A Method for Online Identification of Stall Vortex in Hydraulic Machinery Based on Nonlinear Dynamic Characteristics

Abstract

This invention discloses an online identification method for stall vortices in hydraulic machinery based on nonlinear dynamic characteristics, relating to the field of hydraulic machinery operation monitoring and fault diagnosis. By introducing an empirical formula for the guide vane change rate, the model can distinguish between the "loading" and "unloading" processes, accurately identify the vortex band state on the hysteresis loop, and reduce the dynamic error by more than 80%. Secondly, the empirical formula gives the input of the neural network a clear hydraulic meaning (such as the velocity triangle relationship), avoiding the unreliability of pure black box models. The complex fluid physics laws have been condensed into the empirical formula, and the neural network only needs to process the residual mapping, resulting in extremely fast computation speed, which can be deployed in the local control unit.

Description

Technical Field

[0001] This invention belongs to the field of hydraulic machinery operation monitoring and fault diagnosis, and specifically relates to an online identification method for hydraulic machinery stall vortex based on nonlinear dynamic characteristics. Background Technology

[0002] When hydraulic machinery (such as water turbines and pump-turbines) operates outside their optimal operating range, the water flowing out of the runner outlet often exhibits significant residual vortex flow. When the vortex intensity exceeds a critical value, vortex rupture occurs within the draft tube, forming a spiral stall vortex band. This vortex band induces low-frequency, high-amplitude pressure pulsations, leading to severe unit vibration and even power oscillations throughout the entire hydraulic system.

[0003] In existing technologies, the identification of such vortices mainly relies on two approaches: 1. Computational Fluid Dynamics (CFD) simulation: Although highly accurate, it is computationally time-consuming and cannot meet the needs of real-time online monitoring; 2. Traditional Frequency Domain Analysis (FFT): Performing Fourier transform on the pressure sensor signal. However, when a hydro turbine participates in grid frequency regulation and peak shaving, the operating conditions change extremely rapidly (such as during load shedding), at which time the flow field exhibits strong non-stationarity and hysteresis effects. That is, at the same position when the guide vane opening is open and closed, the state of the vortex band is completely different due to fluid inertia and the historical memory of the flow. Traditional methods cannot identify this dynamic difference, leading to misjudgment by the control system. Summary of the Invention

[0004] To address the problems in related technologies, this invention proposes an online identification method for hydraulic machinery stall vortices based on nonlinear dynamic characteristics, in order to overcome the aforementioned technical problems existing in the existing related technologies.

[0005] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0006] This invention provides an online identification method for stall vortices in hydraulic machinery based on nonlinear dynamic characteristics, comprising the following steps:

[0007] S1. Real-time synchronous acquisition of hydraulic machinery operating parameters, including rotational speed, operating head, guide vane opening, runner blade angle β, and dynamic pressure signal at the tailrace monitoring section. ;

[0008] S2. Preprocess the collected parameters. Based on the similarity law of fluid dynamics, construct a high-dimensional feature vector that can characterize the transient characteristics of the flow field using the proxy variable of swirling intensity and dynamic trend term. ;

[0009] S3, convert the high-dimensional feature vector The input is fed into a pre-trained recurrent neural network model with temporal memory capabilities;

[0010] S4. The neural network model outputs the dimensionless coefficient of the stall vortex intensity at the current moment. and vortex belt precession frequency .

[0011] Preferably, the high-dimensional feature vector in S2 It includes proxy variables for characterizing the swirl intensity of the flow field at the turbine runner outlet. The calculation uses the following formula:

[0012] ;

[0013] in:

[0014] per unit rotational speed, Indicates rotational speed. H Indicates the working head. Unit flow rate; For guide vane opening, The diameter of the wheel; A , B , These are all geometric correction constants determined through model test fitting for specific impeller blade profiles; Q This represents the actual traffic volume.

[0015] This formula is used to approximately quantify the ratio of tangential velocity to axial velocity at the tailrace pipe inlet section without performing full flow field measurements, serving as a physical criterion for neural networks to determine whether a stall vortex has been generated.

[0016] Preferably, the high-dimensional feature vector in S2 It also includes dynamic trend terms for capturing the hysteresis effect of the flow field. Its mathematical expression includes the first derivative of the guide vane opening with respect to time and higher-order coupling terms, as follows:

[0017] ;

[0018] in: This item indicates whether the unit is in a loading (opening degree increased) or unloading (opening degree decreased) state. t Indicates time; For sign functions, and The product term is used to describe the nonlinear offset characteristics of the boundary layer separation point under different adjustment directions.

