embodiment of the present invention.
Figure 2 is a block diagram of a smart factory system that diagnoses the condition using artificial intelligence according to an embodiment of the present invention.
Figure 3 is a flowchart of a smart factory system that diagnoses the condition using artificial intelligence according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS Various embodiments of the present disclosure are described below in conjunction with the accompanying drawings. Various embodiments of the present disclosure can make various changes and have various embodiments, and specific embodiments are illustrated in the drawings and related detailed descriptions are described. However, this is not intended to limit the various embodiments of the present disclosure to specific embodiments, and should be understood to include all changes and/or equivalents or substitutes included in the spirit and technical scope of the various embodiments of the present disclosure. In connection with the description of the drawings, similar reference numbers have been used for similar components.

Expressions such as “includes” or “may include” that may be used in various embodiments of the present disclosure indicate the presence of the disclosed function, operation, or component, and indicate the presence of one or more additional functions, operations, or components. There are no restrictions on components, etc. In addition, in various embodiments of the present disclosure, terms such as "comprise" or "have" are intended to indicate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification. It should be understood that this does not exclude in advance the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

In various embodiments of the present disclosure, expressions such as “or” include any and all combinations of words listed together. For example, “A or B” may include A, B, or both A and B.

Expressions such as “first,” “second,” “first,” or “second” used in various embodiments of the present disclosure may modify various elements of the various embodiments, but do not limit the elements. No. For example, the above expressions do not limit the order and/or importance of the corresponding components. The above expressions can be used to distinguish one component from another. For example, the first user device and the second user device are both user devices and represent different user devices. For example, a first component may be referred to as a second component, and similarly, the second component may be referred to as a first component without departing from the scope of various embodiments of the present disclosure.

When a component is said to be "connected" or "connected" to another component, it means that the component may be directly connected or connected to the other component, but It should be understood that other new components may exist between the above different components. On the other hand, when a component is said to be "directly connected" or "directly connected" to another component, it will be understood that no new components exist between the component and the other component. You should be able to.

Terms used in the various embodiments of the present disclosure are merely used to describe specific embodiments and are not intended to limit the various embodiments of the present disclosure. Singular expressions include plural expressions unless the context clearly dictates otherwise.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the technical field to which the various embodiments of the present disclosure pertain.

Terms such as those defined in commonly used dictionaries should be interpreted as having meanings consistent with the meanings they have in the context of the related technology, and unless clearly defined in various embodiments of the present disclosure, are not ideal or excessively formal. It is not interpreted as meaning.

Figure 1 is a block diagram schematically showing a network system using multi-channels for big data transmission according to an embodiment of the present invention.

Before explaining the sensor network system according to this embodiment, the smart factory system will be briefly described. The smart factory system includes a data collection system, sensor network system, and smart factory platform.

The data collection system collects data generated in the process. The data collection system 1 can collect data generated in a continuous process in which a plurality of processes are performed continuously. At this time, even within a continuous process, the same process may occur in multiple places. For example, one vehicle assembly line is a continuous process, but usually there are multiple assembly lines. At this time, the assembly line is a continuous process and performs the same process.

The data collection system includes various instruments, sensors, actuators, etc. to collect data generated in the process. The data collection system may further include a P/C, PLC (Programmable Logic Controller), DCS (Distributed Control System), etc. that integrate or control data collected by instruments, sensors, actuators, etc. Hereinafter, components that collect data, such as measuring instruments, sensors, and actuators, are collectively referred to as sensors.

At this time, the sensors may include a first sensor group, a second sensor group, and a third sensor group that each collect data. Of course, it could increase further. For example, various sensors exist in multiple identical processes, and they can be grouped into one group. For example, if there are three assembly lines, there are three frame assembly processes of the same process. At this time, a sensor group exists for each frame assembly process. A first sensor group exists in the first frame assembly process, and a second sensor group exists in the second frame assembly process.

Here, the first sensor group includes various types of sensors such as measuring instruments, sensors, and actuators, and will be described below as including a 1-1 sensor, a 1-2 sensor, and a 1-3 sensor as examples. And, the second sensor group includes the 2-1 sensor, the 2-2 sensor, and the 2-3 sensor, and the third sensor group includes the 3-1 sensor, the 3-2 sensor, and the 3-3 sensor. Includes.

The sensor network system collects data from the data collection system and delivers the collected data to the smart factory platform. The network system may include a USN collector, node, network cable, gateway, router, or wireless access point (AP). The following is done and the collected data is delivered to the smart factory platform. A network system refers to a USN collector, node, network cable, gateway, router, or wireless AP (Access Point) as a sensor node.

