Electric power system file management method based on big data

Abstract

The invention discloses an electric power system archive management method based on big data, and relates to the technical field of electric power archive management.The method comprises the steps that historical archive data of each piece of electric power equipment is processed, and the quality of each type of each component in each piece of electric power equipment is classified; the method can provide a basis for judging whether a product purchased by a purchaser is qualified and correct or not, then analyzes the authenticity of element maintenance in the power equipment, reduces the occurrence of false record of archive data, ensures the authenticity of work of the related purchaser and the authenticity of fund declaration and use, and improves the efficiency. Transparent operation and maintenance of the power system can be realized, the operation cost of the power system can be effectively controlled, when the authenticity is relatively low, the archive data of the power equipment is classified and analyzed, and meanwhile, display and prompt are performed according to the prompt priority, so that abnormal personnel and phenomena can be rectified and reformed in time, and the operation efficiency of the power system is improved. And the operation efficiency of power system maintenance is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power archive management, and in particular to a power system archive management method based on big data. Background Art

[0002] Power system archives refer to various forms of historical records with preservation value formed during the operation, maintenance and management of the power system. Managing power system archives can provide evidence for tracing problems when problems arise in the operation of the power system, thereby ensuring the efficiency of power system operation.

[0003] Existing technologies, such as the invention patent disclosed in the application with publication number CN118673528A, disclose an intelligent archive management method and system based on artificial intelligence. The method includes: building a blockchain archive management system to store and encrypt archives; deploying IoT sensors in the power system to collect sensor data in real time, designing an intelligent network scheduling algorithm to update archives in real time, and uploading them to the blockchain archive management system; building a deep learning model for intelligent identification and analysis to extract key information; building an equipment health model based on key information to analyze real-time sensor data and historical archive data, predict potential faults and anomalies, and generate early warning information; integrating natural language analysis technology to retrieve and analyze archives; and building a blockchain archive sharing platform based on archive data to share and collaboratively manage archives. The present invention solves the problem of insufficient data security and credibility in traditional archive management by utilizing blockchain technology to build a storage and management framework for power archive data.

[0004] The above scheme has at least the following deficiencies: 1. The archival data of the power system includes not only the relevant data of the power system operation, but also the information of equipment replacement, procurement and maintenance in the power system. The relevant responsible personnel should select appropriate equipment according to the operation of the power equipment to ensure the safety of operation and save costs. However, the above scheme lacks the analysis of the authenticity of the record data of the purchase and maintenance of relevant equipment in the archival data of the power system, thereby failing to ensure the authenticity of the work of the relevant responsible personnel and the authenticity of the declaration and use of funds, failing to achieve the transparency of the operation and maintenance of the power system, and failing to effectively control the cost of the power system operation.

[0005] 2. The quality of different models of power equipment in the power system is also different. However, the above scheme lacks analysis of the quality of different models of power equipment. It is impossible to accurately understand whether the products purchased by the purchasing personnel are qualified and correct, and it is also impossible to provide data reference and basis for the authenticity analysis of the archival data, thereby reducing the accuracy of the archival data. Summary of the Invention

[0006] In view of the above-mentioned technical deficiencies, the purpose of the present invention is to provide a power system archive management method based on big data.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solution: The present invention provides a power system archive management method based on big data, comprising the following steps: S1, obtaining the archive data and historical archive data of each power equipment, and using the historical archive data of each power equipment to classify the various models of various components in each power equipment, and obtain the type labels corresponding to the various models of various components in each power equipment.

[0008] S2. Analyze the authenticity of component maintenance in the power equipment based on the type labels of each component in each power equipment corresponding to each model and the historical archive data of each power equipment.

[0009] S3. When the authenticity of component maintenance in power equipment is low, the file data of each power equipment is classified using the type labels corresponding to each model of each type of component in each power equipment, and the prompt value of the file data of each power equipment is set, and the file data is sorted and displayed in descending order of the prompt value.

