A method, device and storage medium for constructing a data asset package of a hydropower unit

Abstract

This invention discloses a method, apparatus, and storage medium for constructing a data asset package for hydropower units. The method includes: classifying measuring points according to their business uses, and aggregating the measuring points of each category to form a business dataset of a specific category; configuring the processing strategy of the dataset and outputting a time-stamp table of the data; filtering the original business dataset based on the time-stamp table to form a preliminary dataset; improving the attribute information of the dataset and de-sensitizing the attribute information to form a final dataset that can be independently shared and used.

Description

Technical Field

[0001] This invention relates to hydropower equipment technology, and more particularly to a method, apparatus and storage medium for constructing a data asset package for a hydropower unit. Background Technology

[0002] Currently, most methods for data asset management on the market focus on data asset catalogs, metadata management, and data models, with very few descriptions of how datasets are formed and constructed, especially regarding how industrial time-series data are formed into data assets.

[0003] However, power companies possess massive amounts of equipment operation sequence data. This raw data often presents challenges for business personnel in intuitively and quickly understanding its source, data flow, and the relationship between the data and business operations. They struggle to quickly find, understand, and utilize the data. Therefore, it is necessary to construct business-meaning datasets tailored to business personnel and provide corresponding data services. Summary of the Invention

[0004] This invention provides a method, apparatus, and storage medium for constructing a data asset package for hydropower units.

[0005] Firstly, a method for constructing a data asset package for hydropower units, the method comprising:

[0006] The measurement points are classified using a deep neural network model, and the measurement points of each category are aggregated to form a business dataset for a specific category.

[0007] Configure the dataset processing strategy and output a time-stamped table of the data;

[0008] The original business dataset is filtered based on the time-stamped table to form a preliminary dataset;

[0009] Improve the attribute information of the dataset and perform anonymization processing on the attribute information to form a final dataset that can be independently shared and used.

[0010] Furthermore, the deep neural network employs a convolutional neural network or a long short-term memory network.

[0011] Furthermore, the configuration of the dataset processing strategy and the output data time-stamp table include:

[0012] If at a certain point in time If the difference between the maximum and minimum power values ​​of the generating unit within a set time window is less than a set fluctuation range, then that time point is considered a steady-state time point. The time window is defined as follows: Pushing back to the time point The time range of seconds, that is Maximum power value and minimum power value Specifically:

[0013] ;

[0014] ;

[0015] ;

[0016] in, To set a threshold for power fluctuation amplitude.

[0017] Accumulate steady-state time points into time intervals. When a time interval is longer than the shortest running time, the time interval is considered to be in steady state.

[0018] When performing steady-state calculations, power data below the steady-state minimum threshold are discarded;

[0019] When the interval between two steady-state time periods is less than the set time interval threshold, the two time periods are merged.

[0020] Furthermore, the process of aggregating the measurement points of each category to form a business dataset for a specific category includes:

[0021] The vibration and swing data of the upper guide, lower guide, water guide, upper frame, stator frame, lower frame, and top cover are used to form a vibration and swing business dataset.

[0022] Furthermore, the improved dataset's attribute information includes: the improved dataset's name, description, and category.

[0023] Furthermore, the set time window is as follows: Seconds: A time range that is several seconds prior to a given point in time.

[0024] Secondly, the present invention provides a device for constructing a data asset package for hydropower units, the device comprising:

[0025] The dataset acquisition module is used for:

[0026] The measurement points are classified according to their business purpose, and the measurement points of each category are aggregated to form a specific category of business dataset;

[0027] The module for obtaining time stamp tables is used for:

[0028] Configure the dataset processing strategy and output a time-stamped table of the data;

[0029] The data asset package formation module is used for:

[0030] The original business dataset is filtered based on the time-stamped table to form a preliminary dataset;

[0031] Improve the attribute information of the dataset and perform anonymization processing on the attribute information to form a final dataset that can be independently shared and used.

[0032] Furthermore, the module for obtaining the time stamp table includes:

[0033] The configuration processing submodule is used for:

[0034] If at a certain point in time, the difference between the maximum power value and the minimum power value of the unit within the set time window is less than the set fluctuation range, then the point in time is determined to be a steady-state point.

[0035] Accumulate steady-state time points into time intervals. When a time interval is longer than the shortest running time, the time interval is considered to be in steady state.

[0036] When performing steady-state calculations, power data below the steady-state minimum threshold are discarded;

[0037] When the interval between two steady-state time periods is less than the set time interval threshold, the two time periods are merged.

[0038] Further, the device includes:

[0039] The dataset attributes module is used to: improve the name, description, and category of the dataset.

