Power plant data management method and system based on SIS system

Abstract

The invention discloses a power plant data management method and system based on an SIS system, and relates to the technical field of data management, and the method comprises the steps: obtaining power plant operation data, and carrying out the unified formatting processing of the power plant operation data; preprocessing the formatted data, and removing noise and invalid data; performing quality verification on the preprocessed data, and checking data integrity and consistency; classifying, marking and storing the data subjected to quality verification into a database; and extracting and analyzing data from the database according to operation requirements of the power plant, and generating a decision report. According to the power plant data management method based on the SIS system, through unified formatting and time alignment processing, data format difference and time disorder between different devices are eliminated, and consistency and accuracy of data are ensured. And noise elimination, interpolation processing and anomaly detection are adopted, so that the data quality is guaranteed, and the reliability of an analysis result is improved. And aiming at data with different access frequencies.

Description

Technical Field

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

[0002] In large industrial facilities such as modern power plants, with the popularization of automation equipment and sensors, the various types of data generated by power plants are exploding. In order to effectively utilize this data, power plants usually rely on production information systems (SIS) to collect, store and analyze data. However, in practical applications, there are several prominent problems in data management in power plants:

[0003] There are many types of equipment and sensors in power plants, and each device outputs data in different formats and structures. Traditional power plant data management methods often cannot uniformly process data from different equipment and sensors, resulting in cumbersome data format conversion and prone to errors.

[0004] Due to factors such as different equipment, different collection frequencies, and network delays, power plant data often have problems such as timestamp confusion and inaccurate time alignment. Data between different devices cannot be synchronized, which affects the accuracy and real-time nature of data analysis.

[0005] In power plant operations, data may contain noise, missing values, or outliers due to equipment failures, sensor problems, or external environmental influences. Existing data cleaning and quality verification methods lack pertinence, resulting in data errors not being discovered and processed in a timely manner, thus affecting subsequent analysis and decision-making.

[0006] The amount of data in power plants is huge, and there are different types of data, such as high-frequency data and low-frequency data. Traditional data storage methods are difficult to ensure fast data retrieval and efficient data access while processing large amounts of real-time data, resulting in low system response speed and delayed data analysis.

[0007] There are many types of data in power plants, including real-time data, historical data, frequently accessed data, and infrequently accessed data. How to effectively classify and store them for quick access remains a challenge. Existing technologies cannot reasonably allocate storage space based on the access frequency, importance, and timeliness of data, resulting in waste of resources and inefficient data access.

[0008] The data generated by power plants contain detailed information on equipment operation and sensitive data. How to ensure the security, integrity and privacy of data is a problem that has not been effectively solved in current technology.

[0009] Existing technologies are difficult to process and analyze such large and diverse data efficiently and accurately, and lack a unified technical solution for the specific needs of power plants. Therefore, an efficient, unified and accurate data management method is urgently needed to achieve rapid processing, real-time analysis, accurate storage and efficient retrieval of power plant data. Summary of the invention

[0010] In view of the above-mentioned problems, the present invention is proposed.

[0011] Therefore, the technical problem solved by the present invention is: the existing power plant data management method has difficulties in processing multi-source heterogeneous data, insufficient data quality control, low storage efficiency and data security issues, as well as how to improve the optimization problem of data uniformity, quality, storage efficiency and security.

[0012] In order to solve the above technical problems, the present invention provides the following technical solutions: a power plant data management method based on SIS system, comprising:

[0013] Obtain power plant operation data and perform unified formatting on the power plant operation data;

[0014] Pre-process the formatted data to remove noise and invalid data;

[0015] Perform quality verification on preprocessed data to check data integrity and consistency;

[0016] Classify, label and store the quality-checked data in the database;

[0017] According to the power plant operation needs, data is extracted and analyzed from the database to generate decision-making reports.

[0018] As a preferred solution of the power plant data management method based on the SIS system described in the present invention, the formatting process includes uniformly parsing the multi-source data from different devices and sensors, and using a preset field mapping rule to correspond the output field of each device or sensor to the data structure field predefined by the system;

[0019] Perform time alignment on the data, extract the timestamp of each data, and align all data in chronological order according to the preset time window, and use the timestamp to adjust the data from different sources;

[0020] Convert the measurement units of equipment, convert the units of physical quantities measured by various types of equipment into standard units, and automatically convert by setting conversion rules.

