198 results about "Online computation" patented technology

The invention relates to the technical field of electric power system regulation and control, and particularly discloses an electric power active balance control method for coupling multi-element energy storage of a coal power unit, which is used for solving the problem that the existing static active safety margin evaluation method cannot evaluate the safety of the coal power unit under the complex working conditions of high wind power penetration, large disturbance, system inertia decline and the like. The method solves the problems that multi-stage frequency response cannot be accurately described, online self-adaptive power distribution and continuous smooth scheduling are lacked, and consequently frequency drop is large, recovery is slow and output suddenly changes, and comprises the steps of building a collaborative characteristic model, calculating dominant characteristics on line, optimizing scheduling in a segmented mode and updating parameters in a closed loop. According to the method, by constructing a hierarchical inertia and multi-stage frequency modulation collaborative model, and adopting multi-scale online feature extraction and adaptive power distribution, segmented gradient optimization scheduling and closed-loop online parameter updating, quick response, smooth connection and accurate optimization of frequency support and economic scheduling in a wind power high-permeability scene are realized.

The invention provides an active load shedding optimization control method, system and device of a wind power plant and a storage medium, and belongs to the technical field of active power control of the wind power plant, and the method comprises the steps: constructing and training an SAC intelligent agent through an SAC algorithm; acquiring a wind power plant state quantity; inputting the state quantity of the wind power plant into the SAC intelligent agent to obtain a vector # imgabs0 # composed of active power initial reference values of all wind turbine generators; inputting the # imgabs 1 # into a constraint controller for secondary calculation to obtain a vector # imgabs 2 # composed of active power optimization reference values of the wind turbine generators; the wind power plant executes # imgabs3 #; and repeating the steps, and adjusting the active power of each wind turbine generator in real time. The model is high in generalization, stability, reliability and learning efficiency, real-time online calculation of the equivalent fatigue load can be achieved, reasonable distribution of the active power of the wind power plant can be achieved under the condition that the active power constraint of the wind power plant is met, the equivalent fatigue load of the whole wind power plant can be reduced, and the maintenance cost can be reduced.

The invention relates to a fault-tolerant task reconstruction and scheduling optimization method for an unmanned aerial vehicle cluster, and relates to the technical field of unmanned aerial vehicle scheduling optimization, and the method comprises the steps: carrying out the rehearsal simulation based on preset cluster task planning in combination with a three-dimensional environment model of a task region, and generating a fault-tolerant plan library; issuing the fault-tolerant plan library to the target unmanned aerial vehicle cluster, executing cluster task planning, and continuously monitoring the global state of the cluster through a hierarchical distributed consensus mechanism; and performing node failure judgment according to the cluster global state, and triggering a fault-tolerant plan library to execute scheduling optimization of the target unmanned aerial vehicle cluster according to a node failure judgment result. According to the method, the problems that in task execution of a traditional unmanned aerial vehicle cluster, communication interruption is easily caused by node disability and obstacle interference, the online calculation amount is large, bandwidth occupation is high, fault-tolerant response delay occurs, and scheduling toughness is insufficient are solved.

The invention belongs to the technical field of equipment state monitoring, and particularly relates to a boiler wall temperature anomaly detection and early warning method based on approximate entropy calculation, which comprises the following steps: dividing a large coal-fired power plant boiler wall temperature time sequence into continuously overlapped sliding windows; calculating three statistical parameters in each sliding window; the three statistical parameters comprise standard deviation, range and approximate entropy; forming a three-dimensional time sequence matrix formed by n groups of parameters based on the three statistical parameters; and performing anomaly detection and early warning on the three-dimensional time sequence matrix by using an isolated forest anomaly detection algorithm. Abnormalities are accurately recognized from different dimensions, and high-dimensional data are efficiently dealt with. The method has the real-time performance and the dynamic performance, online calculation and real-time response can be achieved, the model is flexibly updated along with new data inrush, and the anomaly detection requirement of the dynamic data environment is met.

The invention discloses an on-line estimation method and system suitable for cluster type intelligent electric meter error analysis, and the method comprises the steps: building an intelligent electric meter error on-line calculation model through an energy conservation principle based on the characteristic that most intelligent electric meters are distributed according to a tree topology structure in reality, and solving the model to obtain an error estimation value. On this basis, non-uniformity of error information contained in measurement data in time is considered, a weight coefficient represented by attenuation factors is introduced to construct a loss function of a calculation model, different attenuation factors are adopted according to the condition number of a coefficient matrix to improve the tracking capability of an algorithm, an error estimation value is obtained by deriving the loss function, and the tracking precision of the algorithm is improved. And the error estimation value of the electric energy meter is updated in real time through newly collected data, so that the solving precision of the error estimation value is improved.

