AI Diagnosis Method Based on Defect Information and Fault Characteristics of Dispatching Automation System

Abstract

The present invention provides an AI diagnosis method based on defect information and fault characteristics of a dispatching automation system. The method is applied to an AI diagnosis system based on defect information and fault characteristics of a dispatching automation system. The system includes a data receiving module, an automation network data and service data module, an AI data array module, a dispatching automation fault element module, a fault AI algorithm module, and a service module. Through the present invention, various emergencies such as system failures, hardware failures, software failures, and data anomalies in the dispatching automation system can be responded to and processed in a timely manner, thereby improving the efficiency of automated operation and maintenance and shortening the handling time of fault problems.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis, and particularly to an AI diagnosis method based on defect information and fault characteristics of a dispatching automation system. Background Art

[0002] At present, the maintenance of traditional power dispatching automation professional systems relies on manual inspection one by one and regular patrols to support daily operation and maintenance work, resulting in low work efficiency and heavy work burden of operation and maintenance personnel, bringing great uncertain risks to the operation and maintenance of automation systems. In the current business systems of automated operation and management, it is still relatively weak in system operation status monitoring, system defect discovery and fault handling. For various emergencies such as system failures, hardware failures, software failures, and data anomalies in the dispatching automation operation system, the responsible personnel cannot timely know the operation status of the system and equipment and cannot respond and handle them in a timely manner, resulting in low efficiency of automated operation and maintenance and long troubleshooting time. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide an AI diagnosis method based on defect information and fault characteristics of a dispatching automation system to solve at least the above problems.

[0004] The technical solution adopted in the first aspect of the present invention is as follows:

[0005] An AI diagnosis method based on defect information and fault characteristics of a dispatching automation system, the method is applied to an AI diagnosis system based on defect information and fault characteristics of a dispatching automation system, the system includes a data receiving module, an automated network data and service data module, an AI data array module, a dispatching automation fault element module, a fault AI algorithm module and a service module, and the method includes the following steps:

[0006] S1. Receive the monitoring and polling data of network devices, software, and hardware in the dispatching automation system, the defect information of the dispatching automation system, and the cross-security zone network monitoring data of the third-party network management system through the data receiving module;

[0007] S2. Manage the data received by the data receiving module through the automated network data and service data module and form a database table;

[0008] S3. Manage the data array of the database table through the AI data array module and divide it according to the network layer array, software layer array, and hardware layer array;

[0009] S4. The scheduling automation fault element module forms link fault characteristics, network element fault characteristics, and software fault characteristics from the external factors, influencing conditions, condition information, internal fault forms, fault monitorable manifestations, correlation relationships, conductive logics, and fault item indicators of scheduling automation faults in the network layer array, software layer array, and hardware layer array. Then, supplemented by the defect manifestation information continuously supplemented by the scheduling automation system defect information, the scheduling automation fault element data is constructed.

[0010] S5. The fault AI algorithm module constructs a fault AI service platform based on the scheduling automation fault element data.

[0011] S6. The service module provides external fault analysis and identification services based on the analysis and discrimination results of the fault AI service platform.

[0012] Furthermore, the software fault characteristics include the associated database, operation log, and auxiliary software.

[0013] Furthermore, in step S3, the network layer array sets up an AI network data learning model list for the key network device round-robin acquisition information, defect information data of the master station network device, basic information of the network management of the operation and management system network, network device operation status acquisition, and topology relationship data according to categories, models, attributes, and network association configurations.

[0014] Furthermore, in step S3, the software layer array sets up an AI software data learning model list for the business systems related to scheduling automation services, system auxiliary software, types, categories, attributes, affiliated services, correlation relationships, application associations, application service sequences, fault conductivity, and network association configurations of the operating system.