[0021] As a preferred solution of the power plant data management method based on the SIS system described in the present invention, wherein: the elimination of noise and invalid data includes performing noise elimination on the formatted data, using a noise identification algorithm based on dynamic threshold detection, calculating the standard deviation of each data and its surrounding data, and if the standard deviation is lower than a preset threshold, the data is regarded as noise and eliminated;

[0022] Interpolation processing is performed on the data after noise removal. The linear interpolation algorithm is used to calculate the values ​​of the two time points before and after the missing data point, and the missing data is interpolated according to the time difference to maintain the continuity of the data;

[0023] Perform anomaly detection on the interpolated data. Use the Z-score-based anomaly detection algorithm to calculate the Z value of each data. When the Z value exceeds the set threshold, it is marked as abnormal data and the outlier is removed.

[0024] De-duplicate data, use a hash algorithm to generate a unique identifier based on timestamp and device ID, find and delete duplicate records, and ensure the uniqueness of the data.

[0025] As a preferred solution of the power plant data management method based on the SIS system described in the present invention, the quality check includes using a timestamp comparison algorithm to check the difference between the timestamp of each data and the timestamp of its adjacent data. If the time difference exceeds a preset range, the data is marked as inconsistent in time and corrected;

[0026] Use logical consistency check to compare the logical relationship of each record parameter, check the rationality of the parameters according to the working principle and operating conditions of the equipment, and if it does not meet the preset logical relationship, mark the data as inconsistent and make corrections;

[0027] Through continuity testing, a time series detection algorithm is used to check whether there are time breakpoints in the data. When a breakpoint in the time series is found, the data point is marked and the missing part is filled with the average of the previous and next data to correct the discontinuity in the data;

[0028] Use a redundancy check algorithm to find duplicate records through the combination of device ID and timestamp, delete data items with the same timestamp and device ID, and ensure the uniqueness and integrity of the data set.

[0029] As a preferred solution of the power plant data management method based on the SIS system described in the present invention, wherein: the data classification includes dividing the data into real-time data and historical data according to the source and timeliness of the data, the real-time data is stored in a real-time database, and the historical data and low-frequency data are stored in a long-term storage system, and the real-time database can support fast data retrieval and analysis;

[0030] Based on the access frequency of data, the data is further classified, high-frequency data is marked, and the access frequency of data is counted according to the operating status of the device and the frequency of data collection. High-frequency data is stored in the cache first, and less storage space is allocated for low-frequency data.

[0031] A unique identifier is generated for each piece of data using a hash algorithm, and a unique label is generated using the device ID, timestamp, and hash value of the data content;

[0032] Use symmetric encryption algorithm to encrypt sensitive data, and use AES algorithm to encrypt and store data;

[0033] Establish an index structure based on device type, time period and data category, associate each piece of data with multiple index items, and establish a multidimensional index.

[0034] As a preferred solution of the power plant data management method based on the SIS system described in the present invention, the real-time data is the original data generated in each equipment collection cycle, which is stored in a real-time database. The real-time database supports efficient data reading and analysis and can realize fast retrieval;

[0035] The historical data is the operation data of the equipment over a long period of time, which is stored in a long-term storage system, which provides large-capacity storage and long-term data preservation functions;

[0036] By counting the access frequency of each piece of data and the operating status of the device, high-frequency data can be identified and marked.

[0037] As a preferred solution of the power plant data management method based on the SIS system described in the present invention, wherein: the extracting and analyzing data from the database includes using SQL query statements to extract the required data from the storage database, combining a multidimensional data analysis algorithm to analyze the operating status of the equipment, calculate the real-time energy efficiency, load status and failure rate of the equipment, and evaluate the health status of the equipment;

[0038] Use time series analysis methods to analyze the historical data of the equipment, predict the future load demand and scheduled maintenance cycle of the equipment, and output the predicted load demand curve and maintenance suggestions based on the maintenance records of the equipment;

[0039] Based on the analysis results, a decision report is generated in combination with the equipment's operating status and historical data. The report contains equipment operating trends, maintenance cycle recommendations, and fault warning information, which power plant managers use to make equipment management and scheduling decisions.

