CN117272688B - Compression and decompression method, device and system for structural mechanics simulation data - Google Patents
Compression and decompression method, device and system for structural mechanics simulation data Download PDFInfo
- Publication number
- CN117272688B CN117272688B CN202311541564.1A CN202311541564A CN117272688B CN 117272688 B CN117272688 B CN 117272688B CN 202311541564 A CN202311541564 A CN 202311541564A CN 117272688 B CN117272688 B CN 117272688B
- Authority
- CN
- China
- Prior art keywords
- simulation data
- data
- simulation
- compressed
- compressing
- 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.)
- Active
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 246
- 238000007906 compression Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000006835 compression Effects 0.000 title claims abstract description 51
- 230000006837 decompression Effects 0.000 title claims description 36
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000003062 neural network model Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 9
- 238000011176 pooling Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 8
- 230000004069 differentiation Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000011084 recovery Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000013144 data compression Methods 0.000 abstract description 8
- 230000005540 biological transmission Effects 0.000 abstract description 7
- 230000000903 blocking effect Effects 0.000 abstract description 5
- 238000013528 artificial neural network Methods 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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]
-
- 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
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device and a system for compressing and decompressing structural mechanical simulation data, which realize higher data compression rate by carrying out differential compression in the compression process and adding a neural network for feature extraction, thereby reducing the transmission and storage requirements of the structural mechanical simulation data and ensuring that key simulation data information is not lost in the compression process, in particular to highly accurate or sensitive application scenes. Meanwhile, the blocking compression is added into the compression process, so that the delay of displaying the data at the front end is further reduced, and smooth visual experience is provided for the user.
Description
Technical Field
The invention relates to the technical field of data processing and transmission, in particular to a method, a device and a system for compressing and decompressing structural mechanics simulation data based on deep learning.
Background
With the development of numerical simulation technology, structural mechanics simulation has become an important tool in the engineering field. These simulations produce large amounts of data, especially when complex engineering structures and multi-physical field interactions are considered. The transmission, storage and real-time presentation of such large amounts of data becomes a critical issue.
In Advances in Structural Mechanics Simulation Techniques (from Journal of Structural Engineering, 2017, vol. 143, issue 9), although some effective data compression methods have been proposed and implemented, these methods tend to focus on single-aspect problems, for example, only considering data compression, and neglecting the need for real-time decompression and display. Existing data compression relies on traditional compression algorithms such as JPEG, MPEG, etc. which may be very effective in certain applications, but they are not always applicable to numerical simulation data for structural mechanics. In particular, they may not effectively retain key details in simulation results, especially in highly accurate or sensitive engineering applications. The main problems and disadvantages include:
1. the compression efficiency is not enough: many traditional compression methods cannot effectively compress large-scale structural mechanics simulation data; 2. data loss: details critical to certain engineering applications may be lost during compression; 3. delay problem: the prior art may not meet the low latency requirements when transmitting and displaying data in real time.
In view of the foregoing, there is a need for a novel data compression and decompression method that meets the specific requirements of structural mechanics numerical simulation.
Disclosure of Invention
The invention aims to solve the problems of low efficiency, data loss and delay of the traditional compression method in the application of structural mechanical simulation data, provides a deep learning-based structural mechanical numerical simulation data compression and real-time decompression technology, can realize real-time display with higher compression efficiency, data integrity and low delay, and can effectively compress the structural mechanical numerical simulation data in real time and decompress the structural mechanical numerical simulation data rapidly at the front end to realize smooth visualization.
In order to achieve the above object, the present invention provides the following technical solutions:
in a first aspect, the present invention provides a method for compressing structural mechanics simulation data, the method comprising:
extracting current simulation data and historical simulation data of an object to be simulated;
obtaining a difference part of the current simulation data and the historical simulation data through a differentiation algorithm to generate data to be simulated;
generating compressed simulation data corresponding to the data to be simulated according to the compression step corresponding to the data to be simulated;
the compressed simulation data includes a header of the compressed simulation data;
the compressing step includes:
compressing data to be simulated to generate first simulation data;
performing feature extraction and compression on the first simulation data by using a neural network model to generate second simulation data;
and compressing the second simulation data in a blocking way to generate compressed simulation data.