Quantizing tensors and vectors processed within a neural network reduces power consumption and may accelerate processing. Quantization reduces the number of bits used to represent a value, where decreasing the number of bits used can decrease the accuracy of computations that use the value. Ideally, quantization is performed without reducing accuracy. Quantization-aware training (QAT) is performed by dynamically quantizing tensors (weights and activations) using optimal clipping scalars. “Optimal” in that the mean squared error (MSE) of the quantized operation is minimized and the clipping scalars define the degree or amount of quantization for various tensors of the operation. Conventional techniques that quantize tensors during training suffer from high amounts of noise (error). Other techniques compute the clipping scalars offline through a brute force search to provide high accuracy. In contrast, the optimal clipping scalars can be computed online and provide the same accuracy as the clipping scalars computed offline.

The invention discloses a multi-modal KV cache retrieval method and system based on a hybrid architecture, relates to the technical field of data processing, and aims to solve the technical problem that in the prior art, due to the adoption of a full-online computing architecture and lack of a unified cross-modal representation framework, the computing efficiency and the modal fusion effect are difficult to consider at the same time. By constructing a hybrid processing architecture of offline pre-calculation and online processing, multi-modal data is subjected to unified fragmentation coding and KV cache and semantic fingerprints of the multi-modal data are pre-calculated in an offline stage, and cache fragments are intelligently assembled and position codes are dynamically remapped based on a user query intention in an online stage; therefore, online repeated calculation of multi-modal content is fundamentally avoided, coherent alignment and efficient fusion of cross-modal semantics are achieved, the real-time response capability, the cache reuse rate and the multi-modal generation quality of the system are remarkably improved, and high-concurrency scenes can be dynamically adapted.

The invention discloses an online identification method for kinetic parameters of a joint type series robot, which comprises the following steps: S1, for a to-be-identified joint type series industrial robot, establishing a robot kinetic model considering friction; s2, linearization is carried out on the joint type series industrial robot dynamic model; s3, designing an optimal excitation track for an identification experiment, and obtaining an excitation track by using five finite Fourier series and solving a constrained nonlinear optimization problem; and S4, the series robot runs the excitation track, meanwhile, the position information of each joint of the robot and the driving current of each joint at each moment are collected, and to-be-identified parameters are calculated on line at each moment. According to the method, online identification of the robot kinetic parameters can be carried out, the identification efficiency of the robot kinetic parameters is improved, and the method can be used for industrial scenes such as robot moving and carrying, polishing and grinding and heavy-load hydraulic pressure.

The invention relates to a reusable rocket landing section fuel optimal conversion time sequence online generation method and device and a medium, and the method mainly comprises the steps: simplifying the complex three-dimensional motion of a rocket vertical landing section into a one-dimensional vertical motion model; establishing a nonlinear equation set which takes the working time of the engine before and after stage conversion as an unknown quantity and enables the rocket to meet the terminal speed and terminal position constraints and the fuel consumption to be optimal; constructing and solving an approximate analytical solution as an initial value of Newton iteration; and based on the obtained initial value, carrying out iterative solution on a double-constraint nonlinear equation set formed by rocket speed and displacement terminal constraint. According to the method, a form based on analytic iteration is adopted, the fuel optimal control in the rocket landing process is realized through real-time online calculation of an engine conversion time sequence and giving of a corresponding thrust adjustment control instruction, and safe and accurate landing is ensured.

The invention belongs to the technical field of multi-vector model predictive control, and provides a calculation-simplified multi-vector model predictive control method and system. The calculation-simplified multi-vector model prediction control method comprises the following steps: carrying out region division on a three-phase space vector diagram to form a plurality of groups of region sets, and enabling each group of region sets to be in one-to-one correspondence with one space vector; searching a plurality of neighbor space vectors for synthesizing the reference space vector according to the region set where the reference space vector is located; on the basis of a converter model, a reference space vector and all searched neighbor space vectors, all on-off state combinations of the converter are calculated on line with the purpose of minimizing the current tracking error of the converter, and no vector coordinate or state combination or other value tables need to be stored in advance; and based on all the calculated switch state combinations of the converter and the voltage control value function, selecting the switch state combination with the minimum capacitance voltage deviation to control the converter so as to realize multi-objective optimization control of the flying voltage and the midpoint voltage.

