Electric power parameter damage restoration method and device and electronic equipment

Abstract

The invention discloses a power parameter damage restoration method and device and electronic equipment. The method comprises the following steps: acquiring target power data and environmental parameters corresponding to power equipment; calling a data recovery model corresponding to the environmental parameters; determining damaged parameter items and non-damaged parameter items from the target power data by adopting an item identification module in the data recovery model; determining a first feature corresponding to the non-damaged parameter item by adopting a feature determination module in the data recovery model; adopting a parameter recovery module in a data recovery model to determine a recovery parameter value corresponding to the damaged parameter item according to the damaged parameter item and the first feature; and adopting a parameter combination module in the data recovery model to recover the target power data according to the recovery parameter value to obtain recovered power data. According to the method and the device, the technical problems that time and labor are wasted and overall restoration is not easy to achieve when power parameters with relatively high damage degree are restored in related technologies are solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular, to a method, device, and electronic device for restoring damaged power parameters. Background Art

[0002] Currently, when restoring damaged power parameters, the commonly used methods generally include techniques such as copying, tracing, or correction to achieve the restoration of current damaged power parameters. However, due to the uncertainty of the degree of damage to power parameters, when the degree of damage to power parameters is relatively large, relying solely on the commonly used techniques of copying, tracing, or correction for restoring damaged power parameters requires a large amount of time and labor costs, and it is difficult to achieve overall restoration. As a result, when restoring power parameters with a relatively large degree of damage, there are technical problems of being time-consuming and laborious and not being easily able to achieve overall restoration.

[0003] In response to the above problems, no effective solution has been proposed yet. Summary of the Invention

[0004] Embodiments of the present invention provide a method, device, and electronic device for restoring damaged power parameters to at least solve the technical problem in the related art that when restoring power parameters with a relatively large degree of damage, it is time-consuming and laborious and not easily able to achieve overall restoration.

[0005] According to one aspect of the embodiments of the present invention, a method for restoring damaged power parameters is provided, including: obtaining target power data corresponding to a power device and environmental parameters; retrieving a data restoration model corresponding to the environmental parameters, where the data restoration model is obtained by training an initial model based on sample data; using an item identification module in the data restoration model to determine damaged parameter items and non-damaged parameter items from the target power data, where the non-damaged parameter items are parameter items related to the damaged parameter items; using a feature determination module in the data restoration model to determine a first feature corresponding to the non-damaged parameter items; using a parameter restoration module in the data restoration model to determine a restored parameter value corresponding to the damaged parameter items based on the damaged parameter items and the first feature; using a parameter combination module in the data restoration model to restore the target power data based on the restored parameter value to obtain restored power data.

[0006] Optionally, in the parameter recovery module of the data recovery model, determining the recovery parameter value corresponding to the damaged parameter item according to the damaged parameter item and the first feature corresponding to the non-damaged parameter item includes: determining a plurality of candidate parameter values corresponding to the damaged parameter item according to the damaged parameter item and the first feature; determining the estimated probability values corresponding to the plurality of candidate parameter values, where the estimated probability value is used to represent the accuracy of the recovery parameter value corresponding to the damaged parameter item; and determining the recovery parameter value from the plurality of candidate parameter values according to the estimated probability values corresponding to the plurality of candidate parameter values, where the recovery parameter value is the candidate parameter value with the highest corresponding estimated probability value.

[0007] Optionally, determining a plurality of candidate parameter values corresponding to the damaged parameter item according to the damaged parameter item and the first feature includes: when the first feature includes a first feature item and a first feature value, determining the estimated feature value corresponding to the damaged parameter item under the first feature item according to the first feature value; and determining a plurality of candidate parameter values corresponding to the damaged parameter item according to the estimated feature value.

[0008] Optionally, when the first feature item is multiple and the estimated feature values corresponding to the damaged parameter item are multiple, determining the association degrees between the damaged parameter item and the multiple first feature items, where the multiple first feature items and the multiple estimated feature values correspond one by one; and determining a plurality of candidate parameter values corresponding to the damaged parameter item according to the association degrees between the damaged parameter item and the multiple first feature items and the estimated feature values corresponding to the multiple first feature items.

[0009] Optionally, using the feature determination module in the data recovery model to determine the first feature corresponding to the non-damaged parameter item includes: determining the second feature item corresponding to the damaged parameter item; determining whether there is a second feature value corresponding to the second feature item in the target power data, where the second feature value is a non-damaged value; and when there is no second feature value in the target power data, determining the first feature corresponding to the non-damaged parameter item.

[0010] Optionally, after determining whether there is a second feature value corresponding to the second feature item in the target power data, it further includes: when there is a second feature value in the target power data, using the parameter recovery module in the data recovery model to determine the recovery parameter value corresponding to the damaged parameter item according to the second feature value.

[0011] Optionally, obtain environmental parameters corresponding to the power equipment, including: obtaining identification information corresponding to the power equipment; determining a check code corresponding to the power equipment according to the identification information, where the check code is obtained by encrypting the environmental parameters corresponding to the power equipment using the low-density parity-check (LDPC) algorithm; and parsing the check code to obtain the environmental parameters.

[0012] According to one aspect of an embodiment of the present invention, there is provided a power parameter damage restoration device, including: an acquisition module configured to acquire target power data and environmental parameters corresponding to a power equipment; a first determination module configured to retrieve a data restoration model corresponding to the environmental parameters, where the data restoration model is obtained by training an initial model based on sample data; a second determination module configured to determine, in an item identification module of the data restoration model, damaged parameter items and non-damaged parameter items from the target power data, where the non-damaged parameter items are parameter items related to the damaged parameter items; a third determination module configured to determine, in a feature determination module of the data restoration model, a first feature corresponding to the non-damaged parameter items; a fourth determination module configured to determine, in a parameter restoration module of the data restoration model, a restored parameter value corresponding to the damaged parameter items according to the damaged parameter items and the first feature corresponding to the non-damaged parameter items; and a fifth determination module configured to restore the target power data according to the restored parameter value in a parameter combination module of the data restoration model to obtain restored power data.

[0013] According to one aspect of an embodiment of the present invention, there is provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement the power parameter damage restoration method described in any one of the above.

[0014] According to one aspect of an embodiment of the present invention, there is provided a computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the power parameter damage restoration method described in any one of the above.

