Interactive multi-dimensional data analysis processing system and method

Abstract

The invention relates to the technical field of data analysis, and particularly discloses an interactive multi-dimensional data analysis processing system and method, and the system comprises an obtaining module which is used for obtaining the operation index data of each business link of the system, and determining a problem time window according to the operation index data of each business link of the system; the analysis module is used for establishing a topological graph according to the problem time window, searching abnormal nodes in the topological graph and determining problem service links according to the abnormal nodes in the topological graph; and the generation module is used for determining a corresponding abnormal event according to the problem service link and generating an interactive chart according to the problem service link and the corresponding abnormal event. According to the invention, the operation index data of the fuel power plant system can be analyzed and processed in real time, the problem business links of the system operation can be accurately found out, the interactive chart is generated, and a more agile data analysis result is provided for business personnel.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and more specifically, to an interactive multi-dimensional data analysis and processing system and method. Background Art

[0002] With the deep integration of informatization and industrialization, information technology and intelligent technologies have gradually penetrated every aspect of fuel cell power plants. Compared with the internet industry, the massive amount of system operation data accumulated by fuel cell power plants has a higher value density and higher mining value. Therefore, the analysis and processing of multi-dimensional data will become the core advantage and competitiveness of fuel cell power plants in future global competition.

[0003] Since massive amounts of system operation data are generated during the actual operation of a fuel power plant, and each piece of operation data is not independent of each other, when problems arise in the fuel power plant system during operation, it is impossible to accurately identify the business link where the problem occurs, and business personnel are unable to locate the problem node in a timely manner. Summary of the Invention

[0004] The present invention provides an interactive multi-dimensional data analysis and processing system and method to solve the problem in the prior art that the system operation data of fuel power plants cannot be accurately located when an anomaly occurs, including: The acquisition module is used to obtain the operating indicator data of each business link of the system and determine the problem time window based on the operating indicator data of each business link of the system; The analysis module is used to build a topology map based on the problem time window, find abnormal nodes in the topology map, and determine the problem business link based on the abnormal nodes in the topology map; The generation module is used to determine the corresponding abnormal events according to the problematic business links and generate interactive charts based on the problematic business links and the corresponding abnormal events.

[0005] Furthermore, the acquisition module determines the problem time window based on the operating indicator data of each business link of the system, including: Obtain historical operating indicator data for each link of the system and determine the importance of each link based on the historical operating indicator data; Determine the weight of each link according to its importance, and perform weighted summation of the operating index data based on the weight of each link to obtain the overall system operation index; Draw a total index change curve according to the change of the total index of system operation, obtain a preset sliding time window, and segment the total index change curve according to the preset sliding time window; The problematic time window is filtered out based on the curve segmentation results.

[0006] Furthermore, determining the importance of each link based on historical operating indicator data includes: Draw a historical operating indicator data change curve based on the changes in the historical operating indicator data within a preset period, obtain the system efficiency corresponding to the historical operating indicator data, and draw a system efficiency change curve based on the system efficiency corresponding to the historical operating indicator data; The correlation coefficient between the historical operating index data and the corresponding system efficiency is calculated based on the historical operating index data change curve and the corresponding system efficiency change curve. Each correlation coefficient is normalized and the normalized correlation coefficient is determined as the importance of the corresponding link.

[0007] Furthermore, the step of screening out problematic time windows according to the curve segmentation result includes: Obtain a preset standard total index, and calculate the difference between the preset standard total index and the system operation total index within each sliding time window; Determine whether the difference between the preset standard total index and the system operation total index in each sliding time window is less than a first preset threshold; if the difference between the preset standard total index and the system operation total index in each sliding time window is less than the first preset threshold, determine the corresponding sliding event window as a problematic time window; If the difference between the preset standard total index and the system operation total index in each sliding time window is greater than or equal to the first preset threshold, the corresponding sliding event window is determined as a normal time window.

[0008] Furthermore, the analysis module establishes a topology map according to the problem time window, including: Obtain the operating indicator data of all business links in the problem time window and calculate the correlation coefficient of any two operating indicator data; The operation indicator data with a correlation coefficient greater than the second preset threshold is screened out, each business link in the problem time window is used as a node, and the operation indicator data with a correlation coefficient greater than the second preset threshold is edge-connected to generate a topology graph.

