Hydropower unit operation control optimization method and system based on holographic perception

Abstract

The present application provides a method and system for optimizing the operation control of a hydropower unit based on holographic perception, which relates to the field of operation control technology. The method includes: determining information on multiple key parts of a unit; formulating a sensor layout plan, matching the key parts information of multiple units with the sensor network; building a sensor data cloud platform; extracting a first real-time holographic perception operation data set; building a three-dimensional digital model, performing simulation operation, and generating a simulated operation data set; optimizing the sensor network, updating the sensor layout plan, screening N sensors, and determining M sensors; extracting a second real-time holographic perception operation data set, and optimizing the operation control according to the comparison results. This application can solve the technical problems in the prior art caused by inaccurate control and optimization of the operation status of a hydropower unit, achieve the technical goal of comprehensive monitoring of a hydropower unit, and achieve the technical effect of accurate control and optimization of the operation status of a hydropower unit.

Description

Technical Field

[0001] The present application relates to the field of operation control technology, and in particular to a method and system for optimizing operation control of a hydropower unit based on holographic perception. Background Art

[0002] The hydropower unit is the core part of the hydropower system's power generation system. In order to ensure the stable operation of the hydropower unit, condition monitoring is required.

[0003] At present, the existing control system can only obtain part of the operating data of the unit, and cannot fully reflect the actual status of the unit, making it difficult to achieve accurate control and optimization. Therefore, a method is needed to solve the above problem.

[0004] In summary, there are technical problems in the prior art that, due to the poor layout matching between the hydropower unit and the sensor, the sensor's monitoring of the hydropower unit's operating data is relatively one-sided, making it difficult to fully reflect the actual status of the hydropower unit, further affecting the control and optimization of the hydropower unit's operating status. Summary of the invention

[0005] The purpose of this application is to provide a method and system for optimizing the operation control of a hydropower unit based on holographic perception, so as to solve the technical problem in the prior art that, due to the poor layout matching between the hydropower unit and the sensor, the sensor's monitoring of the operation data of the hydropower unit is relatively one-sided, making it difficult to fully reflect the actual status of the hydropower unit, further affecting the control and optimization of the operation status of the hydropower unit.

[0006] In view of the above problems, the present application provides a method and system for optimizing the operation control of a hydropower unit based on holographic perception.

[0007] In the first aspect, the present application provides a method for optimizing the operation control of a hydropower unit based on holographic perception, and the method is implemented by a hydropower unit operation control optimization system based on holographic perception, wherein the method includes: performing key identification based on the unit structure of the target hydropower unit, and determining multiple key parts information of the unit; formulating a sensor layout plan, wherein the sensor layout plan is to construct a sensor network according to the sensor type, and match the multiple key parts information of the unit with the sensor network; executing the sensor layout plan to deploy N sensors and construct a sensor data cloud platform, where N is a positive integer greater than 1; extracting the first real-time holographic perception operation data set of the target hydropower unit in combination with the sensor data cloud platform; and constructing a sensor layout plan for the target hydropower unit. a three-dimensional digital model of the unit, synchronizing the first real-time holographic perception operation data set to the three-dimensional digital model for simulation operation to generate a simulated operation data set; optimizing the sensor network according to the simulated operation data set, updating the sensor layout plan according to the sensor optimization network, screening the N sensors according to the sensor layout optimization plan, and determining M sensors, where M is a positive integer greater than or equal to 0; extracting a second real-time holographic perception operation data set of the target hydropower unit through the sensor data cloud platform based on the M sensors, comparing the second real-time holographic perception operation data set with the first real-time holographic perception operation data set, and performing intelligent optimization of the operation control of the target hydropower unit according to the comparison result.

[0008] In the second aspect, the present application also provides a hydropower unit operation control optimization system based on holographic perception, which is used to execute the hydropower unit operation control optimization method based on holographic perception as described in the first aspect, wherein the system includes: a unit key part information determination module, the unit key part information determination module is used to perform key identification based on the unit structure of the target hydropower unit, and determine multiple unit key part information; a sensor layout plan formulation module, the sensor layout plan formulation module is used to formulate a sensor layout plan, the sensor layout plan is to build a sensor network according to the sensor type, and match the multiple unit key part information with the sensor network; a sensor data cloud platform construction module, the sensor data cloud platform construction module is used to execute the sensor layout plan to deploy N sensors and build a sensor data cloud platform, N is a positive integer greater than 1; a first real-time holographic perception operation data set extraction module, the first real-time holographic perception operation data set extraction module is used to combine the sensor data cloud platform A first real-time holographic perception operation data set of the target hydropower unit is extracted; a simulation operation data set generation module, the simulation operation data set generation module is used to build a three-dimensional digital model of the target hydropower unit, synchronize the first real-time holographic perception operation data set to the three-dimensional digital model for simulation operation, and generate a simulation operation data set; M sensor determination modules, the M sensor determination modules are used to optimize the sensor network according to the simulation operation data set, update the sensor layout plan according to the sensor optimization network, screen the N sensors according to the sensor layout optimization plan, and determine M sensors, M is a positive integer greater than or equal to 0; an intelligent optimization module, the intelligent optimization module is used to extract a second real-time holographic perception operation data set of the target hydropower unit through the sensor data cloud platform based on the M sensors, compare the second real-time holographic perception operation data set with the first real-time holographic perception operation data set, and perform intelligent optimization of operation control of the target hydropower unit according to the comparison result.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By making key identification based on the unit structure of the target hydropower unit, the key part information of multiple units is determined; a sensor layout plan is formulated, and the sensor layout plan is to build a sensor network according to the sensor type, and match the key part information of the multiple units with the sensor network; the sensor layout plan is executed to deploy N sensors, and a sensor data cloud platform is constructed, where N is a positive integer greater than 1; the first real-time holographic perception operation data set of the target hydropower unit is extracted in combination with the sensor data cloud platform; a three-dimensional digital model of the target hydropower unit is constructed, and the first real-time holographic perception operation data set is synchronized to the three-dimensional digital model for simulation operation to generate a simulated operation data set; the sensor network is optimized according to the simulated operation data set, and the sensor network is optimized according to the sensor data set. The sensor optimization network updates the sensor layout plan, screens the N sensors according to the sensor layout optimization plan, determines M sensors, where M is a positive integer greater than or equal to 0; based on the M sensors, extracts a second real-time holographic perception operation data set of the target hydropower unit through the sensor data cloud platform, compares the second real-time holographic perception operation data set with the first real-time holographic perception operation data set, and intelligently optimizes the operation control of the target hydropower unit according to the comparison result. That is to say, through holographic perception technology, all-round monitoring and data collection of the unit's operating status can be achieved, providing more comprehensive and accurate information for the control system, and combining advanced data processing algorithms and control strategies to accurately control and optimize the unit to improve operating efficiency.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a flow chart of the hydropower unit operation control optimization method based on holographic perception in this application;

