Lightweight operation and maintenance fault handling method and device

Abstract

The present invention provides a lightweight operation and maintenance fault handling method and device. The method includes: after the operation and maintenance end sends an operation and maintenance monitoring request, determining the production workshop corresponding to the workshop number and creating a workshop model space; obtaining the equipment log of each equipment unit to extract data, hierarchically classifying the operation data corresponding to different operation dimensions in the same equipment log to obtain each operation data tree diagram; determining the equipment status of each equipment unit, and dividing the workshop model space based on the equipment height of each equipment unit; establishing each log indication unit corresponding to each equipment unit in the upper model space, and each log indication unit has a link relationship with the corresponding operation data tree diagram; when the operation and maintenance end interacts with any log indication unit, the log indication unit is subjected to unit changes based on the equipment status, and the operation data tree diagram with a link relationship with the log indication unit is retrieved for display. The present invention at least improves monitoring efficiency.

Description

Technical Field

[0001] The present invention relates to data processing technology, and in particular to a lightweight operation and maintenance fault processing method and device. Background Art

[0002] There are many production equipment in the production workshop. The good or bad status of the production equipment greatly affects the production efficiency of the production workshop. If the corresponding status of the production equipment can be monitored in real time, the faulty production equipment can be dealt with in time to ensure a certain production efficiency.

[0003] The inventors found in their research that the current status detection of production equipment is mostly performed manually, which wastes a certain amount of manpower and may not promptly detect faulty production equipment, affecting the production efficiency of the production workshop. Summary of the Invention

[0004] Based on the above problems, the present invention is proposed to provide a lightweight operation and maintenance fault handling method and device that overcomes the above problems or at least partially solves the above problems.

[0005] According to one aspect of the present invention, a lightweight operation and maintenance fault handling method is provided, comprising the following steps:

[0006] In response to an operation and maintenance monitoring request sent by the operation and maintenance end and carrying a workshop number, determine the production workshop corresponding to the workshop number, and create a workshop model space corresponding to the production workshop based on digital twin technology;

[0007] Obtaining each equipment log corresponding to each equipment unit located in the workshop model space, extracting data from each equipment log, and hierarchically classifying the extracted operation data corresponding to different operation dimensions located in the same equipment log to obtain a tree diagram of each operation data corresponding to each equipment log;

[0008] Determining the equipment status corresponding to each equipment unit based on each operation data tree diagram, and dividing the workshop model space horizontally based on the equipment heights of each equipment unit in the vertical direction to obtain a lower model space and an upper model space containing each equipment unit;

[0009] Establishing log indication units corresponding to the equipment units in the upper model space, wherein each log indication unit has a link relationship with the corresponding operation data tree diagram;

[0010] In response to the operation and maintenance end interacting with any log indication unit, the log indication unit is changed based on the corresponding device status, and an operation data tree diagram having a link relationship with the log indication unit is retrieved for display.

[0011] Optionally, in the method according to the present invention, hierarchical classification is performed based on the extracted operation data corresponding to different operation dimensions in the same device log to obtain a tree diagram of each operation data corresponding to each device log, including:

[0012] Creating a blank fill layer, and establishing a device node model corresponding to the device unit in the blank fill layer;

[0013] Obtaining each operation dimension in the same device log, and establishing dimension node models corresponding to different operation dimensions along the device node model;

[0014] Determine whether there is a dimension association relationship between the operating dimensions, and divide the operating dimensions that have the same dimension association relationship with each other into the same associated dimension group, and divide the operating dimensions that do not have a dimension association relationship into independent dimension groups, thereby obtaining associated dimension groups and independent dimension groups;

[0015] Determine each piece of operating data corresponding to each operating dimension in the same associated dimension group, and perform data association on each piece of operating data to obtain each piece of associated data corresponding to each associated dimension group;

[0016] Establishing association node models corresponding to associated data along each dimension node model corresponding to each operating dimension in the same associated dimension group, and establishing independent node models corresponding to each operating data along each dimension node model corresponding to each operating dimension in the independent dimension group;

[0017] Based on the preset anomaly verification strategy, each associated data and each operating data is respectively checked for anomalies, and each associated verification result corresponding to each associated data and each independent verification result corresponding to each operating data are determined;

[0018] First verification node models corresponding to the respective associated verification results are established downward along the associated node models, and second verification node models corresponding to the respective independent verification results are established downward along the independent node models.

[0019] Optionally, in the method according to the present invention, determining whether there is a dimension association relationship between the operating dimensions, and grouping the operating dimensions corresponding to each other and having the same dimension association relationship into the same association dimension group includes:

[0020] Retrieving a preset correlation comparison layer, wherein the preset correlation comparison layer includes a correlation coordinate table populated in a first area and a point comparison table populated in a second area, the correlation coordinate table including two sets of dimensional points extending along an X-axis and a Y-axis, respectively, and having the same arrangement order, and the point comparison table including coordinates of each point and a correlation coefficient corresponding to each point coordinate;

[0021] Determine each operating dimension as a primary dimension in turn, and determine all other operating dimensions as secondary dimensions;

[0022] Taking the primary dimension as the horizontal coordinate point and the secondary dimension as the vertical coordinate point, determine the dimensional points between the same primary dimension and the different secondary dimensions in the association coordinate table, and determine the correlation coefficients between the same primary dimension and the different secondary dimensions in the point comparison table based on the point coordinates corresponding to the point of each dimension;

[0023] Determine that the primary dimension and the secondary dimension corresponding to the correlation coefficient greater than the preset coefficient have a dimension correlation relationship, and classify the two into the same correlation dimension group;

[0024] Inverting the primary and secondary dimensions corresponding to the correlation coefficients less than the preset coefficients, determining the inverted points corresponding to the dimension points at the correlation coordinate points, and determining the correlation coefficients between the primary and secondary dimensions after the inversion in the point comparison table based on the point coordinates corresponding to the inverted points;

[0025] The primary dimension and the secondary dimension after the inversion of primary and secondary whose corresponding correlation coefficient is greater than the preset coefficient are determined to have a dimension correlation relationship, and the two are divided into the same correlation dimension group.

[0026] Optionally, in the method according to the present invention, determining each piece of operating data corresponding to each operating dimension in the same associated dimension group, and performing data association on each piece of operating data to obtain each piece of associated data corresponding to each associated dimension group, includes:

[0027] Determining a data collection period corresponding to the operating data, and dividing the data collection period into a preset number of time periods to obtain each data collection period;

[0028] Determine the operating data corresponding to the main-level dimension in the associated dimension group as the main-level data, and divide the main-level data based on each data collection period to obtain main-level period data corresponding to each data collection period;

[0029] Taking the retrieved reference period data as the sequence starting point, the main period data are arranged in chronological order based on each data collection period to obtain the main sequence;

[0030] Determining two time period data between adjacent positions in the main-level sequence as main-level data intervals, thereby obtaining main-level data intervals corresponding to the main-level sequence;

[0031] Determine the operating data corresponding to the secondary dimension in the associated dimension group as secondary data, and divide the secondary data based on each primary data interval to obtain secondary interval values ​​corresponding to each primary data interval;

[0032] Each data collection period, each primary data interval, and each secondary interval value are determined as each associated data corresponding to each associated dimension group.

[0033] Optionally, in the method according to the present invention, performing abnormality checks on each associated data and each operating data based on a preset abnormality check strategy, and determining each associated check result corresponding to each associated data and each independent check result corresponding to each operating data, including:

[0034] Retrieving each abnormality verification data configured by the operation and maintenance end based on each different operation dimension, wherein each abnormality verification data includes an abnormality comparison value and an abnormality trend value;

[0035] Group each abnormality verification data based on each associated dimension group and the independent dimension group to obtain each associated verification group corresponding to each associated dimension group and each independent verification group corresponding to the independent dimension group;

[0036] Performing numerical verification on each associated data based on each abnormal comparison value in each associated verification group, and performing numerical verification on each operating data based on each abnormal comparison value in the independent verification group, to obtain each first associated verification result corresponding to each associated data, and each first independent verification result corresponding to each operating data;

[0037] Perform trend checks on each associated data based on each abnormal trend value in each associated verification group, and perform trend checks on each operating data based on each abnormal trend value in the independent verification group, to obtain each second associated verification result corresponding to each associated data, and each second independent verification result corresponding to each operating data;

[0038] When the first association verification result and the second association verification result corresponding to the same association data are both normal, the association verification result of the association data is determined to be in a normal state;

[0039] When either the first association verification result or the second association verification result corresponding to the same association data is abnormal, determining the association verification result of the association data as an abnormal state;

[0040] When the second independent verification result and the second independent verification result corresponding to the same operating data are both normal, the independent verification result of the operating data is determined to be normal;

[0041] When either the first independent verification result or the second independent verification result corresponding to the same operation data is abnormal, the independent verification result of the operation data is determined to be in an abnormal state.

