CN117494779A - Training method of structure optimization model, structure optimization method and device - Google Patents
Training method of structure optimization model, structure optimization method and device Download PDFInfo
- Publication number
- CN117494779A CN117494779A CN202311754483.XA CN202311754483A CN117494779A CN 117494779 A CN117494779 A CN 117494779A CN 202311754483 A CN202311754483 A CN 202311754483A CN 117494779 A CN117494779 A CN 117494779A
- Authority
- CN
- China
- Prior art keywords
- network
- density
- stress
- training
- predicted
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 169
- 238000005457 optimization Methods 0.000 title claims abstract description 164
- 238000000034 method Methods 0.000 title claims abstract description 90
- 238000005070 sampling Methods 0.000 claims abstract description 147
- 230000006870 function Effects 0.000 claims description 75
- 238000009826 distribution Methods 0.000 claims description 27
- 238000003860 storage Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000013461 design Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 239000002699 waste material Substances 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000011089 mechanical engineering Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a training method of a structure optimization model, a structure optimization method and a device, and relates to the technical field of artificial intelligence. The specific implementation scheme is as follows: sampling the component structure of a sample engineering component in the engineering field to obtain a plurality of sampling points of the sample engineering component; training a stress solving network in the structure optimization model based on the position information of the sampling points to obtain predicted stress of the sampling points; training a density solving network in the structure optimization model based on the predicted stress to obtain the predicted density of the sampling points; based on the position information, the predicted stress and the predicted density of the sampling points, respectively adjusting network parameters of the stress solving network and the density solving network, and continuously training the adjusted network until the end condition of model training is met, so as to obtain the target structure optimization model.
Description
Technical Field
The disclosure relates to the technical field of artificial intelligence, and in particular relates to a training method of a structure optimization model, a structure optimization method and a device.
Background
In order to realize no meshing in the structural topology optimization process, the waste of resources and time is avoided, the structural topology optimization can be performed by using a deep learning network, but the deep learning network cannot give consideration to physical information and structural space information, and has the defects of large data demand, difficult understanding of results and obvious defects.
Disclosure of Invention
The present disclosure provides a training method, a structure optimization method, an apparatus, an electronic device, a storage medium, and a computer program product for a structure optimization model.
According to an aspect of the present disclosure, there is provided a training method of a structural optimization model, including: sampling the component structure of a sample engineering component in the engineering field to obtain a plurality of sampling points of the sample engineering component; training a stress solving network in the structure optimization model based on the position information of the sampling points to obtain predicted stress of the sampling points; training a density solving network in the structure optimization model based on the predicted stress to obtain the predicted density of the sampling point; based on the position information of the sampling points, the predicted stress and the predicted density, respectively adjusting network parameters of the stress solving network and the density solving network, and continuously training the adjusted network until the end condition of model training is met, so as to obtain a target structure optimization model.
According to another aspect of the present disclosure, there is provided a structure optimization method, including: acquiring a component structure of a target engineering component to be optimized; and carrying out density prediction on the component structure of the target engineering component based on a target structure optimization model to obtain density distribution data of the component structure of the target engineering component, wherein the target structure optimization model is a model trained by the training method.
According to another aspect of the present disclosure, there is provided a training apparatus of a structure optimization model, including: the sampling module is used for sampling the component structure of the sample engineering component in the engineering field to obtain a plurality of sampling points of the sample engineering component; the first training module is used for training a stress solving network in the structure optimization model based on the position information of the sampling points to obtain predicted stress of the sampling points; the second training module is used for training a density solving network in the structure optimization model based on the predicted stress to obtain the predicted density of the sampling point; and the adjusting module is used for respectively adjusting network parameters of the stress solving network and the density solving network based on the position information of the sampling points, the predicted stress and the predicted density, and continuously training the adjusted network until the end condition of model training is met, so as to obtain a target structure optimization model.
According to another aspect of the present disclosure, there is provided a structure optimizing apparatus including: the acquisition module is used for acquiring the component structure of the target engineering component to be optimized; the prediction module is used for predicting the density of the component structure of the target engineering component based on a target structure optimization model to obtain density distribution data of the component structure of the target engineering component, wherein the target structure optimization model is a model trained by the training method.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, where the instructions are executable by the at least one processor, so that the at least one processor can execute the training method and the structure optimization method of the structure optimization model according to the embodiments of the foregoing aspect.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium having stored thereon computer instructions for causing the computer to execute the training method and the structure optimization method of the structure optimization model according to the embodiments of the above aspect.
According to another aspect of the present disclosure, there is provided a computer program product including a computer program/instruction, which when executed by a processor, implements the training method and the structure optimization method of the structure optimization model according to the embodiments of the foregoing aspect.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is a schematic flow chart of a training method of a structure optimization model according to an embodiment of the disclosure;
FIG. 2 is a flow chart of another training method of a structural optimization model according to an embodiment of the present disclosure;
FIG. 3 is a schematic flow chart of training a structure optimization model according to an embodiment of the disclosure;
FIG. 4 is a flowchart of another training method of a structural optimization model according to an embodiment of the present disclosure;
fig. 5 is a schematic flow chart of a structure optimization method according to an embodiment of the disclosure;
Fig. 6 is a schematic structural diagram of a training device for a structural optimization model according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a structure optimizing apparatus according to an embodiment of the present disclosure;
FIG. 8 is a block diagram of an electronic device for implementing a training method for a structural optimization model in accordance with an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Artificial intelligence (Artificial Intelligence, AI) is a piece of technical science that studies, develops theories, methods, techniques and application systems for simulating, extending and expanding human intelligence. At present, the AI technology has the advantages of high automation degree, high accuracy and low cost, and is widely applied.