[0040] Another object of the present invention is to provide a power plant data processing system based on the SIS system, which can solve the problems of multi-source data integration and processing difficulties, low data quality, low storage efficiency, and insufficient data security in the existing power plant data management system by constructing a power plant data processing system based on the SIS system.

[0041] In order to solve the above technical problems, the present invention provides the following technical solutions: a power plant data processing system based on the SIS system, comprising: an acquisition module, a processing module, a verification module, a classification module and a decision module; the acquisition module is used to obtain power plant operation data and uniformly format the power plant operation data; the processing module is used to pre-process the formatted data to remove noise and invalid data; the verification module is used to perform quality verification on the pre-processed data to check data integrity and consistency; the classification module is used to classify, mark and store the quality-verified data in a database; the decision module is used to extract and analyze data from the database according to the power plant operation needs and generate a decision report.

[0042] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the power plant data management method based on the SIS system when executing the computer program.

[0043] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the power plant data management method based on the SIS system as described above.

[0044] Beneficial effects of the present invention: The power plant data management method based on the SIS system provided by the present invention eliminates the data format differences and time confusion between different devices through unified formatting and time alignment processing, thereby ensuring the consistency and accuracy of the data. Noise removal, interpolation processing and anomaly detection are adopted to ensure data quality and improve the reliability of analysis results. For data with different access frequencies, the present invention optimizes the storage structure, improves data retrieval efficiency and storage space utilization. At the same time, data security and privacy protection are enhanced through data encryption and multidimensional indexing technology. The present invention supports efficient data extraction and real-time analysis, helps power plants to achieve accurate equipment monitoring, energy efficiency analysis, load forecasting and fault warning, and significantly improves the management efficiency and decision-making accuracy of power plants. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0046] Figure 1 An overall flow chart of a power plant data management method based on a SIS system provided by an embodiment of the present invention.

[0047] Figure 2 This is an overall structural diagram of a power plant data management system based on a SIS system provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Example 1

[0051] Reference Figure 1 , as an embodiment of the present invention, provides a power plant data management method based on a SIS system, comprising:

[0052] Obtain power plant operation data and perform unified formatting on the power plant operation data;

[0053] Pre-process the formatted data to remove noise and invalid data;

[0054] Perform quality verification on preprocessed data to check data integrity and consistency;

[0055] Classify, label and store the quality-checked data in the database;

[0056] According to the power plant operation needs, data is extracted and analyzed from the database to generate decision-making reports.

[0057] The formatting process includes uniformly parsing the multi-source data from different devices and sensors, and using preset field mapping rules to correspond the output field of each device or sensor to the data structure field predefined by the system;

[0058] Perform time alignment on the data, extract the timestamp of each data, and align all data in chronological order according to the preset time window. Use the timestamp to adjust the data from different sources so that they are arranged on the same timeline.

[0059] Convert the measurement units of the equipment, convert the units of physical quantities measured by various types of equipment into standard units, and automatically convert by setting conversion rules to ensure consistency in subsequent processing.

[0060] The result of this step is a data set in a unified format with consistent fields, synchronized time, and standard units, providing consistent basic data for subsequent preprocessing and verification operations.

[0061] The elimination of noise and invalid data includes performing noise elimination on the formatted data, using a noise identification algorithm based on dynamic threshold detection to calculate the standard deviation of each piece of data and its surrounding data, and if the standard deviation is lower than a preset threshold, the data is regarded as noise and eliminated;

[0062] Interpolation processing is performed on the data after noise removal. The linear interpolation algorithm is used to calculate the values ​​of the two time points before and after the missing data point, and the missing data is interpolated according to the time difference to maintain the continuity of the data;

[0063] Perform anomaly detection on the interpolated data. Use the Z-score-based anomaly detection algorithm to calculate the Z value of each data. When the Z value exceeds the set threshold, it is marked as abnormal data and the outlier is removed.

[0064] De-duplicate data, use a hash algorithm to generate a unique identifier based on timestamp and device ID, find and delete duplicate records, and ensure the uniqueness of the data.

[0065] The output of this step is a processed clean data set, including noise removed, interpolation filled, outlier removed, and duplicated data, providing clear input data for quality verification.