[0009] Furthermore, the analysis module searches for abnormal nodes in the topology map and determines problematic business links based on the abnormal nodes in the topology map, including: Standardize the operating indicator data corresponding to each node in the topology diagram, obtain the preset standard indicator data, calculate the difference between the preset standard indicator data and the standardized operating indicator data, and obtain the abnormality degree of each node; The abnormal nodes in the topology diagram are determined according to the abnormality degree of each node, and the business links corresponding to the abnormal nodes are set as the problem business links.

[0010] Furthermore, the abnormal degree of each node determines the abnormal node in the topology graph, including: Obtain the correlation coefficient between the connected nodes in the topology graph, and determine the influence weight of the two connected nodes based on the correlation coefficient; The abnormality degree of the connected nodes is multiplied by the corresponding influence weight and then normalized to obtain the radiation degree of the connected nodes; Correct the abnormality degree of each node in the topology diagram according to the radiation degree of the connected nodes to obtain the corrected abnormality degree; Obtaining a preset abnormality tolerance value, and calculating the difference between the corrected abnormality and the abnormality tolerance value; Nodes whose difference between the corrected abnormality level and the abnormality tolerance value is greater than a third preset threshold are screened out as abnormal nodes in the topology graph.

[0011] Furthermore, the correction of the abnormality of each node in the topology diagram according to the radiation degree of the connected nodes includes: The abnormality degree of each node in the topology graph is corrected according to the abnormality degree correction formula. The abnormality degree correction formula is specifically: , in, is the corrected abnormality level, is the initial abnormality level, is the radiation degree of the nodes connected to this node, is the preset radiation level allowable value, is the preset range coefficient, is the natural exponential function.

[0012] Furthermore, the generation module determines corresponding abnormal events according to the problematic business links, and generates an interactive chart according to the problematic business links and the corresponding abnormal events, including: Obtain the system's historical operation logs and determine the historical abnormality level of the problem business link and the corresponding abnormal events based on the historical operation logs; Establish a training sample set based on the historical abnormality degree and the corresponding abnormal events, establish an initial abnormal event assessment model, train the initial abnormal event assessment model based on the training sample set, and obtain a trained abnormal event assessment model; Input the abnormality degree of the problem business link in the current topology map into the trained abnormal event assessment model to obtain the abnormal event of the problem business link; Generate interactive charts based on all problematic business links and corresponding abnormal events in the topology map.

[0013] In order to achieve the above object, the present invention further provides an interactive multi-dimensional data analysis and processing method, the method comprising: Obtain the operating indicator data of each business link of the system, and determine the problem time window based on the operating indicator data of each business link of the system; Create a topology map based on the problem time window, find abnormal nodes in the topology map, and determine the problem business link based on the abnormal nodes in the topology map; Determine the corresponding abnormal events based on the problematic business links, and generate interactive charts based on the problematic business links and the corresponding abnormal events.

[0014] The beneficial effects of the present invention are: By applying the above technical solutions, the present invention monitors the operating indicator data of each business link in the fuel power plant system in real time, promptly discovers abnormal situations in the system operation process, accurately finds the business links with problems by establishing a topology map, and establishes interactive charts to facilitate business personnel to locate abnormalities, providing business personnel with more agile data analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A schematic diagram of the structure of an interactive multi-dimensional data analysis and processing system proposed in an embodiment of the present invention is shown; Figure 2 The figure shows an overall flow chart of an interactive multi-dimensional data analysis and processing method proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0019] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0020] The present application embodiment provides an interactive multi-dimensional data analysis and processing system, such as Figure 1 As shown, including: The acquisition module is used to obtain the operating indicator data of each business link of the system and determine the problem time window based on the operating indicator data of each business link of the system; the analysis module is used to establish a topology map based on the problem time window, find abnormal nodes in the topology map, and determine the problem business link based on the abnormal nodes in the topology map; the generation module is used to determine the corresponding abnormal events based on the problem business link, and generate interactive charts based on the problem business link and the corresponding abnormal events.

[0021] In this embodiment, the operating indicator data of each business link in the fuel power plant are monitored in real time. The operating indicator data specifically include power generation, fuel consumption rate, system efficiency, emission level, maintenance cost, etc. The problem time window where the problem exists is found through each operating indicator data, and a topology map is established based on the problem time window to screen out the problem business link. An interactive chart is generated through the problem business link and the corresponding abnormal time. When an abnormal alarm occurs, the business personnel can jump to the corresponding abnormal event interface by clicking on the problem business link interface, which is convenient for the business personnel to handle the abnormal event.