[0019] By introducing this set of empirical terms, the neural network is able to distinguish the different flow patterns caused by different historical paths under the same guide vane opening.

[0020] Preferably, the preprocessing and construction of high-dimensional feature vectors in S2 include the following steps:

[0021] S21. Use the 3σ criterion or box plot method to identify abnormal points in the speed, working head, guide vane opening, runner blade angle and tailrace pressure signal data, and then supplement or remove them.

[0022] S22. Synchronize and align the sampling time using the pressure pulsation signal as the reference time axis; and unify the sampling frequency through linear resampling or cubic spline interpolation.

[0023] S23. Bandpass filtering is applied to the dynamic pressure signal to remove low-frequency drift and high-frequency electrical noise; for slow variables such as operating parameters, a moving average window smoothing is used.

[0024] S24. Based on the principle of similarity in fluid dynamics, the original physical quantities are converted into dimensionless characteristics; the original physical quantities include rotational speed, flow coefficient, and pressure coefficient.

[0025] S25. Construct transient feature vectors using a sliding time window;

[0026] S26. Normalize or Z-score standardize all features.

[0027] Preferably, the neural network model in S3 adopts a long short-term memory network or a gated recurrent unit architecture, and the state update equation of its hidden layer embeds a regularization term of physical constraints, as follows:

[0028] ;

[0029] in For data fitting error, The proxy variable for the swirl intensity over time t The function, The critical swirl number threshold. is the regularization coefficient; the regularization term is used to force the network to suppress the output of stall vortex intensity when the swirling intensity is below the critical value, thereby incorporating the stability criterion of fluid dynamics into the network training process.

[0030] Preferably, the dimensionless coefficient of the stall vortex intensity The definition adopts a comprehensive empirical formula that includes pressure pulsation energy and resonance risk weights:

[0031] ;

[0032] in: The root mean square value of pressure pulsation predicted by the neural network; The identified vortex frequency. The natural frequency of the hydraulic system; As a resonance-sensitive factor, For fluid density, g The formula quantifies the pressure amplitude of the vortex belt and also weights the degree of harm when the vortex belt frequency approaches the system's natural frequency through an exponential term, thus achieving a comprehensive evaluation of the destructiveness of the stall vortex.

[0033] Preferably, the constant term in the empirical formula is determined through a virtual-physical fusion method, specifically including:

[0034] S41. Obtain the velocity triangle distribution at the runner exit using unsteady CFD calculations;

[0035] S42. Integrate the velocity triangle distribution and perform inverse fitting. Coefficients of the formula and ;

[0036] S43. Correct the weighting coefficient of the dynamic trend term using the actual machine load shedding test data;

[0037] S41 includes the following steps:

[0038] S411. Establish a three-dimensional geometric model of the entire flow channel of the hydraulic machinery, the model including the inlet flow channel, guide vanes, impeller and tailrace flow channel; then perform mesh generation on the three-dimensional geometric model to obtain a computational mesh model;

[0039] S412. Set boundary conditions and the rotational angular velocity of the impeller, and use the separated eddy simulation (DES) model or the scale adaptive simulation (SAS) model to perform unsteady solution and unsteady calculation to obtain three-dimensional transient velocity field data under stable operating conditions.

[0040] S413. Set up a monitoring section at the outlet of the rotor, extract the axial velocity component and tangential velocity component of each time step on the monitoring section; then calculate the circumferential velocity based on the rotor angular velocity and the radius of the monitoring section, and construct an absolute velocity triangle and a relative velocity triangle by combining the axial velocity component and the tangential velocity component.

[0041] S414. Perform time statistics processing on multiple stabilized rotor cycles to obtain the instantaneous distribution and periodic average distribution of the rotor outlet velocity triangle;

[0042] S42 includes the following steps:

[0043] S421. Establish a three-dimensional full-channel numerical calculation model for hydraulic machinery, and use the separated eddy simulation (DES) model or the scale adaptive simulation (SAS) model to perform unsteady numerical calculations to obtain three-dimensional transient flow field data under stable operating conditions.

[0044] S422. Set up a monitoring section at the outlet of the rotor, extract the instantaneous velocity components on the section, including axial velocity and tangential velocity, and calculate the circumferential velocity based on the rotor angular velocity to construct a velocity triangle distribution;

[0045] S423. Perform area-weighted integration on the outlet section of the runner to obtain overall flow characteristic parameters, including mass flow rate weighted average tangential velocity, mass flow rate weighted average axial velocity, and circulation or swirl integral.