Deep Learning (DL) is a new research direction in the field of Machine Learning (ML), and is an inherent rule and expression hierarchy of Learning sample data, so that a Machine can analyze Learning ability like a person, can recognize data such as characters, images and sounds, and is widely applied to speech and image recognition.
Structural topology optimization is an important engineering task and is currently widely applied to engineering fields such as aerospace, automobile manufacturing, building design, mechanical engineering and the like to improve product design, improve performance and reduce material and energy waste. The method can be used for designing the structure of new materials, improving the strength and durability of the materials, or designing the structure of certain specific parts, and ensuring the structural strength while reducing the weight of the structure.
The training method of the structural optimization model provided by the embodiment of the disclosure can be applied to the engineering fields of aerospace, automobile manufacturing, building design and the like, and is mainly aimed at structural design and optimization of engineering components.
Fig. 1 is a flow chart of a training method of a structural optimization model according to an embodiment of the disclosure. As shown in fig. 1, the training method of the structural optimization model may include:
s101, sampling the component structure of a sample engineering component in the engineering field to obtain a plurality of sampling points of the sample engineering component.
It should be noted that, the execution body of the training method of the structure optimization model in the embodiment of the disclosure may be a hardware device with data information processing capability and/or software necessary for driving the hardware device to work. Alternatively, the execution body may include a server, a computer, a user terminal, and other intelligent devices. The embodiments of the present disclosure are not particularly limited.
It is understood that the component structure of an engineering component refers to a machine-or deep-learned structure designed and constructed to solve specific problems of the component in the engineering field. The component structure of the engineering component may be a network topology.
In some implementations, a plurality of sampling points of a sample engineering component are obtained by sampling a component structure of the sample engineering component. The sampling points collect position information. For example, the sampling points are (x, y, z) in the spatial coordinate system. Alternatively, the component structure of the sample engineering component may be sampled randomly, and also may be sampled uniformly on the component structure of the sample engineering component, so as to obtain a plurality of sampling points. For example, center regions, edge regions, corner regions, etc. on the component structure of the sample engineering component may be sampled.
S102, training a stress solving network in the structure optimization model based on the position information of the sampling points to obtain predicted stress of the sampling points.
In some implementations, a stress solving network in the structural optimization model can be pre-constructed, and position information of the sampling points is input into the stress solving network for training to obtain predicted stress of the sampling points. Wherein the stress solving network may be a linear neural network, the predicted stress is denoted (u, v, w).
Optionally, the training times of the stress solving network can be set, and when the training times of the stress solving network reach the set times, the training of the stress solving network is ended, and then the training of the density solving network is started.
And S103, training a density solving network in the structure optimization model based on the predicted stress to obtain the predicted density of the sampling point.
In some implementations, a density solution network in the structural optimization model may be pre-built, and the predicted stress may be input into the density solution network for training to obtain the predicted density of the sampling points. Wherein the density solving network may be a convolutional neural network, and the predicted density is denoted as (d).
In some implementations, the stress solving network and the density solving network may be trained alternately. That is, the training times of the stress solving network and the training times of the density solving network can be set respectively, the stress solving network is trained first, when the training times reach the set times, the density solving network is trained, and when the training times of the density solving network reach the set times, the stress solving network is trained continuously. In the embodiment of the disclosure, by alternately training the two solving networks, the error accumulation of serial training of the two solving networks can be reduced, and the training precision of the two solving networks can be improved.
For example, the stress solving network is trained first, when the training times reach 50 times, the density solving network is trained, and when the training times reach 100 times, the stress solving network is trained back.
And S104, respectively adjusting network parameters of the stress solving network and the density solving network based on the position information, the predicted stress and the predicted density of the sampling points, and continuously training the adjusted network until the end condition of model training is met, so as to obtain the target structure optimization model.
In some implementations, a loss function of the stress solving network may be determined based on the location information of the sampling points, the predicted stress, and the predicted density, network parameters of the stress solving network may be adjusted based on the loss function, and training of the adjusted stress solving network may continue.
In some implementations, a loss function of the density solution network may also be determined based on the location information of the sampling points, the predicted stress, and the predicted density, network parameters of the density solution network may be adjusted based on the loss function, and training of the adjusted density solution network may be continued.
Optionally, because the stress solving network and the density solving network are trained alternately, network parameters of the stress solving network can be adjusted based on a loss function of the stress solving network, and training of the adjusted stress solving network is continued until the set times are reached. Further, based on the loss function of the density solving network, network parameters of the density solving network are adjusted, and training is carried out on the adjusted density solving network continuously.
Alternatively, the end condition of model training may be determined based on a loss function of the density solution network. The smaller the loss function is, the better the training effect of the model is, the threshold value of the loss function of the density solving network can be set, and the loss function of the density solving network is smaller than or equal to the set threshold value and is used as the ending condition of model training.
