Electronic device for determining operation status of motor drive valve using artificial intelligence, operation method of the same and system

An AI-driven system for motor-driven valves improves failure diagnosis accuracy by processing sensor data, reducing unnecessary replacements and enhancing operational stability.

KR103045778B1Active Publication Date: 2026-11-10CODEVISION INC
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
KR1020230190200
Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2023-12-22
Publication Date
2026-11-10
Estimated Expiration
2043-12-22

AI Technical Summary

Technical Problem

Industrial environments pose challenges in diagnosing equipment failures, particularly in motor-driven valves, due to harsh conditions like high temperatures, vibrations, and chemical exposure, leading to inaccurate repairs and unnecessary replacements, which increase costs and reduce operational stability.

Method used

An electronic device that acquires sensing data from sensors, processes it using an artificial intelligence model, and determines the driving state of motor-driven valves, improving accuracy through training and retraining with synthesized data sets.

Benefits of technology

Enhances the accuracy of diagnosing motor-driven valve states, reducing repair costs and increasing operational stability by detecting anomalies early and performing predictive maintenance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112023144817048-PAT00066_ABST
    Figure 112023144817048-PAT00066_ABST
Patent Text Reader

Abstract

According to various embodiments, the electronic device includes a communication device that acquires a signal from at least one sensor device disposed in a motor-driven valve, a storage device that stores a first fault data set related to the motor-driven valve and a first artificial intelligence model, and at least one processor. The at least one processor can acquire a first sensing data set related to the driving state of the motor-driven valve through at least one sensor device during a specified period, synthesize the first sensing data set and the first fault data set to acquire a first initial learning data set, acquire a first learning data set obtained by converting the first initial learning data set into a multidimensional form, and, based on the first learning data set, train the first artificial intelligence model so that the first artificial intelligence model receives data related to the driving of the motor-driven valve and determines the driving state of the motor-driven valve. In addition to this, various other embodiments identified through the specification are possible.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The various embodiments disclosed in this document relate to an electronic device, a method of operation, and a system for determining the driving state of a motor-driven valve using artificial intelligence. Background Technology

[0002] Various types of equipment are used across diverse industrial sectors. Meanwhile, the stable operation of such equipment directly impacts process efficiency and safety; therefore, assessing the operational safety of this equipment is crucial.

[0003] Examples of various equipment used in these industrial fields include pump systems, compressor systems, generator systems, motor-driven valve systems, rotating equipment, and motor systems. In particular, among these, the motor-driven valve, a type of motor-driven valve system, is a device that opens and closes a valve using an electric motor and is primarily used in various fields such as industrial facilities, power plants, chemical processes, and water treatment systems.

[0004] These motor-driven valves may fail after prolonged use, which can result in unforeseen costs and time losses. For instance, if a motor-driven valve fails to operate properly, it can cause significant damage, including process shutdowns, production stoppages, and losses of manpower and materials. However, due to the nature of the industrial environments where motor-driven valves are used, they involve harsh conditions such as high temperatures, strong vibrations, and chemical exposure, making it difficult to diagnose valve failures. Therefore, considering the difficulty of diagnosis and the potential for damage, motor-driven valves are preventively replaced after a certain period, regardless of whether a failure has occurred. Prior art literature

[65535] Published Patent Application KR 2019-0072165A (June 25, 2019) The problem to be solved

[0005] In industrial environments, various types of equipment are used, but the characteristics of these environments make it difficult to diagnose equipment failures. For example, issues such as high temperatures, strong vibrations, and chemical exposure make it difficult to interpret sensor data acquired during equipment operation, thereby hindering the identification of whether a failure has occurred and its cause.

[0006] Furthermore, while failures in such equipment can be attributed to various causes, identifying these causes is difficult, posing a problem for accurate repair and maintenance. For example, motor-driven valves can fail due to various factors such as electrical issues, mechanical wear, and control system errors, and repairs are challenging because identifying the root cause of these failures is difficult.

[0007] In addition, considering the difficulty of diagnosing such failures and the extent of damage, there is a method of replacing equipment after a certain period regardless of whether it is broken; however, this results in significant cost losses due to unnecessary motor replacements, reduces operational stability of industries and facilities, and causes time consumption due to frequent replacements.

[0008] Accordingly, the present disclosure aims to provide a device that acquires sensing data generated when equipment (e.g., a motor-driven valve) is driven through at least one sensor device, and determines the driving state of the equipment based on the sensing data.

[0009] The present disclosure aims to provide a device that identifies the operating state of equipment (e.g., normal, abnormal, dangerous, failure) and determines the related cause using an artificial intelligence model that determines the operating state of equipment based on sensing data acquired during the operation of the equipment.

[0010] The present disclosure aims to provide a device for further processing sensing data acquired through a sensor device to improve the accuracy of an artificial intelligence model, taking into account the extreme operating environment in which the equipment is operated.

[0011] The present disclosure aims to provide an apparatus that synthesizes sensing data and failure data to generate training data and trains an artificial intelligence model using said training data in order to improve the accuracy of an artificial intelligence model that determines the operating status of equipment.

[0012] The present disclosure aims to provide an apparatus capable of retraining an artificial intelligence model trained to determine the operating status of equipment as needed, and guiding the training of the artificial intelligence model.

[0013] The device of the present disclosure aims to provide a device that can improve the accuracy of determining the operating state and reduce the time required for determination by using training data synthesized from failure data and converting and using data input to an artificial intelligence model.

[0014] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0015] According to various embodiments, the electronic device includes a communication device that acquires a signal from at least one sensor device disposed in a motor-driven valve, a storage device that stores a first fault data set related to the motor-driven valve and a first artificial intelligence model, and at least one processor. The at least one processor can acquire a first sensing data set related to the driving state of the motor-driven valve through at least one sensor device during a specified period, synthesize the first sensing data set and the first fault data set to acquire a first initial learning data set, acquire a first learning data set obtained by converting the first initial learning data set into a multidimensional form, and, based on the first learning data set, train the first artificial intelligence model so that the first artificial intelligence model receives data related to the driving of the motor-driven valve and determines the driving state of the motor-driven valve.

[0016] According to various embodiments, a method of operation of an electronic device for determining the driving state of a motor-driven valve may include: acquiring a first sensing data set related to the driving state of the motor-driven valve through at least one sensor device disposed on the motor-driven valve during a specified period; acquiring a first initial learning data set by synthesizing a first fault data set with the first sensing data set; acquiring a first learning data set obtained by converting the first initial learning data set into a multidimensional form, wherein the first fault data set is fault data related to the motor-driven valve; and training a first artificial intelligence model based on the first learning data set so that the first artificial intelligence model receives data related to the driving of the motor-driven valve and determines the driving state of the motor-driven valve.

[0017] According to various embodiments, a driving state diagnosis system for a motor-driven valve comprises at least one sensor device disposed on the motor-driven valve to acquire sensing information related to the driving of the motor-driven valve, a display device, and a server storing an artificial intelligence model trained to determine the driving state of the motor-driven valve. The server acquires initial sensing data related to the driving of the motor-driven valve acquired through at least one sensor device, acquires diagnostic sensing data converted from the initial sensing data into a multidimensional form, inputs the diagnostic sensing data into an artificial intelligence model to acquire driving state information regarding the driving state of the motor-driven valve, and the artificial intelligence model is trained based on a training data set synthesized from fault data for the motor-driven valve stored in the server and a set of sensing data acquired through the motor-driven valve during a specified period, and transmits the driving state information to the display device, and the display device can display a screen including the driving state information. Effects of the invention

[0018] The electronic device according to the various embodiments disclosed in this document can diagnose faults and perform predictive maintenance by detecting changes in sensing data (e.g., vibration, sound, rotation, temperature, cracks, pressure, etc.) acquired during the operation of specific equipment (e.g., motor-driven valve). Accordingly, repair costs can be reduced and operational stability increased by performing predictive maintenance on specific equipment. For example, by detecting changes in vibration occurring during the operation of a motor-driven valve, an operational anomaly of the motor-driven valve can be detected, and by performing predictive maintenance, the operational stability of the motor-driven valve can be increased and repair costs reduced.

[0019] According to various embodiments, the electronic device can acquire sensing data generated when equipment (e.g., a motor-driven valve) is driven through at least one sensor device, and determine the driving state of the equipment based on the sensing data.

[0020] According to various embodiments, an electronic device can determine the operating state of equipment (e.g., normal, abnormal, dangerous, faulty) and determine the related cause by using an artificial intelligence model that determines the operating state of equipment based on sensing data acquired during the operation of equipment.

[0021] According to various embodiments, the electronic device can accurately determine the operating state even in extreme operating environments where the equipment is operated by further processing sensing data obtained through a sensor device.

[0022] According to various embodiments, an electronic device can synthesize sensing data and failure data to generate training data to increase the accuracy of an artificial intelligence model that determines an operating state, and can train an artificial intelligence model using said training data.

[0023] According to various embodiments, the electronic device can retrain an artificial intelligence model trained to determine the operating state of the equipment and guide the learning of the artificial intelligence model.

[0024] According to various embodiments, the electronic device can improve the accuracy of determining the operating state and reduce the time required for determination by using training data synthesized from failure data and converting and using data input to an artificial intelligence model.

[0025] In addition, various effects that can be identified directly or indirectly through this document may be provided. Brief explanation of the drawing

[0026] FIG. 1 is a block diagram of a driving state determination system for determining the driving state of a motor-driven valve according to various embodiments. Figure 2 is a block diagram of an electronic device for determining the driving state of a motor-driven valve. Figure 3 illustrates a concept for controlling functions related to determining the operating state of an electronic device. FIG. 4 is a flowchart illustrating a method for generating an artificial intelligence model trained so that an electronic device determines the driving state of a motor-driven valve. Figure 5 is a diagram illustrating a training data set for training an artificial intelligence model. FIG. 6 is a diagram illustrating an electronic device acquiring a training data set based on an initial training data set. Figure 7 is a flowchart illustrating the operation of an electronic device training an artificial intelligence model based on label data. FIG. 8 is a flowchart illustrating the operation of an electronic device acquiring a label data set. FIG. 9 is a diagram illustrating an electronic device acquiring a label data set. FIG. 10 is a diagram illustrating the acquisition of driving state information regarding the driving state of a motor-driven valve using an artificial intelligence model. Figure 11 is a flowchart illustrating the operation of an electronic device retraining an artificial intelligence model based on the size of the failure data. FIG. 12 is a flowchart illustrating the operation of an electronic device retraining an artificial intelligence model according to the driving period of a motor-driven valve. FIG. 13 is a flowchart showing the operation of devices within a system for determining the driving state of a motor-driven valve. FIG. 14 shows a user interface output through a display device. In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Specific details for implementing the invention

[0027] Specific structural or functional descriptions regarding various embodiments are illustrative for the purpose of explaining various embodiments, and various embodiments may be implemented in various forms and should not be interpreted as being limited to the embodiments described in this specification or application.

[0028] Since various embodiments may be subject to various modifications and may take various forms, various embodiments are illustrated in the drawings and described in detail in this specification or application. However, the details disclosed in the drawings are not intended to specify or limit the various embodiments, and should be understood to include all modifications, equivalents, and substitutions that fall within the spirit and technical scope of the various embodiments.

[0029] Terms such as "first" and / or "second" may be used to describe various components, but said components shall not be limited by said terms. For the sole purpose of distinguishing one component from another, for example, without departing from the scope of rights according to the concept of the present disclosure, the first component may be named the second component, and similarly, the second component may be named the first component.

[0030] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. Conversely, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions describing the relationship between components, such as "between" and "exactly between," or "adjacent to" and "directly adjacent to," should be interpreted in the same way.

[0031] The terms used herein are used merely to describe specific embodiments and are not intended to limit various embodiments. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as “comprising” or “having” are intended to specify the existence of the described features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0032] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which this disclosure pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.

[0033] The present disclosure will be described in detail below by explaining preferred embodiments of the present disclosure with reference to the attached drawings. Identical reference numerals in each drawing indicate identical components.

[0035] FIG. 1 is a block diagram of a driving state determination system for determining the driving state of a motor-driven valve according to various embodiments.

[0036] Referring to FIG. 1, a drive state determination system for determining the drive state of a motor-driven valve is illustrated. According to various embodiments, the drive state determination system may include an electronic device (100), at least one sensor device (110), and a display device (120). However, the drive state determination system may be implemented to include more devices or / or fewer devices, not limited to the described and / or illustrated examples. Additionally, at least two of the devices illustrated in the drive state determination system may be implemented as a single device.

[0037] Meanwhile, the driving state determination system disclosed in this document is described as being for determining the driving state of a motor-driven valve. However, this is merely for the convenience of explanation, and the system may be applied to determine the driving state of various equipment that operates in the same or similar manner as a motor-driven valve.

[0038] According to various embodiments, the electronic device (100), the sensor device (110), and the display device (120) may be connected electrically, mechanically, or via wired or wireless communication. According to various embodiments, the electronic device (100), the sensor device (110), and the display device (120) may be connected indirectly. For example, the electronic device (100) may obtain sensing data obtained through the sensor device (110) via a data linkage device (e.g., a data linkage module, a hub device).