[0046] S424. Construct a swirling proxy expression based on the integral results in S423. The expression includes two undetermined coefficients A and B. Based on the numerical calculation results under different operating conditions, calculate the actual swirling intensity parameters or pressure pulsation characteristic parameters, and construct a sample dataset.

[0047] S425. Using the least squares method or regularized regression method, the coefficients A and B in the vortex surrogate expression are backfitted to obtain the optimal coefficient combination.

[0048] S426. Use the fitted swirl proxy expression from S425 for hydraulic machinery operating status assessment or subsequent data-driven model input.

[0049] Preferably, S43 specifically includes: constructing a measured hysteresis loop based on experimental data and calculating the hysteresis loop area; constructing a model hysteresis loop under given initial weighting coefficients; establishing an objective function composed of hysteresis area error and trajectory error; optimizing the pressure change rate weighting coefficient and pressure fluctuation intensity weighting coefficient by minimizing the objective function to obtain the optimal weighting coefficients, so that the model hysteresis loop matches the measured hysteresis loop in terms of area, shape and evolution trend, thereby improving stall identification accuracy.

[0050] Preferably, the controller receives the identified Value, when When the preset threshold is exceeded, the opening of the air supply valve is adjusted according to the following nonlinear control law. ;

[0051] ;

[0052] in It is a proportionality coefficient, corresponding to the direct contribution of the current vorticity state to aerodynamics and torque; It is a differential coefficient, corresponding to the contribution of the vorticity state change rate to aerodynamics and torque;

[0053] The control law is used to utilize the identified vortex intensity and its rate of change, and in accordance with... As a gain scheduling factor, it enables adaptive suppression of strong stall vortex conditions.

[0054] An online identification system for stall vortices in hydraulic machinery based on nonlinear dynamic characteristics includes a hydraulic machinery operating parameter acquisition module, a high-dimensional feature vector construction module, and a stall vortex intensity-vortex band precession frequency output module.

[0055] The hydraulic machinery operating parameter acquisition module is used to collect the operating parameters of the hydraulic machinery in real time, including rotational speed, working head, guide vane opening, runner blade angle, and dynamic pressure signal of the tailrace pipe monitoring section.

[0056] The high-dimensional feature vector construction module is used to construct high-dimensional feature vectors based on the data collected by the hydraulic machinery operating parameter acquisition module.

[0057] The stall vortex intensity-vortex precession frequency output module is used to input high-dimensional feature vectors into a pre-trained recurrent neural network model with time-series memory function, and output the dimensionless coefficient of stall vortex intensity and vortex precession frequency at the current moment.

[0058] The present invention has the following beneficial effects:

[0059] 1. By introducing an empirical formula for the guide vane change rate, the model can distinguish between the "loading" and "unloading" processes, accurately identify the vortex band state on the hysteresis loop, and reduce the dynamic error by more than 80%. Secondly, the empirical formula makes the input of the neural network have clear hydraulic meaning (such as velocity triangle relationship), avoiding the unreliability of pure black box models. The complex fluid physics laws have been condensed into the empirical formula, and the neural network only needs to process the residual mapping, which has a very fast computing speed and can be deployed in the local control unit.

[0060] 2. Compared with ordinary BP neural networks that do not incorporate empirical formulas, the method of this invention significantly reduces the recognition error in the dynamic transition process and successfully reproduces the figure-eight hysteresis loop of pressure pulsation as the guide vane opening changes.

[0061] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0062] To more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is a flowchart illustrating the online identification method for stall vortices in hydraulic machinery based on nonlinear dynamic characteristics according to the present invention. Detailed Implementation

[0064] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0065] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0066] Example 1

[0067] Please see Figure 1 This embodiment is an online identification method for stall vortices in hydraulic machinery based on nonlinear dynamic characteristics, including the following steps:

[0068] S1. Real-time synchronous acquisition of hydraulic machinery operating parameters, including rotational speed, operating head, guide vane opening, runner blade angle, and dynamic pressure signal at the tailrace monitoring section. ;

[0069] S2. Preprocess the collected parameters. Based on the similarity law of fluid dynamics, construct a high-dimensional feature vector that can characterize the transient characteristics of the flow field using the proxy variable of swirling intensity and dynamic trend term. ;

[0070] The preprocessing and construction of high-dimensional feature vectors described in S2 include the following steps: S21, processing the real-time acquired rotational speed, working head, guide vane opening, impeller blade angle, and tailrace pressure signals.

