CN116521904A - Ship manufacturing data cloud fusion method and system based on 5G edge calculation - Google Patents
Ship manufacturing data cloud fusion method and system based on 5G edge calculation Download PDFInfo
- Publication number
- CN116521904A CN116521904A CN202310784277.7A CN202310784277A CN116521904A CN 116521904 A CN116521904 A CN 116521904A CN 202310784277 A CN202310784277 A CN 202310784277A CN 116521904 A CN116521904 A CN 116521904A
- Authority
- CN
- China
- Prior art keywords
- data
- representing
- equipment
- triplet
- manufacturing
- 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.)
- Granted
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 97
- 238000004364 calculation method Methods 0.000 title claims abstract description 46
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 10
- 239000000463 material Substances 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000011156 evaluation Methods 0.000 claims description 63
- 239000011159 matrix material Substances 0.000 claims description 47
- 230000004927 fusion Effects 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 22
- 230000005540 biological transmission Effects 0.000 claims description 21
- 239000013598 vector Substances 0.000 claims description 20
- 238000005520 cutting process Methods 0.000 claims description 9
- 230000001186 cumulative effect Effects 0.000 claims description 4
- 230000035945 sensitivity Effects 0.000 claims description 4
- 238000003064 k means clustering Methods 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 2
- 230000003068 static effect Effects 0.000 claims description 2
- 230000001502 supplementing effect Effects 0.000 claims description 2
- 230000002349 favourable effect Effects 0.000 abstract 1
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a ship manufacturing data cloud fusion method and system based on 5G edge calculation, wherein the method comprises the following steps: collecting data of a ship manufacturing workshop and dividing the data into time sequence data and state data; the state data comprise equipment operation state data and material state data; determining the manufacturing process of the equipment according to the equipment operation state data and the material state data, and constructing a first triplet according to the equipment and the manufacturing process of the equipment; carrying out homologous object marking on the time sequence data, and determining a first homologous object; constructing a second triplet by using the first homologous object and the time-ordered data; carrying out homologous object marking on the state data, and determining a second homologous object; constructing a third triplet by using the second homologous object and the state data; and carrying out entity alignment on the first triplet, the second triplet and the third triplet according to the homologous object to construct the ship manufacturing knowledge graph. The method is favorable for efficiently evaluating the manufacturing production efficiency of the ship.
Description
Technical Field
The application relates to the technical field of data fusion, in particular to a ship manufacturing data cloud fusion method and system based on 5G edge calculation.
Background
Data fusion is an important step for realizing transformation and upgrading of manufacturing industry, however, in the intelligent manufacturing workshop scene of ships and the like, a large number of operators, different types of equipment and material types exist, mass manufacturing data can be generated in the daily production and manufacturing process, the types of the data are various, the dimension is extremely high, and the efficient and reliable transmission of the data is the first problem to be solved; how to fully mine useful information in mass data is the second biggest problem to be solved.
Disclosure of Invention
Based on this, there is a need to provide a method for cloud fusion of ship manufacturing data based on 5G edge computation, the method comprising:
s1: collecting data of a ship manufacturing workshop and dividing the data into time sequence data and state data; the state data comprise equipment operation state data and material state data;
s2: determining the manufacturing process of the equipment according to the equipment operation state data and the material state data, and constructing a first triplet according to the equipment and the manufacturing process of the equipment;
s3: marking the time sequence type data with a homologous object, and determining a first homologous object; constructing a second triplet with the first homologous object and the time sequence data;
marking the homologous object of the state data, and determining a second homologous object; and constructing a third triplet with the second cognate object and the stateful data;
s4: and carrying out entity alignment on the first triplet, the second triplet and the third triplet according to the homologous object to construct a ship manufacturing knowledge graph.
The invention also provides a ship manufacturing data cloud fusion system based on 5G edge calculation, which comprises:
the system comprises an acquisition module, a layered transmission module, an edge calculation module, a 5G transmission module, a cloud fusion module and an evaluation module;
the acquisition module is used for acquiring data of a ship manufacturing workshop and dividing the data into time sequence data and state data;
the layered transmission module is used for layered transmission of the time sequence type data and the state type data to the edge calculation module;
the edge calculation module is used for constructing an information model subgraph according to the time sequence type data and the state type data;
the 5G transmission module is used for transmitting the constructed information model subgraph to the cloud fusion module through 5G equipment;
the cloud fusion module is used for fusing the information model subgraphs to construct the ship manufacturing knowledge graph;
the evaluation module is used for cutting the ship manufacturing knowledge graph into target clusters, and further performing ship manufacturing efficiency evaluation based on the target clusters.