According to a specific embodiment, in the compression method, the neural network model includes a convolution layer, an activation function, a pooling layer, a full connection layer, a regularization layer and a batch normalization layer; the convolution layer is used for extracting target features of the first simulation data; the activation function is used for increasing nonlinearity of the neural network model and converting target characteristics into target results; the pooling layer is used for downsampling and compressing the target result to generate second simulation data; the full connection layer is used for carrying out advanced mapping on target features; the regularization layer and the batch normalization layer are used for improving the generalization capability and the training speed of the neural network model according to the mapped target characteristics.
According to a specific embodiment, in the compression method, the compressing step further includes: and according to the preset resolution, compressing the simulation data into first simulation data with the corresponding resolution.
According to a specific embodiment, in the compression method, the block compression specifically includes: equally dividing the second simulation data into data blocks, independently compressing each data block to generate compressed simulation data, encapsulating the position information of each data block in the header of the compressed simulation data, and encapsulating the identification of the compression step in the header of the compressed simulation data.
In a second aspect, the present invention provides a decompression method of structural mechanics simulation data, the decompression method comprising:
receiving compressed simulation data, and decompressing the compressed simulation data into data to be simulated according to a decompression step corresponding to the compressed simulation data;
the decompression step comprises the following steps:
decompressing the compressed simulation data by blocks to generate second simulation data;
decompressing and characteristic reconstructing the second simulation data by using a decompression network model to generate first simulation data;
decompressing the first simulation data to generate data to be simulated.
According to a specific embodiment, in the above decompression method, the decompression network model includes a deconvolution layer and a fully-connected network layer; the deconvolution network is used for up-sampling and feature recovery of the input second simulation data to generate a feature matrix; and the fully-connected network layer is used for processing and integrating the second simulation data based on the feature matrix and outputting the reconstructed first simulation data.
According to a specific embodiment, in the above decompression method, the decompressing step further includes:
unpacking the header of the compressed simulation data, acquiring a compression step from the unpacked header of the compressed simulation data, and determining a corresponding decompression step according to the compression step;
and acquiring the position information of each data block in the header of the unpacked compressed simulation data, and arranging according to the position information.
In a third aspect, the present invention provides a method for compressing and decompressing structural mechanics simulation data, the method comprising:
the client selects an object to be simulated, acquires current simulation data of the object to be simulated, and sends the current simulation data and a simulation request to the server;
the server receives the simulation request and the current simulation data, and obtains compressed simulation data by utilizing the compression method of the structural mechanics simulation data;
the server sends the compressed simulation data to the client;
the client receives the compressed simulation data and decompresses the compressed simulation data by using the decompression method of the structural mechanics simulation data described in any one of the above;
and the client performs structural mechanics simulation according to the decompressed simulation data.
In a fourth aspect, the present invention provides a compression and decompression apparatus for structural mechanics simulation data, the apparatus comprising:
the data acquisition module is used for acquiring current simulation data of the object to be simulated;
the first sending module is used for sending a simulation request and the current simulation data to the server;
the first processing module is used for receiving the simulation request and the current simulation data from the client and acquiring compressed simulation data by utilizing the compression method of the structural mechanics simulation data;
the second sending module is used for sending the compressed simulation data to the client;
the second processing module is used for receiving the compressed simulation data and decompressing the compressed simulation data by using the decompression method of the structural mechanics simulation data;
and the data simulation module is used for carrying out structural mechanics simulation according to the decompressed simulation data.
In a fifth aspect, the present invention provides a system for compressing and decompressing structural mechanics simulation data, where the system includes a client and a server connected to the client.
