Centralized control station information interaction system and method based on digital platform

Abstract

The invention discloses a centralized control station information interaction system and method based on a digital platform, and the system comprises a signal collection module which collects accident information and abnormal information in each transformer substation in real time; the signal processing module is used for starting a defect-eliminating closed-loop processing flow according to the accident information and the abnormal information and tracking the accident information and the abnormal information which cannot be processed in a closed-loop manner; the defect disposal module is used for performing equipment defect identification on the accident information and the abnormal information based on a preset rule, and starting a defect disposal process after the equipment defect is found; the information query module is used for querying completion conditions of defect-eliminating different disposal processes on different dates and performing work quality and efficiency evaluation; according to the invention, through accident and abnormal information acquisition, information processing, defect processing and information recording, a closed-loop management system is constructed, the timeliness of information interaction is improved, and the problem that information notification is not timely in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system automation, and in particular to a centralized control station information interaction system and method based on a digital platform. Background Art

[0002] With the accelerated advancement of the construction of new power systems, the scale of power grid equipment is growing exponentially, and the safety and stability of power grid operations are facing unprecedented challenges. The working mode of the centralized control station needs to adapt to the real-time monitoring requirements of large power grids with multi-business collaboration, multi-task parallelism, and multi-information sharing. However, the current information exchange between the centralized control station and substation operation and maintenance personnel is still highly dependent on traditional manual means, such as single modes such as telephone notification delivery, which can no longer cope with the needs of massive data processing, resulting in a high information transmission delay rate, which seriously threatens the safe operation of the power grid.

[0003] Currently, centralized control stations lack a digital platform covering the entire "monitoring-analysis-handling-archiving" process. This results in the decentralized storage of accident handling records, defect inspection data, and hidden danger investigation results in unstructured form, making it impossible to correlate and analyze multi-source data. At the same time, there are no quantitative standards for evaluating the work quality of monitoring personnel and operation and maintenance teams. Key indicators (such as defect response timeliness and handling process compliance) rely on subjective assessments, resulting in significant deviations in performance management.

[0004] In view of this, the art urgently needs a centralized control station information interaction system and method based on a digital platform to solve the above problems. Summary of the Invention

[0005] In view of the above-mentioned deficiencies in the existing technology, the present invention provides an information interaction system for a centralized control station based on a digital platform to solve the problems in the existing technology such as low information interaction efficiency, lack of full-process digital management, and lack of work quality and efficiency evaluation methods.

[0006] To achieve the above object, the technical solution adopted by the present invention is:

[0007] In a first aspect, the present invention provides an information interaction system for a centralized control station based on a digital platform, comprising a signal acquisition module, a signal processing module, a defect processing module, a defect recording module, a notification module, and an information query module;

[0008] The signal acquisition module is used to collect accident information and abnormal information in each substation in real time;

[0009] The signal processing module is used to start the closed-loop fault elimination process based on the accident information and abnormal information, and track the accident information and abnormal information that cannot be closed-loop processed;

[0010] The defect handling module is used to identify equipment defects based on accident information and abnormal information based on preset rules, and to initiate a defect handling process after an equipment defect is discovered;

[0011] The defect record module is used to automatically generate a defect record based on a pre-trained defect record model and equipment defect evidence obtained during the defect handling process; the defect record includes an equipment defect level;

[0012] The information query module is used to query the completion status of the defect elimination closed-loop disposal process and / or defect disposal process on different dates to evaluate the work quality and efficiency.

[0013] As an optional implementation, a disposal report module is also included;

[0014] The handling report module is used to classify, count and analyze all accident information and all abnormal information, and automatically generate a handling report;

[0015] The total accident information includes accident information that has been handled in a closed-loop manner and accident information that has not been handled in a closed-loop manner;

[0016] The total abnormal information includes abnormal information that has been closed-loop handled and abnormal information that has not been closed-loop handled.

[0017] As an optional implementation method, it also includes a notification module, a task overdue reminder module and a message classification reminder module;

[0018] The notification module is used to generate notifications after the closed-loop defect elimination process and / or defect handling process is initiated;

[0019] The task overdue reminder module is used to monitor the processing tasks with time limits and to remind the processing tasks of work orders that have exceeded the set time threshold and have not been closed-loop processed; the processing tasks include the closed-loop processing process for defect elimination and the defect processing process;

[0020] The message classification reminder module is used to determine the importance and urgency of the task according to the equipment defect level, and preset a reminder mode to remind relevant personnel.

