A method and system for optimizing the operation of power equipment based on digital twin

Abstract

The present invention relates to the technical field of equipment operation optimization, and specifically, to a method and system for optimizing the operation of power equipment based on digital twin. The method includes the following steps: collecting the operation data of physical power equipment through sensors; constructing a digital twin model of the power equipment using the modeling software Simulink based on the operation data; establishing a two-way data stream from the physical power equipment to the digital twin model and from the digital twin model back to the physical power equipment for data synchronization; using the particle filter algorithm to perform state estimation on the synchronized digital twin model, and introducing a physical degradation model of equipment aging during the state estimation process; and optimizing the operation status of the equipment based on the estimated state through the particle swarm optimization algorithm. The design of the present invention can monitor the operation status of power equipment in real time by constructing a digital twin model synchronized with the physical power equipment and using the particle filter algorithm for accurate state estimation.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment operation optimization, and more specifically, to a method and system for optimizing the operation of power equipment based on digital twin. Background Art

[0002] Traditional operation and maintenance of power equipment usually rely on regular inspections and reactive repairs after faults occur. This method cannot predict potential faults, may lead to sudden equipment downtime, increase maintenance costs and time, and reduce the reliability of the system; as the complexity and scale of the power grid continue to expand, it becomes increasingly difficult to efficiently and finely manage power equipment. Traditional methods often lack sufficient data support to make optimal decisions, resulting in low resource utilization efficiency; power equipment will experience natural aging during long-term use, which will affect its performance. If these factors are not considered, it may lead to inaccurate state estimation, which in turn affects the safety and efficiency of the equipment; power equipment will experience natural aging during long-term use, which will affect its performance. If these factors are not considered, it may lead to inaccurate state estimation, which in turn affects the safety and efficiency of the equipment. Therefore, a method and system for optimizing the operation of power equipment based on digital twin are provided. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for optimizing the operation of power equipment based on digital twin, so as to solve the problems of lack of real-time monitoring and predictive maintenance of traditional power equipment, difficulty in achieving refined management, and being affected by equipment aging and performance degradation as mentioned in the above background art.

[0004] To achieve the above purpose, the present invention provides a method for optimizing the operation of power equipment based on digital twin, including:

[0005] S1. Collect the operation data of physical power equipment through sensors;

[0006] S2. Build a digital twin model of the power equipment based on the operation data using the modeling software Simulink;

[0007] S3. Establish a two-way data flow from the physical power equipment to the digital twin model and from the digital twin model back to the physical power equipment for data synchronization;

[0008] S4. Use the particle filter algorithm to perform state estimation on the synchronized digital twin model, and introduce a physical degradation model of equipment aging during the state estimation process;

[0009] S5. Optimize the operation status of the equipment based on the estimated state through the particle swarm optimization algorithm.

[0010] As a further improvement of this technical solution, in S1, the operation data of the power equipment includes: current , voltage , rotational speed .

[0011] As a further improvement of this technical solution, in S2, a digital twin model of the power equipment is constructed using the modeling software Simulink based on the operation data, including the following steps:

[0012] S2.1. Preprocess the collected operation data of the power equipment;

[0013] S2.2. Import the collected current, voltage, and rotational speed data through the input module of Simulink;

[0014] S2.3. Construct a digital twin model of the power equipment in Simulink.

[0015] As a further improvement of this technical solution, in S2.3, the digital twin model of the power equipment is:

[0016] Electrical dynamic equation:

[0017] ;

[0018] Mechanical dynamics equation:

[0019] ;

[0020] Among them, represents resistance; represents inductance; represents capacitance; represents instantaneous torque; represents the rotational speed of the power equipment; represents moment of inertia; represents damping coefficient; represents time; represents the differential symbol.