Compared with the prior art, the invention has the beneficial effects that:
according to the compression method of the structural mechanical simulation data, provided by the invention, the data compression rate is higher by performing differential compression in the compression process and adding the neural network model for feature extraction, so that the transmission and storage requirements are reduced, and the key simulation data information is not lost in the compression process, particularly for highly accurate or sensitive application scenes; meanwhile, the blocking compression can also greatly reduce the delay of data display at the front end, and smooth visual experience is provided for users.
Drawings
FIG. 1 is a flow chart of a method for compressing structural mechanics simulation data provided by an embodiment of the invention;
FIG. 2 is a flow chart of a method for decompressing structural mechanics simulation data according to an embodiment of the present invention;
Detailed Description
The present invention will be described in further detail with reference to test examples and specific embodiments. It should not be construed that the scope of the above subject matter of the present invention is limited to the following embodiments, and all techniques realized based on the present invention are within the scope of the present invention.
Example 1
Fig. 1 shows a flowchart of a method for compressing structural mechanics simulation data, which is provided by the invention and includes:
step 101, extracting current simulation data and historical simulation data of an object to be simulated;
step 102, obtaining a difference part of the current simulation data and the historical simulation data through a differentiation algorithm, and generating data to be simulated;
wherein the differentiation algorithm employs a binary differentiation look-up algorithm (BSDiff, binary SearchandDifference).
Specifically, the client calculates the difference between the current simulation data and the historical simulation data. To achieve this, a binary differentiated look-up algorithm (BSDiff) is used. BSDiff first locates to different regions in the two data sets and then generates a difference patch for these difference regions, i.e. the difference portions of the current simulation data and the historical simulation data. The patch can be applied at the server side to reconstruct the current simulation data from the previous simulation data, so that only the difference patch is required to be transmitted, and the data transmission quantity is greatly reduced.
And step 103, generating compressed simulation data corresponding to the data to be simulated according to the compression step corresponding to the data to be simulated.
Wherein the compressed simulation data comprises a header of the compressed simulation data;
the compressing step includes:
compressing data to be simulated to generate first simulation data; meanwhile, according to the preset resolution, the simulation data are compressed into first simulation data with corresponding resolution;
performing feature extraction and compression on the first simulation data by using a neural network model to generate second simulation data;
and compressing the second simulation data in a blocking way to generate compressed simulation data.
The neural network model comprises a convolution layer, an activation function, a pooling layer, a full-connection layer, a regularization layer and a batch normalization layer; the convolution layer is used for extracting target features of the first simulation data; the activation function is used for increasing nonlinearity of the neural network and converting target characteristics into target results; the pooling layer is used for downsampling and compressing the target result to generate second simulation data; the full connection layer is used for carrying out advanced mapping on target features; the regularization layer and the batch normalization layer are used for improving the generalization capability and the training speed of the neural network model according to the mapped target characteristics.
Wherein the block compression specifically includes: equally dividing the second simulation data into data blocks, independently compressing each data block to generate compressed simulation data, encapsulating the position information of each data block in the header of the compressed simulation data, and encapsulating the identification of the compression step in the header of the compressed simulation data.
In summary, according to the compression method of the structural mechanical simulation data, provided by the invention, by performing differential compression in the compression process and adding the neural network to perform feature extraction, a higher data compression rate is realized, so that the transmission and storage requirements are reduced, and the fact that key simulation data information is not lost in the compression process is ensured, particularly for highly accurate or sensitive application scenes; meanwhile, the blocking compression can also greatly reduce the delay of data display at the front end, and smooth visual experience is provided for users.
Example 2
Fig. 2 shows a flowchart of a decompression method of structural mechanics simulation data, which is provided by an exemplary embodiment of the present invention, where the decompression method includes:
step 201, receiving compressed simulation data;
step 202, according to the decompression step corresponding to the compressed simulation data, decompressing the compressed simulation data into data to be simulated;
the decompression step comprises the following steps:
decompressing the compressed simulation data by blocks to generate second simulation data;
decompressing and characteristic reconstructing the second simulation data by using a decompression network model to generate first simulation data;
decompressing the first simulation data to generate data to be simulated.
