KR20220120456A - Prediction failure diagnosis system for automatic valve using artificial intelligence - Google Patents

Abstract

An edge computing-based artificial intelligence valve failure diagnosis system for a plant automatic-control valve includes: a positioner provided on an automatic valve; a plurality of IIoT sensors provided on the automatic valve; an artificial intelligence valve failure diagnosis unit inferring and analyzing a signal transmitted from the positioner and a signal measured from at least some or all of the plurality of IIoT sensors in real time through an auto-decoder deep learning algorithm to determine the type of a driving abnormality or a failure of the automatic valve; and a management center performing data communication and remote monitoring by using the failure diagnosis unit and an Ethernet internal communication network. The positioner, the IIoT sensors and the failure diagnosis unit are provided on every individual automatic valve. The failure diagnosis unit performs learning and training with data about the normal driving of the automatic valve to calculate a model value, infers data about abnormal driving based on the model value, and determines a situation, in which a restoration error value is greater than a threshold value which is a boundary value between a restoration error maximum value and a restoration error minimum value, as a failure.

Description

Automatic valve's artificial intelligence valve failure prediction diagnosis system {PREDICTION FAILURE DIAGNOSIS SYSTEM FOR AUTOMATIC VALVE USING ARTIFICIAL INTELLIGENCE}

The following description relates to a real-time remote failure prediction diagnosis system and diagnosis method for a plant automatic control valve using artificial intelligence.

Valves for renewable energy power generation (CSP), thermal power, cogeneration and other power generation industries, petrochemical plants are used in harsh conditions (high temperature of 250~800℃, high pressure of 20~300Bar), cryogenic LNG industry, etc. Various valves such as valves, ball valves, and gate valves are used.

However, valves used in such harsh conditions of high temperature and high pressure or cryogenic high pressure suffer from severe mechanical wear, and various failures such as malfunction of the valve and leakage of internal fluid frequently occur, resulting in accidents or when the plant needs to be stopped. There was a risk of deterioration or material/human damage.

In general, in the case of conventional instrumentation and control devices, in order to diagnose the failure of a valve installed in the field, stop or stop the operation of the valve, separate the valve from the pipe by cutting, etc., and operate the separated valve with a specific signal. Analysis and diagnosis were performed in an off-line method of analyzing the operating signal pattern. However, in order to use the existing diagnostic method, there are non-economic aspects such as stopping the process, and there are difficult problems in that the process must be stopped.

The above-mentioned background art is possessed or acquired by the inventor in the process of deriving the disclosure of the present application, and it cannot necessarily be said to be a known technology disclosed to the general public prior to the present application.

An object of the embodiment is to provide an artificial intelligence valve failure prediction diagnosis system installed in a plant automatic control valve to infer and analyze failure of an automatic valve using artificial intelligence.

The problems to be solved in the embodiments 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 following description.

Examples are described. An artificial intelligence valve failure prediction diagnosis system for a plant automatic control valve includes a positioner provided in the automatic valve, a plurality of IIoT sensors provided in the automatic valve, a signal transmitted from the positioner, and at least some or all of the plurality of IIoT sensors An edge-based artificial intelligence valve fault diagnosis device that infers and analyzes the signal measured from the auto decoder in real time using an auto decoder deep learning algorithm to determine and predict the type of abnormal operation or failure of the automatic valve, and the fault diagnosis device and the Ethernet inside and a management center for performing data communication, remote monitoring, and control using a communication network, wherein the positioner, the IIoT sensor, and the fault diagnosis device are provided for each automatic valve, and the fault diagnosis device is operated during normal operation of the automatic valve. The model value is calculated by learning and training using the data of to determine

1 is a diagram illustrating a configuration in which an edge-based artificial intelligence valve failure diagnosis device and an IIoT sensor are installed in an automatic valve according to an embodiment.
FIG. 2 is a view for explaining the configuration, measurement, and monitoring operation of the edge-based artificial intelligence valve failure diagnosis device of FIG. 1 .
3 is a view for explaining the detailed configuration and function of the I/O board.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes may be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all modifications, equivalents and substitutes for the embodiments are included in the scope of the rights.