[0071] Initial screening is performed; specifically, outliers are identified using the 3σ criterion or box plot method; when the continuous missing time is less than 5 sampling periods, linear interpolation is used to fill in the gaps; if it exceeds this threshold, the data segment is discarded. A typical setting is: outlier threshold coefficient k=3;

[0072] S22. Due to differences in sampling frequencies among different sensors, synchronization alignment is first performed using the pressure pulsation signal as the reference time axis; then, the sampling frequency is unified through linear resampling or cubic spline interpolation. For hydraulic machinery pressure pulsation analysis, a typical setup is... =10~20 ;in =n / 60 is the rotation frequency, to ensure sufficient capture of the leaf frequency and its harmonic components;

[0073] S23. Perform bandpass filtering on the dynamic pressure signal; the filtering range is generally set to 0.2. ~20 To remove low-frequency drift and high-frequency electrical noise, a fourth-order Butterworth filter can be used. For slow variables such as operating parameters, a moving average window smoothing method is used, with a recommended window length of L = 5 to 10 time steps.

[0074] S24. Based on the principle of similarity in fluid dynamics, the original physical quantities are converted into dimensionless characteristics to reduce the scale differences between different working conditions. For example:

[0075] Unit speed:

[0076] ;

[0077] Flow coefficient:

[0078] ;

[0079] Pressure coefficient:

[0080] ;

[0081] Where D is the diameter of the wheel. Indicates rotational speed. Indicates the working head. Where ρ is the fluid density and p is the fluid pressure; if the flow rate cannot be directly obtained... Q Empirical characteristic curves can be used to estimate this;

[0082] S25. Construct transient feature vectors using a sliding time window; let the window length be... Step size is Then the first t The time input is:

[0083] ;

[0084] Commonly used in engineering =1 to 3 wheel cycles to ensure complete dynamic and static interference information is included; Indicates the angle of the impeller blades; Representing dynamic signals, these are dynamic data reflecting the operating status of the equipment. t Representing the current moment, The length of the sliding time window is typically 1 to 3 wheel cycles in engineering to cover the complete interference process between the moving and stationary components; Formula Indicates from Time's up t A sequence of dynamic signals within a continuous time range of a given moment; For guide vane opening;

[0085] S26. To improve the training stability of recurrent neural networks, perform Min–Max normalization or Z-score standardization on all features:

[0086] ;

[0087] in, This represents the result of normalization or standardization, where μ is the mean of the training set and σ is the standard deviation of the training set; μ and σ are obtained from the training set statistics and remain consistent during the validation and testing phases.

[0088] The high-dimensional feature vectors mentioned in S2 It includes proxy variables for characterizing the swirl intensity of the flow field at the turbine runner outlet. The calculation uses the following formula:

[0089] ;

[0090] in:

[0091] per unit rotational speed, Indicates rotational speed. H Indicates the working head. Unit flow rate; The diameter of the wheel; A , B , These are all geometric correction constants determined through model test fitting for specific impeller blade profiles; Q This represents the actual traffic volume.

[0092] This formula is used to approximately quantify the ratio of tangential velocity to axial velocity at the tailrace pipe inlet section without performing full flow field measurements, serving as a physical criterion for neural networks to determine whether a stall vortex has been generated.

[0093] The high-dimensional feature vectors mentioned in S2 It also includes dynamic trend terms for capturing the hysteresis effect of the flow field. Its mathematical expression includes the first derivative of the guide vane opening with respect to time and higher-order coupling terms, as follows:

[0094] ;

[0095] in: This item indicates whether the unit is in a loading (opening degree increased) or unloading (opening degree decreased) state. t Indicates time; For sign functions, and The product term is used to describe the nonlinear offset characteristics of the boundary layer separation point under different adjustment directions.

[0096] By introducing this set of empirical terms, the neural network is able to distinguish the different flow patterns caused by different historical paths under the same guide vane opening.

[0097] S3, convert the high-dimensional feature vector The high-dimensional feature vector is input into a pre-trained recurrent neural network model with temporal memory; After being input into a pre-built recurrent neural network model, the sample data is first normalized, and training and validation sets are constructed in time series order. The hidden state of the network at time t is determined by the current input vector and the hidden state at the previous time step, thus achieving the memorization of historical information and dynamic feature extraction. During the training phase, backpropagation is used to optimize the network parameters through a time-series algorithm: first, forward propagation is performed to obtain the predicted output, then a loss function is constructed based on the error between the predicted value and the true label, and finally, the gradient is calculated by expanding the network structure along the time dimension.

