Intelligent equipment anti-error identification and automatic auditing system

Abstract

The invention relates to the technical field of intelligent power grids, in particular to an anti-error identification and automatic auditing system for intelligent equipment. The system comprises an anti-error identification module and an automatic auditing module, and the anti-error process of the anti-error identification module comprises anti-error analysis in the ticket simulation process, anti-error analysis in auditing, automatic anti-error analysis before execution and anti-error analysis in the execution process. The automatic auditing module comprises an operation order obtaining module, an operation order identification module, an auditing rule base, an auditing processing module and a result feedback module. According to the anti-misoperation identification and automatic auditing system for the intelligent equipment, misoperation identification and content automatic auditing in the operation process of the intelligent equipment are achieved through advanced algorithms and technologies. According to the system, the operation safety and the content auditing efficiency are improved, and powerful technical guarantee is provided for wide application of intelligent equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grids, and in particular to a smart device anti-misidentification and automatic audit system. Background Art

[0002] With the rapid development of the national economy, the scale of the power grid will continue to expand. The number of substations under the jurisdiction of power grid dispatching offices at all levels is increasing, and the intensity of their work is also increasing, resulting in increasingly prominent safety issues in the power production process. With the gradual implementation of the large-scale operation management model, power production at all levels is developing towards integration from management to operation systems, and the power system's operation error prevention system should also develop towards integration. Summary of the invention

[0003] The technical problem to be solved by the present invention is: to overcome the deficiencies of the prior art and provide an intelligent device anti-error identification and automatic review system that can perform anti-error analysis from the drafting of tickets to their execution, thereby improving the security of the system.

[0004] The technical solution of the present invention is:

[0005] A smart device anti-error identification and automatic audit system comprises an anti-error identification module and an automatic audit module. The anti-error identification module is based on the power grid model of IEC61970 standard SCADA. The anti-error process of the anti-error identification module comprises: anti-error analysis during the ticket preparation process, anti-error analysis during the audit, automatic anti-error analysis before execution, and anti-error analysis during the execution process. The automatic audit module comprises: an operation ticket acquisition module, an operation ticket recognition module, an audit rule base, an audit processing module, and a result feedback module.

[0006] Preferably, the error-prevention analysis during the ticket preparation process includes:

[0007] Instruction review: The system or humans need to conduct a detailed review of the operation instructions, including checking the source, format, content and compliance with relevant rules and regulations;

[0008] Risk assessment: Identify existing risk points and potential errors by conducting risk assessment on operation instructions, including analyzing equipment failures, human errors, and environmental factors that occur during instruction execution, and formulate corresponding preventive measures;

[0009] Formulate error prevention measures: After identifying potential errors, formulate specific error prevention measures, including setting operation permissions, adding pre-operation confirmation steps, and introducing redundant systems or backup plans to ensure that even if errors occur, they can be corrected in time or serious consequences can be avoided;

[0010] Simulation drill: Before formally executing the operation, a simulation drill is conducted to help further discover potential problems. By simulating the actual operation process, the effectiveness of error prevention measures can be tested, and problems found in the drill can be adjusted and optimized in a timely manner.

[0011] Preferably, the error prevention analysis in the audit includes:

[0012] Cross-review: Through cross-review between different personnel or systems, problems that may be omitted or overlooked in the drafting process can be discovered;

[0013] Expert review: For complex or important operating instructions, experts are invited to review them. With their rich experience and expertise, experts can analyze the potential risks and errors of the instructions in more depth and put forward suggestions for improvement.

[0014] Feedback mechanism: Establish a feedback mechanism to allow auditors to promptly raise and correct any problems they find during the audit process.

[0015] Preferably, the automatic error-prevention analysis before entering execution includes:

[0016] Automatic verification: Use algorithms and technologies to automatically verify the operation instructions, including checking whether the format, content, logic, etc. of the instructions meet the requirements, and whether there are obvious errors or contradictions;

[0017] Risk warning: By real-time monitoring and analyzing relevant data before the execution of operation instructions, the system can predict the risk points and issue warnings in advance;

[0018] Emergency braking: When a serious error or risk is detected, the system automatically triggers the emergency braking mechanism and suspends the execution of the operation instructions.

