Generation method and device of new equipment starting scheme in power system, computer equipment, readable storage medium and program product

Abstract

The invention relates to a generation method and device of a new equipment starting scheme in a power system, equipment, a storage medium and a program product, and relates to the technical field of power control. The method can improve the compiling efficiency and accuracy of the power grid equipment starting scheme. The method comprises the steps that starting steps and conditional statements are trained according to historical operation data and an operation-description data set, and a starting step model and a starting condition model are obtained; performing feature extraction in the power grid topology model by using a graph attention neural network to obtain topological features, and generating a corpus according to an equipment name library and a starting operation word segmentation text library; based on the starting step model and the starting condition model, generating an initial starting scheme of new equipment in the current power system in combination with the topological features and a corpus; and replacing the description of the same operation in the initial start-up scheme with a standard description, and integrating the initial start-up scheme according to the manual intervention supplementary information to obtain a target start-up scheme of new equipment in the current power system.

Description

Technical Field

[0001] The present application relates to the field of power control technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for generating a new device startup plan in a power system. Background Art

[0002] The startup plan is an important guarantee for the safe operation of the power system. Especially before new equipment is put into use, a detailed startup plan must be prepared to verify whether the equipment can operate safely. With the rapid development of the economy and the rapid growth of electricity demand, a large number of infrastructure projects are put into production every year, which puts higher requirements on the efficiency and quality of the startup plan preparation.

[0003] The startup plan preparation method in traditional technology mainly relies on manual operation. Due to human factors, this method can easily lead to low efficiency and accuracy of plan preparation. At the same time, there is also the problem of low intelligence level, which makes it difficult to meet the development needs of large-scale power grids and the goals of safe and stable operation. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for generating a new equipment startup plan in an electric power system in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for generating a new equipment startup plan in a power system, comprising:

[0006] Acquire historical operation data of power systems in multiple different regions, identify different descriptions of the same operation in the different regions in the historical operation data, and obtain an operation-description data set;

[0007] Training the startup step according to the historical operation data and the operation-description data set to obtain a startup step model, and training the conditional statement according to the historical operation data and the operation-description data set to obtain a startup condition model;

[0008] Using the preset graph attention neural network, feature extraction is performed in the power grid topology model to obtain topological features, and a corpus of startup condition text is generated based on the device name library and the startup operation word segmentation text library;

[0009] Based on the startup step model and the startup condition model, combined with the topological features and the corpus, an initial startup plan for new equipment in the current power system is generated;

[0010] The descriptions of the same operations in the initial startup plan are replaced with standard descriptions, and the initial startup plan is integrated according to the manual intervention supplementary information to obtain a target startup plan for the new equipment in the current power system.

[0011] In one embodiment, the training of the startup step according to the historical operation data and the operation-description data set to obtain the startup step model includes:

[0012] Acquire standard operating steps in the historical operation data, and convert the standard operating steps into sequence data including command identifiers and command descriptions; use the command identifiers as inputs of the startup step model, and the command descriptions as outputs of the startup step model, train the startup step, and obtain an initial startup step model; generate a first optimizer and a first loss function based on the operation-description data set, and update the initial startup step model according to the first optimizer and the first loss function to obtain the startup step model.

[0013] In one embodiment, the training of conditional statements according to the historical operation data and the operation-description data set to obtain a start condition model includes:

[0014] Obtain standard conditional statements in the historical operation data, train the conditional statements based on the standard conditional statements and the fully connected layer, and obtain an initial startup condition model; generate a second optimizer and a second loss function based on the operation-description data set, and update the initial startup condition model according to the second optimizer and the second loss function to obtain the startup condition model.

[0015] In one embodiment, before replacing the description of the same operation in the initial startup scheme with the standard description, the method further includes:

[0016] A preset similarity calculation method is used to perform similarity analysis on different description contents of the same operation in different regions to obtain a comprehensive similarity coefficient; among the different description contents, the description content with the highest comprehensive similarity coefficient is identified as the standard description.

[0017] In one embodiment, before integrating the initial startup plan according to the manual intervention supplementary information, the method further includes:

[0018] A manual intervention interface is set up; the manual intervention interface is used to adjust the command sequence, edit the command content, and add safety check steps; the current command sequence, current command content, and current safety check steps obtained through the manual intervention interface are obtained, and the manual intervention supplementary information is generated based on the current command sequence, the current command content, and the current safety check steps.

[0019] In one embodiment, the generating an initial startup plan for a new device in the current power system based on the startup step model and the startup condition model, combined with the topology features and the corpus, includes:

[0020] Predictions are made based on the startup step model and the startup condition model to obtain the commissioning steps and commissioning conditions of the new equipment; the commissioning steps and the commissioning conditions are adjusted in combination with the topological features and the corpus, and the initial startup plan is generated based on the adjusted commissioning steps and commissioning conditions.

[0021] In a second aspect, the present application also provides a device for generating a new equipment startup plan in a power system, comprising:

[0022] A data identification module, used to obtain historical operation data of power systems in multiple different regions, identify different descriptions of the same operation in the different regions in the historical operation data, and obtain an operation-description data set;

[0023] A model training module, used to train the startup steps according to the historical operation data and the operation-description data set to obtain a startup step model, and to train the conditional statements according to the historical operation data and the operation-description data set to obtain a startup condition model;

[0024] The feature extraction module is used to extract features in the power grid topology model using a preset graph attention neural network to obtain topological features, and to generate a corpus of startup condition texts based on a device name library and a startup operation word segmentation text library;

[0025] A scheme generation module, used to generate an initial startup scheme for new equipment in the current power system based on the startup step model and the startup condition model, combined with the topological features and the corpus;

[0026] The scheme integration module is used to replace the description of the same operation in the initial startup scheme with a standard description, and integrate the initial startup scheme according to the manual intervention supplementary information to obtain the target startup scheme of the new equipment in the current power system.

[0027] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0028] Acquire historical operation data of power systems in multiple different regions, identify different descriptions of the same operation in the different regions in the historical operation data, and obtain an operation-description data set; train the startup steps according to the historical operation data and the operation-description data set to obtain a startup step model, and train the conditional statements according to the historical operation data and the operation-description data set to obtain a startup condition model; use a preset graph attention neural network to perform feature extraction in the power grid topology model to obtain topological features, and generate a corpus of startup condition texts based on the equipment name library and the startup operation segmentation text library; based on the startup step model and the startup condition model, combined with the topological features and the corpus, generate an initial startup plan for new equipment in the current power system; replace the description of the same operation in the initial startup plan with a standard description, and integrate the initial startup plan according to the supplementary information of manual intervention to obtain a target startup plan for the new equipment in the current power system.

[0029] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0030] Acquire historical operation data of power systems in multiple different regions, identify different descriptions of the same operation in the different regions in the historical operation data, and obtain an operation-description data set; train the startup steps according to the historical operation data and the operation-description data set to obtain a startup step model, and train the conditional statements according to the historical operation data and the operation-description data set to obtain a startup condition model; use a preset graph attention neural network to perform feature extraction in the power grid topology model to obtain topological features, and generate a corpus of startup condition texts based on the equipment name library and the startup operation segmentation text library; based on the startup step model and the startup condition model, combined with the topological features and the corpus, generate an initial startup plan for new equipment in the current power system; replace the description of the same operation in the initial startup plan with a standard description, and integrate the initial startup plan according to the supplementary information of manual intervention to obtain a target startup plan for the new equipment in the current power system.

[0031] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0032] Acquire historical operation data of power systems in multiple different regions, identify different descriptions of the same operation in the different regions in the historical operation data, and obtain an operation-description data set; train the startup steps according to the historical operation data and the operation-description data set to obtain a startup step model, and train the conditional statements according to the historical operation data and the operation-description data set to obtain a startup condition model; use a preset graph attention neural network to perform feature extraction in the power grid topology model to obtain topological features, and generate a corpus of startup condition texts based on the equipment name library and the startup operation segmentation text library; based on the startup step model and the startup condition model, combined with the topological features and the corpus, generate an initial startup plan for new equipment in the current power system; replace the description of the same operation in the initial startup plan with a standard description, and integrate the initial startup plan according to the supplementary information of manual intervention to obtain a target startup plan for the new equipment in the current power system.

[0033] The method, device, computer device, computer-readable storage medium and computer program product for generating the startup plan of new equipment in the above-mentioned power system automatically learn the startup steps and conditional statement patterns from historical operation data and operation-description data by adopting artificial intelligence technology, and then use the preset graph attention neural network to extract features in the power grid topology model to obtain topological features, and generate a corpus of startup condition texts based on the equipment name library and the startup operation segmentation text library, and then generate the initial startup plan of the new equipment in the current power system based on the startup step model and the startup condition model, combined with the topological features and the corpus, and finally integrate the initial startup plan according to the supplementary information of manual intervention to obtain the target startup plan of the new equipment in the current power system. In summary, the entire technical scheme proposes an intelligent compilation method for the startup plan of new power grid equipment, which improves the efficiency and accuracy of the compilation of the startup plan of power grid equipment by designing the compilation, review and commissioning process of the new equipment, and at the same time avoids the manual operation mode, effectively reduces the workload of operators, and improves the level of intelligence, which can meet the development needs of large-scale power grids and the safe and stable operation goals. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0035] FIG1 is an application environment diagram of a method for generating a new device startup plan in a power system in one embodiment;

[0036] Figure 2 A schematic diagram of a flow chart of a method for generating a new device startup plan in a power system in one embodiment;

[0037] Figure 3 A schematic diagram of a process flow of a startup step and a training step in one embodiment;

[0038] Figure 4 It is a flowchart of a method for generating a new equipment startup plan in a power system in a specific embodiment;

[0039] Figure 5 It is a structural block diagram of a device for generating a new equipment startup plan in a power system in one embodiment;

[0040] FIG. 6 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] The method for generating a new device startup scheme in a power system provided in an embodiment of the present application can be applied in an application environment as shown in FIG1 . The terminal communicates with the server via a network. The data storage system can store data that the server needs to process. The data storage system can be integrated on the server, or placed on a cloud or other network server.

[0043] Specifically, the method for generating a new equipment startup plan in a power system provided in an embodiment of the present application can be executed by a server.

[0044] Exemplarily, the server obtains historical operating data of power systems in multiple different regions, identifies different descriptions of the same operation in different regions in the historical operating data, and obtains an operation-description data set; the server trains the startup steps according to the historical operating data and the operation-description data set to obtain a startup step model, and trains the conditional statements according to the historical operating data and the operation-description data set to obtain a startup condition model; the server uses a preset graph attention neural network to extract features in the power grid topology model to obtain topological features, and generates a corpus of startup condition texts based on the equipment name library and the startup operation segmentation text library; the server generates an initial startup plan for new equipment in the current power system based on the startup step model and the startup condition model, combined with the topological features and the corpus; the server replaces the description of the same operation in the initial startup plan with a standard description, and integrates the initial startup plan based on the supplementary information of manual intervention to obtain a target startup plan for the new equipment in the current power system.

[0045] In the application environment shown in FIG1 , the terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, and tablet computers. The server may be implemented as an independent server or a server cluster consisting of multiple servers.

[0046] In one embodiment, Figure 2 As shown, a method for generating a new device startup plan in a power system is provided, and the method is applied to the server in FIG1 as an example for explanation, including the following steps:

[0047] Step S201 , obtaining historical operation data of power systems in multiple different regions, identifying different descriptions of the same operation in different regions in the historical operation data, and obtaining an operation-description data set.

[0048] Among them, historical operation data includes but is not limited to historical commissioning plans, operation manuals and power grid operation records.

[0049] Specifically, the server collects historical commissioning plans, operation manuals and grid operation records of power systems in different regions, identifies different descriptions of the same operation in different regions, obtains an operation-description data set, and stores the operation-description data set in a database.

[0050] Step S202, training the startup steps according to the historical operation data and the operation-description data set to obtain a startup step model, and training the conditional statements according to the historical operation data and the operation-description data set to obtain a startup condition model.

[0051] Specifically, the server responds to the model training instruction, trains the startup steps and conditional statements based on the historical operation data and operation-description data set, and uses sequential and non-sequential deep learning models to obtain the startup step model and the startup condition model.

[0052] Step S203, using a preset graph attention neural network, feature extraction is performed in the power grid topology model to obtain topological features, and a corpus of the startup condition text is generated based on the device name library and the startup operation word segmentation text library.

[0053] Among them, graph attention neural network is a neural network architecture for graph data, which combines the advantages of graph neural network and attention mechanism.

[0054] Specifically, the server uses a preset graph attention neural network to extract features in the power grid topology model to obtain topological features. At the same time, it forms a corpus of startup condition text based on the device name library and the startup operation word segmentation text library. This corpus will be used for training and prediction of the deep learning model.

[0055] Step S204: Based on the startup step model and the startup condition model, combined with the topological features and the corpus, an initial startup plan for new equipment in the current power system is generated.

[0056] Among them, topological features can represent the connection structure between various devices in the power system.

[0057] Specifically, based on the startup step model and the startup condition model, combined with the extracted topological features and corpus, the server model can automatically predict the steps and conditions for the commissioning of new equipment, and then integrate the predicted startup steps and conditions to generate a complete startup plan. This plan includes the order of equipment startup, the conditions that need to be met before each step, and safety measures.

[0058] Step S205 , replacing the description of the same operation in the initial startup plan with the standard description, and integrating the initial startup plan according to the manual intervention supplementary information to obtain a target startup plan for the new equipment in the current power system.

[0059] Specifically, the server performs a similarity analysis on different descriptions of the same operation in different regions, and then generates a standard description based on the obtained comprehensive similarity coefficient. The description of the same operation in the initial startup plan is replaced with the standard description, and the initial startup plan is integrated according to the supplementary information of manual intervention to obtain the target startup plan for new equipment in the current power system.

[0060] In the method for generating the startup plan of new equipment in the above power system, by adopting artificial intelligence technology, the startup steps and conditional statement patterns are automatically learned from the historical operation data and operation-description data, and then the preset graph attention neural network is used to extract features in the power grid topology model to obtain topological features, and the corpus of the startup condition text is generated according to the equipment name library and the startup operation segmentation text library, and then based on the startup step model and the startup condition model, combined with the topological features and the corpus, the initial startup plan of the new equipment in the current power system is generated, and finally the initial startup plan is integrated according to the supplementary information of manual intervention to obtain the target startup plan of the new equipment in the current power system. In summary, the entire technical scheme proposes an intelligent compilation method for the startup plan of new power grid equipment, which improves the efficiency and accuracy of the compilation of the startup plan of power grid equipment by designing the compilation, review and commissioning process of the new equipment, and at the same time avoids the manual operation mode, effectively reduces the workload of operators, and improves the level of intelligence, which can meet the development needs of large-scale power grids and the safe and stable operation goals.

[0061] In one embodiment, if Figure 3 As shown, in the above step S202, the startup step is trained according to the historical operation data and the operation-description data set to obtain the startup step model, which specifically includes the following steps:

[0062] Step S301, obtaining standard operation steps in historical operation data, and converting the standard operation steps into sequence data including command identifiers and command descriptions.

[0063] Step S302, taking the command identifier as the input of the startup step model and the command description as the output of the startup step model, training the startup step to obtain an initial startup step model.

[0064] Step S303, based on the operation-description data set, generate a first optimizer and a first loss function, and update the initial startup step model according to the first optimizer and the first loss function to obtain a startup step model.

[0065] Specifically, the startup step model training process is as follows:

[0066] S1: Collect the standard operating steps in the historical commissioning plan and convert them into sequence data. Each operating step corresponds to a command ID and command description. These data will serve as the input and output of the model.

[0067] S2: Use LSTM (Long Short-Term Memory) units to build a model because LSTM can handle long-term dependencies in sequence data. The input of the model is the command description of the previous one or more time steps, and the output is the command description of the current time step.

[0068] S3: Use historical data to train the model and update the model parameters through optimizers (such as Adam) and loss functions (such as sparse categorical cross entropy). During the training process, the model learns how to predict the next operation step based on the previous steps.

[0069] S4: Use the validation set to evaluate the performance of the model to ensure that the model can accurately predict the action steps.

[0070] In one embodiment, in the above step S202, the conditional statement is trained according to the historical operation data and the operation-description data set to obtain the start condition model, which specifically includes the following steps:

[0071] Obtain standard conditional statements in historical operation data, train the conditional statements based on the standard conditional statements and the fully connected layer, and obtain an initial startup condition model; generate a second optimizer and a second loss function based on the operation-description data set, and update the initial startup condition model according to the second optimizer and the second loss function to obtain a startup condition model.

[0072] Specifically, the training process of the startup condition model is as follows:

[0073] S1: Collect conditional statements in historical commissioning plans, which describe the conditions that must be met before a specific operation;

[0074] S2: Use a fully connected layer (Dense) to build the model because the conditional statement does not involve the time dependency of the sequence data;

[0075] S3: Use historical data to train the model, and use optimizers (such as SGD) and loss functions (such as categorical cross entropy) to update model parameters. During the training process, the model learns how to identify the conditions that meet specific operations.

[0076] S4: Use the validation set to evaluate the performance of the model to ensure that the model can accurately identify conditional sentences.

[0077] By combining the startup step model and the startup condition model, a new equipment commissioning plan can be automatically generated. The startup step model is responsible for generating ordered operation steps, while the startup condition model is responsible for identifying the conditions required for these steps. This combination ensures that the generated plan conforms to the operation logic and meets the constraints of the actual operation.

[0078] The above two models are used to automatically generate the steps of startup plan information, as follows:

[0079] A graph attention neural network (GAT) is used to extract features from the power grid topology model. These features include the connection relationships between devices and the topological structure of the power grid.

[0080] The startup steps and startup conditions text corpus are formed based on the device name library and the startup operation word segmentation text library. This corpus will be used for the training and prediction of the deep learning model.

[0081] By using the trained startup step model and startup condition model, combined with the extracted topological features and corpus, the model can automatically predict the steps and conditions for the commissioning of new equipment.

[0082] The predicted startup steps and conditions are integrated to generate a complete startup plan, which includes the order of equipment startup, the conditions that need to be met before each step, safety measures, etc.

[0083] In one embodiment, in the above step S204, based on the startup step model and the startup condition model, combined with the topological features and the corpus, an initial startup plan for new equipment in the current power system is generated, which specifically includes the following steps:

[0084] Predictions are made based on the startup step model and the startup condition model to obtain the commissioning steps and commissioning conditions of the new equipment; the commissioning steps and the commissioning conditions are adjusted in combination with the topological features and the corpus, and the initial startup plan is generated based on the adjusted commissioning steps and commissioning conditions.

[0085] Specifically, a standard description is generated based on similarity analysis, and then the description of the same operation in the startup plan is replaced with the standard description; the steps for generating the standard description are as follows:

[0086] The similarity analysis of different descriptions of the same operation in different regions is performed using methods such as cosine similarity or Jaccard similarity coefficient. The purpose is to generate the similarity q between a certain description and other descriptions of the same operation, and then obtain the comprehensive similarity coefficient of each description itself and other descriptions. , the calculation process of the comprehensive similarity coefficient is as follows:

[0087]

[0088] In the above formula, represents the comprehensive similarity coefficient, q i It represents the similarity between the current description and the i-th description, and n is the total number of descriptions collected.

[0089] In this embodiment, the similarity can be obtained by using cosine similarity or Jaccard similarity coefficient, as follows:

[0090] 1. Use cosine similarity to calculate:

[0091]

[0092] In the above formula, is the dot product of vectors A and B, is the Euclidean norm (or length) of vector A; is the Euclidean norm (or length) of vector B. The cosine similarity ranges from -1 to 1, where a value of 1 means the vectors are exactly the same, a value of -1 means the vectors are completely opposite, and a value of 0 means the vectors are orthogonal (no correlation).

[0093] 2. Calculate using Jaccard similarity coefficient:

[0094]

[0095] In the above formula, |A∩B| is the size of the intersection of sets A and B, that is, the number of elements in common in the two sets; |A∪B| is the size of the union of sets A and B, that is, the number of all elements in the two sets, and repeated elements are counted only once; the Jaccard similarity coefficient ranges from 0 to 1, a value of 1 means that the two sets are exactly the same, and a value of 0 means that the two sets have no intersection.

[0096] Through cluster analysis and similarity calculation, common points are extracted to generate a comprehensive standard description applicable to different regions. This standard description is the one with the highest comprehensive similarity coefficient.

[0097] In this embodiment, cosine similarity and Jaccard similarity coefficient can be used to compare the similarity between documents or sentences. Cosine similarity is insensitive to the length of the document, while Jaccard similarity coefficient is sensitive to the size of the collection. Depending on the specific application scenario, a suitable similarity calculation method can be selected, which can be used independently or the average value after the normalization of the two calculation results can be used.

[0098] In one embodiment, before integrating the initial startup plan according to the manual intervention supplementary information, the method of the present application further includes the following steps:

[0099] Set up a manual intervention interface; the manual intervention interface is used to adjust the command sequence, edit command content, and add safety check steps; obtain the current command sequence, current command content, and current safety check steps obtained through the manual intervention interface, and generate manual intervention supplementary information based on the current command sequence, current command content, and current safety check steps.

[0100] Specifically, the server sets up a manual intervention interface for manually adjusting the command sequence and editing the command content to ensure the rationality and safety of the plan, that is, professionals review and adjust the automatically generated standard description. Based on the automatically generated startup plan, manual intervention is a key step to ensure the rationality, safety and adaptability of the plan. The following are several specific scenarios and results of manual intervention:

[0101] Scenario 1: Command sequence adjustment, for example:

[0102] Automatically generated solutions:

[0103] 1. Check the power connection of device A.

[0104] 2. Start device B.

[0105] 3. Verify the operating status of device A.

[0106] In actual operation, it may be necessary to verify the operating status of device A first to ensure that it is in a safe state before starting device B to avoid potential safety risks; therefore, the solution after manual intervention is as follows:

[0107] 1. Check the power connection of device A.

[0108] 2. Verify the operating status of device A.

[0109] 3. Start device B.

[0110] Scenario 2: Command content editing, for example:

[0111] Automatically generated solutions:

[0112] 1. Turn on the power switch of device C.

[0113] Since the automatically generated commands may be too general, manual intervention can provide more detailed operation steps to ensure that the operator can execute them accurately and verify the operation results. Therefore, supplements can be made after manual intervention, such as:

[0114] 1. Turn on the main power switch of device C and check that the power indicator is on.

[0115] Scenario 3: Adding security check steps, for example:

[0116] Automatically generated solutions:

[0117] 1. Connect the control line of device D.

[0118] 2. Start device D.

[0119] In order to ensure the safety of operation, it is necessary to add a grounding check before starting the equipment, which is an important safety step that may be missed in the automatically generated solution. Therefore, after manual intervention:

[0120] 1. Connect the control line of device D.

[0121] 2. Check the grounding condition of equipment D.

[0122] 3. Start device D.

[0123] Scenario 4: Adapting to specific regional regulations, for example:

[0124] Automatically generated solutions:

[0125] 1. Start up Equipment E according to standard procedures.

[0126] Since different regions may have different operating regulations and safety standards, manual intervention can ensure that the solution complies with the laws and regulations of a specific region. Therefore, after manual intervention:

[0127] 1. Adjust the startup parameters of device E according to the special regulations of region X.

[0128] Scenario 5: Handling abnormal situations, such as:

[0129] Automatically generated solutions:

[0130] 1. Start device F as usual.

[0131] Since the automatically generated solution may not take into account all abnormal situations that may be encountered in actual operations, manual intervention can adjust the solution according to the actual situation to ensure the safety and effectiveness of the operation. Therefore, after manual intervention:

[0132] 1. Before starting the device F, check the weather conditions and delay starting if there is a thunderstorm.

[0133] Through these examples of manual intervention, we can see that manual intervention is mainly to make up for the shortcomings of the automatically generated plan, such as lack of details, neglect of safety inspections, non-compliance with specific regional regulations, etc. Manual intervention can improve the practicality and reliability of the startup plan and ensure the smooth commissioning of new equipment.

[0134] The server then integrates the automatically generated information and the information supplemented by manual intervention to generate a complete new equipment startup plan, which is based on the automatically generated information. If manual intervention is determined, the part after manual intervention will replace the original automatically generated part. Finally, these plans are implemented in actual operation, and the rule base is further adjusted and improved based on feedback.

[0135] In one embodiment, Figure 4 As shown, a method for generating a new device startup plan in a power system in a specific embodiment is provided, which specifically includes the following steps:

[0136] Step S401, obtaining historical operation data of power systems in multiple different regions, identifying different descriptions of the same operation in different regions in the historical operation data, and obtaining an operation-description data set.

[0137] Step S402, obtain standard operating steps in historical operation data, and convert the standard operating steps into sequence data including command identifiers and command descriptions; use the command identifiers as inputs of the startup step model, and the command descriptions as outputs of the startup step model, train the startup steps, and obtain an initial startup step model; based on the operation-description data set, generate a first optimizer and a first loss function, and update the initial startup step model according to the first optimizer and the first loss function to obtain a startup step model.

[0138] Step S403, obtain the standard conditional statements in the historical operation data, train the conditional statements based on the standard conditional statements and the fully connected layer, and obtain the initial startup condition model; based on the operation-description data set, generate a second optimizer and a second loss function, and update the initial startup condition model according to the second optimizer and the second loss function to obtain the startup condition model.

[0139] Step S404, using the preset graph attention neural network, feature extraction is performed in the power grid topology model to obtain topological features, and a corpus of startup condition text is generated based on the equipment name library and the startup operation word segmentation text library; prediction is performed based on the startup step model and the startup condition model to obtain the commissioning steps and commissioning conditions of the new equipment; the commissioning steps and commissioning conditions are adjusted in combination with the topological features and the corpus, and an initial startup plan is generated based on the adjusted commissioning steps and commissioning conditions.

[0140] Step S405, using a preset similarity calculation method, similarity analysis is performed on different descriptions of the same operation in different regions to obtain a comprehensive similarity coefficient; among the different descriptions, the description with the highest comprehensive similarity coefficient is identified as the standard description.

[0141] Step S406, setting up a manual intervention interface; the manual intervention interface is used to adjust the command sequence, edit command content, and add security check steps; obtain the current command sequence, current command content, and current security check steps obtained through the manual intervention interface, and generate manual intervention supplementary information based on the current command sequence, current command content, and current security check steps.

[0142] Step S407, replacing the description of the same operation in the initial startup plan with the standard description, and integrating the initial startup plan according to the manual intervention supplementary information to obtain the target startup plan for the new equipment in the current power system.

[0143] The beneficial effects brought by the above embodiments are as follows:

[0144] This application uses deep learning technology to automatically learn the patterns of startup steps and conditional statements from historical data, generate startup step models and startup condition models, and automatically compile startup plans. This method significantly improves the efficiency and accuracy of power grid equipment startup plan writing, reduces human errors, and ensures the consistency and reliability of the plan. In addition, this application uses a B / S architecture system to construct an intelligent compilation system for the startup plan of new power grid equipment, designs the compilation, review process, and commissioning and verification functions of the new equipment, effectively improves the level of intelligence, and meets the needs of large power grid development. In short, the implementation of this application can effectively reduce the workload of operators, improve the risk control of the commissioning of new equipment, and play an important role in ensuring the safe and stable operation of the power system. Through the intelligent compilation system, potential risk points can be identified and avoided in advance to ensure that every step of the commissioning of new equipment is strictly verified and reviewed. This systematic risk management capability is difficult to match with traditional manual compilation methods. It improves the safety and stability of the power system through intelligent means.

[0145] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0146] Based on the same inventive concept, the embodiment of the present application also provides a device for generating a new device startup scheme in a power system for implementing the method for generating a new device startup scheme in a power system involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the device for generating a new device startup scheme in a power system provided below can refer to the limitations of the method for generating a new device startup scheme in a power system above, and will not be repeated here.

[0147] In an exemplary embodiment, Figure 5 As shown, a device for generating a new equipment startup plan in a power system is provided, comprising:

[0148] The data identification module 501 is used to obtain historical operation data of power systems in multiple different regions, identify different descriptions of the same operation in different regions in the historical operation data, and obtain an operation-description data set;

[0149] A model training module 502 is used to train the startup step according to the historical operation data and the operation-description data set to obtain the startup step model, and to train the conditional statement according to the historical operation data and the operation-description data set to obtain the startup condition model;

[0150] The feature extraction module 503 is used to extract features in the power grid topology model using a preset graph attention neural network to obtain topological features, and to generate a corpus of the startup condition text based on the device name library and the startup operation word segmentation text library;

[0151] A scheme generation module 504 is used to generate an initial startup scheme for new equipment in the current power system based on the startup step model and the startup condition model, combined with topological features and corpus;

[0152] The scheme integration module 505 is used to replace the description of the same operation in the initial startup scheme with the standard description, and integrate the initial startup scheme according to the manual intervention supplementary information to obtain the target startup scheme of the new equipment in the current power system.

[0153] In one embodiment, the model training module 502 is also used to obtain standard operating steps in historical operation data, convert the standard operating steps into sequence data including command identifiers and command descriptions; use the command identifier as the input of the startup step model, and the command description as the output of the startup step model, train the startup step to obtain an initial startup step model; generate a first optimizer and a first loss function based on the operation-description data set, and update the initial startup step model according to the first optimizer and the first loss function to obtain a startup step model.

[0154] In one embodiment, the model training module 502 is also used to obtain standard conditional statements in historical operation data, train the conditional statements based on the standard conditional statements and the fully connected layer, and obtain an initial startup condition model; based on the operation-description data set, generate a second optimizer and a second loss function, and update the initial startup condition model according to the second optimizer and the second loss function to obtain a startup condition model.

[0155] In one embodiment, the device for generating a new equipment startup plan in an electric power system also includes a similarity analysis module, which is used to use a preset similarity calculation method to perform similarity analysis on different description contents of the same operation in different regions to obtain a comprehensive similarity coefficient; among the different description contents, the description content with the highest comprehensive similarity coefficient is identified as the standard description.

[0156] In one embodiment, the device for generating a new equipment startup plan in the power system also includes an information supplement module for setting a manual intervention interface; the manual intervention interface is used to adjust the command sequence, edit the command content, and add safety check steps; obtain the current command sequence, current command content, and current safety check steps obtained through the manual intervention interface, and generate manual intervention supplementary information based on the current command sequence, current command content, and current safety check steps.

[0157] In one embodiment, the solution generation module 504 is used to make predictions based on the startup step model and the startup condition model to obtain the commissioning steps and commissioning conditions of the new equipment; adjust the commissioning steps and commissioning conditions in combination with the topological features and the corpus, and generate an initial startup solution based on the adjusted commissioning steps and commissioning conditions.