[0042] Optionally, in the method according to the present invention, numerical verification is performed on each associated data based on each abnormal comparison value in each associated verification group, and numerical verification is performed on each operating data based on each abnormal comparison value in the independent verification group, to obtain each first associated verification result corresponding to each associated data and each first independent verification result corresponding to each operating data, including:

[0043] Compare the main-level time period data corresponding to the same associated dimension group with the corresponding abnormal comparison value, and determine the first associated verification result of the associated data corresponding to any main-level time period data greater than the abnormal comparison value as the verification abnormality, and determine the associated dimension group corresponding to all main-level time period data less than or equal to the abnormal comparison value as the secondary value verification collection;

[0044] Compare each secondary interval value corresponding to the same associated dimension group in the secondary value verification collection with the corresponding abnormal comparison value, and determine the first associated verification result of the associated data corresponding to any secondary interval value greater than the abnormal comparison value as an abnormal verification, and determine the first associated verification result of the associated data corresponding to all secondary interval values ​​less than or equal to the abnormal comparison value as normal verification;

[0045] Divide each operating data into data based on each data collection period to obtain each operating time period data corresponding to each data collection period;

[0046] Compare each operating time period data corresponding to the same operating data with the corresponding abnormal comparison value, and determine the first independent verification result of the operating data corresponding to any operating time period data that is greater than the abnormal comparison value as the verification abnormality, and determine the first independent verification result of the operating data corresponding to all operating time period data that is less than or equal to the abnormal comparison value as the verification normal.

[0047] Optionally, in the method according to the present invention, trend verification is performed on each associated data based on each abnormal trend value in each associated verification group, and trend verification is performed on each operating data based on each abnormal trend value in the independent verification group, to obtain each second associated verification result corresponding to each associated data and each second independent verification result corresponding to each operating data, including:

[0048] Calculate the difference between adjacent positions of each main-level time period data corresponding to the same associated dimension group to obtain each main-level difference, and compare each main-level difference with the corresponding abnormal trend value;

[0049] Determine the first correlation verification result of the correlation data corresponding to any main level difference value greater than the abnormal trend value as the verification abnormality, and determine the correlation dimension group corresponding to all main level difference values ​​less than or equal to the abnormal comparison value as the secondary trend verification collection;

[0050] Calculate the difference between adjacent secondary interval values ​​corresponding to the same associated dimension group in the secondary trend verification collection, and compare the obtained secondary difference values ​​with the corresponding abnormal trend values;

[0051] Determine the second correlation check result of the correlation data corresponding to any secondary difference value greater than the abnormal trend value as abnormal verification, and determine the correlation data corresponding to all secondary difference values ​​less than or equal to the abnormal trend value as normal verification;

[0052] Divide each operating data into data based on each data collection period to obtain each operating time period data corresponding to each data collection period;

[0053] Calculate the difference between adjacent positions of the operating time period data corresponding to the same operating data to obtain each operating difference, and compare each operating difference with the corresponding abnormal trend value;

[0054] The second independent verification result corresponding to any operating data with an operating difference greater than the abnormal trend value is determined as verification abnormality, and the operating data corresponding to all operating differences less than or equal to the abnormal trend value is determined as verification normal.

[0055] Optionally, in the method according to the present invention, establishing first verification node models corresponding to respective associated verification results downward along each associated node model, and establishing second verification node models corresponding to respective independent verification results downward along each independent node model, includes:

[0056] Establishing first initial node models downward along each associated node model, wherein the first initial node model includes a primary abnormal area and a secondary abnormal area;

[0057] Determine respectively the first association anomaly ratios for which the first association verification result of each association node model is an anomaly and the second association anomaly ratios for which the second association verification result is an anomaly;

[0058] Based on each first associated abnormality ratio, a primary abnormality determination axis of a corresponding axis length is generated in each corresponding primary abnormality region; based on each second associated abnormality ratio, a secondary abnormality determination axis of a corresponding axis length is generated in each corresponding secondary abnormality region, to obtain each first verification node model;

[0059] Establishing each second initial node model downward along each independent node model, wherein the second initial node model includes an independent abnormal area;

[0060] Determine the independent verification results corresponding to each independent node model as the independent abnormality ratios of the verification abnormality, generate independent abnormality determination axes of corresponding axis lengths in corresponding independent abnormal areas based on the independent abnormality ratios, and obtain each second verification node model.

[0061] Optionally, in the method according to the present invention, determining each device status corresponding to each device unit based on each operation data tree diagram includes:

[0062] Normalizing the first associated anomaly ratio, the second associated anomaly ratio, and the independent anomaly ratio in the same operation data dendrogram to obtain the first associated anomaly value, the second associated anomaly value, and the independent anomaly value;

[0063] Multiplying the first associated outlier value, the second associated outlier value, and the independent outlier value with the retrieved first associated weight value, the second associated weight value, and the independent weight value respectively to obtain a first associated evaluation value, a second associated evaluation value, and an independent evaluation value;

[0064] The first associated evaluation value, the second associated evaluation value, and the independent evaluation value are summed to obtain a total evaluation value, and an evaluation level determination table is retrieved, wherein the evaluation level determination table includes each evaluation value interval and the device status corresponding to each evaluation value interval;

[0065] The evaluation level determination table is traversed to determine an evaluation value interval including the total evaluation value, and a device state corresponding to the device unit is determined based on the evaluation value interval.

[0066] Optionally, in the method according to the present invention, in response to the operation and maintenance end interacting with any log indication unit, performing a unit change on the log indication unit based on the corresponding device state, and retrieving an operation data tree diagram having a link relationship with the log indication unit for display, including:

[0067] In response to the operation and maintenance end interacting with any log indication unit, determining a device unit corresponding to the log indication unit and a device state corresponding to the device unit;

[0068] Retrieving a status comparison display table, wherein the status comparison display table includes different device states and configuration colors and configuration ratios corresponding to the different device states;

[0069] Traversing the status comparison display table to determine the configuration color and configuration ratio corresponding to the device status;

[0070] Performing unit changes including color change and ratio change on the log indication unit based on the configuration color and the configuration ratio respectively;

[0071] An operation data tree diagram having a link relationship with the log indication unit is retrieved, and model changes including color change and scale change are performed on each node model corresponding to the abnormality checked in the operation data tree diagram.

[0072] According to another aspect of the present invention, a lightweight operation and maintenance fault handling device is provided, comprising:

[0073] A monitoring module is configured to respond to an operation and maintenance monitoring request sent by the operation and maintenance end and carrying a workshop number, determine the production workshop corresponding to the workshop number, and create a workshop model space corresponding to the production workshop based on digital twin technology;

[0074] a classification module configured to obtain each equipment log corresponding to each equipment unit located in the workshop model space, extract data from each equipment log, and hierarchically classify the extracted operation data corresponding to different operation dimensions located in the same equipment log to obtain a tree diagram of each operation data corresponding to each equipment log;

[0075] a partitioning module configured to determine, based on each operation data tree diagram, each device state corresponding to each device unit, and to partition the workshop model space horizontally based on each device height of each device unit in the vertical direction, to obtain a lower model space and an upper model space containing each device unit;

[0076] An establishing module configured to establish, in the upper model space, log indication units corresponding to the equipment units, wherein each log indication unit has a link relationship with a corresponding operation data tree diagram;

[0077] The interaction module is configured to respond to the operation and maintenance end interacting with any log indication unit, perform unit changes on the log indication unit based on the corresponding device status, and call up an operation data tree diagram with a link relationship with the log indication unit for display.

[0078] According to the present invention, a workshop model space corresponding to a production workshop can be created based on digital twin technology. The system then retrieves and extracts data from the equipment logs corresponding to each device unit within the workshop model space. Furthermore, the system hierarchically categorizes the operational data corresponding to different operational dimensions within the same device log based on the existence of dimensional relationships between these operational dimensions, thereby generating a tree diagram of the operational data corresponding to each device log. The server then determines the device status of each device unit, such as whether the device is intact or faulty. Then, the workshop model space is divided in the horizontal direction according to the equipment height of each equipment unit in the vertical direction, thereby obtaining a lower model space and an upper model space containing each equipment unit. In the upper model space, the server will establish each log indication unit corresponding to each equipment unit, and each log indication unit has a link relationship with each corresponding operation data tree diagram, so that when the subsequent operation and maintenance end wants to view the equipment log of a certain equipment unit, it can interact with the log indication unit corresponding to the equipment unit. At this time, the server will change the log indication unit according to the equipment status of the equipment unit, such as configuring it to a different color or a different size, and retrieve the operation data tree diagram with a link relationship with the log indication unit to display it to the operation and maintenance end. The present invention can monitor the status of production equipment in a timely manner through equipment logs and generate corresponding operation data tree diagrams, so that the operation and maintenance end can view the equipment status in a timely manner, thereby improving certain monitoring efficiency and work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 A flowchart of a lightweight operation and maintenance fault handling method according to an embodiment of the present invention is shown;

[0080] Figure 2 A schematic diagram of an operation data tree diagram according to an embodiment of the present invention is shown;

[0081] Figure 3 A schematic diagram of a preset associated comparison layer according to an embodiment of the present invention is shown;

[0082] Figure 4 A structural block diagram of a lightweight operation and maintenance fault handling device according to another embodiment of the present invention is shown. DETAILED DESCRIPTION

[0083] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0084] There are many production equipment in the production workshop. The good or bad status of the production equipment greatly affects the production efficiency of the production workshop. If the corresponding status of the production equipment can be monitored in real time, the faulty production equipment can be dealt with in time to ensure a certain production efficiency.

[0085] The inventors found in their research that the current status detection of production equipment is mostly performed manually, which wastes a certain amount of manpower and may not promptly detect faulty production equipment, affecting the production efficiency of the production workshop.

[0086] To address the aforementioned problems in the prior art, the inventors have proposed the present invention. One embodiment of the present invention provides a lightweight operation and maintenance fault handling method that can be executed on a computing device, where a computing device can be understood as a terminal with data processing capabilities, such as a computer or mobile phone.