In some implementations, when training is performed on the adjusted network, determining whether a loss function of the density solution network is less than or equal to a set threshold, and in response to the loss function of the density solution network being less than or equal to the set threshold, determining that an end condition of model training is met, ending training on the structural optimization model, and obtaining the target structural optimization model.
According to the training method of the structure optimization model, which is provided by the embodiment of the disclosure, the component structure of the sample engineering component in the engineering field is sampled to obtain a plurality of sampling points of the sample engineering component, and the position information of the sampling points is input into a stress solving network in the structure optimization model for training to obtain the predicted stress of the sampling points. And then the predicted stress is input into a density solving network in the structure optimization model for training, so that the predicted density of the sampling points is obtained, and the relevance between stress information and density information can be improved. Further, based on the position information, the predicted stress and the predicted density of the sampling points, the network parameters are adjusted, and the adjusted network is continuously trained until the structural optimization model meets the training ending condition, so that the target structural optimization model is obtained, the generalization capability of the target structural optimization model is improved, the position information, the stress and the density are combined, the capturing and the application of the target structural optimization model to the space information can be improved in the model optimization process, the target structural optimization model is helped to understand the space relation and the geometric structure of the engineering component, and the problem of insufficient interpretability when the target structural optimization model solves the physical problem is solved.
Fig. 2 is a flow chart of a training method of a structural optimization model according to an embodiment of the disclosure. As shown in fig. 2, the training method of the structural optimization model may include:
s201, sampling the component structure of the sample engineering component in the engineering field to obtain a plurality of sampling points of the sample engineering component.
S202, training a stress solving network in the structure optimization model based on the position information of the sampling points to obtain predicted stress of the sampling points.
And S203, training a density solving network in the structure optimization model based on the predicted stress to obtain the predicted density of the sampling points.
The relevant content of steps S201-S203 can be seen in the above embodiments, and will not be described here again.
In some implementations, the stress solving network is a linear neural network, the density solving network is a convolutional neural network, the stress solving network is connected with the density solving network in series, the stress information and the density information can be directly related, and a real determination prediction result can be provided.
When the network in the structure optimization model is trained, the stress solving network and the density solving network are trained alternately, and network parameters of the other network are maintained in the process of training one network, so that the association and fusion of stress information and density information can be promoted, and the overall performance of the model is improved.
That is, training of one network is initiated each time the number of training of the other network reaches a first set number. Each time the training parameters of the other network reach the second set number, training of one of the networks is started.
For example, assuming that the first set number of times of the stress solving network is 100, and the second set number of times of the density solving network is 80, when the training number of times of the stress solving network reaches 100 times, training on the density solving network is started; when the training times of the density solving network reach 80 times, training of the stress solving network is started. Wherein, when training the stress solving network, the network parameters of the density solving network are maintained unchanged. When training the density solving network, the network parameters of the stress solving network are maintained unchanged.
S204, based on the position information of the sampling points, the predicted stress and the predicted density, the network parameters of the stress solving network are adjusted.
In some implementations, network parameters of the stress solving network may be adjusted based on a loss function of the stress solving network in order to optimize performance and generalization capability of the stress solving network. Alternatively, the loss function of the stress solving network may be determined based on the predicted stress and physical information of the sampling points.
Alternatively, the physical information of the sampling point may be obtained based on the position information, the predicted stress and the predicted density of the sampling point, wherein the physical information includes at least a compliance parameter of the sampling point. The location information, predicted stress, and predicted density of the sampling points may be input into a compliance equation based on which compliance parameters of the sampling points are output.
Further, based on the predicted stress and physical information of the sampling points, a first loss function of the stress solving network is obtained, and network parameters of the stress solving network are adjusted based on the first loss function, so that the stress solving network can be adjusted towards a better direction, and the structure optimization model is gradually optimized in the training process.
S205, adjusting network parameters of the density solving network based on the position information of the sampling points, the predicted stress and the predicted density.
In some implementations, network parameters of the density solution network may be adjusted based on a loss function of the density solution network in order to optimize performance and generalization capability of the density solution network. Alternatively, the loss function of the density solving network may be determined based on the predicted density of the sampling points and the physical information.
Alternatively, the physical information of the sampling point may be obtained based on the position information of the sampling point, the predicted stress, and the predicted density. Wherein the physical information may sample the compliance parameters of the points. The location information, predicted stress, and predicted density of the sampling points may be input into a compliance equation based on which compliance parameters of the sampling points are output.
Further, based on the predicted density and the physical information of the sampling points, a second loss function of the density solving network is obtained, and network parameters of the density solving network are adjusted based on the second loss function. The density solving network can be adjusted towards a better direction, so that the structure optimizing model is gradually optimized in the training process.
Optionally, in order to preserve a more compact and smooth structure, the physical information of the sampling points may be subjected to gaussian filtering to obtain derivative information of the physical information, where the derivative information refers to a derivative of the compliance parameter. And based on the predicted density, physical information and derivative information of the sampling points, a second loss function of the density solving network is obtained, and Gaussian filtering is combined with the design of the loss function, so that the smoothness of the predicted result of the density solving network can be improved, and the smoothness of the structure optimization model is optimized.
In some implementations, the network parameters of any solution network may also be adjusted based on gradient information of the loss function to optimize performance and generalization ability of the solution network and the structural optimization model. Optionally, for any one of the stress solving network and the density solving network, performing gradient calculation on the loss function of any one solving network to obtain gradient information of any one solving network, and further adjusting network parameters of any one solving network based on the gradient information.
S206, training the adjusted network until the end condition of model training is met, and obtaining the target structure optimization model.
In some implementations, the end condition of model training may be determined based on a second loss function of the density solution network after each training of the density solution network is completed. Since the smaller the loss function is, the better the training effect of the model is, the set threshold value of the second loss function can be set, and the second loss function is smaller than or equal to the set threshold value as the ending condition of model training.
Optionally, after each training of the density solving network is finished, comparing a second loss function of the density solving network with a set threshold, and if the second loss function is smaller than or equal to the set threshold, determining that the finishing condition of model training is met.
According to the training method of the structure optimization model, which is provided by the embodiment of the disclosure, the component structure of the sample engineering component in the engineering field is sampled to obtain a plurality of sampling points of the sample engineering component, and the position information of the sampling points is input into a stress solving network in the structure optimization model for training to obtain the predicted stress of the sampling points. And then the predicted stress is input into a density solving network in the structure optimization model for training, so that the predicted density of the sampling points is obtained, and the relevance between stress information and density information can be improved. Further, based on the position information, the predicted stress and the predicted density of the sampling points, a first loss function and a second loss function are determined, gradient information of the loss function is calculated, network parameters are adjusted based on the gradient information, the adjusted network is continuously trained until the structure optimization model meets the training ending condition, a target structure optimization model is obtained, the generalization capability of the target structure optimization model is improved, the position information, the stress and the density are combined, and capturing and applying of the target structure optimization model to the space information can be improved in the model optimization process, so that the target structure optimization model is helped to understand the space relation and the geometric structure of engineering components, and the problem of insufficient interpretability when the target structure optimization model solves the physical problem is solved.
A flow chart for training a structural optimization model as shown in fig. 3. The method comprises the steps of obtaining a plurality of sampling points of a component structure of a sample engineering component, inputting the sampling points into a pre-constructed stress solving network, training to obtain predicted stress of the sampling points, and further training the predicted stress input value into a pre-constructed density solving network to obtain predicted density of the sampling points. Based on the predicted stress, the predicted density and the position information of the sampling point, the compliance parameter of the sampling point is determined as physical information, a first loss function of the stress solving network is calculated based on the physical information and the predicted stress, gradient calculation is carried out on the first loss function, gradient information of the first loss function is determined, and network parameters of the stress solving network are updated and adjusted based on the gradient information, so that the adjusted stress solving network is obtained. When the stress solving network is trained and the network parameters are adjusted, the network parameters of the density solving network are maintained unchanged.
Further, after the stress solving network is trained for a set number of times, training of the density solving network is started. The predicted stress output by the last training of the stress solving network is input into the density solving network, the predicted density of the sampling point is trained, the compliance parameter of the sampling point is determined to be physical information based on the predicted stress, the predicted density and the position information of the sampling point, gaussian filtering is carried out on the physical information of the sampling point to obtain derivative information of the physical information, and then the second loss function of the density solving network can be determined based on the predicted density, the physical information and the derivative information. And determining gradient information of the second loss function by carrying out gradient calculation on the second loss function, and updating and adjusting network parameters of the density solving network based on the gradient information to obtain an adjusted density solving network. When training the density solving network and adjusting the network parameters, the network parameters of the stress solving network are maintained unchanged. And after the density solving network training is finished each time, comparing a second loss function of the density solving network with a set threshold value, and if the second loss function is smaller than or equal to the set threshold value, determining that the model training finishing condition is met, ending the model training, and obtaining the target structure optimization model.
Fig. 4 is a flow chart of a training method of a structural optimization model according to an embodiment of the present disclosure. As shown in fig. 4, the training method of the structural optimization model may include:
s401, sampling the component structure of the sample engineering component in the engineering field to obtain a plurality of sampling points of the sample engineering component.
S402, training a stress solving network in the structure optimization model based on the position information of the sampling points to obtain predicted stress of the sampling points.
S403, training a density solving network in the structure optimization model based on the predicted stress to obtain the predicted density of the sampling points.
S404, based on the position information, the predicted stress and the predicted density of the sampling point, obtaining physical information of the sampling point, wherein the physical information at least comprises compliance parameters of the sampling point.
S405, obtaining a first loss function of the stress solving network based on the predicted stress and the physical information of the sampling points.
And S406, adjusting network parameters of the stress solving network based on the first loss function.
S407, obtaining physical information of the sampling points based on the position information, the predicted stress and the predicted density of the sampling points.
S408, obtaining a second loss function of the density solving network based on the predicted density of the sampling points and the physical information.
S409, adjusting network parameters of the density solving network based on the second loss function.
And S410, continuing to train the adjusted network until the end condition of model training is met, and obtaining the target structure optimization model.