[0019] Preferably, the error prevention analysis during the execution process:

[0020] Real-time monitoring: By real-time monitoring of various data during the operation, including equipment status, operation progress, and personnel behavior, the system can detect abnormalities or errors in a timely manner;

[0021] Error detection: In-depth analysis of data during operation to detect whether there are errors or violations, including confusion in the detection of operation sequence and abnormal changes in equipment parameters;

[0022] Corrective measures: When errors or abnormalities are found, the system immediately triggers corrective measures, including suspending operations, issuing alarms, and calling backup plans to ensure the correctness and safety of operations. The system records the cause and process of the error, providing valuable data support for subsequent analysis and improvement.

[0023] Preferably, the automatic verification comprises the following steps:

[0024] Operation ticket preprocessing: remove irrelevant characters, extra spaces, and line breaks from the operation ticket text, convert the operation ticket text into a unified format, and use spelling check tools or algorithms to correct spelling errors in the operation ticket text;

[0025] Word segmentation and part-of-speech tagging: Segment the operation ticket text into separate words or morphemes, and mark the part of speech for each word;

[0026] Semantic analysis: Identify key entities in the operation ticket, identify the relationship between entities in the operation ticket, identify the operation type in the operation ticket, and apply corresponding verification rules according to the operation type;

[0027] Rule matching and verification: Based on the initial state and target state of the equipment, a state conversion list or state query matrix is ​​constructed. Based on the operation rules of the power system, an operation sequence template is constructed to check whether the necessary safety measures are included in the operation ticket.

[0028] Error detection and correction: Detect grammatical errors in operation tickets through grammatical analysis, and detect logical errors in operation tickets through logical analysis. For detected errors, use NLP error correction models or manual methods to correct them to ensure the accuracy of the operation tickets;

[0029] Knowledge graph construction and application: Integrate the information in the operation ticket into a unified knowledge framework, build a knowledge graph for the power system, and use the knowledge graph for advanced query and reasoning to query the connection relationship between equipment and reason about potential risks in the operation process;

[0030] Output results and feedback: Output the verified operation ticket in a human-readable format, establish a feedback mechanism, and collect users' opinions and suggestions on the verification results in order to continuously optimize the NLP algorithm and verification rules.

[0031] Preferably, the operation ticket acquisition module is used to obtain the operation ticket information to be reviewed; the operation ticket identification module is used to identify key information in the operation ticket, and the audit rule library is used to store preset audit rules, including the association relationship between equipment, operation sequence requirements, and safety constraints; the audit processing module is used to automatically audit the operation ticket according to the rules in the audit rule library. The module determines whether the operation ticket meets the audit requirements and generates a corresponding audit result; the result feedback module is used to feed back the audit result to the user or related system. If the operation ticket passes the audit, it will be marked as reviewed; if the audit fails, a corresponding error prompt or modification suggestion is generated.

[0032] Preferably, the automated audit module further includes an anomaly detection module, a log recording module, and a data visualization module. The anomaly detection module is used to detect anomalies or non-compliance in operation tickets, including equipment name errors and inconsistent operation instructions; the log recording module is used to record the system's operation log, user operation log, and interface call log for subsequent analysis and tracking; the data visualization module is used to display audit results, abnormal information and other data to users in the form of charts and reports to improve the readability and comprehensibility of the data.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The intelligent device anti-misidentification and automatic audit system of the present invention realizes the identification of misoperation and automatic audit of content during the operation of intelligent devices through advanced algorithms and technologies. The system not only improves the safety of operation and the efficiency of content audit, but also provides a strong technical guarantee for the wide application of intelligent devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 It is a schematic diagram of the structural composition of the system of the present invention.

[0037] Figure 2 It is a schematic diagram of the anti-misidentification process of the anti-misidentification module of the present invention. DETAILED DESCRIPTION

[0038] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0039] Example

[0040] like Figure 1-2As shown, this embodiment provides an intelligent device anti-error identification and automatic audit system, including an anti-error identification module and an automatic audit module. The anti-error identification module is based on the power grid model of IEC61970 standard SCADA, and the anti-error process of the anti-error identification module includes: anti-error analysis in the ticket preparation process, anti-error analysis in the audit, automatic anti-error analysis before execution, and anti-error analysis during execution; the automatic audit module includes: an operation ticket acquisition module, an operation ticket recognition module, an audit rule base, an audit processing module, and a result feedback module.

