Digital mapping system and method for hydropower station operation regulation and control

Abstract

The invention discloses a digital mapping system and method for hydropower station operation regulation and control. The system comprises a plurality of cascade hydropower stations, a centralized control station, voice terminals arranged at the cascade hydropower stations and the centralized control station, and a central monitoring system arranged at the centralized control station. The central monitoring system comprises a digital mapping model, a voice authority analysis system, a voice instruction correction system and a pre-operation early warning system; the digital mapping model is used for monitoring the state of the cascade hydropower station; the voice permission analysis system is used for judging whether the voice terminal has a centralized control permission and a cross-station control permission; and the voice instruction correction system corrects the voice instruction based on the electricity demand and the flood prevention demand. According to the invention, comprehensive real-time dynamic monitoring of the cascade hydropower station is realized through the digital mapping model, the pre-operation result of the control instruction is displayed and abnormal early warning is carried out, the authority of the voice instruction is dynamically analyzed, and the reliability and efficiency of regulation and control of the cascade hydropower station are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hydropower station control, and particularly to a digital mapping system and method for the operation regulation of hydropower stations. Background Art

[0002] A series of hydropower stations built through cascade development are called cascade hydropower stations. At present, there is a lack of effective monitoring means for basin cascade hydropower stations. Staff cannot visually and comprehensively monitor the power station data, and the pre-operation effects of the control instructions to be executed cannot be pre-displayed either. As a result, some incorrect instructions are found to be unreasonable only after execution, causing losses.

[0003] In addition, in the control mode of cascade hydropower stations, voice commands can be used for control. Staff issue control commands through the phone, and the voice acquisition card acquires the voice commands. After voice recognition, the specific control commands are parsed. However, the personnel on site at cascade hydropower stations are complex, and there are often multiple phone terminals and multiple staff members. The phenomenon of phone mixing often occurs, which cannot ensure the safety of power station control, and it is difficult to trace who specifically issued the voice command. In addition, the existing technology usually can only control the equipment of this power station through the phone terminal and cannot issue voice commands across stations. Although this can ensure safety, in actual use, in some special cases, cross-station control is often required to improve efficiency. Therefore, how to ensure the safety and efficiency of cross-station control is a technical problem that needs to be solved.

[0004] The applicant's prior patent application CN117154943A proposes a system and method for collecting the power generation capacity of cascade power plants in a centralized control center, including a host computer set in the centralized control center of the power plant, and a power plant-side power generation capacity declaration device, a power grid system power generation information receiving device, a cascade power plant generator set operation mode receiving device, an operator station, and a monitoring system that are respectively communicatively connected to the host computer. This invention patent application can summarize data such as the power generation capacity declaration status on the power plant side, power grid system power generation information, and cascade power plant generator set operation modes through the host computer, so as to ensure the accuracy of the data, and thus complete the declaration of the power generation capacity of cascade power plants automatically, efficiently, and accurately. However, this invention does not solve the above problems. Summary of the Invention

[0005] Object of the Invention: Aiming at the above problems, the present invention proposes a digital mapping system and method for the operation regulation of hydropower stations. Technical Solution

[0006] In a first aspect, the present invention provides a digital mapping system for the operation regulation of hydropower stations, including a number of cascade hydropower stations, a centralized control station, a number of voice terminals set in the cascade hydropower stations and the centralized control station, and a central monitoring system set in the centralized control station; Preferably, the central monitoring system of the centralized control station includes a digital mapping model, a voice permission analysis system, a voice command correction system, and a pre-operation warning system; The digital mapping model is used to monitor the status of cascade hydropower stations; The digital mapping model includes an equipment basic module, an operation data module, an alarm rule module, a business data module, a water regime data module, and a duty data module; The voice permission analysis system is used to obtain voice commands and speaker identity data based on a voice recognition model and a voiceprint recognition model; judge whether the voice terminal has centralized control permission and cross-station control permission; the voice command correction system is used to correct the voice command based on the target adjustment direction and target adjustment amount of the target control gate, based on power consumption requirements and flood control requirements. The pre-operation warning system is used to warn of abnormalities in cascade hydropower stations caused by pre-operation execution actions.

[0007] Preferably, the voice permission analysis system is used to analyze the voice content data through a voice recognition model, and identify the gate control command included in the voice command, and the gate control command includes the target control gate and the target control parameter; Query the station where the voice terminal is located based on the terminal identity data, and judge whether the voice terminal is a centralized control voice terminal or a power station voice terminal; If the voice terminal is a power station voice terminal, then judge whether the target control gate and the power station voice terminal belong to associated hydropower stations; Query whether the speaker's permission reaches the cross-station control level according to the speaker identity data.

[0008] Preferably, the voice permission analysis system further includes an association analysis module, which is used to judge whether the target control gate and the power station voice terminal belong to associated hydropower stations; Query the historical records of terminal transmission data and operation execution history of relevant hydropower stations; Obtain the recording time and voice control command content of each voice command of the speaker in the historical record of terminal transmission data within a preset time period, and judge whether there is a cross-station command; Query the operation execution history record, and judge whether there is an operation record consistent with the cross-station command within a preset time period after the recording time of the cross-station command. If so, set the cross-station command as a cross-station permission command; Judge the number of cross-station permission commands within a preset duration. If the threshold is reached, judge that the target control gate and the power station voice terminal belong to associated hydropower stations.

[0009] Preferably, the voice command correction system is used to obtain the target adjustment direction and target adjustment amount of the target control gate based on the current opening and closing state of the target control gate and the target control parameters; If the target adjustment direction is to decrease the opening degree, it is judged whether the power generation range of the downstream cascade hydropower station can meet the electricity demand; If the target adjustment direction is to increase the opening degree, it is judged whether the water level adjustment range of the downstream cascade hydropower station can meet the flood control demand; The voice command is corrected based on the flood control demand and the electricity demand.

[0010] Preferably, the digital mapping model receives the corrected voice command, performs dynamic virtual execution according to the corrected voice command, and displays the pre-operation execution actions; In the digital mapping model, the dynamic and steady-state effects of the gate opening degree and water level change are displayed according to the execution effects of the pre-operation execution actions; The pre-operation warning system judges whether the pre-operation execution actions cause abnormalities in the cascade hydropower station based on the intelligent learning algorithm. If so, it issues a warning and gives recommended handling measures based on the self-learning knowledge base.

[0011] In a second aspect, the present invention also provides a digital mapping method for the operation and regulation of a hydropower station, including the steps: S1. Build a digital mapping model at the centralized control station of the cascade hydropower station, and monitor the state of the cascade hydropower station through the digital mapping model; Among them, building a digital mapping model includes: building an equipment basic model, building an operation data model, building an alarm rule model, building a business data model, building a water regime data model, and building a duty data model; S2. Collect the terminal transmission data of the voice terminal, where the terminal transmission data includes terminal identity data and voice content data; obtain the voice command and the speaker identity data based on the voice recognition model and the voiceprint recognition model; judge whether the voice terminal has the voice control permission for the target control gate, including judging whether the voice terminal has the centralized control permission and the cross-station control permission; S3. Query the speaker permission list of the voice terminal based on the terminal identity data, and judge whether the speaker identity data is found in the speaker permission list. If so, enter S4, otherwise end; S4. Identify the content of the voice command, obtain the target adjustment direction and target adjustment amount of the target control gate, and correct the voice command based on the electricity demand and the flood control demand; S5. Display the pre - operation execution actions of the corrected voice commands in the digital mapping model, and determine whether the pre - operation execution actions cause abnormalities in the cascade hydropower station. If so, give an early warning; if not, confirm the execution of the voice command.

[0012] Preferably, the S2 includes: S21. Analyze the voice content data through the voice recognition model to identify the gate control commands included in the voice command. The gate control commands include the target control gate and the target control parameters. S22. Query the station where the voice terminal is located based on the terminal identity data, and determine whether the voice terminal is a centralized control voice terminal or a power station voice terminal. If it is a centralized control voice terminal, enter S3. S23. If the voice terminal is a power station voice terminal, determine whether the target control gate and the power station voice terminal belong to the associated hydropower station. If so, enter S3; otherwise, enter S24. S24. Analyze the voice content data through the voiceprint recognition model to obtain the speaker identity data. Query whether the speaker's permission reaches the cross - power - station control level according to the speaker identity data. If so, enter S3; otherwise, end.

[0013] Preferably, the determination in S23 of whether the target control gate and the power station voice terminal belong to the associated hydropower station includes: S231. Determine whether the target control gate and the power station voice terminal are of the same hydropower station. If so, determine that they belong to the associated hydropower station; if not, enter S232. S232. Analyze the voice content data through the voiceprint recognition model to obtain the speaker identity data. S233. Query the historical records of terminal transmission data and operation execution history of relevant hydropower stations. The relevant hydropower stations include the hydropower station where the target control gate is located and the hydropower station where the power station voice terminal is located. S234. Obtain the recording time and voice control command content of each voice command of the speaker in the historical record of terminal transmission data within the preset time period, and determine whether there is a cross - station command. If so, enter S235. S235. Query the operation execution history record, and determine whether there is an operation record consistent with the cross - station command within the preset time period after the recording time of the cross - station command. If so, set the cross - station command as a cross - station permission command and enter S236. S236. Determine the number of cross - station permission commands within the preset duration. If it reaches the threshold, determine that the target control gate and the power station voice terminal belong to the associated hydropower station.

[0014] Preferably, the S4 includes: S41. Identify the gate control instruction in the voice command, where the gate control instruction includes the target control gate and the target control parameter; S42. Based on the current opening / closing state of the target control gate and the target control parameter, obtain the target adjustment direction and the target adjustment amount Q of the target control gate, where the target adjustment direction includes decreasing the opening degree and increasing the opening degree; S43. If the target adjustment direction is to decrease the opening degree, then analyze the impact on the power generation range of the downstream cascade hydropower station adjacent to the target control gate according to the target adjustment amount Q, and determine whether the power generation range of the downstream cascade hydropower station can meet the electricity demand; S44. If the target adjustment direction is to increase the opening degree, then analyze the impact on the water level adjustment range of the downstream cascade hydropower station adjacent to the target control gate according to the target adjustment amount Q and the rainfall data, and determine whether the water level adjustment range of the downstream cascade hydropower station can meet the flood control demand; S45. Modify the voice command based on the flood control demand and the electricity demand; modify the target adjustment amount Q. First, ensure that the impact of the target adjustment amount Q must meet the flood control demand, and then meet the electricity demand.

[0015] Preferably, the S5 includes: S51. The digital mapping model receives the modified voice command, performs dynamic virtual execution according to the modified voice command, and displays the pre-operation execution actions; S52. In the digital mapping model, display the dynamic and steady-state effects of the gate opening / closing degree and the water level change according to the execution effects of the pre-operation execution actions; S53. Analyze the gap between the dynamic and steady-state effects and the control target. If it is within the allowable range, enter S54; S54. Based on the intelligent learning algorithm, determine whether the pre-operation execution actions cause abnormalities in the cascade hydropower station. If so, give an early warning and give recommended handling measures based on the self-learning knowledge base. Otherwise, enter S55; S55. Confirm that the pre-operation execution actions are qualified and allow the execution of the modified voice command.

[0016] The present invention has the following beneficial effects compared with the prior art: A digital mapping system for hydropower station operation regulation in the present invention sets up a voice permission analysis system in the central monitoring system, which improves the security of voice control. More importantly, it can determine whether the voice terminal has the voice control permission for the target control gate, including determining whether the voice terminal has the centralized control permission and the cross-station control permission; it can solve the problem of improving work efficiency through cross-station voice commands in special cases. In addition, in the present invention, a voice terminal is usually used by more than one person, so usually multiple people should have the usage permission of the voice terminal. However, in the existing hydropower station control room, there are often problems such as chaotic use and non-standard operation of multiple people and multiple voice terminals. The present invention sets up a speaker permission list for each voice terminal, and judges whether the person issuing the voice command has the usage permission of the voice terminal by identifying the identity data of the speaker, thus improving the security of cascade hydropower station control. In addition, the present invention can obtain the target adjustment direction and target adjustment amount of the target control gate based on the current opening and closing state of the target control gate and the target control parameters, and correct the target adjustment amount based on the power consumption demand and flood control demand, improving the security of voice control. In addition, the present invention can perform all-round dynamic real-time monitoring on the cascade hydropower station through the digital mapping model, and can also perform pre-operation virtual display on the voice command, and can judge whether the pre-operation execution action causes abnormalities in the cascade hydropower station based on the intelligent learning algorithm, improving the reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 FIG. is a schematic structural diagram of a digital mapping system for hydropower station operation regulation provided by an embodiment of the present invention; Figure 2 FIG. is a flowchart of a digital mapping method for hydropower station operation regulation provided by an embodiment of the present invention; Figure 3 FIG. is a flowchart of a method for judging associated hydropower stations provided by an embodiment of the present invention; Figure 4 FIG. is a flowchart of a method for correcting voice commands based on power consumption demand and flood control demand provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] Obviously, many modifications and variations made by those skilled in the art based on the purpose of the present invention fall within the protection scope of the present invention.

[0019] Those skilled in the art can understand that, unless specifically stated otherwise, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present invention means the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups. It should be understood that when an element or component is referred to as being "connected" to another element or component, it can be directly connected to other elements or components, or there may also be intermediate elements or components. The phrase "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0020] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention. Embodiment 1

[0021] The embodiment of the present invention provides a digital mapping system for the operation regulation of a hydropower station. Specifically, please refer to Figure 1 , Figure 1 which is a schematic structural diagram of a digital mapping system for the operation regulation of a hydropower station provided by the embodiment of the present invention. The system includes a number of cascade hydropower stations, a centralized control station, a number of voice terminals provided at the cascade hydropower stations and the centralized control station, and a central monitoring system provided at the centralized control station; Preferably, the central monitoring system of the centralized control station includes a digital mapping model, a voice permission analysis system, a voice command correction system, and a pre-operation warning system; The digital mapping model is used to monitor the status of the cascade hydropower stations; The digital mapping model includes an equipment basic module, an operation data module, an alarm rule module, a business data module, a water regime data module, and a duty data module; The voice permission analysis system is used to obtain voice commands and speaker identity data based on a voice recognition model and a voiceprint recognition model; and judge whether the voice terminal has centralized control permission and cross-station control permission; the voice command correction system is used to correct the voice command based on the target adjustment direction and target adjustment amount of the target control gate, based on the electricity demand and flood control demand; The pre-operation warning system is used to warn of abnormalities in the cascade hydropower stations caused by pre-operation execution actions.

[0022] Preferably, the voice permission analysis system is used to analyze the voice content data through a voice recognition model to identify the gate control instructions included in the voice commands, where the gate control instructions include the target control gate and the target control parameters; Query the site where the voice terminal is located based on the terminal identity data, and determine whether the voice terminal is a centralized control voice terminal or a power station voice terminal; If the voice terminal is a power station voice terminal, determine whether the target control gate and the power station voice terminal belong to the associated hydropower station; Query whether the speaker's permission reaches the cross-station control level according to the speaker identity data.

[0023] Preferably, the voice permission analysis system further includes an association analysis module for determining whether the target control gate and the power station voice terminal belong to the associated hydropower station; Query the historical records of terminal transmission data and operation execution history of relevant hydropower stations; Obtain the recording time and voice control instruction content of each voice command of the speaker in the historical record of the terminal transmission data within a preset period, and determine whether there is a cross-station command; Query the operation execution history record, and determine whether there is an operation record consistent with the cross-station command within a preset period after the recording time of the cross-station command. If so, set the cross-station command as a cross-station permission command; Judge the number of cross-station permission commands within a preset duration. If the threshold is reached, determine that the target control gate and the power station voice terminal belong to the associated hydropower station.

[0024] Preferably, the voice command correction system is used to obtain the target adjustment direction and target adjustment amount of the target control gate based on the current opening and closing state of the target control gate and the target control parameters; If the target adjustment direction is to reduce the opening, determine whether the power generation range of the downstream cascade hydropower station can meet the power consumption demand; If the target adjustment direction is to increase the opening, determine whether the water level adjustment range of the downstream cascade hydropower station can meet the flood control demand; Correct the voice command based on the flood control demand and power consumption demand.

[0025] Preferably, the digital mapping model receives the corrected voice command and performs dynamic virtual execution according to the corrected voice command to display the pre-operation execution action; In the digital mapping model, display the dynamic and steady-state effects of the gate opening degree and water level change according to the execution effect of the pre-operation execution action; The pre-operation warning system determines whether the pre-operation execution action causes abnormalities in the cascade hydropower station based on an intelligent learning algorithm. If so, it issues a warning and provides recommended handling measures based on the self-learning knowledge base. Embodiment 2

[0026] The embodiment of the present invention also provides a digital mapping method for the operation regulation of a hydropower station. For details, please refer to Figure 2 , Figure 2 is a flowchart of a digital mapping method for the operation regulation of a hydropower station provided by the embodiment of the present invention. The method includes the steps: S1. Build a digital mapping model in the centralized control station of the cascade hydropower station, and monitor the state of the cascade hydropower station through the digital mapping model; Among them, building a digital mapping model includes: building an equipment basic model, building an operation data model, building an alarm rule model, building a business data model, building a water regime data model, and building a duty data model; The present invention uses digital mapping technology to build a digital virtual monitoring model for cascade hydropower stations, which can realize the full perception of the production data and production scenarios of cascade hydropower stations, intelligent identification of business models in the management process and production process, such as various work processes of dispatching duty, fault handling processes, defect elimination processes, and work reporting processes, real-time matching and intervention with the business, as well as intelligent construction and intelligent update of the knowledge base, realizing intelligent auxiliary monitoring, intelligent operation guardianship, intelligent auxiliary decision-making and guidance functions for non-intrusive intervention in the hydropower dispatching control production process, assisting staff to carry out various dispatching work, improving the management level of basin hydropower dispatching operation, and providing technical support for the construction of intelligent cascade regulation.

[0027] Among them, building a digital mapping model includes: building an equipment basic model, building an operation data model, building an alarm rule model, building a business data model, building a water regime data model, and building a duty data model.

[0028] Equipment basic model construction: Establish the ownership association relationships for the units, main transformers, switches, disconnectors, and busbars of each power station under its jurisdiction, and uniformly manage all equipment basic models online according to the power station dimension, including the manufacturer, equipment model, factory date, commissioning date, asset unit, and dispatching agency. Data is added, maintained, collected and imported, and connected to third-party systems.

[0029] Operation data modeling and construction: Uniformly configure and manage the information of equipment monitoring point numbers, and construct a structured model of the association relationship of "power station - equipment - point table", including power station name, equipment name, point number, and signal description. The operation data includes telemetry signals and telemetry signals. The data needs to be connected to the monitoring system in Zone 2 or obtained from the mirror library in Zone 3, or can also be connected from a third party such as a big data platform. Provide data support for real-time equipment monitoring, signal identification, and signal warning.

[0030] Alarm rule modeling and construction: Comprehensively analyze and classify a large number of messy alarm information. At the same time, in each label rule model, corresponding rule configurations and customizations are designed to improve and optimize the label rule model library. The system has set various alarm signal judgment rules and label management rules such as associated, overdue and not restored, suppressed, frequent, blocked, instantaneous, telemetry unchanged, and telemetry mutation. Signal identification uses the set rules to realize real-time monitoring, parsing, and analysis of a large number of alarm light signals of cascade power plants in the basin, filter out invalid alarm information, and push effective alarm information and related disposal strategies; at the same time, link the fault / accident intelligent diagnosis model to comprehensively judge whether the alarm signal is a fault / accident, and assist the duty personnel in accurate monitoring and alarm disposal.

[0031] Business data model construction: Connect to various work processes of dispatching duty, fault handling process, defect elimination process, and work report process. The data determines the data source according to the actual situation on site, which is generated by this system or collected and connected from the internal production system of Qingjiang. Uniformly manage the to-do work processes of each production system in the virtual control room, and timely and effectively remind to process the to-do work.

[0032] Water regime data model construction: The connected data includes upstream and downstream water levels, inflow and outflow discharges, and gate openings. The system monitors the water regime picture in real time. When the water regime is abnormal or may be abnormal, it issues a warning in time. The system automatically collects the power generation plan of the power station, the gate passing flow rate, and the water consumption rate according to the existing reservoir water level calculation algorithm program in real time, intelligently analyzes the runoff in the interval, queries the water level - storage capacity curve according to the difference between the inflow and outflow discharges, calculates the change trend of the reservoir water level in the next few days and visualizes it, analyzes the calculation results, and warns of the exceeded data.

[0033] Construction of duty data model: Establish shift handover. On the one hand, it realizes the automatic handover of the system according to the set permissions at the specified time, and on the other hand, it realizes the directional push of the on-duty tasks. The system gives regular reminders for the regular work of the current shift. After the reminder, the on-duty personnel must confirm completion. Otherwise, this reminder will always exist and the reason for non-completion needs to be filled in. For the text messages sent during the flood season, it provides the function of manually turning on and off the reminder program. During the period when the reminder program is turned on, work reminders are given regularly every day. Detect the status of the maintenance application forms and work tickets of the power station. When there is a status change and the on-duty personnel need to handle it, a reminder is sent in time until the maintenance application form is turned to the closed state. Give a reminder for modifying the power generation plan of the power station, and compare the power generation plans before and after the modification, list the modification points, the change in daily average output, and the change in daily planned power consumption, and form a structured text. The structured text can be imported into the duty log with one key.

[0034] S2. Collect the terminal transmission data of the voice terminal. The terminal transmission data includes terminal identity data and voice content data; obtain the voice command and the speaker identity data based on the voice recognition model and the voiceprint recognition model; S21. Analyze the voice content data through the voice recognition model to identify the gate control command included in the voice command. The gate control command includes the target control gate and the target control parameter; S22. Query the site where the voice terminal is located based on the terminal identity data, and judge whether the voice terminal is a centralized control voice terminal or a power station voice terminal; if it is a centralized control voice terminal, then enter S3; S23. If the voice terminal is a power station voice terminal, then judge whether the target control gate and the power station voice terminal belong to the associated hydropower station; if so, enter S3, otherwise enter S24; S24. Analyze the voice content data through the voiceprint recognition model to obtain the speaker identity data; query whether the speaker's permission reaches the cross-station control level according to the speaker identity data. If so, enter S3, otherwise end; It can be understood that generally, it is usually not allowed to transmit commands across power stations. However, in special situations such as the critical moment of severe water conditions, when the expert guidance personnel of other stations issue commands, it is usually necessary to command cascade hydropower stations across stations, which can greatly improve the execution efficiency.

[0035] Among them, the method for judging whether the target control gate and the power station voice terminal belong to the associated hydropower station is specifically referred to Figure 3 , Figure 3 is the flowchart of a method for judging associated hydropower stations provided by an embodiment of the present invention, including: S231. Judge whether the target control gate and the power station voice terminal are the same hydropower station. If so, judge that they belong to the associated hydropower station. If not, enter S232; S232. Analyze the voice content data through the voiceprint recognition model to obtain the speaker identity data; S233. Query the historical records of terminal transmission data and operation execution history of the associated hydropower stations; the associated hydropower stations include the hydropower station where the target control gate is located and the hydropower station where the station voice terminal is located; S234. Obtain the recording time and voice control instruction content of each voice instruction of the speaker in the historical record of the terminal transmission data within a preset time period, and determine whether there is a cross-station instruction. If so, proceed to S235; S235. Query the operation execution history record, and determine whether there is an operation record consistent with the cross-station instruction within a preset time period after the recording time of the cross-station instruction. If so, set the cross-station instruction as a cross-station permission instruction and proceed to S236; S236. Judge the number of cross-station permission instructions within a preset duration. If the threshold is reached, judge that the target control gate and the station voice terminal belong to the associated hydropower stations; In addition, since most current cascade hydropower stations are developing towards unmanned and intelligent, which greatly saves labor costs, multiple cascade hydropower stations belonging to the same group in the neighborhood can adopt the same staff for duty and maintenance. In this case, if the staff can issue control instructions through the voice terminal, the work efficiency can be improved on the premise of ensuring permission security.

[0036] S3. Query the speaker permission list of the voice terminal based on the terminal identity data, and determine whether the speaker identity data is found in the speaker permission list. If so, proceed to S4, otherwise end; In the present invention, a voice terminal is usually used by more than one person. Therefore, usually, multiple people should have the usage permission of the voice terminal. However, there are often problems of chaotic use and non-standard operation of multiple people and multiple voice terminals in the existing hydropower station control rooms. The present invention sets a speaker permission list for each voice terminal, and judges whether the person issuing the voice instruction has the usage permission of the voice terminal by identifying the speaker identity data, thereby improving the safety of cascade hydropower station control.

[0037] S4. Identify the voice instruction content to obtain the target adjustment direction and target adjustment amount of the target control gate, and correct the voice instruction based on the electricity consumption demand and flood control demand; For the specific method of voice instruction correction, please refer to Figure 4 , Figure 4 which is a flowchart of a method for correcting voice instructions based on electricity consumption demand and flood control demand provided by an embodiment of the present invention, including: S41. Identify the gate control instruction in the voice command. The gate control instruction includes the target control gate and the target control parameter; S42. Based on the current opening / closing state of the target control gate and the target control parameter, obtain the target adjustment direction and the target adjustment amount Q of the target control gate. The target adjustment direction includes reducing the opening degree and increasing the opening degree; S43. If the target adjustment direction is to reduce the opening degree, analyze the impact on the power generation range of the downstream cascade hydropower station adjacent to the target control gate according to the target adjustment amount Q, and determine whether the power generation range of the downstream cascade hydropower station can meet the power consumption demand; Among them, based on the target adjustment amount Q, the water level impact amount M on the adjacent downstream cascade hydropower station can be calculated, and further the maximum power generation reduction value ΔE of the downstream cascade hydropower station can be calculated; based on the current water level state and current unit state of the downstream cascade hydropower station, the adjustable power generation range of the downstream cascade hydropower station can be calculated; therefore, combining the maximum power generation reduction value ΔE can obtain the impact of the target adjustment amount Q on the power generation range of the downstream cascade hydropower station adjacent to the target control gate. Further, by comparing with the power generation demand curve, it can be determined whether the power consumption demand can be met.

[0038] S44. If the target adjustment direction is to increase the opening degree, analyze the impact on the water level adjustment range of the downstream cascade hydropower station adjacent to the target control gate according to the target adjustment amount Q and the rainfall data, and determine whether the water level adjustment range of the downstream cascade hydropower station can meet the flood control demand; S45. Modify the voice command based on the flood control demand and the power consumption demand; modify the target adjustment amount Q. First, it is necessary to ensure that the impact of the target adjustment amount Q must meet the flood control demand, and secondly, it is to meet the power consumption demand.

[0039] S5. Display the pre-operation execution action of the modified voice command in the digital mapping model, and determine whether the pre-operation execution action causes an abnormality in the cascade hydropower station. If so, give an early warning; if not, confirm the execution of the voice command; S51. The digital mapping model receives the modified voice command and performs dynamic virtual execution according to the modified voice command to display the pre-operation execution action; S52. In the digital mapping model, display the dynamic and steady-state effects of the gate opening / closing degree and water level change according to the execution effect of the pre-operation execution action; S53. Analyze the gap between the dynamic and steady-state effects and the control target. If it is within the allowable range, enter S54; S54. Determine whether the pre-operation execution action causes an abnormality in the cascade hydropower station based on an intelligent learning algorithm. If so, give an early warning and provide recommended handling measures based on the self-learning knowledge base. Otherwise, proceed to S55; S55. Confirm that the pre-operation execution action is qualified and allow the execution of the corrected voice command.

[0040] The present invention comprehensively monitors cascade hydropower stations based on a digital mapping model established in a centralized control station. After correcting the voice command, first perform the pre-operation display of the voice command in the digital mapping model, and pre-show the execution consequences of the voice command to the staff. The staff can comprehensively and intuitively observe the command execution effect, which is more conducive to the operator making a correct judgment. Moreover, the present invention can predict the situation in the future for a period of time, discover abnormal situations in advance, and greatly improve safety. For example, Real-time monitor the opening degree of the gate, water level, etc. through the digital mapping model, and display the gate and water level conditions of each cascade hydropower station after the pre-operation. Combine multiple factors such as weather and surrounding environment for comprehensive analysis and calculation, and give an early warning in time when the water situation is abnormal or may be abnormal.

[0041] In addition, for the pre-operation execution actions that may cause abnormalities in the cascade hydropower station, the present invention will provide recommended handling measures based on the self-learning knowledge base.

[0042] The present invention builds a knowledge base in the field of cascade hydropower regulation based on knowledge graph construction technology. For the multi-source heterogeneous data in the field of cascade hydropower regulation, use deep learning algorithms to automatically extract regulation knowledge, form a complete hydropower regulation knowledge base, and enable the knowledge base to have the ability of self-update and expansion based on domain knowledge. The technical route for building the hydropower regulation knowledge base mainly includes steps such as corpus construction, ontology construction, knowledge extraction, knowledge storage, and knowledge fusion. First, build a standard corpus in the scheduling field for the text data in the field of cascade hydropower regulation to provide standard corpus for subsequent links. At the same time, sort out the knowledge structure in the field of hydropower regulation and design the conceptual ontology structure of hydropower regulation knowledge while building the corpus; secondly, based on the standard corpus and the conceptual ontology structure, extract the text corpus and structured data, and explore and fuse similar knowledge entities; finally, persistently store the fused knowledge data based on the graph database to form a hydropower regulation knowledge graph.

[0043] In the field of hydropower, there is a rich amount of text data, but the file formats are diverse and there is no unified standard. By constructing a cascade hydropower corpus to uniformly integrate hydropower texts, it provides high-quality corpus data for subsequent hydropower text processing. At the same time, during the process of constructing the hydropower corpus, a hydropower field dictionary can be accumulated, which can provide a true and effective data basis for subsequent tasks. The processing methods for standard text corpora include: Firstly, for corpus data at the text level, the corpus data can be fragmented through regular matching. For example, the text in the pre-plan can be segmented into fault description text, fault impact text, fault handling text, equipment operation status description text, etc. based on regular extraction technology. Secondly, for standard corpora at the paragraph level and sentence level, hydropower field words can be obtained through word segmentation technology and machine learning methods, and a hydropower field dictionary can be formed. Finally, hydropower field word vectors can be obtained through word embedding technology.

[0044] This invention studies a word embedding technology based on the Elmo neural network. The word vectors obtained by the model are calculated based on a two-layer bidirectional language model (BiLSTM). Elmo adopts a typical two-stage process. In the first stage, a pre-trained language model is used for training. In the second stage, when performing specific downstream tasks, the wordEmbedding of the corresponding word is extracted from the pre-trained network and used as a feature to supplement the downstream task. Specifically, in the first stage - pre-training: for the two-layer bidirectional LSTM, static wordEmbedding is used for the context, and the original word vectors are transformed using character-level CNN. Each layer of LSTM concatenates the context vectors as the current vector and is trained using a large amount of corpus. The first layer can learn syntactic features, and the second layer can learn semantic features. The training task at this stage is still the language model, that is, predicting words based on the context. In the second stage - Fine-tuning task: a new sentence is used as the input to the Elmo pre-trained network. In this way, the sentence can obtain three embeddings in the Elmo network. The three embeddings can be weighted as the wordembedding, and this is used as the input for the downstream task.

[0045] Knowledge entity extraction technology: In view of the characteristics of hydropower corpus, the present invention finds that using the Elmo model as the pre-training model can enhance the representation ability of text features. The BiLSTM has strong sequence modeling ability, can capture distant context information, and has the ability of neural network to fit non-linearity. The CRF calculates a joint probability and optimizes the entire sequence rather than splicing the optimal at each moment. Therefore, the CRF is superior to the LSTM. Each of the three models has its own unique advantages. In order to integrate the advantages of these three models in cascade hydropower entity recognition, the BiLSTM-CRF model is adopted. Add a pre-training layer of Elmo to the input layer of the BiLSTM network to convert the text into semantic vectors, which can effectively enhance the representation ability of the text. And add a CRF linear layer after the output layer of the BiLSTM network, which effectively solves the problem of gradient disappearance or gradient explosion existing in the traditional recurrent neural network.

[0046] The various embodiments in this specification are described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the various embodiments, reference can be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method part.

[0047] Those skilled in the art can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in the form of hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0048] Finally, it should also be noted that in this article, relationships such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

Claims

1. A digital mapping system for operation and control of a hydropower station, comprising a plurality of cascade hydropower stations, a centralized control station, a plurality of voice terminals arranged in the cascade hydropower stations and the centralized control station, and a central monitoring system arranged in the centralized control station; characterized in that: The central monitoring system of the centralized control station includes a digital mapping model, a voice authority analysis system, a voice command correction system, and a pre-operation warning system; The digital mapping model is used to monitor the status of the cascade hydropower station; the digital mapping model includes an equipment basic module, an operation data module, an alarm rule module, a business data module, a water condition data module, and a duty data module; The voice authority analysis system is used to obtain voice instructions and speaker identity data based on the voice recognition model and voiceprint recognition model; determine whether the voice terminal has centralized control authority and cross-station control authority; the voice instruction correction system is used to correct the voice instructions based on the target adjustment direction and target adjustment amount of the target control gate, based on electricity demand and flood control needs; the pre-operation warning system is used to warn of abnormalities in cascade hydropower stations caused by pre-operation execution actions.

2. The digital mapping system for operation and control of a hydropower station according to claim 1 is characterized in that: The voice authority analysis system is used to analyze the voice content data through a voice recognition model to identify the gate control instruction contained in the voice instruction, wherein the gate control instruction includes a target control gate and a target control parameter; Based on the terminal identity data, the site where the voice terminal is located is queried to determine whether the voice terminal is a centralized control voice terminal or a power station voice terminal; if the voice terminal is a power station voice terminal, it is determined whether the target control gate and the power station voice terminal belong to an associated hydropower station; based on the speaker identity data, it is queried whether the speaker's authority reaches the cross-power station control level.

3. The digital mapping system for operation and control of a hydropower station according to claim 2 is characterized in that: The voice authority analysis system also includes an association analysis module, which is used to determine whether the target control gate and the power station voice terminal belong to an associated hydropower station; query the terminal transmission data history record and operation execution history record of the relevant hydropower station; obtain the recording time and voice control instruction content of each voice instruction of the speaker in the terminal transmission data history record within a preset time period, and determine whether there is a cross-station instruction; query the operation execution history record to determine whether an operation record consistent with the cross-station instruction is contained within a preset time period after the recording time of the cross-station instruction, and if so, set the cross-station instruction as a cross-station permission instruction; determine the number of the cross-station permission instructions within a preset time length, and if the threshold is reached, determine that the target control gate and the power station voice terminal belong to an associated hydropower station.

4. The digital mapping system for operation and control of a hydropower station according to claim 3 is characterized in that: The voice command correction system is used to obtain a target adjustment direction and a target adjustment amount of the target control gate based on the current opening and closing state of the target control gate and the target control parameter; If the target adjustment direction is to reduce the opening, then determine whether the power generation range of the downstream cascade hydropower station can meet the electricity demand; if the target adjustment direction is to increase the opening, then determine whether the water level adjustment range of the downstream cascade hydropower station can meet the flood control demand; the voice command is modified based on the flood control demand and the electricity demand.

5. The digital mapping system for operation and control of a hydropower station according to claim 4 is characterized in that: The digital mapping model receives the modified voice command, performs dynamic virtual execution according to the modified voice command, and displays the pre-operation execution action; in the digital mapping model, the dynamic effect and steady-state effect of the gate opening and closing degree and water level change are displayed according to the execution effect of the pre-operation execution action; The pre-operation warning system determines whether the pre-operation execution action causes abnormality in the cascade hydropower station based on an intelligent learning algorithm. If so, a warning is issued and suggested treatment measures are given based on a self-learning knowledge base.

6. A digital mapping method for operation and control of a hydropower station, applied to the digital mapping system for operation and control of a hydropower station as claimed in any one of claims 1 to 5, characterized in that: The method includes: S1. Constructing a digital mapping model at a centralized control station of a cascade hydropower station, and monitoring the status of the cascade hydropower station through the digital mapping model; S2. Collecting terminal transmission data of the voice terminal, wherein the terminal transmission data includes terminal identity data and voice content data; acquiring voice instructions and speaker identity data based on a voice recognition model and a voiceprint recognition model; determining whether the voice terminal has voice control authority for a target control gate, including determining whether the voice terminal has centralized control authority and cross-site control authority; S3, querying the speaker authority list of the voice terminal based on the terminal identity data, and determining whether the speaker identity data is found in the speaker authority list, if so, proceeding to S4, otherwise ending; S4, identifying the content of the voice command, obtaining the target adjustment direction and target adjustment amount of the target control gate, and modifying the voice command based on the power demand and flood control demand; S5. Display the pre-operation execution action of the corrected voice command in the digital mapping model, and determine whether the pre-operation execution action causes an abnormality in the cascade hydropower station. If so, issue an early warning; if not, confirm the execution of the voice command.

7. The digital mapping method for operation and control of a hydropower station according to claim 6 is characterized in that: The S2 includes: S21, analyzing the voice content data through a voice recognition model to identify a gate control instruction contained in the voice instruction, wherein the gate control instruction includes a target control gate and a target control parameter; S22, querying the site where the voice terminal is located based on the terminal identity data, and determining whether the voice terminal is a centralized control voice terminal or a power station voice terminal; if it is a centralized control voice terminal, proceeding to S3; S23, if the voice terminal is a power station voice terminal, determine whether the target control gate and the power station voice terminal belong to an associated hydropower station; if so, proceed to S3, otherwise proceed to S24; S24. Analyze the voice content data through the voiceprint recognition model to obtain the speaker identity data; query whether the speaker authority reaches the cross-station control level according to the speaker identity data, if so, enter S3, otherwise end.

8. The digital mapping method for operation and control of a hydropower station according to claim 7 is characterized in that: The step S23 of determining whether the target control gate and the power station voice terminal belong to an associated hydropower station includes: S231, determining whether the target control gate and the power station voice terminal are the same hydropower station, if so, determining that they are associated hydropower stations, if not, proceeding to S232; S232, analyzing the voice content data through a voiceprint recognition model to obtain speaker identity data; S233, querying the terminal transmission data history record and operation execution history record of the relevant hydropower station; the relevant hydropower station includes the hydropower station where the target control gate is located, and the hydropower station where the power station voice terminal is located; S234, obtaining the recording time and voice control instruction content of each voice instruction of the speaker in the terminal transmission data history record within a preset period of time, and determining whether there is a cross-site instruction, if so, proceeding to S235; S235, querying the operation execution history record, determining whether an operation record consistent with the cross-site instruction is included within a preset time period after the recording time of the cross-site instruction, and if so, setting the cross-site instruction as a cross-site permission instruction, and proceeding to S236; S236: Determine the number of the cross-station permission instructions within a preset time period, and if a threshold is reached, determine that the target control gate and the power station voice terminal belong to an associated hydropower station.

9. The digital mapping method for operation and control of a hydropower station according to claim 8, characterized in that: The S4 includes: S41, identifying a gate control instruction in a voice instruction, wherein the gate control instruction includes a target control gate and a target control parameter; S42, based on the current opening and closing state of the target control gate and the target control parameter, obtaining the target adjustment direction and the target adjustment amount Q of the target control gate, wherein the target adjustment direction includes reducing the opening and increasing the opening; S43, if the target adjustment direction is to reduce the opening, then analyzing the impact on the power generation range of the downstream cascade hydropower station adjacent to the target control gate according to the target adjustment amount Q, and judging whether the power generation range of the downstream cascade hydropower station can meet the electricity demand; S44, if the target adjustment direction is to increase the opening, then analyze the impact on the water level adjustment range of the downstream cascade hydropower station adjacent to the target control gate according to the target adjustment amount Q and rainfall data, and judge whether the water level adjustment range of the downstream cascade hydropower station can meet the flood control needs; S45. The voice command is modified based on the flood control demand and the electricity demand. The target adjustment amount Q is modified to first ensure that the impact of the target adjustment amount Q must meet the flood control demand, and then meet the electricity demand.

10. The digital mapping method for operation and control of a hydropower station according to claim 9, characterized in that: The S5 includes: S51, the digital mapping model receives the modified voice command, performs dynamic virtual execution according to the modified voice command, and displays the pre-operation execution action; S52, displaying the dynamic effect and steady-state effect of gate opening and closing degree and water level change in the digital mapping model according to the execution effect of the pre-operation execution action; S53, analyzing the difference between the dynamic effect and the steady-state effect and the control target, and if they are within the allowable range, proceeding to S54; S54, judging whether the pre-operation execution action causes abnormality of the cascade hydropower station based on the intelligent learning algorithm, and if so, issuing an early warning and giving a suggested treatment measure based on the self-learning knowledge base, otherwise proceeding to S55; S55: confirm that the pre-operation execution action is qualified, and allow the modified voice instruction to be executed.

Images