Ultrahigh pressure nuclear phase correction method, device and equipment based on multi-source data fusion and medium

Abstract

The invention discloses an ultra-high voltage nuclear phase correction method, device and equipment based on multi-source data fusion and a medium, and relates to the technical field of power grids, and the method comprises the steps: firstly obtaining the t-th round of multi-source data and a real phase value of ultra-high voltage equipment; and inputting the multi-source data into the pre-trained neural network model to generate a correction coefficient, correcting a phase value by combining the correction coefficient and the original phase value, and calculating a phase error with a real phase value. If the phase error exceeds the error threshold value and the adjustment frequency does not exceed the adjustment frequency threshold value, adjusting the gain of the acquisition equipment amplifier according to the electric field intensity, and re-acquiring the (t + 1) th round of multi-source data; and outputting a corrected phase value if the phase error reaches the standard. In addition, the correction phase value needs to be rechecked by two persons, and when the deviation exceeds a second threshold value, intelligent contract alarm and frozen combination ring operation are triggered; time deviation and a second phase error can be obtained through the current temperature, and secondary correction is carried out on the original phase value. According to the method, the nuclear phase precision and safety of the ultrahigh-voltage equipment can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grids, in particular to a super-high voltage phase correction method and device based on multi-source data fusion, equipment and medium. BACKGROUND

[0002] In a power system, initial phase angle calibration (phase calibration) is a core link to ensure the safe and stable operation of the power grid. In particular, in the operation and maintenance scenarios of 500kV and above super-high voltage substations, the accurate matching of the phase directly relates to the safety of the closing operation, the reliability of the equipment switching and the accuracy of the fault positioning. With the expansion of the power grid scale and the surge in the demand for new energy grid connection, the super-high voltage equipment has increasingly stringent requirements for phase consistency, usually requiring a control error of ≤3°.

[0003] Currently, traditional wired phase calibration equipment relies on local wired connection, and the operator needs to be in close proximity to high-voltage equipment, which poses a safety risk and cannot meet the needs of long-distance and multi-node. Although wireless phase calibration technology reduces manual intervention, it relies on single-band communication and is easily disturbed in complex electromagnetic environments, with a high data packet loss rate (typical value > 5%) and a phase calibration error generally exceeding 10°.

[0004] Therefore, the traditional method cannot meet the accurate calibration of the initial phase angle of 500kV and above super-high voltage equipment, and cannot guarantee the safe and efficient operation of the power grid. SUMMARY

[0005] The present application provides a super-high voltage phase correction method and device based on multi-source data fusion, which can meet the accurate calibration of the initial phase angle of super-high voltage equipment and guarantee the safe and efficient operation of the power grid.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical solutions: In a first aspect, the present application provides a super-high voltage phase correction method based on multi-source data fusion, comprising: obtaining the multi-source data of the tth round of super-high voltage equipment and the true phase value of the super-high voltage equipment, wherein the multi-source data of the tth round includes the original phase value, environmental parameters and time; the environmental parameters include temperature, humidity and electric field intensity; inputting the multi-source data of the tth round into a pre-trained neural network model to generate the correction coefficient of the tth round; obtaining the corrected phase value of the tth round according to the correction coefficient of the tth round and the original phase value; and obtaining the phase error of the tth round according to the corrected phase value of the tth round and the true phase value; judging whether the phase error of the tth round is greater than the error threshold value; if the phase error of the tth round is greater than the error threshold value, judging whether the number of times of adjusting the phase error exceeds the adjustment number threshold value, if the number of times of adjusting the phase error does not exceed the adjustment number threshold value, adjusting the amplifier of the acquisition device according to the electric field intensity, and obtaining the multi-source data of the t+1th round of the super-high voltage device.

[0007] Optionally, the original phase value can be obtained by the following way: obtaining a voltage signal of the super-high voltage device; eliminating high-frequency noise of the voltage signal through a finite impulse response (FIR) filter to obtain a filtered voltage signal; performing Fourier transform on the filtered voltage signal to obtain a frequency domain spectrum, and obtaining an original phase value of the filtered voltage signal according to the frequency domain spectrum.

[0008] Optionally, the adjusting the amplifier of the acquisition device according to the electric field intensity comprises:

[0009] wherein, is the adjusted gain of the amplifier of the acquisition device, is the reference gain of the amplifier of the acquisition device, is the electric field intensity.

[0010] Optionally, the method further comprises: if the phase error of the tth round is less than the error threshold value, outputting the corrected phase value of the tth round.

[0011] Optionally, the method further comprises: if the number of times of adjusting the phase error exceeds the adjustment number threshold value, triggering manual inspection of the acquisition device.

[0012] Optionally, the method further comprises: if the multi-time nuclear phase deviation is greater than the second threshold value, triggering an intelligent contract alarm containing the multi-time nuclear phase deviation value, and freezing the ring operation.

[0013] Optionally, the method further comprises: obtaining a time deviation at a current temperature; obtaining a second phase error according to the time deviation; secondarily correcting the original phase value of the tth round according to the second phase error.

