A method and system for constructing a multi-dimensional data model of a thermal power plant

Abstract

This invention relates to the field of multidimensional data processing technology. It discloses a method and system for constructing a multidimensional data model for thermal power equipment. The method includes: collecting basic and indicator data of the thermal power equipment; using machine learning algorithms to identify data relationships between different business domains and constructing a multi-level data abstract model; defining the hierarchical structure and specific attributes in the data model, as well as the relationships between each layer; and dynamically updating the data relationships to adapt to changes in the data source, forming a data model that supports the entire lifecycle management of the equipment. This method combines advanced machine learning algorithms to identify data relationships between different business domains to support comprehensive equipment management.

Description

Technical Field

[0001] This invention relates to the field of multidimensional data processing technology, and in particular to a method and system for constructing a multidimensional data model of thermal power equipment. Background Technology

[0002] As a crucial component of the modern power industry, thermal power equipment has seen significant advancements in power generation efficiency, environmental performance, and intelligent management thanks to continuous technological progress. In recent years, with the rapid development of data science and machine learning technologies, the management model of thermal power equipment has shifted towards data-driven and intelligent approaches. Through dynamic monitoring and analysis of real-time equipment data, thermal power companies can achieve real-time early warning of equipment status, fault diagnosis, and optimized maintenance decisions. Therefore, constructing multi-dimensional data models based on machine learning to support the full lifecycle management of thermal power equipment has become an important way to promote the efficient operation of the thermal power industry. However, current technologies in the field of thermal power equipment management still have some shortcomings, such as insufficient data collaborative analysis capabilities, significant difficulties in data integration, limited real-time update capabilities, and simplistic decision support. These issues directly affect the operating efficiency and economic benefits of the equipment.

[0003] The shortcomings of existing technologies are mainly reflected in several aspects: First, the ability to automatically collect and integrate data is limited. Although many thermal power plants have established basic data collection systems, the data relationships between different devices, systems, and between them still exist in silos, lacking an effective unified multidimensional data model for horizontal and vertical analysis. Second, there are limitations in data analysis. Current models often cannot effectively identify complex data relationships between business domains or the dynamic changes in real-time data, leading to insufficient accuracy in equipment status assessment and maintenance decisions. Third, decision support systems are often based on static data, lacking real-time feedback and dynamic update mechanisms, and cannot respond promptly to sudden situations and changes in equipment operation. Therefore, how to establish an efficient multidimensional data analysis framework to solve these problems has become an urgent technical challenge. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method for constructing a multidimensional data model for thermal power equipment, which can enhance the correlation and practicality between data through dynamic updates and machine learning technology, thereby achieving real-time and effective full life cycle management of equipment.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a method for constructing a multi-dimensional data model for thermal power equipment, comprising: collecting basic data and indicator data of the thermal power equipment; using machine learning algorithms to identify data relationships between different business domains and constructing a multi-level data abstraction model; defining the hierarchical structure and specific attributes in the data model, as well as the relationships between each layer; dynamically updating the data relationships to adapt to changes in the data source, forming a data model that supports the full lifecycle management of the equipment.

[0007] As a preferred embodiment of the multidimensional data model construction method for thermal power equipment according to the present invention, the basic data includes equipment type, manufacturer, and operating parameters; The data metrics include power generation efficiency, failure rate, and operating time.

[0008] As a preferred embodiment of the multidimensional data model construction method for thermal power equipment described in this invention, the machine learning algorithm includes: collecting corresponding data containing KKS codes, equipment codes and spare parts codes, performing data cleaning, removing missing values ​​and duplicate values, and standardizing text information; The encoded data is converted into a vector representation. Word embedding is performed on the KKS encoding. An improved Skip-Gram model is used to convert each encoding into a high-dimensional vector representation. The same processing is performed on the equipment encoding and spare parts encoding. The enhanced Apriori algorithm is used to mine frequent itemsets between each type of encoding. By setting a minimum support threshold (S), new itemsets are generated iteratively, and the similarity of frequent itemsets is evaluated to enhance the association with different encodings.

