CN117195624A - Multi-specialty collaborative mechanical design method and system for nuclear power station - Google Patents
Multi-specialty collaborative mechanical design method and system for nuclear power station Download PDFInfo
- Publication number
- CN117195624A CN117195624A CN202311050303.XA CN202311050303A CN117195624A CN 117195624 A CN117195624 A CN 117195624A CN 202311050303 A CN202311050303 A CN 202311050303A CN 117195624 A CN117195624 A CN 117195624A
- Authority
- CN
- China
- Prior art keywords
- design
- mechanical
- specialty
- finite element
- calculation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000004364 calculation method Methods 0.000 claims abstract description 122
- 238000005457 optimization Methods 0.000 claims abstract description 46
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 238000007418 data mining Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims description 33
- 238000005516 engineering process Methods 0.000 claims description 25
- 230000006870 function Effects 0.000 claims description 14
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 230000002068 genetic effect Effects 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 7
- 230000007614 genetic variation Effects 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 238000003466 welding Methods 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 5
- 235000013870 dimethyl polysiloxane Nutrition 0.000 claims description 5
- 229920000435 poly(dimethylsiloxane) Polymers 0.000 claims description 5
- 238000006073 displacement reaction Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000012805 post-processing Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 abstract description 2
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Landscapes
- Monitoring And Testing Of Nuclear Reactors (AREA)
Abstract
The invention relates to a multi-specialty collaborative mechanical design method and system for a nuclear power station, wherein the method reads design parameters of different design professions or data center stations and establishes a parameterized mechanical model; performing finite element calculation by combining different working conditions aiming at different types of components and parameterized mechanical models thereof; performing data mining and machine learning on finite element calculation result data of a large number of mechanical models to form a method for intelligently predicting finite element calculation results; setting an optimal design target and an optimal design parameter range for different types of components, and performing intelligent design optimization by using a global optimization algorithm; and feeding the optimal design scheme back to other design professions or data center tables. The invention can greatly improve the mechanical calculation efficiency and accuracy of the components of the nuclear power station, can provide an optimal design scheme by combining the mechanical properties of the nuclear power station equipment, provides mechanical basis for the design of each component, and solves the problems of large dispersion of calculation results obtained by different calculation staff, and the like.
Description
Technical Field
The invention belongs to the nuclear power design technology, and particularly relates to a multi-specialty collaborative mechanical design method and system for a nuclear power station.
Background
The nuclear power station comprises a large number of parts which need to be designed by considering mechanical factors, the traditional mechanical calculation method only carries out mechanical check on the parts, the workload is huge, the time consumption is long, the efficiency is low, the result obtained by analysis of different personnel is high in dispersity, and the function of providing the optimal design opinion is not provided.
If design optimization is required for a certain part, a mechanical model of the part needs to be circularly calculated for a plurality of times in the past, a large amount of modeling and calculating time is required, the total period is long, and the accuracy is low.
The data mining and machine learning method is suitable for being carried out on the basis of a large amount of data, so that the method can be used for predicting mechanical analysis results by combining finite element calculation results, analysis and prediction are carried out on calculation results of different personnel to ensure accuracy, and meanwhile, the mechanical feedback speed is greatly improved, and further, the design optimization speed is also improved.
Disclosure of Invention
The invention aims at overcoming the defects in the prior art, provides a multi-specialty collaborative mechanical design method and system for a nuclear power station, and aims to solve the problems of large dispersibility of calculation results obtained by different calculation staff and the like by combining an intelligent design optimization algorithm based on a large-scale automatic finite element calculation result and applying a data mining and machine learning technology, so as to finally realize rapid automatic mechanical design feedback of the nuclear power station components.
The technical scheme of the invention is as follows: a multi-specialty collaborative mechanical design method of a nuclear power station comprises the following steps:
(1) Reading design parameters required by building part mechanical models of different design professions or data center tables;
(2) The design parameters are stored in a classified mode, and parameterized mechanical model establishment is carried out aiming at different types of parts;
(3) Aiming at different types of components and parameterized mechanical models thereof, carrying out finite element calculation by combining different calculation working conditions to form a large number of finite element calculation results which are stored in a database;
(4) Performing data mining and machine learning on finite element calculation result data of a large number of mechanical models to form a method for intelligently predicting finite element calculation results;
(5) Setting an optimal design target and an optimal design parameter range for different types of components, and performing intelligent design optimization by using a global optimization algorithm;
(6) And (3) carrying out finite element analysis and calculation aiming at the finally obtained component optimal design scheme, and if the calculation result meets the specification requirement, feeding back the optimal design scheme to other design professions or data center stations.