[0014] In a second aspect, the present application provides a super-high voltage nuclear phase correction device based on multi-source data fusion, comprising: The acquisition module is used to acquire the multi-source data of the ultra-high voltage equipment in the t-th round and the actual phase value of the ultra-high voltage equipment. The multi-source data in the t-th round includes: the original phase value, environmental parameters, and time; the environmental parameters include: temperature, humidity, and electric field strength. The processing module is used to input the multi-source data of the t-th round into the pre-trained neural network model to generate the correction coefficients of the t-th round; obtain the corrected phase value of the t-th round based on the correction coefficients of the t-th round and the original phase value; and obtain the phase error of the t-th round based on the corrected phase value of the t-th round and the true phase value. The correction module determines whether the phase error in round t is greater than the error threshold. If the phase error in round t is greater than the error threshold, it determines whether the number of times the phase error is adjusted exceeds the adjustment number threshold. If the number of times the phase error is adjusted does not exceed the adjustment number threshold, it adjusts the amplifier of the acquisition device according to the electric field strength to obtain the multi-source data of the ultra-high voltage equipment in round t+1.

[0015] Thirdly, this application provides a computing device, including a memory and a processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of the first aspects.

[0016] Fourthly, this application provides a computer-readable storage medium for storing a computer program for performing the method as described in any one of the first aspects.

[0017] As can be seen from the above technical solution, this application has at least the following beneficial effects: In this application, multi-source data fusion is used to integrate environmental parameters such as original phase value, temperature and humidity, electric field strength and time information. The correction coefficients are dynamically generated by combining a pre-trained neural network model and a multi-round error feedback adjustment method is introduced. The amplifier gain is optimized in real time based on the electric field strength. With the high-frequency noise suppression and secondary correction of time deviation by the finite-length unit impulse response FIR filter, the phase deviation caused by multiple factors such as electromagnetic interference, environmental drift and clock error is effectively eliminated. The phase error can be stably controlled within the threshold range, which solves the problem that the error of traditional wireless phase matching technology generally exceeds 10°.

[0018] Furthermore, this method reduces close contact between operators and high-voltage equipment, avoiding the safety hazards of traditional wired phase grading; at the same time, the collaborative processing mechanism of multi-source data breaks away from the dependence on a single communication frequency band, can adapt to long-distance, multi-node phase grading scenarios in ultra-high voltage substations, and breaks through the spatial limitations of traditional wired methods.

[0019] To address complex electromagnetic environments, FIR filters are used to specifically eliminate high-frequency noise, while amplifier gain is dynamically adjusted based on electric field strength to enhance the anti-interference capability of signal acquisition. Combined with mechanisms such as dual-person verification and blockchain smart contract alarms, the credibility of the calibration results is further ensured, avoiding the risk of loop closure operations due to data errors and guaranteeing the safe and stable operation of the power grid.

[0020] Furthermore, by real-time sensing and correction of environmental parameters (temperature, humidity, electric field strength) and time deviations, it can adapt to changes in equipment characteristics under different operating conditions, solving the problem of sharp drop in accuracy of traditional methods when the environment fluctuates, and providing reliable technical support for ultra-high voltage phase nucleation in complex scenarios such as new energy grid connection.

[0021] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0022] Figure 1 A flowchart illustrating an ultra-high pressure phase correction method based on multi-source data fusion, provided as an embodiment of this application; Figure 2 A schematic diagram of an ultra-high voltage phase correction device based on multi-source data fusion provided in an embodiment of this application; Figure 3 This is a schematic diagram of a computing device provided in an embodiment of this application. Detailed Implementation

[0023] The terms "first," "second," and "third," etc., used in this application specification and accompanying drawings are used to distinguish different objects, not to limit a specific order.

[0024] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0025] To ensure clarity and conciseness in the description of the following embodiments, a brief introduction to the related technologies is given first: Ultra-high voltage phase verification refers to the initial phase angle verification of ultra-high voltage power equipment (such as GIS equipment, transmission lines, and transformers) of 500kV and above. It is determined by comparing the phase of voltage signals of different equipment or lines to judge the phase consistency, ensuring that there is no phase difference conflict when closing the loop and switching equipment. It is a core link of power grid safe operation and maintenance, and requires the phase verification error to be ≤3° to adapt to the needs of ultra-high voltage scenarios.

[0026] The initial phase angle refers to the phase state of the power frequency voltage signal at the starting point of time. It directly determines the phase matching degree between ultra-high voltage equipment and is the core detection object of phase verification.

[0027] In power systems, initial phase angle verification of 500kV and above ultra-high voltage equipment is a core component in ensuring the safe and stable operation of the power grid. However, traditional phase verification technologies struggle to meet current stringent requirements: traditional wired phase verification equipment relies on local wired connections, requiring operators to be in close proximity to high-voltage equipment, posing safety risks and unsuitable for long-distance, multi-node phase verification scenarios; while wireless phase verification technology reduces human intervention, its reliance on a single frequency band makes it susceptible to interference in the complex electromagnetic environment of substations, with typical data packet loss rates exceeding 5% and phase verification errors generally exceeding 10°, far from meeting the phase consistency requirements (error ≤ 3°) of ultra-high voltage equipment. These problems stem from two main issues: firstly, the time synchronization scheme relies solely on GPS, which is prone to failure in signal-obstructed areas such as underground substations, and lacks a historical clock drift model with temperature compensation, failing to correct for additional phase errors caused by time deviations; secondly, the lack of a rigorous result verification mechanism, without independent dual-person review, blockchain notarization, and smart contract alarms, makes it susceptible to power grid accidents due to human error or data tampering. Therefore, how to improve the accuracy of ultra-high pressure phase nucleation, reduce operational safety risks, enhance adaptability to complex environments, and ensure the reliability of results has become an urgent technical problem to be solved.

