GPS-based three-phase power system phase detection and mobile linkage determination system

Abstract

The present invention relates to a three-phase power system phase detection and mobile interlocking determination system based on PS reference time, characterized by comprising a user terminal equipped with a display unit and a user input unit.

Description

Technology Field

[0001] The present invention relates to a mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction that detects a phase in a three-phase power system and determines it on-site. Background Technology

[0002] Generally, power generated at power plants is transmitted in the form of three-phase alternating current and distributed to distribution and load facilities via substations. Three-phase power is configured such that the phase difference between phases A, B, and C is 120°, and the stability and efficiency of the power system are ensured only when this phase relationship is maintained. However, in actual distribution lines or substation sites, although it is necessary to accurately identify the connected phase of specific equipment, workers often rely on visual markings or experience to verify phase connections, which can lead to misconnections, reverse phase connections, or load imbalances.

[0003] Conventionally, methods primarily used to detect reference phases involved utilizing reference data from substations or power plants, or transmitting reference phase information to a terminal via wireless communication and comparing it with phase information measured in the field. However, these methods suffered from reduced accuracy in field identification if reference phase data accumulated errors over time or if delays occurred during the communication process. Furthermore, if the terminal measurement and reference values ​​were not synchronized in real time, the actual phase could be misidentified, potentially leading to equipment connection errors. Moreover, conventional technologies often performed phase identification based on a single measurement value, which increased the likelihood of misidentification caused by disturbance signals or instantaneous voltage fluctuations; consequently, this presented limitations in adequately guaranteeing the safety and reliability of power facilities.

[0004] Therefore, technical means are required to generate reference phase information more accurately in three-phase power systems and to reduce misjudgment by comparing it in real time with phase data measured in the field. In particular, a new structure is needed to generate absolute phase reference data by combining the reference time of reference time sources such as GPS, PTP (IEEE 1588), IRIG-B, Rubidium, OCXO, etc. (hereinafter referred to as "reference time sources") with transformer PT voltage signals, and to compare and distinguish data measured by field finder devices by linking with a server through a user terminal. The problem to be solved

[0005] The present invention is a system for determining phases in an artificial intelligence-based three-phase power system through phase determination, autonomous error correction, and mobile integration, and aims to solve the aforementioned problems. By generating absolute phase reference data from the reference time of a reference time source and the transformer PT voltage signal through a standard phase detection device installed in a substation, and by storing and managing this data in a server control unit, it is possible to resolve the problem of reference phase information becoming unstable due to time delays or communication errors as in the past.

[0006] The control unit of the server provides absolute phase reference data in real time in response to a request from a user terminal, and receives electrical phase data measured by a finder device at the site and directly compares and calculates it, thereby being able to immediately determine which of phases A, B, or C the phase connection corresponds to.

[0007] Furthermore, the AI-based power equipment connection probe (finder) repeatedly collects electrical phase data multiple times and uses the average of only the values ​​among the repeated measurements whose deviation falls within an allowable range for identification. This significantly reduces the possibility of misidentification caused by disturbances or instantaneous voltage fluctuations compared to conventional methods that relied on a single measurement value. Consequently, field workers can secure stable and reliable phase identification results, and the system provides a three-phase power system phase detection and mobile-linked identification system based on a standard time source, which prevents reverse phase connections, load imbalances, and power accidents caused by incorrect phase connections. means of solving the problem

[0008] A mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction according to one embodiment of the present invention is characterized by including a user terminal provided with a display unit and a user input unit.

[0009] A server connected to the above-mentioned user terminal via a wired or wireless network; comprising, wherein the server includes a communication unit; a storage unit; The device includes a standard phase detection device installed in a substation, comprising a control unit; wherein the standard phase detection device generates absolute phase reference data by combining a reference time and phase information received from a reference time received through a GPS receiver and phase information received from a transformer PT voltage signal, and transmits the generated absolute phase reference data to the server; wherein the control unit stores the absolute phase reference data in the storage unit, and when a request signal for the absolute phase reference data is input from the user terminal, the control unit transmits the absolute phase reference data recorded in the storage unit to the user terminal; wherein when the control unit receives electrical phase data collected by a finder device in the field through a power facility connection probe via the communication unit, the control unit calculates the phase difference between the received electrical phase data and the absolute phase reference data, verifies whether the phase difference corresponds to a 120° phase difference relationship, identifies which of the electrical phases A, B, and C phases corresponds to the verification result, and controls the transmission of the identified result to the user terminal.

[0010] The control unit is characterized by repeatedly collecting the electric phase data a predetermined number of times to obtain multiple measurement values ​​under the same conditions when calculating the phase difference between the absolute phase reference data and the electric phase data, performing reference time alignment and phase difference calculation for each of the obtained multiple measurement values ​​to derive multiple phase difference result values, selecting only the result values ​​among the derived multiple phase difference result values ​​whose deviation is included within a predetermined allowable range to perform an average calculation, and performing phase identification by comparing the result of the average calculation with the absolute phase reference data.

[0011] The control unit performs a comparison and determination process between the absolute phase reference data and the electrical phase data, wherein it records the determined phase information, the time information at which the determination was performed, and the identification information of the finder device together and stores them as log data in the storage unit, verifies the consistency of determination by comparing the past determination result and the current determination result at the same power facility connection location using the stored log data, and if a determination discrepancy is detected as a result of the comparison, the control unit re-executes the determination process to resolve the determination discrepancy, and finally transmits only the determination result for which consistency has been verified to the user terminal.

[0012] The control unit is characterized by individually verifying the continuity of the waveform, whether there is a sudden change in the phase difference, and whether there is a normal range of voltage and frequency for each of the received electrical phase phase data in order to exclude abnormal data distorted by disturbance signals, noise, or instantaneous voltage fluctuations during the phase determination process, excluding data that does not satisfy two or more of the verification criteria from the valid data set, and performing a phase difference calculation with the absolute phase reference data only on the valid data set remaining after exclusion.

[0013] The control unit generates multivariable input data before transmitting the determined phase information to the user terminal, the data including the determined phase information (a specific phase identification value among Phase A, Phase B, and Phase C), the absolute time at which the determination was performed (a synchronization time value calculated by cross-verifying the reference time and the server internal time), the average and standard deviation of the multiple measurement phase difference values ​​derived during the phase difference calculation process, the unique identification information of the finder device (including a serial number and connection location coordinates), the reference number and creation time of the absolute phase reference data, and the number of occurrences of abnormal data excluded during the determination process and the exclusion reason code; the control unit numerically substitutes each of the multivariable input data by applying a random number value calculated from a random number generator as a weighting coefficient, and applies a polynomial-based key operation to the substituted data set, wherein the key operation is a sequential operation comprising a first-order combination of the time information variable and the phase difference variable, a combination of the phase identification variable and the finder device identification variable through a multiplication operation, and an XOR combination of the results obtained by converting the remaining variables (reference number and exclusion reason code) using a hash function. The method is characterized by performing a procedure, finally generating an encrypted result value derived as a result of the sequential operation procedure of XOR combination, and transmitting the generated encrypted result value to the user terminal. Effects of the invention

[0014] By generating absolute phase reference data from a reference time and a transformer PT voltage signal through a standard phase detection device installed at a substation, and by storing and managing this data in the control unit of a server, the problem of reference phase information becoming unstable due to time delays or communication errors, as in the past, can be resolved.

[0015] The control unit of the server provides absolute phase reference data in real time upon request from the user terminal, and receives electrical phase data measured by an AI-based finder device at the site and directly compares and calculates phase data containing external noise based on self-learned data patterns, thereby enabling immediate determination of which of phases A, B, or C the phase connection corresponds to, while excluding error data.

[0016] In addition, by repeatedly collecting electrical phase data multiple times and averaging only the values ​​among the repeated measurements that fall within the allowable range of self-learned criteria and deviations for determination, the possibility of misdetermination due to disturbances or instantaneous voltage fluctuations can be significantly reduced compared to conventional methods that relied on a single measurement value. Through this, field workers can secure stable and reliable phase determination results, and a mobile-linked determination system based on AI-based three-phase power system phase determination and error correction based on a reference time source can be provided, which prevents reverse phase connections, load imbalances, and power accidents caused by incorrect phase connections. Brief explanation of the drawing

[0017] FIG. 1 is a diagram illustrating the schematic configuration of a mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction according to one embodiment of the present invention. FIG. 2 is a diagram illustrating the specific configuration of a mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction according to an embodiment of the present invention. FIG. 3 is a flowchart illustrating the operation of a mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction according to an embodiment of the present invention. Specific details for implementing the invention

[0018] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In the drawings, identical reference numbers or symbols refer to components that perform substantially the same function, and the size of each component in the drawings may be exaggerated for clarity and convenience of explanation. However, the technical concept of the present invention and its core components and operations are not limited only to the components or operations described in the following embodiments. In describing the present invention, if it is determined that a detailed description of known technologies or components related to the present invention may unnecessarily obscure the essence of the present invention, such detailed description will be omitted.