[0041] Preferably, the error-prevention analysis during the ticket preparation process includes:

[0042] Instruction review: The system or humans need to conduct a detailed review of the operation instructions, including checking the source, format, content and compliance with relevant rules and regulations;

[0043] Risk assessment: Identify existing risk points and potential errors by conducting risk assessment on operation instructions, including analyzing equipment failures, human errors, and environmental factors that occur during instruction execution, and formulate corresponding preventive measures;

[0044] Formulate error prevention measures: After identifying potential errors, formulate specific error prevention measures, including setting operation permissions, adding pre-operation confirmation steps, and introducing redundant systems or backup plans to ensure that even if errors occur, they can be corrected in time or serious consequences can be avoided;

[0045] Simulation drill: Before formally executing the operation, a simulation drill is conducted to help further discover potential problems. By simulating the actual operation process, the effectiveness of error prevention measures can be tested, and problems found in the drill can be adjusted and optimized in a timely manner.

[0046] Preferably, the error prevention analysis in the audit includes:

[0047] Cross-review: Through cross-review between different personnel or systems, problems that may be omitted or overlooked in the drafting process can be discovered, which helps to ensure the comprehensiveness and accuracy of the review;

[0048] Expert review: For complex or important operating instructions, experts are invited to review them. With their rich experience and expertise, experts can analyze the potential risks and errors of the instructions in more depth and put forward suggestions for improvement.

[0049] Feedback mechanism: Establishing a feedback mechanism allows auditors to promptly raise and correct issues when they are discovered during the audit process, helping to ensure continuous improvement and optimization of the audit process.

[0050] Preferably, the automatic error-prevention analysis before entering execution includes:

[0051] Automatic verification: Use algorithms and technologies to automatically verify the operation instructions, including checking whether the format, content, logic, etc. of the instructions meet the requirements, and whether there are obvious errors or contradictions;

[0052] Risk warning: By real-time monitoring and analyzing relevant data before the execution of operation instructions, the system can predict the risk points that may occur and issue early warnings, which helps operators take timely measures to avoid potential errors.

[0053] Emergency braking: When a serious error or risk is detected, the system automatically triggers the emergency braking mechanism to suspend the execution of the operating instructions, helping to prevent the further spread of erroneous instructions and the occurrence of serious consequences.

[0054] Preferably, the error prevention analysis during the execution process:

[0055] Real-time monitoring: By real-time monitoring of various data during the operation, including equipment status, operation progress, and personnel behavior, the system can detect abnormalities or errors in a timely manner;

[0056] Error detection: In-depth analysis of data during operation to detect whether there are errors or violations, including confusion in the detection of operation sequence and abnormal changes in equipment parameters;

[0057] Corrective measures: When errors or abnormalities are found, the system immediately triggers corrective measures, including suspending operations, issuing alarms, and calling backup plans to ensure the correctness and safety of operations. The system records the cause and process of the error, providing valuable data support for subsequent analysis and improvement.

[0058] Preferably, the automatic verification comprises the following steps:

[0059] Operation ticket preprocessing: remove irrelevant characters, extra spaces, and line breaks from the operation ticket text, and convert the operation ticket text into a unified format, such as a unified font, font size, encoding, etc., to facilitate subsequent processing; use spelling check tools or algorithms to correct spelling errors in the operation ticket text;

[0060] Word segmentation and part-of-speech tagging: Segment the operation ticket text into separate words or morphemes, and mark each word with its part of speech, such as noun, verb, adjective, etc., to help understand the role of the word in the sentence;

[0061] Semantic analysis: Identify key entities in the operation ticket, such as device name, geographic location, time, etc., and structure them for subsequent processing; identify the relationship between entities in the operation ticket, such as the connection relationship between devices, the dependency relationship between operation items, etc.; identify the operation type in the operation ticket and apply corresponding verification rules according to the operation type;