[0028] In view of this, embodiments of this application provide an ultra-high voltage nuclear phase correction method based on multi-source data fusion, which can be executed by a processing device. This processing device can be a terminal or a server. Terminals include, but are not limited to, smartphones, tablets, laptops, personal digital assistants, or smart wearable devices. Servers can be cloud servers, such as central servers in a central cloud computing cluster or edge servers in an edge cloud computing cluster. Of course, servers can also be servers in a local data center. A local data center refers to a data center directly controlled by the user.

[0029] To address the shortcomings of traditional UHV phase verification technology, such as insufficient accuracy, high safety risks, weak adaptability to complex environments, and low reliability of results, this application firstly collects multi-dimensional data including original phase values, temperature, humidity, and electric field intensity, and combines this with time information obtained through dual-redundant timing via BeiDou-rubidium atomic clocks to construct a multi-source dataset, covering the interference sources of phase deviation at the data level. Secondly, a pre-trained Long Short-Term Memory (LSTM) network model is introduced to learn the correlation patterns of historical phase verification data, dynamically generate correction coefficients, and achieve dynamic cancellation of phase errors through multiple rounds of error feedback. Simultaneously, an FIR filter is used to eliminate high-frequency noise to ensure the purity of the original signal, and secondary time deviation correction is used to eliminate the influence of timing drift. Finally, relying on dual-person verification and blockchain smart contracts, the phase verification results are ensured to be tamper-proof and real-time alarms are provided in case of anomalies. Ultimately, this achieves the goals of UHV phase verification accuracy ≤3°, safe operation without close human contact, low packet loss rate in complex environments, and high reliability of results, meeting the operation and maintenance needs of 500kV and above power grids.

[0030] To make the technical solution of this application clearer and easier to understand, the following description, in conjunction with the accompanying drawings, introduces an ultra-high pressure phase correction method based on multi-source data fusion provided by an embodiment of this application. Figure 1 As shown, this figure is a flowchart of an ultra-high pressure phase correction method based on multi-source data fusion provided in an embodiment of this application. The method includes: S201. Obtain the multi-source data of the ultra-high voltage equipment in round t and the true phase value of the ultra-high voltage equipment. The multi-source data in round t includes: the original phase value, environmental parameters and time; the environmental parameters include: temperature, humidity and electric field strength.

[0031] The original phase value can be obtained in the following way: First, the processing equipment acquires the voltage signal from the ultra-high voltage equipment.

[0032] The voltage level threshold for ultra-high voltage equipment is 330kV, but in actual power grid operation and maintenance, ultra-high voltage equipment is more commonly concentrated at the 500kV and 750kV levels.

[0033] The processing equipment acquires voltage signals from ultra-high voltage equipment in a non-contact manner by controlling a dedicated acquisition terminal. Dedicated data acquisition terminals are specialized hardware devices that are directly deployed at ultra-high voltage equipment sites to perform signal acquisition, data preprocessing, and preliminary communication functions. They ensure safety through non-contact design, adapt to complex environments through modular hardware, and improve data quality through localized preprocessing.

[0034] The processing equipment first sends a control command to the dedicated acquisition terminal, requiring it to be fixed to a non-energized part of the ultra-high voltage equipment and to maintain a safe distance from the energized components to avoid electric field interference and safety risks. Then, the processing equipment drives the broadband antenna or electromagnetic induction sensor built into the dedicated acquisition terminal to capture the voltage signal generated in the surrounding space during the operation of the ultra-high voltage equipment. This voltage signal is completely synchronized with the 50Hz power frequency voltage signal inside the ultra-high voltage equipment. This method eliminates the need for the dedicated acquisition terminal to directly contact the ultra-high voltage components.

[0035] Then, a finite-length unit impulse response (FIR) filter is used to eliminate high-frequency noise in the voltage signal, resulting in a filtered voltage signal.

[0036] After acquiring the voltage signal from the ultra-high voltage equipment, the processing equipment performs high-frequency noise cancellation operation through a finite-length unit impulse response (FIR) filter. Specifically, based on the coefficients of the FIR filter and the voltage signal, the filtered voltage signal is obtained, achieving the goal of retaining the effective power frequency signal and filtering out high-frequency interference.

[0037] An FIR filter is essentially a linear time-invariant filter with a finite unit impulse response length. It can perform weighted filtering of different frequency components in a voltage signal using a preset coefficient sequence. For ultra-high voltage phase-multiplication scenarios, it is necessary to retain the effective 50Hz power frequency signal while attenuating high-frequency noise above 200Hz, such as corona discharge noise and equipment harmonic interference. This filtering function is achieved through the convolution operation of the FIR filter coefficients and the voltage signal.

[0038] First, a preset FIR filter coefficient sequence is loaded. Then, the acquired voltage signal is convolved with this coefficient sequence to obtain the filtered voltage signal, expressed as: Assume the input voltage signal from the ultra-high voltage equipment is a time-domain sequence. ,in, This represents the total number of sampling points for the voltage signal. Representing the Voltage values ​​at each sampling point.