The beneficial effects are that: the method can carry out layered transmission on mass object data in the intelligent manufacturing workshop scene of ships and the like, constructs an information model subgraph, and then fuses to obtain a ship manufacturing knowledge graph, thereby being beneficial to efficiently evaluating the ship manufacturing production efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a ship manufacturing data cloud fusion method based on 5G edge computation according to an embodiment of the present application.
Detailed Description
In order to make the above objects, features and advantages of the present application more comprehensible, embodiments accompanied with figures are described in detail below. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is, however, susceptible of embodiment in many other forms than those described herein and similar modifications can be made by those skilled in the art without departing from the spirit of the application, and therefore the application is not to be limited to the specific embodiments disclosed below.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" is at least two, such as two, three, etc., unless explicitly defined otherwise.
As shown in fig. 1, the present embodiment provides a method for fusing ship manufacturing data cloud based on 5G edge calculation, the method including:
s1: collecting data of a ship manufacturing workshop and dividing the data into time sequence data and state data; the state data comprise equipment operation state data and material state data.
Specifically, the time sequence data is acquired data of a sensor installed on the equipment; the sensor comprises a temperature sensor, a voltage sensor, a current sensor, a vibration sensor and a rotating speed sensor;
the state data also comprises equipment static parameters and personnel state data;
the equipment running state data comprise equipment starting state, equipment stopping state, alarm, fault type and equipment position;
the material state data comprises a material identification code, a product name, a specification and an execution standard;
the personnel status data comprises sign-in, work number, name, on-duty time length, personnel position and work order information.
The time sequence data has the characteristics of time variation, high frequency and large capacity; the state data has the characteristics of state dependence, low frequency and small capacity.
S2: and determining the manufacturing process of the equipment according to the equipment operation state data and the material state data, and constructing a first triplet according to the equipment and the manufacturing process of the equipment.
The method specifically comprises the following steps:
step 1: determining an enabled device according to the device start state and the device stop state; scanning the material identification code to obtain material information, and determining the type of the material according to the material information;
step 2: constructing a state character pair according to the enabled equipment and the types of the materials;
step 3: acquiring expert priori knowledge character pairs from an expert priori knowledge base, and calculating editing distances between the state character pairs and the expert priori knowledge character pairs;
step 4: calculating the similarity between the state character pair and the expert a priori knowledge character pair based on the editing distance;
the similarity calculation formula is as follows:
；
wherein ,representing the similarity between the pair of status characters and the pair of expert a priori knowledge characters; (E',M') represents a pair of status characters; (E,M ) Representing expert a priori knowledge character pairs;E' indicate start-upA device for use;M' indicates the kind of material;Erepresenting enabled devices in the expert a priori knowledge base;Mrepresenting the types of materials in the expert priori knowledge base;n 1 +n 2 representing edit distance between the state character pair and the expert a priori knowledge character pair;n 1 representing the minimum number of edits required to convert the name of the enabled device to the name of the enabled device in the expert a priori knowledge base;n 2 the minimum number of edits required to convert the name representing the category of the material into the name of the category of the material in the expert a priori knowledge base;σthe formula sensitivity control parameter (in this embodiment, the parameter is obtained by setting and can be adjusted according to the actual application condition) is expressed.
Step 5: when the similarity reaches a set threshold, matching infers that the manufacturing process of the device is being performed, i.e., determining the manufacturing process of the device.
The calculation formula is as follows:
；
wherein ,Ed[(E',M'),(E,M )]representing a total edit distance function of the state character pairs and the expert a priori knowledge character pairs;representing the similarity; s represents a set threshold; w represents the manufacturing process.
Table 1 is a partial process priori knowledge table in a ship manufacturing process expert priori knowledge base;
as can be seen from table 1, the vessel manufacturing process expert has a priori knowledge of a part of the process in the vessel manufacturing process expert's a priori knowledge base.
Constructing a first triplet according to a manufacturing process of the apparatus includes:
constructing the first triplet by taking the equipment as a head entity and a process as a relation, and taking the manufacturing process of the equipment as a specific process, wherein the first triplet is expressed as: { header entity, process, specific process }.
