A wind power converter IGBT loss thermoelectric simulation optimization modeling method, system, device and medium

Abstract

This invention relates to a method, system, equipment, and medium for optimizing and simulating IGBT losses in wind power converters. The method includes: acquiring wind turbine operating parameters through a wind farm SCADA system, and simultaneously collecting junction temperature data of IGBT devices under real-world operating conditions using sensor equipment; calculating the ideal and actual losses of the IGBT devices based on the collected wind turbine operating parameters and junction temperature data using an ideal IGBT loss model and an electrical power formula; correcting the model parameters of the ideal IGBT loss model stored in a database based on the difference between the ideal and actual losses, and obtaining an updated IGBT loss model based on the correction results, which is used for loss tracking and aging monitoring of the IGBT devices. This invention can be widely applied in the field of wind power generation technology.

Description

Technical Field

[0001] This invention belongs to the field of wind power generation technology, specifically relating to a method, system, equipment, and medium for simulating and optimizing the thermoelectric simulation of IGBT losses in wind power converters. Background Technology

[0002] IGBTs (Insulated Gate Bipolar Transistors) are core components of modern high-voltage, high-power converters, widely used in wind power generation, rail transit, and high-voltage frequency conversion systems. Their performance stability and thermal reliability directly determine the efficiency and lifespan of the entire system. However, during long-term operation, IGBTs are affected by thermo-electro-mechanical coupling effects. Periodic fluctuations in junction temperature and accumulation of thermal stress can cause fatigue of the chip solder layer, aging of packaging materials, and an increase in internal thermal resistance, leading to a gradual increase in losses and premature failure.

[0003] Traditional loss modeling mainly relies on static data table parameters or single-test curves, such as using on-state voltage drop. Activation loss Shutdown losses Power loss is predicted using a calibration function with temperature. However, these models typically assume that parameters do not change over time and cannot reflect the dynamic behavior of devices under aging or multi-cycle thermal stress. Existing research indicates that when the junction temperature exceeds 125°C and the number of cycles is greater than 10... 6 At that time, the module junction-shell thermal resistance The temperature rise could increase by 15-25%, and without model correction, the system temperature rise and losses would be significantly underestimated.

[0004] In recent years, existing solutions have primarily focused on "digital twin" loss assessment methods based on real-time monitoring and model updates. By introducing an updatable set of parameters into the simulation model, the model can adaptively adjust based on measured data. For example, in electrothermal co-simulation, online regression of the parameters of the IGBT dynamic thermal network (Foster or Cauer model) can gradually approximate the actual thermal performance of the device. However, most of these methods remain at the level of theoretical verification or require expensive external thermal analysis equipment. A mature solution for achieving self-updating of loss models using limited sensor data under industrial conditions remains lacking. Summary of the Invention

[0005] To address the aforementioned issues, the present invention aims to provide a method, system, device, and medium for optimizing and modeling IGBT loss thermoelectric simulation in wind power converters. Based on a loss prediction and model self-updating mechanism that integrates ideal models with measured data, the loss tracking and aging monitoring of IGBT devices can be achieved without the need for additional testing hardware.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for optimizing and modeling the thermoelectric simulation of IGBT losses in wind power converters, comprising: The wind turbine operating parameters are obtained through the wind farm SCADA system, and the junction temperature data of IGBT devices under real operating conditions are collected through sensor equipment. Based on the collected wind turbine operating parameters and junction temperature data, the ideal loss and actual loss of the IGBT device are calculated using the ideal IGBT loss model and the power formula, respectively. Based on the difference between ideal loss and actual loss, the model parameters of the ideal IGBT loss model are corrected, and an updated IGBT loss model is obtained based on the correction results, which is used for loss tracking and aging monitoring of IGBT devices.

[0007] Furthermore, the method also includes: Every preset period, the IGBT loss model stored in the database is updated using the collected wind turbine operating data and junction temperature data to form an adaptive IGBT loss model.

[0008] Furthermore, the acquisition of wind turbine operating parameters through the wind farm SCADA system includes acquiring wind turbine operating power, operating time, turbine-side electrical parameters, and grid-side electrical parameters.