[0039] The preset coefficient sequence of the FIR filter is ,in, The filter order is set to 128 based on the requirements of ultra-high voltage phase gradation. =128, For the first The coefficients of an FIR filter.

[0040] The filtered voltage signal time-domain sequence The expression is:

[0041] in, Indicates the first position in the output sequence Voltage values ​​at each sampling point Indicates the first Voltage values ​​at each sampling point.

[0042] The essence of convolution is to allow the FIR filter coefficient sequence to slide through the entire voltage signal sequence. Specifically, for each output value... Its calculation logic is as follows: In the voltage signal sequence, first determine a position... A sliding window, centered and with a length perfectly matching the filter order, is used. The voltage signal data within this window is then multiplied point-by-point with the coefficient sequence of the FIR filter. Finally, all the multiplication results are summed; this sum is the final output value. .

[0043] Since the filter coefficients are designed based on a 200Hz cutoff frequency, its weighting coefficients for 50Hz power frequency signals are relatively large, ensuring that the signal amplitude is basically preserved. For high-frequency signals above 200Hz, the weighting coefficients are close to 0, achieving significant attenuation. Therefore, the calculated... In the sequence, high-frequency noise is significantly suppressed, and only the 50Hz power frequency effective signal is retained, which is the filtered voltage signal.

[0044] Finally, the filtered voltage signal is subjected to Fourier transform to obtain the frequency domain spectrum. Based on the frequency domain spectrum, the original phase value of the filtered voltage signal is obtained.

[0045] The filtered voltage signal is converted into a frequency domain spectrum using a Fourier transform. The frequency domain spectrum displays the amplitude and phase information of signals at different frequencies. Since high-frequency noise has been filtered out at this point, only the 50Hz power frequency signal is retained. Therefore, the phase data corresponding to the 50Hz frequency is found in the frequency domain spectrum, which is the original phase value of the filtered voltage signal.

[0046] Other methods for obtaining multi-source data are as follows: The processing equipment collects real-time temperature and humidity data of the surrounding environment through temperature and humidity sensors deployed in non-energized areas of ultra-high voltage equipment (such as the casing of 500kV GIS equipment or near substation cabinets). The sensors communicate with the processing equipment wirelessly or via wired means, uploading data every 100ms to ensure that the data in the t-th round reflects the true state of the current environment.

[0047] The processing equipment utilizes a triaxial electric field strength sensor installed in a dedicated acquisition terminal to collect real-time electromagnetic interference intensity data in the vicinity of the ultra-high voltage equipment. During the acquisition process, the triaxial electric field strength sensor converts the measured electric field strength into a digital signal and transmits it to the processing equipment.

[0048] The processing device obtains the time information corresponding to the t-th round of data through a redundancy of BeiDou time synchronization and a rubidium atomic clock. Under normal circumstances, the processing device receives the standard time signal from the BeiDou-3 time synchronization module, such as the UM220-IV chip, with a time synchronization error ≤0.1μs, to ensure that all data in the t-th round are strictly aligned in the time dimension. If the BeiDou signal is blocked, such as in an underground substation, the processing device automatically switches to the built-in rubidium atomic clock, which has an accuracy of 0.1ppb, to maintain time synchronization, and the error is less than 1μs within 24 hours, avoiding data association failure due to time base confusion.

[0049] The actual phase value is not collected in real time, but rather is a baseline value retrieved by the processing equipment from a dynamic database in the cloud. The specific logic is as follows: the cloud database pre-stores at least 100,000 historical phase data records of the ultra-high voltage equipment. These data cover two types of information: first, the initial baseline phase value of the ultra-high voltage equipment under ideal operating conditions such as no electromagnetic interference and stable temperature and humidity during the initial commissioning of the equipment; second, reliable phase records generated during the operation and maintenance of the equipment. These records need to be verified by multiple nodes of the blockchain (such as by generating a unique identifier through the SHA-256 hash algorithm and then storing it on the chain), which can effectively ensure that the data has not been tampered with and has high credibility.

[0050] Meanwhile, all historical phase data are associated with the basic ledger information of ultra-high voltage equipment (including key parameters such as equipment voltage level and insulation resistance) and environmental parameter labels at the time of data acquisition (such as temperature, humidity and electric field strength at that time), forming a correspondence between data, equipment and environment, which facilitates the processing of the reference phase value that is closest to the current operating conditions for subsequent equipment matching.

[0051] After acquiring the environmental parameters for round t, the processing device will match the historical reference phase data that is closest to the current environment (temperature, humidity, electric field strength) and device status in the cloud database, and make fine adjustments in combination with the current operating parameters of the device to finally determine the true phase value for round t.

[0052] Communication between the processing equipment and the dedicated acquisition terminal, as well as between the processing equipment and the cloud data hub, employs a 2.4GHz / 5.8GHz dual-band dynamic switching technology. This technology monitors the electromagnetic interference intensity of the two frequency bands in real time and automatically selects the band with lower interference for data transmission. In open environments, this technology can extend the transmission distance to 500 meters, sufficient to cover the phase comparison requirements of multiple nodes in ultra-high voltage substations. Simultaneously, it can control the data packet loss rate to within 0.1%, far superior to traditional single-band wireless phase comparison technology, thus ensuring the integrity of multi-source data during transmission.