[0015] In an embodiment of the present invention, target power data corresponding to a power device and environmental parameters are obtained; a data recovery model corresponding to the environmental parameters is retrieved, where the data recovery model is obtained by training an initial model based on sample data; an item recognition module in the data recovery model is used to determine damaged parameter items and non-damaged parameter items from the target power data, where the non-damaged parameter items are parameter items related to the damaged parameter items; a feature determination module in the data recovery model is used to determine a first feature corresponding to the non-damaged parameter items; a parameter recovery module in the data recovery model is used to determine a recovery parameter value corresponding to the damaged parameter items based on the damaged parameter items and the first feature; a parameter combination module in the data recovery model is used to recover the target power data based on the recovery parameter value to obtain recovered power data. It can be seen that the embodiment of the present invention uses a data recovery model corresponding to the environmental parameters of the power device to determine whether the relevant parameters of the power device are damaged, and when damaged, uses the first feature corresponding to the first feature of the non-damaged parameter items as a reference and recovery basis to help the data recovery model screen out candidate parameter values more in line with the current situation and perform data recovery, reducing the probability of incorrect recovery, achieving the purpose of accurately recovering damaged power parameter data, thereby realizing the technical effect of improving the restoration of damaged power parameters, and further solving the technical problems in the related art that it is time-consuming and laborious to recover power parameters with a large degree of damage and it is not easy to achieve overall restoration. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0017] Figure 1 is a flowchart of a method for restoring damaged power parameters according to an embodiment of the present invention;

[0018] Figure 2 is a flowchart of a method for restoring damaged power parameters provided by an alternative embodiment of the present invention;

[0019] Figure 3 is a module structure diagram of a computer management center provided by an alternative embodiment of the present invention;

[0020] Figure 4 is a structural block diagram of a device for restoring damaged power parameters according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0023] First, some nouns or terms that appear in the process of describing the embodiments of the present application are applicable to the following explanations:

[0024] Convolutional Neural Network: A Convolutional Neural Network is a deep learning model specifically designed to process data with a grid structure (such as images, videos, sounds, and texts, etc.). The CNN model has a unique architecture and advantages when processing such data, and can automatically detect important features in the input data without manual feature engineering. This is one of the main reasons for its remarkable achievements in the fields of computer vision, natural language processing, audio recognition, etc.

[0025] Feedforward Neural Network: A Feedforward Neural Network is a basic deep learning architecture in which the information in its structure flows unidirectionally, that is, from the input layer through the hidden layer (which can have one or more) to the output layer, without feedback loops. The feedforward neural network learns the mapping relationship from input to output through a multi-layer structure (input layer, hidden layer, output layer) and full connections between neurons. Its core advantage lies in its universal approximation ability, which can theoretically approximate any continuous function and is suitable for regression and classification tasks. Training uses the backpropagation algorithm to optimize the weights to minimize the loss function, thus showing good performance in fields such as image classification and speech recognition.

[0026] Low-Density Parity-Check (LDPC) Algorithm: The Low-Density Parity-Check (LDPC) algorithm is an efficient error detection and correction technique applicable to digital communication and storage. Its core lies in its parity-check matrix, which defines the parity-check relationships among the individual bits in the codeword. At the sending end, according to the LDPC coding rules, the original data bits are encoded into a codeword containing redundant information to enhance the noise resistance of the data. At the receiving end, the LDPC decoder is used to perform decoding iteratively based on the parity-check matrix and the received signal until approaching the Shannon limit. Due to its high error correction ability and good adaptability, the LDPC algorithm has been widely applied in fields such as satellite communication, optical fiber communication, mobile communication, and solid-state drives.

[0027] Embodiment 1

[0028] According to an embodiment of the present invention, an embodiment of a method for restoring damaged power parameters is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0029] Figure 1 is a flowchart of the method for restoring damaged power parameters according to an embodiment of the present invention, as Figure 1 shown, the method includes the following steps:

[0030] Step S102, obtain target power data corresponding to the power device and environmental parameters;

[0031] In step S102 provided in the present application, target power data corresponding to the power device and environmental parameters are obtained.

[0032] Among them, target power data is involved. Target power data is data reflecting the states and operating conditions of various physical quantities during the conversion and transmission of electrical energy in the power system, such as three-phase voltage, three-phase current, active power, etc. The target power data may be damaged for various reasons during transmission to the computer management center, such as being attacked by hackers, circuit failures, manual errors, etc.

[0033] Among them, environmental parameters are involved. Environmental parameters are parameters related to the operating environment of the power device, such as time, weather, location, etc. These data are crucial for the power device status, fault diagnosis, operation optimization, and ensuring the stability and efficiency of the power system. And under different environmental parameters, the target power data corresponding to the power device is different. Therefore, environmental parameters can be used for subsequent target power data processing or recovery processes.

[0034] Since the collection of environmental parameters helps the system understand the performance of power equipment under different conditions, and the operating states of power equipment under different environments affect the changes in target power data, therefore, analyzing and restoring the target power data in combination with environmental parameters can make the restored power data more conform to the real data in the actual situation.

[0035] Step S104: Retrieve the data recovery model corresponding to the environmental parameters, where the data recovery model is obtained by training the initial model based on sample data.

[0036] In step S104 provided in this application, the data recovery model corresponding to the environmental parameters is retrieved.

[0037] Among them, a data recovery model is involved. The data recovery model is specifically a model obtained by training based on sample data, and is used to query, identify, and process damaged data according to the environmental message.

[0038] Since the environmental parameters reflect the environment in which the power equipment operates, different environmental parameters will also result in different target power data corresponding to the power equipment. Therefore, under different environmental parameters, there are corresponding different data recovery models, thus forming the association relationship between the environmental parameters corresponding to the power equipment and the target power data corresponding to the power equipment. Therefore, selecting the corresponding data recovery model based on the power parameters and deeply analyzing the current environmental parameters can more accurately determine the target power data corresponding to the power equipment under the current environmental parameters, which helps to improve the accuracy of restoring damaged power data.

[0039] It should be noted that the data recovery model can be a deep learning algorithm model, and no specific limitation is made here, and it can be custom-set according to the actual application and scenario.

[0040] Step S106: Use the item recognition module in the data recovery model to determine the damaged parameter items and non-damaged parameter items from the target power data, where the non-damaged parameter items are the parameter items related to the damaged parameter items.

[0041] In step S106 provided in this application, based on the item recognition module in the data recovery model, the damaged parameter items and non-damaged parameter items of the target power data are determined.

[0042] Among them, a project identification module is involved. This project identification module is used to analyze parameters in the target power data, such as three-phase voltage, three-phase current, active power, etc. Through algorithm technology, it identifies which parameter items have damaged items. For example, the first-phase voltage data of the three-phase voltage is missing, and which parameter items are not damaged. For example, the second-phase voltage data of the three-phase voltage conforms to industry standards, so as to determine the damaged parameter items and non-damaged parameter items in the target power data. This project identification module helps the data recovery model quickly lock the location of abnormal data in complex power data and provides a basis for subsequent recovery processing.

[0043] Among them, a damaged parameter item is involved. This damaged parameter item is the parameter item corresponding to the damaged parameter value (such as becoming unreliable, missing or incorrect) in the target power data due to various reasons (such as transmission errors, equipment failures, signal attenuation, etc.). For example, if the first-phase voltage data in the three-phase voltage of the target power data is missing, then the first-phase voltage is the damaged parameter item.

[0044] Among them, a non-damaged parameter item is involved. This non-damaged parameter item is the parameter item in the target power data that is not damaged and is related to the damaged item. For example, if the first-phase voltage data of the three-phase voltage in the target power data is missing, then the first-phase voltage is the damaged parameter item. In the case where the second-phase voltage and the third-phase voltage are not damaged, based on the fixed phase relationship (120 degrees apart from each other) between the three-phase voltages and usually assuming that the three-phase system has good symmetry, when the voltages of two of the phases are known, the missing voltage value of the first-phase voltage can be estimated through mathematical calculations and phase relationships. In this scenario, the second-phase voltage and the third-phase voltage are non-damaged parameter items.

