Event alarm reasoning method and system based on substation model and rule instantiation

Abstract

The event alarm reasoning method and system based on substation model and rule instantiation obtain standard signals and standard intervals of the substation model by using the substation data and its transmission relationship collected by the centralized control station system; the event reasoning rules are obtained by logical operation of the standard signals in the standard intervals; the standard signals in the event reasoning rules are updated by the measured signals of the equipment in the actual interval of the substation corresponding to the maximum comprehensive similarity in the standard interval, so that the instantiated event reasoning rules are obtained; the instantiated event reasoning rules are displayed by the logical reasoning graph; the real-time alarm information of the centralized control station system is obtained, the event reasoning is carried out according to the logical reasoning graph, and the event alarm is sent. The application reduces the difficulty of complex event reasoning rule configuration in a visual way, and automatically verifies the event reasoning instantiated rules in advance by using the analog signals, so that the efficiency of complex event reasoning logic configuration and verification is improved.

Description

Technical Field

[0001] This application belongs to the field of centralized control station or substation monitoring technology, specifically, it relates to an event alarm reasoning method and system based on substation model and rule instantiation. Background Technology

[0002] With the rapid development of the power system, the scale of substation equipment is constantly expanding, and the monitoring scope of substation monitoring systems and centralized control station equipment monitoring systems is also constantly expanding, covering primary equipment, secondary equipment, auxiliary equipment, surveillance cameras, inspection robots, and physical areas of substations.

[0003] The monitoring and analysis of large-scale data generates a large number of alarm messages. The lack of effective organization among these alarms and the scattered nature of the information make it difficult for monitoring personnel to accurately characterize and locate accidents, hindering rapid response. Existing technology 1 (CN114050654A) proposes an event-based alarm method and device for substation monitoring information, establishing a standardized processing framework for substation monitoring applications. However, the rule configuration and verification involved are complex, resulting in low efficiency in handling complex logic. Existing technology 2 (CN114186764A) proposes a feature extraction method and device for substation monitoring information. By extracting the basic, state, and temporal features of substation monitoring information, it provides accurate and dimensionality-reduced high-quality data for substation data analysis. The event-based alarm function, represented by technology 2, is mainly based on keyword filtering and signal combination. The rule configuration method using table combinations is not intuitive, struggles to express complex logic, and is difficult for users to edit, supplement, and debug rules, offering limited support for monitoring personnel. Existing technology 3 (CN115328970A) discloses a knowledge extraction system for power grid fault event reasoning. It obtains a corpus by preprocessing the collected power grid fault event reasoning data, extracts the attributes and relationships of the events, and uses it to realize reasoning assistance and intelligent reasoning for power grid fault events. The effectiveness of the method of extracting event reasoning knowledge using artificial intelligence methods, represented by existing technology 3, depends on the quantity and quality of training data. Since actual power grid faults do not occur frequently, case data usually has the problem of incomplete fault feature information. The lack of high-quality cases limits the practicality of such methods. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an event alarm reasoning method and system based on substation models and rule instantiation. It establishes typical intervals based on typical equipment signal models of substations, edits event reasoning rules using a visual method, and matches typical substation signals with measured signals used in the reasoning rules using a similarity algorithm. This instantiates general reasoning rules into engineering reasoning rules. It also receives various alarm signals generated by the monitoring system in real time and performs logical reasoning, organizing fragmented alarm information into event-based alarm reports.

[0005] The present invention adopts the following technical solution.

[0006] An event alarm reasoning method based on substation model and rule instantiation includes:

[0007] Step 1: Use the substation data collected by the central control station system as the standard signal for the substation model;

[0008] Step 2: Determine the connection relationship between substation models based on the transmission relationship between substation data collected by the central control station system. The substation models and their connection relationships constitute standard bays. The names of the standard bays adopt the same naming rules as the actual bays in the substation.

[0009] Step 3: Within the standard interval, the standard signals of the substation model are processed through logical operations to obtain a first-level logical node; starting from the first-level logical node, within the set input validity time, the next-level logical node is processed through logical operations to obtain the previous-level logical node, and finally one logical node is output as an event reasoning rule of the standard interval.