[0019] In embodiments of the present invention, terms including ordinal numbers, such as first, second, etc., are used solely for the purpose of distinguishing one component from another, and singular expressions include plural expressions unless the context clearly indicates otherwise. Furthermore, in embodiments of the present invention, terms such as 'composed of,' 'include,' 'have,' etc., should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Additionally, in embodiments of the present invention, 'module' or 'part' performs at least one function or operation and may be implemented in hardware or software, or as a combination of hardware and software, or may be integrated into at least one module and implemented as at least one processor. Furthermore, in embodiments of the present invention, 'at least one' among a plurality of elements refers not only to all of the plurality of elements but also to each individual element excluding the remainder or all combinations thereof. Additionally, "configured to" may be used interchangeably with, depending on the context, for example, "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of." "Configured to" does not necessarily mean that it is "specifically designed to" in hardware. Instead, in some situations, the expression "device configured to" may mean that the device is "capable of" doing so in conjunction with other devices or components.For example, the phrase “a processor configured (or set) to perform A, B, and C” may mean a dedicated processor for performing said operations (e.g., an embedded processor), or a generic-purpose processor (e.g., a CPU or an application processor) capable of performing said operations by executing one or more software programs stored in a memory device.

[0020] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. This description is intended to be detailed enough for a person skilled in the art to easily practice the invention, and it should be noted that the technical scope and concept of the present invention are not limited thereby.

[0021] FIG. 1 is a diagram illustrating the schematic configuration of a mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction according to an embodiment of the present invention, FIG. 2 is a diagram illustrating the specific configuration of a mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction according to an embodiment of the present invention, and FIG. 3 is a diagram illustrating a flowchart of the operation of a mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction according to an embodiment of the present invention.

[0022] Referring to FIGS. 1 to 3, a mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction according to one embodiment of the present invention comprises a user terminal (100) including a display unit (120) and a user input unit (110), and a server (200) connected to the user terminal (100) via a wired or wireless network.

[0023] Meanwhile, the server (200) includes a communication unit (210); a storage unit (220); and a control unit (230); and the configuration of each of these will be described later.

[0024] A reference time according to one embodiment of the present invention refers to time data set based on absolute time information obtained from a Global Positioning System (GPS), Precision Time Protocol (PTP, IEEE 1588), IRIG-B signal, Rubidium atomic clock, Oven Controlled Crystal Oscillator (OCXO), etc. (hereinafter referred to as “reference time source”) in a Global Navigation Satellite System signal transmitted from an artificial satellite. Although the reference time sources generate the reference time using different physical principles, they are all synchronized with Coordinated Universal Time (UTC) or based on an absolute time axis corresponding thereto.

[0025] The reference time is obtained through a procedure that receives time synchronization signals periodically provided from a reference time source and compares and corrects them with the time information of an internal oscillator. For example, in the case of GPS, time data is restored by tracking the correlation of PRN codes, navigation messages, and carrier phases included in satellite navigation signals, while in the case of PTP, it is corrected by calculating the delay time between the Sync message and the Follow-Up message according to the IEEE 1588 protocol. The IRIG-B signal is input in the form of AM or DC level-modulated time pulses and is restored into hour, minute, and second information through frame decoding, and the Rubidium or OCXO suppresses error accumulation over a long period by utilizing the phase stability of its own frequency reference.

[0026] In addition, in the embodiments of the present invention, the reference time is not merely data for displaying absolute time, but is used as a reference clock to form absolute phase reference data by combining it with phase information extracted from the transformer PT voltage signal. The reference time is not limited to a specific hardware module or a single communication protocol, but can be implemented by including a GPS receiver, IEEE 1588-supported Ethernet equipment, an IRIG-B decoder module, or a high-precision rubidium / OCXO timing module. Therefore, in the embodiments of the present invention, the reference time is a comprehensive concept that can be obtained through various time synchronization technologies or hardware configurations, and can be freely applied within the scope that a person skilled in the art can understand and implement.

[0027] A three-phase power system according to one embodiment of the present invention refers to an entire power grid that generates, transmits, distributes, and consumes alternating current power having three phases (A phase, B phase, and C phase). A three-phase power system is generally configured so that the phase difference between each phase is maintained at 120°, thereby allowing for higher power transmission efficiency compared to single-phase power and stable maintenance of load balance.

[0028] A three-phase power system can be broadly divided into the generation, transmission, distribution, and load sections. The generation section produces three-phase AC power through rotating machinery (generators) from various energy sources, such as hydroelectric, thermal, nuclear, and renewable energy generators. The three-phase power output from the generators is stepped up to high voltage and supplied to the transmission section, which performs long-distance power transmission over hundreds of kilometers using transmission towers and high-voltage transmission lines.

[0029] Transmitted power is converted into at least one of extra-high voltage, high voltage, intermediate voltage, or low voltage through transformers at substations, and then distributed to various load facilities, such as industrial complexes, buildings, and residential areas, through the distribution section. The distribution section includes components such as distribution lines, distribution transformers, protective relays, and switches, and the phase relationship of the three-phase power must be maintained during this process.

[0030] The load section is the area that actually consumes three-phase power and includes large motors, industrial equipment, heating and cooling systems, and household electronic devices. Depending on the consumption characteristics of the load section, currents in each phase may flow unevenly, which can lead to problems such as three-phase imbalance, reverse phase connection, and power quality degradation.

[0031] In the embodiments of the present invention, the three-phase power system is not limited to a specific voltage level or a specific facility structure. It can include not only ultra-high voltage transmission networks such as 154kV, 345kV, and 765kV, but also distribution networks of 22.9kV underground and overhead lines, and 380 / 220V low-voltage systems, and both AC three-phase three-wire or four-wire structures are applicable. Of course, vector groups can be applied to these. Furthermore, it can be equally applied not only to domestic power systems but also to power system structures according to international standards such as IEC and IEEE.

[0032] Therefore, a three-phase power system comprehensively refers to the entire network of power supply and consumption consisting of power sources, transformers, transmission and distribution lines, protection devices, switching devices, load facilities, etc., and in the embodiments of the present invention, it is utilized to generate, manage, and determine reference phase information within such a power system.

[0033] Phase detection of a three-phase power system according to an embodiment of the present invention refers to a procedure for determining, using phase information aligned with the time axis, which phase among A, B, and C corresponds to an electrical signal acquired at an arbitrary measurement point of a three-phase AC power grid, based on an absolute phase reference. The procedure may consist of steps of securing reference data including a reference time and a reference phase, acquiring field measurement data, time synchronization, phase estimation, calculation of phase difference, and phase label determination, and the specific implementation of each step may be realized through hardware, software, or a combination of both. Here, "absolute phase reference" refers to the three-phase relationship established at a standard system point, and "phase label determination" refers to assigning A / B / C identification values ​​to the measured signal.

[0034] As sub-components of the three-phase power system phase detection, examples include (i) a reference data acquisition unit, (ii) a measurement data acquisition unit, (iii) a time synchronization unit, (iv) a phase estimation unit, (v) a comparison and judgment unit, and (vi) a result recording unit. The reference data acquisition unit constructs absolute phase reference data from the reference time and the PT voltage of the reference point, etc., or receives and stores reference data already calculated from a higher-level system such as a server. The measurement data acquisition unit acquires waveforms from voltage probes, clip-type current sensors, non-contact electric field sensors, etc., and, if necessary, obtains the entire raw waveform including harmonic components or a waveform passed through a low-pass filter. The time synchronization unit aligns the measurement time to the reference time system using at least one of different time sources such as GPS, PTP (IEEE 1588), IRIG-B, Rubidium, OCXO.

[0035] The phase estimation unit refers to a functional block that calculates phase information from an acquired waveform. Phase calculation can be performed using one or more different methods, such as a zero-crossing-based method, fundamental phase estimation by DFT / FFT, instantaneous phase estimation using Hilbert transform, or synchronous phase tracking by a software PLL. The output of the phase estimation unit is generally expressed as "electric phase data," which can be defined as a data tuple containing a time tag (t), fundamental frequency (f), effective voltage or current magnitude (Vrms / Irms), quality index (Q), and phase angle (φ). Signal processing conditions, such as the sampling frequency, anti-aliasing filter order, and windowing method, can be set according to the grid frequency (e.g., 50 / 60 Hz) and the field noise environment. Additionally, these conditions can be set by reflecting data obtained through self-learning based on artificial intelligence.