The decompression network model comprises a deconvolution layer and a full-connection network layer; the deconvolution network is used for up-sampling and feature recovery of the input second simulation data to generate a feature matrix; and the fully-connected network layer is used for processing and integrating the second simulation data based on the feature matrix and outputting the reconstructed first simulation data.
Wherein the decompressing step further comprises:
unpacking the header of the compressed simulation data, acquiring a compression step from the unpacked header of the compressed simulation data, and determining a corresponding decompression step according to the compression step;
and acquiring the position information of each data block in the header of the unpacked compressed simulation data, and arranging according to the position information.
Example 3
The embodiment provides a method for compressing and decompressing structural mechanics simulation data, which comprises the following steps:
s1, a client selects an object to be simulated, acquires current simulation data of the object to be simulated, and sends the current simulation data and a simulation request to a server;
s2, the server receives the simulation request and the current simulation data, and compressed simulation data are obtained by using the compression method in the steps S101 to S103;
s3, the server sends the compressed simulation data to the client;
s4, the client receives the compressed simulation data and decompresses the compressed simulation data by using the decompression method described in the steps S201 to S202;
s5, the client performs structural mechanics simulation according to the decompressed simulation data.
Example 4
The present embodiment provides a compression and decompression system for structural mechanics simulation data, which is further described and illustrated below with reference to specific embodiments.
The first step: preparing data;
and selecting a structural mechanics data file of a large bridge to be simulated by a user through a GUI interface at the client.
And a second step of: preprocessing data;
and the client performs preliminary cleaning and preprocessing on the selected current simulation data of the bridge, and removes redundant and invalid information.
And a third step of: a simulation request;
the client sends the simulation request and the preprocessed current simulation data of the bridge to the server by using a safe network protocol.
Fourth step: receiving data;
the server receives the current simulation data and the simulation request of the bridge from the client.
Fifth step: differential compression;
the server searches the last bridge simulation data, compares the current simulation data and the historical simulation data of the bridge, finds out a difference part, uses a differentiation algorithm to compress only the difference part data, and generates the data to be simulated of the bridge.
Sixth step: multi-resolution compression;
and selecting proper resolution according to the network environment of the client and display requirements, and generating corresponding data to be simulated for different resolution requirements by adopting a multi-level quantization technology.
Seventh step: deep learning compression;
a pre-trained Convolutional Neural Network (CNN) model is used to train for the characteristics of structural mechanics. Inputting the data to be simulated of the bridge into a neural network, extracting key features through a plurality of convolution layers, an activation function and a pooling layer, and compressing. At the same time, the model is optimized to ensure that the error after compression is minimal.
The training process of the neural network model is as follows:
obtaining historical simulation data of the bridge stored in the server, screening constant variables in the historical simulation data, and taking the rest variables as characteristic variables;
constructing a neural network model according to the historical simulation data and the characteristic variables;
constructing input and output of the neural network model according to the mapping relation between the difference part of each simulation data and the characteristic variable of the difference part;
and obtaining a trained neural network model according to the neural network model trained by the input and the output.
The neural network model comprises a convolution layer, an activation function, a pooling layer, a full connection layer, a regularization layer and a batch normalization layer; wherein the convolution layer is used for extracting features in the difference part; the activation function is used for increasing nonlinearity of the neural network model and converting the extracted characteristics into characteristic variables; the pooling layer is used for downsampling and compressing the characteristic variables; the full connection layer is used for carrying out advanced mapping on the characteristic variables; the regularization layer and the batch normalization layer are used for improving the generalization capability and the training speed of the neural network model according to the mapped target characteristics.
Eighth step: partitioning and stream compression;
dividing the compressed data to be simulated into blocks with equal size, and independently compressing each data block by using parallel computation. Each data block is appended with a header information indicating its position in the overall data.