Terms used in the examples are used for the purpose of description only, and should not be construed as limiting. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present specification, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It is to be understood that this does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

In addition, in the description with reference to the accompanying drawings, the same components are assigned the same reference numerals regardless of the reference numerals, and the overlapping description thereof will be omitted. In the description of the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description thereof will be omitted.

In addition, in describing the components of the embodiment, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only for distinguishing the elements from other elements, and the essence, order, or order of the elements are not limited by the terms. When it is described that a component is “connected”, “coupled” or “connected” to another component, the component may be directly connected or connected to the other component, but between each component another component It will be understood that may also be "connected", "coupled" or "connected".

Components included in one embodiment and components having a common function will be described using the same names in other embodiments. Unless otherwise stated, descriptions described in one embodiment may be applied to other embodiments as well, and detailed descriptions within the overlapping range will be omitted.

Hereinafter, with reference to FIGS. 1 to 3, the failure of the plant automatic valve operated in a harsh environment of high temperature and high pressure (high temperature of ~800 ℃ level and high pressure of 300 Bar level), cryogenic temperature (-270 ℃ level) high pressure is diagnosed and produced An artificial intelligence valve failure prediction diagnosis system and diagnosis method that can keep product quality stable will be described.

1 is a view for explaining the configuration of the fault diagnosis device 130 and the IIoT sensor 120 installed in the automatic valve (10).

Referring to FIG. 1 , a plant automatic control valve (hereinafter, referred to as an 'automatic valve') 10 is installed in a valve body 11 of a globe valve type, an air actuated cylinder 12 . It may be an offset globe bellows valve of a control method using However, the automatic valve 10 is not limited thereto, and the shape, size, actuator type, usage conditions, and application temperature of the valve may be substantially changed in various ways.

In the automatic valve 10, when the stem 13 provided inside the valve body 11 is driven up and down by the cylinder 12, the globe 14 at the bottom of the stem 13 is connected to a pipe for the flow of fluid. The inlet 15 and outlet 16 are opened and closed.

Edge computing-based artificial intelligence valve fault diagnosis device (AI Valve surveillance Manager, hereinafter referred to as 'failure diagnosis device') 130 is the valve body 11 to predict and diagnose the failure of the automatic valve 10. Alternatively, various industrial Internet of Things (IIoT) sensors 120 are installed in the vicinity of the automatic valve 10, and automatically from the measurement results of the IIoT sensor 120 using an auto encoder deep learning algorithm. Infer/analyze the failure of the valve 10 in real time and online.

The fault diagnosis device 130 learns the signal of the normal operation state of the automatic valve 10 from the measurement result of the IIoT sensor 120 with the auto encoder deep learning artificial intelligence algorithm, infers the abnormal signal from the learned result, and when it is normal If the restoration error value is larger than the threshold value, which is the boundary between the maximum restoration error value of , and the minimum restoration error value when abnormal, it is judged as abnormal and the valve failure is determined.

Here, the fault diagnosis device 130 prepares the collected data as several data sets, learns and trains offline by the AI algorithm, and after the learning is completed, the normal operation characteristics of the automatic valve 10 are evaluated. The included model value is calculated, abnormal driving is inferred using the model value, and a threshold value for discriminating between normal driving and abnormal driving is calculated.

In addition, the fault diagnosis device 130 performs data collection and analysis from individual automatic valves 10 based on edge computing, and monitoring and control of the automatic valves 10 are performed automatically and manually in the field.

On the other hand, since the failure data of the automatic valve 10 is very diverse, it is difficult to secure the failure data. However, the failure diagnosis device 130 may detect the abnormal operation of the automatic valve 10 using the model value and the threshold value learned only from the normal operation data, and analyze it in real time and online.

In addition, hundreds or thousands of automatic valves 10 are used very often in plants. A failure diagnosis device 130 is installed in all automatic valves 10 , and in each failure diagnosis device 130 , each automatic valve 10 is installed. The signal from the installed IIoT sensor 120 is input and processed, and only the processed diagnosis result is transmitted.

The fault diagnosis device 130 includes a positioner 110 (including a control signal CT and a feedback signal FD) and a plurality of IIoT sensors 120 for monitoring the operating state of the automatic valve 10 . can be configured.