[0036] The comparison and judgment unit performs time alignment between the electric phase data and the absolute phase reference data, and then the phase difference Δ Calculate and Δ The A / B / C labels are determined by determining which cluster α belongs to among clusters spaced at 120° intervals. Phase difference calculation is performed using modular arithmetic (e.g., Δ). =( meas- It may include mod 360°), and cluster determination may be performed using a proximity criterion with an tolerance band, a cross-correlation-based similarity criterion, or a combination of multiple criteria. The tolerance band may be calculated by reflecting uncertainties such as sampling jitter, measurement noise, and total distortion (THD), and may be expressed as a single threshold or an adaptive threshold for each interval.

[0037] To ensure the reliability of phase detection, the result recorder may collect multiple phase difference samples through repeated measurements under the same conditions, construct a valid data set by excluding outliers based on statistical tests (deviation, standard deviation, interquartile range, etc.), and then determine the final phase label by applying combination rules such as mean, weighted mean, and majority vote. If necessary, the time domain cross-correlation, frequency domain coherence, and consistency indicators between waveform segments may be calculated in parallel to determine the judgment reliability, and if the reliability falls below the lower limit, re-measurement or measurement interval extension may be performed.

[0038] Depending on field conditions, phase shifts caused by transformer vector groups, phase sequence (ABC / CBA) inversion, the presence or absence of a neutral line, load imbalance, harmonics, and intermittent disturbances may be present. To compensate for these factors, phase detection can refer to vector group correction parameters within the reference data or reset the comparison standard by performing a phase sequence identification routine in advance. Correction can be implemented through the application of a fixed angle shift, line voltage↔phase voltage conversion, or reference frame rotation, but is not limited to a specific method.

[0039] The phase detection results may be stored and transmitted in the form of a data code including a phase label, judgment time, phase difference statistics, quality indicators, and measurement unit identification information. The utilization of the results includes various applications such as verifying equipment connections in distribution automation systems, confirming phase alignment during system expansion, and managing maintenance history, but is not limited to specific applications. In one embodiment of the present invention, each component and processing step may be implemented in any structure such as a control unit of a server, a local control module of a field measurement unit, or a distributed combination thereof, and either one or both of voltage and current may be used as measurement signals. It may be applied within a range selectable by a person of ordinary skill, regardless of wired or wireless communication methods, voltage grades, or distribution / transmission levels.

[0040] Mobile-linked determination according to one embodiment of the present invention refers to an entire procedure for mutually linking reference data managed by a server with electrical phase information measured at the site via a user terminal, and performing phase determination based on the results of this linkage. This may, of course, include a procedure utilizing an AI-based intelligent mobile app. Mobile-linked determination allows an operator to directly verify and control the phase determination process through the display and input sections of the user terminal, and includes a function for coordinating data exchange and collection between the server's control section and the field finder device in real time.

[0041] Examples of sub-components for mobile linkage determination include (i) a communication module, (ii) a synchronization management unit, (iii) a comparison and determination engine, and (iv) a visualization and output unit. The communication module is responsible for the function of the user terminal transmitting and receiving data to and from the server via various wired and wireless networks such as LTE, 5G, Wi-Fi, and Bluetooth. At this time, absolute phase reference data provided by the server and electrical phase data collected by the finder device are received simultaneously, and error detection and retransmission request procedures may be included to minimize time delay or packet loss between the two data. It goes without saying that this may include a procedure for detecting abnormal data caused by disturbance signals, noise, instantaneous voltage fluctuations, etc., based on self-learned criteria.

[0042] The synchronization management unit adjusts the difference between the internal time of the user terminal, the server's reference time, and the measurement time of the finder device. It corrects the difference in reference times between the server and the terminal using protocols such as GPS time, PTP, and IRIG-B, and aligns the received measurement data with the reference time axis by assigning time tags to it. This enables waveform information acquired in the field and the server's reference data to be compared at the same reference time.

[0043] The comparison and discrimination engine can be implemented in a user terminal application or a server-linked module, and identifies the phase by comparing absolute phase reference data with electrical phase phase data. The comparison method may include phase difference calculation, cluster identification, averaging of multiple measurements, and outlier removal, and is not limited to a specific algorithm. The comparison result is output as a phase identification value indicating whether it is Phase A, Phase B, or Phase C, and additionally, the quality of the result can be supplementarily provided by quantifying the discrimination reliability.

[0044] The visualization and output unit displays the identified phase information on the user terminal screen in the form of graphics, numbers, colors, measurement photos, etc. For example, it can assign a unique color to each phase or visually represent a phase difference graph, and allows comparison with past identification results through a log saving function. Additionally, it may include functions to attach photos of the measurement direction to reconfirm phase identification at a specific location via user input, or to report the identification results to a server.

[0045] Therefore, mobile connectivity determination is not merely limited to the comparison of field data and server data, but encompasses the entire series of processes involving communication, synchronization, comparison, and visualization centered around the user terminal. In the embodiments of the present invention, such mobile connectivity determination is performed through the interaction between the server, the user terminal, and the finder device, and is not limited to a specific protocol, a specific terminal type, or a specific network method, but encompasses various implementation means that can be selected by a person skilled in the art.

[0046] A user terminal (100) according to one embodiment of the present invention includes, for example, a personal computer, a server computer, a handheld or laptop device, a mobile device (mobile phone, PDA, media player, etc.), a multiprocessor system, a consumer electronic device, a mini computer, a mainframe computer, a distributed computing environment including any of the aforementioned systems or devices, and an edge computing environment in which data is processed at the edge where data is generated rather than at a central server, and the configuration is not limited only to what is described.

[0047] The user terminal (100) may include at least one processor and memory. Here, the processor may include, for example, a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), and may have multiple cores.

[0048] The memory may be volatile memory (e.g., RAM, etc.), non-volatile memory (e.g., ROM, flash memory, etc.), or a combination thereof. Additionally, the user terminal (100) may include additional storage. The storage includes, but is not limited to, magnetic storage, optical storage, etc. The storage may store computer-readable instructions for implementing one or more embodiments disclosed herein, and may also store other computer-readable instructions for implementing an operating system, an application program, etc. Computer-readable instructions stored in the storage may be loaded into memory to be executed by a processor.

[0049] Additionally, the user terminal (100) may include a user input unit (110) and an output device. The user input unit (110) may include, for example, a keyboard, a mouse, a pen, a voice input device, a touch input device, an infrared camera, a video input device, or any other input device. Additionally, the output device may include, for example, one or more displays, speakers, printers, or any other output devices. Additionally, the computing device may use an input device or an output device provided in another computing device as the user input unit (110) or output device. Additionally, the computing device may include a communication module that enables the computing device to communicate with another device. Here, the communication module may include a modem, a network interface card (NIC), an integrated network interface, a radio frequency transmitter / receiver, an infrared port, a USB connection, or other interfaces for connecting the computing device to another computing device. The communication module may include a wired connection or a wireless connection.

[0050] Each component of the user terminal (100) may be connected by various interconnections such as a bus (e.g., peripheral component interconnection (PCI), USB, firmware (IEEE 1394), optical bus structure, etc.) or may be interconnected by a network. Terms such as “component,” “system,” etc. used in this specification generally refer to computer-related entities that are hardware, a combination of hardware and software, software, or running software.

[0051] A user terminal (100) according to one embodiment of the present invention may include a display unit (120), and the method of implementing the display of the display unit (120) is not limited and may be implemented in various display methods such as liquid crystal, plasma, light-emitting diode, organic light-emitting diode, surface-conduction electron-emitter, carbon nanotube, nanocrystal, etc. In the case of a liquid crystal method, the display unit (120) includes a liquid crystal display panel, a backlight unit that supplies light to the liquid crystal display panel, and a panel driving unit that drives the liquid crystal display panel. Meanwhile, the display unit (120) may be implemented as an OLED panel, which is a self-emissive element, without a backlight unit.

[0052] A server (200) according to one embodiment of the present invention may include a communication unit (210), a storage unit (220), and a control unit (230).

[0053] A communication unit (210) according to one embodiment of the present invention can communicate with a user terminal (100) or other external electronic devices, etc., via wired or wireless communication methods. Therefore, in addition to a connection unit including a connector or terminal for wired connection, it can be implemented in various other communication methods. For example, it can be configured to perform one or more of Wi-Fi, Bluetooth, Zigbee, infrared communication, Radio Control, Ultra-Wide Band (UWM), Wireless USB, Near Field Communication (NFC), and Radio Frequency (RF). The communication unit (210) may include communication modules such as Bluetooth Low Energy (BLE), Serial Port Profile (SPP), Wi-Fi Direct, infrared communication, Zigbee, and Near Field Communication (NFC). Additionally, the communication unit (210) can be implemented in the form of a device, a software module, a circuit, a chip, etc.

