Task search method and system for construction of converter station task event equipment model

Abstract

The invention provides a task searching method and system for construction of a convertor station task event equipment model. The method comprises the following steps: collecting historical data and preprocessing; constructing a sequence event recording model; the method comprises the following steps: arranging events and equipment information in a converter station, and establishing a model for the events and equipment of the converter station according to alarm equipment corresponding to the events; sequential control operation tasks and operation process information of the converter station are sorted, operation equipment information of the converter station is extracted from the operation process information, and a task-equipment model is established according to the sequential control operation tasks, the operation processes and the operation equipment information. And converting information sorted by the event-equipment model and the task-equipment model into a graph. According to the method, events in the converter station and related information of the events are counted, including event occurrence times, corresponding equipment and tasks after the events occur and the like, and finally the events and the related information are displayed to related personnel in a graph mode, so that the related personnel can quickly position the event related information.

Description

Technical Field

[0001] The present invention relates to the field of high voltage direct current transmission system operation, and in particular to a task search method and system for constructing a converter station task event equipment model. Background Art

[0002] The DC converter station is the core part of the high-voltage DC transmission system, providing important guarantee for the stability and reliability of the power system. The monitoring system is the key technology to maintain the safe and stable operation of the DC converter station. In actual operation, the operation and maintenance personnel monitor the converter station equipment through the SER message data of the monitoring system. The establishment of the SER model helps to reveal the operating mechanism of the converter station, provide technical support for the safe operation of the converter station and reduce accidents.

[0003] The SER message of the converter station records the action information of the converter station equipment in sequence. When the converter station fails or performs complex operations, the monitoring system will generate a large number of SER messages in a short period of time. The existing event analysis technology mines the action sequence of the equipment by performing correlation analysis on the SER events, but this type of model can only obtain the relationship between events, and cannot mine the operation mechanism between the equipment in complex operation or failure. Based on this, this project proposes a method for constructing a "task-event-equipment" model and task search for converter station SER event analysis. By organizing the converter station sequential control operation process, operation and maintenance events, and equipment types, a set of models connecting sequential control operation tasks, SER events, and converter station equipment information is formed; the method of searching for the corresponding SER events and corresponding equipment information for the sequential control operation tasks in the model facilitates subsequent personnel to better analyze the converter station SER events. Summary of the invention

[0004] In view of the fact that the current converter station event analysis technology cannot deeply explore the action mechanism of complex operations and faults, the present invention proposes a task search method and system for constructing a converter station task event equipment model.

[0005] The technical solution of the method of the present invention is a task search method for constructing a converter station task event device model, comprising the following steps: Step 1: Collect historical message data of different time periods in the converter station and the sequential control operation task information required for the operation and maintenance of the converter station, collect time data, equipment data, and sequential control operation task data in the message data, and perform preprocessing; Step 2: Use the principal component analysis method to focus on extracting time information, device information, event level information, and specific event content from the information preprocessed in step 1, and build a sequential event record model; Step 3: By sorting out the events and equipment information in the converter station, the events and equipment in the converter station are modeled according to the equipment that generates the corresponding alarms; Step 4: By sorting out the sequential control operation tasks and operation process information of the converter station, extracting its operation equipment information from the operation process information, and establishing a task-equipment model according to the sequential control operation tasks, operation process, and operation equipment information.

[0006] Step 5: Convert the information organized by the event-device model and the task-device model into a graph; Preferably, the event data in step 1: collects historical message data of multiple time nodes from the converter station monitoring system, including event timestamp, event type and event description; The event types are classified into: normal, minor, alarm, emergency; Equipment data in step 1: obtaining equipment information related to the converter station through the equipment monitoring system, maintenance records, and equipment management system, including equipment ID and name, equipment type, and equipment status; The equipment types include: converters, transformers; The equipment status includes: normal, fault, and maintenance; Task data described in step 1: obtain operation task information from the task management system and operation records, focusing on the sequential control operation tasks and operation processes of the DC system; The pre-processing method described in step 1 is as follows: From multiple historical message events, empty sets in the message event data are eliminated, and information with utilization value is screened, that is, the time when the event occurred in the message data, the event level corresponding to the event, the alarm group, the specific information of the event, etc. are extracted as important event information.

[0007] Based on the extracted important event information, the events with the same event level are classified and compressed, and then the equipment in the converter station is classified to establish equipment classes; Classify the sequential control operations and protection actions in the DC control and protection system, and establish a basic set of task data.