[0010] The beneficial effects of the present invention are as follows: the present application provides a power system archive management method based on big data, which processes the historical archive data of each power equipment and classifies the quality of each model of each component in each power equipment, and can provide a basis for judging whether the products purchased by the purchasing person in charge are qualified and correct, and then analyzes the authenticity of the maintenance of components in the power equipment, reduces the occurrence of false records in the archive data, ensures the authenticity of the work of relevant responsible personnel and the authenticity of fund declaration and use, is conducive to achieving the transparency of power system operation and maintenance, and can also effectively control the cost of power system operation, and when the authenticity is low, classifies and analyzes the archive data of each power equipment, and at the same time displays and prompts according to the priority order of prompts, and can promptly rectify abnormal personnel and phenomena to ensure the operational efficiency of power system maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 The figure is a flow chart of the steps for implementing the method of the present invention. DETAILED DESCRIPTION

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0014] See also Figure 1 As shown, a power system archive management method based on big data includes the following steps: S1, obtaining archive data and historical archive data of each power equipment, and using the historical archive data of each power equipment to classify the various models of various components in each power equipment, and obtain type labels corresponding to the various models of various components in each power equipment.

[0015] It should be noted that the archival data and historical archival data of each power equipment are stored in the power system. The archival data records relevant information such as the replacement, procurement and maintenance of power equipment, such as: the model, damage type, number of repairs and usage cycle of various components in the power equipment.

[0016] In a specific embodiment, the classification of various models of various components in each power equipment is carried out as follows: the model, damage type, number of repairs and usage cycle corresponding to each type of component in each power equipment are obtained from the historical archive data of each power equipment, and the damage type, number of repairs and usage cycle of each type of component in each power equipment corresponding to each model are counted.

[0017] Damage types include parts damage and accidental damage. The number of times each type of component in each power equipment corresponds to each model of parts damage and the number of times each type of component in each power equipment corresponds to each model are counted, and the weighted average usage cycle of each type of component in each power equipment corresponding to each model of each use is calculated. At the same time, based on the damage type of each type of component in each power equipment corresponding to each model of each use, the average usage cycle of parts damage of each type of component in each power equipment corresponding to each model of each use is obtained.

[0018] It should be noted that parts damage refers to damage caused by quality problems of the parts themselves, and accidental damage refers to damage caused by external emergencies, such as damage to electrical equipment caused by a tornado.

[0019] The damage levels of various components in various power equipment corresponding to various models are calculated using the number of times parts are damaged in use, the number of times parts are damaged accidentally, the number of times parts are repaired, and the average service life of parts damage. The damage levels include level 1 and level -1. When the damage level is level 1, the type label is a good quality type. When the damage level is level -1, the type label is a poor quality type.

[0020] In the above, the calculation process of the damage level of each type of component in each power equipment corresponding to each model is as follows: the number of times the parts are damaged in use, the number of times the parts are damaged accidentally, the number of times they are repaired, and the average service life of the parts are damaged are recorded as KN respectively. gxy , YK gxy 、WK gxy and TK gxy , where g represents the number of each electrical equipment, x represents the number of each component, and y represents the number of each model. All of g, x, and y are positive integers.

[0021] Using the calculation formula:

[0022] Get the damage level δ of the xth type component corresponding to the yth model in the gth power equipment gxy , where e represents a natural constant, κ represents the set part damage rate threshold, δ is the set part damage characteristic value threshold, YK and TK are the set maintenance times threshold and usage cycle threshold, respectively.

[0023] It should be noted that the parts damage rate threshold is the critical value for judging whether the proportion of damaged parts to the total number is large, and it is set by the power system engineer. When the parts damage rate is greater than the parts damage rate threshold, it indicates that the proportion of damaged parts is large and the quality is poor. Otherwise, it indicates that the proportion of damaged parts is small and the quality is good. Similarly, the parts damage characteristic value threshold is the critical value for judging whether damage is easy. It is set by the power system engineer. When the parts damage characteristic value is greater than the parts damage characteristic value threshold, it indicates that the quality is poor. Otherwise, it indicates that the quality is good. Among them, The calculated value represents the damage characteristic value of the xth component type corresponding to the yth model in the gth power equipment. The maintenance times threshold, the usage cycle threshold, and the component damage rate threshold are set in the same manner and are not further described here.