[0066] The quality check includes using a timestamp comparison algorithm to check the difference between the timestamp of each piece of data and the timestamp of its adjacent data. If the time difference exceeds a preset range, the data is marked as inconsistent in time and corrected.

[0067] Use logical consistency check to compare the logical relationship of each record parameter, including temperature, pressure, flow, etc., and check the rationality of the parameters according to the working principle and operating conditions of the equipment. If it does not meet the preset logical relationship, the data is marked as inconsistent and corrected;

[0068] Through continuity testing, a time series detection algorithm is used to check whether there are time breakpoints in the data. When a breakpoint in the time series is found, the data point is marked and the missing part is filled with the average of the previous and next data to correct the discontinuity in the data;

[0069] Use a redundancy check algorithm to find duplicate records through the combination of device ID and timestamp, delete data items with the same timestamp and device ID, and ensure the uniqueness and integrity of the data set.

[0070] The output of this step is a data set that has been verified in terms of time, logic, continuity, and redundancy. All data that has failed the verification has been marked and corrected, and is ready to enter the classified storage stage.

[0071] The data classification includes classifying the data into real-time data and historical data according to the source and timeliness of the data, the real-time data is stored in a real-time database, and the historical data and low-frequency data are stored in a long-term storage system. The real-time database can support fast data retrieval and analysis;

[0072] Based on the access frequency of data, the data is further classified, high-frequency data is marked, and the access frequency of data is counted according to the operating status of the device and the frequency of data collection. High-frequency data is stored in the cache first, and less storage space is allocated for low-frequency data.

[0073] A unique identifier is generated for each piece of data using a hash algorithm. A unique tag is generated using the device ID, timestamp, and hash value of the data content to ensure that each record has a unique identifier when stored.

[0074] Use symmetric encryption algorithms to encrypt sensitive data, and use AES algorithms to encrypt and store data to prevent data leakage during storage;

[0075] Establish an index structure based on device type, time period and data category, associate each piece of data with multiple index items, establish a multi-dimensional index, improve retrieval performance, and ensure efficient retrieval of large-scale data.

[0076] The result of this step is an efficient and secure data set that is stored according to timeliness and frequency of use. The data is reasonably organized and ensures efficient retrieval and access.

[0077] The real-time data is the raw data generated in each equipment collection cycle and is stored in a real-time database. The real-time database supports efficient data reading and analysis and can achieve fast retrieval;

[0078] The historical data is the operation data of the equipment over a long period of time, which is stored in a long-term storage system, which provides large-capacity storage and long-term data preservation functions;

[0079] By counting the access frequency of each piece of data and the operating status of the device, high-frequency data can be identified and marked.

[0080] The extracting and analyzing data from the database includes extracting the required data from the storage database using SQL query statements, analyzing the operating status of the equipment in combination with a multidimensional data analysis algorithm, calculating the real-time energy efficiency, load status and failure rate of the equipment, and evaluating the health status of the equipment;

[0081] Use time series analysis methods to analyze the historical data of the equipment, predict the future load demand and scheduled maintenance cycle of the equipment, and output the predicted load demand curve and maintenance suggestions based on the maintenance records of the equipment;

[0082] Based on the analysis results, a decision report is generated in combination with the equipment's operating status and historical data. The report contains equipment operating trends, maintenance cycle recommendations, and fault warning information, which power plant managers use to make equipment management and scheduling decisions.

[0083] The output of this step is a decision report based on the analysis. The report includes future operating trends, maintenance cycle recommendations, and potential failure warnings, providing decision support for the operation and management of the power plant.

[0084] It should be noted that, in the embodiment, the source of the power plant operation data includes a variety of automation equipment and sensors in the power plant, such as temperature sensors, pressure sensors, flow meters, gas flow meters, equipment operation status monitoring systems, and production information systems (SIS). These data cover multiple operating parameters of the power plant, such as equipment temperature, pressure, flow, current, voltage, power and other physical quantities. Each device and sensor will collect data at different time intervals, and the generated data will include timestamps, device IDs, measurement units, and measured physical quantities. In order to enable these data from different devices to be managed uniformly, it is first necessary to format the data of different devices and sensors, including field parsing and field mapping. By setting a unified data structure field and predefined field mapping rules, each piece of data will correspond to a specific field, such as device ID, measurement value, timestamp, etc., to ensure that the format of the data is consistent and convenient for subsequent processing.