[0010] Step 4: Select standard bays based on the actual bay names within the substation; within the standard bays, calculate the equipment name similarity between the standard signal corresponding model and the equipment within the actual bay, and the signal name similarity between the standard signal and the measured signal of the equipment within the actual bay, according to a set order. Use the weighted sum of equipment name similarity and signal name similarity as the comprehensive similarity; update the standard signal in the event reasoning rules with the measured signal of the equipment within the actual bay of the substation corresponding to the maximum comprehensive similarity, and obtain the instantiated event reasoning rules.

[0011] Step 5: Display the instantiated event reasoning rules using a logic reasoning diagram; obtain real-time alarm information from the central control station system; perform event reasoning based on the logic reasoning diagram; and issue event-based alarms.

[0012] Standard signals are classified according to operating data, action information, alarm information, and control commands.

[0013] Repeat step 3 to obtain multiple event reasoning rules for each standard interval; use the multiple event reasoning rules corresponding to each standard interval to form a standard event reasoning rule list;

[0014] The event reasoning rule list adopts a list structure of substation, voltage level, bay, and event reasoning rule.

[0015] Logical operations include: AND, OR, NOT, X selects Y, and order changes.

[0016] The input validity period for each level of logic node is set to 20 seconds.

[0017] In step 4, keywords and voltage levels are extracted from the actual bay names within the substation, and standard bays are automatically obtained based on semantic similarity methods.

[0018] Based on the semantic similarity method, the device name similarity between the name of the model corresponding to the standard signal and the name of the device within the actual interval is calculated. Based on the maximum similar subsequence algorithm of strings, the signal name similarity between the standard signal and the measured signal of the device within the actual interval is calculated. The measured signal is preferably the measured signal of the device within the actual interval corresponding to the maximum device name similarity.

[0019] In step 4, the order in which the standard signals appear in the event reasoning rules is used as the set order.

[0020] The logic reasoning graph illustrates the measured signals, logic nodes, and connections between logic nodes in the instantiated event reasoning rules.

[0021] In step 5, the instantiated event reasoning rules are encoded into binary files. The binary files include the ID of the measured signal, the name of the measured signal, the logic node, the input validity time, and the definition of the output event information.

[0022] When the measured signal of a certain event reasoning rule changes, the logic diagram checks whether the output of the first-level logic node obtained by the logical operation of the measured signal is "true". If the output is "true", the logic diagram checks whether the output of the next-level logic node is "true". Otherwise, an alarm message is issued according to the definition of the output event information. If the output is "true" but there is no next-level logic node, that is, the logic node is the highest-level logic node, an alarm message is issued according to the definition of the output event information.

[0023] When the input of each logic node becomes "true", the moment of the input signal change is recorded. When the valid input time is exceeded, the input signal becomes invalid, and an alarm message is issued according to the output event information definition.

[0024] An event alarm reasoning system based on a substation model and rule instantiation includes:

[0025] Standardization module, rule creation module, rule instantiation module, inference and alarm module;

[0026] The standardization module is used to use substation data collected by the central control station system as standard signals for substation models; it determines the connection relationship between substation models based on the transmission relationship between substation data collected by the central control station system, and the substation models and their connection relationships constitute standard bays; the standard bay names adopt the same naming rules as the actual bays in the substation.

[0027] The rule establishment module is used to obtain a first-level logic node by performing logical operations on the standard signals of the substation model within the standard interval; starting from the first-level logic node, within the set input validity time, the next-level logic node is obtained by performing logical operations on the previous-level logic node, and finally outputs 1 logic node as an event reasoning rule of the standard interval.

[0028] The rule instantiation module is used to select standard bays based on the actual bay names within the substation. Within the standard bay, it calculates the equipment name similarity between the standard signal corresponding model and the equipment within the actual bay, and the signal name similarity between the standard signal and the measured signal of the equipment within the actual bay, according to a set order. The weighted sum of the equipment name similarity and the signal name similarity is used as the comprehensive similarity. The standard signal in the event reasoning rule is updated with the measured signal of the equipment within the actual bay of the substation corresponding to the maximum comprehensive similarity, thus obtaining the instantiated event reasoning rule.