[0062] Rule matching and verification: According to the initial state and target state of the equipment, a state transformation list or state query matrix is ​​constructed, and the correctness of the operation process is ensured by comparing the changes in the equipment state in the operation ticket; according to the operation rules of the power system, an operation sequence template is constructed, and the correctness of the operation sequence is ensured by comparing the operation items in the operation ticket with the sequence template; check whether the operation ticket contains necessary safety measures, such as grounding, discharge, etc., to ensure the safety of the operation;

[0063] Error detection and correction: Detect grammatical errors in operation tickets through grammatical analysis, and detect logical errors in operation tickets through logical analysis. For detected errors, use NLP error correction models or manual methods to correct them to ensure the accuracy of the operation tickets;

[0064] Knowledge graph construction and application: Integrate the information in the operation ticket into a unified knowledge framework, build a knowledge graph for the power system, and use the knowledge graph for advanced query and reasoning to query the connection relationship between equipment and reason about potential risks in the operation process;

[0065] Output results and feedback: Output the verified operation ticket in a human-readable format, establish a feedback mechanism, and collect users' opinions and suggestions on the verification results in order to continuously optimize the NLP algorithm and verification rules.

[0066] Preferably, the operation ticket acquisition module is used to obtain the operation ticket information to be reviewed; the operation ticket identification module is used to identify key information in the operation ticket, and the audit rule library is used to store preset audit rules, including the association relationship between equipment, operation sequence requirements, and safety constraints; the audit processing module is used to automatically audit the operation ticket according to the rules in the audit rule library. The module determines whether the operation ticket meets the audit requirements and generates a corresponding audit result; the result feedback module is used to feed back the audit result to the user or related system. If the operation ticket passes the audit, it will be marked as reviewed; if the audit fails, a corresponding error prompt or modification suggestion is generated.

[0067] Preferably, the automated audit module further includes an anomaly detection module, a log recording module, and a data visualization module. The anomaly detection module is used to detect anomalies or non-compliance in operation tickets, including equipment name errors and inconsistent operation instructions; the log recording module is used to record the system's operation log, user operation log, and interface call log for subsequent analysis and tracking; the data visualization module is used to display audit results, abnormal information and other data to users in the form of charts and reports to improve the readability and comprehensibility of the data.

[0068] Although the present invention has been described in detail by referring to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A smart device anti-misidentification and automatic audit system, characterized in that: It includes an anti-error identification module and an automated audit module. The anti-error identification module is based on the power grid model of the IEC61970 standard SCADA. The anti-error identification process of the anti-error identification module includes: anti-error analysis during the drafting process, anti-error analysis during the audit, automatic anti-error analysis before execution, and anti-error analysis during execution. The automated audit module includes: an operation ticket acquisition module, an operation ticket recognition module, an audit rule base, an audit processing module, and a result feedback module.

2. The intelligent device anti-misidentification and automatic auditing system according to claim 1, characterized in that: The error-proof analysis in the ticket preparation process includes the following sub-steps: Instruction review: The system or humans need to conduct a detailed review of the operation instructions, including checking the source, format, content and compliance with relevant rules and regulations; Risk assessment: Identify existing risk points and potential errors by conducting risk assessment on operation instructions, including analyzing equipment failures, human errors, and environmental factors that occur during instruction execution, and formulate corresponding preventive measures; Formulate error prevention measures: After identifying potential errors, formulate specific error prevention measures, including setting operation permissions, adding pre-operation confirmation steps, and introducing redundant systems or backup plans to ensure that even if errors occur, they can be corrected in time or serious consequences can be avoided; Simulation drill: Before formally executing the operation, a simulation drill is conducted to help further discover potential problems. By simulating the actual operation process, the effectiveness of error prevention measures can be tested, and problems found in the drill can be adjusted and optimized in a timely manner.

3. The intelligent device anti-misidentification and automatic auditing system according to claim 1, characterized in that: The error-proofing analysis in the audit includes the following sub-steps: Cross-review: Through cross-review between different personnel or systems, problems that may be omitted or overlooked in the drafting process can be discovered; Expert review: For complex or important operating instructions, experts are invited to review them. With their rich experience and expertise, experts can analyze the potential risks and errors of the instructions in more depth and put forward suggestions for improvement; Feedback mechanism: Establish a feedback mechanism to allow auditors to promptly raise and correct any problems they find during the audit process.