[0053] Before data transmission, end-to-end encryption protection is achieved using the SM4 block cipher algorithm approved by the State Cryptography Administration. The encryption key is dynamically generated and distributed by the blockchain verification nodes and automatically updated every 10 minutes to avoid security risks caused by long-term fixed keys. The encrypted data stream fully complies with the data transmission security requirements of Document No. 36 of the National Energy Administration, preventing the theft and tampering of multi-source data during transmission and ensuring the privacy of nuclear phase data.

[0054] S202. Input the multi-source data of round t into the pre-trained neural network model to generate the correction coefficients of round t.

[0055] The processing device utilizes a pre-trained LSTM model, trained in TensorFlow based on 100,000 historical nuclear phase data, to perform real-time inference on the multi-source data in round t, and outputs the correction coefficients under the corresponding operating conditions.

[0056] Specifically, the processing device standardizes the multi-source data of round t, converts the temperature into a relative value, and normalizes the electric field strength to the range of 0-1, forming a sequence that conforms to the LSTM input format.

[0057] The pre-processed data of round t is input into the pre-trained model. The model uses a gating mechanism of 128 hidden layer nodes, namely forget gate, input gate and output gate, to dynamically capture the temporal correlation and nonlinear coupling relationship of multi-source data. It can learn the complex mapping law from multi-source data to phase deviation under 100,000 working conditions in historical data.

[0058] After the hidden layer operations, the model outputs specific correction coefficients through the output layer. These correction coefficients are the amount of adjustment that the LSTM predicts to make to the original phase value to offset the current environmental interference, based on the current input data and by comparing the phase deviation patterns of similar historical operating conditions. This adjustment is then used for the dynamic correction of the original phase value in subsequent operations.

[0059] S203. Based on the correction coefficient of round t and the original phase value, obtain the corrected phase value of round t.

[0060] The original phase value in round t is the initial phase data before interference is eliminated; the correction coefficient in round t is the deviation of the original phase value predicted by the model based on the current environmental parameters. The sign of the coefficient indicates the direction of the deviation, and the value indicates the magnitude of the deviation. The calculation expression is:

[0061] in, This represents the corrected phase value in round t. This represents the original phase value in round t. This represents the correction coefficient for round t.

[0062] For example, if the original phase value is too small due to the change in the dielectric constant of the equipment insulation caused by high temperature, the true phase value is 30°, while the original phase value is only 29.2°. If the LSTM model outputs a correction coefficient of +0.8°, then the corrected phase value is 29.2° + 0.8° = 30°, indicating that the corrected phase value has initially offset the deviation caused by temperature interference.

[0063] S204. Based on the corrected phase value and the true phase value of round t, obtain the phase error of round t.

[0064] The t-th round corrected phase value is the compensated phase data, while the t-th round true phase value (retrieved from the cloud dynamic database) is the historical benchmark value that best matches the current operating conditions.

[0065] The calculation expression is obtained by using the absolute values ​​of the corrected phase value and the true phase value:

[0066] in, This represents the phase error in round t. This represents the actual phase value in round t.

[0067] For example, if the corrected phase value is 30° and the true phase value is 30.1°, then the phase error is... .

[0068] S205. Determine whether the phase error in round t is greater than the error threshold.

[0069] If the phase error in round t is greater than the error threshold, then execute S206; if the phase error in round t is less than the error threshold, then execute S208. The error threshold is set to 2°. The error threshold is the core standard for judging whether the correction effect meets the requirements. If the phase error is ≤2°, it means that the current correction meets the phase verification requirements; if it is >2°, then the adjustment process needs to be started.

[0070] S206. Determine whether the number of times the phase error is adjusted exceeds the adjustment number threshold.

[0071] If the number of adjustments to the phase error does not exceed the adjustment threshold, then execute S207; if the number of adjustments to the phase error exceeds the adjustment threshold, then execute S209. For example, if the adjustment threshold is set to 3 times, and the phase error still exceeds the limit after 3 adjustments, it indicates that the problem may be beyond the hardware adjustment range (such as equipment failure), and manual inspection should be triggered instead of continuing the cyclic adjustment.

[0072] S207. Adjust the amplifier of the acquisition equipment according to the electric field strength to obtain the multi-source data of the ultra-high voltage equipment in the (t+1)th round.

[0073] The calculation expression is:

[0074] in, The gain of the amplifier in the acquisition device after adjustment. The amplifier reference gain of the acquisition device. Let be the electric field strength. When the electric field strength is... When the gain is increased (e.g., due to strong interference caused by corona discharge), increase the gain proportionally to ensure that weak signals are not overwhelmed by noise; when When reducing gain, decrease the gain to prevent signal saturation. Ensure the integrity of the acquired power frequency voltage waveform is >98% to avoid signal saturation or distortion.

[0075] After the amplifier gain is adjusted, the processing equipment controls the dedicated acquisition terminal to reacquire the voltage signal, environmental parameters (temperature, humidity, new electric field strength) and time information of the ultra-high voltage equipment, forming the (t+1)th round of multi-source data. Then, the process of inputting the model to generate correction coefficients and calculating the correction phase value and phase error is repeated until the phase error meets the standard or triggers manual inspection.

[0076] S208, Output the corrected phase value for the t-th round.