[0039] According to various embodiments, the electronic device (100) can determine the operating state of the motor-driven valve based on sensing data obtained through the sensor device (120) in relation to the operation of the motor-driven valve. For example, the electronic device (100) can determine whether the motor-driven valve is in a normal state, an abnormal operating state, or an operating risk state based on sensing data related to the operation of the motor-driven valve obtained through the sensor device (120). Accordingly, the electronic device (100) can diagnose a failure of the motor-driven valve.

[0040] According to various embodiments, the electronic device (100) may use an artificial intelligence model to determine the operating state of a motor-driven valve. For example, the electronic device (100) may acquire an artificial intelligence model trained to determine the operating state based on sensing data related to the operation of the motor-driven valve, and may determine the operating state of the motor-driven valve using the artificial intelligence model. For example, the electronic device (100) may acquire a training data set by processing first sensing data and fault data acquired during the operation of the motor-driven valve, and may generate an artificial intelligence model trained to determine the operating state of the motor-driven valve based on the training data set. Additionally, the electronic device may acquire diagnostic data by processing sensing data acquired during the operation of the motor-driven valve, and acquire information regarding the operating state by inputting the diagnostic data into the artificial intelligence model.

[0041] According to various embodiments, the electronic device (100) may receive a request to learn the artificial intelligence model, a request to relearn the artificial intelligence model, and / or a request to determine the operating state using the artificial intelligence model. In various embodiments, the electronic device (100) may provide a function corresponding to the request based on receiving the request. The request may be received through an input device (e.g., a touch panel of a display device (120)) connected to the electronic device (100). Accordingly, the operating state determination system may additionally include an input device or an output device, not limited to the devices shown in FIG. 1.

[0042] According to various embodiments, the sensor device (110) may represent a sensor configured to acquire a signal related to the driving state of a motor-driven valve. Although the sensor device (110) is described as a single device for convenience of explanation, it may be composed of a plurality of sensor devices (110) or may be composed of a single sensor device (110) including a plurality of sensors. For example, the sensor device (110) may include at least one of a vibration measuring sensor, an acoustic measuring sensor, a rotational speed measuring sensor, a temperature sensing sensor, a crack sensing sensor, or a pressure sensing sensor for measuring vibration of the motor-driven valve. Specifically, it may include an accelerometer, a speedometer, a pi-conductivity sensor, a laser vibration sensor, a gyroscope, etc., for measuring vibration. Specifically, as a sensor for measuring acoustics, it may include an acoustic sensor, a wave sensor, a sound pressure sensor, a microphone, etc. Specifically, as a sensor for measuring rotational speed, it may include an encoder, a magnetic sensing sensor, a light sensing sensor, an electronic accelerometer, etc. Specifically, sensors for measuring heat may include infrared thermal imaging cameras, infrared temperature sensors, thermocouples, thermal phone sensors, thermometers, etc. Specifically, sensors for detecting cracks may include stress gauges, ultrasonic sensors, current sensors, vibration sensors, etc. Specifically, sensors for measuring pressure may include pressure sensors, stress gauges, fluid pressure sensors, pressure transmitters, etc.

[0043] According to various embodiments, the sensor device (120) is provided (e.g., in contact, mounted, attached, etc.) in association with equipment (e.g., motor-driven valve) to determine the operating state, so as to acquire sensing data during the operation of the motor-driven valve. According to one embodiment, the sensor device (110) can acquire information regarding vibration, sound, rotation, temperature, cracks, pressure, etc. occurring during the operation of the motor-driven valve. In addition, the sensor device (110) can acquire various sensing data that can be acquired during the operation of the motor-driven valve through various sensors, not limited to the examples listed above.

[0044] According to various embodiments, the sensor device (110) can transmit the acquired sensing data to the electronic device (100). For example, the sensor device (110) can transmit the acquired sensing data to the electronic device (100) by establishing a direct (e.g., wired) communication channel or a wireless communication channel.

[0045] According to various embodiments, the sensor device (110) can store various sensing data acquired during the operation of the motor-driven valve. For example, the sensor device (110) can accumulate and store sensing data acquired by providing it to equipment of the same type. Accordingly, the sensor device (110) provided sequentially to a plurality of motor-driven valves can store sensing data for the plurality of motor-driven valves. At this time, the sensor device (110) can identify each of the plurality of motor-driven valves and store the sensing data. The electronic device (100) can utilize the sensing data acquired through the sensor device (110) to train an artificial intelligence model for determining the operation status of the motor-driven valve.

[0046] According to various embodiments, the display device (120) may visually provide information to an external party (e.g., a user). For example, the display device (120) may display various content (e.g., text, images, videos, icons, and / or symbols). According to various embodiments, the display device (120) may include a display. For example, the display device (120) may include a liquid crystal display (LCD), a light-emitting diode (LED) display, or an organic light-emitting diode (OLED) display.

[0047] According to various embodiments, the display device (120) can display various information obtained from the electronic device (100). For example, the display device (120) can obtain driving status information of a motor-driven valve from the electronic device (100) and output a visual object (e.g., a screen displaying driving status information) that includes said driving status information. For example, the electronic device (100) can provide through the display device (120) a screen related to the learning of said artificial intelligence model, a screen related to the retraining of said artificial intelligence model, and / or a screen related to determining the driving status using said artificial intelligence model.

[0048] According to one embodiment, the electronic device (100) can provide driving status information of equipment (e.g., a motor-driven valve) in which the at least one sensor device (110) is placed through a display device (120). For example, the electronic device (100) can transmit driving status information to the display device (120) so that the display device (120) displays a screen containing driving status information.

[0049] According to various embodiments, information obtained by various functions provided by the electronic device (100) may be provided to the user through a display device (120). However, not limited to the examples described above, information obtained by various functions provided by the electronic device (100) may be provided to the user through another output device (e.g., a speaker). To this end, the electronic device (100) may be connected to various devices without being limited to the type of device.

[0050] According to various embodiments, the display device (120) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by a touch. According to various embodiments, the display device (120) may display an execution screen and obtain user touch input for the execution screen using at least one of the touch sensor or the pressure sensor. For example, the display device (120) may display an execution screen that guides a request for learning of an artificial intelligence model for determining the driving state of a motor-driven valve, a request for retraining of the artificial intelligence model, and / or a request for determining the driving state using the artificial intelligence model, and obtain user input for the screen. In various embodiments, the display device (120) may transmit the user input to an electronic device (100).

[0051] According to various embodiments, the electronic device (100) and the display device (120) may be implemented as a single device. In this case, the electronic device (100) can control the display device (120) through the processor to display an execution screen. An example of a case in which the electronic device (100) includes the display device (120) is described later with reference to FIG. 2.

[0052] According to various embodiments, the display device (120) may refer to various devices including a display. For example, it may include a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a camera, or a wearable device. The display device (120) according to the embodiments of this document is not limited to the aforementioned devices.

[0053] According to various embodiments, the electronic device (100), sensor device (110), and / or display device (120) may include an interface (not shown). In one embodiment, the interface may support one or more specified protocols that can be used to connect the electronic device (100), sensor device (110), and / or display device (120) directly or wirelessly with an external electronic device (e.g., electronic device (100), sensor device (110), and / or display device (120)). According to one embodiment, the interface may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0055] Figure 2 is a block diagram of an electronic device for determining the driving state of a motor-driven valve.

[0056] Referring to FIG. 2, the electronic device (100) may include a processor (210), a storage device (220), a communication device (230), and / or a display (240) (e.g., the display device (120) of FIG. 1). The listed components may be operatively or electrically connected to each other. The components of the electronic device (100) shown in FIG. 2 may be partially modified, deleted, or added, as an example.

[0057] According to various embodiments, the electronic device (100) may include a processor (210). The processor (210) may include hardware for executing instructions, such as instructions that constitute a computer program. For example, to execute instructions, the processor (210) may retrieve (or fetch) instructions from an internal register, an internal cache, a storage device (220) (including memory), decode and execute the instructions, and then store the result in the internal register, the internal cache, and the storage device (220).

[0058] In various embodiments, the processor (210) can execute software (e.g., a computer program) to control at least one other component (e.g., a hardware or software component) of the electronic device (100) connected to the processor (210) and can perform various data processing or operations. According to various embodiments, as at least part of the data processing or operations, the processor (210) can store instructions or data received from another component (e.g., a communication device (230)) in volatile memory, process the instructions or data stored in volatile memory, and store the resulting data in non-volatile memory.

[0059] According to various embodiments, the processor (210) may include at least one of a central processing unit (CPU), a graphics processing unit (GPU), a microcontroller unit (MCU), a sensor hub, a supplementary processor, a communication processor, an application processor, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a Neural Processing Unit (NPU), and may have multiple cores.

[0060] According to various embodiments, the processor (210) (e.g., a neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers. The artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), deep Q-networks, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0061] According to various embodiments, the processor (210) can acquire various sensing data of a target device (e.g., a motor-driven valve) through at least one sensor device (e.g., the sensor device (110) of FIG. 1). For example, the processor (210) can acquire sensing data acquired during the operation of the motor-driven valve through at least one sensor device. The sensing data may include at least one of vibration, sound, rotational speed, temperature, crack, and pressure occurring during the operation of the target device (e.g., the motor-driven valve).

[0062] According to various embodiments, the processor (210) can determine the operating state of a target device (e.g., a motor-driven valve) using the sensing data. In this case, the processor (210) may use an artificial intelligence model trained to determine the operating state of the motor-driven valve. In this case, the processor (210) may use a training data set converted from the sensing data to train the artificial intelligence model. Additionally, diagnostic data converted from the sensing data may be used while determining the operating state using the artificial intelligence model.

[0063] Specifically, according to various embodiments, the processor (210) can acquire a first set of sensing data related to the driving state of a motor-driven valve through at least one sensor device (e.g., sensor device (110)) placed in relation to the equipment (e.g., motor-driven valve). For example, the processor (210) can acquire sensing data acquired over a certain period (e.g., 4 weeks) from the day the motor-driven valve is installed.

[0064] According to various embodiments, the processor (210) may obtain a first initial learning data set by synthesizing a first failure data set and a first sensing data set for the corresponding equipment stored in a storage device (220). Additionally, the processor (210) may obtain a first learning data set by converting the first initial learning data set into a multidimensional form. According to various embodiments, the process by which the processor (210) obtains failure data is described in detail below with reference to FIGS. 4 through 6.

[0065] Specifically, according to various embodiments, the processor (210) may obtain a first learning data set that has been converted into a multidimensional first learning data set. For example, the processor (210) may obtain a first learning data set that has been converted into two-dimensional information (e.g., a two-dimensional graph) of the first learning data set. For example, the processor (210) may obtain a first learning data set by converting the first learning data set through at least one of a Fourier transform, a Wavelet transform, a Wavelet spectrogram, and Mel-Frequency Cepstral Coefficients (MFCC), respectively. According to various embodiments, the processor (210) may not use the first learning data set as is, but convert it into a multidimensional first learning data set and use it, thereby clearly visualizing the characteristics of the data and increasing the accuracy of determining the driving state.

[0066] Additionally, the processor (210) can train the first artificial intelligence model based on the first learning data set to receive data related to the operation of the equipment (e.g., motor-driven valve) and determine the operation state of the equipment (e.g., motor-driven valve). For example, the processor (210) can control the artificial intelligence model to learn patterns of sensing data according to the type of operation state of the motor-driven valve through various learning methods such as supervised learning, unsupervised learning, reinforcement learning, self-directed learning, transfer learning, set learning, and / or neural network transfer learning.

[0067] According to various embodiments, the processor (210) may acquire various second sensing data generated during the operation of the equipment through at least one sensor device (110), and based on the second sensing data, may acquire information on the operation status of the equipment through a first artificial intelligence model. At this time, the processor (210) may generate diagnostic data by converting the second sensing data into a multidimensional form and may acquire information on the operation status by inputting the diagnostic data into the first artificial intelligence model. According to various embodiments, the processor (210) may also acquire the second sensing data by converting it into multidimensional diagnostic data through at least one conversion method among Fourier transform, Wavelet transform, Wavelet spectrogram, and Mel-Frequency Cepstral Coefficients (MFCC).

[0068] According to various embodiments, the processor (210) can control the display device (120) to output the operating status information of the equipment obtained through the first artificial intelligence model. An example of a screen related to the processor (210) providing a function to determine the operating status of the equipment through the display device (120) is described later with reference to FIG. 14.

[0069] According to various embodiments, the electronic device (100) may include a storage device (220). According to various embodiments, the storage device (220) may include a mass storage for data or commands. For example, the storage device (220) may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, an optical-magnetic disk, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. In various embodiments, the storage device (220) may include a non-volatile, solid-state memory, or read-only memory (ROM). Such ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically changeable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0070] Although the present disclosure describes and represents a specific storage device, the present disclosure considers any suitable storage device, and the storage device (220) may be inside or outside the electronic device (100).

[0071] According to various embodiments, the processor (210) may store a module in the storage device (220) that provides a function related to determining the driving state of the target equipment (e.g., motor-driven valve) described with reference to FIG. 3.

[0072] According to various embodiments, the processor (210) may execute operations or data processing regarding the control and / or communication of at least one other component of the electronic device (200) using instructions stored in the storage device (220). According to various embodiments, the storage device (220) may store various data used by at least one component of the electronic device (200) (e.g., the processor (210)). The data may include, for example, software (e.g., a program) and input data or output data for related instructions.