According to the training method of the structure optimization model, which is provided by the embodiment of the disclosure, the component structure of the sample engineering component in the engineering field is sampled to obtain a plurality of sampling points of the sample engineering component, and the position information of the sampling points is input into a stress solving network in the structure optimization model for training to obtain the predicted stress of the sampling points. And then the predicted stress is input into a density solving network in the structure optimization model for training, so that the predicted density of the sampling points is obtained, and the relevance between stress information and density information can be improved. Further, based on the position information, the predicted stress and the predicted density of the sampling points, a first loss function and a second loss function are obtained, network parameters are adjusted, and the adjusted network is continuously trained until the structural optimization model meets the training end condition, so that a target structural optimization model is obtained, the generalization capability of the target structural optimization model is improved, the position information, the stress and the density are combined, the capturing and the application of the target structural optimization model to the space information can be improved in the model optimization process, the target structural optimization model is helped to understand the space relation and the geometric structure of the engineering component, and the problem of insufficient interpretability when the target structural optimization model solves the physical problem is solved.
Fig. 5 is a schematic flow chart of a structure optimization method according to an embodiment of the disclosure.
As shown in fig. 5, the structure optimization method may include:
s501, acquiring a component structure of a target engineering component to be optimized.
In some implementations, the component structure of the target engineering component may be generated by scanning and measuring the target engineering component to be optimized. Candidate component structures of the target engineering component may also be obtained from the model library as component structures of the target engineering component. Wherein, the component structure is required to be matched with the shape and the size of the target engineering component.
S502, carrying out density prediction on the component structure of the target engineering component based on the target structure optimization model to obtain density distribution data of the component structure of the target engineering component.
It should be noted that the target structure optimization model may be obtained by using the training method of the structure optimization model shown in fig. 1-4, which is not described herein.
In some implementations, density distribution data of a component structure may be obtained by determining a target location on a component structure of a target engineering component, and performing location acquisition on the target location to obtain location information of the target location on the component structure of the target engineering component, and performing density prediction based on the location information based on a target structure optimization model.
Optionally, inputting the position information of the target position into a stress solving network of the target structure optimizing model to obtain the predicted stress of the target position, and inputting the predicted stress of the target position into a density solving network of the target structure optimizing model to obtain the predicted density of the target position.
Further, with each position on the component structure of the target engineering component as a target position, based on the target structure optimization model, a predicted density based on each target position can be obtained, thereby generating density distribution data of the component structure of the target engineering component.
In some implementations, a determination may be made as to whether the component structure of the target engineering component meets engineering requirements based on the density distribution data. For example, the engineering requirements may require that the density of the component structure of the target engineering component be uniform, and it may be determined whether the density of the component structure of the target engineering component is uniform based on the density distribution data.
In some implementations, if the engineering requirements are not met, optimization information for the component structure of the target engineering component may be generated based on the density distribution data, and the component structure of the target engineering component may be optimized based on the optimization information. For example, an abnormal region of a lower density or a higher density in the component structure of the target engineering component may be acquired based on the density distribution data, and structural optimization may be performed based on the density abnormal region. In the embodiment of the disclosure, the obtained density distribution data of the component structure of the target engineering component can help to optimize the structural performance, reduce the production cost and improve the performance and the reliability of the structure.
Taking the field of automobile manufacturing as an example, taking a target engineering component as a vehicle door, measuring the vehicle door to generate a component structure of the vehicle door, collecting the position of a target position on the component structure to obtain the position information of the target position on the component structure of the vehicle door, inputting the position information into a target structure optimization model to perform density prediction, and obtaining density distribution data of the component structure of the vehicle door.
Further, it is possible to determine whether the component structure of the door satisfies the requirements of automobile manufacturing, such as ensuring the strength and rigidity of the door, based on the density distribution data. In the case where the vehicle manufacturing requirement is not satisfied, optimization information of the vehicle door may be generated based on the density distribution data, and the vehicle door may be optimized based on the optimization information.
According to the structure optimization method provided by the embodiment of the disclosure, the density distribution data of the component structure of the target engineering component can be obtained by acquiring the component structure of the target engineering component to be optimized and inputting the component structure into the target structure optimization model based on the position information of the target position on the component structure. The structure of the target engineering component is optimized based on the density distribution data, which is beneficial to improving structural design, improving performance and reducing waste of materials and energy sources.
Corresponding to the training method of the structural optimization model provided by the above embodiments, an embodiment of the present disclosure further provides a training device of the structural optimization model, and since the training device of the structural optimization model provided by the embodiment of the present disclosure corresponds to the training method of the structural optimization model provided by the above embodiments, the implementation of the training method of the structural optimization model is also applicable to the training device of the structural optimization model provided by the embodiment of the present disclosure, which is not described in detail in the following embodiments.
Fig. 6 is a schematic structural diagram of a training device for a structural optimization model according to an embodiment of the present disclosure.
As shown in fig. 6, a training apparatus 600 for a structural optimization model according to an embodiment of the present disclosure includes: a sampling module 601, a first training module 602, a second training module 603, and an adjustment module 604.
The sampling module 601 is configured to sample a component structure of a sample engineering component in an engineering field, so as to obtain a plurality of sampling points of the sample engineering component.
The first training module 602 is configured to train the stress solving network in the structural optimization model based on the position information of the sampling point, so as to obtain the predicted stress of the sampling point.
And a second training module 603, configured to train the density solving network in the structural optimization model based on the predicted stress, so as to obtain the predicted density of the sampling point.
And the adjusting module 604 is configured to adjust network parameters of the stress solving network and the density solving network respectively based on the position information of the sampling point, the predicted stress and the predicted density, and continuously train the adjusted network until an end condition of model training is met, so as to obtain a target structure optimization model.
In one embodiment of the present disclosure, the adjusting module 604 is further configured to: obtaining physical information of the sampling point based on the position information of the sampling point, the predicted stress and the predicted density, wherein the physical information at least comprises compliance parameters of the sampling point; based on the predicted stress of the sampling point and the physical information, a first loss function of the stress solving network is obtained; and adjusting network parameters of the stress solving network based on the first loss function.
In one embodiment of the present disclosure, the adjusting module 604 is further configured to: obtaining physical information of the sampling point based on the position information of the sampling point, the predicted stress and the predicted density; obtaining a second loss function of the density solving network based on the predicted density of the sampling points and the physical information; and adjusting network parameters of the density solving network based on the second loss function.
In one embodiment of the present disclosure, the adjusting module 604 is further configured to: carrying out Gaussian filtering on the physical information of the sampling points to obtain derivative information of the physical information; and obtaining a second loss function of the density solving network based on the predicted density of the sampling point, the physical information and the derivative information.
In one embodiment of the present disclosure, the adjusting module 604 is further configured to: aiming at any one of the stress solving network and the density solving network, carrying out gradient calculation on a loss function of the any one solving network to obtain gradient information of the any one solving network; and adjusting network parameters of any solving network based on the gradient information.
In one embodiment of the present disclosure, the apparatus further comprises: the stress solving network and the density solving network are trained alternately, and network parameters of one network are maintained during the training of the other network.
In one embodiment of the present disclosure, the apparatus further comprises: after the training times of one network reach the first set times, training the other network is started; and starting to train one of the networks after the training parameters of the other network reach the second set times.
In one embodiment of the present disclosure, the stress solving network is a linear neural network, the density solving network is a convolutional neural network, and the stress solving network is connected in series with the density solving network.
In one embodiment of the present disclosure, the adjusting module 604 is further configured to: and after each training of the density solving network is finished, comparing a second loss function of the density solving network with a set threshold value, and determining that the finishing condition of the model training is met if the second loss function is smaller than or equal to the set threshold value.
According to the training device of the structure optimization model, which is provided by the embodiment of the disclosure, the component structure of the sample engineering component in the engineering field is sampled to obtain a plurality of sampling points of the sample engineering component, and the position information of the sampling points is input into the stress solving network in the structure optimization model for training to obtain the predicted stress of the sampling points. And then the predicted stress is input into a density solving network in the structure optimization model for training, so that the predicted density of the sampling points is obtained, and the relevance between stress information and density information can be improved. Further, based on the position information, the predicted stress and the predicted density of the sampling points, the network parameters are adjusted, and the adjusted network is continuously trained until the structural optimization model meets the training ending condition, so that the target structural optimization model is obtained, the generalization capability of the target structural optimization model is improved, the position information, the stress and the density are combined, the capturing and the application of the target structural optimization model to the space information can be improved in the model optimization process, the target structural optimization model is helped to understand the space relation and the geometric structure of the engineering component, and the problem of insufficient interpretability when the target structural optimization model solves the physical problem is solved.
According to an embodiment of the present disclosure, the present disclosure further provides a structure optimization device, which is configured to implement the above-mentioned structure optimization method.
Fig. 7 is a schematic structural view of a structure optimizing apparatus according to a first embodiment of the present disclosure.
As shown in fig. 7, a structure optimizing apparatus 700 of an embodiment of the present disclosure includes: a first acquisition module 701 and a prediction module 702.
An obtaining module 701, configured to obtain a component structure of a target engineering component to be optimized.
And the prediction module 702 is configured to predict the density of the component structure of the target engineering component based on the target structure optimization model, so as to obtain density distribution data of the component structure of the target engineering component.
In one embodiment of the present disclosure, the apparatus further comprises: generating optimization information of the component structure of the target engineering component based on the density distribution data; and optimizing the component structure of the target engineering component based on the optimization information.
In one embodiment of the present disclosure, the prediction module 702 is further configured to: acquiring position information of a target position on a component structure of the target engineering component; inputting the position information of the target position into a stress solving network of the target structure optimizing model to obtain the predicted stress of the target position; inputting the predicted stress of the target position into a density solving network of the target structure optimizing model to obtain the predicted density of the target position; and generating density distribution data of the component structure of the target engineering component based on the predicted density of each target position.
According to the structure optimizing device provided by the embodiment of the disclosure, the density distribution data of the component structure of the target engineering component can be obtained by acquiring the component structure of the target engineering component to be optimized and inputting the component structure into the target structure optimizing model based on the position information of the target position on the component structure. The structure of the target engineering component is optimized based on the density distribution data, which is beneficial to improving structural design, improving performance and reducing waste of materials and energy sources.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 8 illustrates a schematic block diagram of an example electronic device 800 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 8, the electronic device 800 includes a computing unit 801 that can perform various suitable actions and processes according to computer programs/instructions stored in a read-only memory (ROM) 802 or loaded from a storage unit 806 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.
Various components in device 800 are connected to I/O interface 805, including: an input unit 806 such as a keyboard, mouse, etc.; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, or the like. The communication unit 809 allows the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 801 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the training method of the structural optimization model. For example, in some embodiments, the training method of the structural optimization model may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as in some embodiments of the storage unit 806, part or all of the computer program/instructions may be loaded and/or installed onto the device 800 via the ROM 802 and/or the communication unit 809. When the computer program/instructions are loaded into RAM 803 and executed by computing unit 801, one or more steps of the training method of the structural optimization model described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the training method of the structural optimization model in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs/instructions that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be a special or general purpose programmable processor, operable to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs/instructions running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (27)
1. A method of training a structural optimization model, wherein the method comprises:
sampling the component structure of a sample engineering component in the engineering field to obtain a plurality of sampling points of the sample engineering component;
training a stress solving network in the structure optimization model based on the position information of the sampling points to obtain predicted stress of the sampling points;
training a density solving network in the structure optimization model based on the predicted stress to obtain the predicted density of the sampling point;
Based on the position information of the sampling points, the predicted stress and the predicted density, respectively adjusting network parameters of the stress solving network and the density solving network, and continuously training the adjusted network until the end condition of model training is met, so as to obtain a target structure optimization model.
2. The method of claim 1, wherein adjusting network parameters of the stress solving network comprises:
obtaining physical information of the sampling point based on the position information of the sampling point, the predicted stress and the predicted density, wherein the physical information at least comprises compliance parameters of the sampling point;
based on the predicted stress of the sampling point and the physical information, a first loss function of the stress solving network is obtained;
and adjusting network parameters of the stress solving network based on the first loss function.
3. The method of claim 1, wherein adjusting network parameters of the density solution network comprises:
obtaining physical information of the sampling point based on the position information of the sampling point, the predicted stress and the predicted density;
Obtaining a second loss function of the density solving network based on the predicted density of the sampling points and the physical information;
and adjusting network parameters of the density solving network based on the second loss function.
4. A method according to claim 3, wherein said deriving a second loss function of said density solving network based on said predicted density of said sampling points and said physical information comprises:
carrying out Gaussian filtering on the physical information of the sampling points to obtain derivative information of the physical information;
and obtaining a second loss function of the density solving network based on the predicted density of the sampling point, the physical information and the derivative information.
5. A method according to claim 2 or 3, wherein the method further comprises:
aiming at any one of the stress solving network and the density solving network, carrying out gradient calculation on a loss function of the any one solving network to obtain gradient information of the any one solving network;
and adjusting network parameters of any solving network based on the gradient information.
6. The method of any of claims 1-4, wherein the method further comprises:
The stress solving network and the density solving network are trained alternately, and network parameters of one network are maintained during the training of the other network.
7. The method of claim 5, wherein the method further comprises:
after the training times of one network reach the first set times, training the other network is started;
and starting to train one of the networks after the training parameters of the other network reach the second set times.
8. The method of any of claims 1-4, wherein the stress solving network is a linear neural network, the density solving network is a convolutional neural network, and the stress solving network is connected in series with the density solving network.
9. The method of any of claims 1-4, wherein the method further comprises:
and after each training of the density solving network is finished, comparing a second loss function of the density solving network with a set threshold value, and determining that the finishing condition of the model training is met if the second loss function is smaller than or equal to the set threshold value.
10. A method of structural optimization, wherein the method comprises:
Acquiring a component structure of a target engineering component to be optimized;
and carrying out density prediction on the component structure of the target engineering component based on a target structure optimization model to obtain density distribution data of the component structure of the target engineering component, wherein the target structure optimization model is trained by the method according to any one of claims 1-9.
11. The method of claim 10, wherein the method further comprises:
generating optimization information of the component structure of the target engineering component based on the density distribution data;
and optimizing the component structure of the target engineering component based on the optimization information.
12. The method according to claim 10 or 11, wherein the performing density prediction on the component structure of the target engineering component based on the target structure optimization model to obtain density distribution data of the component structure of the target engineering component includes:
acquiring position information of a target position on a component structure of the target engineering component;
inputting the position information of the target position into a stress solving network of the target structure optimizing model to obtain the predicted stress of the target position;
Inputting the predicted stress of the target position into a density solving network of the target structure optimizing model to obtain the predicted density of the target position;
and generating density distribution data of the component structure of the target engineering component based on the predicted density of each target position.
13. A training device for a structural optimization model, wherein the device comprises:
the sampling module is used for sampling the component structure of the sample engineering component in the engineering field to obtain a plurality of sampling points of the sample engineering component;
the first training module is used for training a stress solving network in the structure optimization model based on the position information of the sampling points to obtain predicted stress of the sampling points;
the second training module is used for training a density solving network in the structure optimization model based on the predicted stress to obtain the predicted density of the sampling point;
and the adjusting module is used for respectively adjusting network parameters of the stress solving network and the density solving network based on the position information of the sampling points, the predicted stress and the predicted density, and continuously training the adjusted network until the end condition of model training is met, so as to obtain a target structure optimization model.
14. The apparatus of claim 13, wherein the adjustment module is further configured to:
obtaining physical information of the sampling point based on the position information of the sampling point, the predicted stress and the predicted density, wherein the physical information at least comprises compliance parameters of the sampling point;
based on the predicted stress of the sampling point and the physical information, a first loss function of the stress solving network is obtained;
and adjusting network parameters of the stress solving network based on the first loss function.
15. The apparatus of claim 13, wherein the adjustment module is further configured to:
obtaining physical information of the sampling point based on the position information of the sampling point, the predicted stress and the predicted density;
obtaining a second loss function of the density solving network based on the predicted density of the sampling points and the physical information;
and adjusting network parameters of the density solving network based on the second loss function.