[0045] Since the degree of damage in the target power data varies, and the situations of which power parameter items are damaged and which are not damaged in the target power data are different, by determining the damaged parameter items, the pertinence and reliability of data recovery can be improved, the repetitive troubleshooting work is reduced, thereby improving the efficiency of data recovery and saving the data recovery cost. By determining the non-damaged parameter items related to the damaged parameter items and using the non-damaged parameter items as reliable reference data for data recovery, the recovery error can be effectively reduced, providing a basis for the accuracy of subsequent data recovery.

[0046] It should be noted that regarding the identification method of this project identification module, no specific restrictions are imposed here, and it can be custom-set according to actual applications and scenarios.

[0047] Step S108, using the feature determination module in the data recovery model, determine the first feature corresponding to the non-damaged parameter item;

[0048] In step S108 provided in this application, based on the feature determination module in the data recovery model, the first feature corresponding to the non-damaged parameter item is determined.

[0049] Among them, the feature determination module is involved. This feature determination module is used to extract and identify the features of non-damaged parameter items. For example, when the non-damaged parameter item is the second-phase voltage, this feature determination module extracts the first feature corresponding to the second-phase voltage through the data of the second-phase voltage, such as the waveform, frequency, and peak value of the second-phase voltage. The extracted first feature will provide a recovery reference basis for the subsequent recovery of damaged parameter items to ensure the accuracy of the recovery of damaged parameter items.

[0050] Among them, the first feature is involved. This first feature is the key information extracted from non-damaged parameter items to characterize non-damaged parameter items. For example, when the non-damaged parameter item is the second-phase voltage, its first feature can be waveform, frequency, and peak value. Among them, the waveform is the shape or pattern of the second-phase voltage changing with time, which can reflect the stability, periodicity, and whether there are abnormal fluctuations or distortions of the second-phase voltage. The frequency is the rate or period of the second-phase voltage change. The stability of the frequency reflects the stability of the second-phase voltage. The peak value is the maximum value reached by the second-phase voltage within a cycle. The size of the peak value directly reflects the intensity of the second-phase voltage. By extracting the first feature, when a damaged parameter item (such as the voltage of another phase) needs to be recovered, it can be used as a reference benchmark in the recovery process. By comparing the features of the damaged parameter item after recovery with the first feature of the non-damaged parameter item, the accuracy and integrity of the recovery can be ensured.

[0051] Determining the first feature corresponding to the non-damaged parameter item provides a realistic and feasible benchmark and reference for the accurate recovery of damaged parameter items. Specifically, since the physical meanings of the power parameters represented by different power parameter items are different, the correlation relationships between each power parameter item are also different. Considering the accuracy of the recovery of damaged parameter items, it is necessary to select a non-damaged parameter item related to the damaged parameter item as the reference basis. When a damaged parameter item needs to be recovered, by determining the first feature of the non-damaged item related to the damaged item and based on this first feature, the damaged parameter item can be recovered more directly and targeted. At the same time, due to the correlation between the damaged parameter item and the non-damaged parameter item, the interference of irrelevant data is avoided, the influence of errors is reduced, and the accuracy of the recovery is ensured.

[0052] It should be noted that regarding the feature extraction method of this feature determination module, it can be a convolutional neural network, and no specific limitation is made here. It can be customized according to the actual application and scenario.

[0053] Step S110, using the parameter recovery module in the data recovery model, based on the damaged parameter item and the first feature, determine the recovery parameter value corresponding to the damaged parameter item;

[0054] In step S110 provided in this application, based on the parameter recovery module in the data recovery model, the damaged parameter item and the first feature, the recovery parameter value corresponding to the damaged parameter item is determined.

[0055] Among them, the parameter recovery module is involved. This parameter recovery module is used to analyze the damaged parameter item and the first feature to determine the recovery parameter value corresponding to the damaged parameter item. For example, if the damaged parameter item is the first-phase voltage and the non-damaged parameter item is the second-phase voltage, and the first features of the non-damaged parameter item are waveform, frequency, and peak value, by analyzing the waveform, frequency, and peak value of the second-phase voltage, the waveform, frequency, and peak value corresponding to the first-phase voltage are determined, and the waveform, frequency, and peak value corresponding to the first-phase voltage obtained will be used as the reference basis for subsequent recovery of the first-phase voltage to ensure the accuracy of the recovered power data, and thus ensure the overall restoration of the target power data.

[0056] Among them, the recovery parameter value is involved. This recovery parameter value is the value corresponding to the damaged parameter item obtained based on the damaged parameter item and the first feature. For example, if the damaged parameter item is the first-phase voltage and the first feature of the non-damaged parameter item is the waveform, frequency, and peak value of the second-phase voltage, then through the parameter recovery module, the values corresponding to the waveform, frequency, and peak value of the first-phase voltage can be obtained.

[0057] Since the recovery parameter value corresponding to the damaged parameter item is determined based on the damaged parameter item (such as the first-phase voltage) and the first feature of the non-damaged parameter item (such as the waveform, frequency, and peak value of the second-phase voltage), this recovery process avoids the interference of irrelevant data, is more targeted, ensures that the recovery parameter value is closer to the actual value damaged by the damaged parameter item in the unified context of the non-damaged parameter item, thereby improving the accuracy of data recovery and ensuring the integrity and reliability of the recovered power data.

[0058] It should be noted that regarding the method for the parameter recovery module to determine the recovery parameter value, it can be a feed-forward neural network, and there is no specific limitation here, and it can be custom-set according to the actual application and scenario.

[0059] In step S112, the parameter combination module in the data recovery model is used to recover the target power data based on the recovery parameter value to obtain the recovered power data.

[0060] In step S112 provided in this application, based on the parameter combination module in the data recovery model and the recovery parameter value, the recovered power data is determined.

[0061] Among them, a parameter combination module is involved. The parameter combination module is used to restore the target power data according to the restoration parameter values and in combination with the non-damaged parameter items in the target power data, and finally obtain the restored power data. For example, if the damaged parameter item is the first item of voltage, the restoration parameter values corresponding to the waveform, frequency, and peak value in the first item of voltage obtained through the parameter combination module in the data restoration model are used to restore the value of the first item of voltage based on the obtained restoration parameter values corresponding to the waveform, frequency, and peak value, so as to obtain the value of the first item of voltage.

[0062] Among them, the restored power data is involved. The restored power data is power parameter data obtained by filling or correcting damaged or missing target power data based on a data restoration model combined with environmental parameters.

[0063] By integrating multiple restoration parameter values, it can be ensured that the obtained restored power data can more accurately fit the true value, and the problem of inaccurate power data restoration caused by the error of a single parameter value is avoided, thereby improving the accuracy of data restoration, ensuring the integrity and reliability of the restored power data, and further ensuring the overall restoration of the target power data.