[0073] According to various embodiments, the program may be stored as software in the storage device (220) and may include, for example, an operating system, middleware, or an application. According to various embodiments, the storage device (220) may store instructions that allow the processor (210) to process data or control components of the electronic device (200) to perform operations of the electronic device (200) at execution. The instructions may include code generated by a compiler or code that can be executed by an interpreter.

[0074] According to various embodiments, the storage device (220) can store various information obtained through the processor (210). For example, the storage device (220) can store sensing data of a target device (e.g., a motor-driven valve) obtained from at least one sensor device (110). Additionally, the storage device (220) can store various artificial intelligence models. For example, the storage device (220) can store an artificial intelligence model that is learned and generated by the processor (210). Thus, the storage device (220) can store the first artificial intelligence model that is learned by the processor (210) to determine the driving state of the motor-driven valve. Furthermore, the storage device (220) can store information processed by the processor (210), such as sensing data obtained through the processor (210), a learning data set and a label data set for training the artificial intelligence model, and a failure data set related to the driving of the motor-driven valve. Additionally, the storage device (220) can store information output from the artificial intelligence model. For example, the storage device (220) can store driving status information of a motor-driven valve obtained from the artificial intelligence model.

[0075] According to various embodiments, the electronic device (100) may include a communication device (230). In various embodiments, the communication device (230) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (200) and an external electronic device (e.g., sensor device (110), display device (120) of FIG. 1), and the performance of communication through the established communication channel. The communication device (230) may include one or more communication processors that operate independently of the processor (210) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication device (230) may include a wireless communication module (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device through a first network (e.g., the network (104) of FIG. 1) (e.g., a short-range communication network such as Bluetooth, WiFi Direct (wireless fidelity direct) or IrDA (infrared data association)) or a second network (e.g., the network (104) of FIG. 1) (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., the network (104) of FIG. 1)) (e.g., a LAN or WAN). The various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips).

[0076] According to various embodiments, the electronic device (100) can transmit and receive various data with various external devices through the communication device (230). Additionally, the electronic device (100) can store the acquired data in the storage device (220). For example, the electronic device (100) can acquire sensing data of a target device (e.g., motor-driven valve) from the sensor device (110) through the communication device (230). Additionally, for example, the electronic device (100) can acquire user input related to determining the driving state through the communication device (230). Additionally, for example, the electronic device (100) can transmit various control signals to the display device (120) through the communication device (230) to display an execution screen related to training an artificial intelligence model to determine the driving state of the target device (e.g., motor-driven valve), an execution screen including driving state information of the target device, and an execution screen related to retraining the artificial intelligence model.

[0077] According to various embodiments, the electronic device (100) may include a display (240). That is, the electronic device (100) may be connected to an external display device (120) to control the display of an execution screen, but may also include a display (240). In the present disclosure, screens displayed by the display device (120) may also be displayed through the display (240).

[0078] According to various embodiments, the display (240) includes a structure similar to the display device (120) described above and can perform a similar function.

[0079] According to various embodiments, the electronic device (100) may include various components in addition to the components shown in FIG. 2.

[0080] According to various embodiments, the electronic device (100) may include an input module (not shown). The input module may receive commands or data to be used for a component of the electronic device (100) (e.g., processor (210)) from outside the electronic device (100) (e.g., user). The input module may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0082] Figure 3 illustrates a concept for controlling functions related to determining the operating state of an electronic device.

[0083] Referring to FIG. 3, the electronic device (200) may utilize hardware and / or software modules (300) to support functions related to the operation diagnosis of equipment (e.g., motor-driven valve), including the operation status of the equipment. For example, the processor (210) may drive at least one of a data acquisition module (310), an artificial intelligence learning module (320), a data processing module (330), an operation status determination module (340), and a data output module (350) by executing instructions stored in a storage device (220). In various embodiments, software modules different from those shown in FIG. 3 may be implemented. For example, at least two modules may be integrated into one module, or one module may be divided into two or more modules. Additionally, work performance may be improved by the hardware and software modules sharing a single function. For example, the electronic device (100) may include both an encoder implemented in hardware and an encoder implemented in a software module, and some of the data acquired through at least one camera module may be processed in the hardware encoder and the rest in the software encoder.

[0084] Hereinafter, for convenience of explanation, the present disclosure describes the case where the equipment is a motor-driven valve. However, the present disclosure is not limited to the examples described herein, and the operating state can be determined for various types of equipment through similar functions.

[0085] According to various embodiments, the data acquisition module (310) may include a module that provides various functions for acquiring sensing data related to the operation of the motor-driven valve. In one embodiment, the data acquisition module (310) may acquire information necessary to determine the operation status of the motor-driven valve from an external device (e.g., a sensor device (110)). For example, the data acquisition module (310) may acquire sensing data acquired during the operation of the motor-driven valve from the sensor device (110). For example, the data acquisition module (310) may acquire sensing data including information regarding vibration, sound, rotation, temperature, cracks, pressure, etc., generated during the operation of the motor-driven valve acquired through the sensor device (120). According to various embodiments, the data acquisition module (310) may acquire each of the sensing data for a plurality of motor-driven valves and identification data of the motor-driven valve for distinguishing said sensing data. Additionally, the data acquisition module (310) can acquire a set of sensing data from the sensor device (110) during the period in which it is deployed and operated in an industrial environment for motor-driven valves.

[0086] Additionally, according to various embodiments, the data acquisition module (310) can acquire fault data related to the operation of the motor-driven valve. For example, the data acquisition module (310) can acquire fault data based on at least one of the following: sensing data acquired when the motor-driven valve is opened beyond a specified range; sensing data acquired when the driving power of the motor-driven valve is below a specified size; sensing data acquired when the external environment of the location where the motor-driven valve is placed is unstable; and / or sensing data acquired by generating noise around the location where the motor-driven valve is placed. According to one embodiment, the data acquisition module (310) can acquire fault data stored in the storage device (220). Alternatively, the data acquisition module (310) can acquire fault data through the sensor device (110).

[0087] According to various embodiments, the data acquisition module (310) can provide a user with a UI (User interface) / GUI (graphical UI) related to determining the driving state (diagnosing a motor-driven valve fault) through a display device (120) and acquire user input through the display device (120). For example, user input provided through the UI / GUI output through the display device of the user device (120) can be acquired through the data acquisition module (310). At this time, the UI / GUI displayed through the display device (120) may include a request for training of an artificial intelligence model for analyzing the driving state, a request for retraining of the artificial intelligence model and / or a notification of an abnormal driving event of the motor-driven valve using the artificial intelligence model, and an execution screen that guides the user to request a determination of the driving state of the motor-driven valve.

[0088] According to various embodiments, the artificial intelligence learning module (320) may include a module that provides various functions for training an artificial intelligence model to output information related to the driving state of the motor-driven valve based on sensing data of the motor-driven valve. For example, the artificial intelligence learning module (320) may train an artificial intelligence model to determine the driving state of the motor-driven valve using sensing data of the motor-driven valve obtained through the data acquisition module (310). For example, the artificial intelligence learning module (320) may train an artificial intelligence model to determine the driving state of the motor-driven valve based on fault data and sensing data obtained through the data acquisition module (310).

[0089] According to various embodiments, the artificial intelligence learning module (320) may provide a function to train an artificial intelligence model in conjunction with the data processing module (330). For example, the artificial intelligence learning module (320) may train an artificial intelligence model to determine the driving state of a motor-driven valve based on data processed through the data processing module (330).

[0090] According to various embodiments, the data processing module (330) may provide data processing functions necessary for providing functions related to determining the driving state of the motor-driven valve of the electronic device (100). For example, the data processing module (330) may acquire initial training data by synthesizing a sensing data set and a failure data set acquired during a specified period through the data acquisition module (310). For example, the data processing module (330) may generate training data by synthesizing signals included in each of the sensing data set and the failure data set through various methods such as linear combination, synthesis through Fourier transform, filtering, and adjustment.

[0091] According to various embodiments, the electronic device (100) can generate an artificial intelligence model that diagnoses the driving state of a motor-driven valve more accurately by training the artificial intelligence model using learning data in which fault data is synthesized through a data processing module (330), rather than using the sensing data obtained through the sensor device (110) as is.

[0092] According to various embodiments, the data processing module (330) can generate a training data set by converting an initial training data set, created by synthesizing the sensing data set and the failure data set, into a multidimensional (e.g., a two-dimensional image). The electronic device (100) can diagnose the driving state of the motor-driven valve more accurately than when using one-dimensional data by training an artificial intelligence model using the training data set converted into a multidimensional dimension through the data processing module (330).

[0093] Additionally, the data processing module (330) can generate diagnostic data by processing the sensing data for diagnosing the driving state of the motor-driven valve into multiple dimensions. For example, the electronic device (100) can acquire sensing data for diagnosing the driving state of the motor-driven valve through the data acquisition module (310), and acquire diagnostic data converted into multiple dimensions through the data processing module (330). By using the diagnostic data converted into multiple dimensions to determine the driving state of the motor-driven valve, the electronic device (100) can determine the driving state of the motor-driven valve with higher accuracy.

[0094] According to various embodiments, the artificial intelligence learning module (320) can train an artificial intelligence model using the training data set processed through the data processing module (330). At this time, the artificial intelligence learning module (320) may acquire a label data set in which data within the training data set is labeled based on the classification of the driving state of the motor-driven valve, and provide a function to train the artificial intelligence model based on the label data set. According to various embodiments, an artificial intelligence model trained to determine (or diagnose faults) the driving state of the motor-driven valve can be generated through the artificial intelligence learning module (320). At this time, the artificial intelligence model may be trained to determine the driving state by learning the pattern between the normal operating state and the fault state of the motor-driven valve. The pattern may include a pattern regarding the cause of the fault of the motor-driven valve's fault state.

[0095] According to various embodiments, the driving state classification may refer to a classification based on the driving state of the motor-driven valve. For example, it may include a normal driving state, an abnormal driving state, and a dangerous driving state of the motor-driven valve. In this case, the abnormal driving state or the dangerous driving state may be classified as a failure state of the motor-driven valve. In this case, the artificial intelligence model may classify the cause of the failure while classifying the failure state of the motor-driven valve. For convenience of explanation, the driving state classification is described as having three types, but it may be classified into multiple states. Accordingly, the type of label data (e.g., third label data, etc.) may also be changed. For example, the driving state classification of the motor-driven valve may include various states such as a normal driving state, a fluctuating driving state, a caution state (e.g., an abnormal driving state or a dangerous driving state), a stopped state, a state under inspection, and a communication abnormal state.

[0096] According to various embodiments, the artificial intelligence learning module (320) may acquire the label data through various methods. For example, the artificial intelligence learning module (320) may acquire a label data set by labeling the learning data set according to a preset standard. According to various embodiments, the artificial intelligence learning module (320) may acquire the label data by linking with the data acquisition module (310) and / or the data output module (350). For example, the display device (120) may display a learning guide screen related to data learning through the data output module (350), and the label data set may be acquired through the data acquisition module (310). That is, the artificial intelligence learning module (320) may acquire the label data set based on user input. According to various embodiments, the operation of acquiring the label data set is described later with reference to FIGS. 7 to 9.

[0097] According to various embodiments, the driving state determination module (340) may provide a function to determine the driving state based on sensing data of the motor-driven valve obtained from the data acquisition module (310). For example, the driving state determination module (340) may determine the driving state of the motor-driven valve based on sensing data of the motor-driven valve obtained in conjunction with the data acquisition module (310). At this time, the driving state determination module (340) may not use the sensing data obtained from the data acquisition module (310) as is, but may process it into multiple dimensions using the data processing module (330) and use it.

[0098] At this time, the data processing module (330) can obtain diagnostic data that has been converted into multiple dimensions of the sensing data. For example, the data processing module (330) can obtain diagnostic data that has been converted into two-dimensional information (e.g., a two-dimensional graph) of sensing data including time-based sensing signals (e.g., vibration, sound, heat, pressure, rotational speed, etc.).

[0099] According to various embodiments, the driving state determination module (340) can determine the driving state of the motor-driven valve using diagnostic data obtained through the data processing module (330). For example, the driving state determination module (340) can obtain driving state information by inputting the diagnostic data into the artificial intelligence model obtained through the artificial intelligence learning module (320).

[0100] According to various embodiments, the driving state information may be information related to the driving state of the motor-driven valve. For example, the driving state determination module (340) may use the artificial intelligence model to obtain driving state information indicating whether the driving state of the motor-driven valve is in a normal state, whether it is in an abnormal driving state, or whether it is in a dangerous driving state. At this time, the driving state information may also include information regarding the cause of the dangerous driving or abnormal driving. For example, the driving state information may include information regarding various causes, such as whether the abnormal driving and / or dangerous driving occurred because the motor-driven valve is open beyond a specified range, whether it occurred because foreign matter is stuck in the motor-driven valve, whether it occurred due to an abnormal driving power supply of the motor-driven valve, whether it occurred because the external environment in which the motor-driven valve is placed is unstable (e.g., abnormal vibration, abnormal temperature, abnormal pressure, etc.), or whether it is due to aging of internal parts of the motor-driven valve.

[0101] According to various embodiments, the data output module (350) may include a module that provides a function of outputting various data obtained by driving the electronic device (100) through an output device (e.g., a display device (120)). For example, the data output module (350) may control the display device (120) to output a set of sensing data obtained from the data acquisition module (310) through the display device (120). Additionally, the data output module (350) may control the display device (120) to output driving state information obtained through the driving state determination module (340). Additionally, the data output module (350) may control the display device (120) to output a guide screen necessary for training an artificial intelligence model to determine the driving state in conjunction with the artificial intelligence learning module (320). According to various embodiments, the data output module (350) may control various output devices (e.g., speakers, etc.) connected to the electronic device (100) to output various information. At this time, the data output module (350) can transmit various information generated through the electronic device (100) as a signal corresponding to the type of output device.