Ninth step: data transmission;
the server starts streaming the compressed data blocks to the client.
Tenth step: stream receiving;
the client receives the data blocks transmitted by the server in real time and sorts the data blocks according to the head information.
Eleventh step: decompressing in real time;
the client adopts a decompression step corresponding to the server to decompress each data block in real time. And reconstructing the compressed data by using the decompression network model, and retaining the most critical information.
Twelfth step: real-time display
The client immediately uses the efficient rendering technology to display the decompressed data, and the latest simulation effect is displayed for the user.
Example 5
The embodiment provides a compression and decompression device of structural mechanics simulation data, which comprises:
the data acquisition module is used for acquiring current simulation data of the object to be simulated;
the first sending module is used for sending a simulation request and the current simulation data to the server;
the first processing module is configured to receive the simulation request and the current simulation data from the client, and acquire compressed simulation data by using the compression method of the structural mechanical simulation data described in the steps 101 to 103;
the second sending module is used for sending the compressed simulation data to the client;
the second processing module is configured to receive the compressed simulation data, and decompress the compressed simulation data by using the decompression method of the structural mechanics simulation data described in the steps 201 to 202;
and the data simulation module is used for carrying out structural mechanics simulation according to the decompressed simulation data.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (8)
1. A method for compressing structural mechanics simulation data, the method comprising:
extracting current simulation data and historical simulation data of an object to be simulated;
obtaining a difference part of the current simulation data and the historical simulation data through a differentiation algorithm to generate data to be simulated;
generating compressed simulation data corresponding to the data to be simulated according to the compression step corresponding to the data to be simulated;
wherein the compressed simulation data comprises a header of the compressed simulation data;
the compressing step includes:
compressing data to be simulated to generate first simulation data;
performing feature extraction and compression on the first simulation data by using a neural network model to generate second simulation data;
compressing the second simulation data in blocks to generate compressed simulation data;
the block compression specifically includes: equally dividing the second simulation data into data blocks, independently compressing each data block to generate compressed simulation data, encapsulating the position information of each data block in the header of the compressed simulation data, and encapsulating the identification of the compression step in the header of the compressed simulation data.
2. The method for compressing structural mechanical simulation data according to claim 1, wherein the neural network model comprises a convolution layer, an activation function, a pooling layer, a full connection layer, a regularization layer and a batch normalization layer; the convolution layer is used for extracting target features of the first simulation data; the activation function is used for increasing nonlinearity of the neural network model and converting target characteristics into target results; the pooling layer is used for downsampling and compressing the target result to generate second simulation data; the full connection layer is used for carrying out advanced mapping on target features; the regularization layer and the batch normalization layer are used for improving the generalization capability and the training speed of the neural network model according to the mapped target characteristics.
3. The method of compressing structural mechanics simulation data according to claim 1, wherein said compressing step further comprises: and according to the preset resolution, compressing the simulation data into first simulation data with the corresponding resolution.
4. A method for decompressing structural mechanics simulation data, the method comprising:
receiving compressed simulation data, and decompressing the compressed simulation data into data to be simulated according to a decompression step corresponding to the compressed simulation data, wherein the data to be simulated is a difference part of current simulation data and historical simulation data;
the decompression step comprises the following steps:
unpacking the header of the compressed simulation data, acquiring a compression step from the unpacked header of the compressed simulation data, and determining a corresponding decompression step according to the compression step;
the position information of each data block is obtained from the head of the unpacked compressed simulation data, and the data blocks are arranged according to the position information;
decompressing the compressed simulation data by blocks to generate second simulation data;
decompressing and characteristic reconstructing the second simulation data by using a decompression network model to generate first simulation data;
decompressing the first simulation data to generate data to be simulated.
5. The method for decompressing structural mechanics simulation data according to claim 4, wherein the decompressed network model comprises a deconvolution layer and a fully-connected network layer; the deconvolution network is used for up-sampling and feature recovery of the input second simulation data to generate a feature matrix; and the fully-connected network layer is used for processing and integrating the second simulation data based on the feature matrix and outputting the reconstructed first simulation data.
6. A method for compressing and decompressing structural mechanics simulation data, the method comprising:
the client selects an object to be simulated, acquires current simulation data of the object to be simulated, and sends the current simulation data and a simulation request to the server;
the server receives the simulation request and the current simulation data, and obtains compressed simulation data by using the compression method of the structural mechanics simulation data according to any one of claims 1 to 3;
the server sends the compressed simulation data to the client;
the client receives the compressed simulation data and decompresses the compressed simulation data using the decompression method of the structural mechanics simulation data of any one of claims 4 to 5;
and the client performs structural mechanics simulation according to the decompressed simulation data.
7. A device for compressing and decompressing structural mechanics simulation data, the device comprising:
the data acquisition module is used for acquiring current simulation data of the object to be simulated;
the first sending module is used for sending a simulation request and the current simulation data to the server;
a first processing module, configured to receive the simulation request and the current simulation data from a client, and obtain compressed simulation data by using the compression method of structural mechanical simulation data according to any one of claims 1 to 3;
the second sending module is used for sending the compressed simulation data to the client;
a second processing module for receiving the compressed simulation data and decompressing the compressed simulation data using the decompression method of the structural mechanics simulation data of any one of claims 4 to 5;
and the data simulation module is used for carrying out structural mechanics simulation according to the decompressed simulation data.
8. The system for compressing and decompressing the structural mechanics simulation data is characterized by comprising a client and a server connected with the client, wherein the client and the server compress and decompress the structural mechanics simulation data by adopting the method of claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311541564.1A CN117272688B (en) | 2023-11-20 | 2023-11-20 | Compression and decompression method, device and system for structural mechanics simulation data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311541564.1A CN117272688B (en) | 2023-11-20 | 2023-11-20 | Compression and decompression method, device and system for structural mechanics simulation data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117272688A CN117272688A (en) | 2023-12-22 |
| CN117272688B true CN117272688B (en) | 2024-02-13 |
Family
ID=89216315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311541564.1A Active CN117272688B (en) | 2023-11-20 | 2023-11-20 | Compression and decompression method, device and system for structural mechanics simulation data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117272688B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018107414A1 (en) * | 2016-12-15 | 2018-06-21 | 上海寒武纪信息科技有限公司 | Apparatus, equipment and method for compressing/decompressing neural network model |
| CN112348914A (en) * | 2020-11-12 | 2021-02-09 | 中国科学院合肥物质科学研究院 | Deep learning image compression sensing algorithm and system based on Internet of vehicles |
| WO2022002068A1 (en) * | 2020-06-29 | 2022-01-06 | 中兴通讯股份有限公司 | Data processing method, system and device and storage medium |
| CN114422607A (en) * | 2022-03-30 | 2022-04-29 | 三峡智控科技有限公司 | Compression transmission method of real-time data |
| WO2022170569A1 (en) * | 2021-02-10 | 2022-08-18 | 华为技术有限公司 | Data processing method and apparatus |
| CN114969958A (en) * | 2021-12-31 | 2022-08-30 | 中国航空工业集团公司西安飞机设计研究所 | Data dimension reduction processing method for airplane load prediction |
| CN116318172A (en) * | 2023-05-25 | 2023-06-23 | 山东华云三维科技有限公司 | Design simulation software data self-adaptive compression method |
-
2023
- 2023-11-20 CN CN202311541564.1A patent/CN117272688B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018107414A1 (en) * | 2016-12-15 | 2018-06-21 | 上海寒武纪信息科技有限公司 | Apparatus, equipment and method for compressing/decompressing neural network model |