[0022] In some embodiments of the present application, the acquisition module determines the problem time window based on the operating index data of each business link of the system, including: obtaining historical operating index data of each link of the system, and determining the importance of each link based on the historical operating index data; determining the weight value of each link based on the importance, and performing weighted summation of the operating index data based on the weight value of each link to obtain the system operation total index; drawing a total index change curve based on the change of the system operation total index, obtaining a preset sliding time window, and segmenting the total index change curve according to the preset sliding time window; and screening out the problem time window based on the curve segmentation result.

[0023] In this embodiment, the acquisition module assigns a weight value set to each business link of the system through historical operation indicator data, and performs weighted summation of the operation indicator data and the corresponding weight value through the weight value set to obtain the system operation total index, and screens out the problem time window through the change curve of the system operation total index.

[0024] In some embodiments of the present application, determining the importance of each link based on historical operating index data includes: drawing a historical operating index data change curve based on the changes in the historical operating index data within a preset time period, obtaining the system efficiency corresponding to the historical operating index data, and drawing a system efficiency change curve based on the system efficiency corresponding to the historical operating index data; calculating the correlation coefficient between the historical operating index data and the corresponding system efficiency based on the historical operating index data change curve and the corresponding system efficiency change curve, normalizing each correlation coefficient, and determining the normalized correlation coefficient as the importance of the corresponding link.

[0025] In this embodiment, the importance of the corresponding link is obtained by calculating the Pearson correlation coefficient between the historical operation index data and the corresponding system efficiency.

[0026] In some embodiments of the present application, the method of screening out problem time windows with problems based on the curve segmentation results includes: obtaining a preset standard total index, calculating the difference between the preset standard total index and the system operation total index in each sliding time window; judging whether the difference between the preset standard total index and the system operation total index in each sliding time window is less than a first preset threshold value, if the difference between the preset standard total index and the system operation total index in each sliding time window is less than the first preset threshold value, then determining the corresponding sliding event window as a problem time window with problems; if the difference between the preset standard total index and the system operation total index in each sliding time window is greater than or equal to the first preset threshold value, then determining the corresponding sliding event window as a normal time window.

[0027] In this embodiment, a preset standard total index is established to screen the total system operation index within the sliding time window, and sliding event windows with a difference less than a first preset threshold are screened out as problem time windows, and sliding event windows with a difference greater than or equal to the first preset threshold are screened out as normal time windows.

[0028] In some embodiments of the present application, the analysis module establishes a topological map based on the problem time window, including: obtaining the operating indicator data of all business links in the problem time window, and calculating the correlation coefficient of any two operating indicator data; screening out the operating indicator data with a correlation coefficient greater than a second preset threshold, taking each business link in the problem time window as a node, and connecting the operating indicator data with a correlation coefficient greater than the second preset threshold to generate a topological map.

[0029] In this embodiment, the nodes of each business link are edge-connected through the correlation coefficient of the operating indicator data of all business links in the problem time window to generate a topology map. The topology map can more intuitively analyze abnormal nodes with abnormalities, thereby finding the corresponding problem business link.

[0030] In some embodiments of the present application, the analysis module searches for abnormal nodes in the topology map and determines the problem business link based on the abnormal nodes in the topology map, including: standardizing the operating indicator data corresponding to each node in the topology map, obtaining preset standard indicator data, calculating the difference between the preset standard indicator data and the standardized operating indicator data, and obtaining the degree of abnormality of each node; determining the abnormal nodes in the topology map based on the degree of abnormality of each node, and setting the business link corresponding to the abnormal node as the problem business link.

[0031] In this embodiment, preset standard indicator data is established to calculate the abnormality degree of the node corresponding to the standardized operation indicator data, thereby screening out the corresponding abnormal nodes and locating the problematic business links.

[0032] In some embodiments of the present application, the abnormality degree of each node determines the abnormal nodes in the topological map, including: obtaining the correlation coefficient between the connected nodes in the topological map, and determining the influence weight of the two connected nodes based on the correlation coefficient; multiplying the abnormality degree of the connected nodes by the corresponding influence weight and then normalizing the result to obtain the radiation degree of the connected nodes; correcting the abnormality degree of each node in the topological map according to the radiation degree of the connected nodes to obtain the corrected abnormality degree; obtaining a preset abnormality degree tolerance value, and calculating the difference between the corrected abnormality degree and the abnormality degree tolerance value; screening out nodes whose difference between the corrected abnormality degree and the abnormality degree tolerance value is greater than a third preset threshold as abnormal nodes in the topological map.