[0102] In the embodiment of FIG. 3, the function performed by the data acquisition module (310), the artificial intelligence learning module (320), the data processing module (330), the driving state determination module (340), and / or the data output module (350) can be understood as being performed by the processor (210) executing instructions stored in the storage device (220). In addition, in various embodiments, the electronic device (100) may utilize one or more hardware processing circuits to perform the various functions and operations disclosed herein.

[0103] Additionally, the connection between hardware and software shown in FIG. 3 is for convenience of explanation and does not restrict the flow or direction of data or commands. The components included in the electronic device (100) may have various electrical / operational connection relationships.

[0105] FIG. 4 is a flowchart (400) illustrating a method for generating an artificial intelligence model trained to determine the driving state of a motor-driven valve for an electronic device. FIG. 5 is a diagram illustrating a training data set for training an artificial intelligence model. FIG. 6 is a diagram illustrating an electronic device acquiring a training data set based on an initial training data set.

[0106] Each of the operations described below may be performed in combination with one another. Additionally, among the operations described below, an operation by an electronic device (100) (e.g., the electronic device (100) of FIG. 1) may mean an operation by a processor (210) of the electronic device (100).

[0107] In addition, the term "information" described below may be interpreted as having the meaning of "data" or "signal," and the term "data" may be understood as a concept that includes both analog data and digital data.

[0108] According to various embodiments, when the electronic device (100) is implemented as a single device including a sensor device (110) and / or a display device (120), the operation of the sensor device (110) and / or the display device (120) can be understood as an operation of the internal configuration of the electronic device (100).

[0109] According to various embodiments, the operations illustrated in FIG. 4 may be performed in various orders, not limited to the order illustrated. Additionally, according to various embodiments, more operations may be performed than those illustrated in FIG. 4, or at least one fewer operation may be performed.

[0110] Referring to FIG. 4, in operation 401, the electronic device (100) can acquire a first set of sensing data related to the operating state of the motor-driven valve through at least one sensor device (e.g., the sensor device (110) of FIG. 1) for a specified period. For example, the electronic device (100) can acquire a first set of sensing data related to the operating state of the motor-driven valve through the sensor device (110) placed in association with the motor-driven valve for a specified period (e.g., 4 weeks). Typically, sensing data acquired early after the installation of the motor-driven valve can be classified as data acquired when the operating state of the motor-driven valve is normal.

[0111] The first sensing data set obtained according to various embodiments may mean data identical and / or similar to the sensing data set described with reference to FIGS. 1 to 3.

[0112] According to various embodiments, in operation 403, the electronic device (100) can obtain a first initial learning data set by synthesizing a first sensing data set and a first failure data set. For example, the electronic device (100) can synthesize the first failure data set stored in the storage device (220) and the first sensing data set, respectively. For example, the first initial learning data (530) can be obtained by synthesizing the first failure data (510) included in the first failure data set and the first sensing data (520) included in the first sensing data set.

[0113] The first failure data set obtained according to various embodiments may mean data identical and / or similar to the failure data set described with reference to FIGS. 1 to 3. Additionally, the first initial training data set may mean data identical and / or similar to the training data set described with reference to FIGS. 1 to 3.

[0114] According to various embodiments, in operation 405, the electronic device (100) can obtain a first learning data set that has been converted into a multidimensional first learning data set.

[0115] According to various embodiments, the initial learning data included in the first initial learning data set may be represented as a one-dimensional graph. For example, referring to FIG. 6, the initial learning data (610) is illustrated. The initial learning data is data obtained by synthesizing the first failure data with the first sensing data, and may include information representing changes in various sensing data that can be obtained through the sensor device (110), such as vibration, sound, rotational speed, temperature, cracks, and / or pressure of the motor-driven valve per hour. For example, the first initial learning data (610) may be represented as a graph with the time during operation of the motor-driven valve on the horizontal axis and the vibration magnitude corresponding to that time on the vertical axis.

[0116] According to various embodiments, the electronic device (100) may obtain a first learning data set by converting the data included in the first initial learning data set into multiple dimensions. For example, referring to FIG. 6, the electronic device (100) may obtain a first learning data (620) obtained by converting the first initial learning data (610) into multiple dimensions. According to various embodiments, the first learning data set including the first learning data (620) may include data representing the change in sensing data of the motor-driven valve per hour in multiple dimensions (e.g., two dimensions, images). For example, the first learning data (620) may be represented as a graph in which sensing data (e.g., vibration, sound, rotational speed, temperature, cracks, and / or pressure, etc.) corresponding to the time is represented in two dimensions with time as the horizontal axis in relation to the operation of the motor-driven valve. For example, an electronic device (100) can obtain first training data (620) by transforming first initial training data (610) through at least one transformation method among Fourier transform, Wavelet transform, Wavelet spectrogram, and Mel-Frequency Cepstral Coefficients (MFCC).

[0117] According to various embodiments, in operation 407, the electronic device (100) may train the first artificial intelligence model to determine the operating state of the motor-driven valve based on the first learning data set. For example, the electronic device (100) may train the first artificial intelligence model to determine the operating state of the motor-driven valve based on the first learning data set including the first learning data (620). At this time, the first artificial intelligence model may be trained not only to determine the operating state of the motor-driven valve but also to output information regarding the cause of failure and countermeasures for the motor-driven valve. For example, based on pattern learning for the first learning data set, it may be trained to receive sensing data input to determine the operating state of the motor-driven valve and to output operating state information of the motor-driven valve (e.g., cause of vibration, frequency, characteristics and phenomena of vibration, countermeasures). Various examples of operating state information are described in detail in [Table 1] to [Table 3] below. That is, the electronic device (100) can train the first artificial intelligence model based on the first learning data set so that the first artificial intelligence model outputs driving state information such as [Table 1] to [Table 3]. However, [Table 1] to [Table 4] are described only when the sensing data obtained through the sensor device (110) is vibration data for convenience of explanation, but the first artificial intelligence model can be trained to output various information related to the driving state without being limited to the described examples.

[0118] Below, [Table 1] shows the causes of abnormal vibration and countermeasures when the driving state of a motor-driven valve is abnormal in relation to fluid vibration.

[0119] Causes of vibration frequency Characteristics and phenomena of vibration countermeasures 1. Cavitation 1) NPSH or insufficient suction level 2) Excessive rotational speed 3) Flow at the pump suction port Frequency is the rotational frequency ( It is unrelated to ) and generally high frequency. Usually 600–25,000 Hz 1) It generates noise characteristic of cavitation and occurs mainly in areas with high discharge flow rates. However, in pumps with high specific speeds, it is prone to occur during stall conditions at partial discharge flow rates. 2) Round pitting often forms on the metal surface of the cavitation-generating area. 3) The vibration spectrum of cavitation is not constant and continuous, but exhibits an abnormal phenomenon of intermittent extinction. Increase the effective suction pressure. 1), 2), and 3) can mainly be resolved during the planning stage. 4) Use at excessive discharge rates The flow rate is adjusted by a flow control valve. 5) Clogging of the suction strainer Remove clogged debris. 2. Surging Natural frequency (normal frequency is a low frequency of about 1 / 10 to 10 Hz). Rotational whirling occurs, and vibration is mainly in the radial direction. 1) It occurs in locations with extremely low discharge flow rates, and in pumps, it occurs in the following cases: (1) The slope of the pump head curve is upward to the right; (2) There is an air chamber or air pocket in the piping; (3) The discharge volume control valve is located behind the air chamber in (2). 2) The ammeter needle shakes significantly. 3) The piping duct connected to the pump, blower, etc., also shakes significantly. 4) The frequency of vibration generated matches the natural frequency of the piping system. 5) In large, low-speed rotating machinery, vibration does not appear significantly in the main body, but often becomes a problem due to vibration in the piping duct section. 6) In cases where the pressure exceeds approximately 700 mmAq, sound is generated due to liquid pulsation. 1) Improve pump and blower performance (this can mainly be resolved during the planning stage). 2) Eliminate areas where air accumulates in the piping. 3) Control the discharge volume using a valve immediately after the pump and blower. 4) Avoid surging operation by changing the flow rate. 3. Water hammering The natural frequency of a piping system. The normal frequency is a low frequency of about 1 / 10 to 10 Hz and is a transient phenomenon. 1) Vibration occurs in the piping during power interruption caused by the starting or stopping of pumps or power outages. 2) As an excessive phenomenon, it causes abnormal pressure rises or drops. 3) Generally, when analyzing water hammer, the cause and location are often measured at the pressure generation site rather than through vibration. 1) It can be resolved by reviewing it in advance during the planning stage. 2) Review the start and stop sequence and re-examine the opening and closing times of the control valve. 3) Install a surge tank to mitigate abnormal pressure rise. 4. Rotating stall ~0.8) Here : Value : Rotation speed (rps) 1) An abnormal phenomenon occurring in rotating machines of axial flow systems, specifically vibrations occurring in the compressor rather than the turbine. A phenomenon in which stall occurs in a part of the blade row when the rotational speed is slow. 2) The natural frequency of the blades and the frequency of the slewing stall may coincide, causing resonance and potentially leading to fatigue failure. Use a variable entrance guide flag. 5. Pulsation, separation, etc. within the pump 1) Pulsation of the impeller outlet flow 2) Flow separation at partial discharge rates The frequency is unrelated to the rotational frequency, and the vibration spectrum is often abnormal and unstable. 1) It often manifests as vibration in connecting pipes, etc., rather than vibration in the pump itself. 2) In particular, since it is not abnormal (dangerous) vibration, it is operated as is, and as a result, it causes not only vibration but also erosion and solid contact of the rotating body. 3) In normal pumps, pulsating flow and flow separation exist to varying degrees, and even if their magnitude is typically small, vibration may occur if the rigidity of the structural system is very weak. 1) It can be resolved through a comprehensive structural review during the design phase. 2) Adjust the discharge volume used. 3) In some cases, vibration can be restrained by reinforcing rigidity. 6. Hydraulic whirl Regardless of the rotational frequency of the fluid machinery, resonance occurs at the natural frequency of the valve system, and the frequency is often relatively high. 1) The valve vibrates severely when it starts to open or just before it expands. 2) In conjunction with this, it may generate pulsating pressure within the pipe and cause the piping system to vibrate severely. 3) In addition, in the case of a control valve, vibration may occur due to poor adjustment of the control system and generate pulsating pressure. 1) Eliminate valve body eccentricity. 2) Improve the shape of the valve body and valve seat. 3) First, switch to a larger capacity valve. Readjust the control system.

[0120] Below, [Table 2] shows the causes of abnormal vibration and countermeasures when the driving state of the motor-driven valve is abnormal in relation to mechanical vibration.