[0087] Figure 1 A flowchart of a lightweight operation and maintenance fault handling method according to an embodiment of the present invention is shown. Figure 1 As shown, the method described in this embodiment begins with step S102, and in step S102, includes the following contents:

[0088] In response to an operation and maintenance monitoring request carrying a workshop number sent by the operation and maintenance end, a production workshop corresponding to the workshop number is determined, and a workshop model space corresponding to the production workshop is created based on digital twin technology.

[0089] For example, in this embodiment, the operation and maintenance end can be understood as the terminal equipment used by the operation and maintenance personnel in the production workshop. The operation and maintenance end can perform corresponding monitoring and fault testing during the production operations in the production workshop. When the operation and maintenance end wants to perform online monitoring of a production workshop, it can send an operation and maintenance monitoring request with a workshop number to the server. After receiving the corresponding operation and maintenance monitoring request, the server will determine the corresponding production workshop based on the carried workshop number, and then create a workshop model space corresponding to the production workshop based on digital twin technology.

[0090] In step S104, the following contents are included:

[0091] Obtain each equipment log corresponding to each equipment unit located in the workshop model space, perform data extraction on each equipment log, and hierarchically classify the operation data corresponding to different operation dimensions located in the same equipment log obtained by extraction to obtain a tree diagram of each operation data corresponding to each equipment log.

[0092] For example, in this embodiment, since the workshop model space is created based on the corresponding production workshop, there are equipment units corresponding to the physical production equipment located in the production workshop in the workshop model space. In order to be able to visualize the equipment logs of each physical equipment, the equipment logs corresponding to each equipment unit in the workshop model space can be obtained first. The equipment logs will record the operating data of the equipment unit, such as the temperature, kinetic energy, heat, or vibration of the transformer, and other operating data of different operating dimensions. The server will then extract data from each equipment log and hierarchically classify the operating data corresponding to different operating dimensions in the same equipment log, thereby obtaining a tree diagram of each operating data corresponding to each equipment log.

[0093] Furthermore, the above-mentioned "classifying the extracted operation data corresponding to different operation dimensions in the same device log into hierarchical categories to obtain a tree diagram of each operation data corresponding to each device log" further includes the following steps:

[0094] Creating a blank fill layer, and establishing a device node model corresponding to the device unit in the blank fill layer;

[0095] Obtaining each operation dimension in the same device log, and establishing dimension node models corresponding to different operation dimensions along the device node model;

[0096] Determine whether there is a dimension association relationship between the operating dimensions, and divide the operating dimensions that have the same dimension association relationship with each other into the same associated dimension group, and divide the operating dimensions that do not have a dimension association relationship into independent dimension groups, thereby obtaining associated dimension groups and independent dimension groups;

[0097] Determine each piece of operating data corresponding to each operating dimension in the same associated dimension group, and perform data association on each piece of operating data to obtain each piece of associated data corresponding to each associated dimension group;

[0098] Establishing association node models corresponding to associated data along each dimension node model corresponding to each operating dimension in the same associated dimension group, and establishing independent node models corresponding to each operating data along each dimension node model corresponding to each operating dimension in the independent dimension group;

[0099] Based on the preset anomaly verification strategy, each associated data and each operating data is respectively checked for anomalies, and each associated verification result corresponding to each associated data and each independent verification result corresponding to each operating data are determined;

[0100] First verification node models corresponding to the respective associated verification results are established downward along the associated node models, and second verification node models corresponding to the respective independent verification results are established downward along the independent node models.

[0101] For example, in this embodiment, after extracting data from each device log, the server creates a blank fill layer and builds device node models corresponding to the device units within the blank fill layer. For example, a device node model corresponding to the transformer device unit is created. This results in the server obtaining device node models corresponding to each device unit. The server then retrieves each operational dimension from the same device log and builds dimension node models corresponding to different operational dimensions, following the device node model.

[0102] At this time, the server will determine whether there is a dimensional correlation between the various operating dimensions. For example, when production equipment generates corresponding heat or kinetic energy, it can also generate corresponding temperature. Therefore, there will be a corresponding dimensional correlation between the heat dimension, temperature dimension, and kinetic energy dimension values, but there will be no corresponding dimensional correlation between the corresponding heat dimension and vibration dimension. Based on this, the server will classify the operating dimensions that have the same dimensional correlation with each other into the same correlation dimension group, thereby obtaining various correlation dimension groups, and classify the operating dimensions that have no dimensional correlation with other operating dimensions into independent dimension groups.

[0103] The server then determines the operational data for each operational dimension within the same associated dimension group and associates the operational data to obtain the associated data corresponding to each associated dimension group. At this point, the server creates associated node models corresponding to the associated data along the dimension node models corresponding to each operational dimension within the same associated dimension group, and creates independent node models corresponding to each operational data along the dimension node models corresponding to each operational dimension within the independent dimension group.

[0104] Finally, the server will perform anomaly checks on each associated data and each operating data based on the preset anomaly check strategy, thereby determining the associated check results of each associated data and the independent check results of each operating data. Then, the server will establish each first check node model corresponding to each associated check result along the associated node model, and each second check node model corresponding to each independent check result along the independent node model, such as Figure 2 As shown, in Figure 2 The corresponding tree structure is included, wherein the parent node can be understood as the device node model of the corresponding device unit (i.e. Figure 2 The child nodes located below the parent node can be understood as node models of different dimensions corresponding to different operating dimensions (i.e. Figure 2 Since there may be corresponding dimension association relationships between the various operating dimensions, it is possible to establish an association node model corresponding to the associated data below the dimension node model of each operating dimension with the same dimension association relationship (in Figure 2 In the example, since the two dimension node models on the left have a dimension association relationship, the corresponding nodes on the third level on the left are established based on the two dimension node models, and an independent node model is established downwards from the dimension node model of the running dimension that does not have a dimension association relationship (that is, Figure 2 Finally, in order to display the verification results of the corresponding abnormality verification, the corresponding first verification node model and the second verification node model (that is, Figure 2 Nodes at the fourth level in ).

[0105] This embodiment can determine each associated dimension group and independent dimension group based on whether there is a dimensional association relationship between each operating dimension, and generate corresponding associated node models and independent node models, and then generate a first verification node model and a second verification node model based on the associated verification results and the independent verification results, which is convenient for subsequent operation and maintenance end to view; and, by integrating data of multiple operating dimensions with dimensional association relationships, it can also be convenient to find corresponding equipment failure problems in the subsequent monitoring process.

[0106] Furthermore, the above-mentioned "determining whether there is a dimension association relationship between the operating dimensions, and grouping the operating dimensions that have the same dimension association relationship with each other into the same association dimension group" further includes the following steps:

[0107] Retrieving a preset correlation comparison layer, wherein the preset correlation comparison layer includes a correlation coordinate table populated in a first area and a point comparison table populated in a second area, the correlation coordinate table including two sets of dimensional points extending along an X-axis and a Y-axis, respectively, and having the same arrangement order, and the point comparison table including coordinates of each point and a correlation coefficient corresponding to each point coordinate;

[0108] Determine each operating dimension as a primary dimension in turn, and determine all other operating dimensions as secondary dimensions;

[0109] Taking the primary dimension as the horizontal coordinate point and the secondary dimension as the vertical coordinate point, determine the dimensional points between the same primary dimension and the different secondary dimensions in the association coordinate table, and determine the correlation coefficients between the same primary dimension and the different secondary dimensions in the point comparison table based on the point coordinates corresponding to the point of each dimension;

[0110] Determine that the primary dimension and the secondary dimension corresponding to the correlation coefficient greater than the preset coefficient have a dimension correlation relationship, and classify the two into the same correlation dimension group;

[0111] Inverting the primary and secondary dimensions corresponding to the correlation coefficients less than the preset coefficients, determining the inverted points corresponding to the dimension points at the correlation coordinate points, and determining the correlation coefficients between the primary and secondary dimensions after the inversion in the point comparison table based on the point coordinates corresponding to the inverted points;

[0112] The primary dimension and the secondary dimension after the inversion of primary and secondary whose corresponding correlation coefficient is greater than the preset coefficient are determined to have a dimension correlation relationship, and the two are divided into the same correlation dimension group.

[0113] For example, in this embodiment, when the server determines whether there is a dimension association relationship between the operating dimensions, it will first call the preset association comparison layer, such as Figure 3 As shown, there are two areas in the preset correlation comparison layer, namely the first area and the second area. The first area is filled with the correlation coordinate table (located in Figure 3 The associated coordinate table includes two sets of dimensional points extending along the X-axis and the Y-axis with the same arrangement order. For example, the two existing operating dimensions are temperature dimension and vibration dimension, and the X-axis includes two dimensional points corresponding to the temperature dimension and the vibration dimension respectively. Similarly, the Y-axis also includes two dimensional points corresponding to the temperature dimension and the vibration dimension respectively. The second area is filled with a point comparison table (located at Figure 3), the point comparison table includes the coordinates of each point and the correlation coefficient corresponding to each point coordinate; it should be noted that, in this embodiment, the specific value of the correlation coefficient can be set based on human intervention. For example, if the operation and maintenance end believes that the heat dimension and the temperature dimension have a greater degree of influence, then the correlation coefficient between the two can be set to a larger value.