[0158] Each module in the device for generating a startup plan for a new device in the power system can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0159] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG6. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store historical operation data of the power system. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for generating a startup scheme for a new device in a power system is implemented.

[0160] Those skilled in the art will understand that the structure shown in FIG. 6 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0161] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0162] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0163] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0165] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0166] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0167] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating a new equipment startup plan in a power system, characterized in that: The method comprises: Acquire historical operation data of power systems in multiple different regions, identify different descriptions of the same operation in the different regions in the historical operation data, and obtain an operation-description data set; Training the startup step according to the historical operation data and the operation-description data set to obtain a startup step model, and training the conditional statement according to the historical operation data and the operation-description data set to obtain a startup condition model; Using the preset graph attention neural network, feature extraction is performed in the power grid topology model to obtain topological features, and a corpus of startup condition text is generated based on the device name library and the startup operation word segmentation text library; Based on the startup step model and the startup condition model, combined with the topological features and the corpus, an initial startup plan for new equipment in the current power system is generated; The descriptions of the same operations in the initial startup plan are replaced with standard descriptions, and the initial startup plan is integrated according to the supplementary information of manual intervention to obtain a target startup plan for the new equipment in the current power system.

2. The method according to claim 1, characterized in that The step of training the startup step according to the historical operation data and the operation-description data set to obtain a startup step model includes: Acquire standard operating steps in the historical operation data, and convert the standard operating steps into sequence data including command identifiers and command descriptions; Taking the command identifier as the input of the startup step model and the command description as the output of the startup step model, training the startup step to obtain an initial startup step model; Based on the operation-description data set, a first optimizer and a first loss function are generated, and according to the first optimizer and the first loss function, the initial startup step model is updated to obtain the startup step model.

3. The method according to claim 1, characterized in that The step of training the conditional statement according to the historical operation data and the operation-description data set to obtain a start condition model includes: Obtaining standard conditional statements in the historical operation data, and training the conditional statements based on the standard conditional statements and a fully connected layer to obtain an initial startup condition model; Based on the operation-description data set, a second optimizer and a second loss function are generated, and according to the second optimizer and the second loss function, the initial startup condition model is updated to obtain the startup condition model.

4. The method according to claim 1, characterized in that: Before replacing the description of the same operation in the initial startup scheme with the standard description, the method further includes: Using a preset similarity calculation method, similarity analysis is performed on different descriptions of the same operation in different regions to obtain a comprehensive similarity coefficient; Among the different description contents, the description content with the highest comprehensive similarity coefficient is identified as the standard description.

5. The method according to claim 4, characterized in that Before integrating the initial startup plan according to the manual intervention supplementary information, the method further includes: Setting up a manual intervention interface; the manual intervention interface is used to adjust the command sequence, edit the command content, and add security check steps; The current command sequence, current command content and current safety check step obtained through the manual intervention interface are obtained, and the manual intervention supplementary information is generated according to the current command sequence, the current command content and the current safety check step.

6. The method according to any one of claims 1 to 5, characterized in that: The generating an initial startup plan for new equipment in the current power system based on the startup step model and the startup condition model, in combination with the topology features and the corpus, includes: Predicting based on the startup step model and the startup condition model to obtain the commissioning steps and commissioning conditions of the new equipment; The operation steps and the operation conditions are adjusted in combination with the topological features and the corpus, and the initial startup plan is generated according to the adjusted operation steps and operation conditions.

7. A device for generating a new equipment startup plan in a power system, characterized in that: The device comprises: A data identification module, used to obtain historical operation data of power systems in multiple different regions, identify different descriptions of the same operation in the different regions in the historical operation data, and obtain an operation-description data set; A model training module, used to train the startup steps according to the historical operation data and the operation-description data set to obtain a startup step model, and to train the conditional statements according to the historical operation data and the operation-description data set to obtain a startup condition model; The feature extraction module is used to extract features in the power grid topology model using a preset graph attention neural network to obtain topological features, and to generate a corpus of startup condition texts based on a device name library and a startup operation word segmentation text library; A scheme generation module, used to generate an initial startup scheme for new equipment in the current power system based on the startup step model and the startup condition model, combined with the topological features and the corpus; The scheme integration module is used to replace the description of the same operation in the initial startup scheme with a standard description, and integrate the initial startup scheme according to the manual intervention supplementary information to obtain the target startup scheme of the new equipment in the current power system.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images