[0121] Causes of vibration frequency Characteristics and phenomena of vibration countermeasures 1. Imbalance of a rotating body 1) Imbalance The frequency matches the rotational frequency of the rotating body. The direction of rotation is the direction of rotation of the rotating body, and it is primarily bending vibration. 1) A vibration corresponding one-to-one with rotation, occurring most frequently among rotating bodies. 2) The phases of the left and right bearings often differ due to vibration modes. 3) Imbalance caused by wear or corrosion of the rotating body tends to result in a gradual increase in the control trend value. 4) The control trend value increases gradually upon the attachment of foreign substances, while the amplitude surges upon their detachment. 5) Vibration increases gradually when the rotating body is deformed, and surges upon failure. 1) Perform balance correction (perform field balancing if possible). 2) Even if the balance is diagnosed as poor, be sure to measure the metal gap, as an increase in the metal gap may also be a possibility. 2) Thermal bending of a rotating body 1) Small rotating bodies, where the magnitude of vibration changes due to thermal load, are relatively less affected. 2) The vibration amplitude increases as time passes from the start of rotation. This phenomenon mainly occurs in large rotating machinery. 1) In cases where the degree of influence is relatively small, equilibrium is achieved by focusing on the midpoint of the thermal effect. 2) Rotating bodies with very large thermal effects (although this is quite rare) must be examined separately, and equilibrium correction must be performed on-site after reaching the operational equilibrium state. 3) When handling high-temperature fluids, vibration may increase only when the temperature rises due to temporary thermal deformation during startup or deformation caused by non-uniformity of the shaft material. 3) Bending of a rotating body due to contact between a stationary part and a rotating shaft There are cases where vibrations increase rapidly due to rubbing. Modification of settings to prevent contact, taking into account changes in thermal alignment 4) Wear and corrosion of rotating bodies The frequency matches the rotational frequency of the rotating body. The direction of rotation is the direction of rotation of the rotating body, and it is primarily bending vibration. The vibration gradually increases over time. Repair of wear and corrosion and correction of equilibrium 5) Attachment of foreign substances Vibrations gradually increase over time, and if part of the attachment peels off, the vibrations surge. Removes foreign substances. Also, prevents the attachment of foreign substances. 6) Deformation or breakage of rotating bodies In the case of deformation, vibration increases gradually, while in the case of failure, vibration increases rapidly. Replacement of parts 7) Looseness in each part There are cases where the joint becomes loose due to heat. Conduct inspections and take appropriate measures when stopping and opening. 8) Unbalance in the combined state Even if it is in equilibrium on its own, connecting rotating bodies can result in imbalance. Balance of the flexible rotor is performed considering the mode of the combined shaft system. 2. Misalignment or misalignment 1) Misalignment Generally, the rotational frequency of the shaft system ( ) or, in extremely large cases, a double component of the rotational frequency occurs in the radial and axial directions. 1) If the center is misaligned and the surface-to-surface centering is poor, the bearing load becomes uneven, making it prone to increased sensitivity to unbalanced vibration. 2) It occurs frequently among the causes of vibration in rotating bodies, following imbalance. 3) It often generates vibration in the axial direction (when it exceeds 50% in the radial direction). 4) The generated frequency is the rotational frequency and its harmonic components, and It is characterized by an increase in lower harmonic components.5) The phase of axial vibration between the two bearings connected by the shaft coupling never reverses.6) The vibration amplitude often increases significantly over time from the start of rotation. In the case of large high-speed rotating machinery, caution is required as the alignment at standstill may differ significantly from the alignment during operation. 1) Centering correction (correction of misalignment) 2) Investigate not only shaft alignment but also shaft-bearing alignment (examine metal contact conditions) 3) Consider measures to reduce thruster force 2) Defect in face setting In special cases, there are also cases where the vibration component is twice the rotational speed. In cases where the centering is extremely poor, the bearing may lift or shift to one side, often causing oil whip or fractional harmonic oscillation. Correction regarding surface centering 3) Changes in thermal alignment The bearing support or casing is thermally deformed, causing the center to be misaligned. Centering is performed considering thermal deformation. 4) Foundation settlement Vibrations increase over time Centering correction 3. Coupling Defects 1) Poor Coupling Accuracy Frequency that mainly matches the rotational frequency - Couple ring exchange 2) Uneven tightening of fastening bolts - Replacement of bolts or rubber sleeves 3) Poor contact of the gears in the gear coupling There are cases where it is accompanied by unusual vibration phenomena. An unusual vibration occurs in relation to the natural frequency of the shaft system. Correcting gear tooth contact 4) Poor lubrication of the gear coupling There are cases where the natural vibration of the shaft system changes abnormally, and also causes the gear surfaces to burn and stick. Review appropriate lubrication methods 5) Vibration caused by fluid coupling - - 4. Bearing Damage and Wear 1) Damage and Wear of Rolling Bearings Abnormal increase in the frequency component accompanying the rotation of the ball or roller It is often accompanied by abnormal sounds. Additionally, vibrations gradually increase over time.1) If the rolling bearing is damaged, the vibration waveform becomes a shock-like waveform.2) Even if the rolling bearing is not damaged, if there is poor fitting or wear, a beat phenomenon appears in the vibration waveform.3) In cylindrical rolling bearings, if the retainer is made of iron, a squeaking sound may occur. This is characteristic of this bearing and is not abnormal if it occurs.4) If high-frequency vibrations that are not synchronized with rotation occur very periodically, the rolling bearing should be suspected first. At low bearing rotational speeds, a slight error will occur from the theoretical frequency. Also, if slippage occurs even at medium to high speeds, there will be an error of several percent. Replace the bearing. Each fault vibration frequency Here : Pitch circle diameter : Rolling body diameter : Number of electric elements : Contact angle a) Inner ring defect b) Outer ring defect c) Transformer defect d) Retainer contact e) Excessive insertion 2) Poor lubrication - - Improve the lubrication method by using appropriate lubricant. 3) Metal contact between sliding bearing and shaft Frequency that is an integer multiple of the number of rotations 1) The generated vibration frequency is determined by the natural frequency of the detection sensor (piezoelectric accelerometer). 2) The vibration pattern generates a high-frequency ringing sound synchronized with the rotation. 3) In the case of an impact signal, it is considered to be caused by another factor (collision between a rotating body and a stationary object). Replace the metal 3. Coupling Defect 1) Poor Coupling Accuracy Frequency that mainly matches the rotational frequency - Couple ring exchange 2) Uneven tightening of fastening bolts - Replacement of bolts or rubber sleeves 3) Poor contact of the gears in the gear coupling There are cases where it is accompanied by unusual vibration phenomena. Peculiar vibrations occur in relation to the natural frequency of the shaft system. Correcting gear tooth contact 4) Poor lubrication of the gear coupling There are cases where the natural vibration of the shaft system changes abnormally, and also causes the gear surfaces to burn and stick. Review appropriate lubrication methods 4. Critical speed of the axis of rotation1) Critical speed Frequency matching the rotational frequency of the shaft 1) Vibration increases sharply near the critical speed of the shaft system, but returns to normal after passing the critical speed region. 2) In shaft systems filled with water, such as pumps, the liquid itself acts as a damping agent, so the critical speed does not appear significantly apparent. This is because the damping effect is greater and it becomes less likely for a peak to occur at the critical speed as there are more parts with a bearing effect, such as labyrinth seals, wear rings, and balance drums (or pistons), and as the clearance between these parts is smaller. 3) In rotating machinery for gases, the critical speed is clearly apparent. 4) In rotating shaft systems for liquids, the critical speed occurs at a rotational speed significantly higher than the generally calculated critical speed due to the bearing effect of the liquid. Therefore, wear on seal parts such as labyrinths and wear rings can cause the critical speed to drop and coincide with the operating rotational speed, leading to resonance. During the planning and design phase, it is common practice to thoroughly review and handle factors such as axial stiffness, damping effects, and operating rotational speed. However, since calculations are often performed as if the bearing were a simply supported rotating body without considering the stiffness and damping effects of the bearing oil film, the stiffness of the bearing support, or the bearing effect caused by the liquid, there are many cases where the actual critical speed is significantly lower than the critical speed calculated under the simply supported model during actual operation. Particular attention must be paid to this point during calculations. It is desirable to set the operating speed approximately 25% lower or higher than the critical speed. 2) Secondary risk speed A frequency twice the shaft rotation frequency 1) Resonance occurs at half the primary critical speed due to secondary component forcing of the rotational order (misalignment, bending), resulting in significant vibration. 2) This occurs frequently, mainly when the shaft stiffness is anisotropic (e.g., two-pole generators, large keyways). Modify to be as isotropic as possible by reviewing the shaft shape and stiffness, as well as keyways. 6. Oil whip or oil whirl Frequency less than or equal to half the rotational frequency (strictly speaking, for an oil whip, it is the shaft's natural frequency, and for an oil whirl, it is 0.38 to 0.49 times the rotational frequency) This is a vibration that frequently occurs in high-speed rotating machinery using sliding bearings, and it is a self-excited vibration caused by the bearing's oil film. This vibration has the following characteristics: a) The frequency is equal to the critical speed of the rotating shaft system. b) It occurs at more than twice the primary critical speed of the rotating body. c) The frequency is independent of the rotating body and remains nearly constant. d) The points of vibration onset and extinction differ during the rise and fall of rotation (hysteresis phenomenon). e) Onset and extinction are sudden. f) Once vibration occurs, it does not decrease even if the rotation increases. g) The direction of the vibration's swirling is the same as the rotation. h) Contact marks often remain on the upper surface of the upper bearing metal. Additionally, the shaft may swirl even when the rotational speed is above the primary critical speed but less than twice that speed. In this case, the frequency is nearly half the rotational speed, and the shaft itself does not bend significantly but exhibits rigid swirling. The former is distinguished as an oil whip, and the latter as an oil whirl. In addition, there are cases where a similar hydraulic whirl occurs in the sealing parts of the rotor and casing. Although this is a matter that should be reviewed during the planning stage, the following countermeasures are effective if it occurs: 1) Increase the shaft eccentricity (to 0.8 or higher). (For example, increase hydraulic pressure from the top or install a reservoir for oil at the top.) 2) Increase bearing stability by creating a groove in the center of the bearing to increase surface pressure and simultaneously alter the bearing's L / D characteristics. 3) Increase the bearing clearance. 4) Lower the viscosity by increasing the temperature of the lubricating oil. 5) Increase the critical speed. 6) In addition, it is advisable to adopt special anti-vibration bearings, such as lobe bearings, floating bush bearings, or tilting pad bearings. Recently, it has become possible to eliminate bearing stability and instability by calculating them to a relatively good degree. 7. Rubbing caused by contact between the rotating part and the stationary part It is a self-excited vibration that vibrates at a relatively high frequency. The direction of swirl is opposite to the direction of rotation. 1) In poorly lubricated bearings, "shaft rotation" vibration occurs. Assuming the shaft surface and the bearing surface rotate in contact without slipping, the rotation speed is calculated as shaft rotation speed x (shaft radius / shaft clearance), resulting in rotation at a considerably high speed. 2) The possible rotational speed range is Here : Rotational angular velocity : Guide surface (e.g., metal inner diameter) : Axis radius : Rotational angular velocity 1) Improvement of lubrication effect 2) Increases critical speed 3) Increases damping. 8. Fractional harmonic resonance due to girders or nonlinearities It rotates at a frequency that is a fractional multiple of the rotational frequency of the shaft, such as 1 / 2 or 1 / 3. If bearings, foundation bolts, etc., contain girders or nonlinear elements, fractional harmonic resonance occurs, causing severe vibration. This vibration has the following characteristics: a) Fractional harmonic vibration occurs only within a limited range of forced frequency and forced vibration force. b) In symmetric linear systems, odd-order fractional harmonic vibrations such as 1 / 3, 1 / 5, etc. occur. c) In asymmetric nonlinear systems, even-order fractional harmonics such as 1 / 2, 1 / 4, etc. occur. Phenomenologically, this vibration is very similar to the oil whip phenomenon described in Clause 6, but it is difficult to distinguish from it by frequency analysis using a conventional vibration analyzer; therefore, it is necessary to record the vibration waveform on an oscilloscope to fully verify the waveform. However, compared to oil whip, cases of fractional harmonic vibration occurrence are extremely rare. The priority is to locate the girder or nonlinear elements of the system (e.g., looseness in the coupling, looseness in the impeller, contact between the casing and the rotating body, etc.) and improve them. However, since it is generally difficult to accurately detect these elements, indirect measures include: a) reducing the vibration force, i.e., imbalance, to an extreme degree to move the system out of the vibration generation zone; b) increasing the damping of the system in some way to move it out of the vibration generation zone; and c) modifying the shaft system to increase the critical speed. 9. Foundation defects 1) Poor installation level Generally, a frequency that matches the rotational speed - Correct it using a liner. 2) Foundation bolt fastening failure - Strengthen the connection. 3) Insufficient Grout - Add Grout 4) Foundation stiffness When foundation rigidity is weak, it often causes problems due to relatively large vibrations, even in the absence of vibrational abnormalities. Particularly in fluid rotating machinery, fluid flow is smooth near peak efficiency, but becomes erratic in low-load regions; this acts as a random disturbance excitation force, frequently causing the machine to vibrate. Furthermore, in vertical rotating machinery, the electric motor is generally installed at the very top, often resulting in a structure where the upper section is unusually large. In such cases, due to insufficient rigidity in the mounting section of the vertical machine, the upper part frequently shakes significantly even under normal imbalances. After comprehensively reviewing the foundation reinforcement machinery, this is a matter to be noted during the structural design stage. 5) Age changes of the foundation Centering is misaligned due to differential settlement of the foundation. Reinforcement of the foundation 10. Resonance, Others1) Resonance of piping systems, etc. Number of rotations of the shaft If the natural frequency of piping systems, ducts, etc., is close to the rotational frequency, it causes resonance and severe vibration occurs. Resonance is avoided by changing the natural frequency through measures such as increasing support stiffness. 2) Resonance in the connected system Number of rotations of the shaft In typical design calculations, the critical speeds of, for example, pumps and motors are often examined separately; however, strictly speaking, the critical speed in a connected system differs from that of a single shaft. Consequently, the shaft's rotational speed may coincide with the critical speed, leading to vibration. Particular caution is required when the prime mover is a diesel engine. The critical speed of a connected shaft system must be calculated as a connected shaft system, not as a single shaft. The engine manufacturer should be commissioned to calculate torsional vibrations, and the design must ensure that harmful torsional vibrations do not occur in the shaft system within the operating range. 3) Deformation of the casing The alignment changes due to thermal deformation of the casing; aside from this, depending on the structure and type of the casing, the casing often undergoes abnormal deformation and comes into contact with the rotating body. Improve the structure to prevent thermal stress. 4) Expansion of pipes There are cases where the piping lengthens due to thermal expansion, pressing against the casing and causing contact. Modify the piping system to allow for thermal expansion, or insert expansion joints in between. 5) Poor machining accuracy of speed-increasing and speed-reducing gears Accompanied by significantly high-frequency vibrations. Rotational frequency ( ) and gear teeth( The product of ) The frequency of ), and an integer multiple ingredient 1) In cases of poor machining accuracy or improper gear setting, vibration caused by the meshing frequency occurs (which is often detected as abnormal noise). Since non-linear elements always exist in gears , Components such as the above may also occur.2) In gear vibration frequency components, high-frequency components (natural vibration components) appear in a larger proportion than low-frequency components.3) This component exists even in normal meshing, but it becomes significant in poor meshing.4) Since the amplitude ratio between normal gears and abnormal gears is about three times smaller, it is advisable to analyze the longitudinal axis as linear when performing frequency analysis.5) Helical gears generate axial force, so they are prone to axial vibration.6) Bevel gears are generally more prone to axial vibration than other gears.7) Since vibration levels are often experienced to drop under no-load conditions, diagnosis must be performed while carefully considering the load conditions. Shave the gears again, or improve or replace the settings. -

[0122] Below, [Table 3] shows the causes of abnormal vibration and countermeasures when the driving state of the motor-driven valve is abnormal in relation to electronic vibration.