| WO2022002068A1 (en) * | 2020-06-29 | 2022-01-06 | 中兴通讯股份有限公司 | Data processing method, system and device and storage medium |
| CN112348914A (en) * | 2020-11-12 | 2021-02-09 | 中国科学院合肥物质科学研究院 | Deep learning image compression sensing algorithm and system based on Internet of vehicles |
| WO2022170569A1 (en) * | 2021-02-10 | 2022-08-18 | 华为技术有限公司 | Data processing method and apparatus |
| CN114969958A (en) * | 2021-12-31 | 2022-08-30 | 中国航空工业集团公司西安飞机设计研究所 | Data dimension reduction processing method for airplane load prediction |
| CN114422607A (en) * | 2022-03-30 | 2022-04-29 | 三峡智控科技有限公司 | Compression transmission method of real-time data |
| WO2023185969A1 (en) * | 2022-03-30 | 2023-10-05 | 三峡智控科技有限公司 | Real-time data compression and transmission method |
| CN116318172A (en) * | 2023-05-25 | 2023-06-23 | 山东华云三维科技有限公司 | Design simulation software data self-adaptive compression method |
Non-Patent Citations (5)
| Title |
|---|
| Neural Networks in the Identification Analysis of Structural Mechanics Problems;Zenon Waszczyszyn 等;Parameter Identification of Materials and Structures;20051231;第265-340页 * |
| 一种神经网络数据压缩算法;杨云升 等;2016’中国西部声学学术交流会论文集;20160821;第496-498页 * |
| 基于电站大数据的过程数据自适应压缩技术研究;刘功庆;中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑;20230315(第03期);第C042-786页 * |
| 数字高程模型压缩研究进展浅析;王小兵 等;测绘科学;20130520;第38卷(第06期);第23-25, 28页 * |
| 数据压缩技术在船舶电力监控系统中的应用;王永臻 等;上海船舶运输科学研究所学报;20200330;第43卷(第01期);第55-60页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117272688A (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111787323B (en) | Variable bit rate generation type compression method based on counterstudy | |
| CN110348487B (en) | Hyperspectral image compression method and device based on deep learning | |
| Chen et al. | Exploiting intra-slice and inter-slice redundancy for learning-based lossless volumetric image compression | |
| CN111669587B (en) | Mimic compression method and device of video image, storage medium and terminal | |
| WO2020018985A1 (en) | Data compression using conditional entropy models | |
| CN113259665B (en) | Image processing method and related equipment | |
| CN109949222B (en) | Image super-resolution reconstruction method based on semantic graph | |
| CN110691243A (en) | Point cloud geometric compression method based on deep convolutional network | |
| CN112950471A (en) | Video super-resolution processing method and device, super-resolution reconstruction model and medium | |
| CN114581544A (en) | Image compression method, computer device and computer storage medium | |
| CN110288524B (en) | Deep learning super-resolution method based on enhanced upsampling and discrimination fusion mechanism | |
| CN113554058A (en) | Method, system, device and storage medium for enhancing resolution of visual target image | |
| CN118153129B (en) | Workpiece three-dimensional model generation method, device and medium based on fine tuning large model | |
| CN115022637A (en) | Image coding method, image decompression method and device | |
| CN115294222A (en) | Image encoding method, image processing method, terminal, and medium | |
| CN114373023A (en) | Point cloud geometric lossy compression reconstruction device and method based on points | |
| CN114501031B (en) | Compression coding and decompression method and device | |
| CN117272688B (en) | Compression and decompression method, device and system for structural mechanics simulation data | |
| CN116095183A (en) | Data compression method and related equipment | |
| CN105828087A (en) | Image compression system based on optical wavelet and compressed sensing | |
| CN114493971B (en) | Media data conversion model training and digital watermark embedding method and device | |
| CN115239563A (en) | Point cloud attribute lossy compression device and method based on neural network | |
| JP2024529309A (en) | Video Compression Using Optical Flow | |
| CN115578561A (en) | Real-time semantic segmentation method and device based on multi-scale context aggregation network | |
| CN113554719B (en) | Image encoding method, decoding method, storage medium and terminal equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |