CN114510517A - A data processing method and system for health management of large rotating units - Google Patents

Abstract

The invention provides a data processing method and system for health management of large-scale rotating units. The system includes a source data layer, a data detail layer, a data augmentation layer and an algorithm application display layer, which are respectively used to obtain the data of the rotating unit during the operation process. Running status data; perform data cleaning and repair processing on the obtained running status data, and obtain a data list; perform dimension expansion processing and dimension information matching processing on the running status data after cleaning and repair, and obtain the full amount of detailed data after dimension increase and information matching Wide table: For the running status data of each dimension in the wide table of full detailed data, match the corresponding deep learning algorithm model to perform data calculation and aggregated statistical analysis, and visualize the data calculation and aggregated statistical analysis results. Using the method and system of the present invention reduces the coupling of data in the deep learning algorithm, increases the reusability of intermediate data, and reduces the labor and time cost of data processing in the process of health management.

Description

A data processing method and system for health management of large rotating units

technical field

The invention relates to the technical field of equipment information monitoring and big data, in particular to a data processing method and system for health management of large-scale rotating units.

Background technique

With the increasing requirements for the safety and reliability of mechanical equipment, the importance of health management and intelligent operation and maintenance technology continues to increase, and the health management and intelligent operation and maintenance technology for large-scale rotating units develops rapidly. The intelligent operation and maintenance of large-scale rotating unit health management is to collect the operating process data of the rotating unit and use the deep learning method to predict the failure, life prediction and maintenance decision of the mechanical equipment. Traditional deep learning methods often have to go through tedious data processing processes to form a large amount of intermediate data. Health management intelligent operation and maintenance data has the characteristics of strong coupling, and it is difficult to reuse data for multiple algorithm models, resulting in a lot of labor and time costs. waste. Therefore, it is necessary to establish a data warehouse for the health management of large-scale rotating units, and to construct health management data with high reusability.

The traditional data warehouse adopts dimensional modeling, which is usually divided into data preparation layer, data detail layer, data summary layer, data mart layer, and data application layer. Traditional data warehouse domain modeling is often oriented to business processes for data stratification and statistical analysis for business needs, while the data required for intelligent operation and maintenance of large-scale rotating unit health management is mainly oriented to the different needs of different deep learning models. Therefore, traditional data The warehouse modeling method is difficult to apply in the intelligent operation and maintenance of the health management of large rotating units. It is necessary to establish a data warehouse for the intelligent operation and maintenance of the health management of large rotating units according to the characteristics of the intelligent operation and maintenance of the health management of large rotating units.

SUMMARY OF THE INVENTION

In view of the above-mentioned deficiencies of the prior art, the actual problem to be solved by the present invention is: how to deal with the data processing method and system for the intelligent operation and maintenance of the health management of large-scale rotating units, so as to solve the problems in the current intelligent operation and maintenance of the health management of rotating units. The data used has strong coupling, low data reuse rate, and high waste of manpower and time.

In order to solve the above-mentioned technical problems, the present invention adopts the following technical solutions:

A data processing method for health management of large-scale rotating units, comprising the following steps:

Step 1: Obtain the operating status data during the operation of the rotary unit;

Step 2: Perform data cleaning and repair processing on the obtained operating status data to obtain a detailed data table;

Step 3: Perform dimension expansion processing and dimension information matching processing on the running status data after cleaning and repair, to obtain a full detailed data wide table after dimension increase and information matching;

Step 4: For the running status data of each dimension in the full detailed data wide table, match the corresponding deep learning algorithm model to perform data calculation and aggregated statistical analysis, and visualize the data calculation and aggregated statistical analysis results.

In the above-mentioned data processing method for the health management of large-scale rotating units, preferably, the step 2 is specifically:

Perform data slicing processing on the obtained operating status data according to different data dimensions, and obtain data details of the operating status data in different data dimensions;

Perform data cleaning on the operating status data of each dimension to remove invalid data;

Perform abnormal data investigation on the running status data of each dimension, and repair the abnormal data found;

Sort out the running status data of each dimension after cleaning and repair, and obtain a detailed data table.

