Water turbine temperature data preprocessing method and device and storage medium

Abstract

The invention discloses a water turbine temperature data preprocessing method and device and a storage medium. The method comprises the steps of obtaining water turbine temperature data; judging the operation state of the water turbine unit; filtering the temperature data according to the operation state of the unit; further filtering the temperature data filtered according to the operation state of the unit through statistical analysis of historical temperature data of the water turbine; and further processing the temperature data based on the business characteristics.

Description

Technical Field

[0001] The invention relates to hydropower generation equipment technology, and in particular to a method, device and storage medium for preprocessing temperature data of a water turbine. Background Art

[0002] At present, the methods for preprocessing industrial data include data-driven methods such as neural networks and clustering, as well as special processing methods based on the business characteristics of various fields. The preprocessing methods for time series data are mainly based on statistics and machine learning.

[0003] Industrial time series data preprocessing is different from other data preprocessing. For complex industrial time series data preprocessing, it is necessary to emphasize the deep integration of analysis purpose, domain knowledge and data analysis process. Therefore, it is particularly important to solve the preprocessing of industrial time series data through knowledge-driven. However, there is still a lack of targeted data preprocessing methods that combine hydropower business knowledge. Summary of the invention

[0004] The invention provides a method, a device and a storage medium for preprocessing temperature data of a water turbine.

[0005] In a first aspect, the present invention provides a method for preprocessing temperature data of a water turbine, the method comprising: Get turbine temperature data; Determine the operating status of the turbine unit; Filter the temperature data according to the operating status of the unit; Further filtering the temperature data filtered according to the operating status of the unit by statistical analysis of the historical temperature data of the turbine; The temperature data is further processed based on business characteristics.

[0006] Furthermore, the determining the operating status of the water turbine unit includes: Get device object model and raw data; Based on the equipment model, the effective power and speed of the units with the same temperature are obtained to determine the unit status.

[0007] Furthermore, filtering the data according to the operating status of the unit includes: The unit is in the power-on state; Abnormal data when the unit is turned on is eliminated, including data with jump abnormalities, over-range abnormalities, and dead value abnormalities.

[0008] Furthermore, the temperature data filtered according to the operating status of the unit is further filtered by statistical analysis of the historical temperature data of the turbine, specifically: The historical data of the time it takes for the temperature to reach a stable state after the unit is started is counted to obtain a threshold of the time it takes for the temperature to reach a stable state after the unit is started; For the temperature data filtered according to the operating status of the unit, the temperature data before the temperature reaches a stable state after startup is eliminated to obtain the stabilized temperature data.

[0009] Furthermore, the temperature data is further processed based on the business characteristics, specifically: Based on the subsequent needs of calculating the daily maximum value, daily minimum value, daily median value, monthly maximum value, monthly minimum value, and monthly median value of the unit temperature, the temperature data is further processed.

[0010] Furthermore, the statistical analysis of the historical data of the turbine temperature includes: Through the big data model and deep neural network, statistical analysis of historical data of turbine temperature is carried out.

[0011] In a second aspect, the present invention provides a turbine temperature data preprocessing device, the device comprising: Get data module, used to: Get turbine temperature data; The first data filtering module is used to: Determine the operating status of the turbine unit; Filter the temperature data according to the operating status of the unit; The second data filtering module is used for: Further filtering the temperature data filtered according to the operating status of the unit by statistical analysis of the historical temperature data of the turbine; The third data filtering module is used to: The temperature data is further processed based on business characteristics.

[0012] Furthermore, the device also includes: The big data model submodule is used to: Through the big data model and deep neural network, statistical analysis of historical data of turbine temperature is carried out.

[0013] In a third aspect, the present invention provides a turbine temperature data preprocessing device, the device comprising: Memory, used to store programs; The processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the above method.

[0014] In a fourth aspect, the present invention provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, causes the one or more processors to execute the above method.

[0015] Compared with the prior art, the present invention has the following advantages: Based on the statistical analysis of historical data, preprocessing rules and parameters for temperature data after startup are added; filtering is performed based on the unit status to eliminate the impact of quality problems, and then the data is preprocessed based on the business characteristics of the data itself, which improves the rationality of the processed data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a method for preprocessing temperature data of a water turbine provided by an embodiment of the present invention; Figure 2 A schematic diagram of the composition of a turbine temperature data preprocessing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] Figure 1 A schematic diagram of a method for preprocessing temperature data of a turbine provided in an embodiment of the present invention, the method comprising: Get turbine temperature data; Determine the operating status of the turbine unit; Filter the temperature data according to the operating status of the unit; Further filtering the temperature data filtered according to the operating status of the unit by statistical analysis of the historical temperature data of the turbine; The temperature data is further processed based on business characteristics.

[0019] In one embodiment, the step of determining the operating state of the water turbine unit includes: Get device object model and raw data; Based on the equipment model, the effective power and speed of the units with the same temperature are obtained to determine the unit status.

[0020] In one embodiment, when preprocessing the water guide bearing temperature of a water turbine, water guide bearing temperature measurement points of 1-8F units of a power station are selected to obtain the equipment object model and original data.

[0021] The effective power and speed of units 1-8F are obtained based on the equipment model to determine the unit status.

