41 results about "Operations order" patented technology

The invention provides an industry vertical data fine tuning method and device based on a large model, and the method comprises the steps: obtaining an operation order text data flow, carrying out the preliminary structural processing of each operation order text, extracting an operation action, an execution object and a constraint condition, and forming text data carrying an initial label; determining an operation process directed acyclic graph and an emergency operation process network according to the fine tuning corpus of the text classification model, and taking the operation process directed acyclic graph and the emergency operation process network as structured training samples for fine tuning of the text classification model; determining a mixed training batch of fine tuning of the text classification model according to the structured training sample of fine tuning of the text classification model, and setting a dynamic balance threshold value of the standard operation sample and the emergency operation sample; and after fine tuning of the text classification model is completed and deployment is carried out, if the operation ticket text to be examined belongs to emergency operation, parallel or conditional branch logic reasoning processing is carried out based on the structure of the emergency operation process network, and a structured examination report is output.

The invention aims to provide the intelligent switching operation ticket forming system and method based on the large model, which are high in efficiency, high in accuracy and low in cost. The system comprises a data access layer (1), a knowledge support layer (2), an intelligent agent execution layer (3), an application layer (4) and a self-learning optimization layer (5). The method comprises the following steps: S1, a data access layer obtains a scheduling instruction and equipment real-time data and transmits the scheduling instruction and the equipment real-time data to an intelligent agent execution layer; s2, an instruction analysis agent (31) analyzes the scheduling instruction to generate structured feature parameters; s3, the statement generation agent (32) generates an operation ticket first draft in combination with the feature parameters, the topological data and the finished ticket knowledge base; s4, performing logic, normative and multi-ticket comparison verification on the first draft by the verification agent (33), and outputting a verification result; and S5, the application layer displays the operation order passing the verification, and feeds back the data to the self-learning optimization layer to update the system. The method is applied to the technical field of power system operation and maintenance intelligentization.

The invention discloses a cooperative generation and closed-loop checking method, system and device for primary and secondary device operation tickets of an electric power system and a storage medium, and the cooperative generation and closed-loop checking method for the primary and secondary device operation tickets comprises the steps: constructing a primary device ticket forming rule tree, and according to a dynamic binding relationship between a primary device rule and a secondary device rule chain, establishing a secondary device ticket forming rule tree; according to the method, intelligent alternate generation of primary and secondary operation steps is realized, and in the invoicing process, consistency checking of primary and secondary equipment state logic is synchronously carried out: through a forward reasoning and reverse tracking mechanism, whether a primary and secondary equipment state mapping relation before and after each step of operation is correct is judged in real time, and an alarm is given for an inconsistent condition. Therefore, self-verification of safety logic is completed while the operation order is generated, a complete closed loop of generation-simulation-check is formed, and the accuracy of the operation order and the safety of field operation are remarkably improved.

The invention relates to the technical field of artificial intelligence. The operation ticket checking method, system and device based on the rule atlas and the medium are provided, and the method comprises the steps that feature extraction is conducted on a topology change event sent by a power grid monitoring system, and an affected device set and connection relation change features are obtained; dynamically associating logic symbols in a preset static rule atlas based on the affected equipment set and the connection relationship change characteristics to generate an executable check atlas; performing topological evolution simulation on the obtained operation order instruction sequence to generate an expected topological state chain; and for each topology state in the expected topology state chain, calling an executable checking graph to perform rule checking, and outputting a checking result set, so as to improve the adaptability of a rule base to dynamic topology, enhance the simulation capability of operation chain time sequence evolution and reduce the hidden risk of a transition state.

The invention relates to the technical field of electrical operation supervision, in particular to a power operation order compliance automatic identification system and method. The power operation ticket compliance automatic identification system comprises a data import module which is used for receiving and analyzing structured operation ticket text data and associating and importing a video file of a corresponding operation execution process; the multi-modal data processing module comprises a voice recognition unit and a video analysis unit; the compliance analysis module is used for comparing and analyzing the output results of the voice recognition unit and the video analysis unit with the operation ticket text data and judging the compliance of the operation process; and the report generation module is used for generating a structured compliance review report. Through cooperative work of the multi-modal data processing module and the compliance analysis module, automatic analysis of an operation order execution process is realized, the problems of missed judgment and misjudgment caused by subjective factors are avoided, and objectivity and fairness of an examination result are ensured.