In the above-mentioned data processing method for the health management of large-scale rotating units, preferably, the step 3 is specifically:

Perform time-frequency analysis and parameter index extraction on the running status data after cleaning and repair, add the data dimension obtained by time-frequency analysis and the data dimension obtained by parameter index extraction to the data list, and perform dimension expansion processing to obtain dimension-enhancing data. wide table;

Match other devices associated with the running status data, and add the other device parameter information associated with the running status data as a new data dimension to the dimension-enhancing data wide table to obtain a full detailed data wide table.

In the above-mentioned data processing method for the health management of large-scale rotating units, preferably, the step 4 is specifically:

Read the running status data of each dimension from the full detailed data wide table, search for the matching deep learning algorithm model from the deep learning algorithm library for the running status data of each dimension, and then call the matching deep learning algorithm model to The running status data of each dimension is used for data calculation;

Perform aggregate statistical analysis on the data calculation results of the running status data of each dimension;

Visually display the data calculation results and aggregated statistical analysis results of the operating status data.

Correspondingly, the present invention provides a data processing system for the health management of large-scale rotating units, including a source data layer, a data detail layer, a data dimension augmentation layer and an algorithm application display layer;

The source data layer is used to store the acquired operating state data during the operation of the rotating unit;

The data detail layer is used to perform data cleaning and repair processing on the obtained operating status data to obtain a data detail table;

The data dimension augmentation layer is used to perform dimension expansion processing and dimension information matching processing on the running state data after cleaning and repair, so as to obtain a full detailed data wide table after dimension addition and information matching;

The algorithm application display layer is used to perform data calculation and aggregated statistical analysis on the running status data of each dimension in the full detailed data wide table, respectively matching the corresponding deep learning algorithm model, and visualize the data calculation and aggregated statistical analysis results. .

In the above-mentioned data processing system for health management of large-scale rotating units, preferably, the data detail layer includes a data slicing module, a data cleaning module, a data repairing module and a data sorting module;

The data slicing module is configured to perform data slicing processing on the obtained operating status data according to different data dimensions, and obtain data details of the operating status data in different data dimensions;

The data cleaning module is used to perform data cleaning processing on the operating status data of each dimension, and remove invalid data therein;

The data repair module is used to check the abnormal data of the running status data of each dimension, and repair the checked abnormal data;

The data sorting module is used for sorting the running status data of each dimension after cleaning and repairing to obtain a detailed data table.

In the above-mentioned data processing system for the health management of large-scale rotating units, preferably, the data dimension augmentation layer includes a signal processing module, an index extraction module and a dimension expansion module;

The signal processing module is used to perform time-frequency analysis on the running state data after cleaning and repairing;

The index extraction module is used for extracting parameter indexes for the running state data after cleaning and repairing;

The dimension expansion module is used to add the data dimension obtained by the time-frequency analysis and the data dimension obtained by the parameter index extraction into the data detailed table, carry out dimension expansion processing, and obtain the dimension-enhanced data wide table; and match the data related to the running state data. For other connected devices, the parameter information of other devices associated with the operating status data is added as a new data dimension to the dimension-enhancing data wide table to obtain a full detailed data wide table.

In the above-mentioned data processing system for the health management of large-scale rotating units, preferably, the algorithm application display layer includes a deep learning algorithm library module, an aggregation statistics module and a visualization module;

The deep learning algorithm library module is provided with a deep learning algorithm library, and the deep learning algorithm library stores a plurality of deep learning algorithm models that match the operating state data of the rotating unit in different dimensions; The full detailed data wide table reads the running state data of each dimension, searches for the matching deep learning algorithm model from the deep learning algorithm library for the running state data of each dimension, and then calls the matching deep learning algorithm model for each dimension. Dimension running state data for data calculation;

The aggregated statistics module is used to perform aggregated statistical analysis on the data calculation results of the operating status data of each dimension;

The visualization module is used to visualize the data calculation results and aggregated statistical analysis results of the operating status data.

Compared with the prior art, the beneficial effects of the present invention are:

1. The present invention is oriented to a data processing method and system for health management of large rotating units. The system includes a source data layer, a data detail layer, a data dimensionality layer and an algorithm application display layer, which are respectively used to obtain the operating status of the rotating unit during the operation process. Data; perform data cleaning and repair processing on the obtained operating status data to obtain a detailed data table; perform dimension expansion processing and dimension information matching processing on the operating status data after cleaning and repair to obtain a wide table of full detailed data after dimension increase and information matching ; For the running status data of each dimension in the full detailed data wide table, respectively match the corresponding deep learning algorithm model to carry out data calculation and aggregation statistical analysis, and visualize the data calculation and aggregation statistical analysis results; The data processing system for health management of large rotating units can store a large amount of operating data of rotating units into data sources according to different topics, which is convenient for calling data of different topics for health management analysis, which solves the problem of many data subject categories and complex data classification during the operation of large rotating units. The problem.

