State feature database construction method for monitoring operation of hydroelectric generating set

Abstract

The invention relates to the technical field of database construction, in particular to a state feature database construction method for hydroelectric generating set operation monitoring, and the method comprises the steps: obtaining each type of operation monitoring data at all moments in each operation process of a hydroelectric generating set, state characteristics and working condition characteristics of the operation monitoring data of each type in each operation process are determined; analyzing the similarity between the two types of operation monitoring data in each operation process, and determining the relevance between the two types of operation monitoring data; and classifying all types of operation monitoring data based on relevance, constructing a storage priority of each data time sequence of each type, performing block storage, and obtaining a state feature database of hydroelectric generating set operation monitoring. The invention aims to optimize and store the operation monitoring data of the hydroelectric generating set, so that the data retrieval precision and efficiency are improved while the data storage efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of database construction technology, specifically to a method for constructing a status feature database for monitoring the operation of hydropower units. Background Technology

[0002] With the continuous advancement of industrialization, electricity demand is growing rapidly. The large-scale deployment of renewable energy sources such as photovoltaics and wind power has made the need for flexible and efficient energy forms in the power system increasingly urgent. Especially in load regulation, the power system urgently needs to achieve effective peak shaving and valley filling operations. Against this backdrop, hydropower stations, as engineering facilities with load regulation capabilities, have become an indispensable regulating tool in the power system. As the core energy conversion equipment in the hydropower energy system, the stable and safe operation of hydropower units is crucial. Faults or abnormal operations can not only affect power generation efficiency but also damage equipment and even trigger more serious accidents. Therefore, ensuring the normal operation of hydropower units is of paramount importance to the safe, stable, and efficient operation of the power system.

[0003] Typically, databases are established to quantitatively assess the status of key components and overall equipment in hydropower units, and to support fault diagnosis. Traditional databases often employ fixed storage methods, unable to dynamically adjust based on the real-time value of the data. This means that even if some data is not important at a particular moment, it will still occupy storage space, resulting in a large amount of redundant storage. This inefficient storage leads to a rapid expansion of the database capacity, reduces data access efficiency, and affects the overall responsiveness of the system. Summary of the Invention

[0004] In view of the above, it is necessary to provide a method for constructing a status characteristic database for monitoring the operation of hydropower units to solve the above problems.

[0005] One embodiment of this application provides a method for constructing a status feature database for monitoring the operation of hydropower units, the method comprising: Acquire operational monitoring data for each type of hydropower unit at all times during each operation, and assemble a time series sequence for each type of data. Analyze the distribution characteristics of elements in each data time series of each type and the distance characteristics between elements with the same value to determine the state characteristics of each data time series of each type; analyze the similarity characteristics between each data time series of each type and the remaining data time series, and combine the differences between the state characteristics to determine the operating condition characteristics of each data time series of each type. Based on the similarity between any two types of operation monitoring data during each operation, and combined with the distribution of the operating condition characteristics, the correlation between the two types of operation monitoring data is determined; based on the correlation, all types of operation monitoring data are classified to obtain several correlation categories; Based on the correlation between each type of operational monitoring data and the other types in each associated category, and the operating condition characteristics of each data time series of each type, the storage priority of each data time series of each type is constructed and stored in blocks to obtain a database of the status characteristics of hydropower unit operation monitoring.

[0006] Preferably, determining the state characteristics of each data time series sequence of each type specifically involves: For each data time series of each type, calculate the minimum time interval between elements with the same value as each element, which is taken as the minimum time distance of each element. Calculate the sum of the minimum time distances obtained by all elements, and positively fuse the sum with the element disorder degree of each data time series to obtain the state characteristics of each data time series of each type.

[0007] Preferably, the specific process for determining the operating condition characteristics of each data time series of each type is as follows: Analyze the distance characteristics between the data time series sequences of two runs of the same type, and combine the differences in the state characteristics to determine the approximation between the data time series sequences of the two runs; For each data time series of each type, the percentage of the maximum approximation among all approximations other than the maximum approximation is obtained, which is used as the operating condition characteristic of each data time series of each type.

[0008] Preferably, the approximation between the data time-series sequences of the two running processes is specifically as follows: For the same type, the distance metric and state characteristic difference between any two data time series are positively fused, and the negative correlation mapping result of the positive fusion is used as the approximation between the two data time series.