[0033] In some embodiments of the present application, the step of correcting the abnormality of each node in the topological graph according to the radiation degree of the connected nodes includes correcting the abnormality of each node in the topological graph according to an abnormality correction formula, wherein the abnormality correction formula is specifically: , in, is the corrected abnormality level, is the initial abnormality level, is the radiation degree of the nodes connected to this node, is the preset radiation level allowable value, is the preset range coefficient, is the natural exponential function.

[0034] In this embodiment, the abnormality degree of each node is corrected by calculating the radiation degree of the connected nodes in the topology graph, and the abnormal nodes are screened out based on the corrected abnormality degree.

[0035] In some embodiments of the present application, the generation module determines the corresponding abnormal events based on the problem business link, and generates an interactive chart based on the problem business link and the corresponding abnormal events, including: obtaining the historical operation log of the system, determining the historical abnormality degree of the problem business link and the corresponding abnormal events based on the historical operation log; establishing a training sample set based on the historical abnormality degree and the corresponding abnormal events, establishing an initial abnormal event evaluation model, training the initial abnormal event evaluation model based on the training sample set, and obtaining a trained abnormal event evaluation model; inputting the abnormality degree of the problem business link in the current topology map into the trained abnormal event evaluation model to obtain the abnormal events of the problem business link; generating an interactive chart based on all the problem business links and the corresponding abnormal events in the topology map.

[0036] In this embodiment, an abnormal event assessment model is established to assess abnormal events in problematic business links, thereby generating an interactive chart so that business personnel can understand relevant abnormal information through the interactive chart.

[0037] Based on the same technical concept, such as Figure 2 As shown, the present invention also provides an interactive multi-dimensional data analysis and processing method, the method comprising: S101, obtaining the operating indicator data of each business link of the system, and determining the problem time window based on the operating indicator data of each business link of the system; S102, establishing a topology map based on the problem time window, finding abnormal nodes in the topology map, and determining the problem business link based on the abnormal nodes in the topology map; S103, determining corresponding abnormal events according to the problematic business links, and generating an interactive chart according to the problematic business links and the corresponding abnormal events.

[0038] By applying the above technical solution, the present invention comprises an acquisition module for acquiring operational indicator data for each business segment of the system and determining a problem time window based on the operational indicator data for each business segment of the system; an analysis module for establishing a topology map based on the problem time window, identifying abnormal nodes in the topology map, and determining the problem business segment based on the abnormal nodes in the topology map; and a generation module for determining corresponding abnormal events based on the problem business segment and generating interactive charts based on the problem business segment and the corresponding abnormal events. The present invention can perform real-time analysis and processing of operational indicator data for a fuel cell power plant system, accurately identifying the problem business segment of the system operation and generating interactive charts, providing business personnel with more agile data analysis results.

[0039] Through the above description of the embodiments, those skilled in the art will clearly understand that the present invention can be implemented via hardware or via software combined with a necessary general-purpose hardware platform. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product. This software product can be stored on a non-volatile storage medium (such as a CD-ROM, USB flash drive, or external hard drive) and includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute the methods described in various implementation scenarios of the present invention.

[0040] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An interactive multi-dimensional data analysis and processing system, characterized in that: include: The acquisition module is used to obtain the operating indicator data of each business link of the system and determine the problem time window based on the operating indicator data of each business link of the system; The analysis module is used to build a topology map based on the problem time window, find abnormal nodes in the topology map, and determine the problem business link based on the abnormal nodes in the topology map; The generation module is used to determine the corresponding abnormal events according to the problematic business links and generate interactive charts based on the problematic business links and the corresponding abnormal events.

2. The interactive multi-dimensional data analysis and processing system according to claim 1, characterized in that: The acquisition module determines the problem time window based on the operating indicator data of each business link of the system, including: Obtain historical operating indicator data for each link of the system and determine the importance of each link based on the historical operating indicator data; Determine the weight of each link according to its importance, and perform weighted summation of the operating index data based on the weight of each link to obtain the overall system operation index; Draw a total index change curve according to the change of the total index of system operation, obtain a preset sliding time window, and segment the total index change curve according to the preset sliding time window; The problematic time window is filtered out based on the curve segmentation results.

3. The interactive multi-dimensional data analysis and processing system according to claim 2, characterized in that: Determining the importance of each link based on historical operating indicator data includes: Draw a historical operating indicator data change curve based on the changes in the historical operating indicator data within a preset period, obtain the system efficiency corresponding to the historical operating indicator data, and draw a system efficiency change curve based on the system efficiency corresponding to the historical operating indicator data; The correlation coefficient between the historical operating index data and the corresponding system efficiency is calculated based on the historical operating index data change curve and the corresponding system efficiency change curve. Each correlation coefficient is normalized and the normalized correlation coefficient is determined as the importance of the corresponding link.