2. The present invention is oriented to the data processing system for the health management of large-scale rotating units. Through the system layering, the source data of the health management of large-scale rotating units is processed by data layering, so that the data at each layer can be multiplexed, and each layer can be reused. The system layers can also run in parallel, which solves the problem of strong data coupling in the intelligent operation and maintenance of large-scale rotating unit health management, and reduces the time and labor costs for processing source data.

3. In the data processing method and system for the health management of large rotating units of the present invention, the data required by the deep learning algorithm model is matched in multiple dimensions, so as to obtain the data required by the algorithm for calculation. Traditional data warehouses are usually only based on business The process performs data stratification and aggregation statistics instead of data stratification according to a specific deep learning model. Therefore, this method solves and systematically solves the problem of matching the data with the deep learning algorithm for calculation in the intelligent operation and maintenance process of the health management of large-scale rotating units, which is more efficient. It is suitable for intelligent operation and maintenance of rotating unit health management.

Description of drawings

In order to make the purpose, technical solutions and advantages of the invention clearer, the present invention will be described in further detail below in conjunction with the accompanying drawings, wherein:

FIG. 1 is a flow chart of a data processing method for health management of large-scale rotating units according to the present invention.

FIG. 2 is a structural diagram of a data processing system for health management of large-scale rotating units according to the present invention.

FIG. 3 is an exemplary diagram of an embodiment of the data processing system for health management of large-scale rotating units according to the present invention.

Detailed ways

The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

The method for intelligent operation and maintenance data processing for the health management of large-scale rotating units proposed by the present invention solves the problems of strong data coupling, low data reuse rate, and high time and labor consumption in the process of rotating unit health management by different deep learning model algorithms. question.

As shown in FIG. 1 , the data processing method for the health management of large-scale rotating units of the present invention includes the following steps:

Step 1: Obtain the operating status data during the operation of the rotary unit.

Step 2: Perform data cleaning and repair processing on the obtained operating status data to obtain a detailed data table.

Step 3: Perform dimension expansion processing and dimension information matching processing on the running state data after cleaning and repair, to obtain a full detailed data wide table after dimension increase and information matching.

Step 4: For the running status data of each dimension in the full detailed data wide table, match the corresponding deep learning algorithm model to perform data calculation and aggregated statistical analysis, and visualize the data calculation and aggregated statistical analysis results.

Correspondingly, as shown in FIG. 2 , the present invention also provides a data processing system for the health management of large-scale rotating units, including a source data layer, a data detail layer, a data dimension augmentation layer and an algorithm application display layer;

The source data layer is used to store the obtained operating state data during the operation of the rotating unit;

The data detail layer is used to perform data cleaning and repair processing on the obtained operating status data to obtain a data detail table;

The data dimension augmentation layer is used to perform dimension expansion processing and dimension information matching processing on the running state data after cleaning and repair, and obtain a full detailed data wide table after dimension addition and information matching;

The algorithm application display layer is used to perform data calculation and aggregated statistical analysis on the running status data of each dimension in the wide table of full detailed data, respectively match the corresponding deep learning algorithm model, and visualize the results of data calculation and aggregated statistical analysis.

First, import the data collected during the operation of the large rotating unit into the source data layer to obtain the original data fact table. Source data refers to the equipment operating status data obtained by different collection methods during the operation of the rotating unit. The data sources of large-scale rotating units are divided into various topics, such as vibration data of CMS (Condition Monitoring System, wind turbine condition monitoring system), SCADA (Supervisory Control And Data Acquisition, data acquisition and monitoring control system) monitoring data, etc., different subject source data have different data processing methods, which also correspond to different deep learning algorithms. As shown in FIG. 3 , this embodiment introduces CMS vibration data as the subject object.

The source data layer is used to store source data. For example, CMS vibration data is the most common data during the operation of rotating units. The vibration data contains a variety of different dimensions, such as wind farm name, fan number, gear box number, measuring point, Point type, sampling time, etc. are imported into the source data layer according to the multi-dimensional statistical CMS vibration data fact table.