[0098] To improve model convergence stability, adaptive optimization algorithms such as Adam are typically used to update weight parameters, and a learning rate decay strategy is implemented to avoid oscillations and overfitting. Simultaneously, Dropout regularization is introduced during training to enhance the model's generalization ability, and an early stopping mechanism is used to monitor changes in validation set loss, terminating training when model performance no longer improves. Finally, the trained RNN model is used to predict new time-series inputs, achieving dynamic estimation of target flow field features or performance parameters.

[0099] The neural network model described in S3 employs a long short-term memory network or a gated recurrent unit architecture, and its hidden layer state update equations embed regularization terms based on physical constraints, as follows:

[0100] ;

[0101] in For data fitting error, The proxy variable for the swirl intensity over time t The function, The critical swirl number threshold. is the regularization coefficient; the regularization term is used to force the network to suppress the output of stall vortex intensity when the swirling intensity is below the critical value, thereby incorporating the stability criterion of fluid dynamics into the network training process;

[0102] S4. The neural network model outputs the dimensionless coefficient of the stall vortex intensity at the current moment. and vortex belt precession frequency This enables real-time identification of stall vortices;

[0103] The dimensionless coefficient of stall vortex intensity The definition adopts a comprehensive empirical formula that includes pressure pulsation energy and resonance risk weights:

[0104] ;

[0105] in: The root mean square value of pressure pulsation predicted by the neural network; The identified vortex frequency. The natural frequency of the hydraulic system; As a resonance-sensitive factor, For fluid density, g The formula quantifies the pressure amplitude of the vortex belt and also weights the degree of harm when the vortex belt frequency approaches the system's natural frequency through an exponential term, thus achieving a comprehensive evaluation of the destructiveness of the stall vortex.

[0106] The constant term in the empirical formula is determined through a virtual-physical fusion approach, specifically including:

[0107] S41. Obtain the velocity triangle distribution at the runner exit using unsteady CFD calculations;

[0108] S42. Integrate the velocity triangle distribution and perform inverse fitting. Coefficients of the formula and ;

[0109] S43. Correct the weighting coefficient of the dynamic trend term using the actual machine load shedding test data;

[0110] S41 includes the following steps:

[0111] S411. Establish a three-dimensional geometric model of the entire flow channel of the hydraulic machinery, the model including the inlet flow channel, guide vanes, impeller and tailrace flow channel; then perform mesh generation on the three-dimensional geometric model to obtain a computational mesh model;

[0112] S412. Set boundary conditions and the rotational angular velocity of the impeller, and use the separated eddy simulation (DES) model or the scale adaptive simulation (SAS) model to perform unsteady solution and unsteady calculation to obtain three-dimensional transient velocity field data under stable operating conditions.

[0113] S413. Set up a monitoring section at the outlet of the rotor, extract the axial velocity component and tangential velocity component of each time step on the monitoring section; then calculate the circumferential velocity based on the rotor angular velocity and the radius of the monitoring section, and construct an absolute velocity triangle and a relative velocity triangle by combining the axial velocity component and the tangential velocity component.

[0114] S414. Perform time statistics processing on multiple stabilized rotor cycles to obtain the instantaneous distribution and periodic average distribution of the rotor outlet velocity triangle;

[0115] S42 includes the following steps:

[0116] S421. Establish a three-dimensional full-channel numerical calculation model for hydraulic machinery, and use the separated eddy simulation (DES) model or the scale adaptive simulation (SAS) model to perform unsteady numerical calculations to obtain three-dimensional transient flow field data under stable operating conditions.

[0117] S422. Set up a monitoring section at the outlet of the rotor, extract the instantaneous velocity components on the section, including axial velocity and tangential velocity, and calculate the circumferential velocity based on the rotor angular velocity to construct a velocity triangle distribution;

[0118] S423. Perform area-weighted integration on the outlet section of the runner to obtain overall flow characteristic parameters, including mass flow rate weighted average tangential velocity, mass flow rate weighted average axial velocity, and circulation or swirl integral.

[0119] S424. Construct a swirling proxy expression based on the integral results in S423. The expression includes two undetermined coefficients A and B. Based on the numerical calculation results under different operating conditions, calculate the actual swirling intensity parameters or pressure pulsation characteristic parameters, and construct a sample dataset.

