CN114997001B - Complex electromechanical equipment performance evaluation method based on substitution model and knowledge graph - Google Patents
Complex electromechanical equipment performance evaluation method based on substitution model and knowledge graph Download PDFInfo
- Publication number
- CN114997001B CN114997001B CN202210573084.2A CN202210573084A CN114997001B CN 114997001 B CN114997001 B CN 114997001B CN 202210573084 A CN202210573084 A CN 202210573084A CN 114997001 B CN114997001 B CN 114997001B
- Authority
- CN
- China
- Prior art keywords
- electromechanical equipment
- model
- knowledge
- knowledge graph
- entity
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 36
- 238000006467 substitution reaction Methods 0.000 title claims abstract description 25
- 230000008878 coupling Effects 0.000 claims abstract description 13
- 238000010168 coupling process Methods 0.000 claims abstract description 13
- 238000005859 coupling reaction Methods 0.000 claims abstract description 13
- 230000004044 response Effects 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000013528 artificial neural network Methods 0.000 claims abstract description 6
- 230000000694 effects Effects 0.000 claims abstract description 4
- 238000005070 sampling Methods 0.000 claims abstract description 3
- 238000000034 method Methods 0.000 claims description 43
- 238000004088 simulation Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000003754 machining Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000006872 improvement Effects 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims 1
- 238000010276 construction Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000012216 screening 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
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
-
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a complex electromechanical equipment performance evaluation method based on a substitution model and a knowledge graph, which comprises the steps of establishing a multi-physical coupling model of complex electromechanical equipment, defining the performance index of the electromechanical equipment and establishing sample points; inputting the sample points into a multi-physical coupling model to obtain response values, and performing series-parallel sampling on the sample points and the response values to generate a data set; preprocessing the data set to remove outliers, noise points and outliers as a training set; defining an objective function for the training set, training by using a neural network, and iterating and optimizing parameters until the best fitting effect is achieved, so as to obtain a substitution model; analyzing by using a substitution model to obtain an input parameter, an entity of an output response and a corresponding relation; establishing a knowledge graph; and carrying out complex electromechanical equipment performance evaluation through semantic retrieval and knowledge reasoning by using the knowledge graph. The invention has high efficiency and high accuracy rate by using the substitution model, and can provide more perfect support for the subsequent performance evaluation of electromechanical equipment.
Description
Technical Field
The invention relates to the field of performance evaluation of electromechanical equipment, in particular to a complex electromechanical equipment performance evaluation method based on a substitution model and a knowledge graph.
Background
The performance indexes of the complex electromechanical equipment are of various types, such as efficiency, reliability, safety, precision and the like, the performance evaluation main bodies of different electromechanical equipment are different, such as the precision of a numerical control machine tool, the safety of some processing equipment and the like, the performance indexes of the different electromechanical equipment can be analyzed by different methods, great trouble is brought to the comprehensive evaluation of one electromechanical equipment, and different parts of the electromechanical equipment can have different influences on the overall performance. Performance evaluation involves multiple disciplines, multiple objective complex analysis problems.
For complex electromechanical equipment performance evaluation, multivariate parameters are involved, high nonlinearity between an analysis target and an input parameter is analyzed, parameters are optimized on a large scale, and a large number of loop iteration problems are caused. If the performance evaluation is obtained by directly simulating the electromechanical equipment based on a finite element model or a multi-physical field coupling model, the calculation amount is extremely large, a large amount of time is required to be consumed, the existing calculation platform is difficult to bear the large calculation amount, and the simulation time is reduced in order to improve the calculation efficiency.
For performance evaluation of different electromechanical equipment, comprehensive analysis is required for different knowledge of each subject, the relation and influence among different elements are researched, and a common table cannot meet the requirement of an image. The method for constructing the knowledge spectrum is often obtained from expert experience or the existing knowledge base, the knowledge spectrum is not perfect, the entity and the attribute and the corresponding relation are lacking, and the knowledge spectrum is updated continuously through the practical process, so that the problems of large updating period, irregular naming mode of the entity, redundant corresponding relation of the entity and the like are caused.
Disclosure of Invention
In order to overcome the problems in the prior art, the invention provides a complex electromechanical equipment performance evaluation method based on a substitution model and a knowledge graph.