[0021] As a further improvement of this technical solution, in S3, a two-way data stream from the physical device to the digital twin model and from the digital twin model back to the physical device is established for data synchronization, including the following steps:

[0022] S3.1. Transmit the collected operation data to the digital twin platform through the communication protocol:

[0023] ;

[0024] Among them, represents time Operating data transmitted from physical power equipment to the digital twin model;

[0025] S3.2. After receiving the operating data from the physical power equipment, parse the communication protocol and convert the operating data into a format acceptable to the Simulink model ;

[0026] S3.3. Input the parsed data into the digital twin model to update the state variables of the digital twin model.

[0027] As a further improvement of this technical solution, in step S4, use the particle filter algorithm to perform state estimation on the synchronized digital twin model, including the following steps:

[0028] S4.1. Generate a set of initial particles based on the historical power equipment state information:

[0029] ;

[0030] Among them, represents the initial state of the th particle, represents the covariance matrix of the initial state represents the particle index, represents the initial state of the power equipment;

[0031] S4.2. At each moment use the state transition equation of the system to predict the state of each particle;

[0032] S4.3. According to the real-time observation data received from the physical device and already converted into a format acceptable to the model , update the weight of each particle through the measurement model:

[0033] ;

[0034] Among them, represents the predicted observation value at time ; represents the mapping function from the state vector of the power equipment to the observation data; represents the observation noise; represents the state vector of the power equipment;

[0035] S4.4. Based on the observation value, update the weight of the particle :

[0036] ;

[0037] Among them, represents the observation likelihood function;

[0038] S4.5. At each moment , calculate the state estimation of the power equipment by weighted average. For the aging of the power equipment, introduce the physical degradation model of equipment aging into the weighted average calculation, and further optimize the weighted average calculation for the insulation deterioration of the power equipment components.

[0039] As a further improvement of this technical solution, in S4.5, the state estimation of the equipment calculated by weighted average is:

[0040] ;

[0041] where represents the state estimation of the power equipment at moment ; represents the state of the th particle at moment ; represents the weight of the th particle at moment ; represents the total number of particles;

[0042] For the aging of the power equipment, introduce the physical degradation model of equipment aging into the weighted average calculation:

[0043] ;

[0044] where represents the state estimation after introducing the physical degradation model of equipment aging; represents the power equipment aging coefficient; represents the physical degradation model of equipment aging;

[0045] For the insulation deterioration of the power equipment components, further optimize the weighted average calculation:

[0046] ;

[0047] where represents the further optimized state estimation; represents the insulation deterioration coefficient; represents the th particle's insulation deterioration function at moment .

[0048] As a further improvement of this technical solution, in S5, based on the estimated state, optimize the operating condition of the equipment through the particle swarm optimization algorithm, including the following steps:

[0049] S5.1. Determine the particle swarm size And the maximum number of iterations ;

[0050] S5.2. Initialize the position and velocity of each particle, and initialize the individual optimal position and the global optimal position of each particle;

[0051] S5.3. Construct a fitness function in combination with the state estimation of power equipment, and optimize the fitness function considering the spatial position of power equipment;

[0052] S5.4. Update the particle velocity and position and calculate the new fitness value of the current particle ;

[0053] S5.5. Update the individual and global optima:

[0054] If , then update the individual optimum:

[0055] ;

[0056] If , then update the global optimum:

[0057] ;

[0058] S5.6. Judge whether the maximum number of iterations is reached ;

[0059] S5.7. Adjust the operating parameters of the power equipment according to the final global optimal position to make the operating parameters of the power equipment close to the optimal state: ;

[0060] S5.8. Apply the optimized operating parameter settings to the actual power equipment.

[0061] As a further improvement of this technical solution, in the above S5.3, the fitness function is:

[0062] ;

[0063] Wherein, represents the fitness function value for the operating state of the power equipment; represents the number of components of the equipment; represents the th impedance of the component; represents the th current of the component; represents the th height of the component; represents the voltage of the nth component; represents the weight of the resistive loss; represents the weight of the resistive loss after height adjustment; represents the weight of the efficiency factor; represents the index of the device component;

[0064] For considering the spatial position of the power equipment, the fitness function is optimized:

[0065] ;

[0066] wherein, represents the spatial distribution position of the device; represents the spatial objective function; represents the weight coefficient of the spatial distribution.