[0064] It should be noted that there is no specific limitation on the method of determining the restored power data according to the parameter combination module here, and it can be adaptively set according to actual applications and scenarios.

[0065] Through the above steps S102 - S112, the target power data and environmental parameters corresponding to the power equipment are obtained; the data restoration model corresponding to the environmental parameters is retrieved, where the data restoration model is obtained by training the initial model according to the sample data; the item recognition module in the data restoration model is used to determine the damaged parameter items and non-damaged parameter items from the target power data, where the non-damaged parameter items are parameter items related to the damaged parameter items; the feature determination module in the data restoration model is used to determine the first feature corresponding to the non-damaged parameter items; the parameter restoration module in the data restoration model is used to determine the restoration parameter values corresponding to the damaged parameter items according to the damaged parameter items and the first feature; the parameter combination module in the data restoration model is used to restore the target power data according to the restoration parameter values to obtain the restored power data. It can be seen that the embodiment of the present invention uses the data restoration model corresponding to the environmental parameters of the power equipment to determine whether the relevant parameters of the power equipment are damaged, and uses the first feature corresponding to the first feature of the non-damaged parameter items as a reference and restoration basis in the case of damage to help the data restoration model screen out candidate parameter values that are more in line with the current situation and perform data restoration, reducing the probability of misrestoration, and further solving the technical problems in the related art that it is time-consuming and laborious to restore power parameters with a large degree of damage and it is not easy to achieve overall restoration.

[0066] As an alternative embodiment, in the parameter recovery module of the data recovery model, according to the damaged parameter item and the first feature corresponding to the non-damaged parameter item, determining the recovery parameter value corresponding to the damaged parameter item includes: determining a plurality of candidate parameter values corresponding to the damaged parameter item according to the damaged parameter item and the first feature; determining the estimated probability values respectively corresponding to the plurality of candidate parameter values, where the estimated probability value is used to represent the accuracy of the recovery parameter value corresponding to the damaged parameter item; and determining the recovery parameter value from the plurality of candidate parameter values according to the estimated probability values respectively corresponding to the plurality of candidate parameter values, where the recovery parameter value is the candidate parameter value with the highest corresponding estimated probability value.

[0067] In this embodiment, the specific steps of determining the recovery parameter value corresponding to the damaged parameter item according to the damaged parameter item and the first feature corresponding to the non-damaged parameter item in the parameter recovery module of the data recovery model are described.

[0068] Among them, the candidate parameter value is involved. The candidate parameter value is an estimated value that may conform to the original value of the damaged parameter item determined according to the damaged parameter item and the first feature.

[0069] Among them, the estimated probability value is involved. The estimated probability value is used to represent the accuracy of the candidate parameter value representing the original value of the damaged parameter item.

[0070] In the steps involved in this embodiment, according to the damaged parameter item and the first feature of the non-damaged parameter item, a plurality of candidate parameter values of the possible damaged parameter items are predicted, and the estimated probability value corresponding to each candidate parameter value is determined, which is used to reflect the accuracy of the candidate parameter value as the recovery parameter value. Select a candidate parameter value with the highest estimated probability value from the plurality of candidate parameter values as the actual recovery parameter value, which is used to fill or replace the value of the damaged parameter item to restore the integrity of the power data. By determining the estimated probability values respectively corresponding to the plurality of candidate parameter values, the accuracy of the candidate parameter values corresponding to the plurality of candidate parameter values that can represent the original value of the damaged parameter item can be initially judged. Taking the corresponding estimated probability value as a reference makes the selected candidate parameter value more conform to the original value of the damaged parameter item, thereby improving the accuracy of the recovery parameter value obtained according to the candidate parameter value, improving the accuracy of data recovery, and ensuring the integrity and reliability of the restored power data.

[0071] It should be noted that the method for determining the candidate parameter value and the estimated probability value can be a feedforward neural network, which is not specifically limited here and can be custom-set according to the actual application and scenario.

[0072] As an alternative embodiment, according to the damaged parameter item and the first feature, a plurality of candidate parameter values corresponding to the damaged parameter item are determined, including: when the first feature includes a first feature item and a first feature value, according to the first feature value, the estimated feature value corresponding to the damaged parameter item under the first feature item is determined; and according to the estimated feature value, a plurality of candidate parameter values corresponding to the damaged parameter item are determined.

[0073] In this embodiment, the specific steps of determining the recovery parameter value corresponding to the damaged parameter item according to the damaged parameter item and the first feature corresponding to the non-damaged parameter item in the parameter recovery module of the data recovery model are described.

[0074] Among them, the first feature item is involved. The first feature item is the item corresponding to the first feature. For example, if the non-damaged parameter item is the first-phase voltage, then the corresponding first feature items are waveform, frequency, and peak value.

[0075] Among them, the first feature value is involved. The first feature value is the specific value corresponding to the first feature item. For example, assuming that the effective value of the first-phase voltage is 220V, the corresponding first feature items are waveform, frequency, and peak value, where the first feature value corresponding to the waveform is a sine wave, the first feature value corresponding to the frequency is 50Hz, and the first feature value corresponding to the peak value is 311V.

[0076] Since the non-damaged parameter item is related to the damaged parameter item, therefore, taking the first feature item and the first feature value corresponding to the first feature of the first item of the non-damaged parameter item as the reference and recovery basis makes the determined candidate parameter values more in line with the actual situation of the damaged parameter item, that is, helps the data recovery model to screen out candidate parameter values more in line with the current situation, reduces the probability of incorrect recovery, and thus helps the subsequent recovery of the damaged parameter item, improving the accuracy of recovering damaged power data.

[0077] As an alternative embodiment, according to the estimated feature value, a plurality of candidate parameter values corresponding to the damaged parameter item are determined, including: when there are a plurality of first feature items and a plurality of estimated feature values corresponding to the damaged parameter item, the association degrees between the damaged parameter item and the plurality of first feature items are determined, where the plurality of first feature items and the plurality of estimated feature values correspond one by one; and according to the association degrees between the damaged parameter item and the plurality of first feature items respectively, and the estimated feature values corresponding to the plurality of first feature items respectively, a plurality of candidate parameter values corresponding to the damaged parameter item are determined.

[0078] In this embodiment, the specific steps of determining a plurality of candidate parameter values corresponding to the damaged parameter item are described.

[0079] In the steps involved in this embodiment, when there are multiple first feature items and multiple estimated feature values corresponding to the damaged parameter items, determine the degree of association between each damaged parameter item and the multiple first feature items. Among them, the multiple first feature items correspond one-to-one with the multiple estimated feature values. Based on the degree of association between each damaged parameter item and the multiple first feature items, and the estimated feature values corresponding to the multiple first feature items, determine multiple candidate parameter values corresponding to the damaged parameter item. For example, if the damaged parameter item is the first-phase voltage, and the non-damaged parameter items are the second-phase voltage and the third-phase voltage, and their corresponding feature items are waveform, frequency, and peak value, then according to the waveform of the second-phase voltage and the waveform of the third-phase voltage, estimate the waveform range of the first-phase voltage. Similarly, estimate the corresponding frequency range and peak value range of the first-phase voltage. According to the association relationship (such as weight value) between the first-phase voltage and the waveform, frequency, and peak value corresponding to the first-phase voltage, and combine the estimated values of the waveform, frequency, and peak value corresponding to the first-phase voltage, determine multiple candidate voltage values corresponding to the first-phase voltage.