The invention discloses a two-ticket operation ticket intelligent verification execution system driven by AR glasses, and belongs to the technical field of electric power operation and maintenance. The system comprises an operation order verification module, a risk assessment module, an AR task interaction module, an execution confirmation module and a system central control module. The operation order verification module performs format normalization and step sequence logicality verification on the operation order, and after the verification is passed, the operation steps are decomposed into operation sub-steps to be stored in a step library; the risk assessment module performs risk scoring on each operation sub-step to obtain a risk value of each operation sub-step; the AR task interaction module identifies target equipment through AR glasses and presents operation sub-steps and risk values; the execution confirmation module receives the sub-step interaction completion instruction; and the system central control module realizes module asynchronous communication and pushes the next operation sub-step. The AR technology is combined with intelligent verification, the operation ticket execution process is standardized, the operation risk is prompted in real time, and the standardization, safety and efficiency of electric power operation and maintenance operation are improved.

The invention aims to provide the switching operation ticket multi-dimensional intelligent verification system and verification method with high accuracy and integrity. The system comprises a data acquisition module (1), an objectification processing module (2), a multi-dimensional verification module (3), a result output module (4) and a verification rule iteration module (5). The method comprises the following steps: T1, a data acquisition module obtains an operation order to be verified and associated data; t2, analyzing the operation ticket into triple data by the objectification processing module; t3, a multi-dimensional verification module sequentially executes topological logic verification, normalization verification, cross-ticket comparison verification and real-time state matching; t4, a result output module generates a verification report containing question types, positions and rectification suggestions; and T5, the verification rule iteration module updates the verification rule base based on manual auditing feedback. The method is applied to the technical field of power safety operation and maintenance.

The invention discloses a construction industry warehouse order time consumption prediction method and system based on machine learning. The method comprises the steps of collecting order data and cleaning the order data; constructing a multivariable feature set and carrying out one-hot coding; an XGBoost model is adopted for training, and parameters are optimized through grid search and random search; a prediction interface is deployed to a warehouse management system, the system comprises a data acquisition module, a data preprocessing module, a feature engineering module, a model training module, a prediction interface module and a prediction module, and tests show that the prediction precision Rreaches 0.85, the MAE is 10.6 minutes, the scheduling conflict rate is reduced to 2%, and the operating cost is saved by 75% annually. The problems that a traditional method depends on manpower and is low in precision are solved.

The invention discloses an operation ticket checking method and device for a transformer substation, relates to the technical field of electric power, and mainly aims to improve the accuracy of an operation ticket checking result. According to the main technical scheme, the method comprises the steps of obtaining a to-be-verified operation ticket, and analyzing an operation item and a check item in the to-be-verified operation ticket; checking whether the sequence relationship between the operation item and the check item is correct or not according to a preset sequence checking model and a colored Petri net model; if yes, verifying whether each operation item meets an execution condition or not according to a vector knowledge base corresponding to the operation locking logic and the real-time state of equipment involved in each operation item; if each operation item meets the execution condition, aiming at each equipment node in a preset equipment knowledge graph, extracting an operation item set having an association relationship with each equipment node from each operation item, and performing operability verification on the operation item set according to a preset five-prevention management rule; and if the operation item set of each equipment node is operable, determining that the to-be-verified operation ticket passes verification.

This invention provides a method and system for checking the pressure plate of a power transmission operation ticket. The method includes: counting the total number of pressure plate operation items and pressure plate inspection items for each cabinet in the power transmission operation ticket; determining the percentage of this total number relative to the actual total number of pressure plates for the corresponding cabinet; if this percentage reaches or exceeds a preset threshold, marking the cabinet as a high-risk suspected omission point; when a cabinet is marked as a high-risk suspected omission point, matching the operation task with a preset custom power outage operation task terminology rule library; if the operation task does not meet the preset representative power outage operation task, it is determined to be a real omission; if the operation task meets the preset representative power outage operation task, the operation ticket is determined to be a power outage operation; after all cabinets have been checked, summarizing the check results for all cabinets and outputting an inspection report. This invention achieves a leap from manual item-by-item verification to automatic, second-level screening by the system, significantly shortening the review time and significantly improving the alarm accuracy.