Here, the fault diagnosis device 130 is mounted on the automatic valve 10 separately from the positioner 110 and the IIoT sensor 120 . By separately forming the failure diagnosis device 130 in this way, it is possible to install without the need to replace or change parts of the existing automatic valve 10, so it can be applied to various types of automatic valves produced by various companies, so compatibility is high. . Of course, the fault diagnosis device 130 may be installed integrally with the positioner 110 .

The positioner 110 is installed in the cylinder 12 of the automatic valve 10 and provides air pressure to the cylinder 12 through the air pressure lines 111 and 112 connected to the upper and lower sides of the cylinder 12 . And the positioner 110 opens and closes the automatic valve 10 by the control signal CT transmitted from the fault diagnosis device 130 .

Here, when the automatic valve 10 operates normally, the feedback signal FD sensed inside the positioner 110 is slightly delayed depending on the position of the automatic valve 10 to achieve approximately the same position as the control signal CT. keep However, when the automatic valve 10 operates abnormally, the feedback signal FD moves incompletely, and a difference occurs between the feedback signal FD and the control signal CT.

The IIoT sensor 120 is installed inside and around the valve body 11 of the automatic valve 10, and includes a plurality of sensors. For example, the IIoT sensor 120 includes a load sensor (or load cell) 121 , an acoustic sensor 122 , temperature sensors 123 and 124 , a flow sensor 125 and a differential pressure ( differential pressure) and a static pressure transducer 126 . Here, the IIoT sensor 120 is not limited thereto, and may include at least any one or more of the above-described sensors according to the conditions to be diagnosed, or other sensors (eg, vibration sensors) other than the above-described sensors. (not shown), limit switches (127, see FIG. 3), etc.), and the number may also be variously changed.

When the load sensor 121 is installed in the middle of the stem 13 , the force applied to the stem 13 is measured. The load sensor 121 may measure a load change due to a mechanical defect when the globe 14 is closed and opened when the automatic valve 10 is opened and closed. In some cases, even when the fluid pressure is changed due to a process change, the load sensor 121 may measure the change in load.

The pressure sensor 126 measures the pressure change between the inlet 15 and the outlet 16 of the automatic valve 10 . For example, the pressure sensor 126 may be a differential pressure sensor that measures the pressure difference between the inlet 15 and the outlet 16 of the automatic valve 10 . Alternatively, the pressure sensor 126 may be a static pressure sensor respectively installed at the inlet 15 and the outlet 16 of the automatic valve 10 .

The pressure sensor 126 may be directly inserted into the piping on the inlet 15 and the outlet 16 side, or may be installed by tubing slightly away from the main piping, and may be installed in a suitable way.

The temperature sensors 123 and 124 are installed on the inlet 15 and outlet 16 sides of the automatic valve 10 .

The acoustic sensor 122 and the flow sensor 125 are installed on the outlet 16 side of the automatic valve 10 and measure the fluid flow and sound level (or vibration level) when the automatic valve 10 is opened and closed. In addition, it is possible to measure and analyze a change according to a Fourier transformation or an octave band in a 100 kHz frequency range of the measured result.

Here, when the automatic valve 10 is in a malfunction state, the opening and closing of the valve is unstable and various fluid flow phenomena occur. A change in noise appears differently, and such a change can be measured from a plurality of IIoT sensors 120 .

The fault diagnosis device 130 may check the operation data of the automatic valve 10 and check the normal/abnormal presence in the field or at an external management center through the Ethernet internal communication network 140 .

Here, the fault diagnosis device 130 may input and process a signal from the IIoT sensor 120 installed in each automatic valve 10 and transmit only the processed diagnosis result to the management center. Alternatively, of course, the data collected from the IIoT sensor 120 through the Ethernet internal communication network 140 may be checked in real time in the management center, or the data may be collected and transmitted to the data server.

Here, since the storage of data is necessary in case of a user's mistake or dispute, it may be stored in the fault diagnosis device 130 itself or in a data server through the Ethernet internal communication network 140 .

2 is a diagram illustrating the detailed configuration and operation of the fault diagnosis device 130 .