[0054] A communication unit (210) according to one embodiment of the present invention may include various communication modules as described above, and may include an IoT communication module having an IoT network for each carrier. An IoT communication module may refer to any IoT communication network in which a plurality of objects having separate communication units (210) are connected through a network to enable services based on various platforms. By using such an IoT communication module, a smoother communication network can be provided within a set area.

[0055] A storage unit (220) according to one embodiment of the present invention may receive information from a user terminal (100) or from an external search platform through a communication unit (210) and store it, and may receive text information and image information included in a plurality of web pages received by a control unit (230) and store them. The storage unit (220) may store various data according to the processing and control of the control unit (230) described later. The storage unit (220) may be accessed by the control unit (230) to perform reading, recording, modification, deletion, updating, etc. of data. The storage unit (220) may include non-volatile memory such as flash memory, hard disk drive, and SSD (solid-state drive) so as to preserve data regardless of whether system power is provided to the server (200). Additionally, the storage unit (220) may include volatile memory, such as a buffer or RAM, for temporarily loading data processed by the control unit (230).

[0056] A control unit (230) according to one embodiment of the present invention can perform control for the operation of various components of a server (200). The control unit (230) may include a control program (or instruction) that enables such control operation, an inactive memory in which the control program is installed, a volatile memory in which at least a portion of the installed control program is loaded, and at least one processor or CPU (Central Processing Unit) that executes the loaded control program. In addition, such a control program may be stored in an external electronic device other than the server (200).

[0057] The control program may include program(s) implemented in at least one form among BIOS, device driver, operating system, firmware, platform, and application. In one embodiment, the application may be pre-installed or stored in the server (200) at the time of manufacturing the server (200), or may be installed in the server (200) based on the received data by receiving data of the application from an external source when it is used later. The data of the application may be downloaded to the server (200) from an external server, such as an application market, for example, a platform according to the present invention, but is not limited thereto. Meanwhile, the control unit (230) may be implemented in the form of a device, S / W module, circuit, chip, etc., or a combination thereof.

[0058] A mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction according to one embodiment of the present invention includes a standard phase detection device installed in a substation.

[0059] A standard phase detection device refers to a device that collects the reference time of a reference time source and transformer PT voltage signals, and combines these signals to generate absolute phase reference data, in order to reliably secure reference phase information at a specific point in a three-phase power system.

[0060] A standard detection device can generally be divided into (i) a receiver of a reference time source, (ii) a voltage signal acquisition unit, (iii) a signal processing unit, (iv) a data generation unit, and (v) a communication interface unit. For example, the GPS receiver receives a time signal synchronized with UTC from a satellite navigation system, and the received time signal may include code phase, carrier phase, navigation messages, etc. The voltage signal acquisition unit acquires the phase voltage or line voltage output from the PT of a substation and converts it into a digital signal through an analog-to-digital converter, and the sampling frequency, resolution, and filtering conditions can be set according to the system frequency and field environment.

[0061] The signal processing unit aligns the reference time and voltage signal of the received reference time source to the same time axis and performs operations to calculate the phase angle of each phase. The phase angle can be obtained by methods such as zero-crossing detection, FFT-based phase estimation, and PLL synchronization, and is not limited to a specific method. The data generation unit combines the aligned reference time and the calculated phase angle to construct absolute phase reference data, and the data may include time tags, phase voltage magnitudes, phase angles, quality indicators, etc.

[0062] The communication interface unit performs the role of transmitting the generated absolute phase reference data to a server or external device. The communication method may include one or more of wired Ethernet, optical communication, RS-485, or wireless methods such as LTE or 5G, and reliability can be ensured by including error detection codes (CRC), encryption protocols, and packet retransmission procedures during data transmission.

[0063] Accordingly, the standard phase detection device is defined as a device that performs a series of processes, including securing a reference time, acquiring substation voltage signals and calculating phase angles, generating absolute phase reference data, and communicating with a server. The embodiments of the present invention should be understood as encompassing a range that includes various signal collection, processing, and transmission means selectable by a person skilled in the art, rather than being limited to specific hardware structures or algorithmic methods.

[0064] According to one embodiment of the present invention, the standard phase detection device generates absolute phase reference data by combining the reference time and the phase information received from the transformer PT voltage signal based on the reference time received through the GPS receiver and the phase information, and transmits the generated absolute phase reference data to the server.

[0065] A standard phase detection device according to one embodiment of the present invention obtains a reference time by receiving a signal transmitted from a satellite through a GPS receiver. The GPS signal contains time information synchronized with UTC, and the GPS receiver calculates the reference time by restoring the navigation message, PRN code, and carrier phase. The calculated reference time is compared and corrected with the time of an internal oscillator and output as an absolute time value having accuracy in microseconds.

[0066] The standard phase detector simultaneously receives the system voltage signal from the potential transformer (PT). The PT voltage signal outputs the voltage waveforms of phases A, B, and C of the three-phase power system by reducing them, and this voltage is sampled through an analog-to-digital converter. The sampling frequency is set to at least 256 times the system frequency (e.g., 60 Hz) to reduce waveform distortion, and the pure fundamental component is secured by passing it through an anti-aliasing filter.

[0067] To extract phase information from sampled voltage data, zero-crossing detection or the Discrete Fourier Transform (DFT) can be performed. For example, performing a DFT on a voltage waveform v(t) yields the real part Re and the imaginary part Im of the fundamental frequency component, and the phase angle is calculated using the atan2(Im, Re) operation. At this time, the phase angle is synchronized with the timestamp assigned to each sample so as to be aligned with the reference time.

[0068] Phase information calculated from the reference time and the PT voltage signal is combined on the time axis. Specifically, the reference time Tgps and the PT voltage phase By matching data pairs (Tgps, It generates ). The data generated in this way is defined as absolute phase reference data, and this data contains time-independent absolute reference phase information. For example, absolute phase reference data is {Tgps = 2025-09-24 13:00:00.000001, Phase A A = 0°, B phase B = 120°, C phase It can be recorded as C = 240°.

[0069] The generated absolute phase reference data is transmitted to a server. During the transmission process, TCP / IP-based wired communication or wireless communication protocols such as LTE or 5G may be used, and a CRC code may be added to the transmission packet to verify data integrity. The absolute phase reference data that arrives at the server is recorded in a storage unit and subsequently used for comparison and identification with electrical phase data collected from the field.

[0070] A control unit according to one embodiment of the present invention stores the absolute phase reference data in the storage unit, and when a request signal for the absolute phase reference data is input from the user terminal, transmits the absolute phase reference data recorded in the storage unit to the user terminal.

[0071] A control unit according to one embodiment of the present invention records generated absolute phase reference data in a storage unit. The absolute phase reference data may be defined as a time-series data set including a reference time and a phase angle calculated from a PT voltage signal, and each data item is {Ti, A, B, It is composed in the form of {C, Q}. Here, Ti is a timestamp aligned to a reference time, A· B· C represents the phase angle of each phase (unit: degrees or rad), and Q represents the signal quality index. The control unit can sequentially add data to the storage unit whenever data is input, or packetize it at regular time intervals (e.g., every second, every 60 seconds) and record it in block units. The storage format can be implemented as CSV, JSON, binary array, etc., but is not limited to a specific format.

[0072] When a request signal is input from the above user terminal, the control unit recognizes it. The request signal can be implemented using various protocols, such as REST API calls, socket communication, or MQTT messages, and the basic structure of the request signal may take the form of {request_id, user_id, request_type, timestamp}. For example, if request_type is set to “absolute_phase_reference”, the control unit identifies that it is a request to call absolute phase reference data.

[0073] The control unit queries data that matches the request condition among the absolute image phase reference data recorded in the storage unit. The request condition may be data corresponding to a specific time (Tx), data from the last N seconds, or data within a specific interval [Tstart, Tend]. For example, if a user terminal requests “absolute image reference data from the last 10 seconds,” the control unit searches for records satisfying the condition timestamp ≥ (current time - 10 seconds) among the data recorded in the storage unit and controls the return of the set D = {d1, d2, … , dn}.

[0074] The retrieved absolute phase reference data undergoes a serialization process for transmission. The control unit converts the data into a transmittable format, such as a JSON string, Protobuf, or binary packet. To verify data integrity during transmission, a CRC16 or SHA256 hash value can be generated and appended to the packet. The final transmitted packet contains the structure {payload: absolute phase reference data, checksum: hash value, seq_no: packet number}.

[0075] The control unit transmits the converted absolute phase reference data to the user terminal. The transmission process can utilize reliable protocols such as TCP / IP, HTTPS, and WebSocket, and is applicable to both wireless networks (LTE, 5G, Wi-Fi) and wired networks (Ethernet, optical communication). The user terminal can decode and verify the received data, then display it on a screen or use it for subsequent calculations.

[0076] A control unit according to one embodiment of the present invention calculates the phase difference between the received electrical phase data and the absolute phase reference data when it receives electrical phase data collected by a finder device at the site through a power facility connection probe via the communication unit.

[0077] A control unit according to one embodiment of the present invention receives electrical phase data collected by a finder device at the field through a power facility connection probe. The finder device includes a connection probe connected to a distribution line or a substation terminal, and the connection probe can be implemented in various forms, such as a clip-type voltage sensor, a non-contact electric field sensor, or a current clamp sensor. The raw voltage or current signal obtained through the connection probe is sampled through an analog-to-digital converter, and a time tag is assigned to each sample.

[0078] The electric phase data acquired in this way is {Ti, It can be defined as a structure of the form {meas, V, f, Q}. Here, Ti is the sample time, meas represents the measured phase angle, V represents the effective voltage or current magnitude, f represents the grid frequency, and Q represents the signal quality indicator. Phase angle Meas can be calculated, for example, through FFT-based phase estimation, zero-crossing detection, or PLL synchronization algorithms, and the calculation formula is meas can be expressed as atan2(Im, Re).

[0079] The above electrical phase data is transmitted from the finder device to the communication unit of the server via a wireless communication module (Wi-Fi, LTE, 5G, Bluetooth, etc.) or a wired communication module (Ethernet, RS-485, etc.). The communication unit loads the received data into a buffer, verifies data integrity through an error detection code (CRC) or hash value, and then transmits it to the control unit.

[0080] The control unit calculates the phase difference by comparing the received electrical phase data with the absolute phase reference data recorded in the storage unit. Phase difference Δ is Δ = ( meas - ref) It is calculated as mod(360°), where ref is the absolute phase reference value synchronized with the reference time. The calculated Δ It is typically normalized within the range of ±180° and is used as a basis value to identify which phase among A, B, and C the measurement signal belongs to by determining whether it belongs to a cluster band near 0°, 120°, or 240°.

[0081] A control unit according to one embodiment of the present invention verifies whether the phase difference corresponds to a phase difference relationship of 120°, identifies which of the A phase, B phase, and C phase the electric phase corresponds to based on the verification result, and controls the transmission of the identified result to the user terminal.

[0082] A control unit according to one embodiment of the present invention comprises a phase difference Δ calculated by comparing electric phase data and absolute phase reference data. It verifies whether it conforms to the theoretical 120° phase difference relationship of a three-phase power system. During the verification process, the control unit determines the phase difference between each phase as Δ AB = ( A - B) mod(360), Δ BC = ( B - C) mod(360), Δ CA = ( C - A) Perform an operation in the form of mod(360) and determine whether each result falls within the range of 120° ± ε (ε is the tolerance, e.g., 5°). At this time, mod(360) is performed so that the result of the operation is normalized to the range of -180° to +180°.

[0083] If the verification result shows that the phase difference is within the allowable range, the control unit identifies which specific electrical phase is phase A, phase B, or phase C. For example, from reference data In the case where A is defined as 0°, Δ If it falls within the range of 0° ± ε, it is identified as Phase A; if it falls within the range of 120° ± ε, as Phase B; and if it falls within the range of 240° ± ε, as Phase C. This identification is not limited to a single sample, but is based on the average phase difference value avg(Δ) of multiple samples. n) = (ΣΔ It can be performed using n) / N, and the standard deviation std(Δ It is confirmed as a final judgment only if n) is included within the allowable range.

[0084] The identified result is the data structure {timestamp, identified_phase, Δ It is generated in the form {, quality_index}. Here, timestamp is the identification time synchronized with the reference time, identified_phase is a string value among “A”, “B”, or “C”, and Δ is the result of the phase difference operation, and quality_index represents the discrimination confidence level (e.g., 0~100%).

[0085] The control unit transmits the generated identification result to the user terminal. During transmission, it is serialized in the form of JSON, Protobuf, or binary packets, and a checksum for error detection may be added. The user terminal can decode the received data and display it on the screen or use it for subsequent control procedures.

[0086] A control unit according to one embodiment of the present invention, when calculating the phase difference between the absolute phase reference data and the electric phase data, repeatedly collects the electric phase data a predetermined number of times to obtain multiple measurement values ​​under the same conditions, and performs reference time alignment and phase difference calculation for each of the obtained multiple measurement values ​​to derive multiple phase difference result values.

[0087] A control unit according to one embodiment of the present invention does not acquire electrical phase data sporadically, but collects it repeatedly at least N times, which is a preset number. Here, N can be set, for example, 5 times, 10 times, 30 times, etc., and the collection interval is adjusted to an integer multiple of the period of the system frequency (e.g., 1 / 60 second = 16.67 ms at 60 Hz). Through this, each measurement is acquired under the same power cycle conditions and maintained in a state where it can be compared.

[0088] The raw data obtained from each iteration includes a time tag Ti and a voltage waveform sample vi(t). To align this with a reference time, the control unit synchronizes the local time of each collected sample with Tgps. The alignment process is performed by estimating the time error expressed as ΔT = Tlocal - Tgps and correcting it for all samples, so that, as a result, each data is mapped to the same reference time axis.

[0089] For each aligned sample, the control unit performs a phase difference calculation. Applying the DFT to the voltage waveform vi(t) yields the real part Re and the imaginary part Im of the fundamental frequency component, and the phase angle It is calculated as meas = atan2(Im, Re). The absolute phase reference value recorded in the storage unit. Compared to ref, the phase difference Δ i = ( meas - ref) It is calculated as mod(360). Here, mod(360) is an operation that normalizes the result to a range of 0° to 360°.

[0090] If this process is performed for N repetitions, the set of multiple phase difference result values ​​ΔΦ = {Δ 1, Δ 2, … , Δ {N} is derived. The control unit stores this set so that it can be utilized for averaging, variance verification, outlier removal, etc., in subsequent processing steps.

[0091] A control unit according to one embodiment of the present invention selects only the result values ​​among the derived plurality of phase difference result values ​​whose deviation is included within a preset allowable range, performs an average operation, and performs phase identification by comparing the result of the average operation with the absolute phase reference data.

[0092] A control unit according to one embodiment of the present invention comprises a plurality of sets of phase difference result values ​​ΔΦ = {Δ 1, Δ 2, … , Δ The deviation of each result is calculated for {N}. Here, the deviation is each result value Δ It can be defined as the difference between i and the overall mean μ, where dev_i = |Δ It is calculated in the form i - μ|. The average μ is μ = (ΣΔ It is derived as i) / N.

[0093] The control unit selects only data where the calculated deviation dev_i is less than or equal to the preset tolerance range ε ​​as valid values. For example, if ε is set to 5°, Δ satisfying the condition dev_i ≤ 5° Only the i value is filtered. The data set selected in this way can be defined as ΔΦvalid.

[0094] For the set ΔΦvalid, the control unit performs the mean operation again. The mean is μvalid = (ΣΔ It is calculated as valid_j) / M, where M is the number of data points satisfying the tolerance condition. Since only values ​​with outliers removed are included in the average calculation process, a stable representative phase difference is derived as a result.

[0095] The control unit uses the calculated representative phase difference μvalid as the absolute phase reference data. Compare with ref. The comparison process is Δ rep = (μvalid - ref) Includes the mod(360) operation, and Δ Determines which cluster band around 0°, 120°, or 240° rep belongs to. The determination criterion is |Δ It can be set as an interval satisfying the condition rep - k| ≤ ε (k = 0, 120, 240).

[0096] Through this process, the control unit identifies which of phases A, B, or C the corresponding electrical phase is. For example, Δ rep If 0°, it is phase A, Δ rep If it is 120°, it is phase B, Δ rep If it is 240°, it is determined to be phase C.

[0097] A control unit according to an embodiment of the present invention performs a comparison and determination process between the absolute phase reference data and the electrical phase data, and records the determined phase information, the time information at which the determination was performed, and the identification information of the finder device together and stores them as log data in the storage unit, verifies the consistency of determination by comparing the past determination result and the current determination result at the same power facility connection location using the stored log data, and if a determination discrepancy is detected as a result of the comparison, the control unit detects and excludes abnormal data caused by disturbance signals, noise, instantaneous voltage fluctuations, etc., and then re-executes the determination process to resolve the determination discrepancy, and finally transmits only the determination result for which consistency has been verified to the user terminal, thereby controlling the field inspector to reliably verify the determined phase result.