[0024] S2. Analyze the authenticity of component maintenance in the power equipment based on the type labels of each component in each power equipment corresponding to each model and the historical archive data of each power equipment.

[0025] In a specific embodiment, the authenticity of the maintenance of components in the power equipment is analyzed, and the specific process is as follows: the model, list of replacement responsible persons, maintenance responsible persons, purchase price and maintenance price corresponding to each replacement of each type of component in each power equipment are obtained from the historical archive data of each power equipment, and based on the type labels corresponding to each model of each type of component in each power equipment, the list of responsible persons, maintenance responsible persons, purchase unit price and maintenance unit price for each type of replacement of each model in each type of label corresponding to each type of component in each power equipment are obtained.

[0026] By using the list of responsible personnel, maintenance personnel, purchase unit price and maintenance unit price for each type of replacement of each model in each type of label corresponding to each type of component in each power equipment, the true characteristic value of power equipment replacement and the true characteristic value of power equipment maintenance are calculated, and then substituted into the authenticity assessment model to output the authenticity assessment results of component maintenance in power equipment.

[0027] The calculation process of the true characteristic value of the replacement of the power equipment is as follows: compare the lists of responsible persons for each replacement of each type of component corresponding to each model in each type of label in each power equipment, obtain the similarity of responsible persons for each replacement of each type of component corresponding to each model in each type of label in each power equipment, record each replacement for which the similarity of responsible persons for each model of each type of component corresponding to each type of label in each power equipment is greater than the set responsible person similarity threshold as each tag replacement, and count the number of tag replacements of each model of each type of component corresponding to each type of label in each power equipment.

[0028] It should be noted that the number of repeated responsible persons in the list of responsible persons between each replacement of each model in each type of label corresponding to each type of component in each power equipment is obtained, and then divided by the total number of responsible persons in the list of responsible persons for each replacement, to obtain the similarity of responsible persons between each replacement of each model in each type of label corresponding to each type of component in each power equipment.

[0029] The process of setting the responsible person similarity threshold is the same as that of setting the parts damage rate threshold, and will not be repeated here.

[0030] Take the responsible persons whose number of appearances in the list of responsible persons for each replacement of each model in each type of label corresponding to each type of component in each power equipment is greater than the appearance number threshold as the first-class label responsible persons list for each model in each type of label corresponding to each type of component in each power equipment.

[0031] The process of setting the occurrence threshold is the same as that of setting the part damage rate threshold, and will not be repeated here.

[0032] At the same time, the lists of responsible persons for each type of marking corresponding to each model in each type of label of each type of component in each power equipment are compared with each other to obtain the similarity of responsible persons for marking between each model in each type of label of each type of component in each power equipment, and the models whose similarity of responsible persons for marking corresponding to each type of label of each type of component in each power equipment is greater than the set responsible person similarity threshold are taken as the marked models, and the number of marked models corresponding to each type of label of each type of component in each power equipment is counted.

[0033] Among them, the calculation method of the similarity of the marking responsible persons between each type of component in each power equipment corresponding to each model in each type of label is the same as the calculation method of the similarity of the responsible persons between each replacement of each model in each type of component in each power equipment corresponding to each type of label, which will not be repeated here.

[0034] Take the marking responsible persons whose appearance times in the marking responsible persons list for each model of each type of label corresponding to each type of component in each power equipment are greater than the appearance times threshold as the second category marking responsible persons list for each type of label corresponding to each type of component in each power equipment.

[0035] Using the purchase price of each replacement of each type of component in each power device corresponding to each model in each type of tag, the average price of each type of component in each power device corresponding to each model in each type of tag and the average price of each type of component in each power device corresponding to each type of tag are obtained.