[0120] S425. Using the least squares method or regularized regression method, the coefficients A and B in the vortex surrogate expression are backfitted to obtain the optimal coefficient combination.

[0121] S426. Use the fitted swirl proxy expression from S425 for hydraulic machinery operation status assessment or subsequent data-driven model input.

[0122] S43 specifically includes: constructing a measured hysteresis loop based on experimental data and calculating the hysteresis loop area; constructing a model hysteresis loop under given initial weighting coefficients; establishing an objective function composed of hysteresis area error and trajectory error; optimizing the pressure change rate weighting coefficient and pressure fluctuation intensity weighting coefficient by minimizing the objective function to obtain the optimal weighting coefficients, so that the model hysteresis loop matches the measured hysteresis loop in terms of area, shape and evolution trend, thereby improving stall identification accuracy;

[0123] The controller receives the identified Value, when When the preset threshold is exceeded, the opening of the air supply valve is adjusted according to the following nonlinear control law. ;

[0124] ;

[0125] in It is a proportionality coefficient, corresponding to the direct contribution of the current vorticity state to aerodynamics and torque; It is a differential coefficient, corresponding to the contribution of the vorticity state change rate to aerodynamics and torque;

[0126] The control law is used to utilize the identified vortex intensity and its rate of change, and in accordance with... As a gain scheduling factor, it enables adaptive suppression of strong stall vortex conditions;

[0127] For example, take a mixed-flow turbine with a single unit capacity of 200MW.

[0128] SCADA data acquisition system with 100 Frequency acquisition guide vane opening Rotation speed The pressure pulsation signals at the inlet of the volute and the tailrace cone section.

[0129] To enable neural networks to understand the physical mechanisms of hydraulics, instead of using the raw data directly, the following empirical features are calculated:

[0130] Cyclone scalar proxy quantity Theoretically, the formation of vortex bands in the tailrace depends on the number of swirls. ;

[0131] ;

[0132] in For the projected length, From a basic perspective, this formula reflects that: the higher the unit rotational speed, the smaller the unit flow rate, and the larger the guide vane angle (under a specific geometry), the larger the tangential component of the fluid relative to the axial component, and the easier it is to form vortices.

[0133] Hysteresis indicator: The turbine is shedding load ( When ), the guide vanes close rapidly. At this point, the fluid inertia is extremely high, and the collapse of the vortex band lags behind the guide vane movement. During the start-up process ( The formation of vortex zones follows different pathways; among them, The rate of change of the guide vane opening (time derivative) reflects whether the guide vane is open or closed, and how fast it changes; therefore, it has the following structural features:

[0134] ;

[0135] These two features clearly inform the neural network of its current adjustment direction and degree of nonlinearity, enabling it to accurately predict hysteresis.

[0136] The upper and lower branches of the ring;

[0137] The neural network model is designed using a 3-layer LSTM network structure;

[0138] Input layer: Contains the values ​​calculated using the above empirical formula. and basic parameters and according to ;

[0139] Calculated dynamic trend term The dynamic trend item It consists of changes in operating parameters and is used to characterize the direction of change in the operating path, thereby depicting the hysteresis effect of the flow field.

[0140] Hidden Layers: Two LSTM layers are set up, each with 32 nodes. The "gating" mechanism of the LSTM cells can effectively store the historical state information of the flow (time constant of about 2-5 seconds), perfectly matching the hysteresis effect caused by the inertia of water flow.

[0141] Output layer: Output vortex band intensity (Linked to pressure pulsation amplitude normalization) and frequency .

[0142] This project utilizes CFD transient simulation data (using the SAS turbulence model to simulate the load shedding process) for pre-training, and then combines it with three months of on-site measured data from the power plant for fine-tuning. ).

[0143] Results Comparison: Compared with the ordinary BP neural network without the introduction of empirical formulas, the recognition error of the method of the present invention in the dynamic transition process is reduced from 18% to less than 3%, and the figure-eight hysteresis loop of pressure pulsation with the change of guide vane opening is successfully reproduced.

[0144] Example 2

[0145] This embodiment discloses an online identification system for stall vortices in hydraulic machinery based on nonlinear dynamic characteristics. The system can implement the method of the above embodiment and includes a hydraulic machinery operating parameter acquisition module, a high-dimensional feature vector construction module, and a stall vortex intensity-vortex band precession frequency output module.

[0146] The hydraulic machinery operating parameter acquisition module is used to collect the operating parameters of the hydraulic machinery in real time, including rotational speed, working head, guide vane opening, runner blade angle, and dynamic pressure signal of the tailrace pipe monitoring section.

