A power operation process digitization adaptive management and control method and system

Abstract

This invention discloses a digital adaptive control method and system for power operation processes, relating to the field of power operation management technology. The method includes: acquiring relevant power operation data and constructing a basic operation dataset; constructing a power operation task model based on the data, parsing the operation plan to generate target operation tasks and characteristic parameters; using the characteristic parameters to conduct risk assessment and determine the operation risk level; generating a collaborative operation process based on the risk level; scheduling and controlling the execution of target operation tasks and acquiring execution status data; monitoring operation tasks based on execution status and adjusting the collaborative operation process when anomalies are detected. This invention enables digital, dynamic, and adaptive control of power operation processes.

Description

Technical Field

[0001] This invention relates to the field of power operation management technology, and in particular to a digital adaptive control method and system for power operation processes. Background Technology

[0002] With the continuous expansion of the power system and the increasing proportion of renewable energy grid connection, power production and operation activities are showing a trend towards diversified operation types, more complex operating environments, and more refined operating processes. In the processes of power equipment maintenance, line maintenance, equipment inspection, and fault handling, it is usually necessary to manage and coordinate various information such as work plans, personnel allocation, equipment status, and the operating environment in a unified manner to ensure the safety and standardization of power operations. Therefore, how to effectively manage and coordinate the entire power operation process has become a crucial technical issue in power production management.

[0003] In existing technologies, power operation management largely relies on operation planning systems, production management systems, or human experience for scheduling and control. Task allocation, risk assessment, and workflow arrangement are typically handled through manual review or fixed rules. This approach struggles to achieve real-time analysis and dynamic adjustment of the operation process when faced with multiple tasks running concurrently, dynamic changes in operational resources, and complex operating environments. Furthermore, the information correlation between different operational stages is low, making it difficult to form a unified data structure for comprehensive analysis of operational data.

[0004] Furthermore, during the execution of power operations, existing systems often focus on the planning and management of tasks, while having limited capabilities for dynamic monitoring of the operation status and handling of anomalies. When personnel changes, equipment status changes, or changes in the working environment occur during the operation, existing work processes usually lack corresponding adaptive adjustment mechanisms, making it difficult to restructure and schedule the work processes in a timely manner, thus affecting the overall coordination and controllability of power operation management.

[0005] Therefore, it is necessary to provide a digital adaptive control method and system for power operation processes. By uniformly modeling and analyzing power operation data, it is possible to realize task parsing, risk assessment, collaborative operation process generation, and dynamic adjustment of the operation process, thereby improving the digital management capability of power operation processes. Summary of the Invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, this invention provides a digital adaptive control method for power operation processes to solve problems such as scattered operation data, insufficient operation task parsing capabilities, and reliance on human experience for operation risk assessment in the existing power operation management process.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0009] In a first aspect, embodiments of the present invention provide a digital adaptive control method for power operation processes, comprising: acquiring power operation-related data, processing the power operation-related data, and constructing a basic dataset for the operation;

[0010] A power operation task model is constructed based on the aforementioned basic dataset. The power operation task model is used to parse the operation plan information, generate target operation tasks, extract the feature parameters of the target operation tasks, and generate operation task association data.

[0011] Based on the power operation task model and the operation task association data, the characteristic parameters of the target operation task are extracted. The characteristic parameters of the target operation task are used as risk assessment input parameters to conduct risk assessment on the target operation task and determine the operation risk level of the target operation task.

[0012] Based on the target task's characteristic parameters and the task's risk level, the target task is configured to generate a collaborative work process;

[0013] Based on the collaborative work process, the target work task is scheduled and executed, and work execution status data is obtained.

[0014] The execution status of the target task is monitored based on the task execution status data, and the collaborative task process is adjusted when an abnormal task execution is detected.

[0015] As a preferred embodiment of the digital adaptive control method for power operation processes described in this invention, the power operation-related data is processed to construct a basic operation dataset, including:

[0016] The acquired power operation-related data is cleaned, including anomaly identification, missing data completion, and duplicate data removal.

[0017] After cleaning, the relevant data of the power operation are standardized, and the fields and units of data from different sources are unified according to the preset data format.

[0018] A unified data index relationship is established based on the information of the operators, equipment, working environment, and work plan, and the relevant data of the power operation are linked and integrated.

[0019] As a preferred embodiment of the digital adaptive control method for power operation processes described in this invention, the method includes: constructing a power operation task model based on the operation baseline dataset, and using the power operation task model to parse operation plan information, including:

[0020] Semantic parsing and field splitting are performed on the job plan information in the job base dataset to extract job plan elements;

[0021] A power operation task model is constructed based on a preset task template. The power operation task model includes a set of task nodes, a set of node attributes, and a set of node relationships.

[0022] The task node set in the power operation task model is instantiated based on the operation plan elements to generate target operation task nodes corresponding to the operation plan information;

[0023] Based on the node attribute set, task feature parameters are configured for the target task nodes, and the relationships between the target task nodes are established according to the node relationship set. The task plan information is then parsed and the target task is generated.

[0024] As a preferred embodiment of the digital adaptive control method for power operation processes described in this invention, the method includes: conducting a risk assessment of the target operation task to determine the operation risk level of the target operation task, including:

[0025] The target task feature parameters are subjected to feature quantization processing, and the target task feature parameters are converted into risk assessment feature vectors using preset feature encoding rules;

[0026] The risk assessment feature vector is input into a preset risk assessment model, and the risk assessment feature vector is calculated by the risk assessment model to obtain the risk assessment value of the target task.

[0027] The risk assessment value is range-mapped according to a preset risk level mapping rule to determine the operational risk level of the target task.

[0028] As a preferred embodiment of the digital adaptive control method for power operation processes described in this invention, the method includes: configuring the target operation task based on the target operation task characteristic parameters and operation risk level to generate a collaborative operation process, including:

[0029] Construct a task attribute matrix and a task resource constraint matrix, and calculate the task attribute matrix and the personnel ability matrix to obtain a preliminary task allocation scheme.

[0030] A task scheduling algorithm is used to iteratively optimize the initial task allocation scheme, adjusting the task execution order and resource allocation.

[0031] As a preferred embodiment of the digital adaptive control method for power operation processes described in this invention, the method includes: scheduling and controlling the execution of the target operation task based on the collaborative operation process, comprising:

[0032] Dynamic scheduling algorithms are used to optimize the job scheduling plan matrix in real time, adjusting the task execution order and resource allocation to respond to changes in the work environment and personnel status.

[0033] During job execution, the job monitoring module collects task execution status data and performs real-time analysis, and adjusts the scheduling plan through a closed-loop control algorithm.

[0034] As a preferred embodiment of the digital adaptive control method for power operation processes described in this invention, the method includes: monitoring the execution status of the target operation task based on the operation execution status data, and adjusting the collaborative operation process when an abnormal operation is detected, including:

[0035] The task execution status data is parsed and time-series organized to construct a task execution status monitoring sequence, and the status of the task execution status monitoring sequence is determined based on preset monitoring rules.

[0036] The execution status monitoring sequence of the job is matched and calculated with the planned execution parameters in the collaborative job process by a status comparison algorithm to generate an execution status deviation matrix;

[0037] The target task is identified as abnormal based on the execution status deviation matrix, and the abnormal task node is determined based on the preset abnormal judgment rules.

[0038] After identifying the abnormal task node, the process adjustment module is invoked to dynamically reconstruct the collaborative work process, recalculating the task order, resource allocation relationship and dependency relationship corresponding to the abnormal task node; and generating an updated collaborative work process based on the reconstructed task order and resource allocation relationship.

[0039] Secondly, embodiments of the present invention provide a digital adaptive control system for power operation processes, comprising:

[0040] The operation data acquisition and processing module is used to acquire power operation-related data, process the power operation-related data, and construct the operation basic dataset;

[0041] The task modeling and parsing module is used to construct a power task model based on the basic task dataset, parse the task plan information using the power task model, generate target tasks, extract the feature parameters of the target tasks, and generate task association data.

[0042] The operation risk assessment module is used to extract the characteristic parameters of the target operation task based on the power operation task model and operation task association data, use the characteristic parameters of the target operation task as risk assessment input parameters, perform risk assessment on the target operation task, and determine the operation risk level of the target operation task.

[0043] The collaborative work process generation module is used to configure the target work task according to the target work task characteristic parameters and work risk level, and generate a collaborative work process.

[0044] The job scheduling and execution control module is used to schedule and control the target job task based on the collaborative job process, and to acquire job execution status data.

[0045] The job status monitoring and process adjustment module is used to monitor the execution status of the target job task based on the job execution status data, and adjust the collaborative job process when an abnormal job execution is detected.

[0046] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, they implement the steps of a digital adaptive control method for power operation processes as described in the first aspect of the present invention.

[0047] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of a digital adaptive control method for power operation processes as described in the first aspect of the present invention.

[0048] The beneficial effects of this invention are as follows: This invention unifies the processing of power operation-related data and constructs a basic dataset for operations, further establishing a power operation task model, parsing operation plan information to generate target operation tasks, and conducting risk assessment based on the characteristic parameters of the target operation tasks, thereby achieving automatic determination of the operation risk level; on this basis, a collaborative operation process is generated according to the characteristic parameters of the target operation tasks and the operation risk level, and the operation tasks are scheduled and executed and controlled. At the same time, the operation process is dynamically monitored by combining operation execution status data, and the collaborative operation process is adjusted when an abnormality in operation execution is detected, thereby achieving digital and adaptive management and control of the power operation process. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0050] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0051] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0052] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0053] Example 1

[0054] Reference Figures 1-2 This is the first embodiment of the present invention, which provides a digital adaptive control method for power operation processes, including:

[0055] S1: Obtain relevant data on power operations, process the relevant data on power operations, and construct a basic dataset for the operations.

[0056] Furthermore, the acquired power operation-related data is cleaned, including anomaly identification, missing data completion, and duplicate data removal.

[0057] After cleaning, the relevant data of the power operation are standardized, and the fields and units of data from different sources are unified according to the preset data format.

[0058] A unified data index relationship is established based on the information of the operators, equipment, working environment, and work plan, and the relevant data of the power operation are linked and integrated.

[0059] It should be noted that in this embodiment, power operation-related data is first acquired. This data can originate from information systems such as power production management systems, equipment monitoring systems, personnel management systems, and work planning systems. This power operation-related data may include information on operators, equipment, the work environment, and work plans. To ensure the accuracy of subsequent task modeling and risk assessment, the acquired data needs to be processed uniformly to construct a structured basic dataset for the operation.

[0060] Furthermore, the acquired power operation-related data undergoes data cleaning. Specifically, the raw data is scanned using a data anomaly detection algorithm to identify data with obvious outliers, which are then corrected or removed according to preset rules. For missing data fields, missing data is filled using historical data, rule-based completion, or default value filling. Simultaneously, duplicate data generated during the multi-source system acquisition process is compared, and duplicate records are identified and removed using unique identifier field matching or timestamp matching.

[0061] After data cleaning, the cleaned power operation-related data undergoes data standardization. Specifically, data from different systems is uniformly converted according to a preset data format, and field names, data types, and data units are standardized. For example, fields representing equipment numbers, operation times, or personnel numbers from different systems are uniformly named, and time formats and equipment parameter units are uniformly converted to form a unified data structure.

[0062] After data standardization, a unified data index relationship is established based on personnel information, equipment information, work environment information, and work plan information. Specifically, by establishing key index fields such as personnel number, equipment number, and work task number, data from different data tables are correlated and matched. Various types of data are then uniformly organized through data association and integration, forming a structured basic dataset for work operations. This provides a data foundation for subsequent power work task model construction and work task analysis.

[0063] S2: Construct a power operation task model based on the aforementioned basic dataset, parse the operation plan information using the power operation task model, generate target operation tasks, extract the feature parameters of the target operation tasks, and generate operation task association data.

[0064] Furthermore, semantic parsing and field splitting are performed on the job plan information in the job base dataset to extract job plan elements;

[0065] A power operation task model is constructed based on a preset task template. The power operation task model includes a set of task nodes, a set of node attributes, and a set of node relationships.

[0066] The task node set in the power operation task model is instantiated based on the operation plan elements to generate target operation task nodes corresponding to the operation plan information;

[0067] Based on the node attribute set, task feature parameters are configured for the target task nodes, and the relationships between the target task nodes are established according to the node relationship set. The task plan information is then parsed and the target task is generated.

[0068] It should be noted that after completing the construction of the basic dataset for the operation, in order to achieve structured parsing and task-based management of power operation plan information, this embodiment constructs a power operation task model to parse the operation plan information and generate target operation tasks for subsequent risk assessment and operation process configuration.

[0069] Furthermore, semantic parsing and field segmentation are performed on the job plan information in the aforementioned job base dataset. Specifically, text parsing algorithms or natural language processing techniques can be used to perform semantic recognition on the job plan text, and the information contained in the job plan, such as job content, job location, job time, equipment involved, and participating personnel, can be segmented into fields to extract standardized job plan elements. For structured job plan information, field mapping rules can be used to extract and transform the original fields to obtain job plan element data in a unified format.

[0070] After obtaining the elements of the work plan, a power work task model is constructed based on a preset work task template. The work task template can be predefined according to common work types in the power industry, such as equipment maintenance, line maintenance, or inspection. The power work task model mainly includes a set of task nodes, a set of node attributes, and a set of node relationships. The set of task nodes represents different types of work task units; the set of node attributes records the task characteristic information corresponding to each task node; and the set of node relationships describes the logical relationships between task nodes, such as sequential relationships, dependency relationships, or parallel relationships.

[0071] After constructing the power operation task model, the task node set is instantiated based on the operation plan elements. Specifically, based on the operation type and content in the operation plan, a corresponding type of task node template can be selected from the task node set, and the operation plan elements can be mapped to the corresponding task node attributes, thereby generating a target operation task node corresponding to the operation plan information. For example, when the operation plan involves the maintenance of a certain equipment, the corresponding maintenance task node template can be called from the task node set, and the task node can be instantiated and configured according to the equipment number, operation time, and personnel information.

[0072] Furthermore, after generating the target task nodes, task feature parameters are configured for the target task nodes based on the node attribute set. Specifically, data such as work equipment information, work environment information, and personnel information can be associated with the task nodes, and this information is written into the node attribute set as task feature parameters. At the same time, logical relationships are established between different target task nodes according to preset relationship rules in the node relationship set. For example, the preparation node, execution node, and completion node are connected in a preset order, or parallel or dependent relationships are established when there are multiple tasks.

[0073] Through the above processing, the parsing of work plan information can be completed, forming a target work task structure consisting of multiple target work task nodes. Simultaneously, work task association data reflecting the relationships between task nodes is generated. These target work tasks and their association data can further serve as the foundational data for subsequent risk assessments and collaborative work process generation.

[0074] S3: Based on the power operation task model and the operation task association data, extract the target operation task feature parameters, use the target operation task feature parameters as risk assessment input parameters, perform risk assessment on the target operation task, and determine the operation risk level of the target operation task.

[0075] Furthermore, the target task feature parameters are subjected to feature quantization processing, and the target task feature parameters are converted into risk assessment feature vectors using preset feature encoding rules;

[0076] The risk assessment feature vector is input into a preset risk assessment model, and the risk assessment feature vector is calculated by the risk assessment model to obtain the risk assessment value of the target task.

[0077] The risk assessment value is range-mapped according to a preset risk level mapping rule to determine the operational risk level of the target task.

[0078] It should be noted that after generating the target task and establishing the associated data, in order to achieve automated identification and assessment of the risks of power operation tasks, this embodiment extracts the characteristic parameters of the target task based on the power operation task model and the associated data, and uses them as input parameters for risk assessment to assess the risks of the target task and thus determine the corresponding risk level of the operation.

[0079] Furthermore, target task feature parameters are extracted from the power operation task model and associated data. Specifically, based on the task node attribute set and node relationship set, data such as personnel information, equipment information, environmental information, and execution conditions related to the target task can be extracted and organized into a parameter set describing the characteristics of the target task. For example, information such as the number of personnel, equipment operating status, environmental conditions, and task node dependencies can be extracted and combined into a unified feature parameter set.

[0080] After obtaining the target task feature parameters, these parameters undergo feature quantification. Specifically, various feature parameters can be numerically converted using preset feature encoding rules. For example, categorical features can be converted using numbered encoding or vector encoding; numerical features can be unified using normalization or interval standardization; and task feature parameters with hierarchical or dependent relationships can be weighted according to preset relationship rules. Through these methods, the target task feature parameters are converted into risk assessment feature vectors that can be used for model calculation.

[0081] Furthermore, the risk assessment feature vector is input into a preset risk assessment model, and the risk assessment feature vector is calculated using the risk assessment model to obtain the risk assessment value of the target task. The risk assessment model can be trained and constructed using historical power operation data, or it can employ a rule-based and model-based assessment method. In specific implementations, task features and corresponding risk results from historical operation data can be used to train the model, thereby forming an assessment model for risk prediction. When a new target task is generated, the corresponding risk assessment feature vector is input into the model for calculation to obtain the corresponding risk assessment value.

[0082] After obtaining the risk assessment value of the target task, the risk assessment value is mapped to a range according to a preset risk level mapping rule. Specifically, multiple risk level ranges can be preset, and the corresponding risk level is determined based on the range in which the risk assessment value falls. For example, a risk assessment value in a lower range can be classified as low-risk, a risk assessment value in the middle range as medium-risk, and a risk assessment value in a higher range as high-risk. Through this range mapping process, the risk level of the target task can be determined, providing a basis for the generation of subsequent collaborative work processes and task scheduling control.

[0083] S4: Configure the target task based on the target task characteristic parameters and the task risk level to generate a collaborative work process.

[0084] Furthermore, a task attribute matrix and a task resource constraint matrix are constructed, and a preliminary task allocation scheme is obtained by calculating the task attribute matrix and the personnel capability matrix.

[0085] A task scheduling algorithm is used to iteratively optimize the initial task allocation scheme, adjusting the task execution order and resource allocation.

[0086] It should be noted that after obtaining the characteristic parameters of the target task and its corresponding risk level, task configuration and resource allocation are required to form a collaborative work process that can guide the actual execution of the task. This embodiment constructs a task attribute matrix and a task resource constraint matrix, and optimizes the task allocation scheme using a task scheduling algorithm, thereby generating a collaborative work process suitable for the current work scenario.

[0087] Furthermore, a task attribute matrix is ​​constructed based on the target task's feature parameters. Specifically, multiple task nodes in the target task can be arranged according to task number, and task attribute fields can be established based on the task feature parameters corresponding to each task node, thus forming a task attribute matrix. Each row in the task attribute matrix can represent a different target task node, and each column can represent the feature attributes corresponding to the task node. In this way, the target task can be structurally represented in matrix form for subsequent calculations and processing.

[0088] Simultaneously, a task resource constraint matrix is ​​constructed based on the personnel and equipment information in the task baseline dataset. Specifically, resource constraints can be established based on constraints such as personnel skill information, equipment usage conditions, and task time limits, and represented in matrix form as the matching relationship between different resources and task nodes. For example, the resource constraint matrix can describe the types of tasks that different personnel can perform, the tasks that equipment can support, and the availability of various resources in different time periods, thus forming a set of resource constraints.

[0089] After obtaining the task attribute matrix and the task resource constraint matrix, the task attribute matrix and the personnel capability matrix are processed to obtain a preliminary task allocation scheme. Specifically, a matrix matching calculation method can be used to match task attributes with personnel capabilities. Based on the matching results, suitable personnel and resources are allocated to each target task node, thus forming a preliminary task allocation result. During this process, matching results that do not meet the constraints can be filtered or eliminated according to the attribute requirements and resource constraints of the task nodes to ensure the executability of the task allocation.

[0090] Furthermore, after obtaining the initial task allocation scheme, a task scheduling algorithm is used to iteratively optimize the scheme. Specifically, the task execution order can be calculated based on the dependencies between task nodes, task time constraints, and resource availability constraints, and the task scheduling result is optimized through iterative calculation. During the optimization process, the task execution order can be dynamically adjusted, and the allocation of personnel and equipment resources can be reconfigured to ensure that the task execution order and resource usage meet preset scheduling constraints.

[0091] S5: Based on the collaborative work process, perform job scheduling and execution control on the target job task, and obtain job execution status data.

[0092] Furthermore, dynamic scheduling algorithms are used to optimize the job scheduling plan matrix in real time, adjusting the task execution order and resource allocation to respond to changes in the work environment and personnel status.

[0093] During job execution, the job monitoring module collects task execution status data and performs real-time analysis, and adjusts the scheduling plan through a closed-loop control algorithm.

[0094] It should be noted that after the collaborative work process is generated, the target work task needs to be scheduled and executed according to the collaborative work process to achieve the orderly execution of the work task in the actual production environment. At the same time, work execution status data is continuously acquired during the work execution process to provide a data foundation for subsequent work status monitoring and process adjustment.

[0095] Furthermore, a job scheduling plan matrix is ​​constructed based on the collaborative work process. Specifically, the target job task nodes, corresponding personnel, equipment, and time information can be structured and organized according to the execution order of each task node in the collaborative work process to form a job scheduling plan matrix. The job scheduling plan matrix can be used to represent the execution time, resource allocation, and execution relationships between each job task node, thus serving as the basic data structure for job scheduling and execution control.

[0096] After forming the job scheduling plan matrix, a dynamic scheduling algorithm is used to optimize the matrix in real time. Specifically, during job execution, the system continuously acquires job environment information and personnel status information, such as changes in equipment operating status, changes in job environment conditions, or personnel attendance. When changes in relevant status information are detected, the changed information can be input as scheduling parameters into the dynamic scheduling algorithm to recalculate the original scheduling plan, thereby adjusting the task execution order and job resource allocation relationships to ensure that the scheduling plan is consistent with the current job conditions.

[0097] Furthermore, during the operation, the operation monitoring module monitors the execution status of the target task and collects task execution status data. This task execution status data can be obtained in various ways, such as collecting operator operation information through on-site terminal devices, obtaining equipment operating status data through an equipment monitoring system, or recording operation progress information through mobile terminals. The collected task execution status data may include task start time, task completion time, equipment operating status, and operation progress information.

[0098] After acquiring task execution status data, this data is analyzed in real time, and the scheduling plan is adjusted using a closed-loop control algorithm. Specifically, the deviation between the current task execution progress and the scheduling plan can be determined based on the task execution status data. When task execution delays, resource conflicts, or abnormal execution status are detected, the job scheduling plan matrix is ​​corrected using the closed-loop control algorithm. This may involve adjusting the execution time of subsequent task nodes or reallocating personnel or equipment resources. Through this method, dynamic management of the job scheduling and execution control process can be achieved, and updated job execution status data can be continuously acquired.

[0099] S6: Monitor the execution status of the target task based on the task execution status data, and adjust the collaborative task process when an abnormal task execution is detected.

[0100] Furthermore, the task execution status data is parsed and time-series organized to construct a task execution status monitoring sequence, and the status of the task execution status monitoring sequence is determined based on preset monitoring rules.

[0101] The execution status monitoring sequence of the job is matched and calculated with the planned execution parameters in the collaborative job process by a status comparison algorithm to generate an execution status deviation matrix;

[0102] The target task is identified as abnormal based on the execution status deviation matrix, and the abnormal task node is determined based on the preset abnormal judgment rules.

[0103] After identifying the abnormal task node, the process adjustment module is invoked to dynamically reconstruct the collaborative work process, recalculating the task order, resource allocation relationship and dependency relationship corresponding to the abnormal task node; and generating an updated collaborative work process based on the reconstructed task order and resource allocation relationship.

[0104] It should be noted that during the job scheduling and execution control process, the system continuously acquires job execution status data. In order to ensure that the power operation process can be executed stably according to the collaborative operation process, this embodiment monitors and analyzes the job execution status data in real time, monitors the execution status of the target job task, and dynamically adjusts the collaborative operation process when job execution abnormalities are detected.

[0105] Furthermore, the task execution status data is analyzed and processed using a time series analysis. Specifically, the collected task execution status data can be analyzed according to task node number and timestamp, and the data can be arranged in chronological order to form a task execution status monitoring sequence. This monitoring sequence reflects the changes in the execution status of the target task at different time points. After forming the monitoring sequence, the status can be determined based on preset monitoring rules, such as identifying the current task status based on task execution progress, resource occupancy status, and equipment operating status, thereby obtaining the execution status information corresponding to each task node.

[0106] After constructing the job execution status monitoring sequence, a status comparison algorithm is used to match and calculate the sequence with the planned execution parameters in the collaborative work process. Specifically, the planned execution time, task order, and resource allocation relationships in the collaborative work process can be used as benchmark parameters and compared with the real-time acquired execution status monitoring sequence to determine the degree of difference between the actual execution status and the planned execution status. This calculation process generates an execution status deviation matrix, which represents the deviation of each task node from the planned execution parameters in terms of execution time, resource usage, and task execution order.

[0107] Furthermore, anomalies in the target task are identified based on the execution status deviation matrix. Specifically, the deviation data in the execution status deviation matrix can be analyzed, and task nodes whose deviations exceed a preset threshold can be identified according to preset anomaly judgment rules. For example, when the execution time of a task node is significantly delayed or its resource usage is inconsistent with the planned configuration, the task node can be identified as an abnormal task node, and the corresponding anomaly type and anomaly parameters can be recorded.

[0108] After identifying the abnormal task nodes, the process adjustment module is invoked to dynamically reconstruct the collaborative work process. Specifically, the abnormal task nodes can be used as the adjustment targets to recalculate the task order, resource allocation relationships, and task dependencies within the collaborative work process. For example, if a task node is delayed, the execution time of subsequent task nodes can be rescheduled; if a resource cannot continue to participate in the job, available resources can be re-matched and the resource allocation relationships updated. Simultaneously, after recalculating the task order and resource allocation relationships, the collaborative work process structure is regenerated based on the updated task node relationships.

[0109] Through the above processing, an updated collaborative work process can be formed and used to guide the execution of subsequent target work tasks, thereby achieving continuous monitoring and dynamic adjustment of the power operation process.

[0110] This embodiment also provides a digital adaptive control system for power operation processes, including:

[0111] The operation data acquisition and processing module is used to acquire power operation-related data, process the power operation-related data, and construct the operation basic dataset;

[0112] The task modeling and parsing module is used to construct a power task model based on the basic task dataset, parse the task plan information using the power task model, generate target tasks, extract the feature parameters of the target tasks, and generate task association data.

[0113] The operation risk assessment module is used to extract the characteristic parameters of the target operation task based on the power operation task model and operation task association data, use the characteristic parameters of the target operation task as risk assessment input parameters, perform risk assessment on the target operation task, and determine the operation risk level of the target operation task.

[0114] The collaborative work process generation module is used to configure the target work task according to the target work task characteristic parameters and work risk level, and generate a collaborative work process.

[0115] The job scheduling and execution control module is used to schedule and control the target job task based on the collaborative job process, and to acquire job execution status data.

[0116] The job status monitoring and process adjustment module is used to monitor the execution status of the target job task based on the job execution status data, and adjust the collaborative job process when an abnormal job execution is detected.

[0117] This embodiment also provides a computer device applicable to a digital adaptive control method for power operation processes, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize a digital adaptive control method for power operation processes as proposed in the above embodiment.

[0118] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0119] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a digital adaptive control method for power operation processes as proposed in the above embodiments.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A digital adaptive control method for power operation processes, characterized in that, include: Acquire relevant data on power operations, process the relevant data, and construct a basic dataset for the operations; A power operation task model is constructed based on the aforementioned basic dataset. The power operation task model is used to parse the operation plan information, generate target operation tasks, extract the feature parameters of the target operation tasks, and generate operation task association data. Based on the power operation task model and operation task association data, the characteristic parameters of the target operation task are extracted. The characteristic parameters of the target operation task are used as risk assessment input parameters to conduct risk assessment on the target operation task and determine the operation risk level of the target operation task. Based on the target task's characteristic parameters and the task's risk level, the target task is configured to generate a collaborative work process; Based on the collaborative work process, the target work task is scheduled and executed, and work execution status data is obtained. The execution status of the target task is monitored based on the task execution status data, and the collaborative task process is adjusted when an abnormal task execution is detected.

2. The digital adaptive control method for power operation processes as described in claim 1, characterized in that, The process of processing the power operation-related data to construct the basic operation dataset includes: The acquired power operation-related data is cleaned, including anomaly identification, missing data completion, and duplicate data removal. After cleaning, the relevant data of the power operation are standardized, and the fields and units of data from different sources are unified according to the preset data format. A unified data index relationship is established based on the information of the operators, equipment, working environment, and work plan, and the relevant data of the power operation are linked and integrated.

3. The digital adaptive control method for power operation processes as described in claim 1, characterized in that, The process of constructing a power operation task model based on the aforementioned basic dataset, and using the power operation task model to parse operation plan information, includes: Semantic parsing and field splitting are performed on the job plan information in the job base dataset to extract job plan elements; A power operation task model is constructed based on a preset task template. The power operation task model includes a set of task nodes, a set of node attributes, and a set of node relationships. The task node set in the power operation task model is instantiated based on the operation plan elements to generate target operation task nodes corresponding to the operation plan information; Based on the node attribute set, task feature parameters are configured for the target task nodes, and the relationships between the target task nodes are established according to the node relationship set. The task plan information is then parsed and the target task is generated.

4. The digital adaptive control method for power operation process as described in claim 1, characterized in that, The step of conducting a risk assessment of the target task and determining the operational risk level of the target task includes: The target task feature parameters are subjected to feature quantization processing, and the target task feature parameters are converted into risk assessment feature vectors using preset feature encoding rules; The risk assessment feature vector is input into a preset risk assessment model, and the risk assessment feature vector is calculated by the risk assessment model to obtain the risk assessment value of the target task. The risk assessment value is range-mapped according to a preset risk level mapping rule to determine the operational risk level of the target task.

5. The digital adaptive control method for power operation process as described in claim 1, characterized in that, The step of configuring the target task based on its characteristic parameters and risk level, and generating a collaborative work process, includes: Construct a task attribute matrix and a task resource constraint matrix, and calculate the task attribute matrix and the personnel ability matrix to obtain a preliminary task allocation scheme. A task scheduling algorithm is used to iteratively optimize the initial task allocation scheme, adjusting the task execution order and resource allocation.

6. The digital adaptive control method for power operation process as described in claim 1, characterized in that, The process of scheduling and controlling the execution of the target task based on the collaborative work process includes: Dynamic scheduling algorithms are used to optimize the job scheduling plan matrix in real time, adjusting the task execution order and resource allocation to respond to changes in the work environment and personnel status. During job execution, the job monitoring module collects task execution status data and performs real-time analysis, and adjusts the scheduling plan through a closed-loop control algorithm.

7. The digital adaptive control method for power operation process as described in claim 1, characterized in that, The step of monitoring the execution status of the target task based on the task execution status data, and adjusting the collaborative task process when an execution anomaly is detected, includes: The task execution status data is parsed and time-series organized to construct a task execution status monitoring sequence, and the status of the task execution status monitoring sequence is determined based on preset monitoring rules. The execution status monitoring sequence of the job is matched and calculated with the planned execution parameters in the collaborative job process by a status comparison algorithm to generate an execution status deviation matrix; The target task is identified as abnormal based on the execution status deviation matrix, and the abnormal task node is determined based on the preset abnormal judgment rules. After identifying the abnormal task node, the process adjustment module is invoked to dynamically reconstruct the collaborative work process, recalculating the task order, resource allocation relationship and dependency relationship corresponding to the abnormal task node; and generating an updated collaborative work process based on the reconstructed task order and resource allocation relationship.

8. A digital adaptive control system for power operation processes, characterized in that, include: The operation data acquisition and processing module is used to acquire power operation-related data, process the power operation-related data, and construct the operation basic dataset; The task modeling and parsing module is used to construct a power task model based on the basic task dataset, parse the task plan information using the power task model, generate target tasks, extract the feature parameters of the target tasks, and generate task association data. The operation risk assessment module is used to extract the characteristic parameters of the target operation task based on the power operation task model and operation task association data, use the characteristic parameters of the target operation task as risk assessment input parameters, perform risk assessment on the target operation task, and determine the operation risk level of the target operation task. The collaborative work process generation module is used to configure the target work task according to the target work task characteristic parameters and work risk level, and generate a collaborative work process. The job scheduling and execution control module is used to schedule and control the target job task based on the collaborative job process, and to acquire job execution status data. The job status monitoring and process adjustment module is used to monitor the execution status of the target job task based on the job execution status data, and adjust the collaborative job process when an abnormal job execution is detected.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the digital adaptive control method for power operation process as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the digital adaptive control method for power operation process as described in any one of claims 1 to 7.

Images