Intelligent control system for Francis turbine and control method thereof

Abstract

This invention discloses an intelligent control system and method for a mixed-flow turbine, belonging to the field of intelligent control technology for mixed-flow turbines. The method includes: real-time monitoring of the mixed-flow turbine to obtain monitoring data; real-time analysis of the monitoring data to determine the power generation efficiency curve; real-time determination of the optimal operating point based on the power generation efficiency curve, and generation of control commands based on the optimal operating point; real-time acquisition of adjustment records of the power generation efficiency curve; classification of the adjustment records according to operating points to obtain operating point efficiency records; acquisition of a standard power generation curve, and generation of efficiency change curves for operating points based on the standard power generation curve and operating point efficiency records; early warning analysis based on the efficiency change curves of each operating point, obtaining corresponding early warning analysis results, and corresponding early warning processing based on the early warning analysis results; real-time acquisition of the start-up and shutdown records of the mixed-flow turbine, and optimization management of the start-up and shutdown of the mixed-flow turbine based on the start-up and shutdown records.

Description

Technical Field

[0001] This invention belongs to the field of intelligent control technology for mixed-flow turbines, specifically an intelligent control system and control method for mixed-flow turbines. Background Technology

[0002] Mixed-flow turbines, with their high efficiency and stability, have been widely used in water conservancy and hydropower projects. However, as the scale of hydropower stations continues to expand and operating conditions become more complex, the performance requirements for mixed-flow turbines are also increasing. While existing mixed-flow turbines have made significant progress in design and manufacturing, they still have shortcomings in intelligent control. Traditional control systems often rely on manual operation and experience-based judgment, making it difficult to achieve precise and efficient automated control.

[0003] With the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, intelligent control systems have been widely applied in various fields. However, in the field of mixed-flow turbines, the application of intelligent control systems is still in its early stages. Most existing intelligent control systems can only achieve simple monitoring and alarm functions, lacking comprehensive, real-time, and precise control over the operating status of mixed-flow turbines. Existing intelligent control systems are often only adaptable to specific operating conditions and lack sufficient adaptability to the complex and ever-changing hydropower station environment.

[0004] In order to solve the above problems, this invention provides an intelligent control system and control method for a mixed-flow turbine. Summary of the Invention

[0005] To address the problems of the aforementioned solutions, this invention provides an intelligent control system and method for mixed-flow turbines, thereby solving the intelligent control problem of existing mixed-flow turbines.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A mixed-flow turbine intelligent control system includes a monitoring module, an efficiency analysis module, a control module, and an anomaly monitoring module;

[0008] The monitoring module is used to monitor the mixed-flow turbine in real time and obtain monitoring data of the mixed-flow turbine.

[0009] The efficiency analysis module is used to analyze the monitoring data of the mixed-flow turbine in real time and determine the power generation efficiency curve of the mixed-flow turbine. The vertical axis of the power generation efficiency curve is the power generation efficiency, and the horizontal axis is the operating point.

[0010] The optimal operating point is determined in real time based on the power generation efficiency curve, and corresponding control commands are generated based on the optimal operating point and sent to the control module.

[0011] Furthermore, the determination of the power generation efficiency curve includes:

[0012] Obtain the standard power generation curve; identify the corresponding control parameter items based on the standard power generation curve; acquire material analysis data of the mixed-flow turbine in real time, including historical monitoring data and historical power generation efficiency;

[0013] Based on the control parameter items, feature identification is performed on the material analysis data to obtain control feature data, which includes control combination features and power generation efficiency features; the control feature data is then classified according to the control combination features to obtain the efficiency-optimized materials corresponding to the control combination features;

[0014] The efficiency optimization data is analyzed to obtain the power generation adjustment efficiency corresponding to the control combination characteristics; the control combination characteristics and power generation adjustment efficiency are integrated into curve adjustment data; the standard power generation curve is adjusted in real time according to the curve adjustment data to obtain the power generation efficiency curve of the mixed-flow turbine.

