Motor multi-physical field agent model construction method, device and equipment and medium

By acquiring and processing on-site operation data, combining Latin hypercube sampling and measurement space method, using the preset periodic boundary three-dimensional flow thermal coupling model, the motor multi-physics agent model is constructed, solving the insufficient accuracy and lack of historical data in the existing technology. The problem of utilization improves model accuracy and simulation accuracy.

CN119066878AActive Publication Date: 2024-12-03CHINA THREE GORGES CORPORATION

Patent Information

Application Number
CN202411264430.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-10
Publication Date
2024-12-03
Estimated Expiration
2044-09-10

AI Technical Summary

Technical Problem

The existing simulation model technology and sample point implementation methods have insufficient accuracy in the digital twinning of hydropower and pumping unit equipment, and fail to make full use of on-site historical data, resulting in insufficient accuracy of the built agent model, which increases the construction time and cost.

Method used

By obtaining the initial data set of on-site operating conditions, determining the working condition data range, performing primary sampling and secondary sampling, combining the measurement space method and preset periodic boundary three-dimensional flow thermal coupling model, removing duplicate points, and building a motor multi-physics target Agent model.

Benefits of technology

This improves the model accuracy, reduces the error caused by multi-physics simulation, enhances the accuracy of sample space point acquisition and the fit between on-site data, and avoids the data set errors built in the early stage of the proxy model.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066878A_ABST
    Figure CN119066878A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of model construction, and discloses a motor multi-physical field agent model construction method, device and equipment and a medium, and the method comprises the steps: firstly determining a local working condition data range through a field operation working condition initial data set, and carrying out the local one-time sampling; furthermore, secondary sampling is carried out in a global preset sample three-dimensional space by using a Latin hypercube sampling method. Furthermore, repeated points of two times of sampling can be removed through a measurement space method, and the accuracy of sample space point collection and the fitting degree with field data are improved. Furthermore, simulation can be carried out by presetting the periodic boundary three-dimensional flow thermal coupling model, and the motor multi-physics field target agent model is constructed by using the target data set obtained by simulation, so that by implementing the method, the model precision is improved, and errors caused by multi-physics field simulation are reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of model construction, and in particular to a method, device, equipment and medium for constructing a multi-physics field proxy model of a motor. Background Art

[0002] As the complexity of the model increases, the amount of calculation in multi-physics simulation continues to increase. In the field of digital twin intelligent operation and maintenance of hydropower and pumped storage unit motors, different methods need to be used to construct real-time simulation models for different models, so as to achieve dimensionality reduction or data fitting of numerical calculation orders, and realize real-time display of multi-physics fields of various components through visualization.

[0003] The surrogate model is an efficient mathematical approximation model. It has gradually developed into a new computing method because it can significantly improve computing efficiency. The sampling method studies how to construct a fitting function with the least error using the least sample points and can take into account the random error of the data, while the accuracy of the surrogate model depends on the distribution of the sample points.

[0004] Existing sample space sampling methods include orthogonal design, uniform design, Latin hypercube design and other methods. In the sampling process, the proxy model is often constructed through a single sampling. However, the distribution of a single sampling often has errors and uncertainties, and it is also impossible to optimize the area with insufficient precision. Furthermore, in the process of selecting the sample space, it is not comprehensive to divide the sampling area based on experience without relying on field operation data, which is inconsistent with the actual long-term operation interval of the power station, resulting in insufficient precision of the constructed proxy model, and also increasing the time and cost of constructing the proxy model.

[0005] Therefore, the existing methods that rely on simulation model technology and sample point addition have certain limitations in the digital twin of hydropower and pumped storage equipment. They only use field data as the basis for determining the accuracy of the digital twin model, or completely ignore the role of some valid data in the field historical data. Summary of the invention

[0006] In view of this, the present invention provides a method, device, equipment and medium for constructing a motor multi-physics field proxy model to solve the problem that the existing method relying on simulation model technology and sample point addition only uses field data as the basis for determining the accuracy of the digital twin model, or completely ignores the role of some valid data in the field historical data.