[0015] Furthermore, in step S3, the hardware layer array obtains the information on the status of the bearing devices of the automation software system from the monitoring round-robin acquisition information, and obtains the defect information data of the master station system devices and the scheduling automation system through the OMS system, third-party operation and management system cross-security zone network monitoring server devices, virtual devices, workstation devices, storage devices, etc. The types, categories, attributes, correlation relationships, application associations, application service sequences, fault conductivity, and network association configurations of the hardware devices serving software such as business systems, application systems, control systems, and monitoring systems are used to set up an AI hardware data learning model list.

[0016] Furthermore, in step S4, the link fault characteristics incorporate the round-robin acquisition information between the gateway devices of the key links, the running state, reference state, and fault state data of the link traffic information, the data matrix analysis form, and the data curve form as network fault characteristics into the AI algorithm of the link fault.

[0017] Further, in step S4, the network element fault features incorporate the information collected by polling key network devices, the defect information data of the master station network devices, the operation and management system information, and the static state, operation state, benchmark state, and fault state data of network objects, the data matrix analysis form, and the data curve form as network fault features into the AI algorithm for network element faults.

[0018] Further, in step S4, the software fault features incorporate the operation state, benchmark state, and fault state data attributes, matrix form, and curve form of the business systems related to dispatching automation services, system auxiliary software, and operating systems as software fault features into the AI algorithm for software faults.

[0019] The technical solution adopted in the second aspect of the present invention is as follows:

[0020] An AI diagnosis system based on defect information and fault features of a dispatching automation system, the system is used to execute the method described in the first aspect, and the system includes a data receiving module, an automated network data and service data module, an AI data array module, a dispatching automation fault element module, a fault AI algorithm module, and a service module.

[0021] Compared with the prior art, the beneficial effects of the present invention are:

[0022] Starting from the thinking mode of big data analysis, the present invention sorts out the technical means and methods for monitoring, discovering, and operating and maintaining the networks and systems of existing dispatching automation, as well as the deficiencies and omissions therein. By introducing the defect information of dispatching operation and maintenance records in big data analysis, the actual defect elimination records of employees over the years are used to enrich the condition elements for fault analysis and diagnosis of AI artificial intelligence.

[0023] Focusing on the thinking of seeking differences and innovation, the present invention breaks out of the thinking mode that only relies on network fault analysis tools, and examines, analyzes, and diagnoses from the perspectives of the physical life forms of network devices, system software, and resource-based hardware and the life cycle of operation data. Using abstract thinking, the data formed by the operation state, benchmark state, and fault state of network devices, system software, and resource-based hardware is used to build data matrix analysis and data curve analysis as the service applications of the point, source, and surface multi-dimensional AI artificial intelligence diagnosis platform for faults. Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only the preferred embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1It is a schematic flowchart of the AI diagnosis method based on the defect information and fault characteristics of the dispatching automation system provided by the embodiments of the present invention.

[0026] Figure 2 It is a schematic overall structural flowchart of the AI diagnosis method based on the defect information and fault characteristics of the dispatching automation system provided by the embodiments of the present invention. Specific embodiments

[0027] The principles and features of the present invention will be described below in conjunction with the accompanying drawings. The listed embodiments are only used to explain the present invention and are not used to limit the scope of the present invention.

[0028] Refer to Figure 1 and Figure 2 The present invention provides an AI diagnosis method based on the defect information and fault characteristics of the dispatching automation system. The method is applied to an AI diagnosis system based on the defect information and fault characteristics of the dispatching automation system. The system includes a data receiving module, an automation network data and service data module, an AI data array module, a dispatching automation fault element module, a fault AI algorithm module, and a service module. The method includes the following steps:

[0029] S1. Receive the monitoring and polling acquisition data of network devices, software, and hardware in the dispatching automation system, the defect information of the dispatching automation system, and the cross-security zone network monitoring data of the third-party network management system through the data receiving module;

[0030] S2. Manage the data received by the data receiving module through the automation network data and service data module and form a database table;

[0031] S3. Manage the data array of the database table through the AI data array module and divide it according to the network layer array, software layer array, and hardware layer array;

[0032] S4. Through the dispatching automation fault element module, form link fault characteristics, network element fault characteristics, and software fault characteristics from the external factors, influencing conditions, condition information, internal fault forms, fault monitorable manifestations, correlation relationships, conductive logic, and fault item indicators of the dispatching automation faults in the network layer array, software layer array, and hardware layer array, and supplement the defect appearance information continuously supplemented by the defect information of the dispatching automation system to construct dispatching automation fault element data;

[0033] S5. The fault AI algorithm module constructs a fault AI service platform based on the dispatching automation fault element data;

[0034] S6. The service module provides external fault analysis and identification services based on the analysis and discrimination results of the fault AI service platform.