4. The interactive multi-dimensional data analysis and processing system according to claim 3, characterized in that: The method of screening out problematic time windows based on the curve segmentation results includes: Obtain a preset standard total index, and calculate the difference between the preset standard total index and the system operation total index within each sliding time window; Determine whether the difference between the preset standard total index and the system operation total index in each sliding time window is less than a first preset threshold; if the difference between the preset standard total index and the system operation total index in each sliding time window is less than the first preset threshold, determine the corresponding sliding event window as a problematic time window; If the difference between the preset standard total index and the system operation total index in each sliding time window is greater than or equal to the first preset threshold, the corresponding sliding event window is determined as a normal time window.

5. The interactive multi-dimensional data analysis and processing system according to claim 4, characterized in that: The analysis module establishes a topology map according to the problem time window, including: Obtain the operating indicator data of all business links in the problem time window and calculate the correlation coefficient of any two operating indicator data; The operation indicator data with a correlation coefficient greater than the second preset threshold is screened out, each business link in the problem time window is used as a node, and the operation indicator data with a correlation coefficient greater than the second preset threshold is edge-connected to generate a topology graph.

6. The interactive multi-dimensional data analysis and processing system according to claim 5, characterized in that: The analysis module searches for abnormal nodes in the topology map and determines problematic business links based on the abnormal nodes in the topology map, including: Standardize the operating indicator data corresponding to each node in the topology diagram, obtain the preset standard indicator data, calculate the difference between the preset standard indicator data and the standardized operating indicator data, and obtain the abnormality degree of each node; The abnormal nodes in the topology diagram are determined according to the abnormality degree of each node, and the business links corresponding to the abnormal nodes are set as the problem business links.

7. The interactive multi-dimensional data analysis and processing system according to claim 6, characterized in that: The abnormal degree of each node determines the abnormal node in the topology graph, including: Obtain the correlation coefficient between the connected nodes in the topology graph, and determine the influence weight of the two connected nodes based on the correlation coefficient; The abnormality degree of the connected nodes is multiplied by the corresponding influence weight and then normalized to obtain the radiation degree of the connected nodes; Correct the abnormality degree of each node in the topology diagram according to the radiation degree of the connected nodes to obtain the corrected abnormality degree; Obtaining a preset abnormality tolerance value, and calculating the difference between the corrected abnormality and the abnormality tolerance value; Nodes whose difference between the corrected abnormality level and the abnormality tolerance value is greater than a third preset threshold are screened out as abnormal nodes in the topology graph.

8. The interactive multi-dimensional data analysis and processing system according to claim 7, characterized in that: The correction of the abnormality of each node in the topology diagram according to the radiation degree of the connected nodes includes: The abnormality degree of each node in the topology graph is corrected according to the abnormality degree correction formula. The abnormality degree correction formula is specifically: ， in, is the corrected abnormality level, is the initial abnormality level, is the radiation degree of the nodes connected to this node, is the preset radiation level allowable value, is the preset range coefficient, is the natural exponential function.

9. The interactive multi-dimensional data analysis and processing system according to claim 8, characterized in that: The generation module determines corresponding abnormal events according to the problematic business links, and generates an interactive chart according to the problematic business links and the corresponding abnormal events, including: Obtain the system's historical operation logs and determine the historical abnormality level of the problem business link and the corresponding abnormal events based on the historical operation logs; Establish a training sample set based on the historical abnormality degree and the corresponding abnormal events, establish an initial abnormal event assessment model, train the initial abnormal event assessment model based on the training sample set, and obtain a trained abnormal event assessment model; Input the abnormality degree of the problem business link in the current topology map into the trained abnormal event assessment model to obtain the abnormal event of the problem business link; Generate interactive charts based on all problematic business links and corresponding abnormal events in the topology map.

10. An interactive multi-dimensional data analysis and processing method, characterized in that: The method comprises: Obtain the operating indicator data of each business link of the system, and determine the problem time window based on the operating indicator data of each business link of the system; Create a topology map based on the problem time window, find abnormal nodes in the topology map, and determine the problem business link based on the abnormal nodes in the topology map; Determine the corresponding abnormal events based on the problematic business links, and generate interactive charts based on the problematic business links and the corresponding abnormal events.

Images