[0007] In a first aspect, the present invention provides a method for constructing a multi-physics proxy model of a motor, the method comprising:

[0008] Acquire the initial data set of the field operating conditions of the target motor; determine the range of the operating condition data based on the initial data set of the field operating conditions; perform a sampling within the range of the operating condition data and determine the first sample point set; perform a secondary sampling in the preset sample three-dimensional space using the Latin hypercube sampling method and determine the second sample point set; obtain the target data set based on the first sample point set and the second sample point set through processing using the metric space method and a preset periodic boundary three-dimensional fluid-thermal coupling model; and use the target data set to construct a multi-physics field target proxy model of the motor.

[0009] The method for constructing a multi-physics proxy model of a motor provided by the present invention first determines the local operating condition data range through the initial data set of the on-site operating condition and performs a local primary sampling. Furthermore, a secondary sampling is performed using the Latin hypercube sampling method in the global preset sample three-dimensional space. Furthermore, the duplicate points of the two samplings can be removed by the metric space method, thereby improving the accuracy of the sample space point acquisition and the degree of fit with the on-site data. Furthermore, a simulation can be performed through a preset periodic boundary three-dimensional fluid-thermal coupling model, and the target data set obtained by the simulation can be used to construct a multi-physics target proxy model of the motor. Therefore, by implementing the present invention, the model accuracy is improved, the error caused by the multi-physics simulation is reduced, and the problem of the existing method of relying on simulation model technology and sample point addition to only use the on-site data as the accuracy of the digital twin model, or completely ignoring the role of some valid data in the on-site historical data, is solved.

[0010] In an optional implementation, determining the operating condition data range based on the initial data set of the on-site operating condition includes:

[0011] The initial data set of the field operating conditions is processed to obtain the target data set of the field operating conditions. Based on the target data set of the field operating conditions, the interquartile range method is used to determine the range of the operating condition data.

[0012] The motor multi-physics field proxy model construction method provided by the present invention, by combining the interquartile range method, can determine the most common operating range of the motor based on the initial data set of field operating conditions, thereby providing support for improving the accuracy of sample space point acquisition and the degree of fit with field data.

[0013] In an optional implementation, based on the first sample point set and the second sample point set, a target data set is obtained by processing with a metric space method and a preset periodic boundary three-dimensional fluid-heat coupling model, including:

[0014] Based on the first sample point set and the second sample point set, the target sample point set is determined through metric space method processing; based on the target sample point set, a preset periodic boundary three-dimensional fluid-thermal coupling model is used for simulation to obtain a target data set.

[0015] The motor multi-physics proxy model construction method provided by the present invention can remove duplicate points of two samplings and determine the final target sample point set through the metric space method, thereby improving the accuracy of sample space point acquisition and the degree of fit with field data. Furthermore, a three-dimensional fluid-thermal coupling model with a preset periodic boundary can be used for simulation and obtain the corresponding target data set, providing data support for the construction of the motor multi-physics target proxy model.

[0016] In an optional implementation, based on the first sample point set and the second sample point set, a target sample point set is determined by processing using a metric space method, including:

[0017] The metric space method is used to determine whether there are repeated sample points in the first sample point set and the second sample point set; when there are no repeated sample points, the target sample point set is determined based on the first sample point set and the second sample point set; when there are repeated sample points, the repeated sample points are deleted in the second sample point set to obtain a third sample point set; the target sample point set is determined based on the first sample point set and the third sample point set.

[0018] In an optional implementation, a motor multi-physics target proxy model is constructed using a target data set, including:

[0019] The target data set is used to construct an initial proxy model of the motor multi-physics field. It is determined whether the error of the initial proxy model of the motor multi-physics field meets the requirements. When the error does not meet the requirements, the model parameters are adjusted and new sample points are selected from the initial data set of the field operating conditions and added to the target sample point set. The training is iterated repeatedly until the target proxy model of the motor multi-physics field that meets the error is obtained.

[0020] The method for constructing a motor multi-physics field proxy model provided by the present invention improves the model training accuracy by adjusting the proxy model parameters and adding field data sample points when the constructed initial motor multi-physics field proxy model does not meet the error requirements, thereby minimizing the data set error of the initial construction of the proxy model, and increasing the fit with the field operation, thereby reducing the error caused by multi-physics field simulation.

[0021] In an optional embodiment, the method further includes:

[0022] When the error meets the requirements, the initial proxy model of the motor multi-physics field is determined as the target proxy model of the motor multi-physics field.