[0021] As an optional implementation method, the function expression of work quality and efficiency evaluation is:

[0022] T=Q A ·T A +Q B ·T B

[0023] Where, T is the work quality and efficiency evaluation; Q A For work quality evaluation; Q B For work efficiency evaluation; TA is the weight of work quality evaluation; T B The weight for evaluating work efficiency;

[0024] Among them, the function expression of the work quality evaluation is:

[0025]

[0026] Where, is the treatment error rate; The number of handling errors; is the total number of disposals;

[0027] The functional expression of the work efficiency evaluation is:

[0028]

[0029] Where, The completion rate of defect elimination and disposal; The number of closed loops for defect elimination; is the total number of defects.

[0030] As an optional implementation method, the system is deployed on a digital cloud platform in a containerized manner;

[0031] The deployment architecture of the digital cloud platform includes an information management area, an Internet area, and an Internet side;

[0032] The information management zone is deployed with an ECS server as the data interface layer, and is equipped with an RDS relational database instance, a Redis cache instance, a load balancing SLB, a mirror repository, and a K8S container cluster;

[0033] The front-end and back-end microservices of the web application in the information management zone are deployed to the cloud platform K8S cluster through the EDAS component, and the back-end microservices of the web application are registered with the cloud platform registration center;

[0034] The Internet zone is deployed with an ECS server, and the mobile application front-end service on the Internet side is deployed on an independent ECS server in the Internet zone;

[0035] A one-way isolation device is provided between the Internet zone and the information management zone to limit direct access to the information management zone from the Internet side and only allow reverse data interaction that has passed security authentication.

[0036] In a second aspect, the present invention provides a centralized control station information interaction method based on a digital platform, which is implemented based on the centralized control station information interaction system as described above, and includes the following steps:

[0037] Real-time collection of accident information and abnormal information from each centralized control station;

[0038] Initiate a closed-loop defect elimination process based on accident and exception information, and track accident and exception information that cannot be closed-loop resolved;

[0039] Identify equipment defects based on accident information and abnormal information based on preset rules. If an equipment defect is found, initiate the defect handling process for the equipment defect.

[0040] Based on the pre-trained defect record model, the system automatically generates defect records based on the equipment defect evidence obtained during the defect handling process; the defect records include the equipment defect level;

[0041] Statistics are collected on the completion status of closed-loop handling processes and / or defect handling processes on different dates to evaluate the quality and efficiency of work.

[0042] As an optional implementation, the pre-trained defect record model may be pre-trained in the following steps:

[0043] S1. Obtain historical defect evidence data and pre-process the historical defect evidence data to construct a training set;

[0044] Among them, historical defect evidence data includes defect pictures, defect videos and defect texts;

[0045] S2. Constructing a defect recording model based on a generative adversarial network; the defect recording model includes a generator network and a discriminator network;

[0046] S3, the generator network generates random noise As input, to generate sample data that approximates the real data distribution;

[0047] S4, inputting the real data in the training set and the sample data into the discriminator network respectively to determine whether the current input is real data or generated data, and feeding the discrimination result back to the generator network;

[0048] S5. Train the generator network and the discriminator network separately and alternately until the accuracy of the sample data generated by the generator network reaches a preset value, and then stop training and output the defect record model after training.

[0049] As an optional implementation, S5 specifically includes the following steps:

[0050] Fix the generator network parameters and train the discriminator network. By maximizing the discriminator's objective function, backpropagate and update the discriminator network parameters, so that the discriminator network can better distinguish between real data and sample data.

[0051] Fix the optimized discriminator network parameters, train the generator network, and backpropagate and update the generator network parameters by minimizing the generator's objective function, so that the generator network can generate more realistic sample data;

[0052] The discriminator network and the generator network are iteratively and alternately trained so that the generator network and the discriminator network reach Nash equilibrium, the defect recording model converges to the optimum, the model parameters are saved, and a trained defect recording model is obtained.

[0053] As an optional implementation method, the objective function of the discriminator is expressed as follows:

[0054]

[0055] Where, is the objective function of the discriminator; x is a sample of the real data distribution; is the probability density function of the real data; Z is the input noise; is the real data expectation; is the discriminator network; is the probability density function of the sample data; is the sample data expectation; is the generator network;

[0056] The objective function of the generator is expressed as follows:

[0057]

[0058] Where, is the objective function of the generator.