[0085] In the process of data processing, noise removal is a key link. A noise identification algorithm based on dynamic threshold detection is used to calculate the standard deviation of each collected data and its surrounding data. If the standard deviation is lower than the preset dynamic threshold, it is determined to be noise data and removed. The setting of this threshold is not static, but is dynamically adjusted according to the real-time fluctuation of the data. Taking into account the working environment and data characteristics of different devices and sensors, the algorithm can adapt to the noise types of different data sources. After removing the noise, the missing part of the data is filled by the linear interpolation algorithm. The advantage of the linear interpolation algorithm is that the calculation is simple and it is suitable for the processing of large-scale real-time data, but its applicable condition is that there are fewer missing data points and the changes between the missing data points and the previous and subsequent data are relatively stable. During the interpolation process, any abnormal large data fluctuation will be regarded as an outlier, which will be identified and removed by the Z-score algorithm to ensure the validity and continuity of the data.

[0086] In the quality verification phase, the timestamp comparison algorithm is first used to check whether the data has time confusion. The range of timestamp comparison is set according to the collection frequency of the equipment and the collection cycle of the data. Different types of data have different requirements on the time difference range. For real-time data, the tolerance range of timestamps is usually small, while for historical data, the tolerance of time difference is larger. Through this comparison, if the time difference exceeds the preset range, it is marked as time-inconsistent data and corrected. Logical consistency verification depends on the working principle of the equipment and the relationship between the actual operating parameters. Taking temperature and pressure as an example, temperature and pressure usually show a certain linear relationship. When the pressure is abnormal, the temperature should also change accordingly. If illogical abnormal data is detected, the system will correct it according to the preset rules.

[0087] In terms of data classification and storage, all pre-processed and quality-checked data will be classified and stored according to timeliness and frequency of use. Real-time data is stored in a real-time database with efficient reading and fast retrieval capabilities, supporting fast query and data analysis; historical data and low-frequency data are stored in a long-term storage system to reduce storage pressure and maintain long-term archiving. For high-frequency data, it will be stored in the cache area first to ensure that data with high access frequency can be processed quickly, while low-frequency data will be allocated less storage space. Sensitive data is encrypted and stored using the AES symmetric encryption algorithm to ensure that the data is not leaked or tampered with during storage. By analyzing information such as data access frequency and equipment operating status, the system can effectively identify and classify data, thereby ensuring efficient storage and reading of different types of data.

[0088] Finally, when extracting and analyzing data from the database, SQL query language combined with multidimensional data analysis algorithms are used to conduct a comprehensive analysis of the equipment's operating status, energy efficiency, load conditions, etc., to help power plant managers make decisions. In addition, based on the time series analysis method of historical data, the future load demand and maintenance cycle of the equipment can be predicted, and scientific maintenance recommendations and equipment operation trend reports can be provided to further support the power plant's operational decisions.

[0089] Example 2

[0090] Reference Figure 2 , is an embodiment of the present invention, and provides a power plant data processing system based on a SIS system, comprising:

[0091] Collection module 100, processing module 200, verification module 300, classification module 400 and decision module 500;

[0092] The acquisition module 100 is used to obtain power plant operation data and perform unified formatting on the power plant operation data;

[0093] The processing module 200 is used to pre-process the formatted data to remove noise and invalid data;

[0094] The verification module 300 is used to perform quality verification on the pre-processed data to check the data integrity and consistency;

[0095] The classification module 400 is used to classify, mark and store the quality-checked data in a database;

[0096] The decision module 500 is used to extract and analyze data from the database and generate a decision report according to the power plant operation requirements.

[0097] Example 3

[0098] An embodiment of the present invention is different from the first two embodiments in that:

[0099] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0100] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0101] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0102] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0103] Example 4

[0104] As an embodiment of the present invention, a power plant data management method based on a SIS system is provided. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0105] The simulation collected data from about 1,000 devices in the power plant, covering real-time data, historical data, and equipment operating status data. Each data source has a different format and structure, and the total amount of data is about 1TB. The data includes types such as temperature, pressure, flow, and fault information, and the collection frequency varies. The data was preprocessed and managed, and the experiment was divided into two groups: one group used traditional methods for data management, and the other group used the method of the present invention.