[0123] Causes of vibration frequency Characteristics and phenomena of vibration countermeasures 1. Static imbalance of the void Twice the power frequency ( ) ingredients and The components of here : Rotor slip : Arbitrary integer : Number of rotor slots Extreme double eyelid surgery : 0 or even 1) It is difficult to identify due to phenomena such as stator abnormalities. 2) Vibration increases as the air gap imbalance increases. 3) Rotating magnetic field ( When ) passes through the minimum air gap position, it generates an unbalanced electromagnetic force, and since it varies by the number of poles, the frequency 4) Caused by misalignment of the stator and rotor shafts, which generate electronic vibrations. 5) Usually, there is no problem if the amount of imbalance is within 10% of the air gap. 6) Generally, resonance with the motor frame occurs frequently. Stator and rotor axis adjustment 2. Dynamic Imbalance of the Void The rotational frequency and its left and right The side-band occurs 1) Frequency is the rotational speed of the rotor or the synchronous rotational speed of the rotating magnetic field ( ) It is one of .2) Vibration is period ( ) As the motor load increases, the slip becomes larger and the period becomes shorter.3) The motor generates a ringing sound that matches the vibration pulsation.4) When zooming in near the rotational frequency, the vibration spectrum shows A sideband occurs, but there is no sideband in the load current and the power frequency component ( ) only exists.5) Unbalanced electromagnetic force due to rotor rotation ( ) and unbalanced force( Generates ). Since the stimulus overtakes the minimum air gap position, the unbalanced electromagnetic force Pulsation 6) Caused by shaft bending caused by aging or external forces, or rotation due to rotor weight imbalance. Perform field balancing of the rotor 3. Stator Abnormalities 1) Weakness or looseness of stator supports 2) Stator winding defects 3) Short circuit of the stator core Twice the power frequency ( ) 1) When the motor power is cut off, the vibration disappears instantly. 2) Vibration occurs in the stator frame, bearings, etc. 3) As the motor's foundation or bolts become loose, the motor's resonant frequency... It often resonates when approaching (within 10%).4) It can also occur due to electrical imbalance between phases of the stator windings.5) The vibration distribution of the stator due to the resonance of electromagnetic vibrations differs in the frame vibration distribution depending on the number of poles. 1) Reinforcement and tightening of the stator support 2) Fixing the stator windings and iron core 4) Looseness of the stator core 1) When vibration occurs due to loose iron core or stator windings, it is accompanied by girder vibration Integer multiple components of 3) 4. Rotor Abnormalities 1) Loose rotor rods 2) Broken or cracked rotor rods 3) Short circuit in rotor core 4) Defective end ring Rotation frequency ( ) and to its left and right The sideband occurs 1) It is difficult to determine because vibration phenomena such as dynamic imbalance of the air gap occur. 2) The motor load current is also the pulsation frequency of the vibration ( Since it pulsates as ), the power supply frequency (on the broadened spectrum of the load current) )above 3) Since a sideband occurs, secondary current does not flow at the minimum air gap position of the rotor conductor, generating an unbalanced electromagnetic force, and the magnetic pole ( Since ) overtakes the minimum void position 4) In squirrel-cage induction motors, the cause is broken rotor conductors, and if the number of broken conductors increases, it is difficult to start the motor. 5) In wound-type induction motors, the cause is electrical imbalance in the rotor winding circuit. Fixing or replacing the rotor rod 5. Static imbalance of the void Twice the power frequency ( ) ingredients and

[0124] FIG. 7 is a flowchart (700) showing the operation of an electronic device training an artificial intelligence model based on label data. FIG. 8 is a flowchart (701) showing the operation of an electronic device acquiring a label data set. FIG. 9 is a diagram for explaining the electronic device acquiring a label data set.

[0125] Each of the operations described below may be performed in combination with one another. Additionally, among the operations described below, an operation by an electronic device (100) (e.g., the electronic device (100) of FIG. 1) may mean an operation by a processor (210) of the electronic device (100).

[0126] In addition, the term "information" described below may be interpreted as having the meaning of "data" or "signal," and the term "data" may be understood as a concept that includes both analog data and digital data.

[0127] According to various embodiments, the operations illustrated in FIG. 8 may be performed in various orders, not limited to the order illustrated. Additionally, according to various embodiments, more operations may be performed than those illustrated in FIG. 7 and FIG. 8, or at least one fewer operation may be performed.

[0128] According to various embodiments, when the electronic device (100) is implemented as a single device including a sensor device (110) and / or a display device (120), the operation of the sensor device (110) and / or the display device (120) can be understood as an operation of the internal configuration of the electronic device (100).

[0129] Referring to FIG. 7, the electronic device (100) can obtain a label data set labeled with a first initial learning data set based on the classification of the driving state of the motor-driven valve in operation 701. According to various embodiments, the electronic device (100) can obtain a label data set labeled with the driving state of the motor-driven valve for each of the data included in the first initial learning data set described with reference to FIG. 4 to 6.

[0130] Meanwhile, not limited to the described examples, the electronic device (100) can perform a similar operation to obtain a labeling data set for the first training data that has been converted into multiple dimensions from the first initial training data.

[0131] Specifically, referring to FIG. 8, the electronic device (100) can control a display device (e.g., the display device (120) of FIG. 1) to display a learning guide screen related to the acquisition of a label data set in operation 801.

[0132] Additionally, the electronic device (100) can acquire a label data set based on an input obtained in relation to a learning guide screen through a display device (120) in operation 803.

[0133] Referring to FIG. 9, it is illustrated that an electronic device (100) acquires a first label data set based on a first initial learning data set (and / or the first learning data set). For convenience of explanation, only the acquisition of the first label data set is illustrated, but by performing a similar operation, the electronic device (100) may acquire various label data for a second label data set and other learning data sets. FIG. 9 illustrates labeling at least one first learning data included in the first learning data set.

[0134] Referring to FIG. 9, first state labels (900a) and second state labels (900b) labeled for the first initial training data (920) and the first training data (910) are illustrated. In this case, the first initial training data (920) may represent data obtained by synthesizing the first sensing data included in the first sensing data set and the first failure data included in the first failure data set. Additionally, the first training data (910) may represent data obtained by converting the first initial training data (920) into a multidimensional (e.g., two-dimensional) form.

[0135] According to various embodiments, the electronic device (100) may obtain a first label data set labeled with the first learning data set based on a driving state classification for the driving of the motor-driven valve, and train the first artificial intelligence model based on the first label data set.

[0136] According to various embodiments, the driving state classification may refer to a classification based on the driving state of the motor-driven valve. For example, the driving state classification of the motor-driven valve may include a classification based on a state where the motor-driven valve is driven normally (e.g., NOMAL) and a classification based on a state where the driving of the motor-driven valve is unstable (e.g., failure, abnormality, danger, etc.). For convenience of explanation, the driving state classification is described as having two types, but it may be classified into multiple states. Accordingly, the type of label data (e.g., third label data, etc.) may also be changed. Additionally, the electronic device (100) may use label data classified according to the cause of the abnormal driving of the motor-driven valve.

[0137] According to various embodiments, the electronic device (100) may label the first initial learning data (920) and / or the first learning data (910) with a first state label (901, 903, 905) for a state in which the motor-driven valve appears to be operating stably. According to various embodiments, the electronic device (100) may label the first initial learning data (920) and / or the first learning data (910) with a second state label (902, 904) for a state in which the operation of the motor-driven valve is unstable (e.g., failure, abnormality, danger, etc.).

[0138] According to various embodiments, the first state labels (900a) and the second state labels (900b) may include labels that add information or annotations to train an artificial intelligence model. According to various embodiments, the electronic device (100) may obtain a first label data set by performing labeling on a first training data set, similar to that illustrated with reference to FIG. 9. Additionally, the electronic device (100) may obtain a second label data set through a similar method for a second training data set used to retrain an artificial intelligence model.

[0139] According to various embodiments, the electronic device (100) may acquire the label data through various methods. For example, the electronic device (100) may acquire a first label data set and / or a second label data set that has been labeled according to a preset standard. According to various embodiments, the electronic device (100) may cause the display device (120) to display a learning guide screen related to data learning (e.g., a screen similar to FIG. 9) and acquire the first label data and / or the second label data through the display device (120) and / or the input interface of the electronic device (100). For example, the electronic device (100) may acquire the first label data and / or the second label data based on user input.

[0140] According to various embodiments, the electronic device (100) can train a first artificial intelligence model based on the label data set and the first training data set in operation 703. For example, the electronic device (100) can train the first artificial intelligence model to determine the driving state of the motor-driven valve based on the label data set and / or the first training data set. According to various embodiments, the electronic device (100) can obtain an artificial intelligence model capable of more accurate and specific classification of the driving state of the motor-driven valve by training the artificial intelligence model using a training data set that synthesizes failure data and converts it into a multidimensional form, and a label data set for the same.

[0142] FIG. 10 is a diagram illustrating the acquisition of driving state information regarding the driving state of a motor-driven valve using an artificial intelligence model.

[0143] Referring to FIG. 10, a first artificial intelligence model (1010) described with reference to FIGS. 4 through 9 is shown. According to various embodiments, an electronic device (100) can acquire a first artificial intelligence model (1010) trained to determine the driving state of a motor-driven valve through a learning method described with reference to FIGS. 4 through 9.

[0144] According to various embodiments, the electronic device (100) can obtain operating state information (1005) using the first artificial intelligence model (1010).

[0145] For example, the electronic device (100) may acquire second sensing data (1001) through a sensor device (110) during the operation of the motor-driven valve to determine the operation state of the motor-driven valve. In various embodiments, the second sensing data (1001) may include at least one of various data such as vibration, sound, pressure, heat, and rotational speed acquired through the sensor device (110) during the operation of the motor-driven valve to determine the operation state of the motor-driven valve.

[0146] According to various embodiments, the electronic device (100) may acquire diagnostic data (1003) to input the second sensing data (1001) into the first artificial intelligence model (1010). For example, the electronic device (100) may acquire diagnostic data (1003) by converting the second sensing data (1001), which is one-dimensional data, into a multi-dimensional one. According to various embodiments, the electronic device (100) may acquire driving state information (1005) of the motor-driven valve by inputting the diagnostic data (1003) converted into a multi-dimensional one into the first artificial intelligence model (1010). At this time, by inputting the diagnostic data (1003) converted into a multi-dimensional one into the first artificial intelligence model (1010), the electronic device (100) may acquire driving state information (1005) with higher accuracy and easier noise processing.

[0147] According to various embodiments, the electronic device (100) may transmit the driving state information (1005) to an output device (e.g., a display device (120)) for output. According to various embodiments, the driving state information (1005) may include various information related to the driving of the motor-driven valve (driving state, cause of failure, countermeasures, characteristics and phenomena, etc.).

[0148] That is, the electronic device (100) inputs diagnostic data (1003), which is a multidimensional conversion of the second sensing data (1001) of the motor-driven valve currently in operation, into the first artificial intelligence model (1010), thereby obtaining operation status information that determines whether the operation state of the motor-driven valve is normal, abnormal, or dangerous. Accordingly, the electronic device (100) can determine whether the motor-driven valve is in a faulty state based on the operation status information. In addition, it can predict and maintain abnormal situations prior to the failure of the motor-driven valve, thereby preparing in advance to ensure the motor-driven valve operates stably.

[0150] FIG. 11 is a flowchart (1100) showing the operation of an electronic device retraining an artificial intelligence model according to the size of the failure data. FIG. 12 is a flowchart (1200) showing the operation of an electronic device retraining an artificial intelligence model according to the driving period of a motor-driven valve.

[0151] Each of the operations described below may be performed in combination with one another. Additionally, among the operations described below, an operation by an electronic device (100) (e.g., the electronic device (100) of FIG. 1) may mean an operation by a processor (210) of the electronic device (100).

[0152] In addition, the term "information" described below may be interpreted as having the meaning of "data" or "signal," and the term "data" may be understood as a concept that includes both analog data and digital data.

[0153] According to various embodiments, the operations illustrated in FIGS. 11 and 12 may be performed in various orders, not limited to the order illustrated. Additionally, according to various embodiments, more operations may be performed than those illustrated in FIGS. 11 and 12, or at least one fewer operation may be performed.

[0154] According to various embodiments, when the electronic device (100) is implemented as a single device including a sensor device (110) and / or a display device (120), the operation of the sensor device (110) and / or the display device (120) can be understood as an operation of the internal configuration of the electronic device (100).

[0155] Referring to FIG. 11, the electronic device (100) can obtain a second fault data set by storing second fault data obtained through at least one sensor device (110) while the motor-driven valve is driven during operation 1101. For example, the electronic device (100) can obtain a second fault data set by classifying and storing data determined to be an abnormal driving state or a dangerous driving state among the sensing data obtained through the sensor device (110) while at least one motor-driven valve is installed and driven in an industrial environment as second fault data. That is, the electronic device (100) can obtain a second fault data set by accumulating data classified as fault data among the sensing data obtained during the driving of the motor-driven valve and storing it in a storage device (220).