[0035] Exemplarily, for the AI data array, first, the monitoring and patrol collection information of key network devices, software, and hardware of the dispatching automation system is collected through the dispatching automation system acquisition tool. The defect information data of the master station equipment and system is obtained through the OMS system, and the cross-security zone network monitoring data of the third-party operation and management system is accessed through the system interface to form database tables of dispatching automation network data and service data. In step C, matrix management of basic information, performance information, association information, etc. is formed according to the network layer, software layer, and hardware layer, and an AI artificial intelligence data array is established. In this process, the relationship between the data of each layer of the network layer, software layer, and hardware layer is sorted out under the guidance of the logical mind map of the dispatching data, and the AI data array follows the logical thinking design of the dispatching data.

[0036] The software fault characteristics include the associated database, operation log, and auxiliary software.

[0037] Exemplarily, the software fault characteristic data is stored through the associated database, operation log, and auxiliary software. The information of the software fault is better grasped through the operation log and auxiliary software of the fault, so as to facilitate rectification.

[0038] In step S3, the network layer array sets up an AI network data learning model list for the patrol collection information of key network devices, the defect information data of the master station network devices, the basic information of the network management of the operation and management system, the collection of the operation status of network devices, and the topology relationship data according to categories, models, attributes, and network association configurations.

[0039] In step S3, the software layer array sets up an AI software data learning model list for the business systems related to dispatching automation services, system auxiliary software, the types, categories, attributes, affiliated services, association relationships, application associations, application service orders, fault conductivity, and network association configurations of the operating systems.

[0040] In step S3, the hardware layer array sets up an AI hardware data learning model list for the information on the status of the bearing devices of the automation software system from the monitoring and patrol collection information, obtains the defect information data of the master station system devices and the dispatching automation system through the OMS system, and the cross-security zone network monitoring server devices, virtual devices, workstation devices, storage devices, etc. of the third-party operation and management system, and the types, categories, attributes, association relationships, application associations, application service orders, fault conductivity, and network association configurations of the hardware devices serving software such as business systems, application systems, control systems, and monitoring systems.

[0041] In step S4, the link fault characteristics include the patrol collection information between the gateway devices of the key links, the running state, reference state, and fault state data of the link traffic information, the data matrix analysis form, and the data curve form as network fault characteristics and incorporate them into the AI algorithm of the link fault.

[0042] In step S4, the network element fault features incorporate the information collected by polling key network devices, the defect information data of the master station network devices, the operation and management system information, and the static state, operating state, reference state, and fault state data of network objects, as well as the data matrix analysis form and data curve form, into the AI algorithm for network element faults.

[0043] In step S4, the software fault features incorporate the operating state, reference state, and fault state data attributes, matrix form, and curve form of the service systems related to dispatching automation services, system auxiliary software, and operating systems, into the AI algorithm for software faults.

[0044] Exemplarily, through the above steps, the AI algorithms for link faults, network element faults, and software faults establish the conditional elements, i.e., algorithm data and conditional basis, for dispatching automation fault analysis and diagnosis.

[0045] On the other hand, the present invention proposes an AI diagnosis system based on the defect information and fault features of a dispatching automation system. The system is used to execute the method described in the first aspect, and the system includes a data receiving module, an automation network data and service data module, an AI data array module, a dispatching automation fault element module, a fault AI algorithm module, and a service module.