[0023] In a second aspect, the present invention provides a device for constructing a multi-physics field proxy model of a motor, the device comprising:

[0024] An acquisition module is used to acquire an initial data set of the on-site operating conditions of the target motor; a determination module is used to determine the range of the operating condition data based on the initial data set of the on-site operating conditions; a first sampling determination module is used to perform a single sampling within the operating condition data range and determine a first sample point set; a second sampling determination module is used to perform a secondary sampling in a preset sample three-dimensional space using a Latin hypercube sampling method and determine a second sample point set; a processing module is used to obtain a target data set based on the first sample point set and the second sample point set, through processing using a metric space method and a preset periodic boundary three-dimensional fluid-thermal coupling model; and a construction module is used to construct a motor multi-physics field target proxy model using the target data set.

[0025] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for constructing a multi-physics proxy model of a motor according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0026] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for constructing a motor multi-physics field proxy model according to the first aspect or any corresponding embodiment thereof.

[0027] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for constructing a motor multi-physics proxy model according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 is a flow chart of a method for constructing a multi-physics proxy model of a motor according to an embodiment of the present invention;

[0030] Figure 2 is a flow chart of another method for constructing a multi-physics proxy model of a motor according to an embodiment of the present invention;

[0031] Figure 3 is a flow chart of another method for constructing a multi-physics proxy model of a motor according to an embodiment of the present invention;

[0032] Figure 4 is a flow chart of a method for constructing a multi-physics proxy model of a motor based on local enhanced sampling according to an embodiment of the present invention;

[0033] Figure 5 is a structural block diagram of a device for constructing a multi-physics proxy model of a motor according to an embodiment of the present invention;

[0034] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0036] An embodiment of the present invention provides a method for constructing a multi-physics proxy model of a motor. Through local primary sampling and global secondary sampling, and removing duplicate points, the accuracy of sample space point acquisition and the degree of fit with field data are improved. Then, a preset periodic boundary three-dimensional fluid-thermal coupling model is used for simulation and the target data set obtained by simulation is used to construct a multi-physics target proxy model of the motor, which improves the model accuracy and reduces the error caused by multi-physics simulation. It solves the problem that the existing methods that rely on simulation model technology and sample point addition only use field data as the basis for determining the accuracy of the digital twin model, or completely ignore the role of some valid data in the field historical data.

[0037] According to an embodiment of the present invention, an embodiment of a method for constructing a multi-physics proxy model of a motor is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0038] In this embodiment, a method for constructing a multi-physics proxy model of a motor is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers, etc. Figure 1 is a flowchart of a method for constructing a motor multi-physics field proxy model according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0039] Step S101, obtaining an initial data set of on-site operating conditions of a target motor.

[0040] Specifically, the on-site operating condition initial data set may include a plurality of on-site operating condition data of the target motor in a normal operating state.

[0041] In this embodiment, the construction of the stator winding and core temperature field proxy model of the pumped storage motor is taken as an example, and the inlet wind speed V, air temperature T1, stator winding average temperature T2, stator core average temperature T3, stator winding current I rms Form an initial data set of on-site operating conditions.

[0042] Step S102, determining the operating condition data range based on the initial data set of the on-site operating condition.

[0043] Specifically, the most common operating range of the target motor, that is, the operating condition data range, can be determined through the initial data set of the on-site operating conditions.

[0044] Step S103, sampling is performed once within the operating condition data range and a first sample point set is determined.

[0045] Specifically, a three-dimensional space can be constructed in the three-dimensional space according to the determined working condition data range, and uniform sampling is performed in the space to collect N sample point data, namely, N first sample points. The sampling interval distance is set to M.

[0046] In one example, taking the construction of the proxy model of the stator winding and core temperature field of a pumped storage motor as an example, the data range of the three variables of wind speed, temperature and current is obtained to construct a three-dimensional space in the three-dimensional space.

[0047] Step S104: In the preset sample stereo space, a Latin hypercube sampling method is used to perform secondary sampling and determine a second sample point set.

[0048] The preset sample three-dimensional space represents a global sample three-dimensional space composed of a data range set according to experience.

[0049] Specifically, Latin hypercube sampling is performed in the preset sample stereo space to collect N ′ The sample point data is N ′ The second sample point.

[0050] In one example, taking the construction of the pumped storage motor stator winding and core temperature field proxy model as an example, according to experience, the data ranges of the three variables of wind speed, temperature, and current are set [V x ,V y ]、[T x ,T y ]、[I x ,I y ] and establish the corresponding preset sample three-dimensional space.

[0051] Step S105 , based on the first sample point set and the second sample point set, a target data set is obtained by processing through a metric space method and a preset periodic boundary three-dimensional fluid-thermal coupling model.

[0052] Among them, the metric space defines a distance function on a set, so that the distance between any two elements in the set can be calculated through this distance function.

[0053] Furthermore, the preset periodic boundary three-dimensional fluid-thermal coupling model is a fluid-temperature coupling field simulation model. Based on the actual motor structure, the periodic boundary can be intercepted during simulation, that is, a certain part can be intercepted for multi-physical field simulation, and the corresponding temperature value can be output according to the input conditions.

[0054] Specifically, by combining the metric space method and the preset periodic boundary three-dimensional fluid-heat coupling model, the final target data set for model training can be obtained.

[0055] Step S106, constructing a motor multi-physics field target proxy model using the target data set.

[0056] Specifically, the target dataset is standardized or normalized to have zero mean and unit variance to improve model performance.

[0057] Furthermore, an appropriate kernel function radial basis function (RBF) kernel is selected to handle nonlinear problems.

[0058] Furthermore, the processed target data set is used to train the SVM model, and the model parameters, such as the penalty parameter (C) and the kernel function parameters (such as γ of the RBF kernel), are determined.

[0059] Furthermore, techniques such as cross validation and grid search are used to find the optimal model parameters.

[0060] Furthermore, the model parameters and the target data set are combined to perform model training until a motor multi-physics field target proxy model that meets the conditions is obtained.

[0061] The method for constructing a multi-physics proxy model of a motor provided in this embodiment first determines the local operating condition data range through the initial data set of the on-site operating condition and performs a local primary sampling. Further, a secondary sampling is performed using the Latin hypercube sampling method in the global preset sample three-dimensional space. Further, the duplicate points of the two samplings can be removed by the metric space method, thereby improving the accuracy of the sample space point acquisition and the degree of fit with the field data. Further, a simulation can be performed through a preset periodic boundary three-dimensional fluid-thermal coupling model and the target data set obtained by the simulation can be used to construct a multi-physics target proxy model of the motor. Therefore, by implementing the present invention, the model accuracy is improved, the error caused by the multi-physics simulation is reduced, and the problem of existing methods that rely on simulation model technology and sample point addition to only use field data as the accuracy of the digital twin model, or completely ignore the role of some valid data in the field historical data, is solved.

[0062] In this embodiment, a method for constructing a multi-physics proxy model of a motor is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers, etc. Figure 2 is a flowchart of a method for constructing a motor multi-physics field proxy model according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0063] Step S201, obtain the initial data set of the field operating conditions of the target motor. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0064] Step S202: determining the operating condition data range based on the initial data set of the on-site operating condition.

[0065] Specifically, the above step S202 includes:

[0066] Step S2021, processing the initial data set of the on-site operating conditions to obtain a target data set of the on-site operating conditions.

[0067] Specifically, taking the construction of the proxy model of the stator winding and core temperature field of the pumped storage motor as an example, the inlet wind speed V, air temperature T1, stator winding heat source P1, and stator core heat source P2 are selected as independent variables, and the stator winding average temperature T2 and the stator core average temperature T3 are selected as dependent variables, that is, the target data set of the on-site operating conditions can include the inlet wind speed V, air temperature T1, stator winding heat source P1, stator core heat source P2, stator winding average temperature T2, and stator core average temperature T3.

[0068] According to the description of step S101, after obtaining the initial data set of the field operating conditions, the stator winding heat source P1 is calculated using the following relationship (1):

[0069] P1=P copper +Pstray (1)

[0070] Where: P copper represents the copper loss (unit: watt, W), which is calculated by the following relations (2) and (3):

[0071]

[0072]

[0073] Where: I rms Indicates the effective value of current (unit: ampere, A); R coil represents the winding resistance (unit: ohm, Ω); ρ represents the resistivity of the wire (unit: ohm·meter, Ω·m), which is related to the material and temperature; l represents the length of the wire (unit: meter, m); A represents the cross-sectional area of ​​the wire (unit: square meter, m 2 ).