The invention relates to an online calculation method for the voidage of a dead stock column in an iron notch area of a blast furnace hearth, and belongs to the technical field of blast furnace ironmaking. Comprising the following steps that 1, hearth geometric parameters, molten iron attributes, tapping data and dead stock column state parameters are obtained; 2, the distance between the molten iron liquid level and the tap hole plane at the beginning of tapping and the distance between the molten iron liquid level and the tap hole plane at the end of tapping are calculated; 3, calculating the voidage of the dead stock column; and 4, repeating the steps 1-3, and calculating the voidage of the dead stock column in the next period. According to the method, the blast furnace dead stock voidage is continuously calculated on line through blast furnace tapping data, the voidage of the blast furnace hearth dead stock in the production and operation process is known in real time, and time and labor are saved.

The present invention discloses a method for optimizing the operation control of a centrifugal pump, which includes an offline calculation module and an online calculation module. The offline calculation module establishes a mathematical model of the centrifugal pump system according to the centrifugal pump theory and outputs the offline data of the centrifugal pump system, and constructs an offline database A; through the actually measured head, efficiency and flow rate data, an offline database B is constructed and corrected by an improved BPNN prediction model. The online calculation module, when the output end of the centrifugal pump system changes, triggers the intelligent control system of the centrifugal pump, searches for the control rate online, and judges whether the state parameter threshold is satisfied to perform operation adjustment. The present invention stores the head, flow rate and rotational speed as tree-shaped data, combines the binary tree search algorithm to quickly search for data under different working conditions, realizes real-time monitoring and optimized control; establishes an improved BPNN prediction model for self-data training to correct the problem of inaccurate mathematical model caused by the aging of the centrifugal pump.

The invention provides a virtual reality system for a rock uniaxial compression experiment, and the system comprises an offline calculation module which is used for generating a numerical simulation sample set based on a random simulation scheme generation service and an elastic brittle damage constitutive model driven numerical simulation system; the online calculation module is used for constructing and training a numerical simulation process agent model based on the numerical simulation sample set and the U-Net network; and the mixed reality visualization and interaction module is used for applying the trained numerical simulation process agent model to a mixed reality scene to complete a mixed reality experiment. According to the virtual experiment system provided by the invention, different accurate experiment results can be obtained according to different parameters, meanwhile, real experiment operation experience is obtained, the experiment cost can be greatly saved, and the environmental protection property is improved; the experiment risk is reduced, and the safety is improved; the space-time limitation is broken, and the self-learning enthusiasm of students is stimulated.

The invention discloses a bridge construction facility safety monitoring method and system based on finite element real-time verification. The method comprises the steps that the actually-measured mechanical response value of each structure measuring point is collected in real time; performing finite element calculation on the mechanical response of each structure measuring point through a finite element online calculation program to obtain a reference check value; setting a verification upper limit and a verification lower limit according to the relationship between the reference verification value and the actually measured mechanical response value as a first-layer dynamic threshold value of the actually measured mechanical response value; setting a second-layer static limit threshold value according to the structural material attribute at the measuring point; according to the actually-measured mechanical response value of each structure measuring point, the average change rate of the actually-measured mechanical response value and the reference verification value on the time sequence, the first-layer dynamic verification threshold value and the second-layer static limit threshold value, graded alarm prompting is carried out on the mechanical response condition of each structure measuring point; the operation condition of the facility is judged in time according to the alarm prompt, the abnormal state of the bridge construction facility is found in time, and the potential danger sensing capability of the monitoring system is improved.

The invention discloses an unmanned aerial vehicle wall-attached disturbance suppression method based on strategy optimization, and aims to solve the problems that in the wall-attached flight or operation process of an unmanned aerial vehicle, strategy optimization needs to be updated online, strong constraints such as the minimum safety distance, the attitude angle, the speed and the acceleration are easily violated, airborne computing power is limited, and safety and real-time performance are difficult to consider at the same time. According to the invention, reachability analysis is carried out based on a dynamical model and wall geometry to train a feasible region approximate network so as to construct a safety supervisor, an initial control instruction is generated by adopting a hierarchical strategy, and optimization and correction are carried out under the constraint of a feasible control region to obtain a safety control instruction. Performing event-triggered online updating based on the intervention amount of the safety supervisor, introducing supervision constraint learning which takes a safety control instruction as a supervision target, and replacing a baseline strategy when a candidate strategy meets a switching condition; the technical effects of improving the adherence disturbance suppression capability and reducing the on-line calculation burden on the premise of meeting the safety constraint are achieved.

A system for speech-to-text conversion of passenger announcements on board of an aircraft comprises a cabin management control configured to provide a speech signal related to an announcement to passengers on board of the aircraft; a cabin application server comprising a processing unit configured to convert the speech signal into a text message containing text corresponding to spoken words of the speech signal, wherein the processing unit is configured to convert the speech signal locally without accessing online computing resources; and a network interface configured to provide the text message to at least one passenger device on board of the aircraft.

The invention belongs to the technical field of transformer winding temperature field rapid calculation, and discloses a transformer winding heat flow field calculation method and a related device, working condition data of a transformer winding are obtained, and the working condition data comprise winding current, winding inlet flow velocity and inlet temperature; the working condition data are processed through a trained neural network model, corresponding key physical quantity information of the transformer winding under the working condition data is obtained, and the key physical quantity information comprises temperature distribution of the transformer winding, an oil flow velocity radial component, an oil flow velocity axial component and oil flow internal pressure. The method can meet the requirement for real scene online calculation of the temperature field of the power equipment of the transformer substation, has important application value for state early warning and reliability evaluation of the transformer, and solves the problems that current mainstream multi-physics field numerical calculation software is low in calculation efficiency and difficult to provide technical support for multi-physics field online real scene display of the power equipment.

The invention belongs to the technical field of microstructure and multi-scale structure design, and particularly relates to a microstructure rapid design and filling method and system based on macroscopic strain. Constructing a microstructure topological optimization model based on the macroscopic strain, sampling the macroscopic strain and the volume fraction to generate a corresponding optimized microstructure, and establishing a microstructure training data sample library with labels; carrying out equivalence analysis on a strain energy expression, solving the problem of variable inconsistency by utilizing an intermediate variable, and converting the strain in the training sample into the intermediate variable; establishing a deep neural network with an intermediate variable and a volume fraction as input and a microstructure topological configuration as output, and training the deep neural network by using a data sample to obtain a microstructure fast reverse design network; and carrying out staged multi-scale structure filling design by using the microstructure fast reverse design network. According to the method, the online calculation cost of microstructure and multi-scale structure design can be reduced, and the design efficiency is improved.

The invention relates to the technical field of optical communication intelligent operation and maintenance, in particular to an optical module failure prediction method and device, a storage medium and electronic equipment, and the method comprises the steps: building an optical module failure prediction model for predicting the remaining life of an optical module; inputting monitoring data of the optical module to be tested, wherein the monitoring data comprises performance parameters, configuration parameters and attribute parameters; and calling the optical module failure prediction model to perform online calculation and analysis on monitoring data of a to-be-measured optical module, and outputting a prediction result of the to-be-measured optical module. According to the method, the residual life of the optical module is predicted based on the machine learning modeling technology for the first time, the efficiency and accuracy of failure prediction can be improved, the online intelligent failure prediction function of the optical module can be achieved under the conditions that an existing system structure is not changed and new interfaces and hardware are not added, and the system reliability is improved. The method can be deployed in an existing network management system and is easy to implement.

The invention discloses a leader-following multi-agent path planning algorithm considering task distribution characteristics, which comprises the steps of self-adaptive task clustering, leader path planning and follower path planning, and is characterized in that tasks are grouped by utilizing a self-adaptive clustering method, and then a leader-following two-layer planning mode is adopted, so that the path of the leader-following multi-agent path planning algorithm is obtained; the influence of aggregation conflicts caused by task distribution aggregation is reduced to the minimum, and compared with a conflict-based search method which depends on a conflict detection and rollback strategy, the conflict solving times can be greatly reduced, and the online calculation efficiency of path planning can be improved; differentiated leader paths are generated among the groups, and a similar following strategy is adopted in the groups, so that the search complexity can be remarkably reduced, and high-concentration real-time agent navigation scheduling is realized in a scene with unbalanced large-scale task distribution; according to the self-adaptive task clustering method, grouping is carried out by comprehensively considering the distance and the vector included angle between the tasks, the distribution characteristics of the tasks can be accurately recognized, and clustering is carried out in a self-adaptive mode.