[0106] In traditional methods, data is not uniformly formatted during processing, time alignment between data is not strictly guaranteed, missing data and noise are only cleaned up through simple threshold setting, storage schemes are not optimized according to data access frequency, and encryption is not performed. When retrieving data, due to the lack of an optimized storage structure, query speed is slow, and data security is not effectively guaranteed.

[0107] In contrast, the method of the present invention first performs a unified formatting process on all collected data, including converting the data output by different devices and sensors into a standardized format through preset field mapping rules. Then, in the data preprocessing stage, dynamic threshold detection and Z-score anomaly detection algorithms are used to eliminate noise and outliers. For time alignment, the present invention uses an accurate timestamp comparison algorithm to ensure that all data can be integrated according to a unified time window. In terms of storage, the method of the present invention classifies and stores data according to its access frequency, stores high-frequency data in a fast-retrieval cache, and stores low-frequency data in a long-term storage system, significantly improving the utilization of storage space. At the same time, all sensitive data is AES encrypted to ensure data security. After the experiment is completed, the record table is shown in Table 1.

[0108] Table 1 Comparison of experimental results

[0109] index Traditional methods Method of the present invention Data quality (percentage of erroneous data) 12％ 3％ Data storage space utilization 68％ 90％ Data retrieval speed (seconds / time) 15 5 Data security (encrypted data ratio) 0％ 100％ System response time (seconds) 30 10 Error data repair time (hours) 8 2

[0110] First, in terms of data quality, the traditional method fails to systematically handle data cleaning and outlier removal, resulting in serious erroneous data. This makes subsequent data analysis and decision-making rely on inaccurate basic data. However, the present invention introduces a unified data formatting, noise removal and anomaly detection mechanism, so that the data has been effectively cleaned before entering the analysis stage, significantly improving the accuracy and reliability of the data.

[0111] Secondly, storage efficiency is another advantage of the present invention that cannot be matched by traditional methods. Traditional methods do not classify and store different types of data, resulting in waste of storage resources and low retrieval efficiency. In contrast, the present invention greatly improves the utilization of storage space and retrieval efficiency by classifying and managing data, optimizing storage structure, and introducing index acceleration, ensuring that efficient responses can be maintained when facing large amounts of data.

[0112] In terms of data security, the traditional method does not encrypt the data, resulting in the risk of sensitive data leakage. The present invention introduces encryption technology in the data storage process, especially adopts advanced encryption algorithms, so that sensitive information can be effectively protected during the storage process, greatly improving the security of the data.

[0113] Finally, the shortened system response time reflects the optimization of the data storage and access mechanism of the present invention. Traditional methods often lead to slow system response due to inefficient data access, especially when the amount of data is huge. Through classified storage, fast indexing and caching mechanism of data, the present invention enables the system to maintain a short response time even when facing a huge amount of data.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A power plant data management method based on SIS system, characterized in that: include: Obtain power plant operation data and perform unified formatting on the power plant operation data; Pre-process the formatted data to remove noise and invalid data; Perform quality verification on preprocessed data to check data integrity and consistency; Classify, label and store the quality-checked data in the database; According to the power plant operation needs, data is extracted and analyzed from the database to generate decision-making reports.

2. The power plant data management method based on the SIS system according to claim 1, characterized in that: The formatting process includes uniformly parsing the multi-source data from different devices and sensors, and using preset field mapping rules to correspond the output field of each device or sensor to the data structure field predefined by the system; Perform time alignment on the data, extract the timestamp of each data, and align all data in chronological order according to the preset time window, and use the timestamp to adjust the data from different sources; Convert the measurement units of equipment, convert the units of physical quantities measured by various types of equipment into standard units, and automatically convert by setting conversion rules.