[0077] If the phase error is ≤ 2°, it means that the corrected phase value has met the accuracy requirements. The corrected phase value can be directly output for phase verification operation without further adjustment.

[0078] S209. Trigger manual inspection of the data acquisition equipment.

[0079] If the number of times the phase error is adjusted exceeds the adjustment threshold, a manual inspection of the acquisition equipment is triggered. If the number of times the phase error is adjusted exceeds 3, it indicates that multiple hardware adjustments have failed to resolve the error issue, which may indicate a malfunction in the acquisition equipment or extreme electromagnetic interference, triggering a manual inspection process, such as inspecting the sensor and troubleshooting the interference source.

[0080] If multiple phase deviations exceed the second threshold, a smart contract alarm containing multiple phase deviation values ​​will be triggered, and the loop operation will be frozen.

[0081] For example: The corrected phase value is reviewed and signed by operators A and B. If the deviation between the two phase checks by operators A and B is greater than the second threshold, a smart contract alarm containing the two phase deviation values ​​is triggered, and the loop-closing operation is frozen. The loop-closing operation is unlocked after the two phase deviations are resolved.

[0082] Operator A first checks whether the corrected phase value matches the actual operating conditions of the equipment, based on the on-site equipment status and the collected data records. For example, in an environment with no significant electromagnetic interference and stable temperature and humidity, the phase value is within the historical normal range. After confirming that there are no errors, A performs an electronic signature (such as a digital signature). Subsequently, operator B independently repeats the complete review process without referring to any of A's results, checking the reliability of the data source, the accuracy of the calculation logic, and the rationality of the phase value one by one. After confirming that there are no errors, B also completes the electronic signature.

[0083] The two signatures will be associated with the corrected phase value and their respective review times, forming a complete traceability chain of data, operation, and time, effectively avoiding the risk of tampering or missigning that may occur during single-person operation.

[0084] The processing equipment compares the corrected phase values ​​verified by operators A and B, calculates the deviation between the two values, and compares it with the second threshold of 1°: If the deviation is ≤1°, it means that the results of the two people are consistent, the data reliability has been verified, and the subsequent loop merging operation process can proceed.

[0085] If the deviation is greater than 1°, it indicates that there is a significant difference between the two phase results, which may be due to data distortion, human error in reading, or potential equipment failure. In this case, the alarm and freeze functions of the smart contract need to be triggered.

[0086] When the deviation between two phase phases exceeds the second threshold of 1°, the processing device will synchronize the deviation data to the blockchain node, thereby triggering the pre-deployed smart contract (based on blockchain frameworks such as Hyperledger Fabric) to automatically execute preset logic: The processing device first submits the phase deviation exceeding the standard result to the smart contract, including the specific value, the reviewer, and the timestamp. Based on this, the smart contract pushes alarm information (such as pop-ups and SMS) to the substation operation and maintenance system and the operator's terminal, clearly indicating that the two phase deviations exceeding the standard need to be investigated for anomalies, and specifying the deviation data synchronized by the processing device and the review record, so as to facilitate quick problem location. At the same time, the smart contract immediately locks the loop closing operation permission based on the abnormal result submitted by the processing device. Even if the operation and maintenance personnel try to initiate the loop closing command, it will be rejected until the processing device completes the new phase detection after anomaly investigation, and the two phase deviations are ≤1° and synchronized to the blockchain node. Only then will the smart contract unlock the command permission.

[0087] The method also includes: The processing equipment first obtains the time deviation at the current temperature.

[0088] The processing equipment first obtains the actual temperature of the environment in which the ultra-high voltage equipment is currently located. T The preset reference temperature is T 0 = 25℃, temperature-time deviation coefficient calibrated before the ultra-high pressure equipment leaves the factory. The deviation coefficient The physical meaning is: the time deviation generated per unit time by the ultra-high pressure equipment for every 1℃ deviation from the preset reference temperature. That is, for every 1℃ increase in actual temperature above the preset reference temperature, a clock deviation of 1μs per second is generated. Therefore, the time deviation at the actual temperature is expressed as:

[0089] in, Indicates the time deviation at the current temperature. This represents the temperature-time deviation coefficient. Indicates the actual temperature. Indicates the preset reference temperature. Indicates the sampling period.

[0090] The processing equipment then obtains the second phase error based on the time deviation.

[0091] Time deviation causes the sampling time to deviate from the actual time, thus influencing the calculated original phase value. This deviation is known as the second phase error. The calculation expression is:

[0092] in, This indicates the second phase error. This indicates the frequency of the ultra-high voltage equipment.

[0093] Finally, the processing equipment performs a second correction on the original phase value of the t-th round based on the second phase error.

[0094] Secondary correction uses a second phase error to offset the original phase error caused by the temperature-time deviation, further improving the original phase value. The expression is:

[0095] in, This represents the original phase value after secondary correction. If the time deviation... If positive, it means the clock has slowed down, and the sampling time lags behind the actual time, then the original phase value... Too big If positive, the phase is completed by subtracting the second phase error; if... A negative value indicates that the clock speeds up and the sampling time is ahead. If the value is negative, subtracting the negative number is equivalent to adding a second phase deviation, which also cancels out the error.

[0096] The first correction uses an LSTM model and amplifier to adjust and mainly counteract the direct interference of temperature, humidity and electric field. The second correction targets the indirect interference of temperature, time deviation and phase error. Even if the second phase error is small, it can still further improve the accuracy of the original phase value under the strict requirement of ultra-high pressure phase error ≤3°.

[0097] Based on the above description, this application has the following beneficial effects: In this application, multi-source data fusion is used to integrate environmental parameters such as original phase value, temperature and humidity, electric field strength and time information. The correction coefficients are dynamically generated by combining a pre-trained neural network model and a multi-round error feedback adjustment method is introduced. The amplifier gain is optimized in real time based on the electric field strength. With the high-frequency noise suppression and secondary correction of time deviation by the finite-length unit impulse response FIR filter, the phase deviation caused by multiple factors such as electromagnetic interference, environmental drift and clock error is effectively eliminated. The phase error can be stably controlled within the threshold range, which solves the problem that the error of traditional wireless phase matching technology generally exceeds 10°.

[0098] Furthermore, this method reduces close contact between operators and high-voltage equipment, avoiding the safety hazards of traditional wired phase grading; at the same time, the collaborative processing mechanism of multi-source data breaks away from the dependence on a single communication frequency band, can adapt to long-distance, multi-node phase grading scenarios in ultra-high voltage substations, and breaks through the spatial limitations of traditional wired methods.

[0099] To address complex electromagnetic environments, FIR filters are used to specifically eliminate high-frequency noise, while amplifier gain is dynamically adjusted based on electric field strength to enhance the anti-interference capability of signal acquisition. Combined with mechanisms such as dual-person verification and blockchain smart contract alarms, the credibility of the calibration results is further ensured, avoiding the risk of loop closure operations due to data errors and guaranteeing the safe and stable operation of the power grid.

[0100] Furthermore, by real-time sensing and correction of environmental parameters (temperature, humidity, electric field strength) and time deviations, it can adapt to changes in equipment characteristics under different operating conditions, solving the problem of sharp drop in accuracy of traditional methods when the environment fluctuates, and providing reliable technical support for ultra-high voltage phase nucleation in complex scenarios such as new energy grid connection.

[0101] The above text combined Figure 1 The ultra-high voltage phase correction method based on multi-source data fusion provided in the embodiments of this application has been described in detail. The apparatus and equipment provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0102] like Figure 2As shown in the figure, this is a schematic diagram of an ultra-high voltage phase correction device based on multi-source data fusion provided in an embodiment of this application. The device includes: The acquisition module 301 is used to acquire the multi-source data of the ultra-high voltage equipment in the t-th round and the true phase value of the ultra-high voltage equipment. The multi-source data in the t-th round includes: the original phase value, environmental parameters and time; the environmental parameters include: temperature, humidity and electric field strength. The processing module 302 is used to input the multi-source data of the t-th round into the pre-trained neural network model to generate the correction coefficients of the t-th round; obtain the corrected phase value of the t-th round based on the correction coefficients of the t-th round and the original phase value; and obtain the phase error of the t-th round based on the corrected phase value of the t-th round and the true phase value. The correction module 303 is used to determine whether the phase error of the t-th round is greater than the error threshold; if the phase error of the t-th round is greater than the error threshold, it determines whether the number of times the phase error is adjusted exceeds the adjustment number threshold; if the number of times the phase error is adjusted does not exceed the adjustment number threshold, it adjusts the amplifier of the acquisition device according to the electric field strength to obtain the multi-source data of the (t+1)-th round of the ultra-high voltage equipment.

[0103] Optionally, the acquisition module 301 is specifically used to acquire the voltage signal of the ultra-high voltage equipment; The processing module 302 is specifically used to eliminate high-frequency noise of the voltage signal through a finite-length unit impulse response (FIR) filter to obtain a filtered voltage signal; to perform a Fourier transform on the filtered voltage signal to obtain a frequency domain spectrum; and to obtain the original phase value of the filtered voltage signal based on the frequency domain spectrum.

[0104] Optionally, the calibration module 303 is specifically used to adjust the amplifier of the acquisition device according to the electric field strength, including:

[0105] in, The gain of the amplifier in the acquisition device after adjustment. The reference gain of the amplifier in the acquisition device. denoted as electric field strength.

[0106] Optionally, the correction module 303 is also used to output the corrected phase value for the t-th round if the phase error of the t-th round is less than the error threshold.

[0107] Optionally, the correction module 303 is also used to trigger a manual inspection of the acquisition device if the number of times the phase error is adjusted exceeds the adjustment number threshold.

[0108] Optionally, the processing module 302 is also used to trigger a smart contract alarm containing multiple phase deviation values ​​and freeze the loop operation if multiple phase deviations exceed the second threshold.

[0109] Optionally, the acquisition module 301 is also used to acquire the time deviation at the current temperature; The correction module 303 is also used to obtain the second phase error based on the time deviation; and to perform secondary correction on the original phase value of the t-th round based on the second phase error.

[0110] The ultra-high pressure phase correction device based on multi-source data fusion according to the embodiments of this application can correspond to the execution of the method described in the embodiments of this application, and the other operations and / or functions of each module / unit of the ultra-high pressure phase correction device based on multi-source data fusion are respectively for implementing Figure 1 For the sake of brevity, the corresponding processes of each method in the illustrated embodiments will not be described in detail here.