[0074] Further, P stray represents the stray loss (unit: watt, W), which is calculated by the following relations (4) to (6):

[0075]

[0076] B=μ·H (5)

[0077]

[0078] Where: k represents a proportional constant, which depends on the material and structure of the winding; B max represents the maximum value of magnetic flux density (unit: Tesla, T); f represents the operating frequency (unit: Hertz, Hz); V coil Indicates the winding volume (unit: cubic meter, m 3 ), B represents magnetic flux density, μ represents magnetic permeability (unit: Henry / meter, H / m), H represents magnetic field strength, N represents the number of turns of the coil, and I represents the effective length of the coil.

[0079] Furthermore, the stator core heat source P2 is calculated using the following equation (7):

[0080] P2=P h +P e (7)

[0081] Where: P h represents the hysteresis loss (unit: watt, W), as shown in the following equation (8); P e represents the eddy current loss (unit: Watt, W), as shown in the following equation (9):

[0082]

[0083]

[0084] Where: k1 represents the hysteresis loss coefficient of the material (unit: W / kg); V represents the volume of the core (unit: cubic meter, m 3 ), σ represents the electrical conductivity of the material (unit: Siemens / meter, S / m), and t represents the thickness of the core.

[0085] Step S2022: Based on the on-site operating condition target data set, the interquartile range method is used to determine the operating condition data range.

[0086] Specifically, taking the construction of the proxy model of the stator winding and core temperature field of the pumped storage motor as an example, the process of determining the operating condition data range may include the following steps:

[0087] (1) Data on wind speed, temperature, and current are usually recorded in a time series format, which includes a timestamp and the corresponding temperature reading.

[0088] (2) The corresponding physical quantity values ​​are extracted every 10 minutes as a node, and sampling is performed at equal time intervals to form a field operation range data set.

[0089] (3) Use the interquartile range to determine the range of physical quantities. For each physical quantity, after sorting the data from small to large, the value at the 25% position is set as Q1, and the value at the 75% position is set as Q3, then the operating data range IQR = Q3-Q1. Among them, the physical quantities include wind speed, temperature, and current. For each physical parameter, it is composed of a corresponding set of values. Here, the physical quantity is divided for each physical quantity data set.

[0090] Step S203, perform a sampling within the working condition data range and determine the first sample point set. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0091] Step S204: In the preset sample stereo space, a Latin hypercube sampling method is used to perform secondary sampling and determine a second sample point set. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0092] Step S205 , based on the first sample point set and the second sample point set, a target data set is obtained by processing through a metric space method and a preset periodic boundary three-dimensional fluid-thermal coupling model.

[0093] Specifically, the above step S205 includes:

[0094] Step S2051: Based on the first sample point set and the second sample point set, a target sample point set is determined by processing using a metric space method.

[0095] Specifically, the metric space method can be used to remove duplicate sample points in the first sample point set and the second sample point set to obtain the final target sample point set.

[0096] In some optional implementations, the above step S2051 includes:

[0097] Step a1: using the metric space method to determine whether there are duplicate sample points in the first sample point set and the second sample point set.

[0098] Step a2: when there are no repeated sample points, determine a target sample point set based on the first sample point set and the second sample point set.

[0099] Step a3: when there are duplicate sample points, delete the duplicate sample points in the second sample point set to obtain a third sample point set.

[0100] Step a4: determining a target sample point set based on the first sample point set and the third sample point set.

[0101] Specifically, according to the metric space method, a distance metric (such as Euclidean distance) d(p,q) is defined as shown in the following equation (10):

[0102]

[0103] Where: p and q represent two points in three-dimensional space respectively.

[0104] Furthermore, a threshold is set. If the distance between the new sample in the second sample point set and any sample point in the known first sample point set is less than the threshold, they are considered to be duplicates. At this time, a point in the second sample point set obtained by Latin hypercube sampling is deleted, and the final third sample point set N is obtained. n .

[0105] Further, we get the final target sample point set m=N+N n .

[0106] Step S2052: Based on the target sample point set, a preset periodic boundary three-dimensional fluid-thermal coupling model is used to perform simulation to obtain a target data set.

[0107] Specifically, taking the construction of the temperature field proxy model of the stator winding and iron core of the pumped storage motor as an example, the preset periodic boundary three-dimensional fluid-thermal coupling model is a periodic boundary three-dimensional fluid-thermal coupling model based on the stator winding and the iron core.