[0080] Since different first feature items have different degrees of influence on the damaged parameter item, their importance for restoring the value of the damaged parameter item is also different. Therefore, it is necessary to consider the degree of association between multiple first feature items and the damaged parameter item. For example, assigning higher weights to more important feature items can improve the accuracy and interpretability of the estimation, and at the same time can avoid a certain feature item being overly dominant due to data imbalance. For example, the value range of some feature items may be much larger than that of others, thereby improving the accuracy of the estimation.

[0081] As an alternative embodiment, use the feature determination module in the data recovery model to determine the first feature corresponding to the non-damaged parameter item, including: determining the second feature item corresponding to the damaged parameter item; determining whether there is a second feature value corresponding to the second feature item in the target power data, where the second feature value is a non-damaged value; in the case where the second feature value does not exist in the target power data, determine the first feature corresponding to the non-damaged parameter item.

[0082] In this embodiment, the specific steps for determining the first feature corresponding to the non-damaged parameter item are described.

[0083] Among them, the second feature item is involved, and the second feature item is the non-damaged feature item corresponding to the damaged parameter item.

[0084] Among them, the second feature value is involved, and the second feature value is the specific value corresponding to the second feature item. For example, when the damaged parameter item is the first-phase voltage, the first feature item can be the waveform, frequency, and peak value corresponding to the first-phase voltage to determine whether the feature corresponding to the first feature item is a damaged value. If the feature values corresponding to the waveform, frequency, and peak value are all damaged (such as missing), then it means that the second feature value does not exist in the target power data.

[0085] In the steps involved in this embodiment, determine the second feature item corresponding to the damaged parameter item; determine whether there is a second feature value corresponding to the second feature item in the target power data, where the second feature value is an undamaged value; in the case where the second feature value does not exist in the target power data, determine the first feature corresponding to the undamaged parameter item. For example, if the damaged parameter item is the first-phase voltage, and the first feature items corresponding to the first-phase voltage, such as waveform, peak value, and frequency, are all damaged items, then it indicates that there is no second feature value in the target power data. In this case, determine the first feature corresponding to the undamaged parameter item.

[0086] By analyzing whether there is a second feature value corresponding to the second feature item, it fully considers that when there is no undamaged second feature item, it is necessary to determine the first feature corresponding to the undamaged parameter item, and when there is an undamaged second feature item, the second feature item corresponding to the damaged parameter item is preferentially selected. It comprehensively considers the actual damaged situation of the damaged parameter item during the recovery process, and improves the reliability of recovering the damaged power data.

[0087] As an alternative embodiment, after determining whether there is a second feature value corresponding to the second feature item in the target power data, it further includes: in the case where the second feature value exists in the target power data, use the parameter recovery module in the data recovery model to determine the recovery parameter value corresponding to the damaged parameter item according to the second feature value.

[0088] In this embodiment, the specific steps of determining the recovery parameter value corresponding to the damaged parameter item in the case where the second feature value exists in the target power data are described.

[0089] In the steps involved in this embodiment, in the case where the second feature value exists in the target power data, use the parameter recovery module in the data recovery model to determine the recovery parameter value corresponding to the damaged parameter item according to the second feature value. For example, in the case where the damaged parameter item is the first-phase voltage, the determined second feature items are waveform, frequency, and peak value, and the feature values corresponding to waveform, frequency, and peak value are not damaged. Then, the value of the first-phase voltage can be determined according to the feature values corresponding to waveform, frequency, and peak value.

[0090] By analyzing whether there is a second feature value corresponding to the second feature item, it fully considers that when there is an undamaged second feature item, its corresponding second feature value can be used, and there is no need to estimate based on the undamaged parameter item, saving the time for determining the specific value corresponding to the damaged parameter item, thereby improving the efficiency of recovering the power data. Moreover, compared with the estimated value based on the undamaged parameter item, when the damaged parameter item has an undamaged feature item, the damaged power data is recovered through the value of the real feature item, making the recovered power data more accurate and reliable.

[0091] As an alternative embodiment, obtaining environmental parameters corresponding to a power device includes: obtaining identification information corresponding to the power device; determining a check code corresponding to the power device according to the identification information, where the check code is obtained by encrypting the environmental parameters corresponding to the power device using the low-density parity-check (LDPC) algorithm; and parsing the check code to obtain the environmental parameters.

[0092] In this embodiment, the specific steps for determining the environmental parameters are described.

[0093] Among them, identification information is involved. The identification information is information used to identify the power device, such as the model of the power device.

[0094] Among them, a check code is involved. The check code is a coding method used to detect errors in power data transmission or storage.

[0095] Among them, the low-density parity-check (LDPC) algorithm is involved. The low-density parity-check (LDPC) algorithm is a coding method that obtains a codeword through the product of sparse matrices. Its parity-check matrix has the characteristic of low density, that is, relative to the length of rows and columns, the number of non-zero elements (row weight, column weight) in each row and column of the parity-check matrix is very small.

[0096] In the steps involved in this embodiment, obtain the identification information corresponding to the power device; determine the check code corresponding to the power device according to the identification information, where the check code is obtained by encrypting the environmental parameters corresponding to the power device using the LDPC algorithm; and parse the check code to obtain the environmental parameters. For example, after collecting the environmental parameters of the power device and encoding them using LDPC codes, when the environmental parameters need to be obtained, first, the identification information of the power device needs to be determined, and then the check code is determined based on the obtained identification information. The check code is an LDPC code. Then, the original environmental parameters are restored through the decoding algorithm of the LDPC code, thereby protecting the integrity of the environmental parameters.

[0097] Since the environmental parameters may be damaged during transmission or storage for various reasons (such as malicious tampering, theft, interference, etc.), encrypting and protecting them by selecting an appropriate check code improves the reliability and security of the environmental parameters during transmission or storage. Through the encoding process of LDPC codes, it can be ensured that these environmental parameters have high reliability and anti-interference ability during transmission or storage. And even if interference occurs during transmission or storage, the decoding algorithm of LDPC codes can effectively restore the original environmental parameters, thereby protecting the integrity of the environmental parameters.

[0098] Based on the above embodiments and alternative embodiments, an alternative implementation manner is provided, which is specifically described below.

[0099] In the related art, when using technologies such as copying, tracing, or correction to restore damaged power data, in the case of a relatively large degree of damage to the power data, there are problems of being time-consuming and laborious, and it is not easy to achieve overall restoration. For example, during the process of sending the collected power parameters from the on-line power parameter monitor to the computer management center, it is disturbed by reasons such as hacker attacks, circuit failures of the on-line power parameter (the same as the above power data) monitor, and manual errors. The power parameters transmitted to the computer management center will be lost or damaged. Currently, the power parameter restoration mode generally relies on technologies such as copying, tracing, or correction. However, such modes are often very time-consuming and laborious, and it is not easy to achieve overall restoration in the case of a relatively large degree of loss or damage to the power parameters.