[0029] The reasoning and alarm module is used to display the instantiated event reasoning rules in a logic reasoning diagram; to obtain real-time alarm information from the central control station system; to perform event reasoning based on the logic reasoning diagram; and to issue event-based alarms.

[0030] The beneficial effects of this invention are as follows: Compared with the prior art, this invention uses standard signals from substation equipment as input and employs cascaded combinations of logical operators to describe substation event reasoning rules in a visual manner. It has the advantages of being convenient to use and easy to understand, which helps operation and maintenance personnel summarize experience and refine complex event reasoning rules. In the engineering configuration phase, the input signals of general event reasoning rules are automatically mapped based on the actual substation model to generate substation event alarm reasoning rule instance files, which can verify the effectiveness of reasoning rules in advance through simulated signals. In the operation phase, by loading the substation event alarm reasoning rule instance files, an event reasoning data structure consisting of input signals, logical nodes and their connection relationships is created in memory, which quickly organizes various trivial alarm information received from the monitoring system into event-based alarm reports.

[0031] This invention reduces the difficulty of configuring complex event reasoning rules through visualization and automatically verifies event reasoning instantiation rules in advance using simulated signals, thereby improving the efficiency of configuring and verifying complex event reasoning logic. Attached Figure Description

[0032] Figure 1 This is a flowchart of an event alarm reasoning method based on a substation model and rule instantiation proposed in this invention;

[0033] Figure 2 This is a schematic diagram of a typical device signal model in an embodiment of the present invention;

[0034] Figure 3 This is a typical interval diagram in an embodiment of the present invention;

[0035] Figure 4 This is a diagram illustrating the configuration of a 220kV line device in an embodiment of the present invention.

[0036] Figure 5 This is a schematic diagram of the reasoning rule for "220kV line circuit breaker A phase tripped, reclosing successful" in an embodiment of the present invention;

[0037] Figure 6 This is a schematic diagram of the event reasoning rules under intervals in an embodiment of the present invention;

[0038] Figure 7 This is a schematic diagram illustrating the instantiation of event reasoning rules under intervals in an embodiment of the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this invention. The embodiments described in this application are merely some embodiments of this invention, and not all embodiments. Based on the spirit of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this invention.

[0040] This invention proposes an event alarm reasoning method based on substation models and rule instantiation, such as... Figure 1 As shown, it includes:

[0041] Step 1: Use the substation data collected by the central control station system as the standard signal for the substation model. The standard signal is classified according to operating data, action information, alarm information and control commands.

[0042] The substation model includes models of primary equipment, secondary equipment, and auxiliary equipment.

[0043] The primary equipment includes 13 categories such as transformers, circuit breakers, GIS (Gas Insulated Switchgear), disconnectors, lines, busbars, capacitors and reactors, voltage and current transformers, arc suppression coils, high-voltage reactors, station power supplies, and DC systems.

[0044] Secondary equipment includes 25 categories such as transformer protection, circuit breaker protection, line protection (220kV and above), line protection (110kV and below), bus protection, bus protection (two-three connection), bus tie (section) protection, integrated protection and testing for low-voltage lines, capacitor protection, low-resistance protection, high-resistance protection, station service transformer protection, neutral point isolation device, automatic transfer switch, low-frequency load shedding, overload interconnection, fault isolation device, stability control device, intelligent terminal, merging unit, data acquisition and execution unit, measurement and control device, multi-functional measurement and control device, network security monitoring device, and other equipment.

[0045] Auxiliary equipment includes six categories: primary equipment online monitoring devices, security and defense equipment, fire fighting equipment, environmental system equipment, video surveillance equipment, and monitoring robots.

[0046] Each type of device model contains a series of standard signals, which are organized according to categories such as operating data, action information, alarm information, and control commands. For example... Figure 2 As shown, the standard signals of a circuit breaker in a primary equipment model include: operating data, action information, and control commands; among which, operating data includes measurement data and position status.