The application discloses a kind of automatic car driving mode conversion test method, simulation simulation device, it is related to railway shunting operation technical field.The application provides scheme: after locomotive shunting mode registration, for by manual driving mode conversion to automatic shunting driving mode, construct test scene, test scene is according to the task legality of operation order, the path feasibility of shunting route, the operation safety of parking state as constraint condition to construct scene, each test scene is according to corresponding with corresponding expected result corresponding configuration, according to each test scene, test scene corresponding expected result, automatic shunting driving mode conversion is tested.The application uses "receives effective operation order", "there is correct shunting route", "is in parking state" constraint condition design test scene, from "task legality", "path feasibility" and "operation safety" three aspects construct solution that is both simple and covers comprehensive to "mode conversion" test.

The invention relates to the technical field of electric power systems, and discloses an operation order execution authority approval method, system, device, medium and product, the method comprises the following steps: predicting a prediction order corresponding to an operation sequence of an operation order by using a large language model, comparing the prediction order with an actual order, checking whether a target order of the operation order is consistent with the actual order, and if yes, executing the operation order execution authority approval. And then, comparing whether the first topological graph after the operation order rehearsal is consistent with the second topological graph of the target power station updated according to the actual dispatching order, and checking whether the expected result of the dispatching order can be accurately achieved after the operation order is executed, thereby checking the matching between the operation order execution result and the expected result of the dispatching order. Therefore, the matching and the consistency between the operation order and the dispatching order are checked, the robustness and the reliability of operation order checking can be effectively improved, and the safety and the accuracy of power grid operation are ensured.

The invention discloses a transformer substation E-key lock management method and system. The method comprises the steps that an operation order is converted into a structured sequence diagram through operation sequence modeling; dynamic permission activation is realized based on a state machine model; performing five-prevention logic real-time verification in linkage with a substation monitoring system; digital signature and bidirectional authentication are adopted to ensure instruction security; local decision execution is realized through intelligent verification of the lockset; a sequence state is automatically advanced based on an operation progress. The system comprises a management background, an intelligent mobile terminal and an intelligent electronic lock, and a complete closed-loop management system is formed. According to the invention, deep binding of lock operation and substation operation processes is realized, the technical problems of extensive management and disjunction with safety regulations of a traditional lock are solved, and the operation safety, the operation and maintenance efficiency and the system reliability are remarkably improved.

The invention relates to an electric power dispatching auxiliary system and method. The system comprises a login authentication module, a data collection module, an auxiliary dispatching operation ticket to-be-written module, an auxiliary terminal calling module, an operation progress supervision module and a data output module. The system realizes secure access through identity recognition and authentication; acquiring and transmitting a scheduling application form, an operation order and equipment running state data by using a data collection module; the auxiliary writing module determines a writing requirement through similarity calculation and generates a corresponding scheduling operation ticket; the auxiliary terminal calling module calls a related unit according to the operation order and records an unsuccessful contact condition; the operation progress supervision module counts timeout conditions caused by equipment defects or low operation speed and calculates timeout rates in a classified manner; and finally, the data output module uniformly outputs various results. According to the method, the scheduling operation ticket generation efficiency can be improved, a scheduling terminal notification and supervision mechanism is optimized, and the intelligence and safety of power scheduling work are enhanced.

The invention relates to a whole-process anti-misoperation simulation method and system for a dispatching operation order, and belongs to the technical field of dispatching automation of a power system. Comprising the following steps: constructing a power grid equipment digital twinborn model library, and integrating equipment static parameters, real-time state quantity and an anti-error rule set; generating an initial operation order step sequence based on the scheduling instruction and the power grid topology constraint; operation ticket simulation rehearsal is executed step by step in the simulation environment; generating an anti-misoperation verification report according to the simulation result, and prompting to modify or confirm the operation order; in the operation order execution stage, the state of field equipment is collected through the Internet of Things terminal, and a simulation rehearsal result and practical operation data are compared in real time; establishing an operation order full life cycle anti-error file, and associating simulation data with an actual execution record; the defect that a traditional operation ticket system depends on manual checking and cannot dynamically pre-judge linkage risks is overcome, the misoperation accident rate is remarkably reduced, and the operation safety of a power grid is improved.