[0100] In view of this, in an alternative embodiment of the present invention, a method and system for restoring damaged power parameters are provided, which can also be referred to as a processing system and method for power parameters, and can effectively solve the problem in the related art that in the case of a relatively large degree of damage to the power data, it is time-consuming and laborious and not easy to achieve overall restoration.

[0101] (1) For the method of restoring damaged power parameters:

[0102] Figure 2 It is a flowchart of the method for restoring damaged power parameters provided by an alternative embodiment of the present invention. As Figure 2 shown, the following will provide a detailed description of the alternative embodiments of the present application.

[0103] S1, obtain target power data corresponding to the power equipment and environmental parameters;

[0104] Specifically, S1 further includes:

[0105] S11, obtain identification information corresponding to the power equipment;

[0106] S12, according to the identification information, determine the check code corresponding to the power equipment, where the check code is obtained by encrypting the environmental parameters corresponding to the power equipment using the low-density parity-check LDPC algorithm;

[0107] S13, analyze the check code to obtain environmental parameters.

[0108] For example, the on-line power parameter monitor sends the collected power parameters to the computer management center for processing. The method for conditioning the damaged power parameters includes: performing processing on the damaged power parameters using the binning method, and then performing processing on the power parameters after the binning method using the mean filtering algorithm, so as to achieve conditioning of the damaged power parameters.

[0109] Next, store the processed power parameters in the computer management center. The method for sending and performing processing in the computer management center includes: receiving damaged power parameters and conditioning the damaged power parameters; extracting information of additional information items from the conditioned power parameters and applying an independent LDPC code to the information of the additional information items; when an error occurs in the additional information item, using the LDPC algorithm to correct and restore the information of the additional information item, and then extracting the information of the additional information item from it to obtain the corresponding environmental message (the same as the above environmental parameters); the additional information item is an information item in the form of a message additionally attached to the power parameters, and is used to store the environmental message corresponding to the power parameters. The environmental message contains information such as the power equipment to which the corresponding power parameters belong and the location of the power equipment.

[0110] S2, retrieve the data recovery model corresponding to the environmental parameters, where the data recovery model is obtained by training the initial model based on sample data;

[0111] For example, query the transfer policy model (the same as the above data recovery model) from the standby terminal according to the environmental message, including: the policy model contains various items (the same as the above power parameters) and components (the same as the above parameter items) required for the set environment; the standby terminal constructs corresponding associations between the required power parameters and the item components in the model according to the item categories and performs storage; the standby terminal receives the query, retrieves the corresponding transfer policy model according to the environmental message, and transmits it to the computer management center.

[0112] According to different environmental information, different policy models are selected. Specifically, according to the correct power parameters, the attributes of the faulty or missing power information are normally predicted, so as to obtain more accurate recovery results. For some environments, the processing personnel can omit some less critical faulty or missing power parameters, saving the resource consumption of power parameter restoration. After sending it to the feedforward neural network for prediction, the normal power parameters can still be restored in the end.

[0113] Among them, the standby terminal stores the relevant associations of different environments and attribute policies. According to the environment, several attribute policies are selected to form a policy model under the set environment. Attributes with high coherence form an item, and the attribute is a component in the item. The item is various types of power parameters such as three-phase voltage, three-phase current, and active power.

[0114] S3, use the item recognition module in the data recovery model to determine the damaged parameter items and non-damaged parameter items from the target power data, where the non-damaged parameter items are the parameter items related to the damaged parameter items;

[0115] For example, supplement the adjusted power parameters (same as the above target power data) according to the transmitted policy model, search for incorrect or missing entries (same as the above damaged parameter items), and obtain the identification codes of the incorrect or missing entries.

[0116] S4. Use the feature determination module in the data recovery model to determine the first feature corresponding to the non-damaged parameter items.

[0117] For example, use a convolutional neural network to extract the attributes (same as the above first feature) of the correct entries (same as the above non-damaged parameter items) in the adjusted power parameters (same as the above target power data), and obtain a number of attribute quantities one.

[0118] Specifically, S4 further includes:

[0119] S41. Determine the second feature item corresponding to the damaged parameter item;

[0120] S42. Determine whether there is a second feature value corresponding to the second feature item in the target power data, where the second feature value is a non-damaged value;

[0121] S43. In the case where the second feature value does not exist in the target power data, determine the first feature corresponding to the non-damaged parameter item. In the case where the second feature value exists in the target power data, use the parameter recovery module in the data recovery model to determine the recovery parameter value corresponding to the damaged parameter item according to the second feature value.

[0122] S5. Use the parameter recovery module in the data recovery model to determine the recovery parameter value corresponding to the damaged parameter item according to the damaged parameter item and the first feature;

[0123] S6. Use the parameter combination module in the data recovery model to recover the target power data according to the recovery parameter value to obtain the recovered power data.

[0124] Specifically, S6 further includes:

[0125] S61. Determine multiple candidate parameter values corresponding to the damaged parameter item according to the damaged parameter item and the first feature;

[0126] S62. Determine the estimated probability values corresponding to the multiple candidate parameter values respectively, where the estimated probability value is used to represent the accuracy of the recovery parameter value corresponding to the damaged parameter item;

[0127] S63. Determine the recovery parameter value from the multiple candidate parameter values according to the estimated probability values corresponding to the multiple candidate parameter values respectively, where the recovery parameter value is the candidate parameter value with the highest corresponding estimated probability value.

[0128] Specifically, S61 further includes:

[0129] S611. When the first feature includes a first feature item and a first feature value, based on the first feature value, determine the estimated feature value corresponding to the damaged parameter item under the first feature item.

[0130] S612. Based on the estimated feature value, determine multiple candidate parameter values corresponding to the damaged parameter item.

[0131] Specifically, S612 further includes:

[0132] S6121. When there are multiple first feature items and multiple estimated feature values corresponding to the damaged parameter item, determine the degree of association between the damaged parameter item and each of the multiple first feature items, where the multiple first feature items and the multiple estimated feature values are in one-to-one correspondence.

[0133] S6122. Based on the degree of association between the damaged parameter item and each of the multiple first feature items, and the estimated feature values corresponding to each of the multiple first feature items, determine multiple candidate parameter values corresponding to the damaged parameter item.

[0134] For example, send the identification codes of several attribute quantities I with errors or omissions into a feedforward neural network to estimate several candidate attribute clusters of the entries with errors or omissions and their corresponding probabilities (the same as the above-mentioned estimated feature values). Each candidate attribute cluster contains several estimated attribute values (the same as the above-mentioned multiple candidate parameter values).

[0135] Select the candidate attribute cluster with the highest probability, extract several attribute values from it (the same as the restored parameter values corresponding to the damaged parameter item above), combine it with the attribute quantity I to obtain a complete attribute group of power parameters; perform a traceability process on the attribute group to obtain the restored power parameters and store them as the processed power parameters in the computer management center. The method of combining several attribute values and the attribute quantity I includes: performing a ⊕ operation or a union operation on several attribute values and the attribute quantity I to obtain an attribute group.