[0014] Figure 2This is a structural diagram of the hydropower unit operation control optimization system based on holographic perception in this application.

[0015] Description of reference numerals:

[0016] The module includes: a module for determining the key parts information of the unit 11; a module for formulating the sensor layout plan 12; a module for constructing a sensor data cloud platform 13; a module for extracting the first real-time holographic perception operation data set 14; a module for generating a simulation operation data set 15; a module for determining M sensors 16; and an intelligent optimization module 17. DETAILED DESCRIPTION

[0017] This application provides a method and system for optimizing the operation control of a hydropower unit based on holographic perception, which solves the technical problem in the prior art that the poor layout matching between the hydropower unit and the sensor leads to a one-sided monitoring of the operation data of the hydropower unit by the sensor, making it difficult to fully reflect the actual state of the hydropower unit, further affecting the control and optimization of the operation state of the hydropower unit. The technical goal of comprehensive monitoring of the hydropower unit is achieved, and the technical effect of accurate control and optimization of the operation state of the hydropower unit is achieved.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] Embodiment 1

[0020] Please refer to the attached Figure 1 The present application provides a method for optimizing the operation control of a hydropower unit based on holographic perception, wherein the method is applied to a system for optimizing the operation control of a hydropower unit based on holographic perception, and the method specifically comprises the following steps:

[0021] Step 1: Perform key identification based on the unit structure of the target hydropower unit and determine the key parts information of multiple units;

[0022] Specifically, according to the structure and function of the unit, key components and functional modules are determined, that is, the important parts that affect the performance and safety of the unit. For example, by obtaining the vulnerability of the components, their importance to the overall operation of the unit, and historical fault records, the key parts information of multiple units can be determined.

[0023] Step 2: Formulate a sensor layout plan, wherein the sensor layout plan is to construct a sensor network according to the sensor type, and match the key part information of the multiple units with the sensor network;

[0024] Specifically, based on the operating environment of the hydropower unit, determine the sensor type and then the sensor network. Confirm the key parts information of the unit, including location, direction, importance, etc. Match the key parts information of the unit with the monitoring range of the sensor network to ensure that each key part is within the monitoring range of at least one sensor.

[0025] Step 3: Execute the sensor layout scheme to deploy N sensors and build a sensor data cloud platform, where N is a positive integer greater than 1;

[0026] Specifically, N sensors are installed one by one according to the position and direction information in the sensor layout plan. A sensor data cloud platform is constructed. The sensor data cloud platform is a platform for transmitting, recording and summarizing sensor data. Since there are more than one sensor type, N is a positive integer greater than 1.

[0027] Step 4: extracting the first real-time holographic perception operation data set of the target hydropower unit in combination with the sensor data cloud platform;

[0028] Specifically, based on the operation data stored in the sensor data cloud platform, the data type, characteristics and change trend are extracted. For each data collection type, a control instruction is formulated. Through the control instruction, N sensors are activated according to the operation demand information of the target hydropower unit. The activated sensors perform real-time holographic acquisition according to the set acquisition frequency to obtain the first real-time holographic perception operation data set.

[0029] Step 5: construct a three-dimensional digital model of the target hydropower unit, synchronize the first real-time holographic perception operation data set to the three-dimensional digital model for simulation operation, and generate a simulation operation data set;

[0030] Specifically, the detailed design information, structural parameters, operation data, etc. of the target hydropower unit are collected. The collected data are preprocessed, including data cleaning, format conversion, etc., to ensure the consistency and accuracy of the data. According to the design information and structural parameters, the various components and the overall structure of the hydropower unit are gradually constructed. Ensure that the geometric shape, size and position of the model are consistent with the actual situation. Verify the constructed three-dimensional digital model to ensure its consistency with the actual unit. Synchronize the first real-time holographic perception operation data set to the three-dimensional digital model through the interface. In the three-dimensional digital model, set the parameters of the simulation operation, such as time step, simulation duration, etc. According to actual needs, adjust the simulation parameters to obtain more accurate simulation results. Start the simulation operation of the three-dimensional digital model. During the simulation operation, monitor the operation status and data changes of the model in real time. Adjust the simulation parameters or model as needed to optimize the simulation effect. After the simulation operation is completed, export the simulation operation data set from the three-dimensional digital model. Among them, the simulation operation data set can contain information such as key parameters, operation status and performance indicators in the simulation process.