[0040] Thirdly, the present invention provides a device for constructing a data asset package for hydropower units, the device comprising:

[0041] Memory, used to store programs;

[0042] A processor is configured to execute a program stored in the memory, and when the program stored in the memory is executed, the processor is configured to perform the above-described method.

[0043] Fourthly, the present invention provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause one or more processors to perform the above-described method.

[0044] Compared with the prior art, the present invention has the following advantages:

[0045] Overcoming the shortcomings of existing technologies, a targeted solution is proposed for constructing time-series data assets for hydropower turbine generator units, which are unique to the hydropower industry. A data asset package is constructed by combining the business characteristics of hydropower, the characteristics of data steady-state, and data anonymization mechanisms. The resulting data asset package can be independently shared for data analysis and model training of similar units within the industry. Attached Figure Description

[0046] Figure 1This is a schematic diagram of a method for constructing a data asset package for hydropower units, provided by an embodiment of the present invention.

[0047] Figure 2 This is a schematic diagram of a device for constructing a data asset package for a hydropower unit, provided in an embodiment of the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0049] Figure 1 This is a schematic diagram of a method for constructing a data asset package for hydropower units according to an embodiment of the present invention. The method includes:

[0050] The measurement points are classified using a deep neural network model, and the measurement points of each category are aggregated to form a business dataset for a specific category.

[0051] Configure the dataset processing strategy and output a time-stamped table of the data;

[0052] The original business dataset is filtered based on the time-stamped table to form a preliminary dataset;

[0053] Improve the attribute information of the dataset and perform anonymization processing on the attribute information to form a final dataset that can be independently shared and used.

[0054] In one embodiment, the deep neural network employs a convolutional neural network or a long short-term memory network.

[0055] In one embodiment, the configuration of the dataset processing strategy and the output of the time-stamped table of the data include:

[0056] If at a certain point in time If the difference between the maximum and minimum power values ​​of the generating unit within a set time window is less than a set fluctuation range, then that time point is considered a steady-state time point. The time window is defined as follows: Pushing back to the time point The time range of seconds, that is Maximum power value and minimum power value Specifically:

[0057] ;

[0058] ;

[0059] ;

[0060] in, To set a threshold for power fluctuation amplitude.

[0061] Accumulate steady-state time points into time intervals. When a time interval is longer than the shortest running time, the time interval is considered to be in steady state.

[0062] When performing steady-state calculations, power data below the steady-state minimum threshold are discarded;

[0063] When the interval between two steady-state time periods is less than the set time interval threshold, the two time periods are merged.

[0064] Configure the dataset processing strategy and output a time-stamped table of the data, including:

[0065] a. At a certain moment, within the preceding "600-second" time window, the difference between the maximum and minimum power values ​​of the unit is less than 20 MW. This time point is determined to be the steady-state time point.

[0066] b. Steady-state time points are accumulated into time periods. Only when the time period is greater than "1800 seconds" is the time period judged to be in steady state.

[0067] c. The above calculations need to exclude power data below "100mw", which are not included in the steady-state calculations.

[0068] d. Time period merging: When the interval between two steady-state time periods is less than 300 seconds, the two time periods are merged.

[0069] In one embodiment, the aggregation of measurement points for each category to form a business dataset for a specific category includes:

[0070] The vibration and swing data of the upper guide, lower guide, water guide, upper frame, stator frame, lower frame, and top cover are used to form a vibration and swing business dataset.

[0071] In one embodiment, a "vibration swing steady-state health data asset package" is constructed for a mixed-flow turbine unit of a power plant, and vibration and swing data of the upper guide, lower guide, water guide, upper frame, stator frame, lower frame, and top cover are selected to form a vibration swing business dataset.

[0072] In one embodiment, the attribute information of the improved dataset includes: the name, description, and category of the improved dataset.

[0073] This invention provides a device for constructing a data asset package for hydropower units, the device comprising:

[0074] The dataset acquisition module is used for:

[0075] The measurement points are classified according to their business purpose, and the measurement points of each category are aggregated to form a specific category of business dataset;

[0076] The module for obtaining time stamp tables is used for:

[0077] Configure the dataset processing strategy and output a time-stamped table of the data;

[0078] The data asset package formation module is used for:

[0079] The original business dataset is filtered based on the time-stamped table to form a preliminary dataset;

[0080] Improve the attribute information of the dataset and perform anonymization processing on the attribute information to form a final dataset that can be independently shared and used.

[0081] Furthermore, the module for obtaining the time stamp table includes:

[0082] The configuration processing submodule is used for:

[0083] If at a certain point in time, the difference between the maximum power value and the minimum power value of the unit within the set time window is less than the set fluctuation range, then the point in time is determined to be a steady-state point.

[0084] Accumulate steady-state time points into time intervals. When a time interval is longer than the shortest running time, the time interval is considered to be in steady state.