[0114] The server will then determine each operating dimension as a primary dimension and all remaining operating dimensions as secondary dimensions. The server will use the primary dimension as the horizontal coordinate point and the secondary dimension as the vertical coordinate point, and determine the dimensional points between the same primary dimension and each different secondary dimension in the associated coordinate table. For example, if the three operating dimensions are temperature, vibration, and heat, and the primary dimension is temperature, then the dimensional points are: the horizontal coordinate point is temperature, the vertical coordinate point is vibration, and the vertical coordinate point is temperature, and the vertical coordinate point is temperature.

[0115] The server will determine the correlation coefficients between the same primary dimension and different secondary dimensions in the point comparison table based on the point coordinates corresponding to each dimensional point. For example, if the point coordinates corresponding to the temperature dimension and the heat dimension are (1, 2), the server will determine the correlation coefficient corresponding to the point coordinates (1, 2) in the point comparison table. If the correlation coefficient is 0.8, then the correlation coefficient between the temperature dimension and the heat dimension is 0.8.

[0116] A preset coefficient is preset in the server. When the correlation coefficient is greater than the preset coefficient, it indicates that there is a dimension correlation relationship between the primary dimension and the secondary dimension, and the server will classify the two into the same correlation dimension group.

[0117] It should be noted that, since the production equipment may have fewer dimensions that affect temperature changes and more dimensions that affect heat changes during the corresponding production process, the degree of influence of heat on temperature will be higher, while the degree of influence of temperature on heat will be lower. Based on this, when the correlation coefficient is less than the preset coefficient, it may be because there is no dimensional correlation relationship between the primary dimension and the secondary dimension, or it may be because the primary dimension has a low degree of influence on the secondary dimension. In this case, the server will re-determine the correlation coefficient between the primary dimension and the secondary dimension through the following method to further determine whether there is a dimensional correlation relationship between the primary dimension and the secondary dimension:

[0118] The server will reverse the order of the primary and secondary dimensions, determine the inverted points corresponding to the dimension points at the associated coordinate points, and then determine the correlation coefficient between the primary and secondary dimensions after the inversion of the primary and secondary dimensions in the point comparison table based on the point coordinates corresponding to the inverted points. The server will determine that the primary and secondary dimensions after the inversion of the primary and secondary dimensions have a dimension correlation relationship if the corresponding correlation coefficient is greater than the preset coefficient. The server will classify the two into the same associated dimension group;

[0119] Furthermore, the above-mentioned "determining the operating data corresponding to the operating dimensions in the same associated dimension group, and performing data association on the operating data to obtain associated data corresponding to the associated dimension groups" further includes the following steps:

[0120] Determining a data collection period corresponding to the operating data, and dividing the data collection period into a preset number of time periods to obtain each data collection period;

[0121] Determine the operating data corresponding to the main-level dimension in the associated dimension group as the main-level data, and divide the main-level data based on each data collection period to obtain main-level period data corresponding to each data collection period;

[0122] Taking the retrieved reference period data as the sequence starting point, the main period data are arranged in chronological order based on each data collection period to obtain the main sequence;

[0123] Determining two time period data between adjacent positions in the main-level sequence as main-level data intervals, thereby obtaining main-level data intervals corresponding to the main-level sequence;

[0124] Determine the operating data corresponding to the secondary dimension in the associated dimension group as secondary data, and divide the secondary data based on each primary data interval to obtain secondary interval values ​​corresponding to each primary data interval;

[0125] Each data collection period, each primary data interval, and each secondary interval value are determined as each associated data corresponding to each associated dimension group.

[0126] For example, in this embodiment, after determining each associated dimension group, the server determines a data collection period for the corresponding operational data. For example, if the data collection period is one day, operational data will be collected once a day. The server then divides the data collection period into a preset number of time periods, thereby obtaining data collection periods. For example, if the preset number is two, the server divides the data collection period into two segments, i.e., into two data collection periods.

[0127] The server then identifies the operational data corresponding to the primary-level dimension in the associated dimension group as primary-level data and partitions the primary-level data based on each data collection period, thereby obtaining primary-level period data corresponding to each primary-level data interval. For example, if the primary-level dimension is the calorie dimension and the data collection cycle is divided into two data collection periods, the server will obtain the calorie value in the first data collection period (i.e., one primary-level period data) and the calorie value in the second data collection period (i.e., another primary-level period data).

[0128] The server uses the time before the device starts operating as the base period. The server then arranges the data for each primary period in chronological order based on the data collection period to create a primary sequence. The server then identifies two adjacent periods of data in the primary sequence as primary data intervals, thereby generating each primary data interval corresponding to the primary sequence.

[0129] The server then identifies the operational data corresponding to the secondary dimensions within the associated dimension group as secondary data and partitions the secondary data based on the primary data intervals, thereby obtaining secondary interval values ​​corresponding to each primary data interval. For example, the server obtains secondary data from two data collection periods within a primary data interval, i.e., secondary interval values. The server then identifies each data collection period, each primary data interval, and each secondary interval value as associated data corresponding to each associated dimension group.

[0130] This embodiment can first determine each primary data interval according to the time sequence, and then determine the corresponding secondary interval value according to each primary data interval, thereby obtaining each associated data.

[0131] Furthermore, the above-mentioned “performing anomaly checks on each associated data and each operating data based on a preset anomaly check strategy, and determining each associated check result corresponding to each associated data and each independent check result corresponding to each operating data” further includes the following steps:

[0132] Retrieving each abnormality verification data configured by the operation and maintenance end based on each different operation dimension, wherein each abnormality verification data includes an abnormality comparison value and an abnormality trend value;

[0133] Group each abnormality verification data based on each associated dimension group and the independent dimension group to obtain each associated verification group corresponding to each associated dimension group and each independent verification group corresponding to the independent dimension group;

[0134] Performing numerical verification on each associated data based on each abnormal comparison value in each associated verification group, and performing numerical verification on each operating data based on each abnormal comparison value in the independent verification group, to obtain each first associated verification result corresponding to each associated data, and each first independent verification result corresponding to each operating data;

[0135] Perform trend checks on each associated data based on each abnormal trend value in each associated verification group, and perform trend checks on each operating data based on each abnormal trend value in the independent verification group, to obtain each second associated verification result corresponding to each associated data, and each second independent verification result corresponding to each operating data;

[0136] When the first association verification result and the second association verification result corresponding to the same association data are both normal, the association verification result of the association data is determined to be in a normal state;

[0137] When either the first association verification result or the second association verification result corresponding to the same association data is abnormal, determining the association verification result of the association data as an abnormal state;

[0138] When the second independent verification result and the second independent verification result corresponding to the same operating data are both normal, the independent verification result of the operating data is determined to be normal;

[0139] When either the first independent verification result or the second independent verification result corresponding to the same operation data is abnormal, the independent verification result of the operation data is determined to be in an abnormal state.

[0140] For example, in this embodiment, when the server performs an abnormality check on each related data and each operation data, it will first retrieve the abnormality check data configured by the operation and maintenance end based on different operation dimensions, and each abnormality check data includes an abnormal comparison value and an abnormal trend value.

[0141] The server groups the anomaly verification data according to the associated dimension groups and independent dimension groups, resulting in associated verification groups corresponding to the associated dimension groups and independent verification groups corresponding to the independent dimension groups. The associated verification groups contain the anomaly comparison values ​​and anomaly trend values ​​for the associated node models; the independent verification groups contain the anomaly comparison values ​​and anomaly trend values ​​for the independent node models.

[0142] The server then performs a numerical check on each associated data item based on the anomaly comparison values ​​in each associated check group, and performs a numerical check on each operational data item based on the anomaly comparison values ​​in the independent check group, thereby obtaining first associated check results corresponding to each associated data item and first independent check results corresponding to each operational data item. The server then performs a trend check on each associated data item based on the anomaly trend values ​​in each associated check group, and performs a trend check on each operational data item based on the anomaly trend values ​​in the independent check group, thereby obtaining second associated check results corresponding to each associated data item and second independent check results corresponding to each operational data item.

[0143] At this time, when the first associated verification result and the second associated verification result corresponding to the same associated data are both normal, the server will determine the associated verification result of the associated data as a normal state; when any one of the first associated verification result and the second associated verification result corresponding to the same associated data is abnormal, the server will determine the associated verification result of the associated data as an abnormal state; when the second independent verification result corresponding to the same operation data and the second independent verification result are both normal, the server will determine the independent verification result of the operation data as a normal state; when any one of the first independent verification result and the second independent verification result corresponding to the same operation data is abnormal, the server will determine the independent verification result of the operation data as an abnormal state.

[0144] Furthermore, the above-mentioned "performing numerical verification on each associated data based on each abnormal comparison value in each associated verification group, and performing numerical verification on each operating data based on each abnormal comparison value in the independent verification group, to obtain each first associated verification result corresponding to each associated data, and each first independent verification result corresponding to each operating data" further includes the following steps:

[0145] Compare the main-level time period data corresponding to the same associated dimension group with the corresponding abnormal comparison value, and determine the first associated verification result of the associated data corresponding to any main-level time period data greater than the abnormal comparison value as the verification abnormality, and determine the associated dimension group corresponding to all main-level time period data less than or equal to the abnormal comparison value as the secondary value verification collection;

[0146] Compare each secondary interval value corresponding to the same associated dimension group in the secondary value verification collection with the corresponding abnormal comparison value, and determine the first associated verification result of the associated data corresponding to any secondary interval value greater than the abnormal comparison value as an abnormal verification, and determine the first associated verification result of the associated data corresponding to all secondary interval values ​​less than or equal to the abnormal comparison value as normal verification;

[0147] Divide each operating data into data based on each data collection period to obtain each operating time period data corresponding to each data collection period;

[0148] Compare each operating time period data corresponding to the same operating data with the corresponding abnormal comparison value, and determine the first independent verification result of the operating data corresponding to any operating time period data that is greater than the abnormal comparison value as the verification abnormality, and determine the first independent verification result of the operating data corresponding to all operating time period data that is less than or equal to the abnormal comparison value as the verification normal.