[0009] As a preferred embodiment of the multi-dimensional data model construction method for thermal power equipment described in this invention, the construction of the multi-level data abstraction model includes, after completing the collection and preliminary classification of data, defining the hierarchy, and determining the hierarchical structure of the data model through expert interviews or collaboration with data scientists. The first layer is the basic data layer, which contains all the raw data. The second layer is the feature layer, which extracts features from the basic data. The third layer is the indicator layer, which summarizes the features to generate key performance indicators. The fourth layer is the visualization layer, which generates visual charts based on the indicators. Each layer of the management mechanism employs access control and data integrity checks, ensuring that each layer operates independently. When the underlying basic data changes, the application change log is synchronized to the upper layer data. A multi-layered data abstraction model is constructed, employing hierarchical storage and abstract interfaces to manage data at each layer, with each layer accessing data at the upper or lower layer through predefined interfaces.

[0010] As a preferred embodiment of the multi-dimensional data model construction method for thermal power equipment according to the present invention, the hierarchical structure and specific attributes in the defined data model include, in the multi-level data abstraction model, the relationship between each layer is reflected through data flow and dependency. From the basic data layer to the feature layer, the basic data layer provides raw data, the feature layer extracts features through statistical analysis and feature extraction techniques, the feature layer inputs the extracted features into the indicator layer, the indicator layer generates calculation formulas based on the current features to calculate KPIs, and the indicator layer provides the calculated indicators to the visualization layer. Data transfer between each layer is ordered. Data in the first layer must be cleaned and verified before it can be transmitted to the second layer. After feature extraction in the second layer is completed, it is transmitted to the third layer for index calculation. Each layer is regarded as a state. Only after the state of the previous layer is verified as qualified can it enter the next layer. In practice, the deviation between the output of the detection index layer and the target layer is used to optimize data collection and feature selection by feeding it back to the basic data layer or feature layer.

[0011] As a preferred embodiment of the multidimensional data model construction method for thermal power equipment described in this invention, the dynamic update of data relationships includes generating an event notification when data in the data source is added, updated, or deleted. When an event is triggered, the event handling process begins. Based on the type of event, the system automatically parses the changes in the relationships between data and uses graph database technology to represent the data and relationships in the form of nodes and edges. If the data of any node is updated, the system retrieves the adjacent nodes of the current node and updates the attributes of the connecting edges of the current node. When real-time data is accessed, a stream processing framework is used to process the data stream in real time. When new data flows into the system, the data is standardized according to a preset format and stored in a temporary cache. When historical data backtracking analysis is needed, historical data is retrieved from the data lake and the relationship between data is re-evaluated according to a specific time window or condition.

[0012] As a preferred embodiment of the multi-dimensional data model construction method for thermal power equipment described in this invention, the data model for full life cycle management includes defining the life cycle stages of the equipment based on the usage characteristics of the thermal power equipment, including the design stage, manufacturing stage, operation and maintenance stage, and scrapping stage. Based on the characteristics of each lifecycle stage, predictive maintenance is adopted in the operation and maintenance stage. By combining real-time data with historical data, the possible failure time and type of equipment are predicted. The constructed multi-level data abstraction model provides support for decision-making at each stage. When the equipment has been running for a set number of hours, maintenance or inspection is automatically suggested, and the maintenance plan is optimized by combining historical damage data.

[0013] As a preferred embodiment of the multi-dimensional data model construction system for thermal power equipment described in this invention, it includes: a data collection module, a data processing and analysis module, a data storage and management module, a visualization and decision support module, and a dynamic update and feedback module; The data collection module is responsible for collecting basic and indicator data of thermal power equipment from various data sources in real time. The data processing and analysis module uses machine learning algorithms to perform in-depth analysis on the collected data, identify data relationships between different business areas, and construct a multi-level data abstraction model. The data storage and management module provides an efficient data storage architecture, ensuring data security and integrity through a hierarchical storage management model for various types of data. The visualization and decision support module transforms analysis results into decision information through visualization tools, providing intuitive data presentation and supporting management decisions. The dynamic update and feedback module is responsible for monitoring changes in the data source and adjusting the data model and data relationships in real time to ensure the flexibility and adaptability of the management system.

[0014] A computer device includes a memory and a processor, wherein the memory stores a computer program, characterized in that the processor executes the computer program to implement the steps of a method for constructing a multidimensional data model of thermal power equipment.

[0015] A computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of a method for constructing a multidimensional data model of thermal power equipment.

[0016] The beneficial effects of this invention are as follows: By employing advanced machine learning algorithms and graph database technology, dynamic association and management of multi-level data in thermal power equipment are achieved. Compared with existing technologies, our proposed multi-dimensional data model and system show significant improvements in data integration, real-time updates, and dynamic feedback. It effectively enhances the efficiency of comprehensive data utilization and provides strong support for refined management throughout the entire equipment lifecycle. Furthermore, by constructing a visual decision support module, it not only intuitively displays various key performance indicators (KPIs) but also predicts equipment performance trends and potential failures through intelligent analysis of historical data. This effectively extends equipment lifespan and operating efficiency, reduces maintenance costs, and brings significant economic and social benefits. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic flowchart of a method for constructing a multidimensional data model of thermal power equipment according to an embodiment of the present invention.

[0019] Figure 2 This is a schematic diagram of the working modules of a multi-dimensional data model construction system for thermal power equipment provided in one embodiment of the present invention. Detailed Implementation

[0020] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0023] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0024] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0025] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0026] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a method for constructing a multidimensional data model of thermal power equipment, including: S1: Collect basic and indicator data of thermal power equipment.

[0027] Furthermore, basic data includes equipment type (such as boiler, steam turbine, generator, etc.), manufacturer information, and operating parameters (such as rated power, circulation mode, water supply temperature, steam pressure, etc.). The aforementioned data include power generation efficiency (such as thermal efficiency, unit efficiency, etc.), failure rate (such as annual number of failures, average repair time, etc.), and operating time (such as continuous operating hours, annual operating time, etc.).

[0028] It should be noted that data should be categorized by type and source, and databases or spreadsheets should be created to facilitate data organization and analysis. Data should also be monitored and updated regularly based on updates and adjustments to equipment operation. S2: Use machine learning algorithms to identify data relationships between different business domains and build a multi-level data abstraction model.

[0029] Furthermore, we collect corresponding data including KKS codes, equipment codes, and spare parts codes, perform data cleaning to remove missing and duplicate values, and standardize text information. Define specifications for KKS codes, equipment codes, and spare parts codes. This includes the code format, length, composition, and the meaning of each part. Identify the data sources to be collected, such as historical databases, equipment manuals, maintenance records, etc., to ensure coding consistency. Before collecting data, ensure that codes across all data sources adhere to the same standard. This may involve reviewing and normalizing existing codes. Initiate naming conventions to maintain consistency during data storage, processing, and analysis. Design detailed coding rules for different types of data. KKS codes involve information such as process flow areas, equipment types, and serial numbers; document the coding rules for easy reference and updates.

[0030] The encoded data is converted into a vector representation. Word embedding is performed on the KKS encoding. An improved Skip-Gram model is used to convert each encoding into a high-dimensional vector representation. The same processing is performed on the equipment encoding and spare parts encoding. The enhanced Apriori algorithm is used to mine frequent itemsets between each type of encoding. By setting a minimum support threshold (S), new itemsets are generated iteratively, and the similarity of frequent itemsets is evaluated to enhance the association with different encodings.

[0031] An improved trust score calculation formula is used to evaluate the similarity of frequent itemsets, enhancing the association with different codes: ; in, The level of trust between A and B, The frequency of A and B appearing together. The frequency of A's occurrence. The weights are dynamically adjusted.

[0032] It should be noted that after the data collection and initial classification are completed, the hierarchy is defined, and the hierarchical structure of the data model is determined through expert interviews or collaboration with data scientists. The first layer is the basic data layer, which contains all the raw data. The second layer is the feature layer, which extracts features from the basic data. The third layer is the indicator layer, which summarizes the features to generate key performance indicators. The fourth layer is the visualization layer, which generates visual charts based on the indicators. Each layer of the management mechanism employs access control and data integrity checks, ensuring that each layer operates independently. When the underlying basic data changes, the application change log is synchronized to the upper layer data. A multi-layered data abstraction model is constructed, employing hierarchical storage and abstract interfaces to manage data at each layer, with each layer accessing data at the upper or lower layer through predefined interfaces.

[0033] Furthermore, each layer of the management mechanism employs access control and data integrity checks to ensure that each layer does not interfere with the others and to guarantee data security. When the underlying basic data changes, the application change log is synchronized to the upper-layer data to ensure data consistency.

[0034] S3: Define the hierarchical structure and specific attributes in the data model, as well as the relationships between the layers.

[0035] Furthermore, in a multi-layered data abstraction model, the relationships between layers are reflected through data flow and dependencies; From the basic data layer to the feature layer, the basic data layer provides raw data, the feature layer extracts features through statistical analysis and feature extraction techniques, the feature layer inputs the extracted features into the indicator layer, the indicator layer generates calculation formulas based on the current features to calculate KPIs, and the indicator layer provides the calculated indicators to the visualization layer. Data transfer between each layer is ordered. Data in the first layer must be cleaned and verified before it can be transmitted to the second layer. After feature extraction in the second layer is completed, it is transmitted to the third layer for index calculation. Each layer is regarded as a state. Only after the state of the previous layer is verified as qualified can it enter the next layer. In practice, the deviation between the output of the detection index layer and the target layer is used to optimize data collection and feature selection by feeding it back to the basic data layer or feature layer.

[0036] It should be noted that a hierarchical storage and abstract interface are used to manage data at each level, and each level accesses data at the upper or lower level through a predefined interface: Layer_1 --> Layer_2: Basic data updates trigger the data processing layer.

[0037] Layer_2 --> Layer_3: Data aggregation triggers metric updates.

[0038] Basic data classification (B): B = {b1, b2, ..., b} n}, where b i For each data item in the basic data, i=1……n, the basic data is calculated using the following formula: ; in, For the updated base data, As the original basic data, For dynamic rate of change, To change the amount, The standard deviation of the fluctuation of the basic data; Indicator data classification (I): I = {i1, i2, ..., i m}, where ij For each indicator, there is a function or formula, j=1……m, and the indicator data is calculated using the following formula: ; in, Let m be the number of data points, and m be the number of data points. As weight, For the k-th basic data value, This is the adjustment value for the indicator.

[0039] S4: Dynamically update data relationships to adapt to changes in data sources, forming a data model that supports the entire lifecycle management of devices.

[0040] Furthermore, event notifications are generated when data is added, updated, or deleted in the data source; When an event is triggered, the event handling process begins. Based on the type of event, the system automatically parses the changes in the relationships between data and uses graph database technology to represent the data and relationships in the form of nodes and edges. If the data of any node is updated, the system retrieves the adjacent nodes of the current node and updates the attributes of the connecting edges of the current node. When receiving real-time data, a stream processing framework is used for real-time data stream processing. As new data flows into the system, a data access pipeline is established by setting up a Kafka stream processing platform, through which all real-time data flows into the system. Upon data inflow, a data cleaning and standardization module performs format conversion, missing value handling, and outlier detection, along with standardization processing including data type conversion, normalization, and field merging to ensure the data format meets storage requirements. After cleaning, the standardized real-time data is cached and stored, and a multi-dimensional data view is created based on the needs of the real-time data.

[0041] When historical data retrospective analysis is required, historical data is retrieved from the data lake. Historical datasets are then filtered from the data lake based on timestamps or specific conditions. An adaptive time-series model is used to predict the impact of historical data on current data and the model, updating model parameters to adapt to the historical data. The association graph is regenerated based on changes in historical data to ensure the current model reflects the impact of past data. A dynamic reconstruction algorithm is employed to update the adjacency matrix. Version control is implemented for the analysis results and historical data records to support data recovery.

[0042] It should be noted that when a change in the data source is detected, an automatic update is performed. The event parsing module is used to analyze the triggered event type to determine whether it is an Add, Update, or Delete event. For each type, the ID, attributes, timestamp, and other information of the changed data are extracted to create a change record.

[0043] Set the changed data as Where ID is the data identifier and A is the attribute; For new data If the data is updated, it is directly added to the relationship graph as a new node. For updated data, the original data node is first searched. And update its attributes: ; To delete data, the corresponding node is removed from the graph and any association with other nodes is broken.

[0044] Once a change occurs, immediately evaluate other nodes associated with the original node. Use an adjacency matrix. To represent the relationships between the nodes in the graph: ; Then, for the updated node, modify the weight W of its adjacent edges: ; Where t is the time factor and f is the weighting function (such as the time decay function) to reflect the change in the strength of the relationship between the data and time.

[0045] Furthermore, based on the usage characteristics of thermal power equipment, the life cycle stages of the equipment are defined, including the design stage, manufacturing stage, operation and maintenance stage, and scrapping stage; Based on the characteristics of each lifecycle stage, predictive maintenance is adopted in the operation and maintenance stage. By combining real-time data with historical data, the possible failure time and type of equipment are predicted. The constructed multi-level data abstraction model provides support for decision-making at each stage. When the equipment has been running for a set number of hours, maintenance or inspection is automatically suggested, and the maintenance plan is optimized by combining historical damage data.

[0046] Example 2, the second embodiment of the present invention, differs from the previous two embodiments in that: If the aforementioned functions are implemented as 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 this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0047] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0048] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0049] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0050] Example 3, referring to Figure 2 As an embodiment of the present invention, a multi-dimensional data model construction system for thermal power equipment is provided, characterized in that it includes a data collection module, a data processing and analysis module, a data storage and management module, a visualization and decision support module, and a dynamic update and feedback module; The data collection module is responsible for collecting basic and indicator data of thermal power equipment from various data sources in real time. The data processing and analysis module uses machine learning algorithms to perform in-depth analysis of the collected data, identify data relationships between different business areas, and build a multi-level data abstraction model. The data storage and management module provides an efficient data storage architecture, ensuring data security and integrity through a hierarchical storage management model for various types of data. The visualization and decision support module uses visualization tools to transform analysis results into decision information, providing intuitive data presentation and supporting management decisions. The dynamic update and feedback module is responsible for monitoring changes in the data source and adjusting the data model and data relationships in real time to ensure the flexibility and adaptability of the management system.

[0051] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for constructing a multidimensional data model of thermal power equipment, characterized in that: include, Collect basic and performance data of thermal power equipment; Utilize machine learning algorithms to identify data relationships between different business domains and construct a multi-level data abstraction model; Define the hierarchical structure and specific attributes in the data model, as well as the relationships between the layers; Dynamically update data relationships to adapt to changes in data sources, forming a data model that supports the entire lifecycle management of devices.

2. The method for constructing a multidimensional data model of thermal power equipment as described in claim 1, characterized in that: The basic data includes equipment type, manufacturer, and operating parameters; The data metrics include power generation efficiency, failure rate, and operating time.

3. The method for constructing a multidimensional data model of thermal power equipment as described in claim 2, characterized in that: The machine learning algorithm includes collecting corresponding data containing KKS codes, equipment codes, and spare parts codes, cleaning the data, removing missing and duplicate values, and standardizing the text information. The encoded data is converted into a vector representation. Word embedding is performed on the KKS encoding. An improved Skip-Gram model is used to convert each encoding into a high-dimensional vector representation. The same processing is performed on the equipment encoding and spare parts encoding. The enhanced Apriori algorithm is used to mine frequent itemsets between each type of encoding. By setting a minimum support threshold (S), new itemsets are generated iteratively, and the similarity of frequent itemsets is evaluated to enhance the association with different encodings.

4. The method for constructing a multidimensional data model of thermal power equipment as described in claim 3, characterized in that: The construction of the multi-level data abstraction model includes defining the hierarchy after completing the collection and preliminary classification of data, and determining the hierarchical structure of the data model through expert interviews or collaboration with data scientists. The first layer is the basic data layer, which contains all the raw data. The second layer is the feature layer, which extracts features from the basic data. The third layer is the indicator layer, which summarizes the features to generate key performance indicators. The fourth layer is the visualization layer, which generates visual charts based on the indicators. Each layer of the management mechanism employs access control and data integrity checks, ensuring that each layer operates independently. When the underlying basic data changes, the application change log is synchronized to the upper layer data. A multi-layered data abstraction model is constructed, employing hierarchical storage and abstract interfaces to manage data at each layer, with each layer accessing data at the upper or lower layer through predefined interfaces.

5. The method for constructing a multidimensional data model of thermal power equipment as described in claim 4, characterized in that: The hierarchical structure and specific attributes in the defined data model include, in a multi-level data abstraction model, the relationships between each layer are reflected through data flow and dependencies. From the basic data layer to the feature layer, the basic data layer provides raw data, and the feature layer extracts features through statistical analysis and feature extraction techniques. The feature layer inputs the extracted features into the indicator layer, which then generates a calculation formula based on the current features to calculate the KPIs. The metrics layer provides the calculated metrics to the visualization layer; Data transfer between each layer is ordered. Data in the first layer must be cleaned and verified before it can be transmitted to the second layer. After feature extraction in the second layer is completed, it is transmitted to the third layer for index calculation. Each layer is regarded as a state. Only after the state of the previous layer is verified as qualified can it enter the next layer. In practice, the deviation between the output of the detection index layer and the target layer is used to optimize data collection and feature selection by feeding it back to the basic data layer or feature layer.

6. The method for constructing a multidimensional data model of thermal power equipment as described in claim 5, characterized in that: The dynamically updated data relationship includes generating an event notification when data in the data source is added, updated, or deleted; When an event is triggered, the event handling process begins. Based on the type of event, the system automatically parses the changes in the relationships between data and uses graph database technology to represent the data and relationships in the form of nodes and edges. If the data of any node is updated, the system retrieves the adjacent nodes of the current node and updates the attributes of the connecting edges of the current node. When real-time data is accessed, a stream processing framework is used to process the data stream in real time. When new data flows into the system, the data is standardized according to a preset format and stored in a temporary cache. When historical data backtracking analysis is needed, historical data is retrieved from the data lake and the relationship between data is re-evaluated according to a specific time window or condition.

7. The method for constructing a multidimensional data model of thermal power equipment as described in claim 6, characterized in that: The data model for the full life cycle management includes defining the life cycle stages of the equipment based on the usage characteristics of thermal power equipment, including the design stage, manufacturing stage, operation and maintenance stage, and scrapping stage; Based on the characteristics of each life cycle stage, predictive maintenance is adopted in the operation and maintenance stage. By combining real-time data with historical data, the possible failure time and type of equipment can be predicted. By utilizing a multi-level data abstraction model, support is provided for decision-making at each stage. When the equipment has run for a set number of hours, maintenance or inspection is automatically suggested, and maintenance plans are optimized by combining historical damage data.

8. A system employing a method for constructing a multidimensional data model of thermal power equipment as described in any one of claims 1 to 7, characterized in that: It includes modules for data collection, data processing and analysis, data storage and management, visualization and decision support, and dynamic updates and feedback. The data collection module is responsible for collecting basic and indicator data of thermal power equipment from various data sources in real time. The data processing and analysis module uses machine learning algorithms to perform in-depth analysis on the collected data, identify data relationships between different business areas, and construct a multi-level data abstraction model. The data storage and management module provides an efficient data storage architecture, ensuring data security and integrity through a hierarchical storage management model for various types of data. The visualization and decision support module transforms analysis results into decision information through visualization tools, providing intuitive data presentation and supporting management decisions. The dynamic update and feedback module is responsible for monitoring changes in the data source and adjusting the data model and data relationships in real time to ensure the flexibility and adaptability of the management system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images