[0009] Furthermore, based on the collected wind turbine operating parameters and junction temperature data, the ideal and actual losses of the IGBT device are calculated using the ideal IGBT loss model and the power formula, respectively, including: Based on the operating parameters of the wind turbine, the collector current and voltage of the IGBT device were obtained through simulation. The junction temperature data of IGBT devices under real operating conditions are filtered and normalized. Input the collector current, voltage and junction temperature data of the IGBT device into the ideal IGBT loss model, and calculate the ideal loss of the IGBT device using the turn-on or turn-off energy curves and thermal impedance parameters provided in the device datasheet. Based on the collector current, voltage, and junction temperature data of IGBT devices, the actual losses of IGBT devices are calculated using the power formula.

[0010] Furthermore, based on the difference between ideal and actual losses, the model parameters of the ideal IGBT loss model are corrected, and an updated IGBT loss model is obtained based on the correction results. This updated model is used for loss tracking and aging monitoring of IGBT devices, including: The difference between actual loss and ideal loss is calculated to obtain the loss difference value; If the loss difference value is greater than the preset threshold, the ideal IGBT loss model is retrained and the parameters are corrected based on the historical operating data and current operating parameters of the wind turbine to obtain the corrected model parameters; otherwise, the IGBT loss model is not updated. The ideal IGBT loss model is updated using the corrected model parameters to obtain the updated IGBT loss model.

[0011] Furthermore, based on the historical operating data and current operating parameters of the wind turbine, the ideal IGBT loss model is retrained and its parameters are corrected to obtain the corrected model parameters, including: Based on the ideal loss of IGBT devices, a correction function of mixed polynomial and exponential form is constructed. The objective function is established based on the correction function and the actual loss of the IGBT device. Based on historical operating data of wind turbine units, the ideal IGBT loss model is retrained and its parameters are corrected using the least squares method, and the model parameters that minimize the objective function are used as the corrected model parameters.

[0012] Furthermore, the correction function is expressed as:

[0013] In the formula, This indicates the corrected power loss. This represents the ideal loss calculated using the ideal IGBT loss model; Indicates the collector current; Indicates the junction temperature; Indicates the current running cycle; Indicates the number of loop iterations; , , , , This represents the coefficients determined through least squares regression.

[0014] Secondly, the present invention provides a simulation optimization modeling system for IGBT loss thermoelectricity of wind power converters, comprising: The data acquisition module is used to acquire the operating parameters of the wind turbine through the wind farm SCADA system, and at the same time to collect the junction temperature data of the IGBT device under real operating conditions through sensor equipment. The loss calculation module is used to calculate the ideal loss and actual loss of IGBT devices based on the collected wind turbine operating parameters and junction temperature data, using the ideal IGBT loss model and the power formula, respectively. The fitting module is used to correct the model parameters of the ideal IGBT loss model based on the difference between the ideal loss and the actual loss, and to obtain an updated IGBT loss model based on the correction results, which is used for loss tracking and aging monitoring of IGBT devices.

[0015] Thirdly, the present invention provides a computer-readable storage medium for storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform a method for optimizing and modeling the thermoelectric simulation of losses in any wind power converter IGBT.

[0016] Fourthly, the present invention provides a computing device, comprising: one or more processors and a memory, wherein the memory stores one or more programs and is configured to be executed by the one or more processors, and the one or more programs include instructions for executing a method for optimizing and modeling the thermoelectric simulation of IGBT losses in any wind power converter.

[0017] The present invention has the following advantages due to the adoption of the above technical solutions: 1. This invention introduces a correction mechanism that fuses ideal models with measured data, enabling the IGBT loss model to continuously calibrate errors during long-term operation, thereby improving the accuracy of loss prediction. This accuracy advantage mainly benefits from the fact that the dynamic regression function can reflect the combined effect of junction temperature changes on conduction and switching losses in real time, overcoming the neglect of aging effects in previous models.

[0018] 2. This invention, through a closed-loop fusion mechanism of "ideal simulation - actual measurement correction - model update", enables the IGBT loss model to adaptively adjust according to operating data. For the first time, it achieves dynamic updating and long-term accuracy maintenance of the IGBT loss model without relying on additional temperature measurement equipment.

[0019] 3. This invention establishes a standardized polynomial-exponential hybrid correction function structure with clear physical meaning and traceable parameters, which can be easily embedded into the simulation platform. This function framework can be extended to the aging modeling of other power devices and has good versatility.

[0020] 4. Since the model parameters are directly related to the number of thermal cycles, this invention can be further used for lifetime estimation and digital twin modeling. By tracking changes in relevant parameters, the device degradation rate can be assessed, enabling early failure warning.

[0021] Therefore, this invention can be widely applied in the field of wind power generation technology. Attached Figure Description

[0022] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. In the drawings: Figure 1 This is a flowchart of the wind power converter IGBT loss thermoelectric simulation optimization modeling method provided in the embodiments of the present invention; Figure 2 This is the overall block diagram of the wind power converter IGBT loss thermoelectric simulation optimization model provided in the embodiments of the present invention; Figure 3 This is a schematic diagram of the circuit structure provided in the embodiments of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0024] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0025] Currently, there are two main methods for simulating the thermoelectric losses of IGBTs in wind power converters: One method involves calculating the losses of IGBT devices using a fixed-parameter thermal resistance model. This type of method relies on thermal characteristic data provided by the device manufacturer (such as junction-to-case thermal resistance). Transient thermal impedance curve and conduction voltage drop (Temperature characteristics) A standard Foster equivalent network model is established in the simulation platform, and junction temperature changes and power losses are obtained by convolution calculation of the input power waveform. This type of method has a clear modeling approach and unified parameter sources, and is suitable for the thermal characteristic analysis of ideal or new devices. In the system design phase, designers can quickly assess the thermal equilibrium state and thermal saturation time by changing the ambient temperature and heat dissipation conditions. Therefore, it is widely used in the predictive models of inverter thermal design and over-temperature protection, and is currently the most common thermal modeling method in the industrial field.

[0026] However, this type of method also has the following drawbacks that cannot be ignored: First, the model parameters in these methods are typically derived from factory calibration data, representing only the initial characteristics of the device under ideal packaging conditions. They fail to reflect the increased thermal resistance caused by solder layer fatigue and interface material aging after long-term operation. Second, the Foster equivalent network model lacks online self-updating capabilities. Once system operating conditions change (e.g., deterioration of cooling conditions or contamination of the heat dissipation interface), the calculation results will deviate significantly from the actual junction temperature. Furthermore, the simulation model cannot perceive the nonlinear loss changes caused by thermo-electro-mechanical coupling, leading to an underestimation of actual power loss in the prediction results. More seriously, fixed-parameter models require recalibration when ported between different batches of modules or replacement models, resulting in high engineering maintenance costs. In summary, these methods are suitable for static analysis but struggle to meet the real-time loss prediction requirements of high-reliability scenarios such as wind power.

[0027] Second, there are IGBT loss modeling methods based on online identification and parameter adaptation. These methods embed recursive least squares or extended Kalman filter algorithms into the inverter control system, utilizing real-time collected collector current, voltage, and casing temperature data to estimate IGBT thermal model parameters online. Unlike traditional static models, this method can dynamically adjust thermal resistance and capacity based on operating conditions, thus capturing aging trends to some extent. Furthermore, some studies have introduced multivariate regression or machine learning methods to establish nonlinear loss mapping models using historical samples, giving the models a certain degree of self-learning capability. This type of technology has shown good results in laboratory settings or high-end equipment, and theoretically can significantly improve loss prediction accuracy, making it suitable for applications in condition monitoring and life assessment.

[0028] Despite their dynamic characteristics, the aforementioned methods still face practical limitations. The online identification algorithms require high-precision temperature and current sensors, significantly increasing system costs. In industrial settings, signal noise and sampling delays can lead to unstable parameter identification, and the algorithms are often highly sensitive to model structure and initial conditions; inaccurate parameter initialization can cause identification divergence. Furthermore, while data-driven methods can fit complex relationships, they lack physical interpretability and portability. Finally, most existing studies have not been validated with actual power cycling test data, resulting in insufficient model generalization ability. In summary, while this method improves accuracy, it increases system complexity and debugging difficulty, and still fails to address the key issue of achieving reliable model updates under limited measurement conditions.

[0029] Based on this, some embodiments of the present invention provide a method for optimizing and modeling the thermoelectric simulation of IGBT losses in wind power converters, aiming to solve the core problems of "mismatch between ideal and actual values ​​and inability to dynamically update" in existing IGBT loss models. The present invention optimizes the model by optimizing the ideal loss... Compared with actual losses This invention uses a functional description to represent the differences between simulation results and actual device performance, thus achieving a leap from a "fixed-value model" to a "data-driven physical model." Its core idea is to use an ideal model as a benchmark and establish a nonlinear correction function through statistical residual characteristics, allowing simulation results to gradually approximate the performance of actual devices. This improves long-term prediction accuracy and reliability, providing a feasible engineering approach for digital twin modeling of power devices. Furthermore, this invention can periodically update existing thermo-electric joint models using voltage, current, and temperature data collected during system operation, without requiring additional testing equipment, thereby achieving adaptive model evolution.