16. The apparatus of claim 15, wherein the adjustment module is further configured to:
carrying out Gaussian filtering on the physical information of the sampling points to obtain derivative information of the physical information;
And obtaining a second loss function of the density solving network based on the predicted density of the sampling point, the physical information and the derivative information.
17. The apparatus of claim 14 or 15, wherein the adjustment module is further configured to:
aiming at any one of the stress solving network and the density solving network, carrying out gradient calculation on a loss function of the any one solving network to obtain gradient information of the any one solving network;
and adjusting network parameters of any solving network based on the gradient information.
18. The apparatus of any of claims 13-16, wherein the apparatus further comprises:
the stress solving network and the density solving network are trained alternately, and network parameters of one network are maintained during the training of the other network.
19. The apparatus of claim 17, wherein the apparatus further comprises:
after the training times of one network reach the first set times, training the other network is started;
and starting to train one of the networks after the training parameters of the other network reach the second set times.
20. The apparatus of any of claims 13-16, wherein the stress solving network is a linear neural network, the density solving network is a convolutional neural network, and the stress solving network is connected in series with the density solving network.
21. The apparatus of any of claims 13-16, wherein the adjustment module is further to:
and after each training of the density solving network is finished, comparing a second loss function of the density solving network with a set threshold value, and determining that the finishing condition of the model training is met if the second loss function is smaller than or equal to the set threshold value.
22. A structure optimization apparatus, wherein the apparatus comprises:
the acquisition module is used for acquiring the component structure of the target engineering component to be optimized;
a prediction module, configured to perform density prediction on a component structure of the target engineering component based on a target structure optimization model, to obtain density distribution data of the component structure of the target engineering component, where the target structure optimization model is obtained by training an apparatus according to any one of claims 13-21.
23. The apparatus of claim 22, wherein the apparatus further comprises:
Generating optimization information of the component structure of the target engineering component based on the density distribution data;
and optimizing the component structure of the target engineering component based on the optimization information.
24. The apparatus of claim 22 or 23, wherein the prediction module is further configured to:
acquiring position information of a target position on a component structure of the target engineering component;
inputting the position information of the target position into a stress solving network of the target structure optimizing model to obtain the predicted stress of the target position;
inputting the predicted stress of the target position into a density solving network of the target structure optimizing model to obtain the predicted density of the target position;
and generating density distribution data of the component structure of the target engineering component based on the predicted density of each target position.
25. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-12.
26. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-12.
27. A computer program product comprising computer program/instructions which, when executed by a processor, implement the method steps of any one of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311754483.XA CN117494779A (en) | 2023-12-19 | 2023-12-19 | Training method of structure optimization model, structure optimization method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311754483.XA CN117494779A (en) | 2023-12-19 | 2023-12-19 | Training method of structure optimization model, structure optimization method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117494779A true CN117494779A (en) | 2024-02-02 |
Family
ID=89685186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311754483.XA Pending CN117494779A (en) | 2023-12-19 | 2023-12-19 | Training method of structure optimization model, structure optimization method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117494779A (en) |
-
2023
- 2023-12-19 CN CN202311754483.XA patent/CN117494779A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113705628B (en) | Determination method and device of pre-training model, electronic equipment and storage medium | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN112528995A (en) | Method for training target detection model, target detection method and device | |
| CN114861039A (en) | Parameter configuration method, device, equipment and storage medium of search engine | |
| CN112862017A (en) | Point cloud data labeling method, device, equipment and medium | |
| CN111461306B (en) | Feature evaluation method and device | |
| CN115859749B (en) | Constraint building method and device of three-dimensional model, electronic equipment and storage medium | |
| US20230123671A1 (en) | Localization and mapping | |
| CN117494779A (en) | Training method of structure optimization model, structure optimization method and device | |
| CN116524165A (en) | Migration method, migration device, migration equipment and migration storage medium for three-dimensional expression model | |
| CN113361575B (en) | Model training method and device and electronic equipment | |
| CN115984309B (en) | Method and apparatus for training image segmentation model and image segmentation | |
| CN112990289B (en) | Data processing method, device, equipment and medium based on multitasking prediction model | |
| CN115456184A (en) | Quantum circuit processing method, quantum state preparation method, device, equipment and medium | |
| CN114067415A (en) | Regression model training method, object evaluation method, device, equipment and medium | |
| CN113313049A (en) | Method, device, equipment, storage medium and computer program product for determining hyper-parameters | |
| CN113961765A (en) | Searching method, device, equipment and medium based on neural network model | |
| CN113052325A (en) | Method, device, equipment, storage medium and program product for optimizing online model | |
| CN113517040A (en) | Quantum intrinsic solver implementation method and device and electronic equipment | |
| CN113032071A (en) | Page element positioning method, page testing method, device, equipment and medium | |
| CN112528123A (en) | Model searching method, model searching apparatus, electronic device, storage medium, and program product | |
| CN116522781B (en) | Sample data generation method, model training method and device | |
| CN117400268B (en) | Nonlinear friction force compensation method and device, electronic equipment and storage medium | |
| CN116933896B (en) | Super-parameter determination and semantic conversion method, device, equipment and medium | |
| CN114331379B (en) | Method for outputting task to be handled, model training method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |