Power generation data visual management system and method based on big data

Abstract

The invention discloses a power generation data visual management system and method based on big data, and relates to the technical field of power plant data management.The historical management data of generator set equipment in a power plant is analyzed, and a knowledge graph of a protection strategy executed by protection equipment in the power plant when the generator set equipment is abnormal is constructed; the method comprises the following steps: acquiring a running state of power plant generator set equipment, when the generator set equipment runs abnormally, matching a management strategy in a knowledge graph, acquiring an operation sequence corresponding to the management strategy, automatically executing operation steps in the operation sequence through related protection equipment in a power plant, and acquiring a change trend of equipment data; calculating the difference between the change trend and the management strategy target, evaluating the protection effect corresponding to the disposal template, generating a feedback report, sending the feedback report to related operation and maintenance personnel, obtaining the management of the abnormal generator set equipment, and updating the knowledge graph according to the disposal result.

Description

Technical Field

[0001] This invention relates to the field of power plant data management technology, specifically to a power generation data visualization management system and method based on big data. Background Technology

[0002] During generator unit operation, power plant systems and personnel need to constantly identify and process data that may appear within a short period of time that deviate from normal operating patterns. These abnormal data may be caused by equipment failure, operational errors, external interference, or other unforeseen events, and they may affect the stability and reliability of generator unit operation. Therefore, timely and accurate processing of these transient abnormal data is crucial to ensuring the normal operation of power generation.

[0003] Currently, the detection of instantaneous anomalies in power generation units at the grassroots level mainly relies on real-time monitoring and early warning systems. These systems primarily use sensors installed on key equipment to monitor the overall system's operational status in real time, such as bus voltage, main steam temperature, and drum water level. When monitored data exceeds normal ranges, the system immediately issues audible and visual warning signals, prompting operators to respond promptly. Data preprocessing in the real-time monitoring and early warning system is mainly achieved through simple data cleaning and aggregation methods. Simple data cleaning is based on the voting mechanism used in switch control, determining the final value from data collected from multiple similar or identical data sources according to preset rules for data verification and redundancy elimination. Data aggregation methods are based on common data aggregation techniques such as averaging. Assuming most data points are accurate and reliable, and with fewer outliers or errors, a more stable and representative value can be obtained, reducing data variability and noise.

[0004] By collecting data on the location and operation records of the generating unit equipment from relevant maintenance personnel, a management and protection plan for the unit equipment can be developed. Through feature matching via a computer system, under certain conditions, automated means can be used to protect the unit equipment. However, current technology lacks effective solutions for monitoring the protection and management methods integrated with automated means. If the automated system matches an incorrect management method, it can further exacerbate the risks to the unit equipment's operation and even cause more serious accidents. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a power generation data visualization management method based on big data, the method comprising:

[0006] Step S100: By analyzing the historical management data of the generator sets in the power plant, a knowledge graph is constructed to show the protection strategies executed by the protection devices in the power plant when abnormalities occur in the generator sets.

[0007] Step S200: Obtain the operating status of the power plant generator set equipment. When the generator set equipment is operating abnormally, match the management strategy in the knowledge graph and obtain the operation sequence corresponding to the management strategy.

[0008] Step S300: Automatically execute the operation steps in the operation sequence through relevant protection equipment in the power plant, obtain the changing trend of equipment data, and calculate the difference between the changing trend and the management strategy objective;

[0009] Step S400: Evaluate the protection effect corresponding to the handling template, generate a feedback report, and send it to relevant operation and maintenance personnel;

[0010] Step S500: Obtain management information for generator sets with abnormalities and update the knowledge graph based on the handling results.

[0011] Furthermore, step S100 includes:

[0012] Step S101: Collect normal historical operation data and abnormal historical operation data of generator sets in the power plant, establish normal historical operation dataset and abnormal historical operation dataset of generator sets respectively, collect the historical operation data of the same generator set equipment, extract the characteristics of the change of operating parameters of the same generator set equipment during the process of changing from normal operation state to abnormal operation state, and obtain the first type of feature function of the change of operating parameters of the same generator set equipment during operation.

[0013] Step S102: Obtain the abnormal equipment handling records in the power plant, perform structured processing on the records using natural language processing technology to obtain a structured dataset, match the data in the structured dataset with the generator set equipment entities, and obtain the second type of feature function of the change in the operating parameter values ​​of the same generator set equipment during the abnormal handling process.