Further, as described above, in the method for designing multi-specialty collaborative mechanics of a nuclear power plant, in step (1), the design specialty may include a system specialty, an arrangement specialty, an equipment specialty, a structure specialty, an electrical specialty, a material welding specialty.
Further, as described above, in the step (1), the design parameters required for building the part mechanical model are read by PDMS software.
Further, as described above, in the method for designing multi-specialty collaborative mechanics of a nuclear power plant, in step (3), the database includes: a bracket stress database, a through-wall point displacement database, a bracket load database, a pipeline stress database, a civil engineering load database, an equipment stress database and a bolt load database.
Further, as described above, in the method for designing multi-specialized collaborative mechanics of a nuclear power plant, in the step (4), the method for forming the intelligent prediction finite element calculation result includes the following steps:
4-1) classifying and counting the calculation result data, and forming a statistic result database;
4-2) changing certain input parameters to perform multiple calculations, analyzing the relevance between the calculation result and the input parameters, and establishing a relevance function;
4-3) adopting optimization technology of genetic combination, genetic variation and natural selection to evaluate the classification accuracy of the training sample set;
4-4) classifying the training sample sets according to the classification accuracy, and calculating the dissimilarity between the sample sets;
4-5) selecting an algorithm for obtaining a result by using a graph theory technology;
4-6) establishing a neural network of the algorithm, and defining each node and a corresponding weight coefficient as an activity function;
4-7) analyzing abnormal conditions in the data, thereby obtaining useful information.
Furthermore, as described above, in the method for designing multi-specialized collaborative mechanics of a nuclear power station, in the step (4), whether calculation results of different persons are accurate or not is fed back, and if the calculation results exceed a threshold value, reminding and checking are performed.
Further, as described above, in the step (5), in the process of optimizing the intelligent design, when finite element analysis is required, the model parameters are modified, and the method for intelligently predicting the finite element calculation result is used to quickly feed back the mechanical calculation result.
The invention further provides a multi-specialty collaborative mechanical design system for the nuclear power station for realizing the method, which comprises the following steps:
the interface management module is used for establishing a data extraction interface with different design professional platforms or data center stations;
the task management module is used for registering and distributing design tasks of different types of components, reading design parameters required by building a component mechanics model of different design professions or data center tables, storing the design parameters in a classified manner, and building a parameterized mechanics model aiming at different types of components;
the calculation analysis module is used for carrying out finite element calculation aiming at different types of components and parameterized mechanical models thereof and combining different calculation working conditions to form a large number of finite element calculation results which are stored in the database;
the data mining and machine learning module is used for carrying out data mining and machine learning on the finite element calculation result data of a large number of mechanical models to form a method for intelligently predicting finite element calculation results, feeding back whether calculation results of different persons are accurate or not, and carrying out reminding inspection if the calculation results exceed a threshold value;
the intelligent design optimization module is used for setting an optimization design target and an optimization design parameter range for different types of components, and performing intelligent design optimization by using a global optimization algorithm;
and the post-processing module is used for carrying out finite element analysis and calculation aiming at the finally obtained component optimal design scheme, and if the calculation result meets the specification requirement, the optimal design scheme is fed back to other design professions or data center stations.
Further, the multi-specialty collaborative mechanical design system of a nuclear power plant as described above, wherein the data mining and machine learning module includes:
the statistical analysis sub-module is used for classifying and counting the calculation result data and forming a statistical result database;
the relevance establishing sub-module is used for carrying out multiple times of calculation by changing certain input parameters, analyzing relevance between a calculation result and the input parameters and establishing a relevance function;
the genetic algorithm submodule adopts optimization technology of genetic combination, genetic variation and natural selection to evaluate the classification accuracy of the training sample set;
the aggregation detection sub-module is used for classifying the training sample sets according to the classification accuracy and calculating the dissimilarity between the sample sets;
connecting analysis submodules, and selecting an algorithm for obtaining a result by using a graph theory technology;
the neural network sub-module is used for establishing a neural network of the algorithm, and defining each node and a corresponding weight coefficient as an activity function;
and the difference analysis sub-module is used for analyzing abnormal conditions in the data so as to obtain useful information.
Further, according to the multi-specialty collaborative mechanical design system of the nuclear power station, the intelligent design optimization module modifies model parameters when finite element analysis is needed in the intelligent design optimization process, and the method for intelligently predicting finite element calculation results by the data mining and machine learning module is used for rapidly feeding back mechanical calculation results.
The beneficial effects of the invention are as follows: according to the invention, by constructing a multi-specialty cooperative platform, automatic mechanical calculation and design optimization of the nuclear power station components are realized, and the calculation result is analyzed by adopting algorithms of data analysis and artificial intelligence through the past data analysis, so that whether the analysis result is accurate or not is judged, and the accuracy of the analysis result is ensured. Compared with the traditional simple mechanical check, the method can not only greatly improve the mechanical calculation efficiency and accuracy of the components of the nuclear power station, but also provide an optimal design scheme by combining the mechanical properties of the nuclear power station equipment, provide mechanical basis for the design of each component of the nuclear power station, and solve the problems of large calculation result dispersion and the like obtained by different calculation staff. The invention has high efficiency and accuracy, and is suitable for large-scale popularization and application.
Drawings
FIG. 1 is a flow chart of a multi-specialty collaborative mechanical design method for a nuclear power plant of the present invention;
FIG. 2 is a schematic diagram of a multi-specialty collaborative mechanical design system of a nuclear power plant;
FIG. 3 is a partial list of parameters extracted from PDMS software according to an embodiment of the present invention;
FIG. 4 is a flow chart of a pipeline anti-seismic calculation in an embodiment of the invention;
FIG. 5 shows the device frequency prediction result and calculation result in the embodiment of the present invention;
FIG. 6 shows the predicted stress results and calculated results of the device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, the multi-specialty collaborative mechanical design method of the nuclear power station provided by the invention comprises the following steps:
step 1, an interface is compiled to automatically extract parameters needed for establishing a mechanical model from a data center or other professions (such as system profession, arrangement profession, equipment profession, structure profession, electric profession, material welding profession and the like).
And step 2, storing the design parameters in a classified manner, and programming to realize parameterized mechanical model establishment aiming at different types of components.
Step 3, aiming at different types of nuclear power plant components and parameterized mechanical models thereof, combining different calculation working conditions, realizing automatic finite element calculation through finite element calculation software programming, and forming a large number of finite element calculation result databases; such as the bracket stress database, through-wall point location database, bracket load database, pipe stress database, civil engineering load database, equipment stress database, bolt load database shown in fig. 2.
And 4, excavating and learning by using a data mining and machine learning method, namely performing finite element analysis calculation result data of a large number of mechanical models to form a method for intelligently predicting finite element calculation results, feeding back whether calculation results of different people are accurate or not, and performing reminding inspection if the calculation results exceed a threshold value, wherein the main adopted technology and main steps are as follows:
4-1) a statistical technique, wherein the calculated result data is classified and counted, and a statistical result database is formed;
4-2) association technology, namely changing certain input parameters to perform multiple calculations, analyzing the association between the calculation result and the input parameters, and establishing an association function;
4-3) genetic algorithm technology, wherein the classification accuracy of the training sample set is evaluated by adopting optimization technology of genetic combination, genetic variation and natural selection;
4-4) an aggregation detection technology, classifying training sample sets according to classification accuracy, and calculating dissimilarity between the sample sets;
4-5) connection analysis technology, the basic principle of which is graph theory, the idea of which is to find an algorithm which can obtain a perfect result, rather than a perfect solution; using graph theory technology, selecting an algorithm for obtaining a result;
4-6) neural network technology, namely establishing a neural network of the algorithm, and defining each node and a corresponding weight coefficient as an activity function;
4-7) differential analysis technology, analyzing abnormal conditions in the data, and further obtaining useful information.
Step 5, setting an optimal design target and an optimal design parameter range for the nuclear power station component, and performing intelligent design optimization by using a global optimization algorithm; in the intelligent design optimization process, when finite element analysis is needed, the method for predicting the finite element calculation result by artificial intelligence is used for replacing the finite element calculation result, so that the mechanical calculation result can be fed back quickly, and the intelligent design optimization speed is improved.
The traditional optimization design technology needs to be repeatedly calculated by using a finite element technology, the calculation times are large, the time is long, and in the method, the machine learning method in the step 4 is used for calculating instead of the finite element method, so that the optimization design can be quickly and efficiently realized.
And 6, carrying out automatic finite element analysis and calculation aiming at the finally obtained optimal design scheme of the nuclear power station component, and if the calculation result meets the specification requirement, feeding back the optimal design scheme to other professions or data center stations.
The structure of the multi-specialty collaborative mechanical design system of the nuclear power station for realizing the method is shown in fig. 2, and the multi-specialty collaborative mechanical design system comprises:
the interface management module is used for establishing a data extraction interface with different design professional platforms or data center stations;
the task management module is used for registering and distributing design tasks of different types of components, reading design parameters required by building a component mechanics model of different design professions or data center tables, storing the design parameters in a classified manner, and building a parameterized mechanics model aiming at different types of components;
the calculation analysis module is used for carrying out finite element calculation aiming at different types of components and parameterized mechanical models thereof and combining different calculation working conditions to form a large number of finite element calculation results which are stored in the database;
the data mining and machine learning module is used for carrying out data mining and machine learning on the finite element calculation result data of a large number of mechanical models to form a method for intelligently predicting finite element calculation results, feeding back whether calculation results of different persons are accurate or not, and carrying out reminding inspection if the calculation results exceed a threshold value; the module further comprises:
the statistical analysis sub-module is used for classifying and counting the calculation result data and forming a statistical result database;
the relevance establishing sub-module is used for carrying out multiple times of calculation by changing certain input parameters, analyzing relevance between a calculation result and the input parameters and establishing a relevance function;
the genetic algorithm submodule adopts optimization technology of genetic combination, genetic variation and natural selection to evaluate the classification accuracy of the training sample set;
the aggregation detection sub-module is used for classifying the training sample sets according to the classification accuracy and calculating the dissimilarity between the sample sets;
connecting analysis submodules, and selecting an algorithm for obtaining a result by using a graph theory technology;
the neural network sub-module is used for establishing a neural network of the algorithm, and defining each node and a corresponding weight coefficient as an activity function;
the difference analysis sub-module is used for analyzing abnormal conditions in the data so as to obtain useful information;
the intelligent design optimization module is used for setting an optimization design target and an optimization design parameter range for different types of components, and performing intelligent design optimization by using a global optimization algorithm; in the intelligent design optimization process, when finite element analysis is needed, a method for predicting finite element calculation results by artificial intelligence is used for replacing the finite element calculation results, so that mechanical calculation results can be fed back quickly;
and the post-processing module is used for carrying out finite element analysis and calculation aiming at the finally obtained component optimal design scheme, and if the calculation result meets the specification requirement, the optimal design scheme is fed back to other design professions or data center stations.
Examples
Taking the mechanical design of a pipeline as an example, the multi-specialty collaborative mechanical design method of the nuclear power station is described.
First, parameters required for pipeline mechanics modeling need to be extracted from PDMS software, as shown in fig. 3. In this embodiment, the fields extracted from PDMS software include: node number, global coordinates, node welding form, node bracket type, combined unit type, bend unit bending radius, nominal diameter, pipe gauge number, element name, belonging branch name, branch or cross-pipe connection node, material, element singleton, node belonging example, node bracket type, constraint elevation, heat preservation, belonging factory building, belonging pipe name, node stress index.
And then, the design parameters are stored in a classified mode, and parameterized mechanical model establishment is realized by programming aiming at different types of components.
And the parameters are programmed by finite element calculation software to realize automatic finite element calculation, and a large number of finite element calculation result databases are formed, and the calculation flow is shown in figure 4.
In the calculation flow, the system profession provides a pipeline list, anti-seismic and security grading, valve parameters and system working condition parameters for setting up a professional ISO model; according to the arrangement of a professional ISO model and the through-wall plugging condition, combining the design contents of a professional pressure vessel, a pump and the like of equipment and the material of a material welding professional, and performing establishment of a mechanical professional pipeline finite element model by welding parameters; the floor reaction spectrum and the relative displacement data of the factory building with specialized structure are used for load loading calculation, automatic finite element calculation is realized, and a finite element calculation result database is formed, for example: a bracket stress database, a through-wall point displacement database, a bracket load database, a pipeline stress database, a civil engineering load database, an equipment stress database and a bolt load database.
According to the method of data mining and machine learning, the data of the database are classified and counted according to the calculation result, the association between the data (such as a bracket, a valve and a later pipeline associated with the current pipeline) is searched by adopting an association coefficient, the algorithm capable of obtaining the optimal result is searched by adopting a genetic algorithm, an aggregation detection technology, a connection analysis technology and the like, a neural network activity function is formed, finally, the abnormal condition in the data is analyzed by adopting differential analysis, and the effective information is stored.