[0149] For example, in this embodiment, when the server performs a numerical check, since when an abnormality occurs in the main-level time period data in the associated dimension group, the corresponding secondary interval value may also be in an abnormal state, in order to reduce a certain amount of calculation by the server, the server will first compare the main-level time period data corresponding to the same associated dimension group with the corresponding abnormal comparison value. When any main-level time period data is greater than the abnormal comparison value, it indicates that an abnormality occurs in the main-level time period data. Therefore, the server will directly determine the first associated check result of the associated data corresponding to the main-level time period data as a verification abnormality; when all main-level time period data in the associated dimension group are less than or equal to the abnormal comparison value, it indicates that the main-level time period data is normal. Therefore, the server needs to further perform an abnormality check on the secondary interval value and determine the associated dimension group as a secondary numerical check collection.

[0150] The server will compare the secondary interval values ​​corresponding to the same associated dimension group in the secondary numerical verification collection with the corresponding abnormal comparison values. When any secondary interval value is greater than the abnormal comparison value, the server will determine the first associated verification result of the corresponding associated data as a verification abnormality; when all secondary interval values ​​are less than or equal to the abnormal comparison value, the server will determine the first associated verification result of the corresponding associated data as a verification normal.

[0151] Then, the server will divide the operation data according to each data collection period, so as to obtain the operation time period data corresponding to each data collection period, and compare the operation time period data corresponding to the same operation data with the corresponding abnormal comparison value. When any operation time period data is greater than the abnormal comparison value, the server will determine the first independent verification result of the corresponding operation data as the verification abnormality; when all operation time period data are less than or equal to the abnormal comparison value, the server will determine the first independent verification result of the corresponding operation data as the verification normal.

[0152] Furthermore, the above-mentioned "performing trend verification on each associated data based on each abnormal trend value in each associated verification group, and performing trend verification on each operating data based on each abnormal trend value in the independent verification group, to obtain each second associated verification result corresponding to each associated data, and each second independent verification result corresponding to each operating data" further includes the following steps:

[0153] Calculate the difference between adjacent positions of each main-level time period data corresponding to the same associated dimension group to obtain each main-level difference, and compare each main-level difference with the corresponding abnormal trend value;

[0154] Determine the first correlation verification result of the correlation data corresponding to any main level difference value greater than the abnormal trend value as the verification abnormality, and determine the correlation dimension group corresponding to all main level difference values ​​less than or equal to the abnormal comparison value as the secondary trend verification collection;

[0155] Calculate the difference between adjacent secondary interval values ​​corresponding to the same associated dimension group in the secondary trend verification collection, and compare the obtained secondary difference values ​​with the corresponding abnormal trend values;

[0156] Determine the second correlation check result of the correlation data corresponding to any secondary difference value greater than the abnormal trend value as abnormal verification, and determine the correlation data corresponding to all secondary difference values ​​less than or equal to the abnormal trend value as normal verification;

[0157] Divide each operating data into data based on each data collection period to obtain each operating time period data corresponding to each data collection period;

[0158] Calculate the difference between adjacent positions of the operating time period data corresponding to the same operating data to obtain each operating difference, and compare each operating difference with the corresponding abnormal trend value;

[0159] The second independent verification result corresponding to any operating data with an operating difference greater than the abnormal trend value is determined as verification abnormality, and the operating data corresponding to all operating differences less than or equal to the abnormal trend value is determined as verification normal.

[0160] For example, in this embodiment, when performing a trend check, the server will first calculate the difference between each adjacent primary-level time period data in each primary-level time period data corresponding to the same associated dimension group, thereby obtaining each primary-level difference value, and then compare each primary-level difference value with the corresponding abnormal trend value. When any primary-level difference value is greater than the abnormal trend value, it indicates that the primary-level difference value is abnormal, so the server will directly determine the first associated verification result of the associated data corresponding to the primary-level difference value as the verification abnormality; when all primary-level difference values ​​in the associated dimension group are less than or equal to the abnormal comparison value, it indicates that the primary-level difference value is normal, so the server needs to further perform abnormality verification on the secondary interval values ​​and determine the associated dimension group as a secondary trend verification collection.

[0161] The server then calculates the difference between adjacent secondary interval values ​​within the secondary interval values ​​corresponding to the same associated dimension group in the secondary trend verification set, and compares each resulting secondary difference with the corresponding abnormal trend value. If any secondary difference is greater than the abnormal trend value, the server will determine the secondary correlation verification result of the corresponding associated data as abnormal. If all secondary differences are less than or equal to the abnormal trend value, the server will determine the secondary correlation verification result of the corresponding associated data as normal.

[0162] Next, the server will divide each operating data according to each data collection period, thereby obtaining each operating period data corresponding to each data collection period. The server will then calculate the difference between adjacent positions of each operating period data corresponding to the same operating data to obtain each operating difference value. Each operating difference value will then be compared with the corresponding abnormal trend value. If any operating difference value is greater than the abnormal trend value, the server will determine the second independent verification result of the corresponding operating data as abnormal. If all operating difference values ​​are less than or equal to the abnormal trend value, the server will determine the second independent verification result of the corresponding operating difference value as normal.

[0163] Furthermore, the above-mentioned "establishing first verification node models corresponding to the respective associated verification results along the associated node models, and establishing second verification node models corresponding to the respective independent verification results along the independent node models" further includes the following steps:

[0164] Establishing first initial node models downward along each associated node model, wherein the first initial node model includes a primary abnormal area and a secondary abnormal area;

[0165] Determine respectively the first association anomaly ratios for which the first association verification result of each association node model is an anomaly and the second association anomaly ratios for which the second association verification result is an anomaly;

[0166] Based on each first associated abnormality ratio, a primary abnormality determination axis of a corresponding axis length is generated in each corresponding primary abnormality region; based on each second associated abnormality ratio, a secondary abnormality determination axis of a corresponding axis length is generated in each corresponding secondary abnormality region, to obtain each first verification node model;

[0167] Establishing respective second initial node models downward along the respective independent node models, wherein the second initial node models include independent abnormal regions;

[0168] Determine the independent verification results corresponding to each independent node model as the independent abnormality ratios of the verification abnormality, generate independent abnormality determination axes of corresponding axis lengths in corresponding independent abnormal areas based on the independent abnormality ratios, and obtain each second verification node model.

[0169] For example, in this embodiment, the server will establish each first initial node model downward along each associated node model, and the first initial node model includes a primary abnormal area and a secondary abnormal area.

[0170] The server then determines the first abnormality ratios for each associated node model whose first associated verification result is an abnormality. For example, if the first abnormality ratio for a associated node model is 50%, the first abnormality ratio is 50%. The server also determines the second abnormality ratios for each associated node model whose second associated verification result is an abnormality. Since the server does not perform further verification on an associated node model if the first associated verification result is an abnormality, the second abnormality ratio may be represented as 0.

[0171] After determining the first and second associated anomaly ratios for each associated node model, the server generates a primary anomaly determination axis with a corresponding axis length in each corresponding primary anomaly region based on the first associated anomaly ratio, and generates a secondary anomaly determination axis with a corresponding axis length in each corresponding secondary anomaly region based on the second associated anomaly ratio, thereby obtaining each first verification node model. For example, if the primary anomaly region has a height of 10 cm and a first associated anomaly ratio of 50%, the server will generate a primary anomaly determination axis with an axis length of 5 cm in the primary anomaly region.

[0172] Next, the server creates second initial node models along each independent node model, including independent abnormal regions. The server determines the independent abnormality ratios corresponding to the independent verification results of each independent node model, and generates independent abnormality determination axes with corresponding axis lengths in the corresponding independent abnormal regions based on the independent abnormality ratios, thereby obtaining second verification node models.

[0173] This embodiment can generate a primary abnormality determination axis, a secondary abnormality determination axis and an independent abnormality determination axis of corresponding axis lengths according to the first associated abnormality ratio, the second associated abnormality ratio and the independent abnormality ratio, so that the subsequent operation and maintenance end can quickly determine the corresponding abnormal situation and the specific location of the abnormal node, which can improve work efficiency to a certain extent.

[0174] In step S106, the following contents are included:

[0175] Based on the tree diagrams of each operation data, the equipment status corresponding to each equipment unit is determined respectively, and based on the equipment heights of each equipment unit in the vertical direction, the workshop model space is divided horizontally to obtain the lower model space and the upper model space containing each equipment unit.

[0176] For example, in this embodiment, after generating each operational data tree diagram, the server determines the equipment status of each equipment unit based on the tree diagram, such as whether the equipment is intact or faulty. The server then divides the workshop model space horizontally based on the vertical height of each equipment unit, thereby generating a lower model space and an upper model space containing each equipment unit.

[0177] This embodiment divides the workshop model space horizontally according to the equipment height of each equipment unit in the vertical direction, so that the height of the divided lower model space is higher than the height of the largest equipment unit, thereby ensuring that the lower model space can accommodate all equipment units.