[0059] As an optional implementation, the method further includes:

[0060] Generate a notification after initiating the closed-loop defect elimination process and / or defect resolution process;

[0061] Classify, count and analyze all accident information and all abnormal information, and automatically generate disposal reports;

[0062] The said total accident information includes accident information that has been handled in a closed-loop manner and accident information that has not been handled in a closed-loop manner; the said total abnormality information includes abnormality information that has been handled in a closed-loop manner and abnormality information that has not been handled in a closed-loop manner;

[0063] Monitor time-bound handling tasks and provide reminders for work order handling tasks that exceed the set time threshold and have not been closed-loop handled; the handling tasks include defect elimination closed-loop handling processes and defect handling processes;

[0064] According to the equipment defect level, the importance of the task is determined, and a reminder mode is preset to remind relevant personnel.

[0065] The beneficial effects brought about by the embodiments provided by the present invention include:

[0066] The present invention constructs an automated closed-loop management system for monitoring, analysis, disposal and archiving through accident and abnormal information collection, accident and abnormal information disposal, equipment defect disposal and information recording, thereby improving the timeliness and accuracy of information interaction and solving the problems of single interaction means and untimely information notification in the existing technology.

[0067] The present invention uses a pre-trained defect record model to automatically identify uploaded defect evidence and generate standardized defect records, significantly reducing manual recording errors and improving defect handling efficiency; the present invention automatically generates staff work quality and efficiency evaluation by quantifying the completion status of the exception handling process and / or defect handling process, thereby improving the objectivity and scientific nature of the work quality and efficiency evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0069] Figure 1 It shows a structural block diagram of the centralized control station information interaction system in the embodiment of this specification;

[0070] Figure 2 The following diagram shows the deployment architecture of the digital cloud platform in the embodiment of this specification;

[0071] Figure 3 The flowchart of the centralized control station information interaction method in the embodiment of this specification is shown. DETAILED DESCRIPTION

[0072] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0073] However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0075] Example 1

[0076] like Figure 1 As shown, this embodiment discloses an information interaction system for a centralized control station based on a digital platform, including a signal acquisition module, a signal processing module, a defect processing module, a defect recording module, a notification module, and an information query module;

[0077] Signal acquisition module, used to collect accident information and abnormal information in each substation in real time;

[0078] Specifically, accident information refers to alarm information of circuit breaker tripping, protection and safety control device operation output caused by power grid failure, equipment failure, etc., as well as other information that affects the safe operation of the entire station. It is important information that needs to be monitored in real time and processed immediately; the abnormal information is alarm information reflecting abnormal equipment operation and information that affects the remote control operation of the equipment. It directly threatens the safety of the power grid and equipment operation, and is important information that needs to be monitored in real time and processed in a timely manner.

[0079] The signal processing module is used to initiate a closed-loop fault elimination process based on accident and abnormal information, and to track accident and abnormal information that cannot be closed-loop processed;

[0080] Among them, accident information and abnormal information that cannot be closed-loop handled are generated due to failure to eliminate defects in a timely manner, so they need to be tracked to urge the completion of the closed-loop defect elimination.

[0081] The defect handling module is used to identify equipment defects based on accident information and abnormal information based on preset rules, and initiate the defect handling process after the equipment defect is discovered;

[0082] Specifically, based on the collected accident and abnormal information, equipment defects are identified according to preset rules. Once the defect is identified and confirmed by the remote monitor, the defect handling process is initiated;

[0083] The defect handling process includes dispatching operations and maintenance personnel to conduct on-site verification and upload defect evidence. After verification, defect handling and defect elimination acceptance are carried out to complete the closed-loop handling. Pre-set rules can be set according to specific power regulations, such as the "Power System Dispatching Regulations" and the "Power Equipment Defect Management Regulations."

[0084] The defect record module is used to automatically generate defect records based on the pre-trained defect record model and the equipment defect evidence obtained during the defect handling process;

[0085] Specifically, the pre-trained defect record model is a model built based on a generative adversarial network. A training set is constructed using historical defect evidence data to train the defect record model, allowing it to learn the various features of the training set.

[0086] The defect record module can call the model to automatically generate defect records after receiving defect pictures and defect videos;

[0087] In some embodiments, the defect record includes the time of discovery of the equipment defect and the equipment defect level; wherein, the equipment defect level includes critical defects, serious defects and general defects; the time of discovery of the equipment defect is recorded to arrange the equipment maintenance plan and record the defect handling status. The handling time limit for critical defects shall not exceed 1 day, for serious defects shall not exceed 1 month, and for general defects shall not exceed one maintenance cycle (for example, 3 months to 12 months).

[0088] The information query module is used to query the completion status of the defect elimination closed-loop disposal process and / or defect disposal process on different dates to evaluate the work quality and efficiency;

[0089] Among them, work quality and efficiency evaluation includes work quality evaluation and work efficiency evaluation;

[0090] Specifically, the function expression of work quality and efficiency evaluation is:

[0091] T=Q A ·T A +Q B ·T B

[0092] Where, T is the work quality and efficiency evaluation; Q A For work quality evaluation; Q B For work efficiency evaluation; T A is the weight of work quality evaluation; T B The weight for evaluating work efficiency;

[0093] Among them, the function expression of work quality evaluation is:

[0094]

[0095] Where, is the treatment error rate; The number of handling errors; is the total number of disposals;

[0096] Among them, the function expression of work efficiency evaluation is:

[0097]

[0098] Where, The completion rate of defect elimination and disposal; The number of closed loops for defect elimination; is the total number of defects.

[0099] In this embodiment, the total number of disposals refers to the total number of closed-loop disposals and defect disposals, and the number of disposal errors refers to the total number of closed-loop disposals and defect disposals that failed to be closed-loop disposed. That is, the lower the disposal error rate, the higher the work quality.

[0100] The total number of defects refers to the number of all equipment defects discovered, and the number of defect elimination closed-loop defects refers to the number of equipment defects that have been closed-loop resolved. That is, the higher the defect elimination completion rate, the higher the work efficiency.

[0101] Exemplarily, the system further includes a treatment reporting module.

[0102] Specifically, the handling report module is used to classify, count and analyze all accident information and all abnormal information, and automatically generate a handling report;

[0103] Among them, all accident information includes accident information that has been closed-loop handled and accident information that has not been closed-loop handled; all abnormal information includes abnormal information that has been closed-loop handled and abnormal information that has not been closed-loop handled;

[0104] In some embodiments, the accident information handling report includes: fault time, faulty equipment, short-circuit current, fault distance, protection action status, and fault recording, which is used to assist the centralized control station in reporting to the relevant dispatcher in a timely manner and notify the operation and maintenance team to conduct on-site inspections;

[0105] The abnormal information handling report includes: the time when the abnormality occurred and the abnormal equipment, which is used to assist the centralized control station in determining whether to notify the operation and maintenance team to conduct on-site inspection and processing. If it affects the normal operation of primary and secondary equipment within the dispatch jurisdiction, it should be reported to the relevant dispatch.

[0106] Exemplarily, the system further includes a notification and announcement module;

[0107] Specifically, the notification and announcement module is used to generate notifications and announcements after the closed-loop defect elimination process and / or defect handling process is initiated;

[0108] Exemplarily, the system further includes a task overdue reminder module;

[0109] Specifically, the task overdue reminder module is used to monitor the processing tasks with time limits and to remind the processing tasks of work orders that have exceeded the set time threshold and have not been closed-loop processed; the processing tasks include the closed-loop processing process for defect elimination and the defect processing process;

[0110] Exemplarily, the system further includes a message classification reminder module;

[0111] Specifically, the message classification reminder module is used to determine the importance and urgency of tasks based on the level of equipment defects, and preset reminder modes to remind relevant personnel;

[0112] In this embodiment, the alarm information can be pushed through differentiated methods such as sound and light alarms, pop-up mandatory reminders, and to-do lists to remind relevant personnel.

[0113] like Figure 2 As shown, in some embodiments, the system is deployed on a digital cloud platform in a containerized manner;

[0114] Specifically, the deployment architecture of the digital cloud platform includes the information management area, the Internet area, and the Internet side;

[0115] The information management zone deploys ECS servers as the data interface layer, configured with RDS relational database instances, Redis cache instances, load balancing SLB, image repositories, and K8S container clusters. The front-end and back-end microservices of web applications in the information management zone are deployed to the cloud platform K8S cluster via EDAS components, and the back-end microservices of web applications are registered with the cloud platform registration center.

[0116] Among them, ECS servers are deployed in the Internet zone, and the mobile application front-end services on the Internet side are deployed on independent ECS servers in the Internet zone; a one-way isolation device is set up between the Internet zone and the information management zone to limit direct access to the information management zone from the Internet side, and only reverse data interaction that has passed security authentication is allowed.

[0117] In this embodiment, the centralized control station information interaction system based on a digital platform deeply integrates cloud computing, big data analysis, and artificial intelligence algorithms. The signal acquisition module collects substation accident and anomaly information in real time. The signal handling module uses preset rules to initiate the fault elimination process and track unclosed-loop tasks. The defect handling module identifies equipment defects based on preset rules, initiates on-site verification and fault elimination acceptance, and automatically generates defect records for uploaded defect images and videos by calling a pre-trained defect record model. The centralized control station information system is deployed on a digital cloud platform to achieve flexible resource scheduling, support the storage and mining of massive data, and ensure data interaction security based on a secure partitioning architecture (unidirectional isolation between the information management zone and the Internet zone). In addition, the expanded overdue reminder function (task overdue reminder module), message classification push function (message classification reminder module), and multi-dimensional data statistical analysis function (information query module) further optimize operation and maintenance decision-making efficiency, achieve closed-loop management of equipment status throughout the entire process, and significantly improve the power grid equipment status perception capability and operation and maintenance reliability.

[0118] Example 2

[0119] like Figure 3 As shown, this embodiment adopts a centralized control station information interaction method based on a digital platform, which is implemented based on the centralized control station information interaction system described in Example 1 and includes the following steps:

[0120] Real-time collection of accident information and abnormal information from each centralized control station;

[0121] For accident tripping information and abnormal information, start the closed-loop fault elimination process and track accident information and abnormal information that cannot be closed-loop handled;

[0122] Identify equipment defects based on accident information and abnormal information based on preset rules. If an equipment defect is found, initiate the defect handling process for the equipment defect.

[0123] Based on the pre-trained defect record model, the system automatically generates defect records based on the equipment defect evidence obtained during the defect handling process. The defect records include the time the equipment defect was discovered and the equipment defect level.

[0124] Statistics are collected on the completion status of closed-loop handling processes and / or defect handling processes on different dates to evaluate the quality and efficiency of work.

[0125] Exemplarily, the method further includes:

[0126] Generate a notification after initiating the closed-loop defect elimination process and / or defect resolution process;

[0127] Classify, count and analyze all accident information and all abnormal information, and automatically generate disposal reports;

[0128] The said total accident information includes accident information that has been handled in a closed-loop manner and accident information that has not been handled in a closed-loop manner; the said total abnormality information includes abnormality information that has been handled in a closed-loop manner and abnormality information that has not been handled in a closed-loop manner;

[0129] Monitor time-bound handling tasks and provide reminders for work order handling tasks that exceed the set time threshold and have not been closed-loop handled; the handling tasks include defect elimination closed-loop handling processes and defect handling processes;

[0130] Determine the importance and urgency of tasks based on the equipment defect level, and preset reminder modes to remind relevant personnel.

[0131] In some embodiments, the defect handling process includes dispatching operation and maintenance personnel to conduct on-site verification and upload defect evidence. After the verification is passed, defect processing and defect elimination acceptance are carried out to complete the closed-loop handling.

[0132] In some embodiments, the pre-trained defect record model may be pre-trained in the following steps:

[0133] S1. Obtain historical defect evidence data and pre-process the historical defect evidence data to construct a training set;

[0134] Among them, historical defect evidence data includes defect pictures, defect videos and defect texts;

[0135] S2. Constructing a defect recording model based on a generative adversarial network; the defect recording model includes a generator network and a discriminator network;

[0136] S3, the generator network generates random noise As input, to generate sample data that approximates the real data distribution;

[0137] S4, inputting the real data in the training set and the sample data into the discriminator network respectively to determine whether the current input is real data or generated data, and feeding the discrimination result back to the generator network;

[0138] S5. Train the generator network and the discriminator network separately and alternately until the accuracy of the sample data generated by the generator network reaches a preset value, and then stop training and output the defect record model after training.

[0139] Specifically, S5 includes the following steps:

[0140] Fix the generator network parameters and train the discriminator network. By maximizing the discriminator's objective function, backpropagate and update the discriminator network parameters, so that the discriminator network can better distinguish between real data and sample data.

