Model optimization method and system based on online parameter identification

Abstract

The application discloses a model optimization method and system based on online parameter identification, and belongs to the technical field of power equipment. The application collects first temperature information corresponding to each detection position at the current time through a control sensor, and obtains motor operation data at the current time; real-time temperature information is determined according to the motor operation data, the first temperature information and corresponding position information; and a speed control model of a double-fed motor is updated according to the real-time temperature information, thereby achieving the beneficial effect of improving the stability of power generation.

Description

Technical Field

[0001] This invention relates to the field of power equipment technology, and in particular to a model optimization method and system based on online parameter identification. Background Technology

[0002] With the development of power systems, the control requirements for power generation devices are becoming increasingly stringent. Doubly fed induction generators (DFIGs) have become the main power equipment for wind power generation. In the practical engineering applications of DFIGs, when operating conditions cause electrical parameters to drift, a severe model mismatch occurs between the "theoretical model" inside the controller and the "physical entity" of the motor, leading to a series of cascading control anomalies. The most direct consequence of parameter drift is that it causes estimation errors in the rotor flux linkage observer. For example, the thermal change of rotor resistance directly alters the rotor time constant, causing the observed flux linkage phase and amplitude to deviate from the true value, thus causing the control of the DFIG to deviate and affecting the stability of power generation. Summary of the Invention

[0003] The present invention aims to solve at least one of the problems existing in the prior art, and to provide a model optimization method and system based on online parameter identification.

[0004] One aspect of the present invention provides a model optimization method based on online parameter identification, comprising: The control sensor collects the first temperature information corresponding to each detection position at the current moment, and obtains the motor operation data at the current moment; Real-time temperature information is determined based on the motor operating data, the first temperature information, and the corresponding location information. The speed control model of the doubly fed motor is updated based on the real-time temperature information.

[0005] Optionally, determining the real-time temperature information based on the motor operating data, the first temperature information, and the corresponding position information includes: The thermal resistance distribution information is determined based on the motor operating data, and the first heat generation information is determined based on the motor operating data; The second temperature information is determined based on the thermal resistance distribution information, the first temperature information, and the corresponding location information. Real-time temperature information is determined based on the first heat generation information and the second temperature information.

[0006] Optionally, the motor operating data includes: operating time, operating conditions, and corresponding time duration; determining the thermal resistance distribution information based on the motor operating data includes: The thermal resistance change information is determined based on the preset analysis model, runtime, operating conditions, and corresponding time length. The thermal resistance distribution information is determined based on the preset reference thermal resistance and the thermal resistance change information.

[0007] Optionally, before determining the thermal resistance change information based on the preset analysis model, runtime, operating conditions, and corresponding time length, the method further includes: Obtain historical operation datasets, which include multiple sets of historical motor operation data and corresponding historical temperature change curves; Historical heating information is determined based on the historical motor operating data, and historical thermal resistance information is determined based on the historical temperature change curve. The preset neural network model is trained based on the historical heating information and the historical thermal resistance information to obtain the preset analysis model.

[0008] Optionally, the step of training a preset neural network model based on the historical heating information and the historical thermal resistance information to obtain the preset analysis model includes: An input feature vector is constructed based on the historical heating information, and an output label is constructed based on the historical thermal resistance information. A training dataset is constructed based on the input feature vector and the output label; The initial neural network model is trained using the training dataset and the backpropagation algorithm to obtain the preset analysis model.

[0009] Optionally, determining the second temperature information based on the thermal resistance distribution information, the first temperature information, and the corresponding location information includes: The temperature coefficient corresponding to each first temperature information is determined based on the thermal resistance distribution information and the location information; The second temperature information is calculated based on the first temperature information and the corresponding temperature coefficient.