Multiple sensor nodes receive data from multiple sensors. For example, the first sensor node is wirelessly/wiredly connected to . That is, one sensor node receives data from multiple sensors.

And, the sensor network system includes a plurality of sensor nodes, such as a first sensor node and a second sensor node. More specifically, the first sensor node receives data from the data collection system. That is, the first sensor node receives data from a plurality of sensors. There may be a plurality of such first sensor nodes. The first sensor node includes a 1-1 sensor node, a 1-2 sensor node, etc.

The sensor network system connects the data collection unit and the smart factory platform and transmits the collected data. At this time, because the data collection unit and the smart factory platform are separated, data is transmitted by a plurality of sensor nodes. That is, the sensor network system includes at least two sensor nodes connected in series or parallel. In this embodiment, the three-stage sensor node is described as an example, but is not limited thereto.

Conventional sensor nodes transmit collected data using one channel out of 16 channels. In order to use artificial intelligence for analysis, sensor nodes need to transmit big data. However, there was a problem that big data could not be processed through a single channel. According to this embodiment, big data can be transmitted through multi-channel communication between sensor nodes.

In more detail, the first sensor node distributes data collected from a plurality of sensor groups and transmits it to the second sensor node using multiple channels. A detailed explanation of this will be given later.

The first sensor node receives data from the data collection unit. At this time, data can be transmitted from at least one sensor group. For example, the 1-1 sensor node receives data from the first sensor group and the second sensor group, and the 1-2 sensor node receives data from the third sensor group and the fourth sensor group.

That is, the first sensor node receives and collects data from a plurality of sensors deployed in the same process. For example, data is collected from a first sensor group disposed in a first frame assembly process among a plurality of assembly lines, and data is collected from a second sensor group disposed in a second frame assembly process.

The first sensor node distributes the collected data through multiple channels and transmits it to the second sensor node.

In more detail, referring to FIG. 2, the 1-1 sensor node collects data from the 1-1 sensor and the 2-1 sensor and transmits it to the second sensor node. At this time, the 1-1 sensor and the 2-1 sensor transmit the same type of data, that is, first data, to the pressure gauge. And the 1-2 sensor and the 2-2 sensor transmit the same type of data, that is, second data, to the thermometer.

The 1-1 sensor node may transmit data collected from the same sensor among the data collected from the first sensor group and the second sensor group to the first channel, and transmit data collected from different types of sensors to the second channel. there is.

At this time, if the number of types of sensors increases, one data cannot be transmitted through one channel. Typically, 4 out of 16 channels can be used for data transmission. If the number of sensor groups exceeds 4, the number of data becomes greater than the number of channels. In other words, the number of types of data collected from a plurality of sensors may exceed the number of available channels.

In this case, the first sensor node can transmit so that the difference in the amount of data transmitted between the plurality of channels is less than 10%. For example, if the amount of data transmitted through the first channel is 1 Mbps, the amount of data transmitted through the second channel can be controlled and transmitted to be 0.9 to 1.1 Mbps.

At this time, the 1-1 sensor node is the 1-1 sensor, the 1-2 sensor, the 1-3 sensor, the 1-4 sensor, the 2-1 sensor, the 2-2 sensor, the 1-4 sensor, etc. Data is transmitted from the 2-3 sensor, 2-4 sensor, etc., and data from the 1-1 sensor, 2-1 sensor, 1-3 sensor, and 2-3 sensor is transmitted to the first channel. data from the 1-2 sensor, 2-2 sensor, 1-4 sensor, and 2-4 sensor can be transmitted to the second channel.

Although the 1-1 sensor node has been described above, the 1-2 sensor node is the same as the 1-1 sensor node, and the 1-3 sensor node (not shown) that can be added is also the same. Therefore, redundant explanations are omitted.

The second sensor node receives data from the first sensor node. As described above, the first sensor node and the second sensor node communicate through multiple channels in order for the smart factory system to later perform analysis using artificial intelligence. That is, the first sensor node and the second sensor node transmit data using multiple channels to transmit/send big data.

And the second sensor node transmits the collected data to the third sensor node through multiple channels. In more detail, the second sensor node transmits the same data to the third sensor node through a plurality of channels.

For example, the second sensor node may transmit data collected from the first sensor node to the third sensor node through four channels. For convenience, the second sensor node is explained as using the first and second channels and the third and fourth channels.

The second sensor node can make the data transmitted through the first and second channels the same as the data transmitted through the third and fourth channels. That is, the second sensor node can duplicate data to prevent incorrect data loss.

The third sensor node can receive data from the second sensor node and transmit it to the smart factory system or to an additional sensor node. At this time, the third sensor node can compare and analyze data received through a plurality of channels, find and supplement erroneous data, and transmit it.