[0067] On the other hand, the present invention provides a digital-twin-based power equipment operation optimization system, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the digital-twin-based power equipment operation optimization method described in any one of the above.

[0068] Compared with the prior art, the beneficial effects of the present invention are:

[0069] 1. In the digital-twin-based power equipment operation optimization method and system, by constructing a digital twin model synchronized with the physical power equipment and using the particle filter algorithm for accurate state estimation, this method can monitor the operation state of the power equipment in real time, including electrical performance, thermal performance, and the aging condition of insulating materials. This enables the system to detect potential problems in a timely manner, such as an increased risk of failure due to insulation deterioration, etc., so as to take maintenance measures in advance, reduce the occurrence probability of sudden failures, and improve the safety and reliability of the operation of power equipment.

[0070] 2. In the digital-twin-based power equipment operation optimization method and system, the particle swarm optimization algorithm is used to adjust the operation parameters of the power equipment. Based on the fitness function considering factors such as equipment aging and spatial position, it ensures that the optimization process not only focuses on the current operation efficiency but also takes into account the impact of long-term performance degradation. This can not only reduce energy consumption but also extend the service life of the equipment and improve the overall operation efficiency. In addition, by optimizing the cooperation relationship between different equipment, the comprehensive efficiency of the power system is further improved, and the optimal configuration and utilization of resources are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 is the overall method flowchart of the present invention. Detailed implementation mode

[0072] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0073] Embodiment 1: Since the wind turbines located in remote areas are exposed to harsh environments for a long time, they begin to experience problems with performance degradation, specifically manifested as reduced efficiency, unstable output power, and increased failure frequency; these problems have led to increased maintenance costs and reduced energy production. In addition, due to their remote locations, regular manual inspections are both expensive and time-consuming. Therefore, a more effective monitoring and optimization method is needed;

[0074] Please refer to Figure 1 As shown, this embodiment provides a method for optimizing the operation of power equipment based on digital twins, including the following steps:

[0075] S1. Collect the operation data of the physical power equipment through sensors;

[0076] In this embodiment, the operation data of the power equipment includes: current , voltage , rotational speed .

[0077] S2. Based on the operation data, use the modeling software Simulink to build a digital twin model of the power equipment so that it can reflect the operation state of the equipment in real time;

[0078] In this embodiment, Simulink can achieve real-time data synchronization between the physical power equipment and its digital twin, allowing engineers to monitor the equipment status in real time and adjust the model parameters according to the latest operation data; Simulink provides a rich component library and toolbox, which can be used to create highly accurate power equipment models, including electrical, thermodynamic and other dynamic characteristics; combined with advanced technologies such as particle filter algorithms, Simulink can help with more accurate state estimation and future trend prediction, which is crucial for preventive maintenance;

[0079] Building a digital twin model of the power equipment based on the operation data using the modeling software Simulink includes the following steps:

[0080] S2.1. Preprocess the collected operation data of the power equipment, and the preprocessing includes filtering, denoising, etc.;

[0081] S2.2. Import the collected current, voltage, and rotational speed data through the input modules of Simulink (such as signal sources, sensor modules, etc.);

[0082] S2.3. In Simulink, construct a digital twin model of the power equipment. Use the components and toolboxes provided by Simulink to establish the model, which should be able to simulate the real behavior of the power equipment, including but not limited to electrical performance, thermal performance, and other dynamic characteristics;

[0083] Furthermore, the digital twin model of the power equipment is as follows:

[0084] Electrical dynamic equation:

[0085] ;

[0086] Mechanical dynamics equation:

[0087] ;

[0088] Where, represents resistance; represents inductance; represents capacitance, that is, the ability of the capacitor to store charge; represents instantaneous torque; represents the rotational speed of the power equipment; represents moment of inertia; represents damping coefficient; represents time; represents the differential symbol.