[0010] Optionally, the control sensor collects first temperature information corresponding to each detection position at the current moment, including: The control end temperature sensor collects the first end temperature information of the winding end; The temperature sensor inside the control slot collects the temperature information of the first slot inside the winding slot; The bearing temperature sensor is used to collect the first bearing temperature information at the bearing location. The first temperature information is determined based on the first end temperature information, the first groove temperature information, and the first bearing temperature information.

[0011] Another aspect of the present invention provides a model optimization system based on online parameter identification, comprising: The data acquisition module is used to control the sensor to acquire the first temperature information corresponding to each detection position at the current moment, and to obtain the motor operation data at the current moment; The analysis module is used to determine real-time temperature information based on the motor operating data, the first temperature information, and the corresponding position information; The adjustment module is used to update the speed control model of the doubly fed motor based on the real-time temperature information.

[0012] In another aspect, the present invention provides a model optimization device based on online parameter identification, the model optimization device based on online parameter identification comprising: a memory, a processor, and a model optimization program based on online parameter identification stored in the memory and executable on the processor, the model optimization program based on online parameter identification being configured to implement the steps of the model optimization method based on online parameter identification as described above.

[0013] In another aspect, the present invention provides a storage medium storing a model optimization program based on online parameter identification, wherein the model optimization program based on online parameter identification, when executed by a processor, implements the steps of the model optimization method based on online parameter identification as described above.

[0014] The model optimization method and system based on online parameter identification of the present invention collects the first temperature information corresponding to each detection position at the current moment by controlling the sensor, and obtains the motor operation data at the current moment. Based on the motor operation data, the first temperature information and the corresponding position information, the real-time temperature information is determined, and the speed control model of the doubly fed motor is updated based on the real-time temperature information. This can improve the accuracy of the data received by the speed control model, thereby improving the stability of the generator in generating electricity. Attached Figure Description

[0015] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0016] Figure 1 This is a schematic diagram of the structure of a model optimization device based on online parameter identification in the hardware operating environment involved in the embodiments of the present invention; Figure 2 A flowchart illustrating a first embodiment of a model optimization method based on online parameter identification provided by the present invention; Figure 3 This is a flowchart illustrating a second embodiment of a model optimization method based on online parameter identification provided by the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details are presented in the embodiments of the present invention to facilitate a better understanding of the invention. However, the technical solutions claimed in the present invention can be implemented even without these technical details and various variations and modifications based on the following embodiments. The division of the following embodiments is for ease of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with and referenced by each other without contradiction.

[0018] Reference Figure 1 , Figure 1 This is a schematic diagram of the model optimization device structure based on online parameter identification for the hardware operating environment involved in the embodiments of the present invention.

[0019] like Figure 1 As shown, the model optimization device based on online parameter identification may include: a processor 1001, a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. The processor 1001 may be a central processing unit (CPU). The communication bus 1002 is used to enable communication between these components. The interactive device 1003 may include a display screen or an input unit such as a keyboard. Optionally, the interactive device 1003 may also be connected to the communication bus via standard wired or wireless interfaces. The network interface 1004 may optionally include standard wired or wireless interfaces (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0020] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the model optimization device based on online parameter identification, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0021] The memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a model optimization program based on online parameter identification.

[0022] exist Figure 1 In the model optimization device based on online parameter identification shown, the network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the model optimization device based on online parameter identification of the present invention can be set in the model optimization device based on online parameter identification. The model optimization device based on online parameter identification calls the model optimization program based on online parameter identification stored in the memory 1005 through the processor 1001 and executes the model optimization method based on online parameter identification provided in the embodiment of the present invention.

[0023] This invention provides a model optimization method based on online parameter identification, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a model optimization method based on online parameter identification provided by the present invention.

[0024] In this embodiment, the model optimization method based on online parameter identification includes steps S1 to S3.

[0025] Step S1: Control the sensor to collect the first temperature information corresponding to each detection position at the current moment, and obtain the motor operation data at the current moment.