Referring to Figure 3, the smart factory platform receives collected data through a network system. The smart factory platform processes collected data, determines whether there are any abnormalities in equipment or materials based on the processed collected data, and provides inquiry and analysis services for stored data. For this purpose, the smart factory platform includes a status diagnosis unit.

The status diagnosis unit analyzes the data received from the network system and determines the status of the equipment. In more detail, the status diagnosis unit receives data in time series form from the network system. At this time, the condition diagnosis unit receives data about the same type of sensor, so there is no need to separate or reprocess it. Of course, the data is structured to identify equipment or processes, such as the type and location of the sensor.

In the case of facilities or equipment used in the process, there are many cases where failure occurs due to power failure. Therefore, if power abnormality can be detected in advance, failure can be prevented in advance. Additionally, because equipment is sensitive to temperature and humidity, the corresponding information can be used to determine whether or not there is a breakdown in advance. Hereinafter, equipment or equipment is referred to as process equipment. The above-described sensor may be attached to a process device or refer to a process device capable of transmitting data.

Therefore, the status diagnosis unit collects data on the power supplied to the process equipment, the power consumed by the process equipment, the operation time of the process equipment, the temperature of the process equipment, the humidity of the process equipment, and the location information of the process equipment. Here, the temperature of the processing device and the humidity of the processing device may be the temperature/humidity of the processing device itself or the temperature and humidity of the location where the processing device is located. And the location of the process equipment is converted into data by coordinates.

The status diagnosis unit collects data on supply power, power consumption, operating time, temperature, humidity, and location information where the failure occurred.

Separately, the status diagnosis unit collects data on power supply, power consumption, operation time, temperature, humidity, and location information during normal operation.

In addition, the status diagnosis unit uses artificial intelligence to learn data on supply power, power consumption, operation time, temperature, humidity, and location information of the failed process equipment.

In addition, the status diagnosis unit uses artificial intelligence to learn data on supply power, power consumption, operation time, temperature, humidity, and location information of the process equipment within the normal operating range.

Here, artificial intelligence may include deep learning and machine learning technologies. Deep learning is a method of performing machine learning using an artificial neural network (ANN: Artificial Neural Network) with multiple layers. It is also called deep learning and can extract key content from a large amount of data through a combination of several non-linear transformation techniques. It can be said to be a capable learning algorithm.

Machine learning is divided into supervised learning and unsupervised learning. Supervised learning refers to learning data to find output values corresponding to input values, while unsupervised learning uses training data containing only input values to find regularities in input values and outputs the results.

And after completing learning, the status diagnosis unit inputs the operation data (supplied power, power consumption, operation time, temperature, humidity, location information) of the process equipment into the learned artificial intelligence to calculate the probability of failure of the process equipment.

And the status diagnosis unit sends a notification to the user when the failure probability exceeds a predetermined value. Here, the predetermined value may be 70%. Because of this, users can inspect process equipment and prevent malfunctions in advance.

As such, the present invention has been described with reference to the embodiments shown in the drawings, but these are merely illustrative, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. . Therefore, the true scope of technical protection of the present invention should be determined by the technical spirit of the attached claims.

Claims (5)

In a smart factory system that collects data from process equipment installed on multiple assembly lines and diagnoses the condition using artificial intelligence, which uses the data to predict the probability of failure,
It includes a condition diagnosis unit that collects data on supply power, power consumption, operation time, temperature, humidity, and location information from the process equipment, and inputs it into artificial intelligence to predict the probability of failure,
The status diagnosis unit is a smart factory system that diagnoses the status using artificial intelligence, using artificial intelligence to learn data about supply power, power consumption, operation time, temperature, humidity, and location information of the faulty process equipment. . According to claim 1,
The status diagnosis unit is a smart factory system that diagnoses the status using artificial intelligence, collecting data on normally operated power supply, power consumption, operation time, temperature, humidity, and location information. According to claim 2,
The status diagnosis unit uses artificial intelligence to learn data on supply power, power consumption, operation time, temperature, humidity, and location information of the process equipment within the normal operating range, and is a smart device that diagnoses the condition using artificial intelligence. factory system According to claim 3,
The state diagnosis unit uses artificial intelligence to calculate the probability of failure of the process equipment by inputting the operation data (supplied power, power consumption, operation time, temperature, humidity, location information) of the process equipment into the learned artificial intelligence after completing learning. A smart factory system that diagnoses the condition using a smart factory system. According to claim 4,
The status diagnosis unit is a smart factory system that diagnoses the status using artificial intelligence, sending a notification to the user when the failure probability exceeds a predetermined value.