[0089] S3. Establish a two-way data flow from the physical power equipment to the digital twin model and from the digital twin model back to the physical power equipment, perform data synchronization, and allow the transmission of real-time monitoring and control instructions;

[0090] In this embodiment, by transmitting the operating data of the physical device (such as current, voltage, temperature, etc.) to the digital twin model, it can ensure that the model always reflects the latest device state; the digital twin model can generate optimal control instructions according to the current state and send these instructions back to the physical device through the data flow to achieve automated adjustment and optimization; the two-way data flow allows the digital twin model to continuously learn and adapt to changes in actual operating conditions, improving its simulation accuracy of the dynamic behavior of the power equipment; by using the digital twin model for simulation and analysis, the best operating parameter settings can be found and these optimized parameters can be applied to the physical device through the data flow to improve efficiency or reduce costs;

[0091] Establish a two-way data flow from the physical device to the digital twin model and from the digital twin model back to the physical device, perform data synchronization, including the following steps:

[0092] S3.1. Transmit the collected operation data to the digital twin platform through the communication protocol (MQTT):

[0093] ;

[0094] Among them, represents the moment the operation data transmitted from the physical power equipment to the digital twin model;

[0095] S3.2. After receiving the operation data from the physical power equipment, parse the communication protocol and convert the operation data into a format acceptable to the Simulink model ;

[0096] S3.3. Input the parsed data into the digital twin model to update the state variables of the digital twin model.

[0097] S4. Use the particle filter algorithm to perform state estimation on the synchronized digital twin model, and introduce a physical degradation model of equipment aging during the state estimation process;

[0098] In this embodiment, the particle filter algorithm approximates the probability distribution of the system through a set of random samples (particles), and updates the states and weights of these particles in real time according to the new observation data, so as to realize the estimation of the system state; the particle filter algorithm does not need to assume that the system is linear or the observation noise is Gaussian distributed, so it is very suitable for complex nonlinear systems such as power equipment, and can adapt to various types of probability distributions, not just Gaussian distribution, which makes it more flexible and accurate when dealing with uncertainties in the real world; the particle filter can update the state estimation of the system in real time based on the latest observation data, ensuring that the digital twin model is always synchronized with the physical equipment. By continuously adjusting the particle weights, the particle filter algorithm can automatically adapt to changes in the system, including factors such as equipment aging and environmental condition changes; the particle filter provides the probability density function of the state estimation, which not only gives the most likely state, but also provides information about the estimation uncertainty, helping with risk assessment and decision-making;

[0099] Performing state estimation on the synchronized digital twin model using the particle filter algorithm includes the following steps:

[0100] S4.1. Generate a set of initial particles according to the historical state information of the power equipment:

[0101] ;

[0102] Among them, represents the initial state of the th particle, represents the covariance matrix of the initial state (reflecting the uncertainty of the initial estimate), represents the particle index, represents the initial state of the power equipment;

[0103] S4.2. At each moment Predict the state of each particle using the state transition equation of the system (which is a mathematical formula describing how the system evolves from one time point to the next). The prediction step enables the particle filter to make a forward-looking estimate of the future state based on the latest control input and process model, without relying on immediate observation data. The generated new particle set will serve as the basis for the next correction step, where they will adjust their weights according to the new observation data to more accurately reflect the state of the real system:

[0104] , where, represents the control input; represents the process noise;

[0105] S4.3. According to the real-time observation data received from the physical device and already converted into a format acceptable to the model , update the weight of each particle through the measurement model:

[0106] ;

[0107] where, represents the predicted observation value at time ; represents the mapping function from the state vector of the power equipment to the observation data. The mapping function converts the internal state vector of the power equipment into directly measurable observation data, such as voltage, current, and temperature, etc.; represents the observation noise, usually assumed to be a random variable with zero mean, reflecting the inevitable uncertainty or error in the observation process; represents the state vector of the power equipment;

[0108] S4.4. Based on the observation value, update the weight of the particle :

[0109] ;