[0022] Furthermore, filtering the data according to the operating status of the unit includes: The unit is in the power-on state; Abnormal data when the unit is turned on is eliminated, including data with jump abnormalities, over-range abnormalities, and dead value abnormalities.

[0023] Furthermore, the temperature data filtered according to the operating status of the unit is further filtered by statistical analysis of the historical temperature data of the turbine, specifically: The historical data of the time it takes for the temperature to reach a stable state after the unit is started is counted to obtain a threshold of the time it takes for the temperature to reach a stable state after the unit is started; For the temperature data filtered according to the operating status of the unit, the temperature data before the temperature reaches a stable state after startup is eliminated to obtain the stabilized temperature data.

[0024] In one embodiment, statistics are collected on the time it takes for the water-conducting tile temperature data to be stable after the unit is started in the one-year historical data.

[0025] Furthermore, the temperature data is further processed based on the business characteristics, specifically: Based on the subsequent needs of calculating the daily maximum value, daily minimum value, daily median value, monthly maximum value, monthly minimum value, and monthly median value of the unit temperature, the temperature data is further processed.

[0026] In one embodiment, the temperature parameters are input into the subsequent calculation link of the daily or monthly maximum, minimum and median values ​​of the water-conducting tile temperature.

[0027] Furthermore, the statistical analysis of the historical data of the turbine temperature includes: Through the big data model and deep neural network, statistical analysis of historical data of turbine temperature is carried out.

[0028] An embodiment of the present invention provides a turbine temperature data preprocessing device, the device comprising: Get data module, used to: Get turbine temperature data; The first data filtering module is used to: Determine the operating status of the turbine unit; Filter the temperature data according to the operating status of the unit; The second data filtering module is used for: Further filtering the temperature data filtered according to the operating status of the unit by statistical analysis of the historical temperature data of the turbine; The third data filtering module is used for: The temperature data is further processed based on business characteristics.

[0029] Furthermore, the device also includes: The big data model submodule is used to: Through the big data model and deep neural network, statistical analysis of historical data of turbine temperature is carried out.

[0030] Figure 2 A schematic diagram of a turbine temperature data preprocessing device provided in an embodiment of the present invention; the device comprises: Memory, used to store programs; The processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the above method.

[0031] In addition, an embodiment of the present invention provides a storage medium storing computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the above method.

[0032] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for preprocessing temperature data of a turbine, characterized in that: The method comprises: Get turbine temperature data; Determine the operating status of the turbine unit; Filter the temperature data according to the operating status of the unit; Further filtering the temperature data filtered according to the operating status of the unit by statistical analysis of the historical temperature data of the turbine; The temperature data is further processed based on business characteristics.

2. The method for preprocessing temperature data of a water turbine according to claim 1, characterized in that: Determining the operating state of the water turbine unit includes: Get device object model and raw data; Based on the equipment model, the effective power and speed of the units with the same temperature are obtained to determine the unit status.

3. The method for preprocessing temperature data of a water turbine according to claim 1, characterized in that: The filtering of data according to the operating status of the unit includes: The unit is in the power-on state; Abnormal data when the unit is turned on is eliminated, including data with jump abnormalities, over-range abnormalities, and dead value abnormalities.

4. The method for preprocessing temperature data of a water turbine according to claim 1, characterized in that: The temperature data filtered according to the operating status of the unit is further filtered by statistical analysis of the historical temperature data of the turbine, specifically: The historical data of the time it takes for the temperature to reach a stable state after the unit is started is counted to obtain a threshold of the time it takes for the temperature to reach a stable state after the unit is started; For the temperature data filtered according to the operating status of the unit, the temperature data before the temperature reaches a stable state after startup is eliminated to obtain the stabilized temperature data.

5. The method for preprocessing temperature data of a water turbine according to claim 1, characterized in that: The further processing of the temperature data based on the business characteristics is specifically as follows: Based on the subsequent needs of calculating the daily maximum value, daily minimum value, daily median value, monthly maximum value, monthly minimum value, and monthly median value of the unit temperature, the temperature data is further processed.

6. The method for preprocessing temperature data of a water turbine according to claim 1, characterized in that: The statistical analysis of the historical data of turbine temperature includes: Through the big data model and deep neural network, statistical analysis of historical data of turbine temperature is carried out.

7. A turbine temperature data preprocessing device, characterized in that: The device comprises: Get data module, used to: Get turbine temperature data; The first data filtering module is used to: Determine the operating status of the turbine unit; Filter the temperature data according to the operating status of the unit; The second data filtering module is used for: Further filtering the temperature data filtered according to the operating status of the unit by statistical analysis of the historical temperature data of the turbine; The third data filtering module is used to: The temperature data is further processed based on business characteristics.

8. The water turbine temperature data preprocessing device according to claim 7, characterized in that: The device also includes: The big data model submodule is used to: Through the big data model and deep neural network, statistical analysis of historical data of turbine temperature is carried out.

9. A turbine temperature data preprocessing device, characterized in that: The device comprises: Memory, used to store programs; A processor, configured to execute the program stored in the memory; when the program stored in the memory is executed, the processor is configured to execute the steps of the method as claimed in any one of claims 1 to 6.

10. A storage medium storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors are caused to perform the steps of the method according to any one of claims 1 to 6.

Images