[0136] (2) For the power parameter damage restoration system:

[0137] The system mainly includes three modules, namely, an online monitoring data subsystem, a calculation management subsystem, and a standby terminal subsystem.

[0138] Among them, the online monitoring data subsystem is communicatively connected to the calculation management subsystem. The online monitoring data subsystem is responsible for sending the collected original power data and original environmental parameters to the calculation management subsystem for preprocessing to obtain the processed target power data and environmental parameters, and storing them in the calculation management subsystem.

[0139] For example, an on-line monitor for electric power parameters (same as the above-mentioned on-line monitoring data subsystem) is communicatively connected to a computer management center (same as the above-mentioned computer management subsystem). The on-line monitor for electric power parameters is used to send the collected electric power parameters (same as the above-mentioned original electric power data and original environmental parameters) to the computer management center for processing, and then store the processed electric power parameters in the computer management center.

[0140] The computer management subsystem is communicatively connected to a standby terminal subsystem, and a plurality of data recovery models are stored in the standby terminal subsystem.

[0141] For example, the computer management center is also communicatively connected to a standby terminal (same as the above-mentioned standby terminal subsystem), and a transfer policy model is stored in the standby terminal; different types of environmental attribute policies are stored in the standby terminal, and the processing personnel can then expand and input more environmental information, thus maintaining the expansion function for this method.

[0142] Among them, the computer management subsystem further includes three modules, namely, a collection module, an extraction module, and a query module.

[0143] The collection module is used to collect target electric power data;

[0144] The extraction module is used to obtain environmental parameters;

[0145] The query module is used to retrieve a data recovery model according to the environmental parameters.

[0146] The supplementary search module is used to analyze the target electric power data by using the data recovery model to determine the damaged parameter items and non-damaged parameter items in the target electric power data;

[0147] The feature extraction module is used to extract the first feature of the non-damaged parameter items;

[0148] The estimation module is used to determine, according to the first feature of the non-damaged parameter items and the damaged parameter items, a plurality of candidate parameter values corresponding to the damaged parameter items and the estimated feature values respectively corresponding to the plurality of candidate parameter values;

[0149] The combination module is used to select the candidate parameter value with the largest estimated feature value as the recovery parameter value corresponding to the damaged parameter item and combine it with the first feature of the non-damaged parameter items;

[0150] The restoration module is used to restore the target electric power data by using the combined recovery parameter value and the first feature to obtain the restored electric power data.

[0151] For example, the computer management center mainly includes eight modules, Figure 3 which is the module structure diagram of the computer management center provided by an alternative embodiment of the present invention, as Figure 3As shown below, a detailed description of the computer management center in the alternative embodiments of the present application will be given.

[0152] A charging module, configured to charge the damaged power parameters and perform conditioning on the damaged power parameters;

[0153] An extraction module, configured to extract the information of the additional information item from the conditioned power parameters, and apply an independent LDPC code to the information of the additional information item; when an error occurs in the additional information item, use the LDPC algorithm to correct and restore the information of the additional information item, and then extract the information of the additional information item from it to obtain the corresponding environmental message;

[0154] An inquiry module, configured to inquire about the transmission policy model from the standby terminal according to the environmental message.

[0155] A supplementary search module, configured to supplement the conditioned power parameters according to the transmitted policy model, search for the incorrect or missing entries, and obtain the identification codes of the incorrect or missing entries;

[0156] An attribute extraction module (same as the above-mentioned feature extraction module), configured to use a convolutional neural network to perform attribute extraction on the correct entries in the conditioned power parameters to obtain a number of attribute quantities one;

[0157] An estimation module, configured to send the number of attribute quantities one and the identification codes of the incorrect or missing entries into a feedforward neural network to estimate a number of candidate attribute clusters of the incorrect or missing entries and their corresponding probabilities;

[0158] A combination module, configured to select the candidate attribute cluster with the highest probability, extract a number of attribute values from it, combine it with the attribute quantity one to obtain a complete attribute group of the power parameters;

[0159] A restoration module, configured to perform traceability processing on the attribute group to obtain the restored power parameters as the processed power parameters and store them in the computer management center.

[0160] Through the above alternative embodiments, at least the following beneficial effects can be achieved:

[0161] (1) Compared with the related technology, the present invention uses the data recovery model corresponding to the environmental parameters of the power equipment to determine whether the relevant parameters of the power equipment are damaged, and uses the first feature corresponding to the first feature of the non-damaged parameter item as a reference and recovery basis in the case of damage, helps the data recovery model screen out candidate parameter values more in line with the current situation and perform data recovery, reduces the probability of incorrect recovery, achieves the purpose of accurately recovering the damaged power parameter data, thus realizing the technical effect of improving the restoration of damaged power parameters, and further solving the technical problems in the related technology that it is time-consuming and laborious to recover power parameters with a large degree of damage and it is not easy to achieve overall restoration.

[0162] (2) Compared with the related art, considering the accuracy of the restoration of damaged parameter items, the present invention selects the undamaged parameter items related to the damaged parameter item as the reference basis, and deeply analyzes and determines the first features of these undamaged parameter items through the data restoration model, so that the determined candidate parameter values are more in line with the actual situation of the damaged parameter item. At the same time, due to the correlation between the damaged parameter item and the undamaged parameter item, the interference of irrelevant data is avoided, the influence of errors is reduced, and thus the accuracy of the restoration is ensured.

[0163] (3) Compared with the related art, aiming at the problem that environmental parameters may be damaged due to malicious tampering, theft, interference and other factors during transmission or storage, the present invention adopts LDPC codes (low-density parity-check codes) for encryption protection, thereby improving the reliability and security of environmental parameters during transmission and storage. And the encoding mechanism of LDPC codes ensures that environmental parameters can have excellent anti-interference ability during transmission or storage, effectively resisting various external interferences. More importantly, even if interference occurs in the transmission or storage link, the decoding algorithm of LDPC codes can still accurately restore the original environmental parameters with its powerful error correction ability, thus ensuring the integrity and authenticity of environmental parameters.

[0164] (4) Compared with the related art, by determining the damaged parameter items and undamaged parameter items according to the data restoration model corresponding to the environmental parameters, and using the undamaged parameter items as a reliable reference for the data restoration of the damaged parameter items, the present invention can not only reduce the errors in the restoration process, but also avoid unnecessary repeated troubleshooting work, thereby effectively improving the overall efficiency of data restoration and correspondingly reducing the cost of data restoration, and solving the technical problem that it is not easy to achieve overall restoration in the current situation of missing or severely damaged power parameters.

[0165] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0166] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0167] Embodiment 2

[0168] According to an embodiment of the present invention, there is also provided a device for implementing the above-mentioned method for restoring damaged power parameters. Figure 4 It is a structural block diagram of a device for restoring damaged power parameters according to an embodiment of the present invention, as Figure 4 shown. The device includes: an acquisition module 402, a first determination module 404, a second determination module 406, a third determination module 408, a fourth determination module 410, and a fifth determination module 412. The device will be described in detail below.