[0036] According to the number of label replacements for each type of component in each power device corresponding to each type of label, the list of persons responsible for a type of label, and the average price, the first true characteristic value of power equipment replacement is calculated and recorded as A1.

[0037] Preferably, the calculation process of the first real characteristic value of the replacement of the power equipment is as follows: according to the number of label replacements of each type of component in each power equipment corresponding to each type of label, the list of responsible persons for a type of label and the average price, the number of label replacements of each type of component in each power equipment corresponding to each type of better quality type, the number of responsible persons for a type of label and the average price are obtained, which are respectively recorded as GF1 gxy RF1 gxy and RG1 gxy , and the number of times the marking of each type of component corresponding to the poor quality type in each power equipment is replaced, the number of people responsible for the first type of marking and the average price are recorded as GF2 gxy RF2 gxy and RG3 gxy .

[0038] According to the calculation formula:

[0039]

[0040] The first true eigenvalue A1 of the replacement of power equipment is obtained, where p, v, and z represent the number of power equipment, the number of component types, and the number of models, respectively; η1, η2, and η3 represent the set replacement number difference rate threshold, the first-class labeling responsible person number difference rate threshold, and the average price difference rate threshold, respectively.

[0041] Based on the number of marked models of each type of label corresponding to each type of component in each power device and the average price of each type of label corresponding to each type of component in each power device, the second real characteristic value of power device replacement is calculated and recorded as A2.

[0042] It should be noted that the second real characteristic value of the power equipment replacement is calculated in the same way as the first real characteristic value of the power equipment replacement, which will not be repeated here.

[0043] Using the calculation formula: Get the true characteristic value A of the power equipment replacement.

[0044] Preferably, the expression of the authenticity assessment model is: Where μ represents the authenticity evaluation result of component maintenance in power equipment, and A′ represents the set true characteristic value threshold.

[0045] The setting of the true characteristic value threshold is the same as that of the part damage rate threshold, which will not be described in detail here.

[0046] The authenticity evaluation result of the maintenance of components in the power equipment contains values ​​of 1 and 0. When the authenticity evaluation result of the maintenance of components in the power equipment is 1, it indicates that the authenticity of the maintenance of components in the power equipment is high. Conversely, when the authenticity evaluation result of the maintenance of components in the power equipment is 0, it indicates that the authenticity of the maintenance of components in the power equipment is low.

[0047] S3. When the authenticity of component maintenance in power equipment is low, the file data of each power equipment is classified using the type labels corresponding to each model of each type of component in each power equipment, and the prompt value of the file data of each power equipment is set, and the file data is sorted and displayed in descending order of the prompt value.

[0048] In a specific embodiment, the archival data of each power equipment is classified, and the specific process is as follows: the model of each type of component in the current power equipment, the list of replacement responsible persons, the maintenance responsible persons for each repair, the purchase price and the maintenance price for each repair are obtained from the archival data of each power equipment, and the type labels of each type of component corresponding to each model in each power equipment are obtained according to the type labels of each type of component in each power equipment. The list of replacement responsible persons for each type of component in the current power equipment is compared with the list of second-class marked responsible persons corresponding to the corresponding type labels, and the number of repeated responsible persons in the replacement responsible persons list and the second-class marked responsible persons list is obtained, recorded as the number of marked responsible persons, and the number of marked maintenance responsible persons for each repair is obtained in this way.

[0049] Compare the purchase price of the corresponding models of various components in each current power equipment with the average price corresponding to the corresponding type label to obtain the purchase price difference of the corresponding models of various components in each current power equipment, and in this way obtain the repair price difference of each repair.

[0050] Calculate the difference results of the archive data of each current power equipment. The difference results include data of 1 and 0. When the difference result is 1, it indicates that the false data in the archive data is small, and the archive data is classified as normal data. When the difference result is 0, it indicates that the false data in the archive data is large, and the archive data is classified as abnormal data.

[0051] In the above, the calculation process of the difference results of the archive data of the current power equipment is as follows: the number of marked maintenance personnel corresponding to each repair of each type of component in each current power equipment and the difference in maintenance price of each repair are averaged to obtain the average number of marked maintenance personnel and the average maintenance price difference. Then, the number of marked maintenance personnel, the average number of marked maintenance personnel, the purchase price difference and the average maintenance price difference corresponding to each type of component in the current power equipment are normalized, and the processed values ​​are recorded as c1, c2 and c3 respectively. gx 、c2 gx 、c3 gx and c4 gx .

[0052] Using the calculation formula: Get the difference result μ of the archive data of the current g-th power equipment g , where The difference evaluation value threshold is set.

[0053] The setting of the difference evaluation value threshold is the same as that of the part damage rate threshold, which will not be described in detail here.

[0054] Preferably, the specific process of setting the prompt value of the archive data of each power device is as follows: if the type of the archive data of a certain power device is normal data, the prompt value of the archive data of the power device is set to 0; if the type of the archive data of a certain power device is abnormal data, the difference evaluation value of the current archive data of the power device is obtained as the prompt value, and the prompt value of the archive data of each power device is set accordingly.

[0055] The embodiment of the present invention processes the historical archival data of each power equipment and classifies the quality of each model of each type of component in each power equipment, which can provide a basis for judging whether the products purchased by the purchasing person in charge are qualified and correct, and then analyzes the authenticity of the maintenance of the components in the power equipment, reduces the occurrence of false records in the archival data, ensures the authenticity of the work of the relevant responsible personnel and the authenticity of the declaration and use of funds, is conducive to achieving the transparency of the operation and maintenance of the power system, and can also effectively control the cost of the power system operation. When the authenticity is low, the archival data of each power equipment is classified and analyzed, and at the same time, it is displayed and prompted according to the priority order of the prompts, so that abnormal personnel and phenomena can be rectified in time to ensure the operational efficiency of the power system maintenance.

[0056] The above content is merely an example and explanation of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the scope of protection of the present invention.

Claims

1. A power system archive management method based on big data, characterized in that: The steps include: S1. Obtain archival data and historical archival data of each power device, and use the historical archival data of each power device to classify the models of various components in each power device, and obtain type labels corresponding to the models of various components in each power device; S2. Analyze the authenticity of component maintenance in power equipment based on the type labels corresponding to each model of each component in each power equipment and the historical archive data of each power equipment; S3. When the authenticity of component maintenance in power equipment is low, the file data of each power equipment is classified using the type labels corresponding to each model of each type of component in each power equipment, and the prompt value of the file data of each power equipment is set, and the file data is sorted and displayed in descending order of the prompt value.

2. The power system archive management method based on big data according to claim 1, characterized in that: The specific process of classifying the various types of components in various power equipment is as follows: Obtain the model, damage type, number of repairs, and usage cycle of each component in each power equipment from the historical archive data of each power equipment, and use this to calculate the damage type, number of repairs, and usage cycle of each component in each power equipment model; Damage types include parts damage and accidental damage. The number of times each component of each type of power equipment has been damaged and the number of times each component has been accidentally damaged are counted. The weighted average of the usage cycles of each component of each type of power equipment for each type of power equipment is then calculated. Based on the damage type of each component of each type of power equipment for each type of power equipment, the average usage cycle of each component of each type of power equipment for each type of power equipment is obtained. The damage levels of various components in various power equipment corresponding to various models are calculated using the number of times parts are damaged in use, the number of times parts are damaged accidentally, the number of times parts are repaired, and the average service life of parts damage. The damage levels include level 1 and level -1. When the damage level is level 1, the type label is a good quality type. When the damage level is level -1, the type label is a poor quality type.