The present invention discloses a method for online identification of the dynamic parameters of an articulated serial robot, comprising the following steps: S1. For the articulated serial industrial robot to be identified, a robot dynamic model that takes friction into account is established; S2. The dynamic model of the articulated serial industrial robot is linearized; S3. An optimal excitation trajectory is designed for the identification experiment, using a five-term finite Fourier series to obtain the excitation trajectory by solving a constrained nonlinear optimization problem; S4. The serial robot runs the excitation trajectory while simultaneously collecting the position information of each joint of the robot and the driving current of each joint at each moment, and online calculating the parameters to be identified at each moment. The present invention can perform online identification of robot dynamic parameters, improves the efficiency of robot dynamic parameter identification, and can be used in industrial scenarios such as robot mobile handling, polishing and grinding, and heavy-load hydraulics.

The application discloses a hand rehabilitation training system and adaptive training method based on brain-muscle coupling and force feedback, comprising a force feedback exoskeleton device, a training task interaction module, an electroencephalogram-electromyogram acquisition module, a synchronous control module, a signal preprocessing and feature extraction module, a brain-muscle coupling analysis module, an adaptive training adjustment module, and a safety constraint and degradation control module. The system is based on a virtual environment, and the user wears the force feedback exoskeleton device to complete the grasping task, and the electroencephalogram and electromyogram signals are synchronously acquired, the brain-muscle coupling indexes of the trial and round are calculated, and the training task difficulty parameters and the force feedback intensity parameters are updated based on the indexes, and the parameter updating process is safety constrained, and the degradation control is executed in abnormal conditions. The application realizes the closed-loop adaptive adjustment of the hand rehabilitation training task difficulty and the force feedback intensity with controllable online calculation, and is helpful to improve the training adaptability and the central-peripheral collaborative training effect.

The invention discloses a judgment feedback method for the selective ore grinding dissociation effect of a stirring mill and a computer system.The judgment feedback method comprises the following steps that S1, a comprehensive evaluation mathematical model Mb of the selective ore grinding dissociation effect is constructed; s2, determining a threshold value T of the mathematical model Mb according to historical field production data or tests; when the Mb value calculated in real time is lower than a threshold value T, the system judges that the current selective ore grinding dissociation effect is poor, and a regulation and control instruction is automatically triggered; and when the Mb value calculated in real time is continuously higher than the threshold value T and is kept stable, the system judges that the current ore grinding effect is good and excessive energy is input, and an energy-saving regulation and control instruction is triggered. According to the method, the comprehensive evaluation value of the ore grinding effect is calculated on line by establishing a comprehensive mathematical model formula Mb, a threshold triggering feedback mechanism is set, key operation parameters of the mill are automatically adjusted, and closed-loop control of evaluation-feedback-regulation is formed.

The present invention provides an online calculation method for the dynamic coupling roll shape of hot rolling, which relates to the field of metallurgical equipment automation, including the forward setting and reverse real-time iteration of the coupled roll shape of each frame, obtaining the deviation curve between the optimal target roll shape and the online predicted roll shape, and using the elastic roll shape and the shifting roll shape to quickly adjust the load roll gap shape on the basis of identifying the original roll shape and the worn roll shape as short-term static factors, while considering the time lag conditions to avoid the previous experience control mode of the roll gap shape of a single factor or a single frame. Therefore, based on complex rolling conditions or rolling rhythms, it is very necessary to perform weighted optimization of each roll shape according to this strategy, which can not only deeply study the coupling degree of the static roll shape, but also facilitate the coupling setting of dynamic factors, so that the associated roll shape parameters can be adjusted in real time according to the actual target requirements, and finally obtain high-quality hot-rolled strip products that meet the shape and size index requirements.

The invention discloses an anti-parameter disturbance bidirectional converter non-linear control method and system, and the method comprises the following steps: building a three-order non-linear dynamic model of a three-phase voltage source converter, defining the reciprocal 1 / Rc of an AC side resistor R and a DC side load resistor in the non-linear dynamic model as an unknown parameter, and calculating the parameter disturbance of the three-order non-linear dynamic model; obtaining a system dynamic equation with parameter uncertainty of the three-phase voltage source converter; designing a state transformation function, linearizing a system dynamic equation, and mapping a state variable x; s30, a tracking error variable is defined as a difference value between the converted state variable and a reference track of the state variable, and the difference value is used for quantifying the deviation between the actual state and the expected state of the system; defining and designing a parameter updating law of the three estimated values, and calculating and updating unknown parameters on line according to the tracking error variable; and designing and calculating a control input law based on the tracking error variable and the three estimated values, and proving the asymptotic stability of the closed-loop system through a Lyapunov function.

An integrated control method for a multi-spacecraft formation system based on predictive behavior control, comprising the following steps: Step S1: Define the global tasks to be executed by the multi-spacecraft formation: formation keeping, movement; local tasks: obstacle avoidance, and then establish a composite task through the way of behavior control projection in the null space; Step S2: Design a trajectory tracker based on decentralized model predictive control to track the reference trajectory; Step S3: Feed the predicted trajectory back to the planning layer for predicting the future task priorities, and extend the single-step planning in the traditional null space to multi-step prediction. Applying this technical solution can obtain a trajectory tracking control problem without task constraints, greatly reducing the online calculation cost. In addition, the predicted information on the future state of the spacecraft is considered in the process of determining the task priorities, making its switching effect more ideal compared with the traditional logic switching method.

The invention discloses a multi-satellite large-scale MIMO (Multiple Input Multiple Output) downlink precoding method and a multi-satellite large-scale MIMO downlink precoding system considering power amplifier nonlinearity. According to the method, different time delays and Doppler frequency shifts of different satellite signals arriving at a user terminal are considered, and pre-compensation is carried out on each satellite sending signal; the input and output characteristics of the satellite side nonlinear power amplifier are modeled by using the polynomial model; establishing an optimization problem to jointly design a precoding vector and a receiving vector; the signal interference noise distortion ratio in the optimization problem considers interference and distortion from other satellites, interference and distortion in the satellite and a noise item; and converting a sum rate maximization problem into a weighted mean square error minimization problem for solving. And a traditional iteration updating step is further mapped into a learnable network layer structure through a deep expansion algorithm, so that the calculation complexity is reduced. Compared with the traditional method, the method provided by the invention is more in line with the actual transmission condition, can improve the system performance and reduce the online calculation overhead, and is suitable for the precoding design in a multi-satellite communication scene.

The invention discloses an online calculation method and analysis system for coupling impedance between multi-feed direct current systems, and belongs to the technical field of high-voltage direct current transmission control. The online calculation method of the coupling impedance is provided for solving the problems that the coupling impedance of a multi-feed direct current system under large-scale new energy access is complex and changeable, and off-line calculation is difficult, and the method further comprises the steps that an equivalent model of the multi-feed high-voltage direct current power transmission system is constructed; on the basis of the equivalent model, the coupling impedance can be calculated in real time to use the electrical quantity in a steady state. The method not only can be used for researching the interactive coupling characteristic in a large power grid, but also can be used for analyzing the risk of an anticipated accident so as to cope with a complex and changeable operation mode of new energy.

The present invention belongs to the technical field of power system analysis, and in particular, relates to a method for rapid and practical online calculation of moment of inertia. The present invention includes a simulation cutting method and a unit accumulation method, and uses the simulation cutting method and the unit accumulation method to calculate the moment of inertia of the system; and also includes: using the simulation cutting method and the unit accumulation method to preliminarily calculate the moment of inertia of different operating modes of the power grid in the same region; using the simulation cutting method and the unit accumulation method to calculate the moment of inertia values ​​of the same power grid, and performing comparative analysis; determining a rapid and practical method for calculating the moment of inertia suitable for the power grid through the functional relationship between the two algorithms. The present invention can quickly calculate the moment of inertia of the system, saving the complex calculation process and a lot of time of simulation calculation. The moment of inertia of a power grid in a certain region can be accurately calculated, and it is highly practical. Different from the previous theoretical algorithms, it is a quantitative analysis, summary, and display of the actual operation mode of the power grid.

The present invention discloses a method and system for online calculation of turbine guide vane leakage, relating to the technical field of operation optimization and maintenance of hydroelectric generator sets. The method comprises collecting historical data of the unit's shutdown process; establishing a relationship between the unit's angular velocity change rate and hydraulic torque to output the unit's guide vane leakage; constructing a database of relationships between head, leakage, and deceleration duration based on the leakage effect; and outputting the unit's leakage using the head value. The method for online calculation of turbine guide vane leakage provided by the present invention outputs the unit's guide vane leakage by establishing a relationship between the unit's angular velocity change rate and hydraulic torque, thereby improving the accuracy of turbine performance analysis and the ease of operation, enhancing the monitoring and diagnosis capabilities of the unit's operating status, and increasing the unit's operating efficiency and reliability. The present invention achieves improved results in terms of the accuracy, reliability, and monitoring efficiency of leakage monitoring and prediction.