3. The power plant data management method based on the SIS system according to claim 2, characterized in that: The elimination of noise and invalid data includes performing noise elimination on the formatted data, using a noise identification algorithm based on dynamic threshold detection to calculate the standard deviation of each piece of data and its surrounding data, and if the standard deviation is lower than a preset threshold, the data is regarded as noise and eliminated; Interpolation processing is performed on the data after noise removal. The linear interpolation algorithm is used to calculate the values ​​of the two time points before and after the missing data point, and the missing data is interpolated according to the time difference to maintain the continuity of the data; Perform anomaly detection on the interpolated data. Use the Z-score-based anomaly detection algorithm to calculate the Z value of each data. When the Z value exceeds the set threshold, it is marked as abnormal data and the outlier is removed. De-duplicate data, use a hash algorithm to generate a unique identifier based on timestamp and device ID, find and delete duplicate records, and ensure the uniqueness of the data.

4. The power plant data management method based on the SIS system according to claim 3, characterized in that: The quality check includes using a timestamp comparison algorithm to check the difference between the timestamp of each piece of data and the timestamp of its adjacent data. If the time difference exceeds a preset range, the data is marked as inconsistent in time and corrected. Use logical consistency check to compare the logical relationship of each record parameter, check the rationality of the parameters according to the working principle and operating conditions of the equipment, and if it does not meet the preset logical relationship, mark the data as inconsistent and make corrections; Through continuity testing, a time series detection algorithm is used to check whether there are time breakpoints in the data. When a breakpoint in the time series is found, the data point is marked and the missing part is filled with the average of the previous and next data to correct the discontinuity in the data; Use a redundancy check algorithm to find duplicate records through the combination of device ID and timestamp, delete data items with the same timestamp and device ID, and ensure the uniqueness and integrity of the data set.

5. The power plant data management method based on the SIS system according to claim 4, characterized in that: The data classification includes classifying the data into real-time data and historical data according to the source and timeliness of the data, the real-time data is stored in a real-time database, and the historical data and low-frequency data are stored in a long-term storage system. The real-time database can support fast data retrieval and analysis; Based on the access frequency of data, the data is further classified, high-frequency data is marked, and the access frequency of data is counted according to the operating status of the device and the frequency of data collection. High-frequency data is stored in the cache first, and less storage space is allocated for low-frequency data. A unique identifier is generated for each piece of data using a hash algorithm, and a unique label is generated using the device ID, timestamp, and hash value of the data content; Use symmetric encryption algorithm to encrypt sensitive data, and use AES algorithm to encrypt and store data; Establish an index structure based on device type, time period and data category, associate each piece of data with multiple index items, and establish a multidimensional index.

6. The power plant data management method based on the SIS system according to claim 5, characterized in that: The real-time data is the raw data generated in each equipment collection cycle and is stored in a real-time database. The real-time database supports efficient data reading and analysis and can achieve fast retrieval; The historical data is the operation data of the equipment over a long period of time, which is stored in a long-term storage system, which provides large-capacity storage and long-term data preservation functions; By counting the access frequency of each piece of data and the operating status of the device, high-frequency data can be identified and marked.

7. The power plant data management method based on the SIS system according to claim 6, characterized in that: The extracting and analyzing data from the database includes extracting the required data from the storage database using SQL query statements, analyzing the operating status of the equipment in combination with a multidimensional data analysis algorithm, calculating the real-time energy efficiency, load status and failure rate of the equipment, and evaluating the health status of the equipment; Use time series analysis methods to analyze the historical data of the equipment, predict the future load demand and scheduled maintenance cycle of the equipment, and output the predicted load demand curve and maintenance suggestions based on the maintenance records of the equipment; Based on the analysis results, a decision report is generated in combination with the equipment's operating status and historical data. The report contains equipment operating trends, maintenance cycle recommendations, and fault warning information, which power plant managers use to make equipment management and scheduling decisions.

8. A system using the power plant data management method based on the SIS system as claimed in any one of claims 1 to 7, characterized in that: include: A collection module (100), a processing module (200), a verification module (300), a classification module (400) and a decision module (500); The acquisition module (100) is used to acquire power plant operation data and perform unified formatting processing on the power plant operation data; The processing module (200) is used to pre-process the formatted data to remove noise and invalid data; The verification module (300) is used to perform quality verification on the pre-processed data to check the data integrity and consistency; The classification module (400) is used to classify, mark and store the quality-checked data in a database; The decision module (500) is used to extract and analyze data from the database and generate a decision report according to the power plant operation requirements.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the power plant data management method based on the SIS system according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power plant data management method based on the SIS system according to any one of claims 1 to 7 are implemented.

Images