The data detail layer mainly preprocesses the data, including data slicing, data cleaning, data repairing, etc. The corresponding functional modules include data slicing module, data cleaning module and data repairing module. CMS data has the characteristics of high collection frequency and large amount of data, so it is necessary to call the data slicing module at the data detail layer to slice it, and the sliced data can be better applied to deep learning.

Specifically, the data detail layer includes a data slicing module, a data cleaning module, a data repairing module and a data sorting module;

The data slicing module is configured to perform data slicing processing on the obtained operating status data according to different data dimensions, and obtain data details of the operating status data in different data dimensions;

The data cleaning module is used to perform data cleaning processing on the operating status data of each dimension, and remove invalid data therein;

The data repair module is used to check the abnormal data of the running status data of each dimension, and repair the checked abnormal data;

The data sorting module is used for sorting the running status data of each dimension after cleaning and repairing to obtain a detailed data table.

Different modules in the data detail layer can be called separately for different thematic data characteristics and different data cleaning and repairing requirements.

Therefore, step 2 of the data processing method for the health management of large-scale rotating units of the present invention is specifically: performing data slicing processing on the obtained operating state data according to different data dimensions, and obtaining data details of the operating state data in different data dimensions; Perform data cleaning on the running status data of the dimension to remove invalid data; check the abnormal data of the running status data of each dimension, and repair the abnormal data found; clean and repair the running status of each dimension The data is organized to obtain a data schedule.

The data dimension augmentation layer mainly further processes the data of the data detail layer according to the requirements of the deep learning algorithm, including signal processing, index extraction, dimension table matching, etc. for dimension expansion. The modules included include signal processing module, index extraction module, Dimension extension modules, etc. For example, since deep learning model algorithms have different dimensional requirements for CMS vibration signals, it is necessary to adopt multiple processing methods for CMS data to meet the needs of different deep learning algorithms.

Specifically, the data augmentation layer includes a signal processing module, an indicator extraction module and a dimension expansion module;

The signal processing module is used to perform time-frequency analysis on the running state data after cleaning and repairing;

The index extraction module is used to extract the parameter index of the running state data after cleaning and repair;

The dimension expansion module is used to add the data dimensions obtained by the time-frequency analysis and the data dimensions extracted from the parameter indicators to the data detailed table, perform dimension expansion processing, and obtain the dimension-enhanced data wide table; and match the data associated with the running status data. For other devices, the parameter information of other devices associated with the running status data is added as a new data dimension to the dimension-enhancing data wide table to obtain a full detailed data wide table.

Therefore, step 3 of the data processing method for the health management of large-scale rotating units of the present invention is specifically: performing time-frequency analysis and parameter index extraction on the operating state data after cleaning and repairing, and extracting the data dimensions and parameter indexes obtained by the time-frequency analysis. All data dimensions are added to the data detail table, and dimension expansion processing is performed to obtain a wide table of dimension-enhanced data; other devices associated with the running status data are matched, and the parameter information of other devices associated with the running status data is used as new data. Dimension, add it to the dimension-enhancing data wide table to get the full detailed data wide table.

For example, for CMS vibration data, the signal processing module needs to be called first to perform time-frequency analysis and processing on the CMS vibration data, including time-frequency analysis methods such as wavelet packet transform and envelope. Different signal time-frequency analysis and processing methods represent a dimension of the fact table , add the signal data processed by signal time-frequency analysis to the fact table of the data detail layer according to different dimensions to form a data augmentation table; then, extract the parameter indicators for the augmented fact table that has undergone signal processing, and call the index extraction The module index extraction method performs parameter index extraction processing on the aforementioned data dimension augmentation table, and obtains data including kurtosis, slope, mean and other data. Different indices represent one dimension, and the index data extracted by the indices is added to the aforementioned data dimension augmentation table. Continue Expand the dimension of the fact table; finally, the dimension-enhanced data wide table obtained from the above-mentioned dimension-enhanced fact table needs to be expanded by the dimension to obtain the full detailed data wide table with comprehensive information, and the dimension table in the dimension expansion module is called for the above The dimension-enhancing data wide table is used for dimension expansion, matching other equipment associated with the operating status data, and extracting other equipment parameter information associated with the operating status data. Since the CMS vibration signal is closely related to the gear box, the gear box can be The box dimension table matches the fact table of the aforementioned CMS operating status data, and the parameter information of the gearbox, such as the name of the gearbox and other mapping information, is used as a new data dimension and added to the above-mentioned dimension-enhancing data width table to form a full detailed data width. surface.