[0026] In this embodiment, applied to the operation of a doubly-fed induction generator (DFIG), the sensor used is a temperature sensor to detect the current temperature of the motor. It should be noted that the sensor's location is not limited in this embodiment; generally, there are more than three sensors. Optionally, four sensors can be set at different locations: the stator winding end, the bearing housing, and the stator core or housing. Specifically, detecting the stator winding end is used to detect the winding's temperature rise; detecting the area near the rotor slip ring is to monitor the slip ring contact resistance and rotor winding heating; detecting the bearing housing is to monitor bearing frictional heat; and detecting the stator core or housing is to monitor iron loss and overall heat dissipation. Because the thermal resistance differs at different locations, there will be temperature differences. Specifically, the first temperature information at each detection location is collected synchronously according to a preset sampling period, and the motor controller simultaneously reads the current stator three-phase current, rotor current, speed, and DC bus voltage, among other motor operating data.

[0027] Step S2: Determine the real-time temperature information based on the motor operating data, the first temperature information, and the corresponding position information.

[0028] It should be noted that the real-time temperature information here refers to the spatial distribution characteristics of the motor's temperature at the current moment. Preferably, in this embodiment, the temperature data at a preset location can be used as the real-time temperature information. In other embodiments, the continuous spatial distribution data of the motor's temperature at the current moment can also be used as the real-time temperature information. Optionally, the discrete first temperature information is used as a limiting condition, combined with the three-dimensional position information of each sensor in the motor coordinate system, and the temperature field analysis is performed using a least squares support vector machine or a finite element reduced-order model to calculate the temperature data corresponding to the preset location.

[0029] Step S3: Update the speed control model of the doubly fed motor based on the real-time temperature information.

[0030] In this embodiment, the real-time temperature information determined in step S2 is substituted into the thermal parameters of the doubly fed motor speed control model for updating, and a prediction algorithm is used to determine the stator and rotor resistance, leakage inductance, and permanent magnet flux linkage that change with temperature, thereby enabling real-time correction of the electrical parameters in the model. The updated parameters are then injected into the flux linkage observer, speed predictor, and current regulator, ensuring that the speed control model always matches the actual thermal characteristics of the motor, eliminating parameter drift errors caused by temperature rise, and thus improving the stability of power generation.

[0031] In this embodiment, the first temperature information corresponding to each detection position at the current moment is collected by the control sensor, and the motor operation data at the current moment is obtained. The real-time temperature information is determined based on the motor operation data, the first temperature information and the corresponding position information, and the speed control model of the doubly fed motor is updated based on the real-time temperature information. This can improve the accuracy of the data received by the speed control model, thereby improving the stability of the generator in generating electricity.

[0032] Furthermore, based on the first embodiment, a second embodiment of the model optimization method based on online parameter identification of the present invention is proposed. In this embodiment, referring to... Figure 3 The step of determining the real-time temperature information based on the motor operating data, the first temperature information, and the corresponding position information includes steps S21 to S23.

[0033] Step S21: Determine the thermal resistance distribution information based on the motor operating data, and determine the first heat generation information based on the motor operating data.

[0034] In this embodiment, it should be noted that the actual thermal resistance of the motor is related to the maintenance conditions. Different maintenance conditions will lead to different degrees of change in the thermal resistance of the motor. At the same time, by analyzing the motor operating data, the stator copper loss, rotor copper loss and core loss are calculated based on the equivalent circuit model of the doubly fed motor, and mechanical loss is superimposed to form the first heat generation information, thereby quantifying the instantaneous heat generation rate of each heat source point inside the motor.

[0035] Step S22: Determine the second temperature information based on the thermal resistance distribution information, the first temperature information, and the corresponding location information.