3. The power system archive management method based on big data according to claim 2, characterized in that: The calculation process of the damage level of each type of component in each power equipment corresponding to each model is as follows: The number of times parts are damaged, the number of times accidental damage occurs, the number of times repairs are performed, and the average service life of parts damaged for each type of component in each power equipment is recorded as KN. gxy , YK gxy 、WK gxy and TK gxy , where g represents the number of each power device, x represents the number of each component, and y represents the number of each model. g, x, and y are all positive integers; Using the calculation formula: Get the damage level δ of the xth type component corresponding to the yth model in the gth power equipment gxy , where e represents a natural constant, κ represents the set part damage rate threshold, δ is the set part damage characteristic value threshold, YK and TK are the set maintenance times threshold and usage cycle threshold, respectively.

4. The power system archive management method based on big data according to claim 1, characterized in that: The specific process of analyzing the authenticity of component maintenance in power equipment is as follows: Obtain the model number, replacement responsible personnel list, maintenance responsible personnel, purchase price and maintenance price corresponding to each replacement of each type of component in each power equipment from the historical archive data of each power equipment, and obtain the list of responsible personnel, maintenance responsible personnel, purchase price and maintenance price corresponding to each type of replacement of each type of component in each power equipment according to the type label corresponding to each model of each type of component in each power equipment; Using the list of responsible personnel, maintenance personnel, purchase price, and maintenance price for each type of component in each type of label corresponding to each model in each power equipment, the true characteristic value of power equipment replacement and the true characteristic value of power equipment maintenance are calculated. These are then substituted into the authenticity assessment model to output the authenticity assessment results of the maintenance of components in the power equipment. The authenticity evaluation result of the maintenance of components in the power equipment contains values ​​of 1 and 0. When the authenticity evaluation result of the maintenance of components in the power equipment is 1, it indicates that the authenticity of the maintenance of components in the power equipment is high. Conversely, when the authenticity evaluation result of the maintenance of components in the power equipment is 0, it indicates that the authenticity of the maintenance of components in the power equipment is low.

5. The power system archive management method based on big data according to claim 4 is characterized in that: The calculation process of the real characteristic value of the power equipment replacement is as follows: Compare the lists of responsible persons for each replacement of each type of component in each power device corresponding to each model in each type of label to obtain the similarity of responsible persons between each replacement of each type of component in each power device corresponding to each model in each type of label. Record each replacement of each type of component in each power device corresponding to each model in each type of label with a similarity greater than a set similarity threshold of responsible persons as each label replacement. Count the number of label replacements of each type of component in each power device corresponding to each model in each type of label. Take the responsible persons whose appearance times in the list of responsible persons for each model of each type of label corresponding to each type of component in each power equipment are greater than the appearance number threshold as the list of responsible persons for each type of label corresponding to each model of each type of component in each power equipment; At the same time, the lists of responsible persons for each type of marking corresponding to each model of each type of label of each type of component in each power device are compared with each other to obtain the similarity of responsible persons for marking between each model of each type of label corresponding to each type of component in each power device, and each model whose similarity of responsible persons for marking corresponding to each type of label of each type of component in each power device is greater than the set responsible person similarity threshold is taken as each marked model, and the number of marked models corresponding to each type of label of each type of component in each power device is counted; Take the marking responsible persons whose appearance times in the list of marking responsible persons for each model of each type of label corresponding to each type of component in each power equipment is greater than the appearance number threshold as the second-category marking responsible persons list for each type of label corresponding to each type of component in each power equipment; Using the purchase price of each replacement of each type of component in each power device corresponding to each model in each type of tag, obtain the average price of each type of component in each power device corresponding to each model in each type of tag and the average price of each type of component in each power device corresponding to each type of tag; Calculate the first true characteristic value of power equipment replacement based on the number of label changes for each type of component in each power equipment, the list of people responsible for each type of label, and the average price, and record it as A1; Based on the number of labeled models of each type of label corresponding to each type of component in each power device and the average price of each type of label corresponding to each type of component in each power device, calculate the second true characteristic value of power device replacement, denoted as A2; Using the calculation formula: Get the true characteristic value A of the power equipment replacement.

6. The power system archive management method based on big data according to claim 5, characterized in that: The calculation process of the first real characteristic value of the power equipment replacement is: According to the number of label replacements for each type of component in each power equipment, the list of responsible personnel for a type of label and the average price, the number of label replacements for each type of component in each power equipment, the number of responsible personnel for a type of label and the average price of each type of component with better quality in each power equipment are obtained, which are recorded as GF1 gxy RF1 gxy and RG1 gxy , and the number of times the marking of each type of component corresponding to the poor quality type in each power equipment is replaced, the number of people responsible for the first type of marking and the average price are recorded as GF2 gxy RF2 gxy and RG3 gxy ; According to the calculation formula: The first true eigenvalue A1 of the replacement of power equipment is obtained, where p, v, and z represent the number of power equipment, the number of component types, and the number of models, respectively; η1, η2, and η3 represent the set replacement number difference rate threshold, the first-class labeling responsible person number difference rate threshold, and the average price difference rate threshold, respectively.

7. The method for managing power system archives based on big data according to claim 6, characterized in that: The process for setting the replacement count difference rate threshold, the first-class tag number of responsible personnel difference rate threshold, and the average price difference rate threshold is as follows: From the number of label changes, the number of personnel responsible for a type of label, and the average price of each type of component with better quality in each power equipment, the maximum number of label changes, the minimum number of personnel responsible for a type of label, the minimum number of personnel responsible for a type of label, the maximum average price, and the minimum average price are selected and recorded as GF max GF min , RF max , RF min RG max and RG min ; Replacement times difference rate threshold: The difference rate threshold of the number of persons responsible for a category of marking is: Average price difference rate threshold:

8. The power system archive management method based on big data according to claim 6, characterized in that: The specific process of classifying the archive data of each power equipment is as follows: Obtain the model of each component in the current power equipment, the list of replacement responsible personnel, the maintenance responsible personnel for each repair, the purchase price and the maintenance price for each repair from the archival data of each power equipment, and obtain the type label of the corresponding model of each component in the current power equipment according to the type label of each model of each component in the power equipment, and compare the list of replacement responsible personnel for each model of each component in the current power equipment with the list of second-class marked responsible personnel corresponding to the corresponding type label, obtain the number of repeated responsible personnel in the replacement responsible personnel list and the second-class marked responsible personnel list, record it as the number of marked responsible personnel, and obtain the number of marked maintenance responsible personnel for each repair in this way; Compare the current purchase price of each component model in each power device with the average price corresponding to the corresponding type label to obtain the current purchase price difference of each component model in each power device, and in this way obtain the maintenance price difference of each repair; Calculate the difference results of the archive data of each current power equipment. The difference results include data of 1 and 0. When the difference result is 1, it indicates that the false data in the archive data is small, and the archive data is classified as normal data. When the difference result is 0, it indicates that the false data in the archive data is large, and the archive data is classified as abnormal data.

9. The power system archive management method based on big data according to claim 8, characterized in that: The calculation process of the difference results of the archive data of the current power equipment is as follows: The number of marked maintenance personnel and the difference in maintenance prices for each component in each power equipment are averaged to obtain the average number of marked maintenance personnel and the average maintenance price difference. Then, the number of marked maintenance personnel, the average number of marked maintenance personnel, the purchase price difference and the average maintenance price difference corresponding to each component in each power equipment are normalized and the processed values ​​are recorded as c1. gx 、c2 gx 、c3 gx and c4 gx ; Using the calculation formula: Get the difference result μ of the archive data of the current g-th power equipment g , where The difference evaluation value threshold is set.

10. The power system archive management method based on big data according to claim 8, characterized in that: The specific process of setting the prompt value of the archive data of each power device is as follows: If the type of the archive data of a certain power equipment is normal data, the prompt value of the archive data of the power equipment is set to 0. If the type of the archive data of a certain power equipment is abnormal data, the difference evaluation value of the current archive data of the power equipment is obtained as the prompt value, and the prompt value of the archive data of each power equipment is set accordingly.

Images