[0031] Step 6: Optimize the sensor network according to the simulation operation data set, update the sensor layout plan according to the sensor optimization network, screen the N sensors according to the sensor layout optimization plan, and determine M sensors, where M is a positive integer greater than or equal to 0;

[0032] Specifically, a coverage assessment is performed on the simulation operation data set, and multiple coverage assessment results are calculated. The multiple coverage assessment results are used as indexes to identify areas in the sensor network where data coverage is insufficient or cannot be covered. A sensor network optimization strategy is formulated. According to the optimization strategy, the sensor network is optimized and adjusted to obtain a sensor optimized network. The layout of N sensors is adjusted to optimize the data perception effect, the sensor layout plan is updated, and a sensor layout optimization plan is generated. The N sensors are screened. For example, it is determined whether a preset standard reference threshold is met, and whether the N sensors meet the data perception collection category, and then they are deleted or added to determine M sensors. Among them, N and M are not necessarily related. If N is increased, M is greater than N, and if N is deleted, M is less than N.

[0033] Step seven: extract a second real-time holographic perception operation data set of the target hydropower unit through the sensor data cloud platform based on the M sensors, compare the second real-time holographic perception operation data set with the first real-time holographic perception operation data set, and intelligently optimize the operation control of the target hydropower unit according to the comparison result.

[0034] Specifically, M sensors are connected to the sensor data cloud platform. Through the sensor data cloud platform, the perception data of the M sensors are extracted in real time to form a second real-time holographic perception operation data set. Using visualization tools, the first operation change trend of the first real-time holographic perception operation data set and the second operation change trend of the second real-time holographic perception operation data set are respectively drawn. The first operation change trend and the second operation change trend are synchronously compared to ensure alignment and consistency on the timeline. Data mining is performed based on the comparison results to analyze the differences and similarities between the two operation change trends to obtain comparison results. Based on the comparison results, the sensor layout, data acquisition frequency, data processing method, etc. of the target hydropower unit are optimized and adjusted to improve the accuracy and reliability of data perception.

[0035] The hydropower unit operation control optimization method based on holographic perception is applied to the hydropower unit operation control optimization system based on holographic perception, which can achieve the technical goal of comprehensive monitoring of the hydropower unit and achieve the technical effect of precise control and optimization of the operating status of the hydropower unit.

[0036] Furthermore, the present application also includes the following steps:

[0037] Retrieve the historical operation data log of the target hydropower unit;

[0038] Perform unit fault matching based on the historical operation data record log to determine fault frequency information and fault quantity information;

[0039] Based on the fault frequency information and the fault quantity information, the faults are sorted in descending order according to their impact, to obtain a fault impact sequence;

[0040] Based on the fault impact sequence and in accordance with the unit structure, weight configuration is performed on the fault points of the target hydropower unit, and multiple fault points are identified according to the weight configuration result;

[0041] The multiple fault points are added to the multiple key parts information of the units.

[0042] Specifically, the identification information of the target hydropower unit is determined, such as the unit number, name or installation location. The data storage system or database of the hydropower unit is accessed and the identification information of the target unit is used for query. The historical operation data record log is extracted from the database, including the unit operation status, temperature, pressure, flow, power, vibration, noise and other parameters and their changes over time.

[0043] Then, analyze the historical operation data record logs to identify abnormal data or events. Match the identified abnormal data with the fault pattern to determine the specific fault type. Count the frequency and number of each fault type to generate fault frequency information and fault number information.

[0044] Next, based on the fault frequency information and fault quantity information, the impact of each fault on the unit operation is evaluated. The faults are sorted in descending order according to their impact, generating a fault impact sequence.

[0045] Next, analyze the possible fault points according to the structure diagram or layout diagram of the target hydropower unit and the fault impact sequence. Perform weight configuration according to the fault frequency and fault impact of the fault point. The higher the weight, the more important the fault point is, and vice versa. Identify each fault point, such as using numbers, colors or text descriptions. Determine multiple fault points and record their relevant information, such as location, weight, fault type, etc.

[0046] In addition, the key parts information of the target hydropower unit is collected or sorted, including known important components and areas. The previously determined multiple fault points are added to the key parts information of the unit to form a complete list of fault points and key parts information.

[0047] By identifying and marking the fault point and integrating it into the key part information of the unit, it provides important reference for subsequent maintenance, inspection and management.

[0048] Furthermore, the present application also includes the following steps:

[0049] Determine monitoring demand data based on the operating environment information of the target hydropower unit;

[0050] Determining the sensor type according to the monitoring requirement data;

[0051] Conducting a deployment feasibility analysis according to the sensor types and generating sensor distribution density data;

[0052] Designing a network topology structure of N sensors based on the sensor distribution density data and the sensor types;

[0053] The sensor network is established based on the network topology.

[0054] Specifically, collect the operating environment information of the target hydropower unit, including geographical location, climate conditions (such as temperature, humidity, wind speed, etc.), water quality, water flow velocity, water level changes, geological structure, etc. Analyze the operating environment information to determine the factors that may affect the operation of the unit and the key parameters that need to be monitored. Based on the analysis results, generate monitoring demand data to clarify the parameters that need to be monitored, the monitoring scope and the monitoring accuracy requirements.