[0009] Preferably, determining the correlation between any two types of operational monitoring data specifically involves: Obtain the common access frequency and maximum access frequency of any two types of operation monitoring data across all runs; calculate the ratio between the common access frequency and the maximum access frequency. Obtain the similarity between the time-series data obtained from each run of any two types of operational monitoring data; calculate the average value of the operating condition characteristics of the time-series data obtained from each run of any two types of operational monitoring data; The product of the similarity level and the average value for each run is obtained. The products obtained from all runs are accumulated and multiplied by the ratio to obtain the correlation between the two types of operation monitoring data.

[0010] Preferably, the specific process for obtaining several related categories is as follows: Randomly select one type of operational monitoring data. All other types of operational monitoring data whose correlation with the selected type of operational monitoring data is greater than a preset threshold are considered as a correlation category. Continue to randomly select the remaining types of monitoring data and repeat this process to obtain all correlation categories.

[0011] Preferably, the specific process for obtaining several related categories is as follows: Randomly select one type of operation monitoring data, and group all other types of operation monitoring data whose correlation with the selected type of operation monitoring data is greater than a preset threshold into one correlation category, and the correlation between any two types of operation monitoring data in a correlation category is greater than the preset threshold; continue to randomly select the remaining types of monitoring data and repeat this process to obtain all correlation categories.

[0012] Preferably, the preset threshold is the average value of the correlation between any two types of operational monitoring data.

[0013] Preferably, the specific process for constructing the storage priority of each data time-series sequence of each type is as follows: For each type of operational monitoring data, calculate the cumulative sum of the correlations between each type and all other types of operational monitoring data in its associated category. Then, perform a positive fusion with the operating condition characteristics of each data time series of each type to obtain the storage priority of each data time series of each type.

[0014] Preferably, the block storage is specifically performed by using the storage priority of each data time sequence of each type as the encoding priority and employing an encoding algorithm for block storage.

[0015] This application has at least the following beneficial effects: This application constructs a state characteristic database for hydropower unit operation monitoring, significantly optimizing the storage and retrieval performance of hydropower unit operation monitoring data. Specifically, it dynamically quantifies data value based on state and operating condition characteristics. By dynamically evaluating the value of each data point through state and operating condition characteristics, it prioritizes storing data with high information content, thus avoiding useless data occupying storage resources. This method helps identify and retain key data, reduces redundant storage, and improves storage space utilization efficiency. Operating condition characteristics help capture key data of abnormal operating conditions, which can help promptly identify potential risks of equipment failure. By monitoring and analyzing these operating condition characteristics, earlier fault warnings and state assessments can be performed. Furthermore, by constructing a storage priority system through a correlation-based block strategy, data can be stored in blocks, improving storage efficiency and security while reducing unnecessary redundant operations during data retrieval. Storage priority ensures that highly correlated and highly characteristic data can be quickly retrieved, reducing retrieval time. Clustering and storing strongly correlated data in blocks ensures rapid retrieval of related data. This strategy effectively reduces cross-slice operations during queries, improves data access speed and efficiency, especially when processing large amounts of data, it can reduce query latency and improve response speed; ultimately, it realizes the construction of a status feature database for hydropower unit operation monitoring, optimizes data storage and retrieval performance, and improves data storage capacity, retrieval efficiency and the accuracy of status assessment. Attached Figure Description

[0016] Figure 1 A flowchart illustrating the method for constructing a status characteristic database for monitoring the operation of hydropower units provided in this application; Figure 2 A flowchart for obtaining storage priority provided in this application. Detailed Implementation

[0017] In the description of the embodiments in this application, the words "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary," "or," and "for example" is intended to present the relevant concepts in a specific manner.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0019] It should also be noted that the terms "first" and "second" in this application and its accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the method. Without departing from the scope of protection of this application, the execution order of multiple steps can be interchanged, and some steps can also be deleted.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0021] This application proposes a method for constructing a state characteristic database for monitoring the operation of hydropower units, which is applied in the field of database construction technology. (See attached document.) Figure 1 The method includes the following steps: S1: Acquire the operational monitoring data of each type at all times during each operation of the hydropower unit, and assemble the time sequence of each data for each type.