[0141] Fix the optimized discriminator network parameters, train the generator network, and backpropagate and update the generator network parameters by minimizing the generator's objective function, so that the generator network can generate more realistic sample data;

[0142] The discriminator network and the generator network are iteratively and alternately trained so that the generator network and the discriminator network reach Nash equilibrium, the defect recording model converges to the optimum, the model parameters are saved, and a trained defect recording model is obtained.

[0143] Among them, the generator network and the discriminator network reaching Nash equilibrium refers to the ideal state of generative adversarial network (GAN) training, which means that the two reach a dynamically stable relationship through game theory, and neither party can gain greater advantage by unilaterally changing its strategy. That is, when the output probabilities of the generator network and the discriminator network are both close to 0.5, the defect recording model converges to the optimal state.

[0144] Specifically, the objective function of the discriminator is expressed as follows:

[0145]

[0146] Where, is the objective function of the discriminator; x is a sample of the real data distribution; is the probability density function of the real data; Z is the input noise; is the real data expectation; is the discriminator network; is the probability density function of the sample data; is the sample data expectation; is the generator network;

[0147] Specifically, the objective function of the generator is expressed as follows:

[0148]

[0149] Where, is the objective function of the generator.

[0150] To sum up, in this embodiment, the signal acquisition module collects accident and abnormal information in real time, the signal handling module starts the closed-loop defect elimination process, the defect handling module identifies equipment defects based on preset rules, and starts the defect handling process for equipment defects, uses the defect recording module to generate defect records, and combines the information query module to query the completion status of different handling processes to build a full-link automated closed-loop management system of "information monitoring, defect analysis, defect elimination and disposal, defect disposal and information archiving", which effectively improves the timeliness and accuracy of information interaction, and solves the problem of single interaction means and untimely information notification in existing technologies.

[0151] In this embodiment, a pre-trained defect record model automatically identifies uploaded defect evidence and generates standardized defect records, significantly reducing manual recording errors and improving defect handling efficiency. This embodiment also quantifies the completion of exception handling and / or defect handling processes to automatically generate staff work quality and efficiency evaluations, enhancing the objectivity and scientific nature of work quality and efficiency assessments. This embodiment effectively ensures the security of core power grid data through a secure isolation architecture between the information management zone and the internet zone, namely, one-way isolation devices and encrypted storage technology in the RDS database.

[0152] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A centralized control station information interaction system based on a digital platform, characterized in that: It includes signal acquisition module, signal processing module, defect processing module, defect recording module, notification module and information query module; The signal acquisition module is used to collect accident information and abnormal information in each substation in real time; The signal processing module is used to start the closed-loop fault elimination process based on the accident information and abnormal information, and track the accident information and abnormal information that cannot be closed-loop processed; The defect handling module is used to identify equipment defects based on accident information and abnormal information based on preset rules, and to initiate a defect handling process after an equipment defect is discovered; The defect recording module is used to automatically generate defect records based on the pre-trained defect recording model and the equipment defect evidence obtained during the defect handling process; The defect record includes the equipment defect level; The information query module is used to query the completion status of the defect elimination closed-loop disposal process and / or defect disposal process on different dates to evaluate the work quality and efficiency.

2. The system according to claim 1, wherein: Also included is a disposition reporting module; The handling report module is used to classify, count and analyze all accident information and all abnormal information, and automatically generate a handling report; The total accident information includes accident information that has been handled in a closed-loop manner and accident information that has not been handled in a closed-loop manner; The total abnormal information includes abnormal information that has been closed-loop handled and abnormal information that has not been closed-loop handled.

3. The system according to claim 1, wherein: It also includes a notification module, a task overdue reminder module, and a message classification reminder module; The notification module is used to generate notifications after the closed-loop defect elimination process and / or defect handling process is initiated; The task overdue reminder module is used to monitor the processing tasks with time limits and to remind the processing tasks of work orders that have exceeded the set time threshold and have not been closed-loop processed; the processing tasks include the closed-loop processing process for defect elimination and the defect processing process; The message classification reminder module is used to determine the importance and urgency of the task according to the equipment defect level, and preset a reminder mode to remind relevant personnel.

4. The system according to claim 1, wherein: The function expression of work quality and efficiency evaluation is: T=Q A ·T A +Q B ·T B； Where, T is the work quality and efficiency evaluation; Q A For work quality evaluation; Q B For work efficiency evaluation; T A is the weight of work quality evaluation; T B The weight for evaluating work efficiency; Among them, the function expression of the work quality evaluation is: ； Where, is the treatment error rate; The number of handling errors; is the total number of disposals; The functional expression of the work efficiency evaluation is: ； Where, The completion rate of defect elimination and disposal; The number of closed loops for defect elimination; is the total number of defects.