Referring to FIG. 2 , the fault diagnosis device 130 may include an I/O board 131 and a micro PC 132 .

The I/O board 131 is provided with a connector 311 connected to the IIoT sensor 120 installed in the automatic valve 10 , and an Ethernet port for transmitting real-time measured data through the Ethernet internal communication network 140 . It may be provided with a WIFI module 313 that communicates with the 312, or to operate and monitor the automatic valve 10 in the field. Alternatively, the I/O board 131 may include only one of the Ethernet port 312 and the WIFI module 313 or both.

The micro PC 132 transmits data from the I/O board 131 using serial communication of UART or RS-232C, and an initialization unit 322 that controls the collection of the transmitted data, and the data may include a buffer 321 that is temporarily collected. And the micro PC 132 is an inference unit (AI interference) 323 for inferring the data collected in the buffer 321 with artificial intelligence, and a web (Web) 324 and a second Ethernet port for data communication ( 325) may be included.

The reasoning unit 323 infers (analyzes) the collected data using the auto-encoder deep learning algorithm to predict a failure or determine whether there is a failure.

The web 324 enables the data collected in the buffer 321 to be monitored in real time, or a result value that is a reconstruction error deduced by the inference unit 323 is monitored.

Meanwhile, the data collected in the buffer 321 may be connected to the hub or switch 141 of the Ethernet internal communication network 140 through the second Ethernet port 325 .

The Ethernet internal communication network 140 is an accessory facility for collecting and analyzing learning data for inference by the fault diagnosis device 20 as big data.

The Ethernet internal communication network 140 transmits data transmitted from the micro PC 132 to an external management center. Here, the management center is connected remotely and wirelessly through the fault diagnosis device 130 and the Ethernet internal communication network 140 , and the central control room 142 , the data server 143 , the web server 144 , and the user of the laptop computer. It may include an app or program installed on the device 145 or the user device 145 . The management center is connected through the fault diagnosis device 130 and the Ethernet internal communication network 140 to check the operation of the automatic valve 10 or store data, and can be remotely monitored and can be a variety of devices that perform control. .

In addition, the Ethernet internal communication network 140 may be configured as a dual network if necessary.

The failure diagnosis device 130 diagnoses the failure of the automatic valve 10 using a deep learning algorithm using an artificial intelligence algorithm, and analyzes (inferences) it with a determination algorithm in real-time to detect failure signs in addition to failure determination. It can predict or even reveal the type of failure. Here, the type of failure may include a behavior and a leak state of the fluid inside the automatic valve 10, and an actuator failure.

For example, the failure diagnosis device 130 may learn and train using the Valve Anomaly Detection Variational Autoencoder. However, this is only an example, and the failure diagnosis device 130 may use various artificial intelligence algorithms as well as auto encoder deep learning algorithms. In addition, as the use time and frequency of plant equipment increases, the component parts deteriorate. By predicting and diagnosing a failure using the failure diagnosis device 130 according to the present embodiment, it is possible to respond quickly, and maintenance costs and failure loss costs can be minimized.

In addition, according to the present embodiment, since the failure diagnosis device 130 predicts and diagnoses a failure in a non-interference type, it is possible to diagnose in real time without stopping the plant, so that it is possible to predict and diagnose the failure safely and quickly. In addition, the failure diagnosis device 130 can accurately predict and diagnose a failure using various IIoT sensors 120 in addition to the positioner 110 .

3 is a view for explaining the detailed configuration and function of the I/O board 131 .

The I/O board 131 is a plurality of devices including a plurality of measurement circuits for collecting signals of the IIoT sensor 120 and a microcontroller 314 for processing and analyzing data, etc. board) can be provided.

The connector 311 of the I/O board 131 may include a plurality of measurement circuits for measuring and collecting signals of the IIoT sensor 120 . The measurement circuit includes a plurality of 4-20 mA measurement circuits 311a that measure signals from the positioner 110 , the pressure sensor 126 and the flow rate sensor 125 , the load sensor 121 , the acoustic sensor 122 , and the vibration A plurality of voltage measuring circuits 311b for measuring signals such as sensors and acceleration sensors, and five several mV measuring circuits 311c for measuring signals from temperature sensors 123 and 124 such as K-type thermocouple sensors, and a limit The switch 127 (refer to FIG. 3 ) may include a plurality of measurement circuits 311d for measuring contact signals. In addition to this, the connector 311 may include various measurement circuits capable of measuring a signal from the IIoT sensor 120 .