[0046] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An AI diagnosis method based on defect information and fault characteristics of a dispatching automation system, characterized in that, The method is applied to an AI diagnosis system based on the defect information and fault characteristics of a dispatching automation system. The system includes a data receiving module, an automation network data and service data module, an AI data array module, a dispatching automation fault element module, a fault AI algorithm module, and a service module. The method includes the following steps: S1. The data receiving module receives the monitoring and polling acquisition data of network devices, software, and hardware in the dispatching automation system, the defect information of the dispatching automation system, and the cross-security zone network monitoring data of the third-party network management system. S2. The automation network data and service data module manages the data received by the data receiving module in a data table and forms a database table. S3. The AI data array module manages the data array of the database table and divides it according to the network layer array, software layer array, and hardware layer array. S4. The dispatching automation fault element module forms link fault characteristics, network element fault characteristics, and software fault characteristics from the external factors, influencing conditions, condition information, internal fault forms, fault monitorable characteristics, association relationships, conductivity logic, and fault item indicators of dispatching automation faults in the network layer array, software layer array, and hardware layer array. Supplementary defect appearance information continuously supplemented by the defect information of the dispatching automation system is used to construct dispatching automation fault element data. The link fault characteristics incorporate the polling acquisition information between gateway devices of key links, the operating state, reference state, and fault state data of link traffic information, data matrix analysis forms, and data curve forms as network fault characteristics into the AI algorithm for link faults. The network element fault characteristics incorporate the polling acquisition information of key network devices, the defect information data of master station network devices, the information of the operation and management system, and the static state, operating state, reference state, and fault state data, data matrix analysis forms, and data curve forms of network objects as network fault characteristics into the AI algorithm for network element faults. The software fault characteristics incorporate the operating state, reference state, and fault state data attributes, matrix forms, and curve forms of business systems, system auxiliary software, and operating systems related to dispatching automation services as software fault characteristics into the AI algorithm for software faults. S5. The fault AI algorithm module constructs a fault AI service platform based on the dispatching automation fault element data. S6. The service module provides external fault analysis and identification services based on the analysis and discrimination results of the fault AI service platform.

2. The AI diagnosis method based on the defect information and fault characteristics of the dispatching automation system according to claim 1, characterized in that The software fault characteristics include the associated database, operation logs, and auxiliary software.

3. The AI diagnosis method based on the defect information and fault characteristics of the dispatching automation system according to claim 1, characterized in that, In step S3, the network layer array sets up an AI network data learning model list for the polling acquisition information of key network devices, the defect information data of master station network devices, the basic information of the operation and management system network management, and the network device operation status acquisition and topology relationship data according to categories, models, attributes, and network association configurations.

4. The AI diagnosis method based on the defect information and fault characteristics of the dispatching automation system according to claim 1, characterized in that, In step S3, the software layer array sets up a list of AI software data learning models for business systems, system auxiliary software, and operating systems related to dispatching automation services according to their types, categories, attributes, affiliated services, association relationships, application associations, application service order, fault conductivity, and network association configurations.

5. The AI diagnosis method based on defect information and fault characteristics of a dispatching automation system according to claim 1, wherein In step S3, the hardware layer array is responsible for collecting the device status information of the devices carrying the automation software system from the monitoring patrol, obtaining the following information data through the OMS system, and setting up a list of AI hardware data learning models based on this: Defect information data of the master station system devices and the dispatching automation system; Relevant device information for cross-security zone network monitoring in the third-party network management system, including: network monitoring server device virtual devices, workstation devices, and storage devices; Detailed information of the hardware devices serving the business system, application system, control system, and monitoring system, specifically including: Device type, device category, device attribute, association relationship between devices, application association information, application service order, fault conductivity analysis, and network association configuration.

6. An AI diagnosis system based on defect information and fault characteristics of a dispatching automation system, characterized in that, The system is used to execute the method according to any one of claims 1-5. The system includes a data receiving module, an automation network data and service data module, an AI data array module, a dispatching automation fault element module, a fault AI algorithm module, and a service module.

Images