[0108] Furthermore, for the m operating points corresponding to the target sample point set, based on the periodic boundary three-dimensional fluid-heat coupling model of the stator winding and the core, the numerical simulation of the operating points is realized by commercial software, and the average temperature of the stator winding and the stator core under different operating conditions is generated, and the corresponding target data set A′ is generated, as shown in the following equation (11):

[0109]

[0110] Step S206: Use the target data set to construct a motor multi-physics target proxy model. Figure 1 Step S106 of the illustrated embodiment will not be described in detail here.

[0111] The method for constructing a multi-physics proxy model of a motor provided in this embodiment first combines the interquartile range method to determine the most frequently operating range of the motor based on the initial data set of the field operating conditions and perform local sampling. Secondly, the Latin hypercube sampling method is used to perform secondary sampling in the global preset sample three-dimensional space. Then, the duplicate points of the two samples can be removed by the metric space method and the final target sample point set can be determined, thereby improving the accuracy of the sample space point acquisition and the degree of fit with the field data. Further, the simulation can be performed and the corresponding target data set can be obtained by presetting the periodic boundary three-dimensional fluid-heat coupling model. Finally, the target proxy model of the multi-physics target of the motor is constructed using the target data set. Therefore, by implementing the present invention, the model accuracy is improved, the error caused by the multi-physics simulation is reduced, and the problem that the existing simulation model technology and the sample point addition implementation method only use the field data as the accuracy of the digital twin model, or completely ignore the role of some valid data in the field historical data, is solved.

[0112] In this embodiment, a method for constructing a multi-physics proxy model of a motor is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers, etc. Figure 3 is a flowchart of a method for constructing a motor multi-physics field proxy model according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0113] Step S301, obtain the initial data set of the field operating conditions of the target motor. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0114] Step S302: Determine the operating condition data range based on the initial data set of the on-site operating condition. Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0115] Step S303, perform a sampling within the working condition data range and determine the first sample point set. Figure 1Step S103 of the illustrated embodiment will not be described in detail here.

[0116] Step S304: In the preset sample stereo space, a Latin hypercube sampling method is used to perform secondary sampling and determine a second sample point set. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0117] Step S305: Based on the first sample point set and the second sample point set, the target data set is obtained by processing the metric space method and the preset periodic boundary three-dimensional fluid-heat coupling model. Figure 2 Step S205 of the illustrated embodiment will not be described in detail here.

[0118] Step S306: construct a motor multi-physics field target proxy model using the target data set.

[0119] Specifically, the above step S306 includes:

[0120] Step S3061, constructing an initial proxy model of the motor multi-physics field using the target data set.

[0121] Specifically, according to the description of step S106 , the target data set is first used to construct an initial proxy model of the motor multi-physics field.

[0122] Step S3062, determining whether the error of the initial proxy model of the motor multi-physics field meets the requirements.

[0123] Specifically, the trained model is used to fit the data and the location of the support vectors in the data set is found.

[0124] Furthermore, the accuracy and generalization ability of the model are evaluated: n field conditions and corresponding output temperature values ​​are randomly selected, and the output temperature value Y of the selected sample point is determined. n and the surrogate model predicted value Y ′ The average error value of n ave , whether it exceeds the specified efficiency value by 10%.

[0125] Among them, the average error value ρ ave It can be calculated by the following relations (12) and (13):

[0126]

[0127] Step S3063, when the error does not meet the requirements, adjust the model parameters and select new sample points from the initial data set of the field operating conditions to add to the target sample point set, and iterate the training until a motor multi-physics field target proxy model that meets the error is obtained.

[0128] Specifically, if the error does not meet the requirement, the output temperature value Y of the sample point is selected n and the surrogate model predicted value Y ′ The average error value of n ave If the efficiency exceeds the specified value by 10%, the model parameters are adjusted according to the model evaluation results to optimize the model performance. At the same time, some new sample points are selected from the data set of the on-site working conditions and added to the sample space, that is, to the target sample point set. Repeated iterative training is carried out until the error meets the requirements to obtain the corresponding motor multi-physics field target proxy model.

[0129] Step S3064: when the error meets the requirement, the motor multi-physics field initial proxy model is determined as the motor multi-physics field target proxy model.

[0130] Specifically, if the error meets the requirement, the output temperature value Y of the sample point is selected n and the surrogate model predicted value Y ′ The average error value of n ave If the efficiency does not exceed the specified value by 10%, the initial multi-physics proxy model of the motor will be used as the final multi-physics target proxy model of the motor.