[0055] Then, according to the monitoring requirement data, the corresponding sensor type is selected to measure the required parameters.

[0056] Next, we will make a preliminary plan for the sensor locations based on the actual layout and operation characteristics of the target hydropower units. We will analyze the monitoring requirements, environmental conditions, and characteristics of sensor types at different locations, conduct a feasibility analysis, and obtain the number, location, and distance of sensors required for each area. Based on the analysis results, we will determine the distribution density of sensors and generate sensor distribution density data.

[0057] Next, design N preliminary schemes for network topologies based on the sensor distribution density data and sensor types. Since there are more than one sensor type, N is a positive integer greater than 1. Consider factors such as network stability, communication efficiency, and data transmission to optimize and adjust the scheme. Determine the final network topology, including the connection method and communication protocol between sensors. Prepare the necessary network equipment and communication modules to realize the establishment of the sensor network.

[0058] In addition, according to the N network topologies, the sensors are arranged and installed, the parameters and communication settings of the sensors are configured, and then the N network topologies are formed to obtain the sensor network.

[0059] The monitoring demand data is determined through the operating environment information of the target hydropower unit, and a suitable sensor network is designed and established to achieve real-time monitoring and data analysis of the unit's operating status.

[0060] Furthermore, the present application also includes the following steps:

[0061] Traversing the key part information of the plurality of units and performing position matching with the sensor network to obtain a matching result, wherein the matching result includes layout position information and layout direction information, and there is a corresponding relationship between the layout position information and the layout direction information;

[0062] Determining whether the sensor distribution density data is in a preset equilibrium interval based on the layout position information;

[0063] If not, the densely located points and the missing points are locked according to the sensor distribution density data;

[0064] The N sensors are evenly distributed based on the densely located points and the missing points, and the sensitivity of the layout direction information is detected. The sensor layout plan is formulated according to the balanced distribution result and the direction-sensitive information.

[0065] Specifically, extract the location data of the key parts of the unit, including the three-dimensional coordinates or relative position of each key part. Obtain the location data of each sensor in the sensor network to ensure that the coordinate system of the location data of the sensor is consistent with the location data of the key parts of the unit. Use spatial matching algorithms, such as the nearest neighbor algorithm, distance threshold method, etc., to match the sensor with the key parts of the unit. Obtain matching results, including layout location information and layout direction information, and obtain a corresponding relationship between the layout location information and layout direction information.

[0066] Then, analyze the layout location information in the matching results and calculate the distribution density of sensors in different areas. Set a preset balance interval. The preset balance interval can be determined based on the importance of the key parts of the unit and the monitoring range of the sensor. Compare the calculated sensor distribution density data with the preset balance interval to determine whether the sensor distribution density data is within the preset balance interval.

[0067] Next, if the sensor distribution density data is not within the preset equilibrium interval, the data distribution is further analyzed. Areas where the sensor distribution is relatively dense are identified as location dense points. Areas where the sensor distribution is obviously insufficient are identified as location missing points. Among them, relatively dense areas and obviously insufficient areas are obtained by technicians in this field according to actual conditions.

[0068] Next, formulate a sensor redistribution plan based on the densely located points and the missing points. Adjust the number or location of sensors at densely located points to reduce the density. Add sensors at the missing points to ensure monitoring coverage of the entire area. For each sensor, analyze the impact of the layout direction information on the monitoring effect. For example, the layout direction of vibration sensors, sound sensors, etc. may directly affect the accuracy and effectiveness of their data collection. According to the directional sensitivity information, adjust the orientation or installation angle of the sensor to optimize the monitoring effect and formulate the final sensor layout plan.

[0069] By ensuring the precise match between the sensor network and the key parts of the unit and optimizing the layout of sensors, the monitoring effect and data accuracy can be improved.

[0070] Furthermore, the present application also includes the following steps:

[0071] Based on the operation data storage archive of the sensor data cloud platform, the data collection type is divided and multiple groups of control instructions are formulated;

[0072] Activate or silence N sensors according to the operation requirement information of the target hydropower unit through the multiple groups of control instructions, perform real-time holographic acquisition according to the activated sensors, and obtain multiple groups of real-time holographic perception operation data;

[0073] Setting data extraction rules, wherein the data extraction rules include extraction frequency and extraction cycle;

[0074] Determining whether the target real-time holographic perception operation data set reaches the upper limit of the extraction frequency based on the extraction cycle through the sensor data cloud platform;

[0075] If not, the target real-time holographic perception operation data set is extracted as the first real-time holographic perception operation data set; if so, random extraction is performed on the multiple groups of real-time holographic perception operation data to output the first real-time holographic perception operation data set.

[0076] Specifically, based on the operation data archives stored in the sensor data cloud platform, the data types, characteristics and change trends are extracted. According to the nature of the data and application requirements, data collection is divided into different types, such as temperature, pressure, flow, vibration, etc. For each data collection type, multiple groups of control instructions are formulated. For example, activation instructions and silent instructions are included. The control instructions specify the sensor number, activation time, collection frequency and other parameters that need to be activated or silent.

[0077] Then, through multiple groups of control instructions, N sensors are activated or silenced according to the operation demand information of the target hydropower unit. The activated sensors perform real-time holographic acquisition according to the set acquisition frequency. For example, according to the acquisition requirements and data characteristics, data extraction rules are set, including extraction frequency and extraction cycle, to obtain multiple groups of real-time holographic perception operation data. Ensure that the collected data is accurate and complete, and upload it to the sensor data cloud platform in real time.

[0078] Next, the extraction frequency in the data extraction rules is set according to the real-time nature and analysis requirements of the data, and the extraction cycle is used to ensure the continuity and integrity of the data.

[0079] In addition, through the sensor data cloud platform, based on the extraction cycle, it is judged whether the target real-time holographic perception operation data set has reached the upper limit of the extraction frequency, so as to avoid repeatedly extracting a data and repeatedly optimizing the same perception data, that is, local optimization, and then other data can be extracted for optimization.

[0080] Finally, if the upper limit is not reached, the target real-time holographic perception operation data set is directly extracted as the first real-time holographic perception operation data set. If the upper limit of the extraction frequency has been reached, random extraction is performed in multiple groups of real-time holographic perception operation data to ensure the representativeness and diversity of the data, while avoiding repeated extraction of the same or similar data to obtain the first real-time holographic perception operation data set.

[0081] By realizing the effective collection, extraction and application of operating data in the sensor data cloud platform, it provides an important basis for the operation management and maintenance of hydropower units.

[0082] Furthermore, the present application also includes the following steps:

[0083] Performing data coverage evaluation on the simulation operation data set to generate multiple coverage evaluation results;

[0084] Using the multiple coverage assessment results as indexes, performing blind spot analysis on the sensor network, optimizing the sensor network according to the analysis results, and obtaining the sensor optimized network;

[0085] Traversing the sensor optimization network to adjust the layout of the N sensors, updating the sensor layout scheme according to the layout adjustment data, and generating the sensor layout optimization scheme;

[0086] Based on the sensor layout optimization scheme, according to the data sensing and acquisition frequency of the N sensors, it is determined in turn whether the sensing data of the N sensors reaches a preset standard reference threshold;

[0087] If yes, then judging whether the N sensors meet the data sensing and collection category based on the sensor layout optimization scheme, if not, adding W sensors according to the data sensing and collection category to determine the M sensors;

[0088] If not, the sensors corresponding to the sensing data that do not reach the preset standard reference threshold are deleted to determine the M sensors.

[0089] Specifically, according to the characteristics and business requirements of the target hydropower units, set indicators for data coverage assessment, such as data integrity, accuracy, and real-time performance. For example, based on statistical methods, machine learning methods, etc., conduct coverage assessment on the simulated operation data set. Based on the set indicators, multiple coverage assessment results are calculated.

[0090] Then, the multiple coverage assessment results are used as indexes to perform blind spot analysis on the sensor network. In this process, areas in the sensor network where data coverage is insufficient or cannot be covered are identified. Based on the blind spot analysis results, a sensor network optimization strategy is formulated. For example, it may include adding sensors, adjusting sensor locations, changing sensor types, etc. Based on the optimization strategy, the sensor network is optimized and adjusted to obtain a sensor optimized network.

[0091] Next, the optimized sensor network is accessed in turn to adjust the layout of the N sensors. The data perception effect is optimized based on the position, angle, spacing and other factors of the sensors. The sensor layout plan is updated based on the layout adjustment data. The sensor layout optimization plan is generated as the basis for subsequent data perception collection.

[0092] Next, based on the sensor layout optimization solution, a judgment is made according to the data sensing acquisition frequency of N sensors. Determine whether the data acquisition of each sensor meets the preset acquisition frequency requirements. If the acquisition frequency is low, such as data is only collected once a month, it is considered to be of no reference value and the sensor can be deleted. Among them, the preset acquisition frequency requirements are obtained by technical personnel in this field according to actual conditions. For sensors that meet the acquisition frequency requirements, determine whether the sensor data reaches the preset standard reference threshold. For example, it may include evaluations of data accuracy, stability, continuity, etc. Among them, the preset standard reference threshold is obtained by technical personnel in this field according to actual conditions.

[0093] In addition, if the sensor data reaches the preset standard reference threshold, it is determined whether the N sensors meet the data perception collection category. For example, some key parts of the hydropower unit need to perceive the vibration data class through other sensors while perceiving the vibration data class through the vibration sensor. The key parts may need to obtain three categories of data, and when only two sensors are actually deployed, it is necessary to increase the sensors according to the category. Furthermore, if the data perception collection category requirements are not met, W sensors are added according to the collection category requirements to determine M sensors. Among them, W and M are positive integers greater than or equal to 0. If the sensor data reaches the preset standard reference threshold and meets the data perception collection category requirements, the sensors will not be deleted or increased.

[0094] Finally, if the sensor data does not reach the preset standard reference threshold, the sensors corresponding to the sensor data that does not reach the preset standard reference threshold are deleted to determine the number and layout of the M sensors.

[0095] By optimizing the sensor network, adjusting the layout and determining the number of sensors, strong support is provided for the operation management and maintenance of hydropower units.

[0096] Furthermore, the present application also includes the following steps:

[0097] Connecting the M sensors to the sensor data cloud platform to extract the second real-time holographic perception operation data set;

[0098] Plotting a second operation change trend of the second real-time holographic perception operation data set and a first operation change trend of the first real-time holographic perception operation data set;

[0099] The second operation change trend and the first operation change trend are synchronously compared to perform data mining to obtain a comparison result.

[0100] Specifically, the optimized M sensors are installed and configured. Ensure that each sensor can work normally and establish a connection with the sensor data cloud platform. Through the sensor data cloud platform, the perception data of the M sensors are extracted in real time to form a second real-time holographic perception operation data set.

[0101] Then, a visualization tool is used to draw the first operation change trend of the first real-time holographic perception operation data set and the second operation change trend of the second real-time holographic perception operation data set, respectively. The trend chart can show the change of data over time, including peak values, valley values, fluctuation ranges and other characteristics.

[0102] Next, the first operation change trend and the second operation change trend are synchronously compared to ensure alignment and consistency on the time axis. Data mining is performed based on the comparison results to analyze the differences and similarities between the two operation change trends. Information and features in the data can be mined through statistical analysis, pattern recognition, machine learning and other methods. Based on the results of data mining, the differences and causes between the two operation change trends are obtained as comparison results.

[0103] By connecting the optimized M sensors to the sensor data cloud platform, the second real-time holographic perception operation data set is extracted, and the second operation change trend is plotted. By synchronously comparing the first and second operation change trends for data mining, the comparison results are obtained, providing strong support for the operation management and optimization of the hydropower unit.

[0104] In summary, the hydropower unit operation control optimization method based on holographic perception provided by this application has the following technical effects:

[0105] By making key identification based on the unit structure of the target hydropower unit, the key part information of multiple units is determined; a sensor layout plan is formulated, and the sensor layout plan is to build a sensor network according to the sensor type, and match the key part information of the multiple units with the sensor network; the sensor layout plan is executed to deploy N sensors, and a sensor data cloud platform is constructed, where N is a positive integer greater than 1; the first real-time holographic perception operation data set of the target hydropower unit is extracted in combination with the sensor data cloud platform; a three-dimensional digital model of the target hydropower unit is constructed, and the first real-time holographic perception operation data set is synchronized to the three-dimensional digital model for simulation operation to generate a simulated operation data set; the sensor network is optimized according to the simulated operation data set, and the sensor network is optimized according to the sensor data set. The sensor optimization network updates the sensor layout plan, screens the N sensors according to the sensor layout optimization plan, determines M sensors, where M is a positive integer greater than or equal to 0; based on the M sensors, extracts a second real-time holographic perception operation data set of the target hydropower unit through the sensor data cloud platform, compares the second real-time holographic perception operation data set with the first real-time holographic perception operation data set, and intelligently optimizes the operation control of the target hydropower unit according to the comparison result. That is to say, through holographic perception technology, all-round monitoring and data collection of the unit's operating status can be achieved, providing more comprehensive and accurate information for the control system, and combining advanced data processing algorithms and control strategies to accurately control and optimize the unit to improve operating efficiency.

[0106] Embodiment 2

[0107] Based on the same inventive concept as the hydropower unit operation control optimization method based on holographic perception in the aforementioned embodiment, the present application also provides a hydropower unit operation control optimization system based on holographic perception, please refer to the attached Figure 2 , the system comprising:

[0108] A unit key part information determination module 11, which is used to perform key identification based on the unit structure of the target hydropower unit and determine multiple units of key part information;

[0109] A sensor layout scheme formulation module 12, wherein the sensor layout scheme formulation module 12 is used to formulate a sensor layout scheme, wherein the sensor layout scheme is to construct a sensor network according to the sensor type, and to match the key parts information of the multiple units with the sensor network;

[0110] A sensor data cloud platform construction module 13, wherein the sensor data cloud platform construction module 13 is used to execute the sensor layout scheme to deploy N sensors and construct a sensor data cloud platform, where N is a positive integer greater than 1;

[0111] A first real-time holographic perception operation data set extraction module 14, which is used to extract a first real-time holographic perception operation data set of a target hydropower unit in combination with the sensor data cloud platform;

[0112] A simulation operation data set generation module 15, wherein the simulation operation data set generation module 15 is used to construct a three-dimensional digital model of a target hydropower unit, synchronize the first real-time holographic perception operation data set to the three-dimensional digital model for simulation operation, and generate a simulation operation data set;

[0113] M sensor determination modules 16, the M sensor determination modules 16 are used to optimize the sensor network according to the simulation operation data set, update the sensor layout plan according to the sensor optimization network, screen the N sensors according to the sensor layout optimization plan, and determine M sensors, where M is a positive integer greater than or equal to 0;

[0114] The intelligent optimization module 17 is used to extract a second real-time holographic perception operation data set of the target hydropower unit through the sensor data cloud platform based on the M sensors, compare the second real-time holographic perception operation data set with the first real-time holographic perception operation data set, and intelligently optimize the operation control of the target hydropower unit according to the comparison result.

[0115] Furthermore, the unit key part information determination module 11 in the system is also used for:

[0116] Retrieve the historical operation data log of the target hydropower unit;

[0117] Perform unit fault matching based on the historical operation data record log to determine fault frequency information and fault quantity information;

[0118] Based on the fault frequency information and the fault quantity information, the faults are sorted in descending order according to their impact, to obtain a fault impact sequence;

[0119] Based on the fault impact sequence and in accordance with the unit structure, weight configuration is performed on the fault points of the target hydropower unit, and multiple fault points are identified according to the weight configuration result;

[0120] The multiple fault points are added to the multiple key parts information of the units.

[0121] Furthermore, the sensor layout scheme formulation module 12 in the system is also used for:

[0122] Determine monitoring demand data based on the operating environment information of the target hydropower unit;

[0123] Determining the sensor type according to the monitoring requirement data;

[0124] Conducting a deployment feasibility analysis according to the sensor types and generating sensor distribution density data;

[0125] Designing a network topology structure of N sensors based on the sensor distribution density data and the sensor types;

[0126] The sensor network is established based on the network topology.

[0127] Furthermore, the sensor layout scheme formulation module 12 in the system is also used for:

[0128] Traversing the key part information of the plurality of units and performing position matching with the sensor network to obtain a matching result, wherein the matching result includes layout position information and layout direction information, and there is a corresponding relationship between the layout position information and the layout direction information;

[0129] Determining whether the sensor distribution density data is in a preset equilibrium interval based on the layout position information;

[0130] If not, the densely located points and the missing points are locked according to the sensor distribution density data;

[0131] The N sensors are evenly distributed based on the densely located points and the missing points, and the sensitivity of the layout direction information is detected. The sensor layout plan is formulated according to the balanced distribution result and the direction-sensitive information.

[0132] Furthermore, the first real-time holographic perception operation data set extraction module 14 in the system is also used for:

[0133] Based on the operation data storage archive of the sensor data cloud platform, the data collection type is divided and multiple groups of control instructions are formulated;

[0134] Activate or silence N sensors according to the operation requirement information of the target hydropower unit through the multiple groups of control instructions, perform real-time holographic acquisition according to the activated sensors, and obtain multiple groups of real-time holographic perception operation data;

[0135] Setting data extraction rules, wherein the data extraction rules include extraction frequency and extraction cycle;

[0136] Determining whether the target real-time holographic perception operation data set reaches the upper limit of the extraction frequency based on the extraction cycle through the sensor data cloud platform;

[0137] If not, the target real-time holographic perception operation data set is extracted as the first real-time holographic perception operation data set; if so, random extraction is performed on the multiple groups of real-time holographic perception operation data to output the first real-time holographic perception operation data set.

[0138] Further, the M sensor determination modules 16 in the system are also used for:

[0139] Performing data coverage evaluation on the simulation operation data set to generate multiple coverage evaluation results;

[0140] Using the multiple coverage assessment results as indexes, performing blind spot analysis on the sensor network, optimizing the sensor network according to the analysis results, and obtaining the sensor optimized network;

[0141] Traversing the sensor optimization network to adjust the layout of the N sensors, updating the sensor layout scheme according to the layout adjustment data, and generating the sensor layout optimization scheme;

[0142] Based on the sensor layout optimization scheme, according to the data sensing and acquisition frequency of the N sensors, it is determined in turn whether the sensing data of the N sensors reaches a preset standard reference threshold;

[0143] If yes, then judging whether the N sensors meet the data sensing and collection category based on the sensor layout optimization scheme, if not, adding W sensors according to the data sensing and collection category to determine the M sensors;

[0144] If not, the sensors corresponding to the sensing data that do not reach the preset standard reference threshold are deleted to determine the M sensors.

[0145] Furthermore, the intelligent optimization module 17 in the system is also used for:

[0146] Connecting the M sensors to the sensor data cloud platform to extract the second real-time holographic perception operation data set;

[0147] Plotting a second operation change trend of the second real-time holographic perception operation data set and a first operation change trend of the first real-time holographic perception operation data set;

[0148] The second operation change trend and the first operation change trend are synchronously compared to perform data mining to obtain a comparison result.

[0149] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The hydropower unit operation control optimization method based on holographic perception and the specific examples in the aforementioned embodiment one are also applicable to the hydropower unit operation control optimization system based on holographic perception in this embodiment. Through the aforementioned detailed description of the hydropower unit operation control optimization method based on holographic perception, those skilled in the art can clearly know the hydropower unit operation control optimization system based on holographic perception in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0150] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0151] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A hydropower unit operation control optimization method based on holographic perception, characterized in that: The method comprises: Perform key identification based on the unit structure of the target hydropower unit and determine the key parts information of multiple units; Formulate a sensor layout plan, wherein the sensor layout plan is to construct a sensor network according to the sensor type, and match the key parts information of the multiple units with the sensor network; Execute the sensor layout scheme to deploy N sensors and build a sensor data cloud platform, where N is a positive integer greater than 1; The first real-time holographic perception operation data set of the target hydropower unit is extracted in combination with the sensor data cloud platform, including: Based on the operation data storage archive of the sensor data cloud platform, the data collection type is divided and multiple groups of control instructions are formulated; Activate or silence N sensors according to the operation demand information of the target hydropower unit through the multiple groups of control instructions, perform real-time holographic acquisition according to the activated sensors, and obtain multiple groups of real-time holographic perception operation data; Setting data extraction rules, wherein the data extraction rules include extraction frequency and extraction cycle; Determining whether the target real-time holographic perception operation data set reaches the upper limit of the extraction frequency based on the extraction cycle through the sensor data cloud platform; If not, extracting the target real-time holographic perception operation data set as the first real-time holographic perception operation data set; if so, randomly extracting from the multiple groups of real-time holographic perception operation data, and outputting the first real-time holographic perception operation data set; Constructing a three-dimensional digital model of the target hydropower unit, synchronizing the first real-time holographic sensing operation data set to the three-dimensional digital model for simulation operation, and generating a simulated operation data set; Optimizing the sensor network according to the simulation operation data set, updating the sensor layout scheme according to the sensor optimization network, screening the N sensors according to the sensor layout optimization scheme, and determining M sensors, where M is a positive integer greater than or equal to 0, including: Performing data coverage evaluation on the simulation operation data set to generate multiple coverage evaluation results; Using the multiple coverage assessment results as indexes, performing blind spot analysis on the sensor network, optimizing the sensor network according to the analysis results, and obtaining the sensor optimized network; Traversing the sensor optimization network to adjust the layout of the N sensors, updating the sensor layout scheme according to the layout adjustment data, and generating the sensor layout optimization scheme; Based on the sensor layout optimization scheme, according to the data sensing and acquisition frequency of the N sensors, it is determined in turn whether the sensing data of the N sensors reaches a preset standard reference threshold; If yes, then judging whether the N sensors meet the data sensing and collection category based on the sensor layout optimization scheme, if not, adding W sensors according to the data sensing and collection category to determine the M sensors; If not, the sensors corresponding to the sensing data that do not reach the preset standard reference threshold are deleted to determine the M sensors; Based on the M sensors, a second real-time holographic perception operation data set of the target hydropower unit is extracted through the sensor data cloud platform, and the second real-time holographic perception operation data set is compared with the first real-time holographic perception operation data set. According to the comparison result, the operation control of the target hydropower unit is intelligently optimized.