[0098] A control unit according to one embodiment of the present invention organizes the result in the form of a data structure when electrical phase determination is performed. This data is {timestamp, identified_phase, Δ It can be defined as {, finder_id}. Here, timestamp is the absolute time synchronized with the reference time, identified_phase is the identified phase (one of A, B, or C), and Δ is the result of the phase difference operation, and finder_id represents the unique identification number of the finder device (e.g., MAC address, serial number, GPS coordinates included). The control unit records this data in the storage unit as log data. The log can be implemented in various ways, such as a simple array structure, a chronological index DB, or a Key-Value Store.

[0099] The stored log data is used to compare past and current determination results at the same power facility connection location. The control unit searches for logs at the same location based on the finder_id and connection coordinates, and compares the recently recorded identified_phase_prev with the newly calculated identified_phase_curr. If the comparison result shows identified_phase_prev = identified_phase_curr, it is determined that consistency has been maintained; otherwise, it is recorded as a determination discrepancy.

[0100] If a discrimination mismatch is detected, the control unit re-collects the same data set or removes outliers from the existing data and re-performs the phase difference operation on only the remaining valid data. For example, Δ The mean μ and deviation dev_i are recalculated from the set, and a new representative phase difference μvalid is derived from the remaining data after excluding values ​​where dev_i > ε. Then, μvalid is compared with the absolute phase reference data to update the final phase determination.

[0101] Finally, only determination results whose consistency has been verified are transmitted to the user terminal. The transmitted data is serialized and sent in the form of {timestamp, identified_phase, reliability_score}, and the reliability_score can be calculated as the match rate among the last M determinations (e.g., reliability_score = matched_count / M × 100%). The user terminal receives this data and displays it on the screen or saves it in the form of a report, allowing the field inspector to reliably verify the determination results.

[0102] A control unit according to one embodiment of the present invention verifies the continuity of a waveform to ensure the quality of electrical phase data input during the phase determination process, and performs the following three-step self-verification process for each measurement data. That is, an artificial intelligence-based waveform analysis model evaluates whether the signal is consistent in terms of time series, a deep learning-based anomaly detection model detects abrupt phase changes, and determines whether it is normal by comparing it with a reference frequency and voltage range.

[0103] The control unit applies an AI-based waveform analysis model in the first step to verify the time-series continuity of the waveform. This waveform analysis model is composed of a neural network that takes a time-series segment of a certain length as input and learns the statistical pattern of the rate of change between each sample, Δv(t) = |v(t) ? v(t ? 1)|, and determines whether the input waveform segment corresponds to the continuity pattern of a normal power waveform. For example, in a normal waveform, Δv(t) is measured to have a distribution below a specific threshold range T_cont, and the control unit calculates a continuity score S_cont by comparing the mean and variance of Δv(t) with a reference time-series pattern generated within the model. If S_cont is greater than or equal to a reference value K_cont, the corresponding waveform segment is determined to be a continuous and normal waveform.

[0104] In the next step, the control unit applies a deep learning-based anomaly detection model to detect abrupt phase changes or sudden waveform deformations. The anomaly detection model separates normal and abnormal patterns using a Long Short-Term Memory (LSTM) or 1D CNN structure based on the change amount dφ / dt of the input phase time series {φ(t1), φ(t2), …}. During the training process, the model constructs a probability density function of the normal group based on the average slope μ_φ and standard deviation σ_φ of normal phase changes, and determines an outlier if the input phase change amount exceeds a statistical threshold, such as |φ(t+1) - φ(t)| > μ_φ + 3·σ_φ. The control unit determines whether the corresponding waveform exhibits abnormal changes due to abrupt changes, distortion, or noise interference by referring to the anomaly score S_anom output by the model.

[0105] In the final step, the control unit determines the physical normality of the measurement data by comparing it with reference frequency and voltage ranges. Frequency verification is performed by measuring the zero-crossing interval Δt_zc of the input waveform and calculating the frequency f = 1 / (2·Δt_zc), and checking whether the calculated f falls within the allowable range (f_min ≤ f ≤ f_max). Voltage verification is performed by calculating the periodic RMS (root mean square) voltage Vrms = sqrt(Σv(t)^2 / N) to determine whether the measured Vrms falls within the specified voltage range (V_min ≤ Vrms ≤ V_max). If the frequency or voltage is outside the allowable range, the corresponding data is considered abnormal data caused by power equipment malfunction, poor contact, or disturbance noise.

[0106] In this manner, in an embodiment of the present invention, the control unit individually calculates a continuity score S_cont, an anomaly detection score S_anom, and a frequency and voltage normality determination result, and recognizes the corresponding electrical phase data as valid data only when two or more of these verification results satisfy the normality condition. This procedure is not limited to a specific neural network structure or a single calculation formula, and is configured to allow a person skilled in the art to implement waveform characteristic analysis, anomaly detection techniques, and frequency and voltage verification logic widely used in time-series-based power signal analysis in various ways.

[0107] A control unit according to one embodiment of the present invention individually verifies the continuity of the waveform, whether there is a sudden change in the phase difference, and whether the voltage and frequency are within a normal range for each of the received electrical phase phase data in order to exclude abnormal data distorted by disturbance signals, noise, or instantaneous voltage fluctuations during the phase determination process.

[0108] A control unit according to one embodiment of the present invention first verifies the continuity of a waveform to ensure the quality of electrical phase data input during the phase determination process. A collected voltage waveform vi(t) is recorded at a constant sampling period Ts, and the voltage difference between adjacent samples is calculated as Δv = |vi(t+Ts) - vi(t)|. The control unit checks whether the waveform is intermittent or abruptly cut by determining whether Δv is less than or equal to an allowable threshold value vmax_diff. If Δv repeatedly exceeds the reference value, the data is determined to be discontinuous and excluded.

[0109] Next, the control unit verifies whether there is a sudden change in the phase difference. The phase difference between two continuously measured time points is Δ k, Δ Let k+1 be the rate of change, Δ diff = |Δ k+1 - Δ It is defined as k|. The control part is Δ diff ≤ The max_jump (e.g., 10°) condition is checked to determine whether the phase difference has abnormally high values ​​within a short period. If the condition is not satisfied, the phase difference in that section is considered to be due to noise and is excluded.

[0110] In addition, the normal range of the voltage is verified. The RMS value of the sampled voltage, Vrms, is calculated as Vrms = sqrt( (1 / N) Σ vi² ). The control unit checks whether Vrms falls within the set voltage allowable range [Vmin, Vmax]. For example, in a 220V system, Vmin can be set to 198V and Vmax to 242V, and data outside the range is determined to be an abnormal state and excluded.

[0111] The normal range of the frequency is also verified. The control unit estimates the frequency f = count / (2ΔT) by counting the number of zero crossings within a certain time interval ΔT, or detects the fundamental frequency based on FFT. If the estimated f falls outside the range of the nominal frequency (e.g., 60Hz) ± allowable deviation (±0.5Hz), the data at that time is determined to be unstable and excluded.

[0112] In this way, after independently verifying waveform continuity, abrupt fluctuations in phase difference, voltage range, and frequency range, the control unit marks any data record that fails to satisfy even one criterion as abnormal data and excludes it from the phase determination operation. Consequently, only valid data that has passed verification is used in the determination process, thereby significantly reducing or completely eliminating the possibility of misdetermination caused by disturbance signals, noise, or instantaneous voltage fluctuations.

[0113] A control unit according to one embodiment of the present invention excludes data that does not satisfy two or more of the verification criteria from the valid data set, and performs a phase difference operation with the absolute phase reference data only on the valid data set remaining after exclusion.

[0114] A control unit according to one embodiment of the present invention evaluates four verification criteria for individual electrical phase data: waveform continuity, phase difference fluctuation rate, voltage range, and frequency range. For each data record, the verification result can be expressed as {C1, C2, C3, C4}, where C1=1 means waveform continuity passed, C2=1 means phase difference fluctuation rate passed, C3=1 means voltage range passed, and C4=1 means frequency range passed. A value of 0 means that the corresponding criterion was not passed.

[0115] The control unit determines data records as abnormal data when ΣCi < 2, that is, when two or more of the four criteria are not satisfied. For example, if C1=0, C2=0, C3=1, and C4=0, the total ΣCi=1, so the corresponding data is excluded from the valid data set. Conversely, if ΣCi ≥ 2 is satisfied, the corresponding data is considered valid and included in subsequent operation steps.

[0116] After the exclusion process, the valid data set ΔΦvalid = {Δ 1, Δ 2, … , Δ {M} is formed. Here, Δ i is the phase difference value calculated from the valid data, and M is the number of valid data. The control unit uses absolute phase reference data only for this set. Performs a comparison operation with ref. The phase difference operation is Δ i_valid = ( meas_i - It is defined in the form of mod(360) and is repeated for each valid data.