[0014] Step S103: Take the process from the discovery of an operational abnormality to the completion of maintenance of the same generator set equipment as a feature event. According to the first type of feature function of the same feature event, obtain the data characteristics of the operating parameter values ​​of the generator set equipment when the protection device executes the protection strategy; according to the second type of feature function of the same feature event, obtain the parameter change amount of each abnormal handling step in the protection strategy on the operating data of the generator set equipment.

[0015] Step S104: Correspond the abnormal handling steps with the parameter changes in the operating data of the generator set equipment, and establish a knowledge graph of the protection strategies executed by the protection equipment in the power plant.

[0016] Furthermore, step S200 includes:

[0017] Step S201: Take a generator set in the power plant as the target device, set a unit sampling period of duration T, and obtain the data characteristics of the parameter values ​​of the target device in the unit sampling period;

[0018] Step S202: Match the data features in the knowledge graph. When a data feature matching the data feature is found in the knowledge graph, obtain the protection strategy corresponding to the data feature from the knowledge graph. Extract the abnormal handling steps executed by the protection device and the control target corresponding to each abnormal handling step from the protection strategy, and aggregate them to obtain the protection operation sequence P, where the i-th element in P includes (m i d i ), m i Let d represent the i-th exception handling step in P. i This represents the control objective corresponding to the i-th abnormal handling step in P;

[0019] In the power plant's equipment management system, the management strategy for the feedback regulation equipment of the generator set is obtained, including the conditions for initiating feedback regulation. By analyzing historical data, the data characteristics that require feedback regulation are obtained, the data characteristics of the current generator set's operating parameters are obtained, and the preset schemes are matched in the knowledge graph.

[0020] By analyzing abnormal data and reasoning based on knowledge, combined with expert knowledge and machine learning algorithms, the operating parameters and handling measures of the equipment are comprehensively analyzed. Historical data matching is performed based on the abnormal conditions of the generator set, and feedback adjustments are made when potential equipment failures occur, so that historical data and expert experience are fully utilized.

[0021] Furthermore, step S300 includes:

[0022] Step S301: Obtain the value v of the target device's operating data after the i-th anomaly handling step in the protection operation sequence P. i Calculate the data difference value k i k i =|v i -d i |;

[0023] Step S302: Obtain the data difference value k after the i-th exception handling step in the protection operation sequence P. i The difference value k between the data and the data after the (i+1)th exception handling step i+1 Get the time t from the start of the i-th exception handling step to the end of the (i+1)-th exception handling step. i，i+1 Calculate the rate of change μ of the j-th difference value. j μ j =(k i+1-k i ) / t i，i+1 , where j = i;

[0024] Step S303: Based on the order of abnormal handling in the protection operation sequence P, aggregate and sort the rate of change of difference values, and calculate the cumulative difference R of the first n rate of change of difference values. n ,

[0025] The actual results after the abnormality handling steps are compared with the control targets of the abnormality handling steps. The difference between the actual results and the control targets is calculated, and the cumulative value of the rate of change of the difference is calculated.

[0026] When the actual difference result gets closer and closer to the control target, the difference value k of the (i+1)th data point i+1 Less than the difference value k of the i-th data i The rate of change of the difference value is negative. When the cumulative rate of change of the difference is small, it indicates that the preset control steps have achieved the expected control effect and the control strategy matched by the system is the correct control measure.

[0027] Furthermore, step S400 includes:

[0028] Step S401: Obtain the first management threshold a, when R n When <a, continue to execute the operation steps in the protection operation sequence P. After the operation steps in the protection operation sequence P are completed, collect the operating data of the target device during the execution of the operation steps and record it in the first type of operation and maintenance data along with the protection operation sequence P.

[0029] Step S402: Obtain the second management threshold b, where b > 0 and b > a, when b > R n When >a, continue to execute the operation steps in the protection operation sequence P. After the operation steps in the protection operation sequence P are completed, collect the operating data of the target device during the execution of the operation steps and record it in the second type of operation and maintenance data along with the protection operation sequence P.

[0030] Step S403: After executing the q-th operation step in the protection operation sequence P, obtain the cumulative difference value R. q When R q When b is greater than or equal to b, the operation steps of the protection device are terminated, the first q operation steps in the protection operation sequence P and the data difference values ​​after each step are collected and recorded in the third type of operation and maintenance data, and alarm prompts are given to relevant operation and maintenance personnel.

[0031] In a protection operation sequence, each anomaly handling step corresponds to a control target. The sequence of target device operating data is compared with the sequence of control target data.i k represents the difference between each set of data. i+1 -k i Indicates changes in differences;

[0032] There are three scenarios for the change in the difference: the difference between the target equipment's operating data and the control target becomes smaller and smaller, and the difference for k... i+1 -k i After accumulating the values, a value less than 0 is obtained; the values ​​of the target equipment operating data and the control target show a roughly similar trend of change, for k i+1 -k i After accumulating the values, we get a value greater than 0. Since the trend of change is quite similar, k i+1 -k i The cumulative values ​​are relatively small; the difference between the target equipment operating data and the control target is increasing, affecting k. i+1 -k i After accumulating the values, we get a value greater than 0. Due to the increasing trend of change, k i+1 -k i The cumulative values ​​are relatively large;

[0033] In order to balance the changes over time, the difference μ per unit time is calculated and accumulated to obtain the cumulative difference value.

[0034] The system provides separate information prompts for three different scenarios after the operation steps are executed. The first type of operation and maintenance data indicates that the control of the generator set meets expectations after the protection equipment executes the operation steps matched from the knowledge graph. The second type of operation and maintenance data indicates that the control of the generator set is effective after the operation steps are executed, but the safety hazards cannot be completely eliminated. The third type of operation and maintenance data indicates that the greater the difference between the actual operating parameters of the generator set and the control target, the more likely there is an error in the matched control strategy or the setting of the control steps. After exceeding a certain threshold, the control steps are interrupted to prevent the danger from worsening.

[0035] Furthermore, step S500 includes:

[0036] Step S501: Send the different types of operation and maintenance data to the relevant departments of the power plant management. The relevant managers analyze the operating status of the target equipment according to the operation steps in the protection operation sequence P and adjust the operation steps in the protection operation sequence P.

[0037] Step S502: Obtain the adjusted operation steps from the relevant management personnel, replace the corresponding steps in the knowledge graph, and update the management strategy in the knowledge graph.

[0038] To better implement the above methods, a power generation data visualization management system based on big data is also proposed. The system includes:

[0039] The system comprises a historical data management module, a protection strategy management module, a difference comparison module, an operation and maintenance management module, and a knowledge graph management module. The historical data management module manages the historical data of generator sets in the power plant and obtains the correspondence between data change patterns and generator set equipment. The protection strategy management module obtains the management strategies and corresponding operation sequences for target equipment. The difference comparison module calculates the difference between the change trend and the management strategy target. The operation and maintenance management module analyzes the data differences and generates corresponding operation and maintenance records. The knowledge graph management module manages the knowledge graph.

[0040] Furthermore, the historical data management module includes: an operation data management unit, an operation and maintenance record management unit, and a data fusion unit. The operation data management unit is used to acquire historical operation data of generator set equipment and extract the patterns of change in the operation data of the same generator set equipment. The operation and maintenance record management unit is used to acquire abnormal equipment handling records in the power plant and extract the patterns of change in the operation data of the same generator set equipment. The data fusion unit is used to perform knowledge fusion on the data based on the correspondence between the data and the equipment entities.

[0041] Furthermore, the protection strategy management module includes: a data sampling unit, a data comparison unit, and an operation sequence management unit. The data sampling unit is used to sample the operating data of the target device, the data comparison unit is used to compare the data features of the operating parameters of the target device with the data features in the knowledge graph, and the operation sequence management unit is used to obtain the protection operation sequence corresponding to the target device.

[0042] Furthermore, the difference comparison module includes: a difference value calculation unit, a difference value change rate calculation unit, and a difference accumulation unit. The difference value calculation unit is used to calculate the difference value between the control target and the actual operating state of the target equipment. The difference value change rate calculation unit is used to calculate the difference value change rate. The difference accumulation unit is used to accumulate the difference value change rate and calculate the difference accumulation value.

[0043] Furthermore, the operation and maintenance management module includes: a first management unit, a second management unit, and a third management unit. The first management unit is used to obtain a first management threshold, compare it with the cumulative difference value, and generate a first type of operation and maintenance data. The second management unit is used to obtain a first management threshold and a second management threshold, compare them with the cumulative difference value, and generate a second type of operation and maintenance data. The third management unit is used to obtain a second management threshold, compare it with the cumulative difference value, terminate the operation steps, and generate a third type of operation and maintenance data.

[0044] Furthermore, the knowledge graph management module includes: a knowledge graph storage unit, a step replacement unit, and a knowledge graph update unit. The knowledge graph storage unit is used to store the knowledge graph, the step replacement unit is used to obtain replacement steps for the protection operation sequence, and the knowledge graph update unit is used to update the knowledge graph.

[0045] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: This invention integrates equipment operation data with unstructured or semi-structured data in equipment management logs to form a management knowledge graph for power plant generator units, identifying entities and relationships, and comprehensively capturing and expressing the complex data relationships in power plant production. Simultaneously, by utilizing the knowledge fusion of the knowledge graph, it matches the occurrence of abnormal data and provides corresponding reference processing methods, enabling power plant operation and maintenance personnel to respond more quickly to abnormal data, judge abnormal situations more accurately, and handle abnormal accidents more precisely, reducing the risk of accidents caused by abnormal data escalating. This invention can generate easily associative digital tags from multi-source heterogeneous data such as power plant unit control logic, operation data, procedures and specifications, emergency plans, technical measures, and accident reports, forming a knowledge graph in the power plant field. Based on the knowledge graph, a system framework can be constructed that can be used for abnormal data processing and provide auxiliary decision-making, providing more accurate operation data analysis and improving the ability of grassroots power plants to handle and respond to abnormal situations. Attached Figure Description

[0046] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0047] Figure 1 This is a schematic diagram of the structure of a power generation data visualization management system based on big data according to the present invention;

[0048] Figure 2 This is a flowchart illustrating a power generation data visualization management method based on big data according to the present invention.

[0049] Figure 3 This is a schematic diagram of a power plant system knowledge graph construction method based on big data-driven power generation data visualization management.

[0050] Figure 4 This is a schematic diagram of the structure of a knowledge graph-based power plant operation and maintenance data processing and auxiliary decision-making system for a power generation data visualization management system based on big data, according to the present invention.

[0051] Figure 5 This is a schematic flowchart of an embodiment of the power generation data visualization management method based on big data according to the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] Please see Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5 The present invention provides the following technical solution:

[0054] Step S100: By analyzing the historical management data of the generator sets in the power plant, a knowledge graph is constructed to show the protection strategies executed by the protection devices in the power plant when abnormalities occur in the generator sets.

[0055] Step S100 includes:

[0056] Step S101: Collect normal historical operation data and abnormal historical operation data of generator sets in the power plant, establish normal historical operation dataset and abnormal historical operation dataset of generator sets respectively, collect the historical operation data of the same generator set equipment, extract the characteristics of the change of operating parameters of the same generator set equipment during the process of changing from normal operation state to abnormal operation state, and obtain the first type of feature function of the change of operating parameters of the same generator set equipment during operation.

[0057] Step S102: Obtain the abnormal equipment handling records in the power plant, perform structured processing on the records using natural language processing technology to obtain a structured dataset, match the data in the structured dataset with the generator set equipment entities, and obtain the second type of feature function of the change in the operating parameter values ​​of the same generator set equipment during the abnormal handling process.

[0058] Step S103: Take the process from the discovery of an operational abnormality to the completion of maintenance of the same generator set equipment as a feature event. According to the first type of feature function of the same feature event, obtain the data characteristics of the operating parameter values ​​of the generator set equipment when the protection device executes the protection strategy; according to the second type of feature function of the same feature event, obtain the parameter change amount of each abnormal handling step in the protection strategy on the operating data of the generator set equipment.

[0059] Step S104: Correspond the abnormal handling steps with the parameter changes in the operating data of the generator set equipment, and establish a knowledge graph of the protection strategies executed by the protection equipment in the power plant;

[0060] Figure 3 The diagram illustrates a method for constructing a knowledge graph for a power plant system according to this embodiment. The main methods for constructing the knowledge graph include:

[0061] A1: Obtain historical normal operation data and historical abnormal operation data of power plant units, perform data cleaning, extract useful information from the raw data, remove noise and redundancy, obtain effective historical normal operation data set and historical abnormal operation data set of units, and label the entities in this structured dataset, and define their attributes and relationships.

[0062] A2: Obtain unstructured or semi-structured data such as power plant regulations, emergency plans, technical measures, and accident reports. Utilize natural language processing technology to extract knowledge from the entities, attributes, and relationships defined in the structured dataset, and transform this unstructured or semi-structured data into a structured dataset.

[0063] A3: The normal historical operation dataset of power plant units and the standard and specification dataset obtained from A1 and A2 are fused together, and the abnormal historical operation dataset of units is fused together with the emergency plan, technical measures and accident report datasets to achieve entity alignment, attribute alignment and relationship alignment, so as to obtain a complete description of the power plant entity operation standards and abnormal situations.

[0064] A4: Obtain the power plant data relationship map and the anomaly case map.

[0065] Step S200: Obtain the operating status of the power plant generator set equipment. When the generator set equipment is operating abnormally, match the management strategy in the knowledge graph and obtain the operation sequence corresponding to the management strategy.

[0066] Step S200 includes:

[0067] Step S201: Take a generator set in the power plant as the target device, set a unit sampling period of duration T, and obtain the data characteristics of the parameter values ​​of the target device in the unit sampling period;

[0068] Step S202: Match the data features in the knowledge graph. When a data feature matching the data feature is found in the knowledge graph, obtain the protection strategy corresponding to the data feature from the knowledge graph. Extract the abnormal handling steps executed by the protection device and the control target corresponding to each abnormal handling step from the protection strategy, and aggregate them to obtain the protection operation sequence P, where the i-th element in P includes (m i d i ), m i Let d represent the i-th exception handling step in P. iThis represents the control objective corresponding to the i-th abnormal handling step in P;

[0069] Step S300: Automatically execute the operation steps in the operation sequence through relevant protection equipment in the power plant, obtain the changing trend of equipment data, and calculate the difference between the changing trend and the management strategy objective;

[0070] Step S300 includes:

[0071] Step S301: Obtain the value v of the target device's operating data after the i-th anomaly handling step in the protection operation sequence P. i Calculate the data difference value k i k i =|v i -d i |;

[0072] Step S302: Obtain the data difference value k after the i-th exception handling step in the protection operation sequence P. i The difference value k between the data and the data after the (i+1)th exception handling step i+1 Get the time t from the start of the i-th exception handling step to the end of the (i+1)-th exception handling step. i，i+1 Calculate the rate of change μ of the j-th difference value. j μ j =(k i+1 -k i ) / t i，i+1 , where j = i;

[0073] Step S303: Based on the order of abnormal handling in the protection operation sequence P, aggregate and sort the rate of change of difference values, and calculate the cumulative difference R of the first n rate of change of difference values. n ,

[0074] Step S400: Evaluate the protection effect corresponding to the handling template, generate a feedback report, and send it to relevant operation and maintenance personnel;

[0075] Step S400 includes:

[0076] Step S401: Obtain the first management threshold a, when R n When <a, continue to execute the operation steps in the protection operation sequence P. After the operation steps in the protection operation sequence P are completed, collect the operating data of the target device during the execution of the operation steps and record it in the first type of operation and maintenance data along with the protection operation sequence P.

[0077] The preferred value is a = 0;

[0078] Step S402: Obtain the second management threshold b, where b > 0 and b > a, when b > R n When >a, continue to execute the operation steps in the protection operation sequence P. After the operation steps in the protection operation sequence P are completed, collect the operating data of the target device during the execution of the operation steps and record it in the second type of operation and maintenance data along with the protection operation sequence P.

[0079] Step S403: After executing the q-th operation step in the protection operation sequence P, obtain the cumulative difference value R. q When R q When b is greater than or equal to b, the operation steps of the protection device are terminated, the first q operation steps in the protection operation sequence P and the data difference values ​​after each step are collected and recorded in the third type of operation and maintenance data, and alarm prompts are given to relevant operation and maintenance personnel.

[0080] Step S500: Obtain management information for generator sets with abnormalities and update the knowledge graph based on the handling results;

[0081] Step S500 includes:

[0082] Step S501: Send the different types of operation and maintenance data to the relevant departments of the power plant management. The relevant managers analyze the operating status of the target equipment according to the operation steps in the protection operation sequence P and adjust the operation steps in the protection operation sequence P.