And setting an optimal design target, such as shortest total length or lowest total weight, for the target pipeline, and adjusting input parameters by using a global optimization algorithm to perform iterative calculation until a stable target value is reached. In the intelligent design optimization process, when finite element analysis is needed, the method for predicting the finite element calculation result by artificial intelligence is used for replacing the finite element calculation result, and the mechanical calculation result can be fed back quickly. Fig. 5 shows a comparison of the predicted device frequency result and the calculated result, and fig. 6 shows a comparison of the predicted device stress result and the calculated result. The predicted outcome is seen to be very close to the calculated outcome.
Finally, the pipeline mechanical analysis and design optimization work are completed simultaneously, and an optimal design scheme for enabling the pipeline to meet the design specification requirements is provided.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (10)
1. The multi-specialty collaborative mechanical design method for the nuclear power station is characterized by comprising the following steps of:
(1) Reading design parameters required by building part mechanical models of different design professions or data center tables;
(2) The design parameters are stored in a classified mode, and parameterized mechanical model establishment is carried out aiming at different types of parts;
(3) Aiming at different types of components and parameterized mechanical models thereof, carrying out finite element calculation by combining different calculation working conditions to form a large number of finite element calculation results which are stored in a database;
(4) Performing data mining and machine learning on finite element calculation result data of a large number of mechanical models to form a method for intelligently predicting finite element calculation results;
(5) Setting an optimal design target and an optimal design parameter range for different types of components, and performing intelligent design optimization by using a global optimization algorithm;
(6) And (3) carrying out finite element analysis and calculation aiming at the finally obtained component optimal design scheme, and if the calculation result meets the specification requirement, feeding back the optimal design scheme to other design professions or data center stations.
2. The multi-specialty collaborative mechanical design method of claim 1, wherein in step (1), the design specialty may include system specialty, deployment specialty, equipment specialty, structural specialty, electrical specialty, material welding specialty.
3. The multi-specialty collaborative mechanical design method of a nuclear power plant according to claim 1 or 2, wherein in step (1), design parameters required for building a mechanical model of the component are read by PDMS software.
4. The multi-specialty collaborative mechanical design method of claim 1, wherein in step (3), the database comprises: a bracket stress database, a through-wall point displacement database, a bracket load database, a pipeline stress database, a civil engineering load database, an equipment stress database and a bolt load database.
5. The multi-specialty collaborative mechanical design method of claim 1, wherein in step (4), the method of forming the intelligent predictive finite element calculation result comprises the steps of:
4-1) classifying and counting the calculation result data, and forming a statistic result database;
4-2) changing certain input parameters to perform multiple calculations, analyzing the relevance between the calculation result and the input parameters, and establishing a relevance function;
4-3) adopting optimization technology of genetic combination, genetic variation and natural selection to evaluate the classification accuracy of the training sample set;
4-4) classifying the training sample sets according to the classification accuracy, and calculating the dissimilarity between the sample sets;
4-5) selecting an algorithm for obtaining a result by using a graph theory technology;
4-6) establishing a neural network of the algorithm, and defining each node and a corresponding weight coefficient as an activity function;
4-7) analyzing abnormal conditions in the data, thereby obtaining useful information.
6. The multi-specialty collaborative mechanical design method of a nuclear power plant according to claim 1 or 5, wherein in step (4), whether the calculation results of different personnel are accurate is fed back, and if the calculation results exceed a threshold value, a reminder check is performed.
7. The multi-specialty collaborative mechanical design method of a nuclear power plant according to claim 1, wherein in step (5), in the process of intelligent design optimization, when finite element analysis is needed, model parameters are modified, and the method for intelligently predicting finite element calculation results is used to quickly feed back mechanical calculation results.
8. A multi-specialty co-mechanical design system for a nuclear power plant for implementing the method of any of claims 1-7, comprising:
the interface management module is used for establishing a data extraction interface with different design professional platforms or data center stations;
the task management module is used for registering and distributing design tasks of different types of components, reading design parameters required by building a component mechanics model of different design professions or data center tables, storing the design parameters in a classified manner, and building a parameterized mechanics model aiming at different types of components;
the calculation analysis module is used for carrying out finite element calculation aiming at different types of components and parameterized mechanical models thereof and combining different calculation working conditions to form a large number of finite element calculation results which are stored in the database;
the data mining and machine learning module is used for carrying out data mining and machine learning on the finite element calculation result data of a large number of mechanical models to form a method for intelligently predicting finite element calculation results, feeding back whether calculation results of different persons are accurate or not, and carrying out reminding inspection if the calculation results exceed a threshold value;
the intelligent design optimization module is used for setting an optimization design target and an optimization design parameter range for different types of components, and performing intelligent design optimization by using a global optimization algorithm;
and the post-processing module is used for carrying out finite element analysis and calculation aiming at the finally obtained component optimal design scheme, and if the calculation result meets the specification requirement, the optimal design scheme is fed back to other design professions or data center stations.
9. The nuclear power plant multi-specialty collaborative mechanical design system of claim 8, wherein the data mining and machine learning module further comprises:
the statistical analysis sub-module is used for classifying and counting the calculation result data and forming a statistical result database;
the relevance establishing sub-module is used for carrying out multiple times of calculation by changing certain input parameters, analyzing relevance between a calculation result and the input parameters and establishing a relevance function;
the genetic algorithm submodule adopts optimization technology of genetic combination, genetic variation and natural selection to evaluate the classification accuracy of the training sample set;
the aggregation detection sub-module is used for classifying the training sample sets according to the classification accuracy and calculating the dissimilarity between the sample sets;
connecting analysis submodules, and selecting an algorithm for obtaining a result by using a graph theory technology;
the neural network sub-module is used for establishing a neural network of the algorithm, and defining each node and a corresponding weight coefficient as an activity function;
and the difference analysis sub-module is used for analyzing abnormal conditions in the data so as to obtain useful information.
10. The multi-specialty collaborative mechanical design system of claim 8, wherein the intelligent design optimization module modifies model parameters when finite element analysis is needed during intelligent design optimization, and uses the method of intelligent prediction finite element calculation results of the data mining and machine learning module to quickly feed back mechanical calculation results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311050303.XA CN117195624A (en) | 2023-08-21 | 2023-08-21 | Multi-specialty collaborative mechanical design method and system for nuclear power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311050303.XA CN117195624A (en) | 2023-08-21 | 2023-08-21 | Multi-specialty collaborative mechanical design method and system for nuclear power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117195624A true CN117195624A (en) | 2023-12-08 |
Family
ID=89002581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311050303.XA Pending CN117195624A (en) | 2023-08-21 | 2023-08-21 | Multi-specialty collaborative mechanical design method and system for nuclear power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117195624A (en) |
-
2023
- 2023-08-21 CN CN202311050303.XA patent/CN117195624A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Saldivar et al. | Self-organizing tool for smart design with predictive customer needs and wants to realize Industry 4.0 | |
| EP3582359A1 (en) | Stability evaluation and static control method for electricity-heat-gas integrated energy system | |
| El Jazzar et al. | Digital twin in construction: An empirical analysis | |
| Semeraro et al. | Digital twin application in energy storage: Trends and challenges | |
| CN105302096B (en) | Intelligent factory scheduling method | |
| CN117391641B (en) | Pilatory production flow management method and system | |
| Wu et al. | Intelligent data-driven approach for enhancing preliminary resource planning in industrial construction | |
| Tang et al. | A framework for making maintenance decisions for oil and gas drilling and production equipment | |
| CN108920609A (en) | Electric power experiment data mining method based on multi-dimensional analysis | |
| CN108491991A (en) | Constraints analysis system based on the industrial big data product duration and method | |
| CN114548494B (en) | Visual cost data prediction intelligent analysis system | |
| CN110781206A (en) | Method for predicting whether electric energy meter in operation fails or not by learning meter-dismantling and returning failure characteristic rule | |
| Altaf et al. | BIM implication of life cycle cost analysis in construction project: a systematic review | |
| Badakhshan et al. | Deploying hybrid modelling to support the development of a digital twin for supply chain master planning under disruptions | |
| CN112070307B (en) | Method and device for predicting energy source load in region | |
| Peng et al. | Knowledge graph for power grid dispatching of digital homes based on graph convolutional network | |
| CN117195624A (en) | Multi-specialty collaborative mechanical design method and system for nuclear power station | |
| CN114841038B (en) | Intelligent design method for primary loop pipeline bracket arrangement of nuclear power station under complex load | |
| Chernyshev et al. | Integration of building information modeling and artificial intelligence systems to create a digital twin of the construction site | |
| CN115130924A (en) | Microgrid power equipment asset evaluation method and system under source grid storage background | |
| Zhou et al. | Nested partitions method for assembly sequences merging | |
| CN113807704A (en) | Intelligent algorithm platform construction method for urban rail transit data | |
| Stryczek | A hybrid approach for manufacturability analysis | |
| Chernyshev et al. | Digital Object Detection of Construction Site Based on Building Information Modeling and Artificial Intelligence Systems. | |
| Lige et al. | Road machinery fault prediction based on big data and machine learning |
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 |