[0156] According to various embodiments, the electronic device (100) may determine whether to retrain the first artificial intelligence model based on at least one of the number of times the second failure data is stored and the size of the second failure data set in operation 1103. For example, the electronic device (100) may accumulate and store the second failure data of at least one motor-driven valve and determine whether to retrain based on whether the number of times the second failure data is stored is greater than or equal to a specified number. Additionally, for example, the storage device (100) may accumulate and store the second failure data of at least one motor-driven valve and determine whether to retrain based on whether the size of the second failure data set stored in the storage device (220) is greater than or equal to a certain size.

[0157] According to various embodiments, the electronic device (100) can obtain a second learning data set in which the second failure data set is converted into a multidimensional form based on the result of the judgment in operation 1105.

[0158] According to one embodiment, the electronic device (100) may determine that it is necessary to retrain the first artificial intelligence model (e.g., the first artificial intelligence model described with reference to FIGS. 1 to 10) when the number of times the second failure data has been stored is greater than a specified number of times (e.g., N times) or when the size of the second failure data set is greater than a specified size. Accordingly, the electronic device (100) may obtain a second training data set by converting the second failure data set into multiple dimensions in order to retrain the first artificial intelligence model. According to various embodiments, obtaining the second training data set by converting the second failure data set into multiple dimensions may be obtained by performing an operation similar to obtaining the first training data set described with reference to FIGS. 4 to 9.

[0159] According to various embodiments, the electronic device (100) may obtain a second artificial intelligence model by retraining the first artificial intelligence model based on the second training data set in operation 1007. For example, the electronic device (100) may obtain a second artificial intelligence model by fine-tuning the first artificial intelligence model based on the second training data set. In various embodiments, the electronic device (100) may obtain the second artificial intelligence model by performing an operation similar to the operation of training the first artificial intelligence model as an operation of retraining the first artificial intelligence model. Alternatively, the electronic device (100) may obtain the second artificial intelligence model by training an artificial intelligence model set only with initial setting values.

[0160] According to various embodiments, the electronic device (100) can obtain an artificial intelligence model that classifies the driving state with higher accuracy by retraining the artificial intelligence model using failure data obtained during the driving of at least one motor-driven valve.

[0161] Additionally, referring to FIG. 12, the electronic device (100) can obtain a third sensing data set by storing third sensing data obtained through at least one sensor device (110) during the driving period in which the motor-driven valve is driven in operation 1201. For example, the electronic device (100) can obtain a third sensing data set by storing sensing data obtained through at least one sensor device (110) while at least one motor-driven valve is driven.

[0162] According to various embodiments, the electronic device (100) can determine whether to relearn the first artificial intelligence model based on the operating period in operation 1203. For example, the electronic device (100) can determine whether to relearn based on whether the period during which at least one motor-driven valve is deployed and operated in an industrial environment is longer than a specified period.

[0163] According to various embodiments, the electronic device (100) may, in operation 1205, acquire a third learning data set by converting the third sensing data set into multiple dimensions based on the result of the determination. For example, the electronic device (100) may determine that if the driving period of the motor-driven valve is longer than a specified period (e.g., N months), it is necessary to retrain the first artificial intelligence model (e.g., the first artificial intelligence model described with reference to FIGS. 1 through 10). Accordingly, the electronic device (100) may acquire a third learning data set by converting the third sensing data set into multiple dimensions in order to retrain the first artificial intelligence model. According to various embodiments, acquiring the third learning data set by converting the third sensing data set into multiple dimensions may be achieved by performing an operation similar to acquiring the first learning data set described with reference to FIGS. 4 through 9.

[0164] According to various embodiments, the electronic device (100) may obtain a second artificial intelligence model by retraining the first artificial intelligence model based on a third training data set in operation 1207. For example, the electronic device (100) may obtain a second artificial intelligence model by fine-tuning the first artificial intelligence model based on the third training data set. In various embodiments, the electronic device (100) may obtain the second artificial intelligence model by performing an operation similar to the operation of training the first artificial intelligence model as an operation of retraining the first artificial intelligence model. Alternatively, the electronic device (100) may obtain the second artificial intelligence model by training an artificial intelligence model set only with initial setting values.

[0165] According to various embodiments, the electronic device (100) can obtain an artificial intelligence model that classifies the driving state with higher accuracy by retraining the artificial intelligence model using a set of sensing data obtained during the driving of at least one motor-driven valve.

[0166] Meanwhile, the electronic device (100) may obtain a second artificial intelligence model by retraining the first artificial intelligence model using various methods, not limited to the examples described in FIGS. 11 and 12.

[0168] FIG. 13 is a flowchart (1300) showing the operation of devices within a system for determining the driving state of a motor-driven valve. FIG. 14 shows a user interface output through a display device.

[0169] Referring to FIG. 13, electronic devices (100), sensor devices (110), and / or display devices (120) are illustrated as devices within a system for determining the operating state of a motor-driven valve. According to various embodiments, a system for determining the operating state of a motor-driven valve may include an operating state determination system described with reference to FIG. 1. Accordingly, descriptions similar to or redundant with those described with reference to FIG. 1 may be omitted below.

[0170] According to various embodiments, the display device (120) may request the electronic device (100) to determine the operating state of the motor-driven valve in operation 1301. For example, the display device (120) may obtain a request from a user to determine the operating state of the motor-driven valve and transmit said request to the electronic device (100). However, the electronic device (100) may obtain a request to determine the operating state of the motor-driven valve, not limited to the illustrated example. For example, the electronic device (100) may identify that it is necessary to determine the operating state of the motor-driven valve based on various information such as the period during which the motor-driven valve is installed and the number of times sensing data is acquired, and obtain a request to determine the operating state. Alternatively, the electronic device (100) may obtain a request to continuously determine the operating state of the motor-driven valve while the motor-driven valve is operating.

[0171] According to various embodiments, the sensor device (110) can acquire initial sensing data related to the operation of the motor-driven valve in operation 1303. For example, the sensor device (110) can continuously acquire initial sensing data related to the operation during the operation of the motor-driven valve. The initial sensing data may include data identical or similar to the sensing data described with reference to FIGS. 1 to 12.

[0172] According to various embodiments, the electronic device (100) may request initial sensing data related to the driving of the motor-driven valve from the sensor device (110) in accordance with the request (1301) in operation 1305.

[0173] Accordingly, the sensor device (110) can transmit initial sensing data in response to the request (1305) in operation 1307. For example, the electronic device (100) can obtain initial sensing data from the sensor device (110) by requesting it to diagnose the operating state of the motor-driven valve.

[0174] According to various embodiments, the electronic device (100) can obtain diagnostic sensing data in operation 1309, in which initial sensing data is converted into multiple dimensions. For example, the electronic device (100) can obtain diagnostic sensing data in which one-dimensional sensing data obtained from a sensor device (110) is converted into multiple dimensions (e.g., two-dimensional image), as described with reference to FIG. 10.

[0175] According to various embodiments, the electronic device (100) can obtain driving state information by inputting diagnostic sensing data into an artificial intelligence model in operation 1311. For example, the electronic device (100) can obtain driving state information of a motor-driven valve by inputting the diagnostic sensing data into a first artificial intelligence model learned through the method described with reference to FIGS. 4 to 9.

[0176] According to various embodiments, the electronic device (100) may transmit the driving state information to the display device (120) in operation 1313. For example, the electronic device (100) may acquire driving state information indicating the driving state of the motor-driven valve through a first artificial intelligence model and transmit the driving state information to the display device (120) to output the driving state information. However, not limited to the illustrated example, the electronic device (100) may transmit the information to various output devices to output the driving state information.

[0177] According to various embodiments, the display device (120) can output driving status information in operation 1315. For example, the display device (120) can output driving status information based on driving status information of a motor-driven valve and / or control signals obtained through the electronic device (100).

[0179] Referring to FIG. 14, the display device (120) may display an execution screen to provide a service related to determining the driving status of a motor-driven valve. At this time, the display device (120) is linked with the electronic device (100) and displays a screen to provide a service related to determining the driving status provided through the electronic device (100), and user input for the screen may be obtained through the display device (120) and transmitted to the electronic device (100).

[0180] According to various embodiments, the display device (120) can display an execution screen (1400) including driving state information obtained through the electronic device (100).

[0181] According to various embodiments, the electronic device (100) may display an execution screen including a first visual object (1410) representing information about a target motor-driven valve to identify the motor-driven valve based on the driving status determination request, a second visual object (1430) representing various information related to the driving of the motor-driven valve, and a third visual object (1450) representing information to check the driving status of the motor-driven valve during a specified period. For example, the display device (120) may display information representing the appearance of the motor-driven valve as the first visual object (1410). Additionally, the display device (120) may display various information related to the driving of the motor-driven valve (e.g., AI diagnosis result (1431), load fluctuation, operating relative, communication status, data status) as the second visual object (1430). At this time, the AI ​​diagnostic result (1431) may include information regarding the operating status of the motor-driven valve obtained through the first artificial intelligence model or the second artificial intelligence model. Additionally, the third visual object (1450) may display various information, including a graph (1451) that allows checking the operating status of the motor-driven valve within a specified period (e.g., several months prior to the present).

[0182] According to various embodiments, not limited to the example illustrated in FIG. 14, the display device (120) may display a screen related to various functions provided through the electronic device (100) for determining the driving state of the motor-driven valve.

[0184] As described above, the electronic device (100) includes a communication device that obtains a signal from at least one sensor device disposed in a motor-driven valve, a storage device that stores a first fault data set and a first artificial intelligence model related to the motor-driven valve, and at least one processor. The at least one processor can obtain a first sensing data set related to the driving state of the motor-driven valve through the at least one sensor device during a specified period, obtain a first initial learning data set by synthesizing the first sensing data set and the first fault data set, obtain a first learning data set by converting the first initial learning data set into a multidimensional form, and, based on the first learning data set, train the first artificial intelligence model so that the first artificial intelligence model receives data related to the driving of the motor-driven valve and determines the driving state of the motor-driven valve.

[0185] According to various embodiments, the at least one processor may be configured to acquire a label data set labeled with the first initial learning data set based on the classification of the driving state of the motor-driven valve, and to train the first artificial intelligence model based on the label data set and the first learning data set.

[0186] According to various embodiments, the at least one processor may be configured to control a display device connected to the electronic device to display a learning guide screen related to the acquisition of the label data set, and to acquire the label data set based on an input acquired in relation to the learning guide screen through the display device.

[0187] According to various embodiments, the at least one processor may acquire second sensing data related to the driving state of the motor-driven valve through the at least one sensor device, acquire diagnostic data converted into multiple dimensions from the second sensing data, input the diagnostic data into the first artificial intelligence model to acquire driving state information of the motor-driven valve, and transmit the driving state information to a display device connected to the electronic device so as to output the driving state information.

[0188] According to various embodiments, the driving state information may include at least one of a first state indicating a normal driving state of the motor-driven valve, a second state indicating an abnormal driving state of the motor-driven valve, and a third state indicating a dangerous driving state of the motor-driven valve.

[0189] According to various embodiments, the at least one processor can determine whether an abnormal driving event has occurred for the motor-driven valve based on the driving state information of the motor-driven valve, and control the display device to output a notification regarding the abnormal driving event based on the determination result.

[0190] According to various embodiments, the first fault data set may be data obtained based on at least one of the following: sensing data obtained when the motor-driven valve is opened beyond a specified range; sensing data obtained due to foreign matter jamming in the motor-driven valve; sensing data obtained when the driving power of the motor-driven valve is below a specified size; sensing data obtained when the external environment of the location where the motor-driven valve is placed is unstable; and sensing data obtained by generating noise around the location where the motor-driven valve is placed.

[0191] According to various embodiments, the at least one processor can obtain the first training data set, which has been transformed into a multidimensional form using a spectrogram transformation.

[0192] According to various embodiments, the at least one processor may obtain a second failure data set by storing second failure data obtained through the at least one sensor device while the motor-driven valve is driven in the storage device, determine whether to retrain the first artificial intelligence model based on at least one of the number of times the second failure data stored in the storage device and the size of the second failure data set, obtain a second training data set obtained by converting the second failure data set into a multidimensional form based on the determination result, and obtain a second artificial intelligence model obtained by retraining the first artificial intelligence model based on the second training data set.

[0193] According to various embodiments, the at least one processor may acquire a third sensing data set by storing third sensing data acquired through the at least one sensor device during the driving period in which the motor-driven valve is driven in the storage device, determine whether to retrain the first artificial intelligence model based on the driving period, acquire a third training data set obtained by converting the third sensing data set into a multidimensional form based on the determination result, and acquire a second artificial intelligence model obtained by retraining the first artificial intelligence model based on the third training data set.

[0194] According to various embodiments, the at least one sensor device may include at least one of a vibration measuring sensor, an acoustic measuring sensor, a rotational speed measuring sensor, a temperature sensing sensor, a crack sensing sensor, or a pressure sensing sensor of the motor-driven valve.

[0195] As described above, the method of operation of an electronic device for determining the driving state of a motor-driven valve may include: acquiring a first sensing data set related to the driving state of the motor-driven valve through at least one sensor device disposed on the motor-driven valve during a specified period; acquiring a first initial learning data set by synthesizing a first fault data set with the first sensing data set; acquiring a first learning data set obtained by converting the first initial learning data set into a multidimensional form, wherein the first fault data set is fault data related to the motor-driven valve; and training a first artificial intelligence model based on the first learning data set so that the first artificial intelligence model receives data related to the driving of the motor-driven valve and determines the driving state of the motor-driven valve.

[0196] According to various embodiments, the method may include acquiring second sensing data related to the driving state of the motor-driven valve through at least one sensor device, acquiring diagnostic data converted into multiple dimensions from the second sensing data, acquiring driving state information of the motor-driven valve by inputting the diagnostic data into the first artificial intelligence model, and transmitting the driving state information to a display device connected to the electronic device to output the driving state information.

[0197] According to various embodiments, the driving state information may include at least one of a first state indicating a normal driving state of the motor-driven valve, a second state indicating an abnormal driving state of the motor-driven valve, and a third state indicating a dangerous driving state of the motor-driven valve.

[0198] According to various embodiments, the first fault data set may be data obtained based on at least one of the following: sensing data obtained when the motor-driven valve is opened beyond a specified range; sensing data obtained due to foreign matter jamming in the motor-driven valve; sensing data obtained when the driving power of the motor-driven valve is below a specified size; sensing data obtained when the external environment of the location where the motor-driven valve is placed is unstable; and sensing data obtained by generating noise around the location where the motor-driven valve is placed.

[0199] According to various embodiments, the operation of acquiring the first training data set may further include the operation of transforming the first initial training data based on a spectrogram transformation.

[0200] According to various embodiments, the method may further include the operation of obtaining a second failure data set by storing second failure data obtained through at least one sensor device while the motor-driven valve is driven, the operation of determining whether to retrain the first artificial intelligence model based on at least one of the number of times the second failure data is stored and the size of the second failure data set, the operation of obtaining a second training data set obtained by converting the second failure data set into a multidimensional form based on the determination result, and the operation of obtaining a second artificial intelligence model obtained by retraining the first artificial intelligence model based on the second training data set.

[0201] According to various embodiments, the method may further include: acquiring a third sensing data set by storing third sensing data acquired through at least one sensor device during the driving period in which the motor-driven valve is driven; determining whether to retrain the first artificial intelligence model based on the driving period; acquiring a third training data set obtained by converting the third sensing data set into a multidimensional form based on the determination result; and acquiring a second artificial intelligence model obtained by retraining the first artificial intelligence model based on the third training data set.

[0202] According to various embodiments, the operation of training the first artificial intelligence model may further include the operation of obtaining a label data set labeled by the first initial training data set based on the classification of the driving state of the motor-driven valve, and the operation of training the first artificial intelligence model based on the label data set and the first training data set.

[0203] As described above, the driving state diagnosis system for a motor-driven valve comprises at least one sensor device disposed on the motor-driven valve to acquire sensing information related to the driving of the motor-driven valve, a display device, and a server storing an artificial intelligence model trained to determine the driving state of the motor-driven valve. The server acquires initial sensing data related to the driving of the motor-driven valve acquired through the at least one sensor device, acquires diagnostic sensing data converted from the initial sensing data into a multidimensional form, inputs the diagnostic sensing data into the artificial intelligence model to acquire driving state information regarding the driving state of the motor-driven valve, and the artificial intelligence model is trained based on a learning data set that synthesizes fault data for the motor-driven valve stored in the server and a set of sensing data acquired through the motor-driven valve during a specified period, and transmits the driving state information to the display device, and the display device can display a screen including the driving state information.

[0204] In the present disclosure, each of the phrases such as “A or B”, “at least one of A and B”, “at least one of A or B”, “A, B or C”, “at least one of A, B and C”, and “at least one of A, B, or C” may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof.

[0205] Terms such as "first," "second," or "first" or "second" may be used simply to distinguish a component from another component and do not limit the components in other aspects (e.g., importance or order).

[0206] The term “module” as used in various embodiments of the present disclosure may include a unit implemented in hardware, software, or firmware. For example, it may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions.

[0207] Various embodiments of the present disclosure may be implemented as software (e.g., a program) comprising one or more instructions stored in memory (e.g., internal memory or external memory) that can be read by a device (e.g., an electronic device (100)). The memory may be represented as a storage medium.

[0208] According to one embodiment, the method according to the various embodiments disclosed herein may be provided as included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., CD-ROM (compact disc read-only memory)), or distributed online (e.g., download or upload) through an application store or directly between two user devices.

[0209] According to various embodiments, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Additionally or substantially, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to the integration.

[0210] According to various embodiments, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

Claim 1 In an electronic device, a communication device for acquiring a signal from at least one sensor device disposed on a motor-driven valve; a storage device for storing a first fault data set and a first artificial intelligence model associated with the motor-driven valve, wherein the first fault data set is data acquired based on at least one of: sensing data acquired when the motor-driven valve is opened beyond a specified range; sensing data acquired due to foreign matter jamming in the motor-driven valve; sensing data acquired when the driving power of the motor-driven valve is below a specified size; sensing data acquired when the external environment of the location where the motor-driven valve is disposed is unstable; or sensing data acquired by generating noise around the location where the motor-driven valve is disposed; An electronic device comprising at least one processor, wherein the at least one processor: acquires a first sensing data set related to the driving state of the motor-driven valve through the at least one sensor device during a specified period, acquires a first initial learning data set by synthesizing the first sensing data set and the first failure data set, acquires a first learning data set obtained by converting the first initial learning data set into a multidimensional form, and, based on the first learning data set, trains the first artificial intelligence model so that the first artificial intelligence model receives data related to the driving of the motor-driven valve and determines the driving state of the motor-driven valve. Claim 2 An electronic device according to claim 1, wherein the at least one processor is configured to acquire a label data set labeled by the first initial learning data set based on the driving state classification of the motor-driven valve, and to train the first artificial intelligence model based on the label data set and the first learning data set. Claim 3 The electronic device according to claim 2, wherein the at least one processor controls a display device connected to the electronic device to display a learning guide screen related to the acquisition of the label data set, and is configured to acquire the label data set based on an input acquired in relation to the learning guide screen through the display device. Claim 4 An electronic device according to claim 1, wherein the at least one processor: acquires second sensing data related to the driving state of the motor-driven valve through the at least one sensor device, acquires diagnostic data converted into a multidimensional form of the second sensing data, inputs the diagnostic data into the first artificial intelligence model to acquire driving state information of the motor-driven valve, and transmits the driving state information to a display device connected to the electronic device so as to output the driving state information. Claim 5 An electronic device according to claim 4, wherein the driving state information comprises at least one of a first state indicating a normal driving state of the motor-driven valve, a second state indicating an abnormal driving state of the motor-driven valve, and a third state indicating a dangerous driving state of the motor-driven valve. Claim 6 An electronic device according to claim 4, wherein the at least one processor determines whether a driving abnormal event occurs for the motor-driven valve based on the driving state information of the motor-driven valve, and controls the display device to output a notification for the driving abnormal event based on the result of determining whether a driving abnormal event occurs for the motor-driven valve. Claim 7 delete Claim 8 An electronic device according to claim 1, wherein at least one processor obtains the first training data set obtained by converting the first initial training data set into a multidimensional form using a spectrogram transformation. Claim 9 An electronic device according to claim 1, wherein the at least one processor: stores second fault data obtained through the at least one sensor device while the motor-driven valve is driven in the storage device to obtain a second fault data set; determines whether to retrain the first artificial intelligence model based on at least one of the number of times the second fault data stored in the storage device and the size of the second fault data set; obtains a second training data set obtained by converting the second fault data set into a multidimensional form based on the result of determining whether to retrain the first artificial intelligence model; and obtains a second artificial intelligence model obtained by retraining the first artificial intelligence model based on the second training data set. Claim 10 An electronic device according to claim 1, wherein the at least one processor: stores third sensing data obtained through the at least one sensor device during the driving period in which the motor-driven valve is driven in the storage device to obtain a third sensing data set; determines whether to retrain the first artificial intelligence model based on the driving period; obtains a third training data set obtained by converting the third sensing data set into a multidimensional form based on the result of determining whether to retrain the first artificial intelligence model; and obtains a second artificial intelligence model obtained by retraining the first artificial intelligence model based on the third training data set. Claim 11 An electronic device according to claim 1, wherein the at least one sensor device comprises at least one of a vibration measuring sensor, an acoustic measuring sensor, a rotational speed measuring sensor, a temperature sensing sensor, a crack sensing sensor, or a pressure sensing sensor of the motor-driven valve. Claim 12 A method of operation of an electronic device for determining the driving state of a motor-driven valve, comprising: an operation of acquiring a first sensing data set related to the driving state of the motor-driven valve through at least one sensor device disposed on the motor-driven valve during a specified period; an operation of acquiring a first initial learning data set by synthesizing a first fault data set with the first sensing data set, wherein the first fault data set is data acquired based on at least one of the following: sensing data acquired when the motor-driven valve is opened beyond a specified range; sensing data acquired due to foreign matter jamming in the motor-driven valve; sensing data acquired when the driving power of the motor-driven valve is below a specified size; sensing data acquired when the external environment of the location where the motor-driven valve is disposed is unstable; or sensing data acquired by generating noise around the location where the motor-driven valve is disposed; and an operation of acquiring a first learning data set obtained by converting the first initial learning data set into a multidimensional form. A method of operation of an electronic device comprising the operation of training a first artificial intelligence model based on the first learning data set, wherein the first artificial intelligence model receives data related to the driving of the motor-driven valve and determines the driving state of the motor-driven valve. Claim 13 A method of operation of an electronic device according to claim 12, comprising: acquiring second sensing data related to the driving state of the motor-driven valve through the at least one sensor device; acquiring diagnostic data converted into a multidimensional form of the second sensing data; acquiring driving state information of the motor-driven valve by inputting the diagnostic data into the first artificial intelligence model; and transmitting the driving state information to a display device connected to the electronic device so as to output the driving state information. Claim 14 A method of operation of an electronic device according to claim 13, wherein the driving state information comprises at least one of a first state indicating a normal driving state of the motor-driven valve, a second state indicating an abnormal driving state of the motor-driven valve, and a third state indicating a dangerous driving state of the motor-driven valve. Claim 15 delete Claim 16 A method of operation of an electronic device according to claim 12, wherein the operation of acquiring the first learning data set further includes the operation of converting the first initial learning data based on a spectrogram conversion. Claim 17 A method of operation of an electronic device according to claim 12, further comprising: an operation of obtaining a second failure data set by storing second failure data obtained through at least one sensor device while the motor-driven valve is driven; an operation of determining whether to retrain the first artificial intelligence model based on at least one of the number of times the second failure data is stored and the size of the second failure data set; an operation of obtaining a second training data set obtained by converting the second failure data set into a multidimensional form based on the result of determining whether to retrain the first artificial intelligence model; and an operation of obtaining a second artificial intelligence model obtained by retraining the first artificial intelligence model based on the second training data set. Claim 18 A method of operation of an electronic device according to claim 12, further comprising: an operation of obtaining a third sensing data set by storing third sensing data obtained through at least one sensor device during the driving period in which the motor-driven valve is driven; an operation of determining whether to retrain the first artificial intelligence model based on the driving period; an operation of obtaining a third training data set obtained by converting the third sensing data set into a multidimensional form based on the result of determining whether to retrain the first artificial intelligence model; and an operation of obtaining a second artificial intelligence model obtained by retraining the first artificial intelligence model based on the third training data set. Claim 19 A method of operation of an electronic device according to claim 12, wherein the operation of training the first artificial intelligence model further comprises: the operation of obtaining a label data set labeled by the first initial training data set based on the classification of the driving state of the motor-driven valve; and the operation of training the first artificial intelligence model based on the label data set and the first training data set. Claim 20 In a system for diagnosing the driving state of a motor-driven valve, at least one sensor device disposed on the motor-driven valve to acquire sensing information related to the driving of the motor-driven valve; a display device; The system includes a server storing an artificial intelligence model trained to determine the driving state of the motor-driven valve, wherein the server: acquires initial sensing data related to the driving of the motor-driven valve obtained through at least one sensor device, acquires diagnostic sensing data converted into a multidimensional form of the initial sensing data, inputs the diagnostic sensing data into the artificial intelligence model to acquire driving state information regarding the driving state of the motor-driven valve, and the artificial intelligence model is trained based on a learning data set that synthesizes failure data for the motor-driven valve stored in the server and a set of sensing data obtained through the motor-driven valve during a specified period, and transmits the driving state information to the display device, wherein the display device displays a screen including the driving state information, and the failure data for the motor-driven valve includes sensing data obtained when the motor-driven valve is opened beyond a specified range, sensing data obtained due to foreign matter jamming in the motor-driven valve, sensing data obtained when the driving power of the motor-driven valve is below a specified size, and the motor-driven valve is positioned A system for diagnosing the driving state of a motor-driven valve, wherein the data is obtained based on at least one of sensing data obtained when the external environment of the location is unstable, or sensing data obtained by generating noise around the location where the motor-driven valve is placed.

Citation Information

Patent Citations

  • Artificial intelligent smart valve control system based on database

    KR101797558B1

  • Data learning server, method for generating and using thereof

    KR1020190043258A

  • Fault diagnosis apparatus and method based on artificial intelligence technology

    KR1020210060157A

  • Method for managing storage space and electronic device supporting the same

    KR1020220139684A

  • Prediction failure diagnosis system for automatic valve using artificial intelligence

    KR1020220120456A