[0022] This application acquires data related to the operation of hydropower units through sensor monitoring networks, hydropower plant monitoring systems, and externally accessed hydrological and meteorological data. This includes unit operating data such as bearing temperature, unit speed, axial displacement, lubricating oil pressure, lubricating oil level, bearing runout, and frame vibration; electrical operating data such as stator / rotor current, voltage, power, power factor, frequency, partial discharge (PD), generator air gap monitoring, and stator winding temperature distribution; hydraulic system data such as head (static head and dynamic head), flow rate, spiral casing pressure, tailrace pressure pulsation, guide vane opening, and blade angle; and environmental and operating condition data such as reservoir water level, downstream water level, water temperature, and sediment content.

[0023] The operational monitoring data collected during each operation of the hydropower unit is stored to form the original database for hydropower unit operation monitoring. Simultaneously, access logs of this original database are obtained so that, during fault and status analysis of the hydropower unit, the overall status of the equipment can be determined and faults diagnosed by comparing the operational monitoring data with the database.

[0024] S2: Analyze the distribution characteristics of elements in each data time series of each type and the distance characteristics between elements with the same value to determine the state characteristics of each data time series of each type; analyze the similarity characteristics between each data time series of each type and the remaining data time series, and combine the differences between the state characteristics to determine the operating condition characteristics of each data time series of each type.

[0025] When constructing a condition characteristic database for hydropower units, the original database faces core challenges such as data explosion, read / write performance bottlenecks, uneven value density, difficulties in managing multi-source heterogeneous systems, and a lack of lifecycle information. These issues result in low efficiency and accuracy in providing decision support for fault diagnosis and condition-based maintenance of hydropower units. Therefore, this application further analyzes the operational monitoring data of hydropower units, extracts the unit characteristic data, optimizes the data storage of the original database, completes the construction of the condition characteristic database, improves the accuracy and efficiency of data retrieval, and assists in the overall condition assessment and fault diagnosis of the equipment.

[0026] The operational monitoring data of each type at all times during each operation of the hydropower unit are combined into a time series sequence for each type of data. For example, the bearing runout data collected at all times during each operation of the hydropower unit are combined into a time series sequence for the bearing runout.

[0027] First, the state characteristics of the data are reflected by the repetition of each data time series of each type. Specifically: for each data time series of each type, the minimum time interval between elements with the same value is calculated as the minimum time distance of each element. The sum of the minimum time distances of all elements is calculated, and this sum is positively integrated with the disorder of elements in each data time series to obtain the state characteristics of each data time series of each type. It should be noted that if there is no other element with the same value in the data time series, the minimum time interval between the elements with the closest value is taken as the minimum time interval of that element.

[0028] In this embodiment, the state characteristics of each data time series sequence of each type are denoted as: Its formula is as follows: In the formula: Y represents the number of elements in each data time series of each type; Information entropy represents the information entropy of each data time series of each type. It is used to measure the degree of disorder of the sequence elements. The higher the information entropy, the higher the uncertainty of the distribution of data values ​​in the data time series, the more information it contains, and the greater the state characteristics. This represents the minimum time distance between the i-th element and elements with the same data value. As an example, the obtained time series data is... , among which, element The minimum time distance is the element with index 1 in the sequence. With the element with index 3 The larger the sum of the minimum time intervals, the less likely the data will repeat, the less repetitive it is, and the more information it contains.

[0029] It should be understood that the larger the cumulative sum of the minimum time intervals, the higher the repetition between data points, and the more concentrated the distribution of data points with the same value. This indicates that the data variation is small, the amount of information is small, and the state characteristic value is also low. In this case, the data is more eliminable, meaning that the data storage priority in this time series is low. Conversely, the greater the state characteristic, the lower the repetition of data points, the more key information about the equipment's operating conditions it contains, the larger the amount of information, the less eliminable the data, and the higher the storage priority should be.