The invention discloses a power transformation operation ticket intelligent analysis and remote video verification system, belongs to the technical field of power system automation and intelligent monitoring, and aims to solve the problems of low operation ticket analysis efficiency, insufficient remote verification intelligence and disjunction of analysis and verification links in the prior art. Operation information structured extraction is realized through matching of an NLP technology and a rule base; the remote video acquisition module acquires a multi-view operation video; the video intelligent verification module quantifies key indexes such as the operation step matching degree and the protective equipment recognition confidence degree through an algorithm formula based on the analysis result; the control center module stores data and generates a feedback instruction; according to the method, end-to-end automation from operation ticket text analysis to video behavior verification is realized, and the consumed time of traditional manual verification is compressed from an hour level to a second level through support of a three-level response mechanism and a millisecond-level time sequence database.

The invention discloses a local anti-misoperation system and method applied to switching of a transformer substation, the system comprises an AI glasses end and an edge calculation box end which are in communication connection with each other, and the AI glasses end comprises a data acquisition module and a man-machine interaction module; the edge calculation box end comprises a knowledge graph module which is used for storing and loading a time sequence knowledge graph of an operation order; the visual identification module is used for receiving the equipment image and identifying field equipment information; and the inference engine module is used for receiving the equipment information and the eyeball movement data, performing inference based on the time sequence knowledge graph so as to verify the compliance triggered by the current operation and the next operation, and outputting corresponding operation prompt or alarm information based on a verification result. According to the invention, localized, real-time and intelligent safety management and control of the switching operation of the transformer substation are realized through the steps of determining the knowledge graph, collecting data, identifying equipment, reasoning and checking, outputting information and the like.

The invention discloses a power transformation switching operation intelligent ticket forming method based on reinforcement learning, and relates to the technical field of power system substation automation control, and the method comprises the following steps: S1, constructing a reinforcement learning agent, and generating a preliminary operation sequence based on historical operation data; s2, establishing a real-time state sensing interface, and obtaining power grid real-time topology, equipment state and grounding wire state data; according to the power transformation switching operation intelligent ticket forming method based on reinforcement learning, the technical scheme of combining a reinforcement learning agent and a dual real-time verification mechanism is introduced, so that the intelligence level and safety of power transformation switching operation ticket generation are effectively improved. The real-time state of the power grid can be dynamically sensed, the generated operation order is ensured to conform to the safety rule of the power grid and be strictly matched with the actual state of field equipment through logic consistency and operability dual verification, and the risk of misoperation caused by manual negligence or information lag is fundamentally reduced.

The invention discloses a power grid operation order sorting method and device, terminal equipment and a storage medium, and belongs to the technical field of power grid operation order sorting, and the method comprises the steps: obtaining a power grid topological feature matrix of a power grid and an operation step feature matrix of an operation order to be sorted, and inputting the matrixes into a preset sorting model, the confidence coefficient of each to-be-sorted operation order is obtained through calculation of a preset sorting model; and finally, according to the confidence coefficient and the topological characteristic matrix of the power grid, performing repeated sorting operation on the operation orders to be sorted until the current step sequence contains all the operation orders to be sorted, obtaining a sorting result of the operation orders, and scheduling the power grid according to the sorting result of the operation orders. By implementing the method and the device, the problems that in the prior art, a sorting mode depending on artificial experience is difficult to meet efficient and accurate scheduling requirements, and a high sorting error rate is easily caused can be solved.

A setting support system includes: a first reception unit that receives, regarding a setting of sequence control that controls a series of operations in a machine, inputs of component information indicating an operation component that operates in the series of operations and operation order information indicating an operation order of the operation component; a processing unit that specifies a time range in which each of a plurality of target operations constituting the series of operations is executable based on the component information and the operation order information and a logic of a sequence for the series of operations; and a display control unit that displays, on a display device, a sequence image in which a plurality of target images corresponding to each of the plurality of target operations are disposed in an execution order, based on the time range specified for each of the plurality of target operations.