The I/O board 131 may include a power supply block 315 that receives power +24V DC and supplies it with +3.3V DC power required for the configuration circuit.

The I/O board 131 may include various output ports 316 in addition to the Ethernet port 312 and the WIFI module 313 . For example, the output port 316 is a port for embedding firmware in the EEPROM, a UART port that can transmit the measured signal and analyzed data to another operation circuit board using serial data communication, an RS-232C port, and It may include a spare port and the like.

The I/O board 131 may be provided with a notification unit 317 to inform whether the device is operating normally. For example, the notification unit 317 may include an LED circuit that emits light so as to know the normal operation of the I/O board 131, and an LED circuit that emits light to know whether Ethernet communication is normally connected. have. In addition to this, the notification unit 317 may include substantially various devices that allow the user to know whether the I/O board 131 and the fault diagnosis device 130 are normally operated.

In addition, the I/O board 131 transmits a part of real-time data to the micro PC 132, or a flash that temporarily stores data in order to check and confirm when the valve is broken due to a user's mistake or error. A memory 318 may also be provided.

In addition, the I/O board 131 includes a microphone, an acceleration and position sensor, a 9-axis gyro sensor, a humidity sensor, a temperature sensor, etc. Health measuring sensors 319 that allow to know the environment, such as surrounding conditions, may be provided on-board.

However, the configuration and arrangement of the I/O board 131 are not limited by the drawings, and the components may be omitted or may be added or changed.

According to the present embodiment, the fault diagnosis device 130 is provided in all automatic valves 10 to measure, collect and analyze the signals of the IIoT sensor 120 installed in each automatic valve 10, and edge computing (edge). Data is collected from the field (ie, individual automatic valve 10) by computing, mFinder; SD), and the management center performs only comprehensive management and control of the data for the diagnosis result transmitted from the fault diagnosis device 130. .

In this way, it is possible to directly or automatically command the control of the automatic valve 10 and the fault diagnosis device 130 in the field, and since it is possible to monitor it wirelessly, it is possible to omit the cable connection between the field and the management center. / It is possible to reduce the cost of installation/commissioning/maintenance, etc. and shorten the construction period. In addition, since data communication is performed using the Ethernet internal communication network 140, the fault diagnosis device 130 is easy to transmit data, and after installation, wiring check is hardly required (only the communication network is checked), and the cost can be reduced. .

And by predicting or diagnosing the failure of the automatic valve 10 in real time, the failure diagnosis device 130 can prevent an accident due to a sudden stop or malfunction of the process, or production disruption due to incorrect quality control. .

As described above, although the embodiments have been described with reference to the limited drawings, those skilled in the art may apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

10: automatic valve
11: valve body
12: cylinder
13: stem
14: Globe
15: Entrance
16: Exit
110: positioner
111, 112: pneumatic line
120: IIoT sensor
121: load sensor
122: acoustic sensor
123, 124: temperature sensor
125; flow sensor
126: pressure sensor
130: AI valve fault diagnosis device
131: I/O board
132: micro pc
140: Ethernet internal network
141: hub
CT: control signal
FD: feedback signal

Claims (18)