[0083] Step S502: Obtain the adjusted operation steps from the relevant management personnel, replace the corresponding steps in the knowledge graph, and update the management strategy in the knowledge graph;

[0084] Figure 4 This embodiment illustrates the workflow of the knowledge graph-based power plant operation and maintenance data processing and decision support system. Figure 5 This embodiment illustrates the steps of the implementation process, including:

[0085] B1: Obtain real-time power plant operation data and determine whether the protection equipment is abnormal by using a knowledge graph of the protection strategy execution.

[0086] B11: Real-time data anomaly: Yes, proceed to step B2;

[0087] B12: Real-time data is normal: No, proceed to step B3;

[0088] B2: After determining that the real-time data is abnormal, the knowledge graph of the protection policy executed by the protection device is used to determine whether it matches the protection policy. When a protection policy is matched, it is determined to trigger the main protection.

[0089] B21: Match found: Yes, proceed to step B4;

[0090] B22: No match found: No, proceed to step B5;

[0091] B3: After determining that the real-time data is normal, determine whether there is an abnormal trend;

[0092] B31: Error: Yes, proceed to step B5;

[0093] B32: Normal: No, proceed to step B6;

[0094] B4: After determining that the main protection has been triggered, calculate the matching degree based on the knowledge graph of the protection strategy executed by the protection device, align with the case with the highest matching degree and output it, and proceed to step B8;

[0095] B5: Based on the existing abnormality assessment information, notify the maintenance personnel to conduct further inspections and proceed to step B7;

[0096] B6: Record this situation in the knowledge graph of the protection device's protection strategy and update the knowledge graph;

[0097] B7: After the maintenance personnel have identified the cause, output the semi-structured anomaly report results and record this anomaly in the anomaly case graph;

[0098] B8: Use the anomaly case graph to perform path retrieval, provide the operation and maintenance personnel with the processing paths for reference, wait for the operation and maintenance personnel to make a decision, and then feed back the selected processing solution to the power plant's main control logic system.

[0099] B9: Based on the abnormal case map, integrate the operational data of the abnormal situation, enter the abnormal case map, update it, and output a standardized accident report.

[0100] The system includes:

[0101] Historical data management module, protection strategy management module, difference comparison module, operation and maintenance management module, and knowledge graph management module;

[0102] The historical data management module is used to manage the historical data of generator sets in the power plant, and to obtain the correspondence between data change patterns and generator sets. The historical data management module includes: an operation data management unit, an operation and maintenance record management unit, and a data fusion unit. The operation data management unit is used to obtain historical operation data of generator sets and extract the patterns of operation data changes of the same generator set. The operation and maintenance record management unit is used to obtain abnormal equipment handling records in the power plant and extract the patterns of operation data changes of the same generator set. The data fusion unit is used to perform knowledge fusion on the data based on the correspondence between data and equipment entities.

[0103] The protection strategy management module is used to obtain the management strategy and corresponding operation sequence of the target device. The protection strategy management module includes a data sampling unit, a data comparison unit and an operation sequence management unit. The data sampling unit is used to sample the operating data of the target device. The data comparison unit is used to compare the data features of the operating parameters of the target device with the data features in the knowledge graph. The operation sequence management unit is used to obtain the protection operation sequence corresponding to the target device.

[0104] The difference comparison module is used to calculate the difference between the changing trend and the management strategy target. The difference comparison module includes: a difference value calculation unit, a difference value change rate calculation unit, and a difference accumulation unit. The difference value calculation unit is used to calculate the difference value between the control target and the actual operating status of the target equipment. The difference value change rate calculation unit is used to calculate the difference value change rate. The difference accumulation unit is used to accumulate the difference value change rate and calculate the difference accumulation value.

[0105] The operation and maintenance management module is used to analyze data differences and generate corresponding operation and maintenance records. The operation and maintenance management module includes a first management unit, a second management unit, and a third management unit. The first management unit is used to obtain a first management threshold, compare it with the cumulative difference value, and generate a first type of operation and maintenance data. The second management unit is used to obtain a first management threshold and a second management threshold, compare them with the cumulative difference value, and generate a second type of operation and maintenance data. The third management unit is used to obtain a second management threshold, compare it with the cumulative difference value, terminate the operation steps, and generate a third type of operation and maintenance data.

[0106] The knowledge graph management module is used to manage the knowledge graph. It includes a knowledge graph storage unit, a step replacement unit, and a knowledge graph update unit. The knowledge graph storage unit stores the knowledge graph, the step replacement unit obtains the replacement steps for the protection operation sequence, and the knowledge graph update unit updates the knowledge graph.

[0107] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0108] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for visual management of power generation data based on big data, characterized in that: The method comprises the following steps: Step S100: By analyzing the historical management data of the generator set equipment in the power plant, a knowledge graph is constructed for the protection strategy executed by the protection equipment in the power plant when an abnormality occurs in the generator set equipment; Step S200: Obtain the operating status of the power plant generator set equipment. When the generator set equipment operates abnormally, match the management strategy in the knowledge graph to obtain the operation sequence corresponding to the management strategy; Step S300: automatically executing the operation steps in the operation sequence through the relevant protection devices in the power plant, obtaining the change trend of the device data, and calculating the difference between the change trend and the management strategy target; Step S400: Evaluate the protection effect corresponding to the disposal template, generate a feedback report, and send it to relevant operation and maintenance personnel; Step S500: Obtain the management of abnormal generator set equipment and update the knowledge graph according to the disposal results.

2. The method for visual management of power generation data based on big data according to claim 1, characterized in that: Step S100 includes: Step S101: collecting normal historical operation data and abnormal historical operation data of generator set equipment in the power plant, respectively establishing a normal historical operation data set and an abnormal historical operation data set of the generator set, collecting the historical operation data of the same generator set equipment, extracting the numerical change characteristics of the operating parameters of the generator set equipment during the process of the same generator set equipment changing from a normal operation state to an abnormal operation state, and obtaining the first type of characteristic function of the numerical change of the operating parameters of the same generator set equipment during the operation process; Step S102: Acquire abnormal equipment processing records in the power plant, perform structured processing on the records through natural language processing technology to obtain a structured data set, correspond the data in the structured data set to the generator set equipment entity, and obtain the second type of characteristic function of the numerical change of the operating parameters of the same generator set equipment during the abnormal processing process; Step S103: taking the process from the discovery of abnormal operation to the completion of maintenance of the same generator set equipment as a characteristic event, and obtaining the data characteristics of the numerical values ​​of the operating parameters of the generator set equipment when the protection device executes the protection strategy according to the first characteristic function of the same characteristic event; and obtaining the parameter change amount of the operating data of the generator set equipment in each abnormal handling step in the protection strategy according to the second characteristic function of the same characteristic event; Step S104: Match the abnormal handling steps with the parameter changes of the operating data of the generator set equipment, and establish a knowledge graph for the protection devices in the power plant to execute the protection strategy.

3. The method for visual management of power generation data based on big data according to claim 2, characterized in that: Step S200 includes: Step S201: taking a generator set in a power plant as a target device, setting a unit sampling period of duration T, and obtaining data characteristics of parameter values ​​of the target device in the unit sampling period; Step S202: Match the data feature in the knowledge graph. When a data feature identical to the data feature is matched in the knowledge graph, obtain the protection strategy corresponding to the data feature from the knowledge graph, extract the abnormality handling steps performed by the protection device and the control target corresponding to each abnormality handling step from the protection strategy, and collect them to obtain a protection operation sequence P, where the i-th element in P includes (m i , d i ), m i represents the i-th abnormal handling step in P, d i Represents the control target corresponding to the i-th abnormal handling step in P.

4. The method for visual management of power generation data based on big data according to claim 3 is characterized by: Step S300 includes: Step S301: Obtain the value v of the target device operation data after executing the i-th abnormality handling step in the protection operation sequence P i , calculate the data difference value k i , k i =|v i -d i |; Step S302: Obtain the data difference value ki after the i-th abnormal handling step and the data difference value k after the i+1-th abnormal handling step in the execution protection operation sequence P. i+1 , obtain the time length t from the start of executing the i-th abnormal handling step to the end of executing the i+1-th abnormal handling step i，i+1 , calculate the j-th difference value change rate μ j , μ j =(k i+1 -k i ) / t i，i+1 , where j = i; Step S303: According to the order of abnormal handling in the protection operation sequence P, the difference change rates are collected and sorted, and the difference cumulative value R of the first n difference change rates is calculated. n , 5. The method for visual management of power generation data based on big data according to claim 4 is characterized in that: Step S400 includes: Step S401: Obtain the first management threshold a. n When <a, continue to execute the operation steps in the protection operation sequence P. After the operation steps of the protection operation sequence P are completed, collect the operation data of the target device during the execution of the operation steps by the protection device, and record it with the protection operation sequence P into the first type of operation and maintenance data; Step S402: Obtain a second management threshold b, where b>0 and b>a. When b>R n >a, continue to execute the operation steps in the protection operation sequence P. After the operation steps of the protection operation sequence P are completed, collect the operation data of the target device during the protection device executing the operation steps, and record them together with the protection operation sequence P in the second type of operation and maintenance data; Step S403: After executing the qth operation step in the protection operation sequence P, obtain the difference cumulative value R q , when R q When ≥b, the operation steps of the protection equipment are terminated, the data difference values ​​of the first q operation steps in the protection operation sequence P and after each step are executed are collected and recorded in the third category of operation and maintenance data, and an alarm is given to the relevant operation and maintenance personnel.

6. The method for visual management of power generation data based on big data according to claim 5 is characterized by: Step S500 includes: Step S501: sending different types of operation and maintenance data to relevant departments of power plant management, and relevant managers analyze the operating status of target equipment along the operation steps in the protection operation sequence P, and adjust the operation steps in the protection operation sequence P; Step S502: Obtain the operation steps adjusted by the relevant managers, replace the corresponding steps in the knowledge graph, and update the management strategy in the knowledge graph.

7. A power generation data visualization management system for a power generation data visualization management method based on big data as claimed in any one of claims 1 to 6, characterized in that: The system includes the following modules: a historical data management module, a protection strategy management module, a difference comparison module, an operation and maintenance management module and a knowledge graph management module, wherein the historical data management module is used to manage the historical data of the generator set equipment in the power plant, and obtain the correspondence between the data change law and the generator set equipment; the protection strategy management module is used to obtain the management strategy of the target equipment and the corresponding operation sequence; the difference comparison module is used to calculate the difference between the change trend and the management strategy target; the operation and maintenance management module is used to analyze the data difference and generate the corresponding operation and maintenance records; the knowledge graph management module is used to manage the knowledge graph.

8. The power generation data visualization management system according to claim 7, characterized in that: The historical data management module includes: an operation data management unit, an operation and maintenance record management unit and a data fusion unit, wherein the operation data management unit is used to obtain the historical operation data of the generator set equipment and extract the law of the change of the operation data of the same generator set equipment; the operation and maintenance record management unit is used to obtain the abnormal equipment processing records in the power plant and extract the law of the change of the operation data of the same generator set equipment; the data fusion unit is used to perform knowledge fusion on the data according to the corresponding relationship between the data and the equipment entity; The protection strategy management module includes: a data sampling unit, a data comparison unit and an operation sequence management unit, wherein the data sampling unit is used to sample the operating data of the target device, the data comparison unit is used to compare the data features of the operating parameters of the target device with the data features in the knowledge graph, and the operation sequence management unit is used to obtain the protection operation sequence corresponding to the target device.

9. The power generation data visualization management system according to claim 7, characterized in that: The difference comparison module includes: a difference value calculation unit, a difference value change rate calculation unit and a difference accumulation unit, wherein the difference value calculation unit is used to calculate the difference value between the control target and the actual operating state of the target device, the difference value change rate calculation unit is used to calculate the difference value change rate, and the difference accumulation unit is used to accumulate the difference value change rate to calculate the difference accumulation value; The operation and maintenance management module includes: a first management unit, a second management unit and a third management unit, wherein the first management unit is used to obtain a first management threshold, compare it with the cumulative difference value, and generate a first type of operation and maintenance data; the second management unit is used to obtain the first management threshold and the second management threshold, compare them with the cumulative difference value, and generate a second type of operation and maintenance data; the third management unit is used to obtain the second management threshold, compare it with the cumulative difference value, terminate the operation step, and generate a third type of operation and maintenance data.

10. The power generation data visualization management system according to claim 7, characterized in that: The knowledge graph management module includes: a knowledge graph storage unit, a step replacement unit and a knowledge graph update unit, wherein the knowledge graph storage unit is used to store the knowledge graph, the step replacement unit is used to obtain replacement steps for the protection operation sequence, and the knowledge graph update unit is used to update the knowledge graph.

Images