The algorithm application display layer mainly uses the deep learning algorithm in the algorithm module, which matches the above-mentioned full detailed fact wide table, that is, each algorithm needs to specify the data dimension information to be matched, that is, the algorithm dimension table needs to include the wind field number. , fan number, measuring point information, sensor code, sampling frequency, slice length, signal processing method, required indicators and other dimensions, and also need to include the address of the algorithm for calling.

Specifically, the algorithm application display layer includes a deep learning algorithm library module, an aggregation statistics module and a visualization module;

The deep learning algorithm library module is provided with a deep learning algorithm library, and the deep learning algorithm library stores a plurality of deep learning algorithm models that match the operating state data of the rotating unit in different dimensions; the deep learning algorithm library module is used for full details. The data wide table reads the running status data of each dimension, searches for the matching deep learning algorithm model from the deep learning algorithm library for the running status data of each dimension, and then calls the matching deep learning algorithm model for each dimension. Running state data for data calculation;

The aggregated statistics module is used to perform aggregated statistical analysis on the data calculation results of the running status data of each dimension;

The visualization module is used to visualize the data calculation results and aggregated statistical analysis results of the running state data.

Therefore, step 4 of the data processing method for the health management of large-scale rotating units of the present invention is specifically as follows: reading the operating state data of each dimension from the full detailed data wide table, and obtaining the operating state data for each dimension from the deep learning algorithm library. Find the matching deep learning algorithm model, so as to call the matching deep learning algorithm model to perform data calculation on the running state data of each dimension; perform aggregate statistical analysis on the data calculation results of the running state data of each dimension; The data calculation results and aggregated statistical analysis results of the operating status data are displayed visually.

In the specific implementation, the algorithm dimension table in the deep learning algorithm library module needs to be maintained manually. When the different deep learning algorithm models in the deep learning algorithm library module match the data dimensions in the full data detail table one by one, the corresponding data can be obtained. , when using deep learning test data, the accuracy of the test model is often calculated multiple times to obtain an average value, and the calculation results of various methods are compared. Therefore, it is necessary to aggregate and summarize the calculation results of deep learning, and Visualize the display.

To sum up, the present invention is oriented to the data processing system for the health management of large-scale rotating units. Through the system layering, the source data of the health management of large-scale rotating units is processed by data layering, so that the data at each layer can be multiplexed for multiple times. , and each system layer can also be run in parallel, which solves the problem of strong data coupling in the process of intelligent operation and maintenance of large-scale rotating unit health management, and reduces the time and labor cost of processing source data; at the same time, the method and system of the present invention are , the data required by the deep learning algorithm model is matched in multiple dimensions, so as to obtain the data required by the algorithm for calculation. Traditional data warehouses usually only perform data stratification and aggregation statistics according to business processes instead of data according to specific deep learning models. Therefore, this method solves and systematically solves the problem of matching data and deep learning algorithms for calculation in the process of intelligent operation and maintenance of health management of large rotating units, and is more suitable for intelligent operation and maintenance of health management of rotating units.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described with reference to the preferred embodiments of the present invention, those of ordinary skill in the art should Various changes in the above and in the details may be made therein without departing from the spirit and scope of the present invention as defined by the appended claims.

Claims (8)

1. A data processing method for health management of a large-scale rotating unit is characterized by comprising the following steps:

step 1: acquiring running state data of a rotating unit in a running process;

step 2: carrying out data cleaning and repairing treatment on the obtained running state data to obtain a data list;

and step 3: carrying out dimension expansion processing and dimension information matching processing on the cleaned and repaired running state data to obtain a full detailed data wide table after dimension increasing and information matching;

and 4, step 4: and respectively matching the running state data of each dimensionality in the full detail data wide table with the corresponding deep learning algorithm model to perform data calculation and aggregate statistical analysis, and visually displaying the data calculation and aggregate statistical analysis results.