[0117] By performing discrimination operations using only such filtered data, outliers caused by disturbances, noise, and instantaneous fluctuations are prevented from interfering with the image identification process, and consequently, the accuracy of image discrimination is improved.

[0118] A control unit according to an embodiment of the present invention generates multivariable input data including, before transmitting the determined phase information to the user terminal, the determined phase information (a specific phase identification value among phases A, B, and C), the absolute time at which the determination was performed (a synchronization time value calculated by cross-verifying the reference time of the reference time source and the internal time of the server), the average and standard deviation of the multiple measurement phase difference values ​​derived during the phase difference calculation process, the unique identification information of the finder device (including a serial number and connection location coordinates), the reference number and creation time of the absolute phase reference data, and the number of occurrences of abnormal data excluded during the determination process and the exclusion reason code.

[0119] A control unit according to one embodiment of the present invention does not simply transmit the result of the phase determination process as a phase identification value, but generates multivariable input data including various additional information.

[0120] First, the identified phase information serves as an identifier indicating which of phases A, B, or C it corresponds to, and can be encoded in a vector form, for example, {A=0, B=1, C=0}. This enables storage and transmission of machine-readable values ​​rather than simple character displays.

[0121] Next, the absolute time uses the result of cross-verification by simultaneously referencing the reference time of the reference time source and the server's internal time. Given the reference time t_gps and the server's internal time t_srv, the control unit calculates Δt = |t_gps - t_srv|, and if the condition Δt ≤ ε (where ε is a tolerance in the range of several milliseconds) is satisfied, it calculates the synchronization time t_sync = (t_gps + t_srv) / 2. Through this, a reliable time value can be secured without relying on a single reference.

[0122] The multiple measurement values ​​derived during the phase difference calculation process are {Δ 1, Δ 2, … , Δ It is defined as {N}. The control unit for these is average μ = (ΣΔ i) / N and standard deviation σ = sqrt(Σ(Δ Calculate i - μ)^2 / N). μ represents the representative phase difference, and σ represents the degree of data dispersion; these two values ​​are used as the basis for determining discriminant reliability.

[0123] In addition, the unique identification information of the finder device includes a device serial number (ID_device) and connection location coordinates (x, y, z). The serial number is a unique code assigned at the time of manufacture, and the coordinates use actual location values ​​measured from the GPS module or the installation point. This allows for tracking the consistency of repeated determination results at the same location.

[0124] The reference number (ID_ref) and creation time (t_gen) of the absolute phase reference data are automatically assigned when the server generates the reference data, and are recorded as metadata to ensure accurate matching with the data at the time of determination.

[0125] Finally, the number of occurrences of abnormal data excluded during the screening process (k_outlier) and the exclusion reason code (Code_outlier) are included. For example, it specifically records which verification criterion failed, such as k_outlier=3 and Code_outlier={C1_fail, C3_fail, C4_fail}.

[0126] In this way, the control unit configures the phase identification value, synchronization time, phase difference statistics, device identification information, reference data reference information, and abnormal data log into a single multivariable input data ΔV = {ID_phase, t_sync, μ, σ, ID_device, (x,y,z), ID_ref, t_gen, k_outlier, Code_outlier}. This data structure can be used as an input value in subsequent encryption operations and reliability verification steps.

[0127] A control unit according to one embodiment of the present invention numerically substitutes each of the multivariable input data by applying a random number value calculated from a random number generator as a weighting coefficient, and applies a polynomial-based key operation to the substituted data set, wherein the key operation performs a sequential operation procedure in which a first combination of a time information variable and a phase difference variable, a combination of a phase identification variable and a finder device identification variable through a multiplication operation, and an XOR combination of the result obtained by converting a residual variable (reference number and exclusion reason code) into a hash function, and finally generates an encrypted result value derived from the result of the XOR combination sequential operation procedure, and transmits the generated encrypted result value to the user terminal.

[0128] A control unit according to one embodiment of the present invention numerically substitutes each variable by applying a random number-based weight before encrypting multivariable input data. A random number generator may use a pseudo-random number generator or a hardware random number generator, and the calculated random number value r_i is multiplied by each variable value v_i to be substituted in the form w_i = v_i × r_i. For example, if the phase difference average μ is calculated as 118.5° and the random number value r_1 is calculated as 0.973, it is substituted as w_1 = 118.5 × 0.973 = 115.35. Since this substitution process is performed independently for each variable, a different encrypted input is formed each time depending on the random number value, even for the same input.

[0129] Polynomial-based key operations are applied to the permuted data set {w_1, w_2, … , w_n}. The time information variable t_sync and the phase difference variable μ are combined in a linear manner and computed in the form f1 = a×t_sync + b×μ. Here, a and b are integer coefficients predefined within the control unit, and their ranges are adjusted through experimental verification. This process is intended to generate a single key element that simultaneously reflects both time and phase information.

[0130] In addition, the phase identification variable (ID_phase) and the finder device identification variable (ID_device) are combined through a multiplication operation. That is, the operation is performed as f2 = ID_phase × ID_device, and this value functions as a combined key valid only when a specific phase is identified in a specific device. For example, if ID_phase = 2 (Phase B) and ID_device = 10321, a result such as f2 = 20642 is obtained.

[0131] The residual variables, the reference data reference number (ID_ref) and the exclusion reason code (Code_outlier), are converted into a hash function. SHA-256 or a lightweight hash algorithm can be applied, and the result is defined as h = Hash(ID_ref || Code_outlier). Here, || signifies a string concatenation operation. Additionally, a current measurement unit of the finder, which simultaneously measures load current by phase, can be additionally installed to identify uneven loads.

[0132] In addition, a finder device according to one embodiment of the present invention may be configured to further include a current measuring unit for measuring the load current for each phase in real time along with the electrical phase data of each phase. The current measuring unit may be implemented using various current detection technologies, such as a non-contact clamp sensor, a shunt resistor-based current sensor, a Rogowski coil, or a Hall sensor method, and is not limited to a specific sensor method.

[0133] The current measuring unit is installed at a location corresponding to the conductors of phases A, B, and C, respectively, and is configured to simultaneously measure phase-specific current values ​​I_A, I_B, and I_C at the same time. The control unit calculates, for example, ΔI_AB = |I_A ? I_B|, ΔI_BC = |I_B ? I_C|, and ΔI_CA = |I_C ? I_A| to evaluate the degree of inter-phase load imbalance from the measured current values, and determines whether there is an unbalanced load using the maximum or average value among these.

[0134] The comparison of current values ​​is not fixed to a specific threshold but can be variably set according to the type, capacity, and operating conditions of the power equipment. The control unit can be configured to calculate a dynamic threshold T_imbalance based on past field log data, substation load characteristics, or rated values ​​listed in the equipment specifications, and to determine an unbalanced load if ΔI_max > T_imbalance.

[0135] In addition, the phase-specific current values ​​provided by the current measuring unit are utilized as auxiliary information in the phase determination process, and can be controlled to automatically adjust the reliability weighting of the phase determination result of the corresponding phase or to perform an additional phase difference verification procedure when an abnormally high current is measured in a specific phase. The current measuring unit may be provided as an independent hardware module inside the finder device, or only data may be input into the finder device by linking with external measuring equipment, so the implementation method can be applied in various ways within a range selectable by a person of ordinary skill.

[0136] As such, the current measuring unit according to the embodiment of the present invention is configured to determine load imbalance by simultaneously measuring currents by phase, and provides an extended function capable of comprehensively evaluating the condition of power equipment in parallel with phase determination.

[0137] Finally, the control unit generates the final encrypted result by XORing the operation results f1, f2, and h. That is, it is expressed in the form Enc = f1 f2 h, and each operation is performed using bitwise exclusive OR. This encrypted result Enc guarantees uniqueness and tamper resistance, and is ultimately transmitted to the user terminal.

[0138] A control unit according to one embodiment of the present invention generates a first verification token by combining the encrypted result value, a reference time hash value synchronized within the server, a face determination reliability index (a value calculated as the reciprocal of the standard deviation of multiple measurements), and a session identification number included in the request signal of the user terminal as additional variables before transmitting the encrypted result value to the user terminal.

[0139] A control unit according to one embodiment of the present invention converts a reference time synchronized within the server into a single string value through a hash operation before transmitting an encrypted result value. The reference time is calculated as a corrected synchronization time t_sync by comparing the reference time t_gps with the server internal clock time t_srv, and can be defined as t_sync = (t_gps + t_srv) / 2. This value is converted to h_time = H(t_sync) by applying a hash function H(), and the hash result is represented as a fixed-length 256-bit value.