[0131] The method for constructing a multi-physics proxy model of a motor provided in this embodiment first determines the local operating condition data range through the initial data set of the on-site operating condition and performs a local primary sampling. Further, the Latin hypercube sampling method is used to perform secondary sampling in the global preset sample three-dimensional space. Further, the duplicate points of the two samplings can be removed by the metric space method, thereby improving the accuracy of the sample space point acquisition and the degree of fit with the on-site data. Further, the simulation can be performed through the preset periodic boundary three-dimensional fluid-thermal coupling model and the target data set obtained by the simulation can be used to construct the initial proxy model of the multi-physics field of the motor. Further, when the constructed initial proxy model of the multi-physics field of the motor does not meet the error requirements, the model training accuracy is improved by adjusting the proxy model parameters and adding field data sample points, thereby minimizing the error of the data set constructed in the initial stage of the proxy model, while increasing the fit with the on-site operation and reducing the error caused by the multi-physics field simulation.

[0132] In one example, a method for constructing a multi-physics proxy model of a motor based on local enhanced sampling is provided. The specific process is as follows: Figure 4 As shown in the figure, by implementing this process, the construction of the unit equipment agent model becomes more efficient and accurate. The beneficial effects of this method are not only reflected in improving work efficiency and accuracy, but also in promoting the intelligent and digital process in the field of hydropower and pumped storage engineering, and providing support for the innovation and development of engineering management.

[0133] In this embodiment, a motor multi-physics proxy model construction device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0134] This embodiment provides a motor multi-physics field proxy model construction device, such as Figure 5 As shown, including:

[0135] The acquisition module 501 is used to acquire an initial data set of the on-site operating conditions of the target motor.

[0136] The determination module 502 is used to determine the operating condition data range based on the initial data set of the on-site operating condition.

[0137] The first sampling determination module 503 is used to perform a sampling within the operating condition data range and determine a first sample point set.

[0138] The second sampling determination module 504 is used to perform secondary sampling in a preset sample three-dimensional space by using a Latin hypercube sampling method and determine a second sample point set.

[0139] The processing module 505 is used to obtain a target data set based on the first sample point set and the second sample point set through a metric space method and a preset periodic boundary three-dimensional fluid-thermal coupling model.

[0140] The construction module 506 is used to construct a motor multi-physics target proxy model using the target data set.

[0141] In some optional implementations, the determining module 502 includes:

[0142] The processing submodule is used to process the initial data set of the field operation condition to obtain the target data set of the field operation condition.

[0143] The first determination submodule is used to determine the range of the operating condition data by using the interquartile range method based on the on-site operating condition target data set.

[0144] In some optional implementations, the processing module 505 includes:

[0145] The processing and determination submodule is used to determine the target sample point set based on the first sample point set and the second sample point set through metric space method processing.

[0146] The simulation submodule is used to perform simulation based on the target sample point set using a preset periodic boundary three-dimensional fluid-thermal coupling model to obtain a target data set.

[0147] In some optional implementations, the processing and determining submodule includes:

[0148] The judging unit is used to judge whether there are repeated sample points in the first sample point set and the second sample point set by using the metric space method.

[0149] The first determining unit is configured to determine a target sample point set based on the first sample point set and the second sample point set when there are no repeated sample points.

[0150] The deleting unit is used to delete the duplicate sample points in the second sample point set when there are duplicate sample points, so as to obtain a third sample point set.

[0151] The second determining unit is configured to determine a target sample point set based on the first sample point set and the third sample point set.

[0152] In some optional implementations, the construction module 506 includes:

[0153] The construction submodule is used to build an initial multiphysics proxy model of the motor using the target dataset.

[0154] The judgment submodule is used to judge whether the error of the initial proxy model of the motor multi-physics field meets the requirements.

[0155] The iteration module is used to adjust the model parameters and select new sample points from the initial data set of the field operating conditions to add to the target sample point set when the error does not meet the requirements, and repeatedly iterate the training until the motor multi-physics field target proxy model that meets the error is obtained.

[0156] In some optional implementations, the construction module 506 further includes:

[0157] The second determination submodule is used to determine the motor multi-physics field initial proxy model as the motor multi-physics field target proxy model when the error meets the requirement.