[0036] In this embodiment, a heat transfer path is constructed using the known first temperature information and the position information of each sensor in the motor coordinate system, based on the thermal resistance distribution information determined in the previous step. Temperature data at a preset location is calculated using a preset conversion factor and used as the second temperature information. In this embodiment, the temperature data at the preset location can be determined based on finite element analysis. Optionally, for cases requiring complete temperature field information, the temperature data inside the motor can be determined using discrete point temperatures. Optionally, when the number of detected temperature points is large, interpolation can be used to determine the temperature. In this embodiment, the initial temperature field estimate derived from the thermal conduction physical model effectively fills the temperature blind spot in areas not covered by the sensors, realizing a spatial mapping from sparse measurement points to a continuous temperature distribution, providing a reference temperature field for subsequent fusion of heat source information.

[0037] Step S23: Determine real-time temperature information based on the first heating information and the second temperature information.

[0038] In this embodiment, specifically, the first heat generation information is introduced into the thermal network model as a transient heat source term, and the state is updated by extended Kalman filtering based on the second temperature information as the initial state or observation constraint. This allows for real-time correction of the thermal model state composed of material heat capacity, thermal resistance, and convective heat dissipation coefficient, eliminating temperature estimation deviations caused by measurement noise or model errors, and ultimately outputting real-time temperature information that takes into account both heat source dynamics and measured calibration.

[0039] In this embodiment, thermal resistance distribution information is determined by the motor operating data, and first heating information is determined based on the motor operating data. Second temperature information is determined based on the thermal resistance distribution information, the first temperature information, and the corresponding position information. Real-time temperature information is determined based on the first heating information and the second temperature information, thereby improving the accuracy of the real-time temperature information.

[0040] Furthermore, based on the first or second embodiment, a third embodiment of the model optimization method based on online parameter identification of the present invention is proposed. In this embodiment, the motor operating data includes: operating time, operating conditions, and corresponding time lengths; the step of determining thermal resistance distribution information based on the motor operating data includes: The thermal resistance change information is determined based on the preset analysis model, runtime, operating conditions, and corresponding time length. The thermal resistance distribution information is determined based on the preset reference thermal resistance and the thermal resistance change information.

[0041] In this embodiment, by analyzing the cumulative running time, load condition level, and corresponding duration in the motor operating data, a preset analysis model is used to evaluate the aging and decay of the thermal resistance of the insulation material over time, as well as the cumulative degradation of the contact thermal resistance under frequent start-stop conditions. The offset of the model's output relative to the factory reference is used as thermal resistance change information, and this is vector-superimposed with the preset reference thermal resistance set based on the motor structural parameters to correct the effective thermal resistance value of each heat transfer path in real time.

[0042] It should be noted that, compared with the limitations of the traditional constant thermal resistance assumption, this time-varying thermal resistance identification method enables temperature estimation to track the thermal characteristic drift throughout the entire life cycle of the motor, significantly improving the accuracy of thermal state observation under long-term operation.

[0043] Furthermore, before determining the thermal resistance change information based on the preset analysis model, runtime, operating conditions, and corresponding time length, the method further includes: Obtain historical operation datasets, which include multiple sets of historical motor operation data and corresponding historical temperature change curves; Historical heating information is determined based on the historical motor operating data, and historical thermal resistance information is determined based on the historical temperature change curve. The preset neural network model is trained based on the historical heating information and the historical thermal resistance information to obtain the preset analysis model.

[0044] In this embodiment, multiple sets of operating records at different times, load rates, and service years are obtained from the historical operating data of the motor and combined into a historical operating dataset containing electrical parameters and temperature response.

[0045] The actual thermal resistance value at each moment is analyzed from historical temperature change curves using a thermal network inversion algorithm. Simultaneously, the corresponding heat generation power is calculated based on historical motor operating data, forming a mapping sample pair between thermal resistance and heat generation. These sample pairs are then used to train a pre-defined neural network model, enabling it to learn the nonlinear relationship between operating time, operating condition intensity, and thermal resistance degradation. This provides a high-precision predictive model foundation for online thermal resistance identification.