[0147] The high-dimensional feature vector construction module is used to construct high-dimensional feature vectors based on the data collected by the hydraulic machinery operating parameter acquisition module.

[0148] The stall vortex intensity-vortex precession frequency output module is used to input high-dimensional feature vectors into a pre-trained recurrent neural network model with time-series memory function, and output the dimensionless coefficient of stall vortex intensity and vortex precession frequency at the current moment.

[0149] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0150] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present invention.

Claims

1. A method for online identification of stall vortices in hydraulic machinery based on nonlinear dynamic characteristics, characterized in that, Includes the following steps: S1. Real-time synchronous acquisition of hydraulic machinery operating parameters, including rotational speed, operating head, guide vane opening, runner blade angle, and dynamic pressure signal at the tailrace monitoring section. ; S2. Preprocess the collected parameters. Based on the similarity law of fluid dynamics, construct a high-dimensional feature vector that can characterize the transient characteristics of the flow field using the proxy variable of swirling intensity and dynamic trend term. ; The high-dimensional feature vector It includes proxy variables for characterizing the swirl intensity of the flow field at the turbine runner outlet. The calculation uses the following formula: ； in: per unit rotational speed, H represents the rotational speed, and H represents the operating head. Unit flow rate; For guide vane opening, Where A is the diameter of the rotating wheel; B, All of these are geometric correction constants determined through model tests for specific impeller blade profiles; Q is the actual flow rate. The high-dimensional feature vector It also includes dynamic trend terms for capturing the hysteresis effect of the flow field. Its mathematical expression includes the first derivative of the guide vane opening with respect to time and higher-order coupling terms, as follows: ； in: This field indicates whether the unit is in a loading or unloading state. t Indicates time; For sign functions, and The product term is used to describe the nonlinear offset characteristics of the boundary layer separation point under different adjustment directions; S3, convert the high-dimensional feature vector The input is fed into a pre-trained recurrent neural network model with temporal memory capabilities; The neural network model employs a long short-term memory network or a gated recurrent unit architecture, and its hidden layer state update equations embed regularization terms based on physical constraints, as follows: in For data fitting error, The proxy variable for the swirl intensity over time t The function, The critical swirl number threshold. is the regularization coefficient; the regularization term is used to force the network to suppress the output of stall vortex intensity when the vortex intensity is below a critical value; S4. The neural network model outputs the dimensionless coefficient of the stall vortex intensity at the current moment. and vortex belt precession frequency .

2. The method for online identification of hydraulic machinery stall vortex based on nonlinear dynamic characteristics according to claim 1, characterized in that, The preprocessing and construction of high-dimensional feature vectors described in S2 include the following steps: S21. Use the 3σ criterion or box plot method to identify abnormal points in the speed, working head, guide vane opening, runner blade angle and tailrace pressure signal data, and then supplement or remove them. S22. Synchronize and align the sampling time with the pressure pulsation signal as the reference time axis, and unify the sampling frequency through linear resampling or cubic spline interpolation. S23. Bandpass filtering is applied to the dynamic pressure signal to remove low-frequency drift and high-frequency electrical noise; for slow variables such as operating parameters, a moving average window smoothing is used. S24. Based on the principle of similarity in fluid dynamics, the original physical quantities are converted into dimensionless characteristics; the original physical quantities include rotational speed, flow coefficient, and pressure coefficient. S25. Construct transient feature vectors using a sliding time window; S26. Normalize or Z-score standardize all features.

3. The method for online identification of hydraulic machinery stall vortex based on nonlinear dynamic characteristics according to claim 1, characterized in that, The dimensionless coefficient of stall vortex intensity The definition adopts a comprehensive empirical formula that includes pressure pulsation energy and resonance risk weights: in: The root mean square value of pressure pulsation predicted by the neural network; The identified vortex frequency. The natural frequency of the hydraulic system; As a resonance-sensitive factor, For fluid density, g This is the acceleration due to gravity.