[0158] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0159] The motor multi-physics field proxy model building device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0160] The embodiment of the present invention also provides a computer device having the above Figure 5 The apparatus for building a multiphysics proxy model of an electric motor is shown.

[0161] See also Figure 6 , Figure 6 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0162] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0163] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0164] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0165] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0166] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0167] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0168] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0169] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for constructing a multi-physics proxy model of a motor, characterized in that: The method comprises: Obtaining an initial data set of the field operating conditions of the target motor; Determining a range of operating condition data based on the initial data set of on-site operating conditions; Performing a sampling within the operating condition data range and determining a first sample point set; In the preset sample three-dimensional space, a Latin hypercube sampling method is used to perform secondary sampling and determine a second sample point set; Based on the first sample point set and the second sample point set, a target data set is obtained by processing the first sample point set and the second sample point set using a metric space method and a preset periodic boundary three-dimensional fluid-thermal coupling model; The target data set is used to construct a motor multi-physics target proxy model.

2. The method according to claim 1, characterized in that Determining the operating condition data range based on the initial data set of the on-site operating condition includes: Processing the initial data set of field operating conditions to obtain a target data set of field operating conditions; Based on the on-site operating condition target data set, the operating condition data range is determined using the interquartile range method.

3. The method according to claim 1, characterized in that Based on the first sample point set and the second sample point set, a target data set is obtained by processing with a metric space method and a preset periodic boundary three-dimensional fluid-thermal coupling model, including: Based on the first sample point set and the second sample point set, a target sample point set is determined by processing with a metric space method; Based on the target sample point set, a preset periodic boundary three-dimensional fluid-thermal coupling model is used to perform simulation to obtain the target data set.

4. The method according to claim 3, characterized in that Based on the first sample point set and the second sample point set, a target sample point set is determined by processing using a metric space method, including: Using the metric space method to determine whether there are duplicate sample points in the first sample point set and the second sample point set; When there are no repeated sample points, determining the target sample point set based on the first sample point set and the second sample point set; When there are repeated sample points, the repeated sample points are deleted from the second sample point set to obtain a third sample point set; The target sample point set is determined based on the first sample point set and the third sample point set.

5. The method according to claim 3, characterized in that: The target data set is used to construct a motor multi-physics target proxy model, including: Using the target data set to construct an initial proxy model of the motor multi-physics field; Determining whether the error of the initial proxy model of the motor multi-physics field meets the requirements; When the error does not meet the requirements, the model parameters are adjusted and new sample points are selected from the initial data set of the field operating conditions and added to the target sample point set, and the training is iterated repeatedly until a motor multi-physics field target proxy model that meets the error is obtained.

6. The method according to claim 5, characterized in that The method further comprises: When the error meets the requirement, the motor multi-physics field initial proxy model is determined as the motor multi-physics field target proxy model.

7. A motor multi-physics field proxy model construction device, characterized in that: The device comprises: An acquisition module, used to acquire an initial data set of the field operating conditions of the target motor; A determination module, configured to determine a range of operating condition data based on the initial data set of the on-site operating condition; A first sampling determination module, used for performing a sampling within the operating condition data range and determining a first sample point set; A second sampling determination module is used to perform secondary sampling and determine a second sample point set in a preset sample three-dimensional space by using a Latin hypercube sampling method; A processing module, configured to obtain a target data set based on the first sample point set and the second sample point set by processing them through a metric space method and a preset periodic boundary three-dimensional fluid-thermal coupling model; A construction module is used to construct a motor multi-physics field target proxy model using the target data set.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the motor multi-physics field proxy model construction method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the motor multi-physics field proxy model construction method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to cause a computer to execute the method for constructing a multi-physics proxy model of a motor according to any one of claims 1 to 6.

Citation Information

Patent Citations

  • Motor multi-target robustness optimization method based on local agent model

    CN114398824A

  • Method and system for optimizing power of floating wind power plant based on assistance of proxy model

    CN115809594A

  • Motor combination agent model construction method, system and device and storage medium

    CN116432403A

  • Motor temperature stress field proxy model construction method and device, equipment and medium

    CN118395802A

  • Method and device for constructing multi-physics field digital twinborn simulation model of power equipment

    CN118468983A

Cited By

  • Motor multi-physical field agent model construction method and related device

    CN120012617A

  • Method and device for constructing digital real-time simulation model of generator stator

    CN120068668A