a positioner provided in the automatic valve;
a plurality of IIoT sensors provided in the automatic valve;
The signal transmitted from the positioner and the signal measured from at least some or all of the plurality of IIoT sensors are inferred and analyzed in real time using an auto decoder deep learning algorithm to determine and predict the type of abnormal operation or failure of the automatic valve. edge-based artificial intelligence valve fault diagnosis device; and
a management center for performing data communication, remote monitoring and control using the fault diagnosis unit and an Ethernet internal communication network;
including,
The positioner, the IIoT sensor, and the fault diagnosis device are provided for each automatic valve,
The fault diagnosis device calculates a model value by learning and training using data during normal operation of the automatic valve, inferring data during abnormal operation based on the model value, and a boundary between the maximum restoration error value and the minimum restoration error value If the restoration error value is larger than the critical value, it is determined as a failure,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
According to claim 1,
The fault diagnosis device is formed separately from the positioner or is integrally formed with the positioner and can be mounted on the automatic valve,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
According to claim 1,
The fault diagnosis device measures a difference between a control signal transmitted from the fault diagnosis device and a feedback signal generated from the positioner by the operation of the automatic valve,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
According to claim 1,
The IIoT sensor includes a load sensor, an acoustic sensor, a temperature sensor, a flow sensor, and a pressure sensor,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
5. The method of claim 4,
The load sensor is installed on the stem of the automatic valve, and measures the load change due to fluid pressure fluctuations during opening and closing of the automatic valve or process fluctuations,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
5. The method of claim 4,
The pressure sensor includes a differential pressure sensor for measuring pressure fluctuations between the inlet and the outlet of the automatic valve or a static pressure sensor respectively installed at the inlet and outlet of the automatic valve,
The pressure sensor is installed by being directly inserted into the pipe provided at the inlet and the outlet of the automatic valve or installed by tubing from the main pipe,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
5. The method of claim 4,
The temperature sensor is installed at the inlet and outlet of the automatic valve, respectively, to measure the temperature fluctuation between the inlet and the outlet,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
5. The method of claim 4,
The flow sensor is installed at the outlet of the automatic valve to measure the flow state of the fluid flowing through the automatic valve in a frequency range of 100 kHz or a Fourier transform or change for each octave band,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
5. The method of claim 4,
The sound sensor is installed at the outlet of the automatic valve to measure the Fourier transform or octave band change in the sound level at the outlet side of the automatic valve in a 100 kHz frequency range,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
According to claim 1,
The fault diagnosis device includes an I/O board and a micro PC,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
11. The method of claim 10,
The micro PC includes an initialization unit for data communication with the I/O board, a buffer for collecting data, an inference unit that infers and analyzes data with an auto-encoder deep learning algorithm, and a web that enables real-time monitoring of data And, having an Ethernet port connected to the Ethernet internal communication network,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
11. The method of claim 10,
The I/O board includes a connector connected to the plurality of IIoT sensors, an Ethernet port connected to an Ethernet internal communication network, a plurality of measurement circuits for measuring signals from the IIoT sensor, a microcontroller, and a power source for operation including a power block that supplies
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
13. The method of claim 12,
The IIoT sensor includes a load sensor, an acoustic sensor, a temperature sensor, a flow sensor, and a pressure sensor,
The measuring circuit includes a plurality of 4-20 mA measuring circuits connected to the positioner and the pressure sensor and the flow sensor, a plurality of volt measuring circuits connected to the load sensor and the acoustic sensor, the vibration sensor and the acceleration sensor, the temperature 5 several mV measuring circuits connected to the sensor, comprising a measuring circuit measuring a contact signal including a limit switch,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
13. The method of claim 12,
The I/O board includes a notification unit to let you know the normal operation,
The notification unit includes an LED circuit notifying the normal operation of the I/O board, and an LED indicating the normal operation of Ethernet communication,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
13. The method of claim 12,
The I/O board is provided on-board and includes a plurality of health measurement sensors for sealing the case of the fault diagnosis device and measuring the surrounding environment,
The health measurement sensor includes any one or more of a gyro sensor, a humidity sensor, and a temperature sensor for measuring acceleration and position,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
13. The method of claim 12,
The I/O board has a plurality of output ports for outputting or communicating data,
The output port is a port for embedding firmware in EEPROM, a UART port and RS-232C port for serial data communication of measured signals and analyzed data to other operation circuit boards, a spare port, and an Ethernet internal communication network for real-time measured data. comprising any one or more of the Ethernet TCP/IP ports that transmit over;
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
13. The method of claim 12,
The I/O board includes a flash memory that temporarily stores a portion of data,
Automatic valve's artificial intelligence valve failure prediction diagnosis system.
13. The method of claim 12,
The I/O board is equipped with an on-board WIFI module so that each automatic valve can directly monitor and control it.
Automatic valve's artificial intelligence valve failure prediction diagnosis system.

Images