[0015] Furthermore, the materials for efficiency optimization are analyzed, including:

[0016] Step SA1: Identify the power generation efficiency features corresponding to the efficiency optimization materials, classify the same power generation efficiency features into one category, and mark them as unit efficiency features; identify the unit value and number of units corresponding to the unit efficiency features, where the number of units is the number of power generation efficiency features contained in the unit efficiency feature, and the unit value is the power generation efficiency corresponding to the unit efficiency feature;

[0017] Step SA2: Merge any two cell efficiency features with the largest number of cells according to the preset representative merging formula to obtain new cell efficiency features; the representative merging formula is:

[0018] ;

[0019] d = d1 + d2;

[0020] In the formula: L is the unit value of the new unit efficiency feature; L1 and L2 are the unit values ​​of the two unit efficiency features being merged; d1 and d2 are the number of units of the two unit efficiency features being merged; d is the number of units of the new unit efficiency feature.

[0021] Step SA3: Repeat step SA2 until there is only one unit efficiency characteristic, and determine the power generation adjustment efficiency based on the unit value of the unit efficiency characteristic.

[0022] Furthermore, the optimal operating point is determined in real time based on the power generation efficiency curve, including:

[0023] Based on the power generation efficiency curve, identify the operating point corresponding to each power generation efficiency, mark it as the calibration operating point, perform calibration analysis on the calibration operating point, and obtain several preliminary operating points.

[0024] Identify the highest power generation efficiency among the initial selected operating points and mark the initial selected operating point corresponding to the highest power generation efficiency as the candidate operating point;

[0025] The selection of operating points is screened to obtain the optimal operating point.

[0026] Furthermore, calibration analysis is performed on the operating points, including:

[0027] Identify the benchmark operating point based on the monitoring data; establish a control calibration model, analyze the benchmark operating point and calibration operating point through the control calibration model, and obtain the calibration result of the calibration operating point, including calibration pass and calibration fail; mark the calibration operating point with calibration pass as the initial selected operating point.

[0028] Furthermore, the expression for the control calibration model is:

[0029] ;

[0030] In the formula: (GK, HK) are the input data, GK is the reference operating point, and HK is the calibration operating point; GK→HK means that the reference operating point can be adjusted to the corresponding calibration operating point through the control module; the output data is the control calibration value KP(GK, HK), and the control calibration value is 1 or 0.

[0031] The reference operating point and calibration operating point are analyzed by controlling the calibration model to obtain the corresponding control calibration values;

[0032] When the control calibration value is 1, the calibration result is that the calibration is passed;

[0033] When the control calibration value is 0, the calibration result is "calibration failed".

[0034] Furthermore, before determining the optimal operating point based on the power generation efficiency curve, environmental adjustment items are first determined, and environmental adjustment data is obtained through real-time monitoring based on these items. Environmental adjustment interval data is then determined based on the environmental adjustment interval data and the power generation efficiency curve.

[0035] The control module is used to make control adjustments based on the received control commands.

[0036] The anomaly monitoring module is used to perform anomaly early warning analysis based on the power generation efficiency curve and to obtain the adjustment records of the power generation efficiency curve in real time.

[0037] The adjustment records are classified according to the operating points to obtain the operating efficiency records of the operating points; a standard power generation curve is obtained, and an efficiency change curve of the operating points is generated based on the standard power generation curve and the operating efficiency records. The horizontal axis of the efficiency change curve is time, and the vertical axis is the efficiency change value.

[0038] Early warning analysis is performed based on the efficiency change curves at various operating points to obtain corresponding early warning analysis results, and corresponding early warning processing is carried out based on the early warning analysis results.

[0039] Furthermore, early warning analysis is performed based on the efficiency change curves at each operating point, including:

[0040] The efficiency change curve is fitted to obtain the efficiency change function, which is denoted as HY(t), where t is time.

[0041] An efficiency early warning model is established, and its expression is as follows:

[0042] ;

[0043] In the formula: [HY(t)] is the input data, X1 and X2 are both thresholds; kt represents the slope of the efficiency change function at the corresponding time; the output data is the efficiency warning value QS[HY(t)], and the efficiency warning value is 1, 2 or 0;

[0044] The efficiency change function is analyzed by using an efficiency early warning model to obtain the corresponding efficiency early warning value; the early warning analysis results are determined based on the efficiency early warning value.