[0085] When performing steady-state calculations, power data below the steady-state minimum threshold are discarded;

[0086] When the interval between two steady-state time periods is less than the set time interval threshold, the two time periods are merged.

[0087] Further, the device includes:

[0088] The dataset attributes module is used to: improve the name, description, and category of the dataset.

[0089] Figure 2 This invention provides a schematic diagram of a device for constructing a data asset package for a hydropower unit; the device includes:

[0090] Memory, used to store programs;

[0091] A processor is configured to execute a program stored in the memory, and when the program stored in the memory is executed, the processor is configured to perform the above-described method.

[0092] Furthermore, embodiments of the present invention provide a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the above-described method.

[0093] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for constructing a data asset package for hydropower units, characterized in that, The method includes: The measurement points are classified using a deep neural network model, and the measurement points of each category are aggregated to form a business dataset for a specific category. Configure the dataset processing strategy and output a time-stamped table of the data; The original business dataset is filtered based on the time-stamped table to form a preliminary dataset; Improve the attribute information of the dataset and perform anonymization processing on the attribute information to form a final dataset that can be independently shared and used; The processing strategy for the configured dataset, and the output data time-stamp table, include: If at a certain point in time If the difference between the maximum and minimum power values ​​of the generating unit within a set time window is less than a set fluctuation range, then that time point is considered a steady-state time point. The time window is defined as follows: Pushing back to the time point The time range of seconds, that is Maximum power value and minimum power value Specifically: ； ； ； in, To set a threshold for power fluctuation amplitude; Accumulate steady-state time points into time intervals. When a time interval is longer than the shortest running time, the time interval is considered to be in steady state. When performing steady-state calculations, power data below the steady-state minimum threshold are discarded; When the interval between two steady-state time periods is less than the set time interval threshold, the two time periods are merged.

2. The method for constructing a data asset package for hydropower units as described in claim 1, characterized in that, The deep neural network is a convolutional neural network or a long short-term memory network.

3. The method for constructing a data asset package for hydropower units as described in claim 1, characterized in that, The process of aggregating measurement points for each category to form a business dataset for a specific category includes: The vibration and swing data of the upper guide, lower guide, water guide, upper frame, stator frame, lower frame, and top cover are used to form a vibration and swing business dataset.

4. The method for constructing a data asset package for hydropower units as described in claim 1, characterized in that, The attribute information of the improved dataset includes: the name, description, and category of the improved dataset.

5. A device for constructing a data asset package for hydropower units, characterized in that, The device includes: The dataset acquisition module is used for: The measurement points are classified according to their business purpose, and the measurement points of each category are aggregated to form a specific category of business dataset; The module for obtaining time stamp tables is used for: Configure the dataset processing strategy and output a time-stamped table of the data; The data asset package formation module is used for: The original business dataset is filtered based on the time-stamped table to form a preliminary dataset; Improve the attribute information of the dataset and perform anonymization processing on the attribute information to form a final dataset that can be independently shared and used; The processing strategy for the configured dataset, and the output data time-stamp table, include: If at a certain point in time If the difference between the maximum and minimum power values ​​of the generating unit within a set time window is less than a set fluctuation range, then that time point is considered a steady-state time point. The time window is defined as follows: Pushing back to the time point The time range of seconds, that is Maximum power value and minimum power value Specifically: ； ； ； in, To set a threshold for power fluctuation amplitude; Accumulate steady-state time points into time intervals. When a time interval is longer than the shortest running time, the time interval is considered to be in steady state. When performing steady-state calculations, power data below the steady-state minimum threshold are discarded; When the interval between two steady-state time periods is less than the set time interval threshold, the two time periods are merged.

6. The hydropower unit data asset package construction device as described in claim 5, characterized in that, The module for obtaining the time stamp table includes: The configuration processing submodule is used for: If at a certain point in time, the difference between the maximum power value and the minimum power value of the unit within the set time window is less than the set fluctuation range, then the point in time is determined to be a steady-state point. Accumulate steady-state time points into time intervals. When a time interval is longer than the shortest running time, the time interval is considered to be in steady state. When performing steady-state calculations, power data below the steady-state minimum threshold are discarded; When the interval between two steady-state time periods is less than the set time interval threshold, the two time periods are merged.

7. The hydropower unit data asset package construction device as described in claim 5, characterized in that, The device includes: The dataset attributes module is used to: improve the name, description, and category of the dataset.

8. A device for constructing a data asset package for hydropower units, characterized in that, The device includes: Memory, used to store programs; A processor for executing a program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to perform the steps of the method as described in any one of claims 1 to 4.

9. A storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the method as claimed in any one of claims 1 to 4.

Images