[0030] Correspondingly, in other embodiments of the present invention, a system, device, and medium for simulating and optimizing the thermoelectric simulation of IGBT losses in wind power converters are provided.

[0031] Example 1 like Figure 1 , Figure 2 As shown in the figure, this embodiment provides a method for optimizing the thermoelectric simulation modeling of IGBT losses in wind power converters, which includes the following steps: 1) The wind turbine's operating parameters are obtained through the wind farm's SCADA (Supervisory Control and Data Acquisition) system, while the junction temperature data of the IGBT device under real operating conditions is collected through sensor equipment. 2) Based on the collected wind turbine operating parameters and junction temperature data, the ideal losses of the IGBT devices are calculated using the ideal IGBT loss model and the power formula, respectively. and actual losses ; 3) Based on ideal loss and actual losses The differences between them are used to correct the model parameters of the ideal IGBT loss model stored in the database using mathematical methods such as the least squares method, and the updated IGBT loss model is obtained based on the correction results. 4) Repeat steps 1) to 3) every preset period to form an adaptive evolution IGBT loss model for loss tracking and aging monitoring of IGBT devices.

[0032] Furthermore, in step 1) above, when collecting the operating parameters of the wind turbine, the collected operating parameters mainly include the wind turbine operating power, operating time, turbine-side electrical parameters, and grid-side electrical parameters.

[0033] When collecting junction temperature data of IGBT devices, sensor devices, such as high-speed data acquisition devices, can be set at a preset position of the IGBT device to record the junction temperature data of the IGBT device under real operating conditions in real time.

[0034] Furthermore, step 2) above includes the following steps: 2.1) Based on the operating parameters of the wind turbine, the collector current of the IGBT device was obtained through simulation. and voltage ; 2.2) Filter and normalize the junction temperature data of IGBT devices under actual operating conditions; 2.3) The collector current of the IGBT device ,Voltage and junction temperature Inputting an ideal IGBT loss model based on a Foster equivalent network, the instantaneous loss, i.e., the ideal loss, is calculated using the turn-on / turn-off energy curves and thermal impedance parameters provided in the device datasheet. ; 2.4) Based on the collector current, voltage, and junction temperature data of the IGBT device under actual operating conditions, the average power loss of the IGBT under actual operating conditions, i.e., the actual power loss, is calculated using the power formula. .

[0035] Average power loss, which integrates multiple factors such as conduction loss, switching loss, and parasitic loss, is a key indicator reflecting the true operating state of a device.

[0036] Furthermore, in step 2.3) above, such as Figure 2 As shown, the ideal IGBT loss model is integrated into PLECS. Through the establishment of a joint simulation model using MATLAB / Simulink and PLECS, it is used to calculate the conduction loss, switching loss, and overall thermal power consumption under standard operating conditions—that is, the ideal loss—based on device datasheet parameters (such as IGBT switching losses and IGBT conduction losses) and circuit operating conditions (such as the conduction state of the IGBT in the working circuit under different control methods). In the picture, Indicates the thermal resistance of the junction; Indicates the thermal resistance of the thermal paste on the heatsink; This indicates the ambient thermal resistance of the radiator.

[0037] The calculation of ideal losses is usually based on the Foster thermal network model and device parameters in the datasheet, ignoring the effects of device aging, operating condition fluctuations and thermal stress on performance, thus reflecting idealized device behavior.

[0038] Furthermore, step 3) above includes the following steps: 3.1) Actual losses Compared with ideal loss The difference between them is calculated to obtain the loss difference value. This loss difference value reflects the degree of deviation between the ideal IGBT loss model and actual operation; 3.2) Determine the difference in loss value Is it greater than the preset threshold? If yes, proceed to step 3.3; otherwise, do not update the IGBT loss model. 3.3) Based on the historical operating data and current operating parameters of the wind turbine, mathematical methods such as the least squares method are used to retrain and correct the parameters of the ideal IGBT loss model in the database to obtain the corrected model parameters. 3.4) Update the ideal IGBT loss model in the database using the corrected model parameters to obtain the updated IGBT loss model.