[0046] Furthermore, the step of training a preset neural network model based on the historical heating information and the historical thermal resistance information to obtain the preset analysis model includes: An input feature vector is constructed based on the historical heating information, and an output label is constructed based on the historical thermal resistance information. A training dataset is constructed based on the input feature vector and the output label; The initial neural network model is trained using the training dataset and the backpropagation algorithm to obtain the preset analysis model.

[0047] In this embodiment, feature engineering is performed on historical heat generation information to extract key parameters such as power density, temperature rise rate, and number of thermal cycles to construct input feature vectors. Simultaneously, historical thermal resistance information parsed at corresponding times is used as output labels to form the training dataset required for supervised learning. This dataset is then input into an initial neural network model, and the error gradient between the predicted and actual thermal resistance is calculated using the backpropagation algorithm. The network weights are updated layer by layer to minimize the loss function until the model converges. This yields a usable pre-defined analysis model.

[0048] Furthermore, based on any of the above embodiments, a fourth embodiment of the model optimization method based on online parameter identification of the present invention is proposed. In this embodiment, determining the second temperature information based on the thermal resistance distribution information, the first temperature information, and the corresponding location information includes: The temperature coefficient corresponding to each first temperature information is determined based on the thermal resistance distribution information and the location information; The second temperature information is calculated based on the first temperature information and the corresponding temperature coefficient.

[0049] In this embodiment, the temperature coefficient reflects the ratio of the temperature at a specific measuring point to the temperature at a preset location. The second temperature information is obtained by weighted calculation of all the first temperature information and their corresponding temperature coefficients. In other embodiments, paths closer to the heat source and with lower thermal resistance are given higher weights, while those farther away are attenuated. This establishes a linear mapping between sparse measuring points and a continuous temperature distribution, providing physical constraints for spatial interpolation in subsequent temperature field expansion. Specifically, the second temperature information is obtained by multiplying the temperature coefficient by the first temperature information.

[0050] Furthermore, based on any of the above embodiments, a fifth embodiment of the model optimization method based on online parameter identification of the present invention is proposed, wherein the control sensor collects the first temperature information corresponding to each detection position at the current moment, including: The control end temperature sensor collects the first end temperature information of the winding end; The temperature sensor inside the control slot collects the temperature information of the first slot inside the winding slot; The bearing temperature sensor is used to collect the first bearing temperature information at the bearing location. The first temperature information is determined based on the first end temperature information, the first groove temperature information, and the first bearing temperature information.

[0051] In this embodiment, the bearing temperature information at the bearing location is collected. The bearing serves as the mechanical support point of the rotor system, and its temperature rise originates from friction loss and deterioration of lubrication, directly affecting the rotor dynamic characteristics and air gap uniformity. Monitoring the bearing temperature not only improves the external boundary conditions of the motor thermal network but also provides early warning of the risk of rotor eccentricity or stator rubbing caused by bearing overheating.

[0052] Furthermore, this invention also proposes a model optimization system based on online parameter identification, including a data acquisition module, an analysis module, and an adjustment module.

[0053] The data acquisition module is used to control the sensor to acquire the first temperature information corresponding to each detection position at the current moment, and to obtain the motor operation data at the current moment.

[0054] The analysis module is used to determine real-time temperature information based on the motor operating data, the first temperature information, and the corresponding position information.

[0055] The adjustment module is used to update the speed control model of the doubly fed motor based on the real-time temperature information.

[0056] Furthermore, this invention also proposes a model optimization device based on online parameter identification. The device includes: a memory, a processor, and a model optimization program based on online parameter identification stored in the memory and executable on the processor. The model optimization program based on online parameter identification is configured to implement the steps of the model optimization method based on online parameter identification described above.

[0057] Furthermore, this embodiment of the invention also proposes a storage medium storing a model optimization program based on online parameter identification, wherein when the model optimization program based on online parameter identification is executed by a processor, it implements the steps of the model optimization method based on online parameter identification described above.

[0058] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0059] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0060] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0061] Those skilled in the art will understand that the above embodiments are specific implementations of the present invention, and in practical applications, various changes can be made in form and detail without departing from the spirit and scope of the present invention.

