Hydraulic power plant operation on-duty log auxiliary generation method

Abstract

The invention discloses a hydraulic power plant operation on-duty log auxiliary generation method. The method comprises the following steps: S1, multivariate data acquisition: acquiring structured data and time sequence measurement point data of a monitoring system, an online monitoring system and a production management system in real time; s2, a rule arrangement engine: configuring a working condition judgment operator and a log output operator through a visual interface, establishing a mapping relation between an equipment state and log generation, and performing anomaly recognition and early warning; s3, service arrangement: performing secondary arrangement on the basic service data based on the log template to generate log paragraphs conforming to specifications; s4, automatic writing: writing the generated log content into a production management system database through a data interface; and S5, service authentication identification: arranging a service processing process in a visual mode and exposing the service processing process as a callable service. According to the method, automatic, standard and accurate generation of the on-duty log is realized through automatic collection of multi-source data, regularized anomaly recognition and early warning coefficient calculation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent supervision of hydropower plants, and in particular to a method for assisting the generation of a hydropower plant operation shift log. BACKGROUND

[0002] With the development of digital technology, intelligent supervision and shift log intelligent recognition through Internet of Things devices are inevitable trends.

[0003] In the prior art, CN117371990B proposes an intelligent management platform for water power plant tools based on the Internet of Things; it relates to the technical field of water power plant diversion tool management. The management platform monitors the state of the diversion tool in real time and detects whether the diversion tool is affected by blockage, cracks or other abnormal conditions in a timely manner. Through the monitoring of turbulent flow state, problems caused by turbulent flow can be found and addressed in a timely manner, so that the water power plant can take necessary maintenance measures before the problem occurs, reducing the risk of equipment failure and downtime, thereby improving the reliability and continuity of production.

[0004] CN110020965A proposes an intelligent start-stop guidance strategy and system for giant hydropower plants; the generator set start-stop monitoring information is obtained; the system characteristic quantity of the generator set monitoring information is obtained according to the start-stop monitoring information; then the generator set system characteristic quantity data increase value is calculated; finally, it is judged whether the characteristic quantity data increase value exceeds the alarm reference value, if not, return to step to reacquire generator set start-stop detection information; if it exceeds the alarm reference value, dynamic alarm is given. The start-stop monitoring and guidance function of the generator set is realized, the key links of the unit start-stop process are effectively and automatically monitored, the information such as the time used by each link, the trend change, and whether the device measurement point state is normal is automatically displayed, important measurement points are developed for the whole process monitoring and analysis of the unit start-stop transient and steady state conditions, the problems existing in the equipment during the start-stop process are warned in advance, and the efficiency of the operation personnel monitoring and the success rate of the automatic start-stop of the power plant are improved.

[0005] The operation personnel of the power plant must manually fill in the operation shift log in the production management system every shift, which is the most important part of the daily work of the operation personnel. The current problems are as follows: Manual filling is inefficient, multiple business system data (monitoring system, online monitoring system, production management system, etc.) need to be manually integrated, and more than 100 information items are processed daily; log specification is poor: relying on the experience of the operation personnel, it is easy to have inconsistent descriptions and missing information; real-time performance is insufficient: it is not possible to record equipment state changes (such as start-stop operation, early warning events, etc.) in a timely manner.

[0006] The prior art has gradually carried out intelligent identification and early warning through Internet of Things + data identification, but the intelligent identification and early warning is based on overall monitoring data, and there are many error items and interference items, which is not conducive to the accuracy of intelligent identification and early warning. SUMMARY

[0007] The technical problem to be solved by the present application is to provide a hydroelectric plant operation duty log auxiliary generation method, which solves the technical problems of low efficiency, poor standardization, insufficient real-time performance caused by manual filling of the hydroelectric plant operation duty log, and low early warning accuracy of the existing intelligent identification system due to data redundancy and many interference items, and realizes automatic, standardized and accurate generation of the duty log through multi-source data automatic acquisition, rule-based abnormality identification and early warning coefficient calculation.

[0008] To solve the above technical problems, the technical scheme adopted by the present application is: a hydroelectric plant operation duty log auxiliary generation method, comprising the following steps: S1, multi-element data acquisition: real-time acquisition of structured data and time sequence measurement point data of a monitoring system, an online monitoring system and a production management system; S2, rule arrangement engine: configuring working condition judgment operators and log output operators through a visual interface, establishing a mapping relationship between device states and log generation, and performing abnormality identification and early warning; S3, service arrangement: performing secondary arrangement of basic service data based on a log template to generate log paragraphs conforming to the specification; S4, automatic writing: writing the generated log content into a production management system database through a data interface; S5, service authentication identification: arranging the service processing process in a visual manner and exposing it as a callable service.

[0009] Preferably, the step S2 comprises the following steps: S201, start-up and shutdown operation identification: realizing state change judgment of unit start-up and shutdown related measurement point signals through a rule arrangement tool, generating basic data into a duty record table, and then generating the final duty log after basic data assembly through service arrangement; S202, water regime identification: acquiring upstream water level, downstream water level, inflow and outflow data according to the periodic acquisition measurement points configured by the duty log generation, assembling the generated content according to the acquired data to obtain water regime identification data; S203, natural disaster early warning identification: connecting natural disaster early warning data, if early warning data is monitored during the shift, outputting meteorological early warning information of the duty log according to the configuration template, and identifying future climate data to obtain climate identification data.

[0010] Preferably, the start-up and shutdown operation identification in the step 201 comprises: The water power plant start-up operation to shutdown operation is divided into an operation cycle; Obtaining equipment parameters, water flow parameters, valve parameters and pressure parameters in the operation cycle; Building a working condition judgment operator, predicting the pressure parameters and calculating the abnormal coefficient; The operation cycle is divided into start-up, running and shutdown three stages, the abnormal coefficient is calculated respectively, and the operation cycle abnormal coefficient is obtained comprehensively; The calculation formula of the operation cycle abnormal coefficient is: ; Among them, The operation cycle abnormal coefficient is represented; The start-up abnormal coefficient is represented; The first weight is represented; The running abnormal coefficient is represented; The second weight is represented; The shutdown abnormal coefficient is represented; The third weight is represented.

[0011] Preferably, the step S201 further comprises: Setting a time cycle, monitoring the number of start-up and shutdown operations and the interval time in the cycle; According to the relationship between the operation cycle abnormal coefficient and the time interval, the time interval index and the mutation index are identified; Calculate the comprehensive abnormal coefficient, which is used to evaluate the abnormal operation degree of the equipment in the time cycle; The calculation formula of the comprehensive abnormal coefficient is: ; Among them, The comprehensive abnormal coefficient is represented; The operation cycle abnormal coefficient is represented; The cycle weight coefficient is represented; The time interval index is represented, which is obtained according to the relationship between the operation cycle abnormal coefficient and the time interval; The mutation index is represented, which is obtained by identifying the data difference between the operation cycles.

[0012] Preferably, the step S201 further comprises: According to the natural climate data and the water regime data, the future water regime parameters are predicted, and the predicted water flow parameters are obtained; Calculate the water regime change coefficient and the working condition correction coefficient; Combined with the water regime change coefficient, the comprehensive abnormal coefficient and the working condition correction coefficient, the early warning coefficient is calculated; ; Among them, The early warning coefficient is represented; represents the water regime change coefficient; represents the water regime change weight; represents the comprehensive anomaly coefficient; represents the working condition correction coefficient.

[0013] Preferably, the step S202 is specifically as follows: Data acquisition: the system automatically acquires upstream water level, downstream water level, inflow and outflow data from the measuring point according to the preset time period (such as every hour, every day); the data sources include sensors, databases or API interfaces; Data assembly: the acquired data is assembled according to the predefined format to generate structured water regime data; the assembled data includes timestamp, measuring point name, water level data and flow data; Data analysis: the assembled data is analyzed to identify abnormal water level or flow changes; a water regime identification report is generated, including detailed information of normal and abnormal water regimes; Data storage and display: the generated water regime identification data is stored in the database for subsequent query and analysis; the water regime data is displayed through visualization tools (such as dashboards, charts) for real-time monitoring by management personnel.

[0014] Preferably, the step S203 is specifically as follows: Early warning data docking: the system is docked with the enterprise information integration system to obtain real-time natural disaster early warning data; the early warning data includes meteorological early warning data (such as heavy rain, flood) and geological disaster early warning data; Early warning monitoring and log generation: during the shift, the system monitors the early warning data in real time; if early warning information is detected, the system automatically generates a shift log according to the configured template; the shift log content includes early warning type, early warning level, impact range and expected duration; Climate data identification: the system is docked with future climate data (such as weather forecast) to identify possible future climate changes; according to the climate data, a climate identification report is generated, including future rainfall, temperature change and wind speed information; Early warning response and notification: the system automatically triggers the response mechanism according to the early warning level and sends notifications to relevant personnel or starts the emergency plan; provides visual display of early warning information to help management personnel quickly understand the current and future climate conditions.

[0015] Preferably, the step S3 is specifically as follows: Template engine architecture: Introducing a template engine based on natural language processing (NLP), supporting dynamic variable placeholders such as {time} and {measurement point value}, and automatically populating structured data through contextual semantic analysis; The logical layers of the template engine include a basic data layer (storing raw measurement point data), a logical assembly layer (executing rule judgment and data association), and a semantic optimization layer (converting structured data into natural language log paragraphs). Data adaptation: Establish a mapping table between the measurement point codes of each system in the hydropower plant and the fields of the production management system to solve the problem of data naming differences across systems; for the missing time-series measurement point data in the monitoring system, use linear interpolation algorithm or prediction algorithm based on operating conditions to complete the data; Version management: Supports archiving and quick rollback of historical versions of log templates, and records operation logs for each template modification; provides A / B testing functionality, which can run multiple template versions in parallel and compare the readability and accuracy of the generated logs.

[0016] Preferably, the automatic writing in step S4 adopts a two-phase commit mechanism and breakpoint resume technology to ensure the atomicity and reliability of log writing.

[0017] Preferably, step S5 is as follows: The service request component, data processing component, and service response component are orchestrated in a visual drag-and-drop manner, allowing business personnel to view the entire data service processing flow in real time. The orchestrated services are exposed to the outside world through standardized interfaces, which can only be called by authorized advanced application systems of hydropower plants and third-party platforms.

[0018] This invention provides a method for assisting in the generation of hydropower plant operation duty logs, which has the following beneficial effects: 1. Compared to the overall data identification in existing technologies, this invention divides the hydropower plant's start-up and shutdown operations into three phases: start-up, operation, and shutdown. The invention acquires the hydropower plant's operating parameters within this phase and further divides the phase into three stages: start-up, operation, and shutdown. Within each stage, the pressure parameter prediction module identifies equipment parameters, water flow parameters, and valve parameters to obtain predicted pressure parameters. Anomaly coefficients are obtained by comparing the predicted and actual pressure parameters, resulting in start-up anomaly coefficients, operation anomaly coefficients, and shutdown anomaly coefficients. Further calculation yields the operation cycle anomaly coefficient. This allows for the hierarchical and categorized use of hydropower plant data, effectively avoiding the influence of redundant data and improving identification accuracy and efficiency.

[0019] 2. Following the initial step of further dividing the operation cycle into three stages: startup, operation, and shutdown; and calculating the startup anomaly coefficient, operation anomaly coefficient, shutdown anomaly coefficient, and operation cycle anomaly coefficient, this application further sets a time period to monitor the number of startup and shutdown operations within that time period, as well as the interval time; identifies the time interval index based on the relationship between the operation cycle anomaly coefficient and the time interval; identifies the mutation index by analyzing the data differences among the startup, operation, and shutdown time periods within each operation cycle; and identifies the comprehensive anomaly coefficient based on the operation cycle anomaly coefficient and the time interval within the time period. Through the comprehensive anomaly coefficient, abnormal equipment operation can be accurately and promptly detected, allowing for appropriate maintenance measures to be taken.

[0020] 3. By using historical event cycle data, and based on natural climate and hydrological data, predictive hydrological parameters for future cycles are obtained to acquire predicted flow parameters. Based on the predicted flow parameters and their variations, hydrological variation coefficients are identified. Operating condition correction coefficients are obtained by combining operational cycle anomaly coefficients and time intervals with mechanical wear, hydraulic impact, vibration fluctuations, pipeline vacuum, and thermal stress accumulation. Based on the hydrological variation coefficient, comprehensive anomaly coefficient, and operating condition correction coefficient, early warning coefficients are predicted, thus accurately determining the degree of danger of start-up and shutdown operations in future time cycles based on historical event cycle parameters. This provides reference technology for equipment maintenance and operation. Attached Figure Description

[0021] The present invention will be further described below with reference to the accompanying drawings and embodiments: Figure 1 This is a schematic diagram of the structure of the present invention; Figure 2 This is a flowchart illustrating the start / stop operation recognition process of the present invention. Figure 3 This is a flowchart of the comprehensive anomaly coefficient calculation for this invention; Figure 4 This is a flowchart of the early warning coefficient calculation process of the present invention. Detailed Implementation

[0022] like Figure 1 As shown, a method for assisting in the generation of a hydropower plant operation duty log includes the following steps: S1. Multi-source data acquisition: Real-time acquisition of structured data and time series measurement point data from monitoring systems, online monitoring systems, and production management systems; During the operation of a hydropower plant, start-up and shutdown operations are required due to changes in load demand, equipment maintenance and repair, water level changes, and power grid frequency regulation.

[0023] The start and stop operation of the hydropower plant is an important link in the operation and management of the hydropower plant, which involves the start and stop process of the generator unit. Reasonable start and stop operation is crucial to ensure the safety of the power plant equipment, improve the efficiency of power generation, and ensure the stability of power supply.

[0024] Therefore, the start and stop operation of the hydropower plant is taken as the core, and multi-source data is collected. Through the power plant monitoring system, time sequence measurement point data related to the start and stop identification steps of the hydropower plant, water level and flow time sequence measurement point data are collected. Through the interface of enterprise information integration system, natural disaster warning data is collected.

[0025] The start and stop related data, unit state, GCB closing and opening, unit speed, active power, start and stop step number, and related data that need to be abnormally warned during the start and stop process: pressure data, flow data, valve data, etc.

[0026] S2, rule arrangement engine: configure the working condition judgment operator and the log output operator through the visual interface, establish the mapping relationship between the device state and the log generation, and perform abnormal identification and warning; S3, service arrangement: based on the log template, the basic service data is arranged again to generate the log paragraph conforming to the specification; S4, automatic writing: the generated log content is written into the production management system database through the data interface; S5, service authentication identification: the service processing process is arranged in a visual way and exposed as a callable service.

[0027] Preferably, the step S2 comprises the following steps: S201, start and stop operation identification: the state change of the unit start and stop related measurement point signal is judged through the rule arrangement tool, and the basic data is generated into the duty record table. Then, the final duty log is generated after the basic data is assembled through service arrangement; The operators used are introduced: working condition judgment operator, used for single and multiple measurement point configuration condition judgment; duty log output operator, used for outputting the duty log basic data to the duty log table.

[0028] During the start and stop operation of the hydropower plant, the frequent opening and closing of the valve can easily cause harm to the hydropower plant facilities, such as water hammer phenomenon. Water hammer phenomenon refers to the phenomenon of abnormal pressure fluctuation in a fluid system due to sudden change of flow rate. Therefore, the abnormality during the start and stop operation is identified and warned.

[0029] S202, water regime identification: according to the periodic acquisition measurement points generated by the duty log configuration, the upstream water level, downstream water level, and inflow and outflow data are obtained. According to the obtained data, the content is assembled to obtain the water regime identification data; S203, natural disaster warning identification: interface with natural disaster warning data, if warning data is monitored during the shift, output the weather warning information value shift log according to the configuration template, and identify the future climate data to obtain climate identification data.

[0030] Preferably, as shown in the step 201, the start-stop operation identification includes: Figure 2 Divide the start-stop operation of the hydropower plant into an operation cycle; Obtain device parameters, water flow parameters, valve parameters, and pressure parameters within the operation cycle; Device parameters: pipe wall thickness, pipe length, pipe diameter, pipe structure, pipe tensile coefficient, etc. Water flow parameters: water flow velocity, water head height, water flow temperature, water viscosity, water flow rate Valve parameters: valve opening and closing speed Pressure parameters: pressure wave peak value, pressure wave duration; the pressure parameters are obtained by setting monitoring points at various locations in the hydropower plant.

[0031] Construct a working condition judgment operator to predict pressure parameters and calculate abnormal coefficients; The working condition judgment operator includes a pressure parameter prediction module, which identifies device parameters, water flow parameters, and valve parameters based on the pressure parameter prediction module to obtain predicted pressure parameters; and obtains abnormal coefficients based on the predicted pressure parameters and actual pressure parameters; Divide the operation cycle into start, run, and stop three stages, respectively calculate the abnormal coefficients, and comprehensively obtain the operation cycle abnormal coefficients; The calculation formula of the operation cycle abnormal coefficient is: ; Wherein, represents the operation cycle abnormal coefficient; represents the start abnormal coefficient; represents the first weight; represents the run abnormal coefficient; represents the second weight; represents the stop abnormal coefficient; represents the third weight.

[0032] During the operation of the hydropower plant equipment and system, monitoring and analyzing the frequency and interval time of start-stop operation are crucial to ensure the stability of the equipment and predict potential failures. By monitoring the start-stop operation within a set time period, the number of operations within the period and the interval time between each operation can be obtained. These data provide a basis for further analyzing the running state of the equipment.

[0033] ​Preferably, as Figure 3 As shown in the step S201 further comprises: Set a time period, monitor the number of start-stop operations and interval time within the period; According to the relationship between the operation cycle abnormal coefficient and the time interval, identify the time interval index and the mutation index; Calculate the comprehensive abnormal coefficient for evaluating the degree of abnormal operation of the equipment within the time period; The formula for calculating the comprehensive abnormal coefficient is: ; Among them, Comprehensive abnormal coefficient; Operation cycle abnormal coefficient; Cycle weight coefficient; Time interval index, identified according to the relationship between the operation cycle abnormal coefficient and the time interval; Mutation index, identified by the data difference between operation cycles.

[0034] In this formula, Comprehensive abnormal coefficient, reflecting the abnormal degree of operation of the equipment within a certain time period. Operation cycle abnormal coefficient, which measures the abnormal situation of the start-stop operation cycle of a hydropower plant within a time period.

[0035] Cycle weight coefficient For adjusting the influence degree of time interval on the comprehensive abnormal coefficient.

[0036] Time interval index Is identified according to the relationship between the operation cycle abnormal coefficient and the time interval, reflecting the influence of operation interval time on the abnormal degree. Specifically, it is identified by the change of operation cycle abnormal coefficient with time interval of each operation cycle.

[0037] Mutation index Is identified by the data difference between operation cycles, measuring the mutation situation between operation cycles; specifically, it is identified by the data difference of start-up, running and shutdown in each operation cycle; This method not only can help to identify the potential failure of the equipment, but also can provide data support for the maintenance and optimization of the equipment. By regularly monitoring and analyzing the comprehensive abnormal coefficient, the abnormal operation of the equipment can be found in time, and corresponding maintenance measures can be taken to avoid equipment failure and improve the running efficiency and reliability of the equipment.

[0038] Preferably, as Figure 4 As shown in the step S201 further comprises: According to natural climate data and water regime data to predict future water regime parameters, and obtain predicted water flow parameters; Calculate the water regime change coefficient and the working condition correction coefficient; Combine the water regime change coefficient, the comprehensive anomaly coefficient and the working condition correction coefficient to calculate the warning coefficient; ; Among them, The warning coefficient is represented by W; The water regime change coefficient is represented by W; The water regime change weight is represented by W; The comprehensive anomaly coefficient is represented by W; The working condition correction coefficient is represented by W.

[0039] The working condition correction coefficient is obtained by identifying the working condition wear correction module in the working condition judgment operator; the acquisition process is: due to the start and stop operation of the hydropower plant, it will cause: Mechanical fatigue: the guide vane pivot wear rate increases by 3 times (actual measurement data: the annual wear amount increases from 0.1mm to 0.3mm); Water hammer pressure impact: the pressure pulsation peak value exceeds the design value by 2.1 times (8MPa vs 3.8MPa) during emergency shutdown, causing pipeline weld cracking; Vibration anomaly accumulation: frequent start and stop makes the rotor imbalance accumulate, and the vibration intensity deteriorates from 2.5mm / s to 8.3mm / s (ISO 10816-5 standard limit value 7.1mm / s) and the like.

[0040] Therefore, in the warning process, the wear condition of the working condition needs to be identified to improve the accuracy of the prediction; Screening the indicators closely related to start and stop, including five dimensions: mechanical wear, hydraulic impact, vibration fluctuation, pipeline vacuum and thermal stress accumulation; and selecting core indicators, as shown in the following table:

[0041] Through the above five data dimensions, combined with the obtained operation period anomaly coefficient and time interval, the working condition correction coefficient is obtained.

[0042] Preferably, the step S202 is specifically as follows: Data acquisition: the system automatically acquires upstream water level, downstream water level, inflow and outflow data from the measurement point according to the preset time period (such as every hour, every day); the data sources include sensors, databases or API interfaces; Data assembly: the obtained data is assembled according to the predefined format to generate structured water regime data; the assembled data includes timestamp, measurement point name, water level data and flow data; Data analysis: Analyze the assembled data to identify abnormal water level or flow changes; generate a water regime identification report, including detailed information of normal and abnormal water regimes; Data storage and display: Store the generated water regime identification data in the database for subsequent query and analysis; display the water regime data through visualization tools (such as dashboards, charts) for real-time monitoring by management personnel.

[0043] Preferably, the step S203 is specifically as follows: Early warning data docking: The system is docked with the enterprise information integration system to obtain real-time natural disaster early warning data; the early warning data includes meteorological early warning data (such as heavy rain, flood) and geological disaster early warning data; Early warning monitoring and log generation: During the shift, the system monitors the early warning data in real time; if early warning information is detected, the system automatically generates a shift log according to the configured template; the shift log content includes early warning type, early warning level, impact range, and expected duration; Climate data identification: The system is docked with future climate data (such as weather forecast) to identify possible future climate changes; according to the climate data, a climate identification report is generated, including future rainfall, temperature change, and wind speed information; Early warning response and notification: The system automatically triggers the response mechanism according to the early warning level and sends notifications to relevant personnel or starts the emergency plan; provides visual display of early warning information to help management personnel quickly understand the current and future climate conditions.

[0044] Preferably, the step S3 is specifically as follows: Template engine architecture: Introduce a natural language processing (NLP) based template engine, support {time}, {measuring point value} and other dynamic variable placeholders, automatically fill in structured data through context semantic analysis; the logic layer of the template engine includes a basic data layer (stores original measuring point data), a logical assembly layer (executes rule judgment and data association), and a semantic optimization layer (converts structured data into natural language log paragraphs); Data adaptation: Establish a mapping table between the measuring point codes of each system in the hydropower plant and the fields of the production management system to solve the problem of cross-system data naming differences; for missing time series measuring point data in the monitoring system, use linear interpolation algorithm or prediction algorithm based on working condition state for data completion; Version management: Support historical version archiving and quick rollback of log templates, record operation logs of each template modification; provide A / B testing function, run multiple template versions in parallel and compare the readability and accuracy of generated logs.

[0045] Preferably, the step S4 uses a two-phase commit mechanism and breakpoint resume technology to ensure the atomicity and reliability of log writing.

[0046] Preferably, the step S5 is specifically as follows: The service request component, the data processing component and the service response component are arranged in a visual drag-and-drop manner, so that a business personnel can view a whole process of data service in real time. The service after arrangement is exposed to the outside through a standardized interface, and only authorized senior application systems of hydropower plants and third-party platforms are allowed to call.

[0047] The application firstly collects structured data and time series measurement point data (focusing on start-stop, water regime and natural disaster early warning related data) of a monitoring system, an online monitoring system, a production management system and an enterprise information integration system in real time; secondly, a work condition judgment operator and a log output operator are configured based on a visual interface, start-stop operation recognition (operation cycle abnormality coefficient is calculated in stages according to a "start-up-operation-stop" cycle), water regime recognition (water level and flow data are periodically acquired and analyzed for abnormality), and natural disaster early warning recognition (warning data are connected to generate logs and predict climate) are completed, and a comprehensive abnormality coefficient and a warning coefficient are calculated in combination with work condition wear data in five dimensions of operation cycle abnormality coefficient, time interval and mechanical wear, so as to improve the abnormality recognition precision; thirdly, a basic data is secondarily arranged based on a natural language processing template engine, so as to solve the cross-system data adaptation problem and support template version management; fourthly, a two-stage commit and breakpoint resume technology is used to automatically write logs into a production management system database; and finally, a service processing process is visualized and arranged, and only authorized systems are allowed to call. The method realizes automatic, standardized and accurate generation of a duty log, effectively reduces data redundancy interference, improves equipment abnormality warning precision and operation reliability, and reduces manual operation cost.

[0048] The above-mentioned embodiments are only preferred technical solutions of the application, and should not be regarded as limitation of the application. The protection scope of the application should be the technical solutions recited in the claims, including equivalent replacement solutions of the technical features recited in the claims. That is, equivalent replacement improvements within this range are also within the protection scope of the application.

Claims

1. A method for assisting generation of a hydroelectric plant operation shift log, characterized in that, The method comprises the following steps: S1, multi-element data acquisition: real-time acquisition of structured data and time series measurement point data of a monitoring system, an online monitoring system and a production management system; S2, rule arrangement engine: configuring working condition judgment operators and log output operators through a visual interface, establishing a mapping relationship between device states and log generation, and performing abnormality identification and early warning; S3, service arrangement: performing secondary arrangement on basic service data based on a log template to generate a log paragraph conforming to a specification; S4, automatic writing: writing the generated log content into a production management system database through a data interface; S5, service authentication identification: arranging a service processing process in a visual manner and exposing it as a callable service.

2. The method of claim 1, wherein, The step S2 comprises the following steps: S201, start-stop operation identification: realizing state change judgment of unit start-stop related measurement point signals through a rule arrangement tool, generating basic data into a shift record table, and then generating a final shift log after basic data assembly through service arrangement; S202, water regime identification: acquiring upstream water level, downstream water level, reservoir inflow and outflow data according to a periodically generated configuration measurement point, assembling generated content according to the acquired data to obtain water regime identification data; S203, natural disaster early warning identification: connecting natural disaster early warning data, if early warning data is monitored during a shift, outputting meteorological early warning information of the shift log according to a configuration template, and identifying future climate data to obtain climate identification data.

3. The method of claim 2, wherein, The start-stop operation identification in the step 201 comprises: dividing water plant start operation to stop operation into an operation period; acquiring device parameters, water flow parameters, valve parameters and pressure parameters in the operation period; constructing a working condition judgment operator, predicting a pressure parameter and calculating an abnormality coefficient; dividing the operation period into start, running and stop three stages, respectively calculating the abnormality coefficient, and comprehensively obtaining an operation period abnormality coefficient; the calculation formula of the operation period abnormality coefficient is: ； wherein, represents an operating cycle abnormality coefficient; represents a start-up abnormality coefficient; represents a first weight; represents a running abnormality coefficient; represents a second weight; represents a stop abnormality coefficient; represents a third weight.

4. The method of claim 3, wherein, The step S201 further comprises: setting a time period, monitoring the number of start-stop operations and interval time in the period; identifying a time interval index and a mutation index according to the relationship between the operation period abnormality coefficient and the time interval; calculating a comprehensive abnormality coefficient for evaluating the abnormal operation degree of the device in the time period; The calculation formula of the comprehensive abnormality coefficient is: ; wherein, represents a comprehensive abnormality coefficient; represents an operation period abnormality coefficient; represents a period weight coefficient; represents a time interval index, which is identified according to the relationship between the operation period abnormality coefficient and the time interval; represents a mutation index, which is identified by the data difference between the operation periods.

5. The method of claim 5, wherein, The step S201 further comprises: predicting future water regime parameters according to natural climate data and water regime data to obtain predicted water flow parameters; calculating a water regime change coefficient and a working condition correction coefficient; combining the water regime change coefficient, the comprehensive abnormality coefficient and the working condition correction coefficient to calculate a warning coefficient; ； wherein, represents a warning coefficient; represents a water regime change coefficient; represents a water regime change weight; represents a comprehensive anomaly coefficient; represents a working condition correction coefficient.

6. The method of claim 2, wherein, The step S202 specifically comprises the following steps: data acquisition: the system automatically acquires upstream water level, downstream water level, reservoir inflow and outflow data from measurement points according to a preset time period; data sources include sensors, databases or API interfaces; data assembly: assembling the acquired data according to a predefined format to generate structured water regime data; the assembled data includes timestamp, measurement point name, water level data and flow data; Data analysis: Analyze the assembled data to identify abnormal water level or flow changes; generate a water regime identification report, including detailed information on normal and abnormal water regimes; Data storage and display: Store the generated water regime identification data in the database for future queries and analysis; display the water regime data through visualization tools for real-time monitoring by management personnel.

7. The method of claim 2, wherein, The step S203 is specifically as follows: Early warning data docking: The system is integrated with the enterprise information system to obtain real-time natural disaster early warning data; the early warning data includes meteorological early warning data and geological disaster early warning data; Early warning monitoring and log generation: During the shift, the system monitors the early warning data in real time; If early warning information is detected, the system automatically generates a shift log according to the configured template; the shift log content includes early warning type, early warning level, impact range, and expected duration; Climate data identification: The system interfaces with future climate to identify possible future climate changes; based on climate data, generate a climate identification report including future rainfall, temperature changes, and wind speed information; Early warning response and notification: The system automatically triggers the response mechanism according to the early warning level and sends notifications to relevant personnel or initiates emergency plans; provides visual display of early warning information to help management personnel quickly understand the current and future climate conditions.

8. The method of claim 1, wherein, The step S3 is specifically as follows: Template engine architecture: Introduce a template engine based on natural language processing, support dynamic variable placeholders, and automatically fill structured data through context semantic analysis; the logical layers of the template engine include a basic data layer, a logical assembly layer, and a semantic optimization layer; Data adaptation: Establish a mapping table between the water and power plant system measurement point codes and the production management system fields to solve the cross-system data naming difference problem; for missing time series measurement point data in the monitoring system, use linear interpolation algorithm or condition-based prediction algorithm for data completion; Version management: Support historical version archiving and quick rollback of log templates, record the operation log of each template modification; provide A / B testing function, run multiple template versions in parallel and compare the readability and accuracy of generated logs.

9. The method of claim 1, wherein, The automatic writing in step S4 uses a two-phase commit mechanism and a breakpoint resume technology to ensure the atomicity and reliability of log writing.

10. The method of claim 1, wherein, The step S5 is specifically as follows: Arrange the service request component, data processing component, and service response component in a visual drag-and-drop manner, allowing business personnel to view the full process of data service processing in real time; The completed service is exposed to the outside through a standardized interface, and only authorized senior application systems of the hydropower plant and third-party platforms are allowed to call it.

Images