[0039] Furthermore, in step 3.3) above, in this embodiment, the key coefficients and equivalent thermal parameters in the ideal IGBT loss model are corrected by minimizing the sum of squared residuals or gradient descent algorithm, so that the performance of the ideal IGBT loss model gradually approaches the actual thermal behavior of the IGBT device, and the loss calculation is more accurate.

[0040] Specifically, it includes the following steps: 3.3.1) Ideal Loss Based on IGBT Devices Construct a correction function in a mixed polynomial and exponential form. .

[0041] In this embodiment, the correction function adopts a hybrid form of polynomial and exponential to balance fitting accuracy and physical meaning. Specifically, the correction function is expressed as:

[0042] In the formula, This indicates the corrected power loss. This represents the ideal loss calculated using the ideal IGBT loss model; Indicates the collector current; Indicates the junction temperature; Indicates the operating cycle; Indicates the number of cycles (reflecting the degree of aging); , , , , This represents the coefficients determined through least squares regression.

[0043] 3.3.2) Based on the correction function and the actual loss of IGBT devices An objective function is established, and the model parameters that minimize the objective function are calculated using the least squares method based on the historical operating data of the wind turbine.

[0044] Among them, based on the correction function and measured loss The established objective function is expressed as:

[0045] In the formula, Indicates the time of IGBT devices The actual loss; Indicates the time of IGBT devices The corrected power loss; This indicates minimization.

[0046] In this embodiment, the IGBT loss model is iteratively updated in each operating cycle by minimizing the objective function, allowing the error to gradually converge. This mathematical structure maintains interpretability (parameters are directly related to physical quantities) and can achieve accuracy adaptation through real-time data, serving as a key intermediate layer connecting ideal simulation and actual measurement.

[0047] Through continuous retraining, the IGBT loss model can dynamically track the thermal resistance, conduction loss, and dynamic junction temperature characteristics of IGBT devices as they age, realizing a leap from static modeling to dynamic learning in thermal simulation models. This significantly improves the accuracy and real-time performance of the operational status assessment and lifetime prediction of IGBT devices in wind power converters.

[0048] This invention achieves closed-loop coupling of "data-model-data" by periodically executing this process, ensuring that the IGBT loss model maintains high consistency and accuracy with actual operating conditions over the long term. This dynamic comparison method between ideal and actual losses not only ensures the calculation accuracy of the IGBT loss model but can also be used to identify the health status of IGBTs, providing data support for IGBT device lifespan prediction, preventative maintenance, and wind power converter system optimization.

[0049] Example 2 This invention can be applied to wind power converter applications. For example... Figure 3The diagram illustrates a thermo-electric coupling circuit structure for IGBT dynamic loss modeling and lifetime prediction. This circuit structure consists of multiple modules, including connections between a wind turbine, a machine-side converter, a grid-side converter, and a PWM controller. The wind turbine is connected to a DFIG (doubly fed induction generator) via a gearbox, and the DFIG is connected to the machine-side converter, the grid-side converter, and the power grid. The IGBTs and other power electronic switching devices within the machine-side and grid-side converters are regulated and power converted by the PWM controller. The IGBTs and other power electronic switching devices control current flow and exchange power with the grid through voltage and current waveform regulation. Each module is tightly connected via electrical signals and data flow, ensuring that the wind turbine's operating state matches the simulation signals. Through real-time data acquisition and signal feedback, the system can accurately calculate the losses and junction temperatures of the IGBTs and other power electronic switching devices, and optimize the loss model through parameter correction. This closed-loop control structure ensures accurate transmission of electrical signals, achieving efficient operation and accurate lifetime prediction of the wind power system. Each module plays a crucial role in the system, ensuring the integrity of collaborative work between different parts and the flow of data.

[0050] Example 3 The above-described embodiment 1 provides a method for optimizing and modeling the thermoelectric simulation of IGBT losses in a wind power converter. Correspondingly, this embodiment provides a system for optimizing and modeling the thermoelectric simulation of IGBT losses in a wind power converter. The system provided in this embodiment can implement the method for optimizing and modeling the thermoelectric simulation of IGBT losses in a wind power converter as described in embodiment 1. This system can be implemented through software, hardware, or a combination of both. For example, the system may include integrated or separate functional modules or units to execute the corresponding steps in the methods of embodiment 1. Since the system in this embodiment is basically similar to the method embodiment, the description process in this embodiment is relatively simple. For relevant details, please refer to the description of embodiment 1. The system embodiment provided in this embodiment is merely illustrative.

[0051] This embodiment provides a simulation optimization modeling system for IGBT loss in wind power converters, which includes: The data acquisition module is used to acquire the operating parameters of the wind turbine through the wind farm SCADA system, and at the same time to collect the junction temperature data of the IGBT device under real operating conditions through sensor equipment. The loss calculation module is used to calculate the ideal loss of IGBT devices based on the collected wind turbine operating parameters and junction temperature data, using both the ideal IGBT loss model and the power formula. and actual losses ; Fitting module, used for fitting based on ideal loss and actual losses The differences between them are used to correct the model parameters of the ideal IGBT loss model stored in the database using mathematical methods such as the least squares method, and the updated IGBT loss model is obtained based on the correction results. The periodic update module is used to update the IGBT loss model every preset period using the collected wind turbine operating parameters and junction temperature data, forming an adaptive evolution IGBT loss model for loss tracking and aging monitoring of IGBT devices.

[0052] Furthermore, the fitting module includes: The residual calculation module is used to calculate the actual loss. Compared with ideal loss The difference between them is calculated to obtain the loss difference value; Update the judgment module to determine the loss difference value. Is it greater than the preset threshold? If yes, proceed to the parameter correction module; otherwise, return to the data acquisition module. The parameter correction module is used to correct the model parameters of the ideal IGBT loss model based on historical operating data and current operating parameters, using mathematical methods such as the least squares method, to ensure that the residual is minimized and the loss calculation is more accurate. The model update module is used to update the ideal IGBT loss model in the database using the corrected model parameters, so as to obtain the updated IGBT loss model.

[0053] Example 4 This embodiment provides a processing device corresponding to the wind power converter IGBT loss thermoelectric simulation optimization modeling method provided in Embodiment 1. The processing device can be a client-side processing device, such as a mobile phone, laptop, tablet computer, desktop computer, etc., to execute the method of Embodiment 1.

[0054] The processing device includes a processor, a memory, a communication interface, and a bus. The processor, memory, and communication interface are connected via the bus to enable communication between them. The memory stores a computer program that can run on the processor. When the processor runs the computer program, it executes the wind power converter IGBT loss thermoelectric simulation optimization modeling method provided in Embodiment 1.

[0055] Preferably, the memory may be high-speed random access memory (RAM), and may also include non-volatile memory, such as at least one disk storage device.

[0056] Preferably, the processor can be any type of general-purpose processor such as a central processing unit (CPU) or a digital signal processor (DSP), and there is no limitation herein.

[0057] Example 5 The wind power converter IGBT loss thermoelectric simulation optimization modeling method of this embodiment 1 can be specifically implemented as a computer program product. The computer program product may include a computer-readable storage medium on which computer-readable program instructions for executing the wind power converter IGBT loss thermoelectric simulation optimization modeling method of this embodiment 1 are loaded.

[0058] A computer-readable storage medium can be a tangible device that holds and stores instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof.

[0059] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0060] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0061] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0062] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A wind power converter IGBT loss thermal simulation optimization modeling method, characterized in that, include: The wind turbine operating parameters are obtained through the wind farm SCADA system, and the junction temperature data of IGBT devices under real operating conditions are collected through sensor equipment. Based on the collected wind turbine operating parameters and junction temperature data, the ideal loss and actual loss of the IGBT device are calculated using the ideal IGBT loss model and the power formula, respectively. Based on the difference between ideal loss and actual loss, the model parameters of the ideal IGBT loss model are corrected, and an updated IGBT loss model is obtained based on the correction results, which is used for loss tracking and aging monitoring of IGBT devices. The model parameters of the ideal IGBT loss model are corrected based on the difference between ideal and actual losses, and an updated IGBT loss model is obtained based on the correction results. This updated model is used for loss tracking and aging monitoring of IGBT devices, including: The difference between actual loss and ideal loss is calculated to obtain the loss difference value; If the loss difference value is greater than the preset threshold, the ideal IGBT loss model is retrained and the parameters are corrected based on the historical operating data and current operating parameters of the wind turbine to obtain the corrected model parameters; otherwise, the IGBT loss model is not updated. The ideal IGBT loss model is updated using the corrected model parameters to obtain the updated IGBT loss model. The ideal IGBT loss model is retrained and its parameters are corrected based on historical operating data and current operating parameters of the wind turbine, resulting in corrected model parameters, including: Based on the ideal loss of IGBT devices, a correction function of mixed polynomial and exponential form is constructed. The objective function is established based on the correction function and the actual loss of the IGBT device. Based on historical operating data of wind turbine units, the ideal IGBT loss model is retrained and its parameters are corrected using the least squares method, and the model parameters that minimize the objective function are used as the corrected model parameters. The correction function is expressed as follows: ； In the formula, This indicates the corrected power loss. This represents the ideal loss calculated using the ideal IGBT loss model; Indicates the collector current; Indicates the junction temperature; Indicates the current running cycle; Indicates the number of loop iterations; , , , , This represents the coefficients determined through least squares regression.