[0045] Furthermore, it also includes a start-stop management module, which is used to optimize the start-stop management of the mixed-flow turbine, obtain the start-stop records of the mixed-flow turbine in real time, and the start-stop records include start-stop time, start-stop reason, and start-stop number; identify the start-stop reasons in the start-stop records, and classify the start-stop reasons into management type and adjustment type according to whether the number of start-stops can be reduced through the control and management of the mixed-flow turbine;

[0046] Set up corresponding optimized management methods for the start-up and shutdown reasons of the management category, and manage the mixed-flow turbine according to the optimized management methods.

[0047] A control method for a mixed-flow turbine, the method comprising:

[0048] Real-time monitoring of the mixed-flow turbine was conducted to obtain monitoring data of the mixed-flow turbine.

[0049] Real-time analysis of monitoring data is performed to determine the power generation efficiency curve of the mixed-flow turbine;

[0050] The optimal operating point is determined in real time based on the power generation efficiency curve, and control commands are generated based on the optimal operating point; the mixed-flow turbine is then controlled and adjusted according to the control commands.

[0051] The system acquires adjustment records of the power generation efficiency curve in real time; classifies the adjustment records according to operating points to obtain the operating efficiency records of the operating points; acquires the standard power generation curve, and generates the efficiency change curve of the operating point based on the standard power generation curve and the operating efficiency records.

[0052] Based on the efficiency change curves of each operating point, early warning analysis is performed to obtain corresponding early warning analysis results, and corresponding early warning processing is carried out based on the early warning analysis results.

[0053] Real-time acquisition of start-up and shutdown records of mixed-flow turbines, and optimization management of start-up and shutdown of mixed-flow turbines based on these records.

[0054] Compared with the prior art, the beneficial effects of the present invention are:

[0055] Through the coordinated operation of the monitoring module, efficiency analysis module, control module, and anomaly monitoring module, comprehensive monitoring and precise control of the mixed-flow turbine's operating status are achieved. The system can automatically adjust control strategies based on the actual operating conditions of the hydropower station, ensuring optimal performance under various environments. This high adaptability not only improves the system's reliability and stability but also reduces reliance on manual intervention. Furthermore, by incorporating a start-stop management module, the system intelligently reduces the number of start-stop cycles of the mixed-flow turbine, improving its stability, extending its service life, and enhancing the economic benefits of the hydropower station. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a block diagram illustrating the principle of the present invention. Detailed Implementation

[0058] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0059] like Figure 1As shown, an intelligent control system for a mixed-flow turbine includes a monitoring module, an efficiency analysis module, a control module, an anomaly monitoring module, and a start-stop management module.

[0060] The monitoring module is used to monitor the mixed-flow turbine in real time and obtain relevant monitoring data, such as flow rate, pressure, speed, temperature and other related data; and to perform corresponding monitoring using the configured relevant sensors.

[0061] The efficiency analysis module is used to analyze the monitoring data of the mixed-flow turbine in real time, determine the power generation efficiency curve of the mixed-flow turbine, with the vertical axis representing power generation efficiency and the horizontal axis representing various control parameters affecting power generation efficiency, such as guide vane opening, speed, flow rate, and head. Subsequent adjustments are made based on the adjustable control parameters. For example, it is determined whether parameters such as flow rate and head can be adjusted according to the actual situation. If not, the power generation efficiency is adjusted mainly by adjusting the guide vane opening and speed of the mixed-flow turbine. The corresponding combination of control parameters is marked as the operating point, i.e., the horizontal axis is composed of the corresponding operating points. The optimal operating point is determined in real time based on the power generation efficiency curve, and corresponding control commands are generated based on the optimal operating point and sent to the control module.

[0062] The aforementioned mixed-flow turbine refers to a mixed-flow turbine that requires intelligent control after installation and application.

[0063] In one embodiment, the power generation efficiency curve can be determined based on existing methods, such as using the power generation efficiency curve determined by the previous real machine experiment, and then correcting the power generation efficiency curve in sync during subsequent equipment maintenance; or it can be based on intelligent algorithms such as deep learning algorithms to establish an intelligent model, and then analyze the monitoring data through the successfully trained intelligent model to obtain the power generation efficiency curve.

[0064] In one embodiment, determining the power generation efficiency curve includes:

[0065] The power generation efficiency curve obtained from previous real-machine experiments or other simulation experiments is marked as the standard power generation curve;

[0066] Identify the corresponding control parameters based on the standard power generation curve, and acquire material analysis data of the mixed-flow turbine in real time. Material analysis data refers to the recent historical monitoring data of the mixed-flow turbine and the corresponding historical power generation efficiency, such as within a day or a week. Generally, the material data is collected according to the corresponding power generation efficiency. For example, for power generation efficiency A, one hour of historical monitoring data at that power generation efficiency is required. Then, historical monitoring data is collected according to the corresponding time. The specific material analysis data is collected according to the actual situation.

[0067] Based on the control parameter items, feature identification is performed on the material analysis data to obtain control feature data. The control feature data includes control combination features and power generation efficiency features. The control combination features are the combinations of control parameters corresponding to each control parameter item, and the power generation efficiency features refer to the historical power generation efficiency corresponding to the control combination features. The control feature data is classified according to the control combination features to obtain the efficiency optimization materials corresponding to the control combination features.

[0068] The efficiency optimization data is analyzed to obtain the power generation adjustment efficiency corresponding to the control combination characteristics. The control combination characteristics and power generation adjustment efficiency are integrated into curve adjustment data. The standard power generation curve is adjusted in real time according to the curve adjustment data to obtain the power generation efficiency curve of the mixed-flow turbine. That is, the curve adjustment data is used as the new curve coordinates for curve adjustment.

[0069] In one embodiment, the efficiency optimization material is analyzed using existing mathematical statistical methods to determine the representative power generation efficiency corresponding to the control combination characteristics, which is then labeled as the power generation adjustment efficiency; for example, the power generation adjustment efficiency is determined using mathematical statistical methods such as mode and mean.

[0070] In one embodiment, analyzing efficiency-optimized materials includes:

[0071] Step SA1: Identify the power generation efficiency features corresponding to the efficiency optimization materials, group those with the same power generation efficiency features into one category and mark them as unit efficiency features, identify the unit value and number of units corresponding to the unit efficiency features, the number of units is the number of power generation efficiency features corresponding to the unit efficiency features, and the unit value is the historical power generation efficiency corresponding to the unit efficiency features or the new unit value calculated by subsequent merging.

[0072] Step SA2: Merge any two unit efficiency features with the largest number of units according to the preset representative merging formula to obtain a new unit efficiency feature; if the unit with the largest number of units has two unit efficiency features, then merge these two unit efficiency features; if the unit with the largest number of units has 5, then randomly select two from the 5 to merge, and so on.

[0073] Identify the cell value and number of cells corresponding to the new cell efficiency characteristics; the representative merging formula is:

[0074] ;

[0075] In the formula: L is the unit value corresponding to the combined efficiency features of the two units; L1 and L2 are the unit values ​​of the efficiency features of the two units, respectively; d1 and d2 are the number of units of the efficiency features of the two units, respectively.

[0076] The number of units for the new unit efficiency feature is:

[0077] d = d1 + d2;

[0078] d represents the number of units for the new unit efficiency characteristic;

[0079] Merging two unit efficiency features into a new unit efficiency feature is equivalent to the union of sets.

[0080] Step SA3: Repeat step SA2 until there is only one unit efficiency characteristic, and mark the unit value of that unit efficiency characteristic as the power generation adjustment efficiency.

[0081] In one embodiment, the optimal operating point is determined in real time based on the power generation efficiency curve. The operating point refers to the working state of the mixed-flow turbine under specific flow rate, head, speed, and other conditions. The optimal operating point refers to the state under these conditions where the power generation efficiency of the mixed-flow turbine is the highest and its operation is the most stable. The optimal operating point is determined based on the above definition and using existing methods.

[0082] In one embodiment, determining the optimal operating point in real time based on the power generation efficiency curve includes:

[0083] Based on the power generation efficiency curve, identify the operating point corresponding to each power generation efficiency and mark it as the calibration operating point. Perform calibration analysis on the calibration operating point and mark the achievable calibration operating point as the initial selection operating point. Identify the highest power generation efficiency among the initial selection operating points and mark the initial selection operating point corresponding to the highest power generation efficiency as the candidate operating point.

[0084] The selection of operating points is screened to obtain the optimal operating point.

[0085] In one embodiment, calibration analysis of the operating point can be performed based on existing calibration methods, such as calibration based on the actual controllable situation, to determine whether the current operating point can be adjusted to the corresponding operating point.

[0086] In one embodiment, calibration analysis of the operating point includes:

[0087] The current operating point is identified based on monitoring data and marked as the baseline operating point. A control calibration model is established based on the actual control conditions of the mixed-flow turbine. The model is trained using set training data, such as simulating the baseline operating point, calibration operating point, and calibration results. The baseline operating point and calibration operating point are analyzed through the control calibration model to obtain the corresponding calibration results. The calibration results include calibration pass and calibration fail. Calibration pass indicates that control adjustment can be performed.

[0088] The initial operating point is determined based on the obtained calibration results.

[0089] In one embodiment, the control calibration model can be built based on neural networks such as CNN or DNN networks.

[0090] In one embodiment, the expression for controlling the calibration model is:

[0091] ;

[0092] In the formula: (GK, HK) are the input data, GK is the reference operating point, and HK is the calibration operating point; GK→HK means that the reference operating point can be adjusted to the corresponding calibration operating point through the control module; the output data is the control calibration value KP(GK, HK), and the control calibration value is 1 or 0.

[0093] The reference operating point and calibration operating point are analyzed by controlling the calibration model to obtain the corresponding control calibration values;

[0094] When the control calibration value is 1, the calibration result is that the calibration is passed;

[0095] When the control calibration value is 0, the calibration result is "calibration failed".

[0096] In one embodiment, the selection of operating points is screened, mainly based on factors such as operational stability, maintenance cost, and control adjustment time, to determine the optimal operating point. This can be achieved by pre-setting weight coefficients for each screening factor, extracting features based on the screening factors, determining priorities based on the weight coefficients of the screening factors, and then determining the optimal operating point based on the priorities.

[0097] In one embodiment, the selection of operating points can be screened, and other existing screening methods can also be used for screening analysis to determine the optimal operating point.

[0098] In one embodiment, when the operating environment of the mixed-flow turbine has conditions for adjusting water flow rate, head, etc., environmental adjustment items are determined according to the actual situation, and environmental adjustment items are set according to the adjustable head, etc.; intelligent analysis technology can also be used to recommend to the user whether the corresponding environmental adjustment items can be applied in the actual environment and the best implementation method, thereby improving the operating environment of the mixed-flow turbine and realizing the adjustability of some or all environmental influencing factors; specifically:

[0099] The environmental adjustment items are determined, and real-time monitoring is performed based on these items to obtain environmental adjustment data. Based on the environmental adjustment data, the environmental adjustment range data is determined, that is, the control range of the environmental adjustment items is used to determine the range within which the environmental adjustment data can be adjusted, thereby determining the environmental adjustment range data. Based on the environmental adjustment range data and the power generation efficiency curve, the optimal operating point is determined. The difference from the above embodiment is that the environmental adjustment items can be changed to achieve higher power generation efficiency.

[0100] The control module is used to make control adjustments based on the received control commands.

[0101] The anomaly monitoring module is used to perform anomaly early warning analysis based on the power generation efficiency curve, and to obtain the adjustment records of the power generation efficiency curve in real time, that is, the change adjustment records of power generation efficiency corresponding to each operating point. The adjustment records are classified according to the operating point to obtain the operating efficiency record of the corresponding operating point. The efficiency change curve of the corresponding operating point is generated based on the operating efficiency record, that is, the efficiency curve is generated based on the change value of power generation efficiency, and the calculation is compared with the standard power generation curve. The horizontal axis of the efficiency change curve is time, and the vertical axis is the efficiency change value.

[0102] Early warning analysis is performed based on the efficiency change curves at various operating points to obtain corresponding early warning analysis results. Based on the early warning analysis results, corresponding early warning actions are taken, such as issuing warnings to management personnel or taking emergency measures.

[0103] In one embodiment, early warning analysis is performed based on the efficiency change curves at various operating points. This analysis primarily relies on the slope changes and magnitudes of efficiency change values ​​of the curves over the same period. Existing methods can be combined to perform early warning analysis on efficiency change curves. For example, an intelligent early warning model can be established using deep learning algorithms. A corresponding training set can be manually created for training. The training set includes input and output data. The input data consists of the efficiency change curves at various operating points, and the output data consists of the corresponding early warning analysis results. The analysis is then performed using the successfully trained intelligent early warning model.

[0104] In one embodiment, early warning analysis is performed based on the efficiency change curves at various operating points, including:

[0105] The efficiency change curve is fitted to obtain the efficiency change function, which is denoted as HY(t), where t is time.

[0106] An efficiency early warning model is established, and its expression is as follows:

[0107] ;

[0108] In the formula: [HY(t)] is the input data, X1 and X2 are thresholds, which are set according to the user's requirements for slope change and cumulative difference, respectively. Generally, multiple simulations can be used to select a threshold X2 that meets the user's requirements; kt represents the slope of the efficiency change function at the corresponding time; the output data is the efficiency warning value QS[HY(t)], and the efficiency warning value is 1, 2 or 0;

[0109] The efficiency change function is analyzed by an efficiency early warning model to obtain the corresponding efficiency early warning value. The early warning analysis result is determined based on the efficiency early warning value. Different efficiency early warning values ​​correspond to different results, and corresponding handling measures can be preset for handling.

[0110] The start-stop management module is used to optimize the start-stop management of the mixed-flow turbine, and to obtain the start-stop records of the mixed-flow turbine in real time. The start-stop records include relevant data such as start-stop time, start-stop reason, and number of times. Various reasons may be related to the start-stop, such as changes in grid demand, equipment failure, protection mechanisms, and operating environment. For example, with the introduction of intermittent energy sources such as wind and solar power, the power supply in the grid becomes more unstable. When the grid load decreases, the turbine may need to reduce its output or even shut down; while when the load increases, it is necessary to start or increase the output of the turbine.

[0111] The start-stop records are identified for their causes, which are then categorized into two types based on whether the frequency of start-stop operations can be reduced through control and management of the mixed-flow turbine: management-related and adjustment-related. Management-related causes, such as grid demand and equipment temperature, can reduce the frequency of start-stop operations by controlling the operation of the mixed-flow turbine. These can be avoided or delayed by pre-emptively adjusting the turbine's control. Adjustment-related causes, such as flow interruption, water quality deterioration, excessively high ambient temperature, and equipment malfunction, cannot be reduced through turbine management alone and require additional adjustments to equipment components. Adjustments to the adjustment-related causes will increase the number of start-stop causes within the management-related categories. Therefore, the management and adjustment categories formed from the start-stop records are dynamically updated.

[0112] Set up corresponding optimized management methods for the start-up and shutdown reasons of the management category, and manage the mixed-flow turbine according to the optimized management methods.

[0113] In one embodiment, the reasons for start-up and shutdown are divided into management and adjustment categories. This can be done according to the above definition and existing methods, such as using intelligent models with deep learning algorithms for intelligent classification, followed by manual confirmation to ensure classification accuracy. Alternatively, since the number of start-up and shutdown reasons is small and they are well-known to professionals, they can also be classified manually.

[0114] In one embodiment, for the start / stop reasons corresponding to the adjustment category, the available improvement solutions can be intelligently analyzed, evaluated and screened based on the user's improvement requirements, such as improvement cost requirements, etc.; and improvements can be made according to the screened improvement solutions.

[0115] In one embodiment, corresponding optimized management methods are set for start-up and shutdown reasons corresponding to management categories. An experimental simulation model capable of simulating the operation of a mixed-flow turbine can be established based on technologies such as digital twins. Various methods for reducing the number of start-ups and shutdowns corresponding to the given start-up and shutdown reasons are analyzed. For example, for major grid demand reasons, the operation of the mixed-flow turbine can be pre-adjusted by predicting grid demand, and optimization adjustments can also be made in conjunction with energy storage systems. Specifically, there are multiple feasible ways to overcome a certain start-up and shutdown reason. Historical operating condition data of the mixed-flow turbine is obtained, mainly including relevant historical start-up and shutdown data for that reason. The determined methods are simulated using the experimental simulation model and historical operating adjustment data to determine the number of simulated start-ups and shutdowns. By performing cyclic simulations and comparing the number of start-ups and shutdowns, the method with the highest priority that can be applied is determined and marked as the optimized management method.

[0116] In one embodiment, an optimized management method is set for the start-up and shutdown reasons corresponding to the management class. With the development of technology, various methods can also be applied to implement the optimized management method for determining the corresponding start-up and shutdown reasons.

[0117] By setting up a start-stop management module, the number of start-stop cycles of the mixed-flow turbine can be intelligently reduced, improving the stability of the mixed-flow turbine, extending its service life, and enhancing the economic benefits of the hydropower station.

[0118] A control method for a mixed-flow turbine, the method comprising:

[0119] Real-time monitoring of the mixed-flow turbine was conducted to obtain monitoring data of the mixed-flow turbine.

[0120] Real-time analysis of monitoring data is performed to determine the power generation efficiency curve of the mixed-flow turbine;

[0121] The optimal operating point is determined in real time based on the power generation efficiency curve, and control commands are generated based on the optimal operating point; the mixed-flow turbine is then controlled and adjusted according to the control commands.

[0122] The system acquires adjustment records of the power generation efficiency curve in real time; classifies the adjustment records according to operating points to obtain the operating efficiency records of the operating points; acquires the standard power generation curve, and generates the efficiency change curve of the operating point based on the standard power generation curve and the operating efficiency records.

[0123] Based on the efficiency change curves of each operating point, early warning analysis is performed to obtain corresponding early warning analysis results, and corresponding early warning processing is carried out based on the early warning analysis results.

[0124] Real-time acquisition of start-up and shutdown records of mixed-flow turbines, and optimization management of start-up and shutdown of mixed-flow turbines based on these records.

[0125] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0126] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An intelligent control system for a mixed-flow turbine, characterized in that, It includes a monitoring module, an efficiency analysis module, a control module, and an anomaly monitoring module; The monitoring module is used to monitor the mixed-flow turbine in real time and obtain monitoring data of the mixed-flow turbine. The efficiency analysis module is used to analyze the monitoring data of the mixed-flow turbine in real time and determine the power generation efficiency curve of the mixed-flow turbine. The vertical axis of the power generation efficiency curve is the power generation efficiency, and the horizontal axis is the operating point. The optimal operating point is determined in real time based on the power generation efficiency curve, and corresponding control commands are generated based on the optimal operating point and sent to the control module. The control module is used to make control adjustments according to the received control commands; The anomaly monitoring module is used to perform anomaly early warning analysis based on the power generation efficiency curve and to obtain the adjustment records of the power generation efficiency curve in real time. The adjustment records are classified according to the operating points to obtain the operating efficiency records of the operating points; a standard power generation curve is obtained, and an efficiency change curve of the operating points is generated based on the standard power generation curve and the operating efficiency records. The horizontal axis of the efficiency change curve is time, and the vertical axis is the efficiency change value. Based on the efficiency change curves of each operating point, early warning analysis is performed to obtain corresponding early warning analysis results, and corresponding early warning processing is carried out based on the early warning analysis results. Determining the power generation efficiency curve includes: Obtain the standard power generation curve; identify the corresponding control parameter items based on the standard power generation curve; acquire material analysis data of the mixed-flow turbine in real time, including historical monitoring data and historical power generation efficiency; Based on the control parameter items, feature identification is performed on the material analysis data to obtain control feature data, which includes control combination features and power generation efficiency features; the control feature data is then classified according to the control combination features to obtain the efficiency-optimized materials corresponding to the control combination features; The efficiency optimization data is analyzed to obtain the power generation adjustment efficiency corresponding to the control combination characteristics; the control combination characteristics and power generation adjustment efficiency are integrated into curve adjustment data; the standard power generation curve is adjusted in real time according to the curve adjustment data to obtain the power generation efficiency curve of the mixed-flow turbine. Analyze materials for efficiency optimization, including: Step SA1: Identify the power generation efficiency features corresponding to the efficiency optimization materials, classify the same power generation efficiency features into one category, and mark them as unit efficiency features; identify the unit value and number of units corresponding to the unit efficiency features, where the number of units is the number of power generation efficiency features contained in the unit efficiency feature, and the unit value is the power generation efficiency corresponding to the unit efficiency feature; Step SA2: Merge any two cell efficiency features with the largest number of cells according to the preset representative merging formula to obtain new cell efficiency features; the representative merging formula is: ； d = d1 + d2; In the formula: L is the unit value of the new unit efficiency feature; L1 and L2 are the unit values ​​of the two unit efficiency features being merged; d1 and d2 are the number of units of the two unit efficiency features being merged; d is the number of units of the new unit efficiency feature. Step SA3: Repeat step SA2 until only one unit efficiency characteristic remains, and determine the power generation adjustment efficiency based on the unit value of the unit efficiency characteristic; The optimal operating point is determined in real time based on the power generation efficiency curve, including: Based on the power generation efficiency curve, identify the operating point corresponding to each power generation efficiency, mark it as the calibration operating point, perform calibration analysis on the calibration operating point, and obtain several preliminary operating points. Identify the highest power generation efficiency among the initial selected operating points and mark the initial selected operating point corresponding to the highest power generation efficiency as the candidate operating point; The selection of operating points is screened to obtain the optimal operating point; Calibration analysis of operating points includes: Identify benchmark operating points based on monitoring data; establish a control calibration model, analyze the benchmark and calibration operating points using the control calibration model, and obtain the calibration results for the calibration operating points, including calibration pass and calibration fail; mark the calibration operating points with calibration pass results as initial selected operating points; the expression of the control calibration model is: ； In the formula: (GK, HK) are the input data, GK is the reference operating point, and HK is the calibration operating point; GK→HK means that the reference operating point can be adjusted to the corresponding calibration operating point through the control module; the output data is the control calibration value KP(GK, HK), and the control calibration value is 1 or 0. The reference operating point and calibration operating point are analyzed by controlling the calibration model to obtain the corresponding control calibration values; When the control calibration value is 1, the calibration result is that the calibration is passed; When the control calibration value is 0, the calibration result is calibration failure; Early warning analysis is performed based on the efficiency change curves at various operating points, including: The efficiency change curve is fitted to obtain the efficiency change function, which is denoted as HY(t), where t is time. An efficiency early warning model is established, and its expression is as follows: ； In the formula: [HY(t)] is the input data, X1 and X2 are both thresholds; kt represents the slope of the efficiency change function at the corresponding time; the output data is the efficiency warning value QS[HY(t)], and the efficiency warning value is 1, 2 or 0; The efficiency change function is analyzed by using an efficiency early warning model to obtain the corresponding efficiency early warning value; the early warning analysis results are determined based on the efficiency early warning value.

2. The intelligent control system for a mixed-flow turbine according to claim 1, characterized in that, Before determining the optimal operating point based on the power generation efficiency curve, the environmental adjustment items are first determined, and environmental adjustment data is obtained through real-time monitoring based on the environmental adjustment items. The environmental adjustment interval data is then determined based on the environmental adjustment interval data and the power generation efficiency curve.

3. The intelligent control system for a mixed-flow turbine according to claim 1, characterized in that, It also includes a start-stop management module, which is used to optimize the start-stop management of the mixed-flow turbine, obtain the start-stop records of the mixed-flow turbine in real time, and the start-stop records include start-stop time, start-stop reason, and start-stop number; identify the start-stop reasons in the start-stop records, and classify the start-stop reasons into management type and adjustment type according to whether the number of start-stops can be reduced by controlling and managing the mixed-flow turbine; Set up corresponding optimized management methods for the start-up and shutdown reasons of the management category, and manage the mixed-flow turbine according to the optimized management methods.

4. A control method for a mixed-flow turbine, characterized in that, The method, applied to an intelligent control system for a mixed-flow turbine as described in any one of claims 1 to 3, comprises: Real-time monitoring of the mixed-flow turbine was conducted to obtain monitoring data of the mixed-flow turbine. Real-time analysis of monitoring data is performed to determine the power generation efficiency curve of the mixed-flow turbine; The optimal operating point is determined in real time based on the power generation efficiency curve, and control commands are generated based on the optimal operating point; the mixed-flow turbine is then controlled and adjusted according to the control commands. The system acquires adjustment records of the power generation efficiency curve in real time; classifies the adjustment records according to operating points to obtain the operating efficiency records of the operating points; acquires the standard power generation curve, and generates the efficiency change curve of the operating point based on the standard power generation curve and the operating efficiency records. Based on the efficiency change curves of each operating point, early warning analysis is performed to obtain corresponding early warning analysis results, and corresponding early warning processing is carried out based on the early warning analysis results. Real-time acquisition of start-up and shutdown records of mixed-flow turbines, and optimization management of start-up and shutdown of mixed-flow turbines based on these records.

Images