The invention relates to a typical operation ticket intelligent revision method. The method comprises the following steps: obtaining equipment information in a transformer substation and power grid topological structure data; calculating the similarity theta between the operation task and a typical operation ticket stored in a typical operation ticket database, sorting, taking the maximum value theta max for judgment, if the theta max is greater than or equal to 0.6 and less than 0.9, judging that part of the operation task is similar, and entering the step (4); and if the theta max is greater than or equal to 0.9, judging that all the theta max are consistent, and entering the step (5). According to the method, equipment information in a transformer substation and power grid topological structure data are acquired, equipment involved in an operation task is taken out according to a preset operation rule, matching with a typical operation ticket database is carried out based on related information of the operation task, a typical work ticket is extracted, and revision adjustment is carried out according to similarity; the problem of manually selecting typical work tickets similar to the actual work tickets on site is solved, the intelligent level of finished tickets is improved, the finished tickets can be conveniently and quickly issued, the workload of repairing and changing the tickets is reduced, and the ticket issuing efficiency is improved.

The invention discloses a power distribution network scheduling behavior analysis method, system and device, and a medium. The method comprises the following steps: setting a scheduling rule corresponding to a scheduling behavior; analyzing the scheduling behavior through the scheduling operation ticket to obtain each operation instruction and target equipment, and judging whether each operation instruction violates a corresponding scheduling rule or not; recording the scheduling behaviors violating the scheduling rule, and for the scheduling behaviors not violating the scheduling rule, obtaining the target equipment and various state data of a feeder line where the target equipment is located; performing data preprocessing on the state data, and establishing an effective data set; and combining the effective data set with the recorded scheduling behaviors, and establishing a normal and abnormal behavior library of power distribution network scheduling. According to the method, a preliminary dispatching operation order dispatching instruction rule is formed according to a power distribution network dispatching procedure, primary preliminary checking is firstly carried out on each instruction by utilizing analysis of a dispatching operation order, and a basic error of a power distribution network dispatching behavior is identified.

The embodiment of the invention provides a data synchronization method and device, equipment and a medium. The method comprises the following steps: acquiring to-be-synchronized data; the to-be-synchronized data comprises at least one field; determining whether the at least one field meets a preset association condition or not; under the condition that the at least one field meets a preset association condition, determining an operation sequence of operations required for performing data synchronization on the to-be-synchronized data; according to the operation sequence, performing data synchronization on the to-be-synchronized data; under the condition that synchronization of the to-be-synchronized data fails, a first time period corresponding to the to-be-synchronized data is determined, and data synchronization is conducted on the to-be-synchronized data again according to the first time period and the operation sequence; and after data synchronization is carried out again, if the to-be-synchronized data is not synchronized successfully in the preset time window, reminding information is output to the user, and the reminding information is used for reminding the user to carry out manual data synchronization on the to-be-synchronized data, so that the system can properly process the data synchronization problem.

The invention belongs to the technical field of electric digital data processing, and particularly discloses a substation regional collaborative anti-error method and system based on multi-source information, and the method comprises the steps: obtaining process data and state information from an operation order system and a real-time equipment sensor, aligning timestamps of the process data and the state information through a time synchronization algorithm to obtain fusion data under a unified time reference; according to the forced constraint and mutual exclusion constraint relationship between the fusion data extraction devices, determining the constraint type and dependency sequence of the forced constraint and mutual exclusion constraint relationship by adopting an association rule mining algorithm, and obtaining an initial structure of a link network; for a precondition in the initial structure, if it is judged that the state collection frequency is higher than a preset threshold value, a timestamp missing part is filled with an interpolation method; the invention aims to solve the problems of asynchronous equipment state and flow data time, complex constraint relation and delayed real-time interaction response in an industrial scene.

The invention relates to a railway station operation self-adaptive compiling and optimizing system fusing multi-system shunting resources, and the system comprises an information obtaining and optimizing module which is used for obtaining multi-source heterogeneous information, carrying out the preprocessing optimization of the multi-source heterogeneous information, and obtaining optimized data; the route sequence generation module is used for constructing a hierarchical model according to the optimized data and obtaining a final route sequence set; the shunting operation list automatic compiling module is used for constructing a multi-objective optimization model according to the final route sequence set and solving the multi-objective optimization model, obtaining an initial operation sequence scheme set and optimizing the initial operation sequence scheme set, and obtaining a shunting operation list; and the shunting operation management and control module is used for carrying out state monitoring and conflict pre-judgment on the shunting operation list, if no risk and abnormity occur, the shunting operation is completed, and if the risk and abnormity occur, the shunting operation list is returned to the shunting operation list automatic compiling module to optimize the shunting operation list. According to the invention, the optimal decision can be made timely and efficiently.