[0008] Preferably, the time information in step 2 is: recording the exact time when the event occurs; The device information in step 2 is: identifying the specific device associated with each event; The event level information in step 2 is: assigning a level to each event; The specific event content described in step 2 is: describing the nature and impact of each event in detail.

[0009] Store the extracted information in a new table to form a new data set.

[0010] Based on the sorted information, the sequential event record (SER) data is constructed using principal component analysis.

[0011] Preferably, the step 3 is as follows: Step 3.1: Define the basic device class; Define the basic device class. To build the model, you first need to define a basic device class. In this class, you will set the device ID, name, type, status, and system to which the device belongs. In the basic equipment category, basic operation methods must also be provided, such as the opening and closing of circuit breakers and the starting and stopping of equipment; Create specific subclasses for different types of equipment in converter stations based on their basic parameters such as rated power; By integrating all the above information, a complete device model is constructed using the device's ID, name, type, status, system it belongs to, and the definition of the device subclass.

[0012] Step 3.2: Create a specific device subclass; Create subclasses with specific device parameters for different types of equipment such as transformers, disconnectors, filters, etc. Finally, build a comprehensive device class based on the device ID, name, type, status, system, and device subclass.

[0013] Step 3.3: Keyword match the device information in the device class with the device information of the SER model in step 2, merge the SER model with the device information in the device class, and construct an event-device model.

[0014] Preferably, the step 4 is as follows: Step 4.1: Extract key information of sequential control operation; Organize information on sequential control operation tasks and operation processes, identify and record detailed information on the operation steps in the sequential control operation tasks, and record the operation sequence and execution conditions.

[0015] Step 4.2: Build a sequential control device set; Clarify the specific equipment involved in each task and operation in the sequential control operation, such as knife switches, switches and control systems, ensure that the operation steps correspond to the equipment information they operate, organize the equipment information corresponding to each task together, and build a sequential control equipment set separately to facilitate subsequent equipment information matching.

[0016] Step 4.3: The task information, sequential control equipment set, and specific operation information are identified and sorted out and stored in a table to construct a task class. The device information in the task class is matched with the device class in step 3 by keywords, and the task class and the device class are merged to construct a task-device model.

[0017] Preferably, the basic components of the graph in step 5 include nodes and arrows; Among them, nodes represent variables. If there is a connection between two variables, the nodes are connected with arrows, and the relationship between the nodes is marked on the arrows; The conversion into a spectrum described in step 5 is as follows: Construct nodes with event information and device information in the event-device model and connect them; Construct nodes from task information, operation information, and operation device information in the task-device model, and connect tasks with their corresponding operations and devices; By sequentially matching the device information corresponding to the events in the sequence control device set and the emergency event set, that is, by establishing nodes and connecting them to form a graph, the matching results are presented in the form of a graph; The graph model will form a task-event-device model from event set to device class and then to task class.

[0018] Based on the event information obtained from the SER data in step 2, the decision tree method will be used to automatically match events, that is, the timing nodes of the devices corresponding to the events are matched with the devices in the task operations, and finally the corresponding task columns are recursively searched out.

[0019] The present invention also proposes a task search system for constructing a converter station task event device model, comprising: The data collection and preprocessing module is used to collect the historical message data of different time periods in the converter station and the sequential control operation task information required for the operation and maintenance of the converter station, collect the time data, equipment data, and sequential control operation task data in the message data, and perform preprocessing; The sequential event record model construction module is used to use the principal component analysis method to focus on extracting time information, device information, event level information and specific event content from the pre-processed information, and to construct a sequential event record model; The event and equipment model building module is used to organize the event and equipment information in the converter station and build a model for the events and equipment in the converter station according to the equipment corresponding to the alarm of the event; The task and equipment model building module is used to organize the sequential control operation tasks and operation process information of the converter station, extract the operation equipment information from the operation process information, and establish the task-equipment model according to the sequential control operation tasks, operation process, and operation equipment information.

[0020] The graph conversion module is used to convert the information sorted out by the event-device model and the task-device model into a graph.

[0021] The advantage of the present invention is that it counts events and related information in the converter station, including the number of event occurrences, the equipment and tasks corresponding to the events after the events occur, etc., and finally presents them to relevant personnel in the form of a graph to facilitate them to quickly locate event-related information. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 : Flow chart of the method of an embodiment of the present invention.

[0023] Figure 2 : Event-device and task-device model diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In specific implementation, the method proposed in the technical solution of the present invention can be implemented by technical personnel in this field using computer software technology to realize automatic operation process. System devices for implementing the method, such as computer-readable storage media storing the corresponding computer program of the technical solution of the present invention and computer equipment running the corresponding computer program, should also be within the scope of protection of the present invention.

[0026] Converter stations are key facilities in high-voltage direct current (HVDC) transmission systems. When a DC system fails or undergoes complex operations, a large number of events will occur in a short period of time. If the operation and maintenance personnel are unable to promptly discover and analyze key events and information in a short period of time, the accident may expand and cause a safety accident. This solution focuses on building a task event equipment model and presenting the model to operation and maintenance personnel in a graphical manner, so as to quickly locate abnormal events and obtain relevant information.

[0027] Combine the following Figure 1 The specific implementation of the present invention is a task search method for constructing a converter station task event device model, which is as follows: Step 1: Collect historical message data of different time periods in the converter station and the sequential control operation task information required for the operation and maintenance of the converter station, collect time data, equipment data, and sequential control operation task data in the message data, and perform preprocessing; The event data in step 1: collect historical message data of multiple time nodes from the converter station monitoring system, including event timestamp, event type and event description; The event types are classified into: normal, minor, alarm, emergency; Equipment data in step 1: obtaining equipment information related to the converter station through the equipment monitoring system, maintenance records, and equipment management system, including equipment ID and name, equipment type, and equipment status; The equipment types include: converters, transformers; The equipment status includes: normal, fault, and maintenance; Task data described in step 1: obtain operation task information from the task management system and operation records, focusing on the sequential control operation tasks and operation processes of the DC system; The pre-processing method described in step 1 is as follows: From multiple historical message events, empty sets in the message event data are eliminated, and information with utilization value is screened, that is, the time when the event occurred in the message data, the event level corresponding to the event, the alarm group, the specific information of the event, etc. are extracted as important event information.

[0028] Based on the extracted important event information, the events with the same event level are classified and compressed, and then the equipment in the converter station is classified to establish equipment classes; Classify the sequential control operations and protection actions in the DC control and protection system, and establish a basic set of task data.

[0029] Step 2: Use the principal component analysis method to focus on extracting time information, device information, event level information, and specific event content from the information preprocessed in step 1, and build a sequential event record model: The time information in step 2 is: recording the exact time when the event occurred; The device information in step 2 is: identifying the specific device associated with each event; The event level information in step 2 is: assigning a level to each event; The specific event content described in step 2 is: describing the nature and impact of each event in detail.

[0030] Store the extracted information in a new table to form a new data set.

[0031] Based on the sorted information, the sequential event record (SER) data is constructed using principal component analysis.

[0032] Step 3: By sorting out the events and equipment information in the converter station, the events and equipment in the converter station are modeled according to the equipment that generates the corresponding alarms; The step 3 is as follows: Step 3.1: Define the basic device class; Define the basic device class. To build the model, you first need to define a basic device class. In this class, you will set the device ID, name, type, status, and system to which the device belongs. In the basic equipment category, basic operation methods must also be provided, such as the opening and closing of circuit breakers and the starting and stopping of equipment; Create specific subclasses for different types of equipment in converter stations based on their basic parameters such as rated power; By integrating all the above information, a complete device model is constructed using the device's ID, name, type, status, system it belongs to, and the definition of the device subclass.

[0033] Step 3.2: Create a specific device subclass; Create subclasses with specific device parameters for different types of equipment such as transformers, disconnectors, filters, etc. Finally, build a comprehensive device class based on the device ID, name, type, status, system, and device subclass.

[0034] Step 3.3: Keyword match the device information in the device class with the device information of the SER model in step 2, merge the SER model with the device information in the device class, and construct an event-device model.

[0035] Step 4: Task-equipment modeling: By sorting out the sequential control operation tasks and operation process information of the converter station, extracting its operation equipment information from the operation process information, and establishing a task-equipment model according to the sequential control operation tasks, operation process, and operation equipment information.

[0036] The step 4 is specifically as follows: Step 4.1: Extract key information of sequential control operation; Organize information on sequential control operation tasks and operation processes, identify and record detailed information on the operation steps in the sequential control operation tasks, and record the operation sequence and execution conditions.

[0037] Step 4.2: Build a sequential control device set; Clarify the specific equipment involved in each task and operation in the sequential control operation, such as knife switches, switches and control systems, ensure that the operation steps correspond to the equipment information they operate, organize the equipment information corresponding to each task together, and build a sequential control equipment set separately to facilitate subsequent equipment information matching.

[0038] Step 4.3: The task information, sequential control equipment set, and specific operation information are identified and sorted out and stored in a table to construct a task class. The device information in the task class is matched with the device class in step 3 by keywords, and the task class and the device class are merged to construct a task-device model.

[0039] Step 5: Convert the information organized by the event-device model and the task-device model into a graph; The basic components of the graph in step 5 include nodes and arrows; Among them, nodes represent variables. If there is a connection between two variables, the nodes are connected with arrows, and the relationship between the nodes is marked on the arrows; The conversion into a spectrum described in step 5 is as follows: Construct nodes with event information and device information in the event-device model and connect them; Construct nodes from task information, operation information, and operation device information in the task-device model, and connect tasks with their corresponding operations and devices; By sequentially matching the device information corresponding to the events in the sequence control device set and the emergency event set, that is, by establishing nodes and connecting them to form a graph, the matching results are presented in the form of a graph; The graph model will form a task-event-device model from event set to device class and then to task class.

[0040] Based on the event information obtained from the SER data in step 2, the decision tree method will be used to automatically match events, that is, the timing nodes of the devices corresponding to the events are matched with the devices in the task operations, and finally the corresponding task columns are recursively searched out.

[0041] The specific implementation of the system of the present invention is a task search system constructed by a converter station task event device model, including The data collection and preprocessing module is used to collect the historical message data of different time periods in the converter station and the sequential control operation task information required for the operation and maintenance of the converter station, collect the time data, equipment data, and sequential control operation task data in the message data, and perform preprocessing; The sequential event record model construction module is used to use the principal component analysis method to focus on extracting time information, device information, event level information and specific event content from the pre-processed information, and to construct a sequential event record model; The event and equipment model building module is used to organize the event and equipment information in the converter station and build a model for the events and equipment in the converter station according to the equipment corresponding to the alarm of the event; The task and equipment model building module is used to organize the sequential control operation tasks and operation process information of the converter station, extract the operation equipment information from the operation process information, and establish the task-equipment model according to the sequential control operation tasks, operation process, and operation equipment information; The graph conversion module is used to convert the information sorted out by the event-device model and the task-device model into a graph.

[0042] The present invention counts events and related information in the converter station, including the number of event occurrences, the equipment and tasks corresponding to the events after the events occur, etc., and finally presents them to relevant personnel in the form of a graph to facilitate them to quickly locate event-related information.

[0043] Figure 2 In the figure, the dark green nodes are sequential control operation tasks, the orange nodes are operation process information, the blue nodes are the devices corresponding to the operations, and the red nodes are events and their corresponding devices.

[0044] In the graph, double-clicking a node will display or close related information linked to this node.

[0045] It should be understood that parts not elaborated in detail in this specification belong to the prior art.

[0046] It should be understood that the above description of the preferred embodiment is relatively detailed and cannot be regarded as limiting the scope of patent protection of the present invention. Under the enlightenment of the present invention, ordinary technicians in this field can also make substitutions or modifications without departing from the scope of protection of the claims of the present invention, which all fall within the scope of protection of the present invention. The scope of protection requested for the present invention shall be based on the attached claims.

Claims

1. A task search method for constructing a converter station task event device model, characterized in that: The following steps are involved: Step 1: Collect historical message data of different time periods in the converter station and the sequential control operation task information required for the operation and maintenance of the converter station, collect time data, equipment data, and sequential control operation task data in the message data, and perform preprocessing; Step 2: Use the principal component analysis method to focus on extracting time information, device information, event level information, and specific event content from the information preprocessed in step 1, and build a sequential event record model; Step 3: By sorting out the events and equipment information in the converter station, the events and equipment in the converter station are modeled according to the equipment that generates the corresponding alarms; Step 4: Task-equipment modeling: By sorting out the sequential control operation tasks and operation process information of the converter station, extracting its operation equipment information from the operation process information, and establishing a task-equipment model according to the sequential control operation tasks, operation process, and operation equipment information; Step 5: Convert the information organized by the event-device model and task-device model into a graph.

2. The task search method for constructing a converter station task event device model according to claim 1, characterized in that: The event data in step 1: collect historical message data of multiple time nodes from the converter station monitoring system, including event timestamp, event type and event description; The event types are classified into: normal, minor, alarm, emergency; Equipment data in step 1: obtaining equipment information related to the converter station through the equipment monitoring system, maintenance records, and equipment management system, including equipment ID and name, equipment type, and equipment status; The equipment types include: converters, transformers; The equipment status includes: normal, fault, and maintenance; Task data described in step 1: obtain operation task information from the task management system and operation records, focusing on the sequential control operation tasks and operation processes of the DC system.

3. The task search method for constructing a converter station task event device model according to claim 2, characterized in that: The pre-processing method described in step 1 is as follows: From multiple historical message events, remove the empty sets in the message event data and filter out the information with useful value, that is, extract the time when the event occurred, the event level corresponding to the event, the alarm group, the specific information of the event, etc. as the important information of the event; Based on the extracted important event information, the events with the same event level are classified and compressed, and then the equipment in the converter station is classified to establish equipment classes; Classify the sequential control operations and protection actions in the DC control and protection system, and establish a basic set of task data.

4. The task search method for constructing a converter station task event device model according to claim 3 is characterized in that: The time information in step 2 is: recording the exact time when the event occurred; The device information in step 2 is: identifying the specific device associated with each event; The event level information in step 2 is: assigning a level to each event; The specific event content described in step 2 is: a detailed description of the nature and impact of each event; Store the extracted information in a new table to form a new data set; Based on the sorted information, the sequential event record (SER) data is constructed using principal component analysis.

5. The task search method for constructing a converter station task event device model according to claim 4 is characterized in that: The step 3 is as follows: Step 3.1: Define the basic device class; Define the basic device class. To build the model, you first need to define a basic device class. In this class, you will set the device ID, name, type, status, and system to which the device belongs. In the basic equipment category, basic operation methods must also be provided, such as the opening and closing of circuit breakers and the starting and stopping of equipment; Create specific subclasses for different types of equipment in converter stations based on their basic parameters such as rated power; By combining all the above information, a complete device model is constructed using the device's ID, name, type, status, system it belongs to, and the definition of the device subclass; Step 3.2: Create a specific device subclass; Create subclasses for specific device parameters for different types of equipment such as transformers, disconnectors, filters, etc. Finally, build a comprehensive device class based on the device ID, name, type, status, system, and device subclass; Step 3.3: Keyword match the device information in the device class with the device information of the SER model in step 2, merge the SER model with the device information in the device class, and construct an event-device model.

6. The task search method for constructing a converter station task event device model according to claim 5, characterized in that: The step 4 is specifically as follows: Step 4.1: Extract key information of sequential control operation; Organize information on sequential control operation tasks and operation processes, identify and record detailed information on the operation steps in the sequential control operation tasks, and record the operation sequence and execution conditions; Step 4.2: Build a sequential control device set; Identify the specific equipment involved in each task and operation in the sequential control operation, such as switches, switches and control systems, ensure that the operation steps correspond to the equipment information they operate, organize the equipment information corresponding to each task, and build a sequential control equipment set respectively, so as to facilitate subsequent equipment information matching; Step 4.3: The task information, sequential control equipment set, and specific operation information are identified and sorted out and stored in a table to construct a task class. The device information in the task class is matched with the device class in step 3 by keywords, and the task class and the device class are merged to construct a task-device model.

7. The task search method for constructing a converter station task event device model according to claim 6, characterized in that: The basic components of the graph in step 5 include nodes and arrows; Among them, the node represents the variable. If there is a connection between two variables, the nodes are connected with arrows, and the relationship between the nodes is marked on the arrow.

8. The task search method for constructing a converter station task event device model according to claim 7, characterized in that: The conversion into a spectrum described in step 5 is as follows: Construct nodes with event information and device information in the event-device model and connect them; Construct nodes from task information, operation information, and operation device information in the task-device model, and connect tasks with their corresponding operations and devices; By sequentially matching the device information corresponding to the events in the sequence control device set and the emergency event set, that is, by establishing nodes and connecting them to form a graph, the matching results are presented in the form of a graph; The graph model will form a task-event-device model from event set to device class and then to task class; Based on the event information obtained from the SER data in step 2, the decision tree method will be used to automatically match events, that is, the timing nodes of the devices corresponding to the events are matched with the devices in the task operations, and finally the corresponding task columns are recursively searched out.

9. A task search system for constructing a converter station task event device model, characterized in that: include The data collection and preprocessing module is used to collect the historical message data of different time periods in the converter station and the sequential control operation task information required for the operation and maintenance of the converter station, collect the time data, equipment data, and sequential control operation task data in the message data, and perform preprocessing; The sequential event record model construction module is used to use the principal component analysis method to focus on extracting time information, device information, event level information and specific event content from the pre-processed information, and to construct a sequential event record model; The event and equipment model building module is used to organize the event and equipment information in the converter station and build a model for the events and equipment in the converter station according to the equipment corresponding to the alarm of the event; The task and equipment model building module is used to organize the sequential control operation tasks and operation process information of the converter station, extract the operation equipment information from the operation process information, and establish the task-equipment model according to the sequential control operation tasks, operation process, and operation equipment information; The graph conversion module is used to convert the information sorted out by the event-device model and the task-device model into a graph.

Images