[0140] The phase discrimination reliability index is calculated by taking the reciprocal based on the standard deviation σ of multiple measured phase difference values. When the phase difference measurements are {θ_1, θ_2, … , θ_n}, the mean μ is obtained as (Σθ_i) / n, and the standard deviation σ is calculated as sqrt(Σ(θ_i - μ)^2 / n). Subsequently, the reliability index R is calculated in the form R = 1 / (1 + σ), and a larger value indicates higher consistency of the discrimination results.

[0141] The session identification number is a unique number included whenever a user terminal sends a request, and the server identifies it to ensure data transmission that is valid only within the same session. The session identification number is assigned in the form of a 32-bit integer or a UUID, and the control unit stores this value as an additional variable.

[0142] Finally, the control unit combines the encryption result value Enc, the reference time hash value h_time, the determination confidence index R, and the session identification number S into a single data structure to generate the first verification token Token_1. This combination is not a simple concatenation, but is performed through a string concatenation operation as Token_1 = Enc || h_time || R || S. Here, || means concatenating variables sequentially.

[0143] A control unit according to one embodiment of the present invention rearranges the first verification token through a permutation matrix based on a random number seed, generates a second encryption token by performing multiple hash operations (parallel application of SHA-2 and lightweight hash algorithms), inserts the second encryption token into the header of a transmission data packet, and controls the transmission of the result determination result to the user terminal by separating it from the body.

[0144] A control unit according to one embodiment of the present invention first rearranges a first verification token (Token_1) using a permutation matrix initialized with a random number seed. The random number seed uses a value r_seed output from a random number generator, and the permutation matrix P consists of an NxN integer array generated according to the r_seed value. For example, if Token_1 is represented as a byte array {b1, b2, … , bn}, the control unit maps index i to the permutation matrix P(i) to generate a new order {bP(1), bP(2), … , bP(n)}. Through this, different rearrangement results are derived depending on the random number seed value, even with the same input.

[0145] The rearranged token then undergoes multiple hash operations. The control unit applies the SHA-2 hash function and the LightHash hash function in parallel to the same input data and combines the results using an XOR operation. For example, H1 is calculated as SHA2(rearranged_token) and H2 as LightHash(rearranged_token), and then the final combined hash value H_final is calculated as H1 XOR H2. The H_final generated in this way can simultaneously ensure collision resistance and computational efficiency.

[0146] The H_final generated in this process is defined as the second encryption token (Token_2). Token_2 is inserted into the transmission data packet structure; the control unit includes Token_2 in the packet header area and separately records only the status determination result data in the body. That is, the packet structure is configured in the form of {Header: Token_2, Body: Determination Result}, allowing the user terminal to first utilize the Token_2 in the header for verification upon reception and interpret the body data separately.

[0147] A control unit according to one embodiment of the present invention sets a random seed r_seed as an initial value to generate a random seed-based permutation matrix P, prepares an array {1, 2, … , n}, and then performs permutation using a Fisher-Yates shuffle method. Specifically, while repeating the index k in reverse order from n to 2, a random index j is generated in the range from 1 to k, and an element a[k] and a[j] of the array are swapped. When this process is completed, the array a is transformed into a random permutation, and this array is defined as the permutation matrix P. Accordingly, the input data {b1, b2, … , bn} is rearranged by P into the form {bP(1), bP(2), … , bP(n)}.

[0148] In this method, even with identical input data, if the random seed r_seed value is different, the result of the permutation matrix P changes, so the rearrangement result also changes unpredictably. Additionally, since the r_seed value can be calculated by combining the server's internal time, a portion of the determination result hash, and the user request session number, it has a structure that makes it difficult to reproduce the same seed from the outside.

[0149] The rearranged token data is then input into a parallel hash processing stage. The SHA-2 hash provides strong collision avoidance in 256-bit block units, and the LightHash uses a simplified modular arithmetic-based compression function to ensure fast computation speeds even on low-spec terminals. The two hash results, H1 = SHA2(rearranged_token) and H2 = LightHash(rearranged_token), are combined using XOR combination H_final = H1 XOR H2, and this value is defined as the second encryption token, Token_2.

[0150] Finally, Token_2 is inserted into the header area of ​​the transmitted data packet, and the status determination result is independently recorded in the body. Through this structure, the user terminal can immediately verify data integrity using Token_2 in the header and reliably interpret the body data. Explanation of the symbols

[0151] 100: User terminal 110: User Input Section 120: Display section 200: Server 210: Communications Department 220: Storage section 230: Control unit

Claims

Claim 1 A mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction comprises: a user terminal provided with a display unit and a user input unit; and a server connected to the user terminal via a wired or wireless network, wherein the server comprises a communication unit and a storage unit. The AI-based three-phase power system phase includes a standard phase detection device installed in a substation, comprising a control unit; wherein the standard phase detection device generates absolute phase reference data by combining a reference time received through a GPS receiver and phase information received from a transformer PT voltage signal, and transmits the generated absolute phase reference data to the server; wherein the control unit stores the absolute phase reference data in the storage unit, and when a request signal for the absolute phase reference data is input from the user terminal, the control unit transmits the absolute phase reference data recorded in the storage unit to the user terminal; wherein when the control unit receives electrical phase data collected by a finder device in the field through a power facility connection probe via the communication unit, the control unit calculates the phase difference between the received electrical phase data and the absolute phase reference data, verifies whether the phase difference corresponds to a 120° phase difference relationship, identifies which of phase A, B, or C the electrical phase corresponds to based on the verification result, and controls the transmission of the identified result to the user terminal. Mobile-linked discrimination system based on discrimination and error correction. Claim 2 delete Claim 3 A mobile interlocking discrimination system based on artificial intelligence-based three-phase power system phase discrimination and error correction, wherein, in claim 1, the control unit repeatedly collects the electric phase phase data a predetermined number of times to obtain multiple measurement values ​​under the same conditions when calculating the phase difference between the absolute phase reference data and the electric phase phase data, performs reference time alignment and phase difference calculation for each of the obtained multiple measurement values ​​to derive multiple phase difference result values, selects only the result values ​​among the derived multiple phase difference result values ​​whose deviation is included within a predetermined allowable range to perform an average calculation, and performs phase identification by comparing the result of the average calculation with the absolute phase reference data. Claim 4 In paragraph 3, the control unit performs a comparison and determination process between the absolute phase reference data and the electrical phase data, records the determined phase information, the time information at which the determination was performed, and the identification information of the finder device together and stores them as log data in the storage unit, verifies the consistency of determination by comparing past determination results and current determination results at the same power facility connection location using the stored log data, and if a determination discrepancy is detected as a result of the comparison, the control unit re-executes the determination process to resolve the determination discrepancy, and finally transmits only the determination result for which consistency has been verified to the user terminal, characterized by an AI-based mobile interlocking determination system based on three-phase power system phase determination and error correction. Claim 5 A mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction, wherein, in the 4th paragraph, the control unit individually verifies the continuity of the waveform, whether there is a sudden change in phase difference, and whether there is a normal range of voltage and frequency for each of the received electrical phase phase data in order to exclude abnormal data distorted by disturbance signals, noise, or instantaneous voltage fluctuations during the phase determination process, excludes data that does not satisfy two or more of the verification criteria from the valid data set, and performs a phase difference calculation with the absolute phase reference data only on the valid data set remaining after exclusion. Claim 6 In paragraph 5, the control unit generates multivariable input data including the determined reference phase information (a specific phase identification value among phases A, B, and C), the absolute time at which the determination was performed (a synchronization time value calculated by cross-verifying the reference time and the server internal time), the average and standard deviation of the multiple measurement phase difference values ​​derived from the phase difference calculation process, the unique identification information of the finder device (including a serial number and connection location coordinates), the reference number and creation time of the absolute phase reference data, and the number of occurrences of abnormal data excluded during the determination process and the exclusion reason code, before transmitting the reference phase information determined through the finder to the user terminal; and the control unit numerically substitutes each of the multivariable input data by applying a random number value calculated from a random number generator as a weighting coefficient, and applies a polynomial-based key operation to the substituted data set, wherein the key operation is a first-order combination of the time information variable and the phase difference variable, a combination of the phase identification variable and the finder device identification variable through a multiplication operation, and hash the remaining variables (reference number and exclusion reason code). A mobile interlocking determination system based on artificial intelligence-based three-phase power system phase determination and error correction, characterized by performing a sequential operation procedure to XOR combine results converted into a function, finally generating an encrypted result value derived from the XOR combination sequential operation procedure, and transmitting the generated encrypted result value to the user terminal.

Images