4. The method for online identification of hydraulic machinery stall vortex based on nonlinear dynamic characteristics according to claim 3, characterized in that, The constant term in the empirical formula is determined through a virtual-physical fusion approach, specifically including: S41. Obtain the velocity triangle distribution at the runner exit using unsteady CFD calculations; S42. Integrate the velocity triangle distribution and perform inverse fitting. Coefficients of the formula and ; S43. Correct the weighting coefficient of the dynamic trend term using the actual machine load shedding test data; S41 includes the following steps: S411. Establish a three-dimensional geometric model of the entire flow channel of the hydraulic machinery, the model including the inlet flow channel, guide vanes, impeller and tailrace flow channel; then perform mesh generation on the three-dimensional geometric model to obtain a computational mesh model; S412. Set boundary conditions and the rotational angular velocity of the impeller, and use the separated eddy simulation (DES) model or the scale adaptive simulation (SAS) model to perform unsteady solution and unsteady calculation to obtain three-dimensional transient velocity field data under stable operating conditions. S413. Set up a monitoring section at the outlet of the rotor, extract the axial velocity component and tangential velocity component of each time step on the monitoring section; then calculate the circumferential velocity based on the rotor angular velocity and the radius of the monitoring section, and construct an absolute velocity triangle and a relative velocity triangle by combining the axial velocity component and the tangential velocity component. S414. Perform time statistics processing on multiple stabilized rotor cycles to obtain the instantaneous distribution and periodic average distribution of the rotor outlet velocity triangle; S42 includes the following steps: S421. Establish a three-dimensional full-channel numerical calculation model for hydraulic machinery, and use the separated eddy simulation (DES) model or the scale adaptive simulation (SAS) model to perform unsteady numerical calculations to obtain three-dimensional transient flow field data under stable operating conditions. S422. Set up a monitoring section at the outlet of the rotor, extract the instantaneous velocity components on the section, including axial velocity and tangential velocity, and calculate the circumferential velocity based on the rotor angular velocity to construct a velocity triangle distribution; S423. Perform area-weighted integration on the outlet section of the runner to obtain overall flow characteristic parameters, including mass flow rate weighted average tangential velocity, mass flow rate weighted average axial velocity, and circulation or swirl integral. S424. Construct a swirling proxy expression based on the integral results in S423. The expression includes two undetermined coefficients A and B. Based on the numerical calculation results under different operating conditions, calculate the actual swirling intensity parameters or pressure pulsation characteristic parameters, and construct a sample dataset. S425. Using the least squares method or regularized regression method, the coefficients A and B in the vortex surrogate expression are backfitted to obtain the optimal coefficient combination. S426. Use the fitted swirl proxy expression from S425 for hydraulic machinery operating status assessment or subsequent data-driven model input.

5. The method for online identification of hydraulic machinery stall vortex based on nonlinear dynamic characteristics according to claim 4, characterized in that, S43 specifically includes: constructing a measured hysteresis loop based on experimental data and calculating the hysteresis loop area; constructing a model hysteresis loop under given initial weighting coefficients; establishing an objective function composed of hysteresis area error and trajectory error; optimizing the pressure change rate weighting coefficient and pressure fluctuation intensity weighting coefficient by minimizing the objective function to obtain the optimal weighting coefficients, so that the model hysteresis loop matches the measured hysteresis loop in terms of area, shape and evolution trend.

6. The method for online identification of hydraulic machinery stall vortex based on nonlinear dynamic characteristics according to claim 5, characterized in that, The controller receives the identified Value, when When the preset threshold is exceeded, the opening of the air supply valve is adjusted according to the following nonlinear control law. ; ； in It is a proportionality coefficient, corresponding to the direct contribution of the current vorticity state to aerodynamics and torque; It is a differential coefficient, corresponding to the contribution of the vorticity state change rate to aerodynamics and torque; The control law is used to utilize the identified vortex intensity and its rate of change, and in accordance with... As a gain scheduling factor, it enables adaptive suppression of strong stall vortex conditions.

7. A system for implementing the online identification method for hydraulic machinery stall vortex based on nonlinear dynamic characteristics as described in any one of claims 1-6, characterized in that: It includes a hydraulic machinery operating parameter acquisition module, a high-dimensional feature vector construction module, and a stall vortex intensity-vortex band precession frequency output module; The hydraulic machinery operating parameter acquisition module is used to collect the operating parameters of the hydraulic machinery in real time, including rotational speed, working head, guide vane opening, runner blade angle, and dynamic pressure signal of the tailrace pipe monitoring section. The high-dimensional feature vector construction module is used to construct high-dimensional feature vectors based on the data collected by the hydraulic machinery operating parameter acquisition module. The stall vortex intensity-vortex precession frequency output module is used to input high-dimensional feature vectors into a pre-trained recurrent neural network model with time-series memory function, and output the dimensionless coefficient of stall vortex intensity and vortex precession frequency at the current moment.

Images