2. The data processing method for health management of the large-scale rotating unit according to claim 1, wherein the step 2 specifically comprises:

performing data slicing processing on the obtained running state data according to different data dimensions to obtain data details of the running state data in different data dimensions;

carrying out data cleaning processing on the running state data of each dimension to remove invalid data in the running state data;

abnormal data investigation is carried out on the running state data of each dimension, and the investigated abnormal data is repaired;

and sorting the operation state data of each dimension after cleaning and repairing to obtain a data detail table.

3. The data processing method for health management of the large-scale rotating unit according to claim 1, wherein the step 3 specifically comprises:

performing time-frequency analysis and parameter index extraction on the cleaned and repaired running state data, adding data dimensionality obtained by the time-frequency analysis and data dimensionality obtained by the parameter index extraction into the data detail table, and performing dimensionality extension processing to obtain a dimensionality data wide table;

and matching other equipment associated with the operation state data, and adding other equipment parameter information associated with the operation state data into the dimension-increased data width table as a new data dimension to obtain a full detailed data width table.

4. The data processing method for health management of the large-scale rotating machine set according to claim 1, wherein the step 4 is specifically:

reading the running state data of each dimension from the full detail data wide table, and respectively searching a matched deep learning algorithm model from a deep learning algorithm library aiming at the running state data of each dimension, so as to call the matched deep learning algorithm model to respectively perform data calculation on the running state data of each dimension;

respectively carrying out aggregate statistical analysis on the data calculation results of the running state data of each dimension;

and visually displaying the data calculation result and the aggregation statistical analysis result of the running state data.

5. A data processing system for health management of a large-scale rotating unit is characterized by comprising a source data layer, a data detail layer, a data dimension increasing layer and an algorithm application display layer;

the source data layer is used for storing the acquired running state data of the rotating unit in the running process;

the data detail layer is used for carrying out data cleaning and repairing treatment on the obtained running state data to obtain a data detail table;

the data dimension increasing layer is used for performing dimension expanding processing and dimension information matching processing on the cleaned and repaired running state data to obtain a full detailed data wide table after dimension increasing and information matching;

the algorithm application display layer is used for matching the running state data of each dimensionality in the full-detail data wide table with the corresponding deep learning algorithm model respectively to perform data calculation and aggregate statistical analysis, and performing visual display on data calculation and aggregate statistical analysis results.

6. The data processing system for health management of large-scale rotating units according to claim 5, wherein the data detail layer comprises a data slicing module, a data cleaning module, a data repairing module and a data sorting module;

the data slicing module is used for carrying out data slicing processing on the obtained running state data according to different data dimensions to obtain data details of the running state data in different data dimensions;

the data cleaning module is used for cleaning the data of the running state data of each dimension and removing invalid data in the running state data;

the data restoration module is used for performing abnormal data investigation on the running state data of each dimension and restoring the investigated abnormal data;

the data sorting module is used for sorting the operation state data of each dimensionality after cleaning and repairing to obtain a data detail table.

7. The data processing system for health management of the large-scale rotating units according to claim 5, wherein the data dimension increasing layer comprises a signal processing module, an index extraction module and a dimension expansion module;

the signal processing module is used for performing time-frequency analysis on the cleaned and repaired running state data;

the index extraction module is used for extracting parameter indexes of the cleaned and repaired running state data;

the dimension expansion module is used for adding the data dimension obtained by time-frequency analysis and the data dimension obtained by parameter index extraction into the data detail table, and performing dimension expansion processing to obtain a dimension-increased data wide table; and matching other devices associated with the operation state data, and adding parameter information of other devices associated with the operation state data into the dimension-increased data width table as a new data dimension to obtain a full detailed data width table.

8. The data processing system for health management of large rotating units according to claim 5, wherein the algorithm application display layer comprises a deep learning algorithm library module, an aggregation statistical module and a visualization module;

the deep learning algorithm library module is provided with a deep learning algorithm library, and a plurality of deep learning algorithm models matched with running state data of different dimensions of the rotating unit are stored in the deep learning algorithm library; the deep learning algorithm library module is used for reading the running state data of each dimension from the full detailed data wide table, and searching a matched deep learning algorithm model from the deep learning algorithm library aiming at the running state data of each dimension, so that the matched deep learning algorithm model is called to perform data calculation on the running state data of each dimension;

the aggregation statistical module is used for respectively carrying out aggregation statistical analysis on the data calculation results of the running state data of each dimension;

the visualization module is used for visually displaying the data calculation result and the aggregation statistical analysis result of the running state data.

Images