[0030] Furthermore, the data change characteristics between each data time series of each type and the remaining data time series are analyzed to obtain the operating condition characteristics of each type of data time series. This is used to identify the operating condition data that occurs when the hydropower unit equipment experiences a fault or abnormal operation. Specifically: for the same type, the distance metric and state characteristic difference between any two data time series are positively fused, and the negative correlation mapping result of the positive fusion is used as the approximation between the two data time series. For each data time series of each type, the proportion of the maximum approximation among all approximations other than the maximum approximation is obtained as the operating condition characteristics of each data time series of each type.

[0031] In this embodiment, the approximation between data time series sequence A and data time series sequence B of the same type is denoted as . Its formula is as follows: ;In the formula, , Represent the state characteristics of each type of data time series sequence A and data time series sequence B, respectively. It represents the state characteristic difference between data time series A and data time series B, and represents the difference in the amount of information contained in the two data time series. The larger the value, the smaller the approximation. Represents the DTW distance function; This indicates a preset parameter greater than zero to prevent the denominator from being 0. In this embodiment, the value is 0.001, but implementers can adjust it according to the actual situation.

[0032] Let the operating condition characteristics of each type of data time series A be denoted as... Its formula is as follows: ;In the formula: This represents the maximum approximation of a time series sequence A within the same type. This indicates the approximation between data time series sequence A and the nth data time series sequence of the same type, excluding the data time series sequence corresponding to the maximum approximation. This indicates the number of all time-series data for each type.

[0033] It should be understood that the greater the characteristic of the operating condition, the more the data time series conforms to the characteristics of the characteristic operating condition, exhibiting both randomness and regularity. Randomness refers to situations that rarely occur in the historical operation of hydropower units, while regularity refers to the fact that the information contained in the same type of data time series is relatively similar in different operating processes, possibly manifesting as typical characteristics when a certain equipment failure occurs. Therefore, the greater the characteristic of the operating condition, the higher the probability that the data time series contains data related to the characteristic operating condition; conversely, the smaller the characteristic of the operating condition, the lower the probability that the data time series contains data related to the characteristic operating condition.

[0034] S3: Based on the similarity between any two types of operation monitoring data during each operation, and combined with the distribution of the operating condition characteristics, determine the correlation between the two types of operation monitoring data; classify all types of operation monitoring data based on the correlation to obtain several correlation categories.

[0035] While storing data solely based on operational condition characteristics can effectively improve data storage efficiency and security under specific conditions, this approach ignores the correlations between changes in data within the same operational condition. This can lead to low efficiency when retrieving data from the database. Therefore, this application constructs correlations between different types of operational monitoring data to improve retrieval efficiency.

[0036] During the monitoring of hydropower unit operation, changes in different types of operational monitoring data often exhibit certain correlations. For example, when the head decreases, maintaining the same power requires increasing the guide vane opening, which can trigger vortex band vibration in the draft tube and increase the harmonic components of the stator current. Based on this, this application constructs the correlation between any two types of operational monitoring data by examining the changes in different types of operational monitoring data in the original database and the access patterns of different types of data.

[0037] Specifically, the common access frequency and maximum access frequency of any two types of operational monitoring data across all runs are obtained; the ratio between the common access frequency and the maximum access frequency is calculated; the similarity between the time-series data sequences obtained from each run for any two types of operational monitoring data is obtained; the average value of the operational characteristic of the time-series data sequences obtained from each run for any two types of operational monitoring data is calculated; the product of the similarity and the average value for each run is obtained, the products obtained from all runs are accumulated, and then multiplied by the ratio to obtain the correlation between the two types of operational monitoring data. In this embodiment, the similarity between sequences is calculated using the Pearson correlation coefficient.

[0038] It should be understood that the greater the product of the similarity of each run and the average value, the stronger the correlation between the changes of the two types of data under the same characteristic operating conditions. The higher the correlation between the two types of operational monitoring data, the more likely an anomaly will occur during hydropower unit equipment condition assessment or fault diagnosis. Because of the strong correlation between the two types of data, if one type of data fails, the other type of data will often also fail. Therefore, it is more necessary to store and reference these two types of data as a single category, thereby helping to improve the accuracy and efficiency of hydropower unit condition assessment and fault diagnosis.