The technical scheme adopted for solving the technical problems is as follows: a complex electromechanical equipment performance evaluation method based on a substitution model and a knowledge graph comprises the following steps:
Step 1, a multi-physical coupling model of complex electromechanical equipment is established, performance indexes of the electromechanical equipment are clarified, and input sample points are established;
Step 2, inputting the sample points into a multi-physical coupling model to obtain response values, and performing series-parallel sampling on the sample points and the response values to generate a data set;
step 3, preprocessing the data set obtained in the step 2 to remove outliers, noise points and abnormal values as a training set;
Step 4, training the training set obtained in the step 3 to define an objective function, and performing iterative optimization on parameters by using a neural network until the best fitting effect is achieved, so as to obtain a substitute model;
Step 5, analyzing by using the substitution model obtained in the step 4 to obtain an input parameter, an entity outputting response and a corresponding relation;
Step 6, establishing a knowledge graph;
and 7, performing complex electromechanical equipment performance evaluation through semantic retrieval and knowledge reasoning by using the knowledge graph obtained in the step 6.
The method for evaluating the performance of the complex electromechanical equipment based on the substitution model and the knowledge graph, wherein the establishing the multi-physical coupling model of the complex electromechanical equipment in the step 1 specifically comprises the following steps: and (3) definitely determining participation parts of the complex electromechanical equipment in the working process, establishing models of different parts by using a finite element analysis method, establishing the models, establishing a Matlab/simulink system, establishing a simulation model, establishing a mathematical model related to the system, and performing multi-physical-field simulation calculation on a simulation platform by taking a simulation result as an initial condition.
The above-mentioned complex electromechanical equipment performance evaluation method based on the substitution model and the knowledge graph, the specific process of the step 6 includes:
step 6.1, preprocessing the data obtained in the step 5;
Step 6.2, naming the entity and normalizing the term of the data obtained in the step 6.1;
Step 6.3, extracting different entities, entity relations and entity attribute information to form an ontology knowledge expression;
and 6.4, integrating the knowledge obtained in the step 6.3, eliminating contradiction and ambiguity, and adding qualified knowledge into the knowledge graph.
The method for evaluating the performance of the complex electromechanical equipment based on the substitution model and the knowledge graph comprises the steps of normalizing, discretizing and sparsifying the data.
The complex electromechanical equipment performance evaluation method based on the substitution model and the knowledge graph comprises a clustering algorithm, a KNN algorithm and an SVM algorithm.
The complex electromechanical equipment performance evaluation method based on the substitution model and the knowledge graph comprises an equal frequency method, an equal width method and a clustering method.
The invention has the advantages that the response and the input generated by using the alternative model are structured data, and the preprocessing part can be skipped to directly carry out entity extraction, relation extraction and attribute extraction; the external knowledge base can be combined more conveniently, and the conflict between the data layer and the mode layer can be processed; a large number of entity relations and attributes can be obtained more quickly and efficiently, and the knowledge graph is expanded;
Some imperfect entities and attributes thereof in the knowledge graph can enrich the existing entity relationship and attributes after fitting response through established substitution models; some beneficial knowledge may also help build a surrogate model that fits better to reality, fitting better; the obtained knowledge graph can provide more perfect support for subsequent electromechanical equipment performance evaluation.
Drawings
The invention will be further described with reference to the drawings and examples.
FIG. 1 is a flow chart of the multi-physical field coupling model establishment of the present invention;
FIG. 2 is a flow chart of an alternate model creation process of the present invention;
FIG. 3 is a flow chart of the present invention for creating a knowledge graph using an alternative model;
FIG. 4 is a flow chart of an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the drawings and detailed description to enable those skilled in the art to better understand the technical scheme of the present invention.
The embodiment discloses a performance evaluation method of a numerical control machine tool, wherein the specific flow is shown in fig. 4, and step 1: establishing a multi-physical field coupling model: as shown in fig. 1, three-dimensional components of a numerically-controlled machine tool are built by using solidworks and assembled, a stress-strain analysis model of a machine tool mechanism is built by using Abaqus, a machine tool electric control device is modeled by using simscan, a dynamic model of hydraulic transmission of a feeding shaft of the numerically-controlled machine tool is built by using Amesim, various models of the system are built by connection, mathematical models related to the system are built, a simulation model of the machine tool is built by using a Matlab/simulink system, mathematical relations between different physical quantities, such as relations between spindle rotation speed and cutter heat production amount, relations between hole axis matching errors and machining efficiency, and a multi-physical field coupling model is built on a comsol simulation platform by using mathematical relations of different physical quantities.
Step 2, constructing a data set, performing outlier removal, noise point removal and outlier removal on normal distribution in the data set according to Laida rule, and removing noise point outlier by using a DBSCAN method and an isolated forest method on other training sets: according to the performance evaluation content of the machine tool equipment and influence factors, for example, when evaluating the operation precision index of the machine tool, a given CNC machining center program code is firstly input into an established ideal model, a series of track interpolation operations are carried out, the result is input into the established servo control device and machine tool transmission device model, and a batch of parts continuous machining results at the moment are recorded to be used as repeated positioning precision. Then, according to an industry empirical formula and an existing knowledge base, factors influencing the working accuracy of the machine tool are definitely considered, the influences of component manufacturing assembly errors, the rigidity of a stand column base and the environmental temperature are generally considered, the influence of error-causing components, the sizes, shapes and position errors of error-causing components (a machine tool spindle, a guide rail and the like) are definitely determined, the matching errors of different components, materials and working condition environmental factors are combined to establish input quantities, for different components, the components considering the influence of the manufacturing errors are used for replacing ideal components of a multi-physical field coupling simulation model respectively, given program codes are repeatedly operated, the processing results of the components at the moment are observed, and compared with the ideal conditions to obtain the influence on the processing accuracy performance at the moment, so that the influence of the dimensional shape and position errors of the different components on the repeated positioning accuracy is obtained. The matching relation among different parts in the ideal model can be changed, the simulation is performed again, a given section of code is repeatedly operated, and the influence of assembly precision errors among different parts on the repeated positioning precision of the machine tool is obtained. And (3) adding the influence of the temperature field to the machine tool, repeating the steps to obtain the influence of the ambient temperature on the repeated positioning accuracy of the machine tool, and taking the influence as an output sample space.
And 3, after obtaining the input output quantity, namely a trained sample space, taking the value of repeated positioning accuracy as an objective function, training by using a BP neural network or an SVM neural network, determining the trained parameters and a loss function by using a minimum gradient descent optimization algorithm, continuously updating the parameters, checking errors, and performing loop iteration until a relatively accurate substitution model is obtained, wherein the construction process of the substitution model is shown in figure 2.
And 4, changing the input of the substitution model and outputting corresponding repeated positioning accuracy by using the substitution model obtained in the previous step and combining the actual environment, the actual running condition and the evaluation requirement to generate different entities, entity relations and attributes.
And 5, preprocessing the original data such as input of the substitution model and obtained output data in the last step, normalizing the data by using a clustering algorithm, a KNN algorithm, an SVM algorithm and the like, discretizing by using an equal-frequency method, an equal-width method, a clustering method and the like, and finally sparsifying to obtain ideal data.
Step 6, constructing a knowledge graph, as shown in fig. 3: extracting information from the data collected in the step 5, and extracting structured information such as entities, entity relations, attributes and the like: firstly, entity naming and term normalization are completed, the specific steps are that corresponding concept classes are defined according to factors which influence the performance of complex electromechanical equipment according to indexes required by performance evaluation of the complex electromechanical equipment, a core concept set of influence factors and evaluation indexes is abstracted, related terms are subjected to normalization processing, the related terms can be divided into control structures, transmission devices, hydraulic devices, electric devices and the like according to hardware topology of the complex electromechanical equipment, entity naming can be performed according to performance influence factors, such as factors (assembly errors, manufacturing errors, shape and position errors) and the like can be considered when operation precision evaluation is performed, and at the moment, the format of influence factors plus influence results is used. Of course, the entity naming identification can be performed on some existing expert knowledge and operation design documents according to the Bi-LSTM+CRF model, and the sequence from top to bottom or from bottom to top is adopted;
After obtaining the entity names, obtaining entity relations and entity attribute information from the collected data, for example, the entity relations comprise factors influencing performance, positions where the factors appear and results influencing performance in the map construction process, the entity relations are the internal relations among the entities, rules-based extraction of the entities can be used, templates which are well defined by people can be used, and experts can perform context matching on two entities in the input text according to the performance names to be evaluated and indexes for measuring the performance, factors influencing the performance, handwriting rules matching texts, or search engines are used for collecting massive related data and counting the obtained statistical templates. With the development of computer technology, this part may use a method based on supervised learning, and the main steps include first defining some relation categories in advance and marking some relevant data, selecting classification methods (SVM, NN, naive bayes, etc.) to be used according to the previously designed entity naming representation method, and performing automatic classification. As basic parameters specific to the entity, different types of entities have different entity attributes, when different equipment performance knowledge maps are constructed, the attribute emphasis point of the same entity is also different, for example, when complex electromechanical equipment working accuracy evaluation is carried out, the attribute of the component entity mainly comprises data such as the roughness of the machined surface of the component, the tolerance of the hole axis fit and the like;
Relationships among entities and entity attributes are extracted, obtained knowledge is represented, common representation methods comprise RDF triple representation, a generating rule representation method, a semantic network representation method, a framework representation method and the like. The method comprises the steps of completing entity disambiguation and coreference resolution, selecting a proper method by combining the source of data and the type of the data, dividing the method into a cluster-based entity disambiguation system and a system using entity linkage according to whether target entities are listed, and linking entity index items with corresponding entities in a table by giving a target entity list. If not, all the index items pointing to the same target entity are clustered below the same category, wherein each category corresponds to one target entity, and therefore entity relations corresponding to some repetitions are simplified. Determining entity relation, obtaining different entity relation networks according to different classification basis, combining the same entity nodes in the different entity relation networks but disjoint parts of edges (entity relation) to form a logic relation diagram containing equipment performance influence factors, influence sources, performance evaluation indexes, complex electromechanical equipment performance evaluation of the whole machine and parts, and finally extracting a relation matrix;
in this embodiment, when different design errors of the machine tool spindle may have different effects on the repeated positioning accuracy, so as to generate different triples, and when the machining accuracy of the evaluation machine tool is constructed, the repeated positioning accuracy is used as a judgment index, and is recorded as: error source (spindle) error type (manufacturing error) error attribute (manufacturing error level) affects the index (repeated positioning accuracy).
After entity disambiguation and coreference resolution are completed, knowledge is processed, wherein the knowledge mainly comprises ontology construction, namely a concept description layer is constructed and used as a concept template of the knowledge, and the method mainly comprises manual construction and automatic construction (predicting index measures of the same concept classification between two entities to determine parallel relations of the entities and determining upper and lower relations according to membership relations between the concepts). Knowledge reasoning, namely, according to the existing entity relation in a knowledge base, through reasoning, the relation among the entities is found, a knowledge network is enriched, and common methods are reasoning and graph-based reasoning according to first-order predicate logic, descriptive logic or rules, and a common neural network or PATHRANKING algorithm is adopted.
In the present embodiment, a concept hierarchy is described based on the constituent structure of a machine tool, and as a concept template of knowledge, automatic construction is used. Through knowledge reasoning, according to the existing entity relation in the knowledge base, through reasoning, the relation between the entities is found, the knowledge network is enriched, or the reasoning and the graph-based reasoning are carried out according to rules, the obtained new knowledge is integrated, contradiction and ambiguity are eliminated, the same triples and entity relation attributes of the corresponding entities are removed, and the obtained knowledge is stored in a Neo4j graph database.
And updating knowledge, namely carrying out body alignment on the obtained new knowledge according to a similarity combination strategy by using a method such as a matching algorithm library in an automatic body matching system Falcon-AO, and adding a knowledge graph which accords with grammar specifications and accords with a logic relation through quality evaluation (manual screening) to realize updating.
Step 7, performing complex electromechanical equipment performance evaluation through semantic retrieval and knowledge reasoning by using the knowledge graph obtained in the step 6: when the machine tool machining precision performance evaluation is carried out, two steps of semantic search and knowledge reasoning are mainly carried out, the semantic search firstly builds a query command according to keywords, forms, natural language and formal language, the query command can be built according to query statement rules of Neo4j, query processing is completed through matching and reasoning, and the final result is displayed by using a visual mode of graph data. All factors affecting the machining precision of the numerical control machine tool and the weight of the influence of the factors are obtained, the entity affecting the machining precision performance and the corresponding attribute and entity relation are obtained, and the improvement of the electromechanical equipment performance can be obtained by changing the factors affecting the precision, or the most efficient method for improving the machining precision of the machine tool is found.
The above embodiments are only exemplary embodiments of the present invention and are not intended to limit the present invention, the scope of which is defined by the claims. Various modifications and equivalent arrangements of this invention will occur to those skilled in the art, and are intended to be within the spirit and scope of the invention.
Claims (5)
1. A complex electromechanical equipment performance evaluation method based on a substitution model and a knowledge graph is characterized by comprising the following steps: the method comprises the following steps:
Step 1, a multi-physical coupling model of complex electromechanical equipment is established, performance indexes of the electromechanical equipment are clarified, and input sample points are established;
Step 2, inputting the sample points into a multi-physical coupling model to obtain response values, and performing series-parallel sampling on the sample points and the response values to generate a data set;
step 3, preprocessing the data set obtained in the step 2 to remove outliers, noise points and abnormal values as a training set;
Step 4, training the training set obtained in the step 3 to define an objective function, and performing iterative optimization on parameters by using a neural network until the best fitting effect is achieved, so as to obtain a substitute model;
Step 5, analyzing by using the substitution model obtained in the step 4 to obtain an input parameter, an entity outputting response and a corresponding relation;
Step 6, establishing a knowledge graph;
Step 7, performing complex electromechanical equipment performance evaluation through semantic retrieval and knowledge reasoning by using the knowledge graph obtained in the step 6; when evaluating the machining precision performance of a machine tool, through two steps of semantic search and knowledge reasoning, the semantic search firstly constructs a query command according to keywords, forms, natural language and formal language, constructs the query command according to query statement rules of Neo4j, completes query processing through matching and reasoning, and finally displays the result by using a visual mode of graph data to obtain all factors and influenced weights for influencing the machining precision of the numerical control machine tool, obtains an entity and corresponding attribute and entity relation for influencing the machining precision performance, and obtains the improvement on the performance of mechanical and electrical equipment by changing the influencing precision factors or finds the most efficient method for improving the machining precision of the machine tool;
The specific process of the step 6 comprises the following steps:
step 6.1, preprocessing the data obtained in the step 5;
Step 6.2, naming the entity and normalizing the term of the data obtained in the step 6.1;
Step 6.3, extracting different entities, entity relations and entity attribute information to form an ontology knowledge expression;
and 6.4, integrating the knowledge obtained in the step 6.3, eliminating contradiction and ambiguity, and adding qualified knowledge into the knowledge graph.
2. The method for evaluating the performance of the complex electromechanical device based on the surrogate model and the knowledge graph according to claim 1, wherein the establishing the multi-physical coupling model of the complex electromechanical device in step 1 specifically comprises: and (3) definitely determining participation parts of the complex electromechanical equipment in the working process, establishing models of different parts by using a finite element analysis method, establishing a Matlab/simulink system by using the models of different parts established by the finite element analysis method, establishing a simulation model, establishing a mathematical model related to the system, and performing multi-physical field simulation calculation on a simulation platform by taking a simulation result as an initial condition.
3. The method for evaluating the performance of the complex electromechanical equipment based on the substitution model and the knowledge graph according to claim 1, wherein the preprocessing method in the step 6.1 comprises normalization, discretization and sparsification of data.
4. A complex electromechanical equipment performance evaluation method based on a surrogate model and a knowledge graph according to claim 3, wherein the normalization processing adopts a method comprising a clustering algorithm, a KNN algorithm and an SVM algorithm.
5. The complex electromechanical equipment performance evaluation method based on the substitution model and the knowledge graph according to claim 3, wherein the discretization processing method comprises an equal frequency method, an equal width method and a clustering method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210573084.2A CN114997001B (en) | 2022-05-25 | 2022-05-25 | Complex electromechanical equipment performance evaluation method based on substitution model and knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210573084.2A CN114997001B (en) | 2022-05-25 | 2022-05-25 | Complex electromechanical equipment performance evaluation method based on substitution model and knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114997001A CN114997001A (en) | 2022-09-02 |
| CN114997001B true CN114997001B (en) | 2024-04-26 |
Family
ID=83029070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210573084.2A Active CN114997001B (en) | 2022-05-25 | 2022-05-25 | Complex electromechanical equipment performance evaluation method based on substitution model and knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114997001B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103310102A (en) * | 2013-06-07 | 2013-09-18 | 沈阳机床(集团)有限责任公司 | Comprehensive machine tool property evaluation method based on entropy weight and membership theory |
| CN111090735A (en) * | 2019-12-25 | 2020-05-01 | 成都航天科工大数据研究院有限公司 | Intelligent question-answering method based on knowledge graph and performance evaluation method thereof |
| CN113269371A (en) * | 2021-06-23 | 2021-08-17 | 华北电力大学（保定） | Method and system for evaluating comprehensive performance of power supply of intelligent power distribution network |
| CN113946692A (en) * | 2021-11-04 | 2022-01-18 | 讯飞智元信息科技有限公司 | Knowledge graph ontology evaluation method, device, equipment and storage medium |
| CN114332135A (en) * | 2022-03-10 | 2022-04-12 | 之江实验室 | Semi-supervised medical image segmentation method and device based on dual-model interactive learning |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4031627B2 (en) * | 2001-10-02 | 2008-01-09 | 株式会社森精機製作所 | Machine tool performance evaluation apparatus and performance evaluation system including the same |
| US10814448B2 (en) * | 2018-08-28 | 2020-10-27 | Dalian University Of Technology | Comprehensive performance evaluation method for CNC machine tools based on improved pull-off grade method |
-
2022
- 2022-05-25 CN CN202210573084.2A patent/CN114997001B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103310102A (en) * | 2013-06-07 | 2013-09-18 | 沈阳机床(集团)有限责任公司 | Comprehensive machine tool property evaluation method based on entropy weight and membership theory |
| CN111090735A (en) * | 2019-12-25 | 2020-05-01 | 成都航天科工大数据研究院有限公司 | Intelligent question-answering method based on knowledge graph and performance evaluation method thereof |
| CN113269371A (en) * | 2021-06-23 | 2021-08-17 | 华北电力大学（保定） | Method and system for evaluating comprehensive performance of power supply of intelligent power distribution network |
| CN113946692A (en) * | 2021-11-04 | 2022-01-18 | 讯飞智元信息科技有限公司 | Knowledge graph ontology evaluation method, device, equipment and storage medium |
| CN114332135A (en) * | 2022-03-10 | 2022-04-12 | 之江实验室 | Semi-supervised medical image segmentation method and device based on dual-model interactive learning |
Non-Patent Citations (2)
| Title |
|---|
| Ruihang Wang,et al.Kalibre: Knowledge-based Neural Surrogate Model Calibration for Data Center Digital Twins.《arXiv:2001.10681v3》.2020,正文第1-10页. * |
| 基于贝叶斯理论的复杂装备综合性能评价方法研究;吴永明 等;《组合机床与自动化加工技术》;20200331;正文第164-168页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114997001A (en) | 2022-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yan et al. | KnowIME: a system to construct a knowledge graph for intelligent manufacturing equipment | |
| CN104408173A (en) | Method for automatically extracting kernel keyword based on B2B platform | |
| CN110704577A (en) | Method and system for searching power grid scheduling data | |
| CN112199512B (en) | Scientific and technological service-oriented case map construction method, device, equipment and storage medium | |
| CN116340530A (en) | Intelligent design method based on mechanical knowledge graph | |
| Bortnikova et al. | Queries classification using machine learning for implementation in intelligent manufacturing | |
| Popping et al. | Network approaches in text analysis | |
| CN106844765B (en) | Significant information detection method and device based on convolutional neural network | |
| Leng et al. | Automatic MEP knowledge acquisition based on documents and natural language processing | |
| Priandini et al. | Categorizing document by fuzzy C-Means and K-nearest neighbors approach | |
| Ge et al. | A Novel Chinese Domain Ontology Construction Method for Petroleum Exploration Information. | |
| Zhang et al. | A knowledge reuse-based computer-aided fixture design framework | |
| CN114997001B (en) | Complex electromechanical equipment performance evaluation method based on substitution model and knowledge graph | |
| CN116737967A (en) | Knowledge graph construction and perfecting system and method based on natural language | |
| CN117010373A (en) | Recommendation method for category and group to which asset management data of power equipment belong | |
| CN110866317A (en) | Design tool kit reconstruction method based on product historical information and design behavior analysis | |
| Zhuo | Consumer Demand Behavior Mining and Product Recommendation Based on Online Product Review Mining and Fuzzy Sets | |
| CN111581815B (en) | XML-based process model ontology construction method | |
| CN113326348A (en) | Blog quality evaluation method and tool | |
| Anastasopoulos et al. | Computational text analysis for public management research: An annotated application to county budgets | |
| Shang et al. | Correlation based analysis of parameter change propagation in variant product design | |
| CN109492303B (en) | Derivation rule automatic generation method based on product family script | |
| Charnine et al. | Optimal automated method for collaborative development of universiry curricula | |
| Wei et al. | A Data-Driven Human–Machine Collaborative Product Design System Toward Intelligent Manufacturing | |
| Qi et al. | A hierarchical category model for geometrical product specifications (GPS) |
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 |