4. The intelligent device anti-misidentification and automatic auditing system according to claim 1, characterized in that: The automatic error prevention analysis before entering execution includes the following sub-steps: Automatic verification: Use algorithms and technologies to automatically verify the operation instructions, including checking whether the format, content, and logic of the instructions meet the requirements, and whether there are obvious errors or contradictions; Risk warning: By real-time monitoring and analyzing relevant data before the execution of operation instructions, the system can predict the risk points and issue warnings in advance; Emergency braking: When a serious error or risk is detected, the system automatically triggers the emergency braking mechanism and suspends the execution of the operation instructions.

5. The intelligent device anti-misidentification and automatic auditing system according to claim 1, characterized in that: The error prevention analysis during the execution process includes the following sub-steps: Real-time monitoring: By real-time monitoring of various data during the operation, including equipment status, operation progress, and personnel behavior, the system can detect abnormalities or errors in a timely manner; Error detection: In-depth analysis of data during operation to detect whether there are errors or violations, including confusion in the detection of operation sequence and abnormal changes in equipment parameters; Corrective measures: When errors or abnormalities are found, the system immediately triggers corrective measures, including suspending operations, issuing alarms, and calling backup plans to ensure the correctness and safety of operations. The system records the cause and process of the error, providing valuable data support for subsequent analysis and improvement.

6. The intelligent device anti-misidentification and automatic auditing system according to claim 4, characterized in that: The automatic verification includes the following sub-steps: Operation ticket preprocessing: remove irrelevant characters, extra spaces, and line breaks from the operation ticket text, convert the operation ticket text into a unified format, and use spelling check tools or algorithms to correct spelling errors in the operation ticket text; Word segmentation and part-of-speech tagging: Segment the operation ticket text into separate words or morphemes, and mark the part of speech for each word; Semantic analysis: Identify key entities in the operation ticket, identify the relationship between entities in the operation ticket, identify the operation type in the operation ticket, and apply corresponding verification rules according to the operation type; Rule matching and verification: According to the initial state and target state of the equipment, a state conversion list or state query matrix is ​​constructed. According to the operation rules of the power system, an operation sequence template is constructed to check whether the operation ticket contains necessary safety measures. Error detection and correction: Detect grammatical errors in operation tickets through grammatical analysis, and detect logical errors in operation tickets through logical analysis. For detected errors, use NLP error correction models or manual methods to correct them to ensure the accuracy of the operation tickets; Knowledge graph construction and application: Integrate the information in the operation ticket into a unified knowledge framework, build a knowledge graph for the power system, and use the knowledge graph for advanced query and reasoning to query the connection relationship between equipment and reason about potential risks in the operation process; Output results and feedback: Output the verified operation ticket in a human-readable format, establish a feedback mechanism, and collect users' opinions and suggestions on the verification results in order to continuously optimize the NLP algorithm and verification rules.

7. The intelligent device anti-misidentification and automatic auditing system according to claim 1, characterized in that: The operation ticket acquisition module is used to obtain the operation ticket information to be reviewed; the operation ticket identification module is used to identify the key information in the operation ticket, and the audit rule library is used to store the preset audit rules, including the association relationship between devices, operation sequence requirements, and safety constraints; the audit processing module is used to automatically audit the operation ticket according to the rules in the audit rule library, and the module determines whether the operation ticket meets the audit requirements and generates the corresponding audit results; The result feedback module is used to feed back the audit results to the user or related system. If the operation ticket passes the audit, it will be marked as audited; if the audit fails, a corresponding error prompt or modification suggestion will be generated.

8. The intelligent device anti-misidentification and automatic auditing system according to claim 1, characterized in that: The automated audit module further includes an anomaly detection module, a log recording module, and a data visualization module. The anomaly detection module is used to detect anomalies or non-compliance in operation tickets, including equipment name errors and inconsistent operation instructions; the log recording module is used to record the system's operation log, user operation log, and interface call log for subsequent analysis and tracking; the data visualization module is used to display the audit results and abnormal information data to users in the form of charts and reports to improve the readability and comprehensibility of the data.

Images