[0039] By identifying the correlations between different types of operational monitoring data, and adaptively clustering these data based on these correlations, the collected operational monitoring data of different types are divided into different correlation categories. This allows for the storage of operational monitoring data of different correlation categories in a database block format. Specifically, data of the same correlation category are stored on the same server, while data of different correlation categories are stored on different servers. This reduces the probability of cross-segment queries when subsequently assessing the equipment status or diagnosing faults of hydropower units based on the database, thereby improving the efficiency and accuracy of database queries and writes.

[0040] After normalizing all the obtained correlations, statistical analysis is performed to obtain the correlation dataset. The average value of all data in the correlation dataset is used as the preset threshold. The method for obtaining the preset threshold can be adjusted by the implementer.

[0041] In this embodiment, a type of operation monitoring data is randomly selected. Taking the Qth type of operation monitoring data as an example, the correlation between the Qth type of operation monitoring data and the other types of operation monitoring data is obtained. If the correlation is greater than or equal to a preset threshold, it is determined that the Qth type of operation monitoring data is highly correlated with the data of that category and can be regarded as the same related category. Otherwise, they are not the same related data. The above steps are repeated until the number of data types in the related category to which the Qth type of operation monitoring data belongs does not change. Then, the above steps are repeated by randomly selecting unclassified data types until the number of data types in all related categories does not change.

[0042] As an example, there are , , , , There are 5 types of operational monitoring data. You can choose any one type, for example... , obtain The correlation with the other four types of operational monitoring data; if the correlation is greater than a preset threshold, then... If they belong to the same related category, and If they belong to the same category, then they become , , , Then, choose any of the remaining categories, for example, select... , obtain The correlation with the other two types of operational monitoring data; if the correlation is greater than a preset threshold, then... If they belong to the same category, they are not in the same category. Repeat this process until all categories of data no longer change.

[0043] In another embodiment, when obtaining the associated category, it is also necessary to satisfy the condition that the correlation between any two types of operation monitoring data in the same associated category is greater than a preset threshold.

[0044] It should be noted that if there are still discrete operational monitoring data of a certain type at this time, the average correlation between the operational monitoring data of that type and all types of data in each related category is obtained, and the related category with the largest average correlation is selected as the category to which the operational monitoring data of that type belongs.

[0045] S4: Based on the correlation between each type of operational monitoring data and the other types in each associated category, and the operating condition characteristics of each data time series of each type, construct the storage priority of each data time series of each type and perform block storage to obtain the status characteristic database of hydropower unit operation monitoring.

[0046] The above steps adaptively divide different types of operational monitoring data from hydropower units into multiple related categories. Each related category is stored in a different block in the database, completing the block storage of the database. This improves data storage efficiency and security while also enhancing data retrieval efficiency and accuracy.

[0047] In this application, the storage priority of each data time series is constructed based on the correlation between each type of operational monitoring data and the other types of operational monitoring data in each associated category, as well as the operating condition characteristics of each data time series of operational monitoring data. The formula is as follows: In the formula: F represents the storage priority of each data time series of each type; Z represents the operating condition characteristics of each data time series of each type; S represents the number of data types in the associated category to which each data time series of each type belongs; This indicates the correlation between the operational monitoring data of the time series type and the operational monitoring data of the s-th type in the associated category.

[0048] The flowchart for obtaining storage priority is as follows: Figure 2 As shown.

[0049] It should be understood that a higher storage priority indicates that the data time series is more likely to contain characteristic information of the operating conditions of the hydropower unit, while a lower storage priority indicates that the data time series is less likely to contain characteristic information of the operating conditions.

[0050] The storage priority of each time series of data in each type of operation monitoring data is obtained, and the storage priority is used as the encoding priority in Huffman coding to complete the block storage of the database. Huffman coding technology is a well-known method and will not be described in detail here. The above steps are repeated until each type of operation monitoring data is stored. The block optimization storage of the original database of hydropower unit operation monitoring is completed, and the state feature database of hydropower unit operation monitoring is obtained.