2. The wind power converter IGBT loss thermal simulation optimization modeling method of claim 1, wherein, The method further includes: Every preset period, the IGBT loss model stored in the database is updated using the collected wind turbine operating data and junction temperature data to form an adaptive IGBT loss model.

3. The wind power converter IGBT loss thermal simulation optimization modeling method of claim 1, wherein, The method of obtaining wind turbine operating parameters through the wind farm SCADA system includes obtaining wind turbine operating power, operating time, turbine-side electrical parameters and grid-side electrical parameters.

4. The wind power converter IGBT loss thermal simulation optimization modeling method of claim 1, wherein, Based on the collected wind turbine operating parameters and junction temperature data, the ideal and actual losses of the IGBT device are calculated using the ideal IGBT loss model and the power formula, respectively, including: Based on the operating parameters of the wind turbine, the collector current and voltage of the IGBT device were obtained through simulation. The junction temperature data of IGBT devices under real operating conditions are filtered and normalized. Input the collector current, voltage and junction temperature data of the IGBT device into the ideal IGBT loss model, and calculate the ideal loss of the IGBT device using the turn-on or turn-off energy curves and thermal impedance parameters provided in the device datasheet. Based on the collector current, voltage, and junction temperature data of IGBT devices, the actual losses of IGBT devices are calculated using the power formula.

5. A wind power converter IGBT loss thermal electrical emulation optimization modeling system, characterized in that, include: The data acquisition module is used to acquire the operating parameters of the wind turbine through the wind farm SCADA system, and at the same time to collect the junction temperature data of the IGBT device under real operating conditions through sensor equipment. The loss calculation module is used to calculate the ideal loss and actual loss of IGBT devices based on the collected wind turbine operating parameters and junction temperature data, using the ideal IGBT loss model and the power formula, respectively. The fitting module is used to correct the model parameters of the ideal IGBT loss model based on the difference between the ideal loss and the actual loss, and to obtain the updated IGBT loss model based on the correction results, which is used for loss tracking and aging monitoring of IGBT devices. The model parameters of the ideal IGBT loss model are corrected based on the difference between ideal and actual losses, and an updated IGBT loss model is obtained based on the correction results. This updated model is used for loss tracking and aging monitoring of IGBT devices, including: The difference between actual loss and ideal loss is calculated to obtain the loss difference value; If the loss difference value is greater than the preset threshold, the ideal IGBT loss model is retrained and the parameters are corrected based on the historical operating data and current operating parameters of the wind turbine to obtain the corrected model parameters; otherwise, the IGBT loss model is not updated. The ideal IGBT loss model is updated using the corrected model parameters to obtain the updated IGBT loss model. The ideal IGBT loss model is retrained and its parameters are corrected based on historical operating data and current operating parameters of the wind turbine, resulting in corrected model parameters, including: Based on the ideal loss of IGBT devices, a correction function of mixed polynomial and exponential form is constructed. The objective function is established based on the correction function and the actual loss of the IGBT device. Based on historical operating data of wind turbine units, the ideal IGBT loss model is retrained and its parameters are corrected using the least squares method, and the model parameters that minimize the objective function are used as the corrected model parameters. The correction function is expressed as follows: ； In the formula, This indicates the corrected power loss. This represents the ideal loss calculated using the ideal IGBT loss model; Indicates the collector current; Indicates the junction temperature; Indicates the current running cycle; Indicates the number of loop iterations; , , , , This represents the coefficients determined through least squares regression.

6. A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions that when executed by a computer cause the computer to perform a method comprising: The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods described in claims 1 to 4.

7. A computing device, comprising: include: One or more processors and a memory, wherein the memory stores one or more programs and is configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods described in claims 1 to 4.

Images