[0110] where, represents the observation likelihood function, that is, the probability density of the observation data when the particle state is , , where, represents the covariance matrix of the observation noise;

[0111] S4.5. At each moment , calculate the state estimation of power equipment by weighted average. For the aging of power equipment, introduce the physical degradation model of equipment aging into the calculation of weighted average, and further optimize the calculation of weighted average for the insulation deterioration of power equipment components;

[0112] Furthermore, the main purpose of calculating the state estimation of power equipment by weighted average is to integrate the information of all particles and obtain a more accurate and reliable system state estimation. This method can effectively process multiple possible states (i.e., particles) generated by the particle filter algorithm and integrate them into a single optimal estimation value; each particle represents a possible state of the system, and these particles are generated based on different assumptions and random sampling. Through weighted average, these scattered possibilities can be concentrated to form a more accurate overall estimation; the state estimation of a single particle may be affected by noise or model errors, but through weighted average, these outliers can be smoothed out to obtain a more stable result; compared with directly selecting the optimal particle as the final estimation, weighted average utilizes the information of all particles, avoids wasting computing resources, and improves the overall efficiency of the algorithm;

[0113] The state estimation of the equipment calculated by weighted average is:

[0114] ;

[0115] where, represents the state estimation of the power equipment at time ; represents the th particle's state at time , representing the estimation of each particle's state of the equipment in the particle filter algorithm; represents the weight of the th particle at time ; represents the total number of particles;

[0116] Over time, the performance of power equipment will decline due to aging and wear. The aging process will cause changes in the electrical performance, thermal performance, etc. of the equipment, directly affecting its operating efficiency and safety. By introducing a degradation model, these changes can be considered in the state estimation, making the digital twin model more accurately reflect the current state of the equipment; the aging and degradation of the equipment may lead to deviations between some initial observed values and the actual performance. For example, the degradation of insulation materials will affect the response of current and voltage, and thus affect the state estimation of the digital twin model. If these degradation factors are not considered, the estimation result may deviate from the actual situation. By introducing the aging degradation factor into the weighted average, this deviation can be corrected and the estimation accuracy can be improved;

[0117] For the aging of power equipment, a physical degradation model of equipment aging is introduced into the weighted average calculation method:

[0118] ;

[0119] ;

[0120] wherein, represents the state estimation after introducing the physical degradation model of equipment aging; represents the aging coefficient of power equipment; represents the physical degradation model of equipment aging; represents the time The power output at represents the power performance of the equipment at different time points; represents the maximum power output of the equipment, usually the rated power of the equipment, which is used to calculate the relative degree of degradation;

[0121] Insulating materials in power equipment (such as transformers, cables, switchgear, etc.) will gradually deteriorate with the increase of service time. This deterioration will lead to a decline in the insulation performance of the equipment, increasing the risk of failures (such as electrical breakdown, short circuit, leakage, etc.), and may even cause the equipment to stop operating. In order to accurately reflect the true state of the equipment, the influence of insulation deterioration must be considered in the state estimation; insulation deterioration will cause changes in operating parameters such as current and voltage, directly affecting the operating state of the equipment. If insulation deterioration is ignored, it will lead to deviations in the state estimation results, affecting the judgment of the equipment's health status. By introducing the insulation deterioration factor into the weighted average calculation, the state estimation can more realistically reflect the current performance of the equipment, increasing the accuracy of prediction;

[0122] For the insulation deterioration of power equipment components, the weighted average calculation method is further optimized:

[0123] ;

[0124] ;

[0125] wherein, represents the further optimized state estimation; represents the insulation deterioration coefficient, which reflects the influence degree of insulation material degradation on the equipment state estimation. It is a positive number, representing the influence of insulation degradation on the performance of power equipment; represents the th particle's insulation deterioration function at time , representing the influence degree of the th particle on insulation deterioration; The coefficient indicating the deterioration of the insulating material, which is a positive number, is used to adjust the rate of insulation degradation; Indicates the th particle at time The insulation degradation rate, which represents the degree of degradation of the insulating material at that moment and is related to factors such as temperature, humidity, and operating load.