[0051] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0052] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for constructing a state characteristic database for monitoring the operation of hydropower units, characterized in that, The method includes the following steps: Acquire operational monitoring data for each type of hydropower unit at all times during each operation, and assemble a time series sequence for each type of data. Analyze the distribution characteristics of elements in each data time series of each type and the distance characteristics between elements with the same value to determine the state characteristics of each data time series of each type; analyze the similarity characteristics between each data time series of each type and the remaining data time series, and combine the differences between the state characteristics to determine the operating condition characteristics of each data time series of each type. Based on the similarity between any two types of operation monitoring data during each operation, and combined with the distribution of the operating condition characteristics, the correlation between the two types of operation monitoring data is determined; based on the correlation, all types of operation monitoring data are classified to obtain several correlation categories; Based on the correlation between each type of operational monitoring data and the other types in each associated category, and the operating condition characteristics of each data time series of each type, the storage priority of each data time series of each type is constructed and stored in blocks to obtain a database of the status characteristics of hydropower unit operation monitoring.

2. The method for constructing a status feature database for monitoring the operation of hydropower units as described in claim 1, characterized in that, The determination of the state characteristics of each data time series sequence of each type specifically involves: For each data time series of each type, calculate the minimum time interval between elements with the same value as each element, which is taken as the minimum time distance of each element. Calculate the sum of the minimum time distances obtained by all elements, and positively fuse the sum with the element disorder degree of each data time series to obtain the state characteristics of each data time series of each type.

3. The method for constructing a status feature database for monitoring the operation of hydropower units as described in claim 1, characterized in that, The specific process for determining the operating condition characteristics of each data time series of each type is as follows: Analyze the distance characteristics between the data time series sequences of two runs of the same type, and combine the differences in the state characteristics to determine the approximation between the data time series sequences of the two runs; For each data time series of each type, the percentage of the maximum approximation among all approximations other than the maximum approximation is obtained, which is used as the operating condition characteristic of each data time series of each type.

4. The method for constructing a status feature database for monitoring the operation of hydropower units as described in claim 3, characterized in that, The approximation between the data time-series sequences of the two runs is specifically as follows: For the same type, the distance metric and state characteristic difference between any two data time series are positively fused, and the negative correlation mapping result of the positive fusion is used as the approximation between the two data time series.

5. The method for constructing a status feature database for monitoring the operation of hydropower units as described in claim 1, characterized in that, The determination of the correlation between any two types of operational monitoring data specifically involves: Obtain the common access frequency and maximum access frequency of any two types of operation monitoring data across all runs; calculate the ratio between the common access frequency and the maximum access frequency. Obtain the similarity between the time-series data obtained from each run for any two types of operational monitoring data; Calculate the average value of the operating condition characteristics of the time series data obtained in each run for any two types of operation monitoring data; The product of the similarity level and the average value for each run is obtained. The products obtained from all runs are accumulated and multiplied by the ratio to obtain the correlation between the two types of operation monitoring data.

6. The method for constructing a status feature database for monitoring the operation of hydropower units as described in claim 1, characterized in that, The specific process for obtaining several related categories is as follows: Randomly select one type of operational monitoring data. All other types of operational monitoring data whose correlation with the selected type of operational monitoring data is greater than a preset threshold are considered as a correlation category. Continue to randomly select the remaining types of monitoring data and repeat this process to obtain all correlation categories.

7. The method for constructing a status feature database for monitoring the operation of hydropower units as described in claim 1, characterized in that, The specific process of obtaining several related categories is as follows: Randomly select one type of operation monitoring data, and take all other types of operation monitoring data whose correlation with the selected type of operation monitoring data is greater than a preset threshold as an association category, and the correlation between any two types of operation monitoring data in an association category is greater than a preset threshold; Continue to randomly select the remaining types of monitoring data and repeat this process to obtain all associated categories.

8. The method for constructing a status feature database for monitoring the operation of hydropower units as described in claim 7, characterized in that, The preset threshold is specifically the average value of the correlation between any two types of operational monitoring data.

9. The method for constructing a status feature database for monitoring the operation of hydropower units as described in claim 1, characterized in that, The specific process for constructing the storage priority of each data time series for each type is as follows: For each type of operational monitoring data, calculate the cumulative sum of the correlations between each type and all other types of operational monitoring data in its associated category. Then, perform a positive fusion with the operating condition characteristics of each data time series of each type to obtain the storage priority of each data time series of each type.

10. The method for constructing a status feature database for monitoring the operation of hydropower units as described in claim 1, characterized in that, The block storage is specifically performed by using the storage priority of each data time sequence of each type as the encoding priority and employing an encoding algorithm for block storage.

Images