[0047] Step 2: Determine the connection relationship between substation models based on the transmission relationship between substation data collected by the central control station system. The substation models and their connection relationships constitute standard bays. The names of standard bays adopt the same naming rules as the actual bays in the substation.

[0048] Specifically, the standard interval includes: the model of primary equipment, the model of secondary equipment, the model of auxiliary equipment, and the connection relationship between the three models. When the same standard interval contains the same equipment model, an alias for the equipment model is added to distinguish them.

[0049] Specifically, standard intervals are established based on 13 categories of primary equipment, 25 categories of secondary equipment, and 6 categories of auxiliary equipment, such as... Figure 3 As shown. Taking a standard bay of a "220kV line" as an example, as... Figure 4 As shown, it consists of lines, circuit breakers, disconnectors, monitoring and control devices, GIS, merging units, intelligent terminals, and line protection (220kV and above). Among them, the merging units, intelligent terminals, and line protection (220kV and above) are configured in two sets and are distinguished by aliases. For example, the intelligent terminals are distinguished by the first set of intelligent terminals and the second set of intelligent terminals.

[0050] Step 3: Within the standard interval, the standard signals of the substation model are processed through logical operations to obtain a first-level logical node; starting from the first-level logical node, within the set input validity time, the next-level logical node is processed through logical operations to obtain the previous-level logical node, and finally one logical node is output as an event reasoning rule of the standard interval; a standard event reasoning rule list is formed using the multiple event reasoning rules corresponding to each standard interval.

[0051] The event reasoning rule list adopts a list structure of substation / voltage level / bay / event reasoning rule.

[0052] Each standard interval corresponds to multiple event reasoning rules.

[0053] Logical operations include, but are not limited to: AND, OR, NOT, X selects Y, and order changes.

[0054] Taking the addition of the event reasoning rule "220kV XX line XX circuit breaker A tripped A closed, reclosing successful" to the standard bay of "220kV line" as an example, such as Figure 5 As shown, in the standard bay, the standard signals "XX line protection A phase trip output = 1" and "XX line protection output = 1" of the first set of protection are selected and the first primary logic node 1 is obtained by "OR" logic operation. The standard signals "XX line protection A phase trip output = 1" and "XX line protection output = 1" of the second set of protection are selected and the second primary logic node 2 is obtained by "OR" logic operation. The first primary logic node 1 and the second primary logic node 2 are obtained by "AND" logic operation.

[0055] Select the standard signal "XX line protection reclosing action = 1" for dual protection, and use "OR" logic to obtain the third primary logic node 4; select the standard signals "XX switch A phase position = 0" and "XX switch A phase position = 1" for circuit breaker protection, and use "sequential execution" logic to define the fourth primary logic node 5; select the standard signals "XX bay fault signal = 1" and "total station fault = 1" for circuit breaker protection, and use "OR" logic to define the fifth primary logic node 6.

[0056] The second-level logical node 3, the third first-level logical node 4, the fourth first-level logical node 5, and the fifth first-level logical node 6 are combined with an "AND" logical operation to obtain logical node 7, which serves as a data alarm node, i.e., an event reasoning rule of the standard interval.

[0057] This invention uses standard signals from substation equipment as input and employs cascaded combinations of logical operators to visually describe substation event reasoning rules. It has the advantages of being easy to use and understand, and helps maintenance personnel summarize experience and refine complex event reasoning rules.

[0058] Furthermore, the input validity period for each level of logic node is 20 seconds, which can be adjusted according to actual needs. This setting of the validity period ensures the accuracy and reliability of the event reasoning rules.

[0059] Repeat step 3 to configure multiple event reasoning rules under the "220kV line" standard bay. The multiple event reasoning rules for each standard bay form a standard event reasoning rule list. The event reasoning rule list adopts a list structure of substation / voltage level / bay / event reasoning rule.

[0060] Taking the "200kV Chengbei Substation" as an example, its "220kV voltage level" "220kV Wancheng South Line 262" bay is automatically matched to the "220kV line" standard bay type. The "220kV Wancheng South Line 262" standard bay is then used to create an event reasoning rule list according to step 3. This event reasoning rule list is organized according to the list structure of substation / voltage level / bay / event reasoning rule, such as... Figure 6 As shown.

[0061] Step 4: Select a standard bay based on the actual bay names within the substation; within the standard bay, calculate the equipment name similarity between the standard signal corresponding model and the equipment within the actual bay, and the signal name similarity between the standard signal and the measured signal of the equipment within the actual bay, according to a set order. Use the weighted sum of the equipment name similarity and the signal name similarity as the comprehensive similarity; update the standard signal in the event reasoning rule with the measured signal of the equipment within the actual bay of the substation corresponding to the maximum comprehensive similarity, and obtain the instantiated event reasoning rule.

[0062] Specifically, since the standard bay name and the actual bay in the substation use the same naming rules, keywords, voltage level and other information are extracted from the actual bay name. Based on the semantic similarity method, the standard bay is automatically matched, thereby realizing the mapping between the standard bay and the actual bay.

[0063] Specifically, the order in which standard signals appear in the event reasoning rules is set as the order. This ensures that the standard interval and the actual interval correspond one-to-one, further prevents omissions during automatic similarity calculation, and does not change the original structure of the event reasoning rules during instantiation.

[0064] Specifically, based on semantic similarity methods, the device name similarity between the name of the model corresponding to the standard signal and the name of the device within the actual interval is calculated. Based on the maximum similarity subsequence algorithm for strings, the signal name similarity between the standard signal and the measured signals of the devices within the actual interval is calculated. The measured signals are preferably the measured signals of the devices within the actual interval corresponding to the maximum device name similarity. A list of measured device signals is also constructed using the measured signals.

[0065] Preferably, the weighting coefficients for both device name similarity and signal name similarity are 0.5.

[0066] Specifically, the measured signal of the equipment in the actual bay of the substation corresponding to the maximum comprehensive similarity is selected to replace the standard signal. Step 3 is repeated to obtain the instantiated event reasoning rules, thereby completing the mapping and matching between the event reasoning rule list of the standard bay and the instantiated event reasoning rule list of the actual bay of the substation.

[0067] In this embodiment of the invention, the event reasoning rules under the "220kV Wancheng South Line 262" bay are instantiated as follows:

[0068] The "220kV Wancheng South Line 262" bay contains 25 primary, secondary, and auxiliary devices, including the "262 switch". It is necessary to instantiate 9 event reasoning rules, such as "220kV XX line XX circuit breaker three-phase trip". Taking the event reasoning rule "220kV XX line XX circuit breaker A trip A close, reclosing successful" as an example, the standard signals include: "total station accident", "XXA phase switch position", "XX bay accident signal", "XX line protection reclosing action", "XX line protection output", "XX line protection A phase trip output", and "XX line protection reclosing action" of the first and second line protection systems. The most matching signal for "Total Station Accident" was found within the entire "220kV Chengbei Substation" area, and its signal ID (1103000000001700191) was recorded. Within the "220kV Wancheng South Line 262" bay area, the most matching signal for the first set of line protection "XX Line Protection Reclosing Action" was found: "220kV Wancheng South Line 262PRS-753A-DA-G Line Protection Reclosing Output," and its signal ID (1103000000001712161) was recorded. The measured signals that best match the standard signals were searched sequentially, and their signal IDs were recorded. This completes the instantiation of the event reasoning rule, such as... Figure 7 As shown.

[0069] Furthermore, in step 4, the instantiated event reasoning rules are checked. If the measured signal does not match correctly, manual matching can be performed through a global search. If the measured signal matches correctly, it is confirmed and marked as enabled.

[0070] The actual substation model organizes and displays actual substation data according to a tree-like list structure of substation / voltage level / bay / equipment / measuring point. In this embodiment of the invention, the event reasoning rule list of the substation is organized according to a list structure of substation / voltage level / bay / event reasoning rule, with a one-to-one correspondence between bays. During the rule instantiation process, it is only necessary to search the list of measured signals of the equipment under the bay to complete the instantiation of the standard signals of the event reasoning rule, thus improving the processing speed.

[0071] During the engineering configuration phase, this invention automatically maps the input signals of general event reasoning rules based on the actual substation model, generating an example file of substation event alarm reasoning rules. This allows for prior verification of the validity of the reasoning rules through simulated signals.

[0072] Step 5: Display the instantiated event reasoning rules using a logic reasoning diagram; obtain real-time alarm information from the central control station system; perform event reasoning based on the logic reasoning diagram; and issue event-based alarms.

[0073] Specifically, the logic reasoning graph illustrates the measured signals, logic nodes, and connections between logic nodes in the instantiated event reasoning rules.

[0074] Specifically, step 5 includes: serializing the instantiated event reasoning rules into binary encoding, and writing the ID of the measured signal, the name of the measured signal, the logical node, the input validity time, and the output event information definition into the binary encoding. This yields a machine-readable binary file of the instantiated event-based reasoning rules for a real substation.

[0075] Specifically, the online module loads the binary file of the event reasoning rules and receives all real-time alarm information generated by the system. When the measured signal of a certain event reasoning rule changes, event reasoning is performed according to the logic reasoning graph. The event reasoning process involves solving the logic nodes layer by layer, ultimately converging on a single logic node as the event reasoning result. In this process, each logic node performs calculations according to its hierarchical order and logical operations, gradually passing the results of the lower-level logic nodes to the upper levels, finally obtaining an event reasoning result, and implementing event-based alarms based on the result, as detailed below:

[0076] 1) When the measured signal of a certain event reasoning rule changes, check whether the output of the first-level logic node obtained by the measured signal through logical operation is "true". If the output is "true", check whether the output of the next-level logic node is "true". If the output is "true" but there is no next-level logic node, that is, the logic node is the highest level logic node, then issue an alarm message according to the definition of the output event information.

[0077] The logic node consists of several measured signals and a logic operation. The logic operation can be any one of AND, OR, NOT, X selects Y, or sequential change.

[0078] Furthermore, a logic node consists of several logic nodes or a combination of several measured signals and logic nodes, along with a logic operation.

[0079] 2) The valid input time for each level of logic node is 20 seconds. When the input of each level of logic node becomes "true", the time of change of the input signal is recorded. When the valid input time is exceeded, the input signal becomes invalid and an alarm message is issued according to the output event information definition.

[0080] Specifically, the binary file representing the instantiated event-driven reasoning rules of the actual substation is stored in an event-driven reasoning rule file named "substation name.eri" and submitted to the file service directory of the automation system to create an event-driven reasoning data structure in memory.

[0081] Specifically, the event reasoning service module periodically checks the file service directory. When the event-based reasoning rule file "substation name.eri" is created or updated, it reads the event-based reasoning rules from the file and forms a logical reasoning graph in the software memory. The measured signal ID and the logical reasoning rule instance containing the measured signal are stored in the form of a hash table.

[0082] Specifically, the event reasoning service module also receives various alarm information from the automation system, extracts the ID of the measured signal that triggered the alarm from the alarm information, and retrieves the associated logical reasoning rule instance in the hash table.

[0083] In this embodiment of the invention, the event display and verification module receives event-based alarm information, displays the alarm information in the form of an event list, can retrieve the logical reasoning graph of the event, and renders the logical reasoning activation path with a special color to help operators quickly confirm the correctness of the reasoning event.

[0084] This invention also proposes an event alarm reasoning system based on a substation model and rule instantiation, comprising:

[0085] Standardization module, rule creation module, rule instantiation module, inference and alarm module;

[0086] The standardization module is used to use substation data collected by the central control station system as standard signals for substation models; it determines the connection relationship between substation models based on the transmission relationship between substation data collected by the central control station system, and the substation models and their connection relationships constitute standard bays; the standard bay names adopt the same naming rules as the actual bays in the substation.

[0087] Furthermore, the standardization module uses a graphical interactive method to edit standard intervals.

[0088] The rule establishment module is used to obtain a first-level logic node by performing logical operations on the standard signals of the substation model within the standard interval; starting from the first-level logic node, within the set input validity time, the next-level logic node is obtained by performing logical operations on the previous-level logic node, and finally outputs 1 logic node as an event reasoning rule of the standard interval.

[0089] Furthermore, the rule creation module uses a graphical interactive method to edit an event reasoning rule with a standard interval.

[0090] The rule instantiation module is used to select standard bays based on the actual bay names within the substation. Within the standard bay, it calculates the equipment name similarity between the standard signal corresponding model and the equipment within the actual bay, and the signal name similarity between the standard signal and the measured signal of the equipment within the actual bay, according to a set order. The weighted sum of the equipment name similarity and the signal name similarity is used as the comprehensive similarity. The standard signal in the event reasoning rule is updated with the measured signal of the equipment within the actual bay of the substation corresponding to the maximum comprehensive similarity, thus obtaining the instantiated event reasoning rule.

[0091] Furthermore, the rule instantiation module instantiates the related event reasoning rules according to the actual intervals based on the actual substation conditions, and organizes the reasoning rule files by substation.

[0092] The reasoning and alarm module is used to display the instantiated event reasoning rules in a logic reasoning diagram; to obtain real-time alarm information from the central control station system; to perform event reasoning based on the logic reasoning diagram; and to issue event-based alarms.

[0093] Specifically, the reasoning and alarm module includes an event reasoning service unit and an event display and verification unit.

[0094] The event reasoning service unit is used to read reasoning rule files according to actual substations, form a logical reasoning graph data structure in the software memory consisting of input objects, logical node objects and their connection relationships, receive various alarm information from the monitoring system, activate reasoning logical nodes step by step according to judgment conditions, finally form reasoning results, and issue event-based alarms.

[0095] The event display and verification unit organizes and displays the results according to event-based alarms and event-related alarm information. It also displays the logic reasoning diagram and signal activation reasoning path in a graphical way, allowing operators to confirm the correctness of the event reasoning.

[0096] During the operation phase, by loading the substation event alarm reasoning rule instance file, an event reasoning data structure consisting of input signals, logical nodes and their connection relationships is created in memory, and various trivial alarm information received from the monitoring system is quickly organized into event-based alarm reports.

[0097] This invention reduces the difficulty of configuring complex event reasoning rules through visualization and automatically verifies event reasoning instantiation rules in advance using simulated signals, thereby improving the efficiency of configuring and verifying complex event reasoning logic.

[0098] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0099] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0100] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0101] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. An event alarm reasoning method based on substation model and rule instantiation, characterized in that, include: Step 1: Use the substation data collected by the central control station system as the standard signal for the substation model; Step 2: Determine the connection relationship between substation models based on the transmission relationship between substation data collected by the central control station system. The substation models and their connection relationships constitute standard bays. The names of the standard bays adopt the same naming rules as the actual bays in the substation. Step 3: Within the standard interval, the standard signals of the substation model are processed through logical operations to obtain a first-level logical node; starting from the first-level logical node, within the set input validity time, the next-level logical node is processed through logical operations to obtain the previous-level logical node, and finally one logical node is output as an event reasoning rule of the standard interval. Step 4: Select standard bays based on the actual bay names within the substation; within the standard bays, calculate the equipment name similarity between the standard signal corresponding model and the equipment within the actual bay, and the signal name similarity between the standard signal and the measured signal of the equipment within the actual bay, according to a set order. Use the weighted sum of equipment name similarity and signal name similarity as the comprehensive similarity; update the standard signal in the event reasoning rules with the measured signal of the equipment within the actual bay of the substation corresponding to the maximum comprehensive similarity, and obtain the instantiated event reasoning rules. Step 5: Display the instantiated event reasoning rules using a logic reasoning diagram; obtain real-time alarm information from the central control station system; perform event reasoning based on the logic reasoning diagram; and issue event-based alarms.

2. The event alarm reasoning method based on substation model and rule instantiation according to claim 1, characterized in that, Standard signals are classified according to operating data, action information, alarm information, and control commands.

3. The event alarm reasoning method based on substation model and rule instantiation according to claim 1, characterized in that, Repeat step 3 to obtain multiple event reasoning rules for each standard interval; use the multiple event reasoning rules corresponding to each standard interval to form a standard event reasoning rule list; The event reasoning rule list adopts a list structure of substation, voltage level, bay, and event reasoning rule.

4. The event alarm reasoning method based on substation model and rule instantiation according to claim 1, characterized in that, Logical operations include: AND, OR, NOT, X selects Y, and order changes.

5. The event alarm reasoning method based on substation model and rule instantiation according to claim 1, characterized in that, The input validity period for each level of logic node is set to 20 seconds.

6. The event alarm reasoning method based on substation model and rule instantiation according to claim 1, characterized in that, In step 4, keywords and voltage levels are extracted from the actual bay names within the substation, and standard bays are automatically obtained based on semantic similarity methods. Based on the semantic similarity method, the device name similarity between the name of the model corresponding to the standard signal and the name of the device within the actual interval is calculated. Based on the maximum similar subsequence algorithm of strings, the signal name similarity between the standard signal and the measured signal of the device within the actual interval is calculated. The measured signal is preferably the measured signal of the device within the actual interval corresponding to the maximum device name similarity.

7. The event alarm reasoning method based on substation model and rule instantiation according to claim 1, characterized in that, In step 4, the order in which the standard signals appear in the event reasoning rules is used as the set order.

8. The event alarm reasoning method based on substation model and rule instantiation according to claim 1, characterized in that, The logic reasoning graph illustrates the measured signals, logic nodes, and connections between logic nodes in the instantiated event reasoning rules.

9. The event alarm reasoning method based on substation model and rule instantiation according to claim 8, characterized in that, In step 5, the instantiated event reasoning rules are encoded into binary files. The binary files include the ID of the measured signal, the name of the measured signal, the logic node, the input validity time, and the definition of the output event information. When the measured signal of a certain event reasoning rule changes, the logic diagram checks whether the output of the first-level logic node obtained by the logical operation of the measured signal is "true". If the output is "true", the logic diagram checks whether the output of the next-level logic node is "true". Otherwise, an alarm message is issued according to the definition of the output event information. If the output is "true" but there is no next-level logic node, that is, the logic node is the highest-level logic node, an alarm message is issued according to the definition of the output event information. When the input of each logic node becomes "true", the moment of the input signal change is recorded. When the valid input time is exceeded, the input signal becomes invalid, and an alarm message is issued according to the output event information definition.

10. An event alarm reasoning system based on a substation model and rule instantiation, used to implement the method described in any one of claims 1 to 9, characterized in that, The system includes: Standardization module, rule creation module, rule instantiation module, inference and alarm module; The standardization module is used to utilize substation data collected by the central control station system as standard signals for the substation model; The connection relationships between substation models are determined based on the transmission relationships between substation data collected by the central control station system. The substation models and their connection relationships constitute standard bays. The names of the standard bays follow the same naming rules as the actual bays within the substations. The rule establishment module is used to obtain a first-level logic node by performing logical operations on the standard signals of the substation model within the standard interval; starting from the first-level logic node, within the set input validity time, the next-level logic node is obtained by performing logical operations on the previous-level logic node, and finally outputs 1 logic node as an event reasoning rule of the standard interval. The rule instantiation module is used to select standard bays based on the actual bay names within the substation. Within the standard bay, it calculates the equipment name similarity between the standard signal corresponding model and the equipment within the actual bay, and the signal name similarity between the standard signal and the measured signal of the equipment within the actual bay, according to a set order. The weighted sum of the equipment name similarity and the signal name similarity is used as the comprehensive similarity. The standard signal in the event reasoning rule is updated with the measured signal of the equipment within the actual bay of the substation corresponding to the maximum comprehensive similarity, thus obtaining the instantiated event reasoning rule. The reasoning and alarm module is used to display the instantiated event reasoning rules in a logic reasoning diagram; to obtain real-time alarm information from the central control station system; to perform event reasoning based on the logic reasoning diagram; and to issue event-based alarms.

Images