[0126] S5. Optimize the operating condition of the equipment through the particle swarm optimization algorithm based on the estimated state;

[0127] In this embodiment, the particle swarm optimization (PSO) algorithm is an optimization method based on swarm intelligence, where multiple particles fly in the solution space and adjust their trajectories according to the historical best positions of individuals and the group to find the global optimal solution; The PSO algorithm utilizes swarm intelligence and can effectively search in a large solution space through the update mechanism of individual and global optimal positions, reducing the risk of falling into local optima. For problems with multiple potential optimal solutions, PSO can explore different solution regions to find the global optimum or multiple high-quality solutions; Since each particle is guided by its own historical best position and the global best position of the group, the PSO algorithm can usually converge to the vicinity of the optimal solution at a relatively fast speed. As the number of iterations increases, the particle swarm will gradually concentrate in the most promising solution region, further accelerating the convergence speed;

[0128] Optimizing the operating condition of the equipment through the particle swarm optimization algorithm based on the estimated state includes the following steps:

[0129] S5.1. Determine the particle swarm size and the maximum number of iterations ;

[0130] S5.2. Initialize the position and velocity of each particle, and initialize the individual optimal position and the global optimal position of each particle;

[0131] S5.3. Construct a fitness function by combining the state estimation of the power equipment, and optimize the fitness function considering the spatial position of the power equipment;

[0132] The main purpose of constructing a fitness function in combination with the state estimation of power equipment is to provide a quantitative criterion in the particle swarm optimization (PSO) algorithm for evaluating the quality of the solutions represented by each particle. This fitness function is the core of the optimization process, which guides how particles update their positions and velocities to find the optimal solution; by integrating the latest state estimation results into the fitness function, it can ensure that the optimization process is always based on the most real operating data of power equipment. This makes the optimization scheme closer to the actual situation and improves its practicality and effectiveness; combined with state estimation, the fitness function can more accurately evaluate potential risks, such as failure probability or safety issues, and help formulate more reasonable maintenance plans and emergency response plans;

[0133] Furthermore, the fitness function is:

[0134] ;

[0135] where, represents the fitness function value for the operating state of the power equipment; represents the number of components of the equipment; represents the th impedance of the component; represents the th current of the component; represents the th height of the component; represents the th voltage of the component; represents the weight of the resistive loss; represents the weight of the resistive loss adjusted by height; represents the weight of the efficiency factor; represents the index of the equipment component;

[0136] Equipment in the power system is usually distributed. The operating state of each equipment is not only affected by its own parameters, but also by the operating states, physical locations and network topologies of other equipment; the spatial distribution affects the transmission path and efficiency of electricity. Optimizing spatial factors helps reduce transmission losses and improve system operating efficiency; the transmission efficiency of the power system is affected by the layout between equipment. Especially in distributed power systems (such as microgrids or regional power grids), optimizing the positions of equipment helps reduce the complexity of the transmission path and improve the transmission efficiency of power flow; long-distance power transmission not only easily leads to increased losses, but may also cause system instability due to overly long lines or unreasonable layouts. By optimizing the positions of equipment, the impact of overly long connections on system stability can be reduced. At the same time, a reasonable spatial layout helps reduce the risk of large-scale cascading failures caused by single-point failures;

[0137] Optimize the fitness function considering the spatial location of power equipment:

[0138] ;

[0139] ;

[0140] Among them, represents the spatial distribution location of the equipment; represents the spatial objective function, which is used to optimize the coordination relationship between different equipment; represents the weight coefficient of the spatial distribution; represents the equipment adjacent equipment set; represents the equipment and the equipment the connection weight between them (such as the capacity or importance of the power transmission path); represents the index of the current equipment; represents the index of the neighbor equipment; represents the equipment spatial location (coordinate vector); represents the equipment spatial location (coordinate vector);