[0169] The acquisition module 402 is used to acquire target power data corresponding to a power device and environmental parameters; the first determination module 404 is connected to the above-mentioned acquisition module 402 and is used to retrieve a data recovery model corresponding to the environmental parameters, where the data recovery model is obtained by training an initial model based on sample data; the second determination module 406 is connected to the above-mentioned first determination module 404 and is used to determine damaged parameter items and non-damaged parameter items from the target power data in the item recognition module of the data recovery model, where the non-damaged parameter items are parameter items related to the damaged parameter items; the third determination module 408 is connected to the above-mentioned second determination module 406 and is used to determine a first feature corresponding to the non-damaged parameter items in the feature determination module of the data recovery model; the fourth determination module 410 is connected to the above-mentioned third determination module 408 and is used to determine a recovery parameter value corresponding to the damaged parameter items according to the damaged parameter items and the first feature corresponding to the non-damaged parameter items in the parameter recovery module of the data recovery model; the fifth determination module 412 is connected to the above-mentioned fourth determination module 410 and is used to restore the target power data according to the recovery parameter value in the parameter combination module of the data recovery model to obtain recovered power data.

[0170] It should be noted here that the above-mentioned acquisition module 402, first determination module 404, second determination module 406, third determination module 408, fourth determination module 410, and fifth determination module 412 correspond to steps S102 to S112 in the implementation of the power parameter damage restoration method. The instances and application scenarios implemented by multiple modules and the corresponding steps are the same, but are not limited to the content disclosed in the above-mentioned Embodiment 1.

[0171] Embodiment 3

[0172] According to another aspect of the embodiments of the present invention, an electronic device is further provided, including: a processor; a memory for storing processor-executable instructions, wherein the processor is configured to execute the instructions to implement the power parameter damage restoration method of any one of the above.

[0173] Embodiment 4

[0174] According to another aspect of the embodiments of the present invention, a computer-readable storage medium is further provided. When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can execute the power parameter damage restoration method of any one of the above.

[0175] The above serial numbers of the embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0176] In the above embodiments of the present invention, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0177] In the several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of units can be a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of units or modules can be electrical or other forms.

[0178] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0179] In addition, in each embodiment of the present invention, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0180] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0181] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for restoring power parameters after damage, characterized in that: include: Acquire target power data and environmental parameters corresponding to the power equipment; Retrieving a data recovery model corresponding to the environmental parameters, wherein the data recovery model is obtained by training an initial model based on sample data; Using the item identification module in the data recovery model, determining damaged parameter items and non-damaged parameter items from the target power data, wherein the non-damaged parameter items are parameter items related to the damaged parameter items; Using a feature determination module in the data recovery model, determine a first feature corresponding to the non-damaged parameter item; Using a parameter recovery module in the data recovery model, according to the damaged parameter item and the first feature, determine a recovery parameter value corresponding to the damaged parameter item; The parameter combination module in the data recovery model is used to recover the target power data according to the recovery parameter value to obtain the recovered power data.

2. The method according to claim 1, characterized in that: The method of using the parameter recovery module in the data recovery model to determine the recovery parameter value corresponding to the damaged parameter item according to the damaged parameter item and the first feature corresponding to the non-damaged parameter item includes: Determining, based on the damaged parameter item and the first feature, a plurality of candidate parameter values ​​corresponding to the damaged parameter item; Determine estimated probability values ​​corresponding to the multiple candidate parameter values ​​respectively, wherein the estimated probability value is used to represent the accuracy of the restored parameter value corresponding to the damaged parameter item; A restored parameter value is determined from the multiple candidate parameter values ​​according to the estimated probability values ​​respectively corresponding to the multiple candidate parameter values, wherein the restored parameter value is the candidate parameter value having the highest corresponding estimated probability value.

3. The method according to claim 2, characterized in that The determining, based on the damaged parameter item and the first feature, a plurality of candidate parameter values ​​corresponding to the damaged parameter item includes: In the case where the first feature includes a first feature item and a first feature value, determining, according to the first feature value, an estimated feature value corresponding to the damaged parameter item under the first feature item; Based on the estimated characteristic value, a plurality of candidate parameter values ​​corresponding to the damaged parameter item are determined.

4. The method according to claim 3, characterized in that The step of determining a plurality of candidate parameter values ​​corresponding to the damaged parameter item based on the estimated characteristic value includes: In the case where there are multiple first feature items and multiple estimated feature values ​​corresponding to the damaged parameter item, determining the degree of association between the damaged parameter item and the multiple first feature items, respectively, wherein the multiple first feature items correspond to the multiple estimated feature values ​​one by one; According to the association degrees between the damaged parameter item and the plurality of first feature items, and the estimated feature values ​​corresponding to the plurality of first feature items, a plurality of candidate parameter values ​​corresponding to the damaged parameter item are determined.

5. The method according to claim 1, characterized in that The step of using a feature determination module in the data recovery model to determine a first feature corresponding to the non-damaged parameter item includes: Determining a second characteristic item corresponding to the damaged parameter item; Determine whether there is a second characteristic value corresponding to the second characteristic item in the target power data, wherein the second characteristic value is a non-damaged value; In a case where the second feature value does not exist in the target power data, the first feature corresponding to the non-damaged parameter item is determined.

6. The method according to claim 5, characterized in that After determining whether the target power data includes a second characteristic value corresponding to the second characteristic item, the method further includes: In the case where the second eigenvalue exists in the target power data, a parameter recovery module in the data recovery model is used to determine a recovery parameter value corresponding to the damaged parameter item according to the second eigenvalue.

7. The method according to any one of claims 1 to 6, characterized in that Obtain environmental parameters corresponding to power equipment, including: Obtaining identification information corresponding to the electric power equipment; Determine, according to the identification information, a check code corresponding to the electric power equipment, wherein the check code is obtained by encrypting the environmental parameters corresponding to the electric power equipment using a low-density parity check (LDPC) algorithm; The verification code is parsed to obtain the environmental parameters.

8. A device for restoring damaged power parameters, characterized in that: include: An acquisition module, used to acquire target power data and environmental parameters corresponding to the power equipment; A first determination module is used to retrieve a data recovery model corresponding to the environmental parameter, wherein the data recovery model is obtained by training an initial model based on sample data; A second determination module, configured to determine, in the item identification module in the data recovery model, damaged parameter items and non-damaged parameter items from the target power data, wherein the non-damaged parameter items are parameter items related to the damaged parameter items; A third determination module, configured to determine, in the feature determination module in the data recovery model, a first feature corresponding to the non-damaged parameter item; a fourth determination module, configured to determine, in a parameter recovery module in the data recovery model, a recovery parameter value corresponding to the damaged parameter item according to the damaged parameter item and the first feature corresponding to the non-damaged parameter item; The fifth determination module is used to restore the target power data according to the restoration parameter value in the parameter combination module in the data restoration model to obtain the restored power data.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the power parameter impairment recovery method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the power parameter impairment recovery method as described in any one of claims 1 to 7.

Images