5. The system according to claim 1-4, characterized in that The system is deployed on a digital cloud platform in a containerized manner; The deployment architecture of the digital cloud platform includes an information management area, an Internet area, and an Internet side; The information management zone is deployed with an ECS server as the data interface layer, and is equipped with an RDS relational database instance, a Redis cache instance, a load balancing SLB, a mirror repository, and a K8S container cluster; The front-end and back-end microservices of the web application in the information management zone are deployed to the cloud platform K8S cluster through the EDAS component, and the back-end microservices of the web application are registered with the cloud platform registration center; The Internet zone is deployed with an ECS server, and the mobile application front-end service on the Internet side is deployed on an independent ECS server in the Internet zone; A one-way isolation device is provided between the Internet zone and the information management zone to limit direct access to the information management zone from the Internet side and only allow reverse data interaction that has passed security authentication.

6. A centralized control station information interaction method based on a digital platform, characterized in that: The information interaction system of the centralized control station according to any one of claims 1 to 5 is implemented, comprising the following steps: Real-time collection of accident information and abnormal information from each centralized control station; Initiate a closed-loop defect elimination process based on accident and exception information, and track accident and exception information that cannot be closed-loop resolved; Identify equipment defects based on accident information and abnormal information based on preset rules. If an equipment defect is found, initiate the defect handling process for the equipment defect. Based on the pre-trained defect record model, the system automatically generates defect records based on the equipment defect evidence obtained during the defect handling process; the defect records include the equipment defect level; Statistics are collected on the completion status of closed-loop handling processes and / or defect handling processes on different dates to evaluate the quality and efficiency of work.

7. The method according to claim 6, characterized in that The method further comprises: Generate a notification after initiating the closed-loop defect elimination process and / or defect resolution process; Classify, count and analyze all accident information and all abnormal information, and automatically generate disposal reports; The said total accident information includes accident information that has been handled in a closed-loop manner and accident information that has not been handled in a closed-loop manner; the said total abnormality information includes abnormality information that has been handled in a closed-loop manner and abnormality information that has not been handled in a closed-loop manner; Monitor time-bound handling tasks and provide reminders for work order handling tasks that exceed the set time threshold and have not been closed-loop handled; the handling tasks include defect elimination closed-loop handling processes and defect handling processes; According to the equipment defect level, the importance of the task is determined, and a reminder mode is preset to remind relevant personnel.

8. The system according to claim 6, wherein: The pre-trained defect recording model has the following pre-training steps: S1. Obtain historical defect evidence data and pre-process the historical defect evidence data to construct a training set; Among them, historical defect evidence data includes defect pictures, defect videos and defect texts; S2. Constructing a defect recording model based on a generative adversarial network; the defect recording model includes a generator network and a discriminator network; S3, the generator network generates random noise As input, to generate sample data that approximates the real data distribution; S4, inputting the real data in the training set and the sample data into the discriminator network respectively to determine whether the current input is real data or generated data, and feeding the discrimination result back to the generator network; S5. Train the generator network and the discriminator network separately and alternately until the accuracy of the sample data generated by the generator network reaches a preset value, and then stop training and output the defect record model after training.

9. The system according to claim 8, characterized in that The S5 specifically includes the following steps: Fix the generator network parameters and train the discriminator network. By maximizing the discriminator's objective function, backpropagate and update the discriminator network parameters, so that the discriminator network can better distinguish between real data and sample data. Fix the optimized discriminator network parameters, train the generator network, and backpropagate and update the generator network parameters by minimizing the generator's objective function, so that the generator network can generate more realistic sample data; The discriminator network and the generator network are iteratively and alternately trained so that the generator network and the discriminator network reach Nash equilibrium, the defect recording model converges to the optimum, the model parameters are saved, and a trained defect recording model is obtained.

10. The system according to claim 9, characterized in that The objective function of the discriminator is expressed as follows: ； Where, is the objective function of the discriminator; x is a sample of the real data distribution; is the probability density function of the real data; Z is the input noise; is the real data expectation; is the discriminator network; is the probability density function of the sample data; is the sample data expectation; is the generator network; The objective function of the generator is expressed as follows: ； Where, is the objective function of the generator.

Images