[0141] S5.4. Update the particle velocity and position and calculate the new fitness value of the current particle ;

[0142] S5.5. Update the individual and global optima:

[0143] If , then update the individual optimum (each particle has its own historical best position , which is the best position ever visited by this particle. By continuously updating , the particle can remember the best solution it has encountered and use this as a reference point for subsequent exploration):

[0144] ;

[0145] If , then update the global optimum ( is the best solution found by all particles in the entire particle swarm. By updating , the particle swarm can share each other's information, promote the accumulation of collective wisdom, which helps to speed up the convergence rate and increase the probability of finding the global optimum solution):

[0146] ;

[0147] S5.6. Judge whether the maximum number of iterations is reached ;

[0148] S5.7. According to the final globally optimal position , adjust the operating parameters of the power equipment to make the operating parameters of the power equipment close to the optimal state: ;

[0149] S5.8. Apply the optimized operating parameter settings to the actual power equipment to comprehensively improve the operating conditions of the equipment, achieving higher efficiency, better stability and lower costs.

[0150] Embodiment 2: This embodiment provides a power equipment operation optimization system based on digital twin, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the power equipment operation optimization method based on digital twin described in any one of the above.

[0151] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed.

Claims

1. A method for optimizing the operation of power equipment based on digital twin, characterized in that, It includes the following steps: S1. Collect the operation data of physical power equipment through sensors; S2. Based on the operation data, use the modeling software Simulink to build a digital twin model of the power equipment; S3. Establish a two-way data stream from the physical power equipment to the digital twin model and from the digital twin model back to the physical power equipment for data synchronization; S4. Use the particle filter algorithm to perform state estimation on the synchronized digital twin model, and introduce a physical degradation model of equipment aging and an insulation degradation function during the state estimation process. Among them, the physical degradation model of equipment aging is specifically: ； Physical degradation model indicating equipment aging; Indicates the moment Power output at, representing the power performance of the equipment at different time points; Indicates the maximum power output of the equipment, usually the rated power of the equipment, used to calculate the relative degree of degradation; The insulation degradation function is: ； Among them, represents the insulation degradation function of the th particle at time ; represents the coefficient of insulation material degradation; represents the insulation degradation rate of the th particle at time ; S5. Based on the estimated state, use the particle swarm optimization algorithm to optimize the operation status of the equipment. Among them, a fitness function is constructed in combination with the state estimation of the power equipment, and considering the spatial position of the power equipment, a spatial objective function is introduced to optimize the fitness function; And the spatial objective function is specifically: ； Represents the spatial objective function, which is used to optimize the collaborative relationship between different devices; Represents the device Adjacent device set; Represents the device And the device Connection weight between; Represents the index of the current device; Represents the index of the neighbor device; Represents the device Spatial location; Represents the device Spatial location, Represents the index of the device component.

2. The method for optimizing the operation of power equipment based on digital twin according to claim 1, wherein: In the above S1, the operation data of the power equipment includes: current , voltage , rotational speed .

3. The method for optimizing the operation of power equipment based on digital twin according to claim 2, wherein: In S2, based on the operation data, use the modeling software Simulink to build a digital twin model of the power equipment, including the following steps: S2.

1. Preprocess the collected operation data of the power equipment; S2.

2. Through the input module of Simulink, import the collected current, voltage and speed data; S2.

3. In Simulink, build a digital twin model of the power equipment.

4. The method for optimizing the operation of power equipment based on digital twin according to claim 3, characterized in that: In S2.3, the digital twin model of the power equipment is: Electrical dynamic equation: ； Mechanical dynamics equation: ； Among them, represents resistance; represents inductance; represents capacitance; represents instantaneous torque; represents the rotational speed of the power equipment; represents moment of inertia; represents damping coefficient; represents time; represents the differential symbol.

5. The method for optimizing the operation of power equipment based on digital twin according to claim 4, characterized in that: In S3, establish a two-way data stream from the physical device to the digital twin model and from the digital twin model back to the physical device for data synchronization, including the following steps: S3.