[0178] Furthermore, the above-mentioned “determining the device status corresponding to each device unit based on each operation data tree diagram” further includes the following steps:

[0179] Normalizing the first associated anomaly ratio, the second associated anomaly ratio, and the independent anomaly ratio in the same operation data dendrogram to obtain the first associated anomaly value, the second associated anomaly value, and the independent anomaly value;

[0180] Multiplying the first associated outlier value, the second associated outlier value, and the independent outlier value with the retrieved first associated weight value, the second associated weight value, and the independent weight value respectively to obtain a first associated evaluation value, a second associated evaluation value, and an independent evaluation value;

[0181] The first associated evaluation value, the second associated evaluation value, and the independent evaluation value are summed to obtain a total evaluation value, and an evaluation level determination table is retrieved, wherein the evaluation level determination table includes each evaluation value interval and the device status corresponding to each evaluation value interval;

[0182] The evaluation level determination table is traversed to determine an evaluation value interval including the total evaluation value, and a device state corresponding to the device unit is determined based on the evaluation value interval.

[0183] For example, in this embodiment, the server normalizes the first-association anomaly ratio, the second-association anomaly ratio, and the independent anomaly ratio in the same operation data tree diagram to obtain the first-association anomaly value, the second-association anomaly value, and the independent anomaly value. The larger the anomaly ratio, the larger the anomaly value, i.e., the more severe the anomaly. The server then multiplies the first-association anomaly value, the second-association anomaly value, and the independent anomaly value by the retrieved first-association weight value, the second-association weight value, and the independent weight value, respectively, to obtain the first-association evaluation value, the second-association evaluation value, and the independent evaluation value.

[0184] Finally, the server calculates the sum of the first associated evaluation value, the second associated evaluation value, and the independent evaluation value to obtain a total evaluation value. The server then retrieves an evaluation grade determination table, which includes various evaluation value intervals and the device states corresponding to each evaluation value interval. The server identifies the evaluation value interval in the evaluation grade determination table that includes the total evaluation value and determines the device state corresponding to the evaluation value interval as the device state of the device unit.

[0185]

[0186] For example, in this embodiment, the calculation process of the first correlation evaluation value, the second correlation evaluation value, and the independent evaluation value can be specifically shown in the following formula:

[0187] Among them, in the above formula, the P m is the total evaluation value, P1 is the first associated abnormality ratio, k1 is the first normalized value, l1 is the first associated weight value, P2 is the second associated abnormality ratio, k2 is the second normalized value, l2 is the second associated weight value, P3 is the independent abnormality ratio, k3 is the third normalized value, l3 is the independent weight value, and l m is the evaluation weight value.

[0188] For example, in this embodiment, after obtaining the first associated abnormality ratio, the second associated abnormality ratio, and the independent abnormality ratio based on the aforementioned method steps, the normalized value corresponding to each abnormality ratio can be retrieved, and each abnormality ratio can be normalized based on the normalized value, and the first associated evaluation value, the second associated evaluation value, and the independent evaluation value can be obtained by multiplying the obtained normalized values ​​with the retrieved corresponding weight values.

[0189] Finally, a summation calculation can be performed based on the obtained first associated evaluation value, the second associated evaluation value and the independent evaluation value, and the obtained value can be multiplied by the retrieved evaluation weight value to obtain the corresponding total evaluation value. By setting the corresponding normalization value and weight value, the accuracy of obtaining the corresponding total evaluation value can be improved, thereby improving the accuracy of judging the equipment status.

[0190] Here, the above-mentioned total evaluation value is obtained based on the first associated evaluation value, the second associated evaluation value and the independent evaluation value. The first associated evaluation value is obtained by multiplying the first associated abnormality ratio and the first associated weight value, the second associated evaluation value is obtained by multiplying the second associated abnormality ratio and the second associated weight value, and the independent associated evaluation value is obtained by multiplying the independent abnormality ratio and the independent weight value. Based on this, the equipment status determined by the numerical comparison result may have a certain deviation from the actual situation. In order to improve the corresponding determination accuracy, the corresponding weight values ​​can be updated and trained in real time to realize the process of updating and iterating each weight value, thereby continuously improving the corresponding determination accuracy.

[0191] Here, the update iteration of each weight value can be achieved through the following steps:

[0192] The method further comprises:

[0193] Acquire an actual total value sent by the management end based on the device unit, and compare the actual total value with the evaluation total value;

[0194] If the actual total value is greater than the evaluation total value, then increasing training is performed on the first associated weight value, the second associated weight value and the independent weight value respectively;

[0195] If the actual total value is less than the evaluation total value, the first associated weight value, the second associated weight value and the independent weight value are respectively subjected to reduction training;

[0196]

[0197] The first associated weight value, the second associated weight value, and the independent weight value after training are obtained by the following formula:

[0198] Among them, q + The number of training increases for the first association weight value l1, ε is the training constant value of the first association weight value l1, q - The number of training times is reduced for the first association weight value l1, α is the first association weight value after training, v + The number of training increases for the second association weight value l2, δ is the training constant value of the second association weight value l2, v -The number of training times is reduced for the second association weight value l2, β is the second association weight value after training, w + The number of training increases for the independent weight value l3, θ is the training constant value of the independent weight value l3, w - To reduce the number of training times for the independent weight value l3, γ is the independent weight value after training.

[0199] In step S108, the following contents are included:

[0200] In the upper model space, log indication units corresponding to the equipment units are established, wherein each log indication unit has a link relationship with the corresponding operation data tree diagram.

[0201] For example, in this embodiment, the server will establish a model of the device log corresponding to each device unit in the upper model space, that is, each log indication unit, and each log indication unit has a link relationship with the corresponding operation data tree diagram.

[0202] In step S110, the following contents are included:

[0203] In response to the operation and maintenance end interacting with any log indication unit, the log indication unit is changed based on the corresponding device status, and an operation data tree diagram having a link relationship with the log indication unit is retrieved for display.

[0204] For example, in this embodiment, when the operation and maintenance end wants to view the device log of a certain device unit, it can interact with the log indication unit corresponding to the device unit. At this time, the server will change the log indication unit according to the device status of the device unit, such as configuring it to a different color or a different size, and call out the operation data tree diagram that has a link relationship with the log indication unit to display it to the operation and maintenance end.

[0205] Furthermore, the above-mentioned "in response to the operation and maintenance end interacting with any log indication unit, performing a unit change on the log indication unit based on the corresponding device state, and retrieving an operation data tree diagram having a link relationship with the log indication unit for display" also includes the following steps:

[0206] In response to the operation and maintenance end interacting with any log indication unit, determining a device unit corresponding to the log indication unit and a device state corresponding to the device unit;

[0207] Retrieving a status comparison display table, wherein the status comparison display table includes different device states and configuration colors and configuration ratios corresponding to the different device states;

[0208] Traversing the status comparison display table to determine the configuration color and configuration ratio corresponding to the device status;

[0209] Performing unit changes including color change and ratio change on the log indication unit based on the configuration color and the configuration ratio respectively;

[0210] An operation data tree diagram having a link relationship with the log indication unit is retrieved, and model changes including color change and scale change are performed on each node model corresponding to the abnormality checked in the operation data tree diagram.

[0211] For example, in this embodiment, when the operation and maintenance end interacts with any log indicator unit, the server determines the device unit corresponding to the log indicator unit and the device status of the device unit. It then retrieves a status comparison display table, which includes various device states and the corresponding configuration colors and configuration ratios. For example, when the device status is good, the corresponding configuration color is green, with a configuration ratio of 1:1; when the device status is high-risk, the corresponding configuration color is red, with a configuration ratio of 3:1.

[0212] The server then changes the log indicator unit to the color and scale of the configured color and scale. The server then retrieves the operational data tree diagram linked to the log indicator unit and changes the model of each node in the operational data tree diagram corresponding to the abnormality being checked, including color and scale changes.

[0213] This embodiment can not only configure different colors for different device states, but also magnify the log indication unit based on different magnification factors according to the different device states, thereby increasing a certain degree of identification, so that the operation and maintenance end can quickly know the device status of the log indication unit.

[0214] According to the present invention, a workshop model space corresponding to a production workshop can be created based on digital twin technology. The system then retrieves and extracts data from the equipment logs corresponding to each device unit within the workshop model space. Furthermore, the system hierarchically categorizes the operational data corresponding to different operational dimensions within the same device log based on the existence of dimensional relationships between these operational dimensions, thereby generating a tree diagram of the operational data corresponding to each device log. The server then determines the device status of each device unit, such as whether the device is intact or faulty. Then, the workshop model space is divided in the horizontal direction according to the equipment height of each equipment unit in the vertical direction, thereby obtaining a lower model space and an upper model space containing each equipment unit. In the upper model space, the server will establish each log indication unit corresponding to each equipment unit, and each log indication unit has a link relationship with each corresponding operation data tree diagram, so that when the subsequent operation and maintenance end wants to view the equipment log of a certain equipment unit, it can interact with the log indication unit corresponding to the equipment unit. At this time, the server will change the log indication unit according to the equipment status of the equipment unit, such as configuring it to a different color or a different size, and retrieve the operation data tree diagram with a link relationship with the log indication unit to display it to the operation and maintenance end. The present invention can monitor the status of production equipment in a timely manner through equipment logs and generate corresponding operation data tree diagrams, so that the operation and maintenance end can view the equipment status in a timely manner, thereby improving certain monitoring efficiency and work efficiency.