Claims

1. A model optimization method based on online parameter identification, characterized in that, include: The control sensor collects the first temperature information corresponding to each detection position at the current moment, and obtains the motor operation data at the current moment; Real-time temperature information is determined based on the motor operating data, the first temperature information, and the corresponding location information. The speed control model of the doubly fed motor is updated based on the real-time temperature information.

2. The model optimization method based on online parameter identification according to claim 1, characterized in that, The method of determining real-time temperature information based on the motor operating data, the first temperature information, and the corresponding position information includes: The thermal resistance distribution information is determined based on the motor operating data, and the first heat generation information is determined based on the motor operating data; The second temperature information is determined based on the thermal resistance distribution information, the first temperature information, and the corresponding location information. Real-time temperature information is determined based on the first heat generation information and the second temperature information.

3. The model optimization method based on online parameter identification according to claim 1, characterized in that, The motor operating data includes: operating time, operating conditions, and corresponding time duration; determining the thermal resistance distribution information based on the motor operating data includes: The thermal resistance change information is determined based on the preset analysis model, runtime, operating conditions, and corresponding time length. The thermal resistance distribution information is determined based on the preset reference thermal resistance and the thermal resistance change information.

4. The model optimization method based on online parameter identification according to claim 3, characterized in that, Before determining the thermal resistance change information based on the preset analysis model, runtime, operating conditions, and corresponding time length, the method further includes: Obtain historical operation datasets, which include multiple sets of historical motor operation data and corresponding historical temperature change curves; Historical heating information is determined based on the historical motor operating data, and historical thermal resistance information is determined based on the historical temperature change curve. The preset neural network model is trained based on the historical heating information and the historical thermal resistance information to obtain the preset analysis model.

5. The model optimization method based on online parameter identification according to claim 4, characterized in that, The step of training a preset neural network model based on the historical heating information and the historical thermal resistance information to obtain the preset analysis model includes: An input feature vector is constructed based on the historical heating information, and an output label is constructed based on the historical thermal resistance information. A training dataset is constructed based on the input feature vector and the output label; The initial neural network model is trained using the training dataset and the backpropagation algorithm to obtain the preset analysis model.

6. The model optimization method based on online parameter identification according to claim 2, characterized in that, The step of determining the second temperature information based on the thermal resistance distribution information, the first temperature information, and the corresponding location information includes: The temperature coefficient corresponding to each first temperature information is determined based on the thermal resistance distribution information and the location information; The second temperature information is calculated based on the first temperature information and the corresponding temperature coefficient.

7. The model optimization method based on online parameter identification according to any one of claims 1 to 6, characterized in that, The control sensor collects the first temperature information corresponding to each detection position at the current moment, including: The control end temperature sensor collects the first end temperature information of the winding end; The temperature sensor inside the control slot collects the temperature information of the first slot inside the winding slot; The bearing temperature sensor is used to collect the first bearing temperature information at the bearing location. The first temperature information is determined based on the first end temperature information, the first groove temperature information, and the first bearing temperature information.

8. A model optimization system based on online parameter identification, characterized in that, include: The data acquisition module is used to control the sensor to acquire the first temperature information corresponding to each detection position at the current moment, and to obtain the motor operation data at the current moment; The analysis module is used to determine real-time temperature information based on the motor operating data, the first temperature information, and the corresponding position information; The adjustment module is used to update the speed control model of the doubly fed motor based on the real-time temperature information.

9. A model optimization device based on online parameter identification, characterized in that, The model optimization device based on online parameter identification includes: a memory, a processor, and a model optimization program based on online parameter identification stored in the memory and executable on the processor, wherein the model optimization program based on online parameter identification is configured to implement the steps of the model optimization method based on online parameter identification according to any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a model optimization program based on online parameter identification, which, when executed by a processor, implements the steps of the model optimization method based on online parameter identification according to any one of claims 1 to 7.

Images