1. Transmit the collected operation data to the digital twin platform through the communication protocol: ； Among them, represents the moment the operation data transmitted from the physical power equipment to the digital twin model; S3.

2. After receiving the operation data from the physical power equipment, parse the communication protocol and convert the operation data into a format acceptable to the Simulink model ; S3.

3. Input the parsed data into the digital twin model to update the state variables of the digital twin model.

6. The method for optimizing the operation of power equipment based on digital twin according to claim 5, wherein: In S4, use the particle filter algorithm to perform state estimation on the synchronized digital twin model, including the following steps: S4.

1. Generate a set of initial particles according to the historical state information of the power equipment; ； Among them, represents the initial state of the th particle, represents the covariance matrix of the initial state represents the particle index, represents the initial state of the power equipment; S4.

2. At each moment Predict the state of each particle using the state transition equation of the system; S4.

3. Update the weight of each particle through the measurement model according to the real-time observation data received from the physical device and already converted into a format acceptable to the model , as follows: ； Among them, represents the predicted observation value at time ; represents the mapping function from the state vector of the power equipment to the observation data; represents the observation noise; represents the state vector of the power equipment. S4.

4. Update the weights of the particles based on the observations : ； Among them, represents the observation likelihood function; S4.

5. At each moment , calculate the state estimation of the power equipment by means of weighted average. For the aging of power equipment, introduce the physical degradation model of equipment aging into the calculation of weighted average, and further optimize the calculation of weighted average for the insulation deterioration of power equipment components.

7. The method for optimizing the operation of power equipment based on digital twin according to claim 6, wherein: In S4.5, calculate the state estimation of the equipment by means of weighted average as: ； Among them, represents the state estimation of the power equipment at the moment ; represents the state of the -th particle at the moment ; represents the weight of the -th particle at the moment ; represents the total number of particles; For the aging of power equipment, introduce the physical degradation model of equipment aging in the weighted average calculation; ； Among them, represents the state estimation after introducing the physical degradation model of equipment aging; represents the aging coefficient of power equipment; represents the physical degradation model of equipment aging; For the insulation degradation of power equipment components, further optimize the weighted average calculation method; ； Among them, represents the further optimized state estimation; represents the insulation degradation coefficient; represents the th particle at the moment of the insulation degradation function.

8. The method for optimizing the operation of power equipment based on digital twin according to claim 7, characterized in that: In S5, based on the estimated state, use the particle swarm optimization algorithm to optimize the operation status of the equipment, including the following steps: S5.

1. Determine the particle swarm size and the maximum number of iterations ; S5.

2. Initialize the positions of each particle and velocities , and initialize the individual best positions of each particle and the global best position ; S5.

3. Construct a fitness function in combination with the state estimation of the power equipment, and optimize the fitness function considering the spatial position of the power equipment; Among them, the fitness function is: ； Among them, represents the fitness function value for the operating state of the power equipment; represents the number of components of the equipment; represents the impedance of the th component; represents the th component's current; represents the th component's height; represents the th component's voltage; represents the weight of the resistance loss after height adjustment; represents the weight of the efficiency factor; represents the index of the equipment component; Optimize the fitness function considering the spatial position of the power equipment; ； Among them, represents the device spatial distribution position; represents the spatial objective function; represents the weight coefficient of the spatial distribution; S5.

4. Update the particle velocity and position and calculate the new fitness value of the current particle ; S5.

5. Update the individual and global optima; If , update the individual optimum: ； If , then update the global optimum: ； S5.

6. Determine whether the maximum number of iterations has been reached ; S5.

7. Adjust the operating parameters of the power equipment according to the final globally optimal position so that the operating parameters of the power equipment approach the optimal state: ; S5.

8. Apply the optimized operation parameter settings to the actual power equipment.

9. A power equipment operation optimization system based on digital twin, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: The processor executes a computer program to implement the digital twin-based power equipment operation optimization method according to any one of claims 1-8.

Images