[0111] This application also provides a computing device. For example... Figure 3 As shown in the figure, this is a schematic diagram of a computing device provided in an embodiment of this application. The computing device 700 includes a bus 701, a processor 702, a communication interface 703, and a memory 704. The processor 702, the memory 704, and the communication interface 703 communicate with each other via the bus 701.

[0112] The 701 bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0113] The processor 702 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0114] The communication interface 703 is used for communication with external devices.

[0115] Memory 704 may include volatile memory, such as random access memory (RAM). Memory 704 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0116] The memory 704 stores executable code, and the processor 702 executes the executable code to perform the aforementioned ultra-high voltage nuclear phase correction method based on multi-source data fusion.

[0117] Specifically, in achieving Figure 2 In the case of the illustrated embodiment, and Figure 2 When the modules or units of the ultra-high voltage phase correction device based on multi-source data fusion described in the embodiments are implemented by software, the execution... Figure 2 The software or program code required for the functions of each module / unit can be partially or entirely stored in the memory 704. The processor 702 executes the program code corresponding to each unit stored in the memory 704, and executes the aforementioned ultra-high voltage phase correction method based on multi-source data fusion.

[0118] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct a computing device to execute the aforementioned ultra-high voltage nuclear phase correction method based on multi-source data fusion.

[0119] This application also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application are generated.

[0120] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0121] When the computer program product is executed by a computer, the computer executes any of the aforementioned methods of the ultra-high voltage phase correction method based on multi-source data fusion. The computer program product can be a software installation package; when any of the aforementioned methods of the ultra-high voltage phase correction method based on multi-source data fusion needs to be used, the computer program product can be downloaded and executed on the computer.

[0122] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0123] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A method for ultra-high pressure phase correction based on multi-source data fusion, characterized in that, The method includes: The t-th round of multi-source data from the ultra-high voltage equipment and the actual phase value of the ultra-high voltage equipment are obtained. The t-th round of multi-source data includes: the original phase value, environmental parameters, and time; the environmental parameters include: temperature, humidity, and electric field strength. The multi-source data of the t-th round is input into the pre-trained neural network model to generate the correction coefficients of the t-th round; Based on the correction coefficient of round t and the original phase value, the corrected phase value of round t is obtained; based on the corrected phase value of round t and the true phase value, the phase error of round t is obtained. Determine whether the phase error in round t is greater than the error threshold; if the phase error in round t is greater than the error threshold, determine whether the number of times the phase error is adjusted exceeds the adjustment number threshold; if the number of times the phase error is adjusted does not exceed the adjustment number threshold, adjust the amplifier of the acquisition device according to the electric field strength to obtain the multi-source data of round t+1 of the ultra-high voltage equipment.

2. The method according to claim 1, characterized in that, The original phase value can be obtained in the following way: Acquire voltage signals from ultra-high voltage equipment; The high-frequency noise of the voltage signal is eliminated by using a finite-length unit impulse response (FIR) filter to obtain the filtered voltage signal. The filtered voltage signal is subjected to Fourier transform to obtain the frequency domain spectrum. Based on the frequency domain spectrum, the original phase value of the filtered voltage signal is obtained.

3. The method according to claim 1, characterized in that, The adjustment of the amplifier of the acquisition device based on the electric field strength includes: in, The gain of the amplifier in the acquisition device after adjustment. The reference gain of the amplifier in the acquisition device. denoted as electric field strength.

4. The method according to claim 1, characterized in that, The method also includes: If the phase error in round t is less than the error threshold, output the corrected phase value for round t.

5. The method according to claim 1, characterized in that, The method also includes: If the number of times the phase error is adjusted exceeds the adjustment threshold, a manual inspection of the acquisition equipment is triggered.

6. The method according to claim 1, characterized in that, The method further includes: If multiple phase deviations exceed the second threshold, a smart contract alarm containing multiple phase deviation values ​​will be triggered, and the loop operation will be frozen.

7. The method according to claim 1, characterized in that, The method further includes: Obtain the time deviation at the current temperature; The second phase error is obtained based on the time deviation; Based on the second phase error, the original phase value of the t-th round is corrected a second time.

8. A high-voltage phase correction device based on multi-source data fusion, characterized in that, The device includes: The acquisition module is used to acquire the multi-source data of the ultra-high voltage equipment in the t-th round and the actual phase value of the ultra-high voltage equipment. The multi-source data in the t-th round includes: the original phase value, environmental parameters, and time; the environmental parameters include: temperature, humidity, and electric field strength. The processing module is used to input the multi-source data of the t-th round into the pre-trained neural network model to generate the correction coefficients of the t-th round; obtain the corrected phase value of the t-th round based on the correction coefficients of the t-th round and the original phase value; and obtain the phase error of the t-th round based on the corrected phase value of the t-th round and the true phase value. The correction module is used to determine whether the phase error in round t is greater than the error threshold. If the phase error in round t is greater than the error threshold, it determines whether the number of times the phase error is adjusted exceeds the adjustment number threshold. If the number of times the phase error is adjusted does not exceed the adjustment number threshold, the amplifier of the acquisition device is adjusted according to the electric field strength to obtain the multi-source data of round t+1 of the ultra-high voltage equipment.

9. A computing device, characterized in that, Including memory and processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method as described in any one of claims 1 to 7.

Images