2. The method for optimizing the operation control of a hydropower unit based on holographic perception according to claim 1, characterized in that: Based on the unit structure of the target hydropower unit, key identification is performed to determine the key parts information of multiple units. The method includes: Retrieve the historical operation data log of the target hydropower unit; Perform unit fault matching based on the historical operation data record log to determine fault frequency information and fault quantity information; Based on the fault frequency information and the fault quantity information, the faults are sorted in descending order according to their impact, to obtain a fault impact sequence; Based on the fault impact sequence and in accordance with the unit structure, weight configuration is performed on the fault points of the target hydropower unit, and multiple fault points are identified according to the weight configuration result; The multiple fault points are added to the multiple key parts information of the units.

3. The hydropower unit operation control optimization method based on holographic perception according to claim 1 is characterized in that: Building a sensor network based on sensor types includes: Determine monitoring demand data based on the operating environment information of the target hydropower unit; Determining the sensor type according to the monitoring requirement data; Conducting a deployment feasibility analysis according to the sensor types and generating sensor distribution density data; Designing a network topology structure of N sensors based on the sensor distribution density data and the sensor types; The sensor network is established based on the network topology.

4. The hydropower unit operation control optimization method based on holographic perception according to claim 3 is characterized in that: According to the information of the key parts of the plurality of units, the method is matched with the sensor network, and includes: Traversing the key part information of the plurality of units and performing position matching with the sensor network to obtain a matching result, wherein the matching result includes layout position information and layout direction information, and there is a corresponding relationship between the layout position information and the layout direction information; Determining whether the sensor distribution density data is in a preset equilibrium interval based on the layout position information; If not, the densely located points and the missing points are locked according to the sensor distribution density data; The N sensors are evenly distributed based on the densely located points and the missing points, and the sensitivity of the layout direction information is detected. The sensor layout plan is formulated according to the balanced distribution result and the direction-sensitive information.

5. The hydropower unit operation control optimization method based on holographic perception according to claim 1 is characterized in that: Based on the M sensors, a second real-time holographic perception operation data set of the target hydropower unit is extracted through the sensor data cloud platform, and the second real-time holographic perception operation data set is compared with the first real-time holographic perception operation data set, the method comprising: Connecting the M sensors to the sensor data cloud platform to extract the second real-time holographic perception operation data set; Plotting a second operation change trend of the second real-time holographic perception operation data set and a first operation change trend of the first real-time holographic perception operation data set; The second operation change trend and the first operation change trend are synchronously compared to perform data mining to obtain a comparison result.

6. The hydropower unit operation control optimization system based on holographic perception is characterized by: For implementing the steps of the method according to any one of claims 1 to 5, the system comprises: A unit key part information determination module, the unit key part information determination module is used to perform key identification based on the unit structure of the target hydropower unit and determine multiple unit key part information; A sensor layout scheme formulation module, wherein the sensor layout scheme formulation module is used to formulate a sensor layout scheme, wherein the sensor layout scheme is to construct a sensor network according to the sensor type, and to match the sensor network with the key part information of the multiple units; A sensor data cloud platform construction module, wherein the sensor data cloud platform construction module is used to execute the sensor layout scheme to deploy N sensors and construct a sensor data cloud platform, where N is a positive integer greater than 1; A first real-time holographic perception operation data set extraction module, which is used to extract a first real-time holographic perception operation data set of a target hydropower unit in combination with the sensor data cloud platform; A simulation operation data set generation module, wherein the simulation operation data set generation module is used to construct a three-dimensional digital model of a target hydropower unit, synchronize the first real-time holographic perception operation data set to the three-dimensional digital model for simulation operation, and generate a simulation operation data set; M sensor determination modules, the M sensor determination modules are used to optimize the sensor network according to the simulation operation data set, update the sensor layout plan according to the sensor optimization network, screen the N sensors according to the sensor layout optimization plan, and determine M sensors, where M is a positive integer greater than or equal to 0; An intelligent optimization module is used to extract a second real-time holographic perception operation data set of the target hydropower unit through the sensor data cloud platform based on the M sensors, compare the second real-time holographic perception operation data set with the first real-time holographic perception operation data set, and intelligently optimize the operation control of the target hydropower unit according to the comparison result.

Images