The application discloses a kind of task flow legitimacy verification and mistake control method, system, equipment and medium, method includes: obtaining operation instruction in power distribution network dispatching operation order, operation instruction is structured and analyzed, and task flow model is obtained;According to the task flow model, device state change model is constructed, and the device state change model is analyzed, and the legality of the power distribution network dispatching operation order is verified, and verification result is obtained;Based on the verification result, the dispatching operation order is identified potential misoperation risk, and according to the potential misoperation risk, mistake control strategy is generated, and the task flow model and the mistake control strategy are integrated, and the legality of task flow is verified and mistake control is realized, with good engineering feasibility, scalability and adaptability.

The present application relates to a kind of test script intelligent generation method and system of substation anti-misoperation dynamic check.Test method is: the content of substation interlocking logic diagram or anti-misoperation acceptance card is extracted and the anti-misoperation logic formula of fixed format is generated;Operation order is generated based on the anti-misoperation logic formula and covers positive and negative direction full acceptance;Through text matching large model, in 103 communication text, 104 point table or SCD configuration file, the path or point number matched with each description object in operation order is found and associated, to generate the first edition substation anti-misoperation dynamic check test script;Self-check is carried out to the first edition substation anti-misoperation dynamic check test script, to obtain accurate substation anti-misoperation dynamic check test script.The system includes anti-misoperation interlocking logic analysis module, anti-misoperation operation order automatic generation module, three remote signal automatic association module, anti-misoperation check script self-checking module connected in turn.The present application can guarantee the quality of substation anti-misoperation dynamic check, improve check efficiency.

The application discloses a production line scheduling method based on data and model hybrid driving, first, according to the resource position and layout, the number and type of operation orders, random noise disturbance and other elements in the flexible production line, a flexible production line scheduling model under random disturbance is constructed; then, according to the data and model hybrid driving framework, the scheduling model is solved; in the data and model hybrid driving framework, the data driving refers to the multi-agent reinforcement learning algorithm based on value decomposition, the model driving refers to the heuristic dispatching rule and experience knowledge, and the hybrid driving of the two mainly embodies three aspects: one is that the scheduling rule is used for guiding the agent strategy selection, two is that the reward function is designed based on the scheduling scene knowledge, and three is that the historical experience and data are supervised to train the noise detection and denoising module; finally, in the disturbance environment, the production line scheduling is carried out by adopting the data and model hybrid driving method, and the application is used for solving the flexible production scheduling under random disturbance.

The invention relates to the technical field of power system safety and stability control, in particular to a remote safety regulation and control method and system for a low-frequency and low-voltage load shedding device, electronic equipment and a medium. The method comprises the following steps: firstly, acquiring running state data of the low-frequency and low-voltage load shedding device and real-time running data of a power grid; based on the running state data and the real-time running data of the power grid, generating a standardized operation ticket of the low-frequency and low-voltage load shedding device through the cloud platform; the standardized operation order is transmitted to side equipment through a safety pipeline; and performing instruction verification on the received standardized operation order through the side equipment, and after the instruction verification is passed, executing local logic locking verification based on the real-time operation data of the power grid so as to generate a security permission allowing instruction issuing. By means of the mode, the problem that it is difficult to achieve efficient and reliable management of remote modification of the low-frequency and low-voltage load shedding device under the condition that safety is guaranteed in the prior art is solved, and the intelligent level and operation and maintenance efficiency of power grid safety control are improved.

The invention discloses an operation order verification method, device and equipment in a power system, a medium and a product. The method comprises the following steps: extracting operation steps in an operation order in a power system in a segmented manner, and performing semantic recognition on each operation step to generate structured step data; the structured step data comprises a step serial number, a target device, an execution action and a constraint condition; taking the equipment ledger ID of the target equipment as an index, and obtaining a target rule corresponding to the target equipment from a pre-constructed weighting rule knowledge graph; if the verification condition of the target rule depends on the real-time data, concurrently calling a corresponding external data source interface to obtain the real-time data; and performing matching verification based on the real-time data and the rule logic of the target rule, and generating a verification report according to a verification result. According to the embodiment of the invention, the verification efficiency and accuracy can be improved, the omission ratio is reduced, and the self-adaptive capability of the knowledge base is improved.