[0215] Another embodiment of the present invention provides a lightweight operation and maintenance fault handling device, Figure 4 The corresponding device block diagram is as follows:

[0216] A monitoring module is configured to respond to an operation and maintenance monitoring request sent by the operation and maintenance end and carrying a workshop number, determine the production workshop corresponding to the workshop number, and create a workshop model space corresponding to the production workshop based on digital twin technology;

[0217] a classification module configured to obtain each equipment log corresponding to each equipment unit located in the workshop model space, extract data from each equipment log, and hierarchically classify the extracted operation data corresponding to different operation dimensions located in the same equipment log to obtain a tree diagram of each operation data corresponding to each equipment log;

[0218] a partitioning module configured to determine, based on each operation data tree diagram, each device state corresponding to each device unit, and to partition the workshop model space horizontally based on each device height of each device unit in the vertical direction, to obtain a lower model space and an upper model space containing each device unit;

[0219] An establishing module configured to establish, in the upper model space, log indication units corresponding to the equipment units, wherein each log indication unit has a link relationship with a corresponding operation data tree diagram;

[0220] The interaction module is configured to respond to the operation and maintenance end interacting with any log indication unit, perform unit changes on the log indication unit based on the corresponding device status, and call up an operation data tree diagram with a link relationship with the log indication unit for display.

[0221] In the description provided herein, the algorithms and displays are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems may also be used in conjunction with the examples of the present invention. Based on the above description, it is apparent that the structure required for constructing such systems is well understood. In addition, the present invention is not directed to any specific programming language. It should be understood that various programming languages ​​may be utilized to implement the present invention described herein, and the description of specific languages ​​above is provided for the purpose of disclosing preferred embodiments of the present invention.

[0222] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0223] Similarly, it should be understood that in order to streamline the disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together into a single embodiment, figure, or description thereof.

[0224] Those skilled in the art will appreciate that the modules, units, or components of the devices in the examples disclosed herein may be arranged in the device described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or further divided into multiple submodules.

[0225] Those skilled in the art will appreciate that the modules in the devices of the embodiments can be adaptively changed and installed in one or more devices different from the embodiments. The modules, units, or components in the embodiments can be combined into one module, unit, or component, and furthermore, they can be divided into multiple submodules, subunits, or subcomponents.

[0226] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features and not other features included in other embodiments, the combination of features from different embodiments is intended to be within the scope of the invention and to form different embodiments.

[0227] In addition, some of the embodiments are described herein as methods or combinations of method elements that can be implemented by a processor of a computer system or by other devices that perform the functions described. Thus, a processor having the necessary instructions for implementing the method or method element forms a device for implementing the method or method element. Furthermore, the elements described herein of the device embodiments are examples of devices for implementing the functions performed by the elements for the purpose of implementing the invention.

[0228] As used herein, unless otherwise specified, the use of ordinal numbers "first," "second," "third," etc. to describe common objects merely indicates that different instances of similar objects are involved and are not intended to imply that the objects so described must have a given order in time, space, ranking, or in any other manner.

[0229] Although the present invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of the foregoing description, will appreciate that other embodiments are contemplated within the scope of the invention thus described. Furthermore, it should be noted that the language used in this specification has been selected primarily for readability and instructional purposes and is not selected to explain or limit the subject matter of the present invention.

Claims

1. A lightweight operation and maintenance fault handling method, characterized in that: The following steps are involved: In response to an operation and maintenance monitoring request sent by the operation and maintenance end and carrying a workshop number, determine the production workshop corresponding to the workshop number, and create a workshop model space corresponding to the production workshop based on digital twin technology; Obtaining each equipment log corresponding to each equipment unit located in the workshop model space, extracting data from each equipment log, and hierarchically classifying the extracted operation data corresponding to different operation dimensions located in the same equipment log to obtain a tree diagram of each operation data corresponding to each equipment log; Determining the equipment status corresponding to each equipment unit based on each operation data tree diagram, and dividing the workshop model space horizontally based on the equipment heights of each equipment unit in the vertical direction to obtain a lower model space and an upper model space containing each equipment unit; Establishing log indication units corresponding to the equipment units in the upper model space, wherein each log indication unit has a link relationship with the corresponding operation data tree diagram; In response to the operation and maintenance end interacting with any log indication unit, performing a unit change on the log indication unit based on the corresponding device state, and retrieving an operation data tree diagram having a link relationship with the log indication unit for display; The extracted operation data corresponding to different operation dimensions in the same device log are hierarchically classified to obtain a tree diagram of the operation data corresponding to each device log, including: Creating a blank fill layer, and establishing a device node model corresponding to the device unit in the blank fill layer; Obtaining each operation dimension in the same device log, and establishing dimension node models corresponding to different operation dimensions along the device node model; Determine whether there is a dimension association relationship between the operating dimensions, and divide the operating dimensions that have the same dimension association relationship with each other into the same associated dimension group, and divide the operating dimensions that do not have a dimension association relationship into independent dimension groups, thereby obtaining associated dimension groups and independent dimension groups; Determine each piece of operating data corresponding to each operating dimension in the same associated dimension group, and perform data association on each piece of operating data to obtain each piece of associated data corresponding to each associated dimension group; Establishing association node models corresponding to associated data along each dimension node model corresponding to each operating dimension in the same associated dimension group, and establishing independent node models corresponding to each operating data along each dimension node model corresponding to each operating dimension in the independent dimension group; Based on the preset anomaly verification strategy, each associated data and each operating data is respectively checked for anomalies, and each associated verification result corresponding to each associated data and each independent verification result corresponding to each operating data are determined; First verification node models corresponding to the respective associated verification results are established downward along the associated node models, and second verification node models corresponding to the respective independent verification results are established downward along the independent node models.

2. The lightweight operation and maintenance fault handling method according to claim 1 is characterized in that: Determine whether there is a dimension association relationship between the operating dimensions, and group the operating dimensions that have the same dimension association relationship with each other into the same association dimension group, including: Retrieving a preset correlation comparison layer, wherein the preset correlation comparison layer includes a correlation coordinate table populated in a first area and a point comparison table populated in a second area, the correlation coordinate table including two sets of dimensional points extending along an X-axis and a Y-axis, respectively, and having the same arrangement order, and the point comparison table including coordinates of each point and a correlation coefficient corresponding to each point coordinate; Determine each operating dimension as a primary dimension in turn, and determine all other operating dimensions as secondary dimensions; Taking the primary dimension as the horizontal coordinate point and the secondary dimension as the vertical coordinate point, determine the dimensional points between the same primary dimension and the different secondary dimensions in the association coordinate table, and determine the correlation coefficients between the same primary dimension and the different secondary dimensions in the point comparison table based on the point coordinates corresponding to the point of each dimension; Determine that the primary dimension and the secondary dimension corresponding to the correlation coefficient greater than the preset coefficient have a dimension correlation relationship, and classify the two into the same correlation dimension group; Inverting the primary and secondary dimensions corresponding to the correlation coefficients less than the preset coefficients, determining the inverted points corresponding to the dimension points at the correlation coordinate points, and determining the correlation coefficients between the primary and secondary dimensions after the inversion in the point comparison table based on the point coordinates corresponding to the inverted points; The primary dimension and the secondary dimension after the inversion of primary and secondary whose corresponding correlation coefficient is greater than the preset coefficient are determined to have a dimension correlation relationship, and the two are divided into the same correlation dimension group.

3. The lightweight operation and maintenance fault handling method according to claim 2 is characterized in that: Determine each piece of operating data corresponding to each operating dimension in the same associated dimension group, and perform data association on each piece of operating data to obtain each piece of associated data corresponding to each associated dimension group, including: Determining a data collection period corresponding to the operating data, and dividing the data collection period into a preset number of time periods to obtain each data collection period; Determine the operating data corresponding to the main-level dimension in the associated dimension group as the main-level data, and divide the main-level data based on each data collection period to obtain main-level period data corresponding to each data collection period; Taking the retrieved reference period data as the sequence starting point, the main period data are arranged in chronological order based on each data collection period to obtain the main sequence; Determining two time period data between adjacent positions in the main-level sequence as main-level data intervals, thereby obtaining main-level data intervals corresponding to the main-level sequence; Determine the operating data corresponding to the secondary dimension in the associated dimension group as secondary data, and divide the secondary data based on each primary data interval to obtain secondary interval values ​​corresponding to each primary data interval; Each data collection period, each primary data interval, and each secondary interval value are determined as each associated data corresponding to each associated dimension group.

4. The lightweight operation and maintenance fault handling method according to claim 3 is characterized in that: Based on the preset anomaly verification strategy, each associated data and each operating data is respectively checked for anomalies, and each associated verification result corresponding to each associated data and each independent verification result corresponding to each operating data are determined, including: Retrieving each abnormality verification data configured by the operation and maintenance end based on each different operation dimension, wherein each abnormality verification data includes an abnormality comparison value and an abnormality trend value; Grouping each abnormality verification data based on each associated dimension group and the independent dimension group to obtain each associated verification group corresponding to each associated dimension group and each independent verification group corresponding to the independent dimension group; Performing numerical verification on each associated data based on each abnormal comparison value in each associated verification group, and performing numerical verification on each operating data based on each abnormal comparison value in the independent verification group, to obtain each first associated verification result corresponding to each associated data, and each first independent verification result corresponding to each operating data; Perform trend checks on each associated data based on each abnormal trend value in each associated verification group, and perform trend checks on each operating data based on each abnormal trend value in the independent verification group, to obtain each second associated verification result corresponding to each associated data, and each second independent verification result corresponding to each operating data; When the first association verification result and the second association verification result corresponding to the same association data are both normal, the association verification result of the association data is determined to be in a normal state; When either the first association verification result or the second association verification result corresponding to the same association data is abnormal, determining the association verification result of the association data as an abnormal state; When the first independent verification result and the second independent verification result corresponding to the same operation data are both normal, the independent verification result of the operation data is determined to be normal; When either the first independent verification result or the second independent verification result corresponding to the same operation data is abnormal, the independent verification result of the operation data is determined to be in an abnormal state.

5. The lightweight operation and maintenance fault handling method according to claim 4 is characterized in that: Numerical verification is performed on each associated data based on each abnormal comparison value in each associated verification group, and numerical verification is performed on each operating data based on each abnormal comparison value in the independent verification group, to obtain each first associated verification result corresponding to each associated data and each first independent verification result corresponding to each operating data, including: Compare the main-level time period data corresponding to the same associated dimension group with the corresponding abnormal comparison value, and determine the first associated verification result of the associated data corresponding to any main-level time period data greater than the abnormal comparison value as the verification abnormality, and determine the associated dimension group corresponding to all main-level time period data less than or equal to the abnormal comparison value as the secondary value verification collection; Compare each secondary interval value corresponding to the same associated dimension group in the secondary value verification collection with the corresponding abnormal comparison value, and determine the first associated verification result of the associated data corresponding to any secondary interval value greater than the abnormal comparison value as an abnormal verification, and determine the first associated verification result of the associated data corresponding to all secondary interval values ​​less than or equal to the abnormal comparison value as normal verification; Divide each operating data into data based on each data collection period to obtain each operating time period data corresponding to each data collection period; Compare each operating time period data corresponding to the same operating data with the corresponding abnormal comparison value, and determine the first independent verification result of the operating data corresponding to any operating time period data that is greater than the abnormal comparison value as the verification abnormality, and determine the first independent verification result of the operating data corresponding to all operating time period data that is less than or equal to the abnormal comparison value as the verification normal.

6. The lightweight operation and maintenance fault handling method according to claim 4 is characterized in that: Perform trend checks on each associated data based on each abnormal trend value in each associated verification group, and perform trend checks on each operating data based on each abnormal trend value in the independent verification group, to obtain each second associated verification result corresponding to each associated data and each second independent verification result corresponding to each operating data, including: Calculate the difference between adjacent positions of each main-level time period data corresponding to the same associated dimension group to obtain each main-level difference, and compare each main-level difference with the corresponding abnormal trend value; Determine the first correlation verification result of the correlation data corresponding to any main level difference value greater than the abnormal trend value as the verification abnormality, and determine the correlation dimension group corresponding to all main level difference values ​​less than or equal to the abnormal comparison value as the secondary trend verification collection; Calculate the difference between adjacent secondary interval values ​​corresponding to the same associated dimension group in the secondary trend verification collection, and compare the obtained secondary difference values ​​with the corresponding abnormal trend values; Determine the second correlation check result of the correlation data corresponding to any secondary difference value greater than the abnormal trend value as abnormal verification, and determine the correlation data corresponding to all secondary difference values ​​less than or equal to the abnormal trend value as normal verification; Divide each operating data into data based on each data collection period to obtain each operating time period data corresponding to each data collection period; Calculate the difference between adjacent positions of the operating time period data corresponding to the same operating data to obtain each operating difference, and compare each operating difference with the corresponding abnormal trend value; The second independent verification result corresponding to any operating data with an operating difference greater than the abnormal trend value is determined as verification abnormality, and the operating data corresponding to all operating differences less than or equal to the abnormal trend value is determined as verification normal.

7. The lightweight operation and maintenance fault handling method according to claim 6 is characterized in that: Establishing first verification node models corresponding to the respective associated verification results downward along the associated node models, and establishing second verification node models corresponding to the respective independent verification results downward along the independent node models, including: Establishing first initial node models downward along each associated node model, wherein the first initial node model includes a primary abnormal area and a secondary abnormal area; Determine respectively the first association anomaly ratios for which the first association verification result of each association node model is an anomaly and the second association anomaly ratios for which the second association verification result is an anomaly; Based on each first associated abnormality ratio, a primary abnormality determination axis of a corresponding axis length is generated in each corresponding primary abnormality region; based on each second associated abnormality ratio, a secondary abnormality determination axis of a corresponding axis length is generated in each corresponding secondary abnormality region, to obtain each first verification node model; Establishing each second initial node model downward along each independent node model, wherein the second initial node model includes an independent abnormal area; Determine the independent verification results corresponding to each independent node model as the independent abnormality ratios of the verification abnormality, generate independent abnormality determination axes of corresponding axis lengths in corresponding independent abnormal areas based on the independent abnormality ratios, and obtain each second verification node model.

8. The lightweight operation and maintenance fault handling method according to claim 7 is characterized in that: Based on each operation data tree diagram, the device status corresponding to each device unit is determined respectively, including: Normalizing the first associated anomaly ratio, the second associated anomaly ratio, and the independent anomaly ratio in the same operation data dendrogram to obtain the first associated anomaly value, the second associated anomaly value, and the independent anomaly value; Multiplying the first associated outlier value, the second associated outlier value, and the independent outlier value with the retrieved first associated weight value, the second associated weight value, and the independent weight value respectively to obtain a first associated evaluation value, a second associated evaluation value, and an independent evaluation value; The first associated evaluation value, the second associated evaluation value, and the independent evaluation value are summed to obtain a total evaluation value, and an evaluation level determination table is retrieved, wherein the evaluation level determination table includes each evaluation value interval and the device status corresponding to each evaluation value interval; The evaluation level determination table is traversed to determine an evaluation value interval including the total evaluation value, and a device state corresponding to the device unit is determined based on the evaluation value interval.

9. The lightweight operation and maintenance fault handling method according to claim 8, characterized in that: In response to the operation and maintenance end interacting with any log indication unit, the log indication unit is changed based on the corresponding device state, and an operation data tree diagram having a link relationship with the log indication unit is retrieved for display, including: In response to the operation and maintenance end interacting with any log indication unit, determining a device unit corresponding to the log indication unit and a device state corresponding to the device unit; Retrieving a status comparison display table, wherein the status comparison display table includes different device states and configuration colors and configuration ratios corresponding to the different device states; Traversing the status comparison display table to determine the configuration color and configuration ratio corresponding to the device status; Performing unit changes including color change and ratio change on the log indication unit based on the configuration color and the configuration ratio respectively; An operation data tree diagram having a link relationship with the log indication unit is retrieved, and model changes including color change and scale change are performed on each node model corresponding to the abnormality checked in the operation data tree diagram.

10. A lightweight operation and maintenance fault handling device, characterized in that: include: A monitoring module is configured to respond to an operation and maintenance monitoring request sent by the operation and maintenance end and carrying a workshop number, determine the production workshop corresponding to the workshop number, and create a workshop model space corresponding to the production workshop based on digital twin technology; a classification module configured to obtain each equipment log corresponding to each equipment unit located in the workshop model space, extract data from each equipment log, and hierarchically classify the extracted operation data corresponding to different operation dimensions located in the same equipment log to obtain a tree diagram of each operation data corresponding to each equipment log; a partitioning module configured to determine, based on each operation data tree diagram, each device state corresponding to each device unit, and to partition the workshop model space horizontally based on each device height of each device unit in the vertical direction, to obtain a lower model space and an upper model space containing each device unit; An establishing module configured to establish, in the upper model space, log indication units corresponding to the equipment units, wherein each log indication unit has a link relationship with a corresponding operation data tree diagram; an interaction module configured to, in response to the operation and maintenance end interacting with any log indication unit, perform a unit change on the log indication unit based on the corresponding device state, and retrieve and display an operation data tree diagram having a link relationship with the log indication unit; The extracted operation data corresponding to different operation dimensions in the same device log are hierarchically classified to obtain a tree diagram of the operation data corresponding to each device log, including: Creating a blank fill layer, and establishing a device node model corresponding to the device unit in the blank fill layer; Obtaining each operation dimension in the same device log, and establishing dimension node models corresponding to different operation dimensions along the device node model; Determine whether there is a dimension association relationship between the operating dimensions, and divide the operating dimensions that have the same dimension association relationship with each other into the same associated dimension group, and divide the operating dimensions that do not have a dimension association relationship into independent dimension groups, thereby obtaining associated dimension groups and independent dimension groups; Determine each piece of operating data corresponding to each operating dimension in the same associated dimension group, and perform data association on each piece of operating data to obtain each piece of associated data corresponding to each associated dimension group; Establishing association node models corresponding to associated data along each dimension node model corresponding to each operating dimension in the same associated dimension group, and establishing independent node models corresponding to each operating data along each dimension node model corresponding to each operating dimension in the independent dimension group; Based on the preset anomaly verification strategy, each associated data and each operating data is respectively checked for anomalies, and each associated verification result corresponding to each associated data and each independent verification result corresponding to each operating data are determined; First verification node models corresponding to the respective associated verification results are established downward along the associated node models, and second verification node models corresponding to the respective independent verification results are established downward along the independent node models.

Images