S3: marking the time sequence type data with a homologous object, and determining a first homologous object; constructing a second triplet with the first homologous object and the time sequence data;
marking the homologous object of the state data, and determining a second homologous object; and constructing a third triplet with the second cognate object and the stateful data.
Specifically, constructing a second triplet with the first synchronization object and the time-sequential data includes:
taking the first homologous object as a head entity, taking a sensor type as an attribute, taking time sequence data corresponding to the sensor type as an attribute value, and constructing the second triplet, wherein the second triplet is expressed as: { header entity, attribute value };
constructing a third triplet with the second cognate object and the stateful data comprises:
and constructing the third triplet by taking the second homologous object as a head entity, the category of the state data as a relation, and the data corresponding to the category of the state data as a tail entity, wherein the third triplet is expressed as: { head entity, relationship, tail entity }.
In this embodiment, the first and second homologous objects may be the same object.
In the embodiment, an entity relation extraction rule is formulated, and time sequence type data and state type data acquired under a homologous object are mapped and constructed according to the entity relation extraction rule to form an attribute, an attribute value or a relation and a tail entity based on the rule;
table 2 is a table of entity relationship extraction rules;
as can be seen from table 2, the mapping rule of the time-series type data and the state type data.
For example, when a welder is a homologous object, a head entity is first constructed as a welder, and attribute values are constructed from values of a current-voltage sensor, such as "current" and "voltage", which are constructed from types of current-voltage sensors.
S4: and carrying out entity alignment on the first triplet, the second triplet and the third triplet according to the homologous object to construct a ship manufacturing knowledge graph.
The method specifically comprises the following steps:
s4.1: aligning the first triples, the second triples and the third triples with the same head entity to obtain an information model subgraph; the information model subgraph comprises a plurality of information model subgraphs;
s4.2: and carrying out entity alignment on the information model subgraphs by taking the equipment type as an entity, and constructing the ship manufacturing knowledge graph.
In this embodiment, the ship manufacturing data cloud fusion method further includes:
s5: carrying out graph cutting on the ship manufacturing knowledge graph by adopting a spectral clustering algorithm, and cutting out a target cluster; the target cluster comprises a human target cluster, a device target cluster and a process for cutting out the target cluster by the material target cluster, wherein the process comprises the following steps:
s5.1: setting the number of target clusters to be 3, and taking each information model subgraph as a sample point; including a plurality of specific process or attribute values or tail entities in the sample points, and the plurality of specific process or attribute values or tail entities forming a vector; the dimension of the vector corresponding to each sample point is different;
s5.2: searching the highest dimension of the vector, and supplementing the vector with the low dimension by adding 0 with the highest dimension as the upper limit; after the dimensions are aligned, calculating the similarity between every two sample points; constructing a similarity matrix according to the similarity between every two sample points; the similarity between every two sample points is used as the weight between every two sample points;
the calculation formula is as follows:
；
wherein ,represent the firstiSample points and the firstjSimilarity between individual sample points;nrepresenting the number of sample points;represent the firstiSample points and the firstjL2 norms between sample points;σexpressing a formula sensitivity control parameter; the size of the similarity matrix isn×n；
S5.3: calculating a similarity matrix of the similarity matrix according to the similarity matrix; the calculation formula is as follows:
；
wherein ,d i a representation;W ab representing the first in the similarity matrixaLine 1bSimilarity of columns; the similarity matrix isd i A diagonal array of the size ofn×n；
S5.4: calculating a Laplace matrix according to the similarity matrix and the degree matrix; the calculation formula is as follows:
L=D-W；
wherein ,Lrepresenting a laplace matrix;Da degree matrix representing a similarity matrix;Wrepresenting a similarity matrix;
s5.5: calculating first eigenvalues in the Laplace matrix, sorting the first eigenvalues from small to large, and selecting the first 3 eigenvalues; calculating the feature vectors of the first 3 selected feature values;
the first characteristic value is calculated by the following calculation formula:
；
wherein ,Lrepresenting a laplace matrix;λis a variable;Qis thatn×nIs a matrix of units of (a);representing a feature polynomial; and the root of the characteristic polynomial is the first characteristic value. The characteristic polynomial is a determinant, the determinant is expanded into a unitary multiple equation, and the variable is divided into a plurality of functionsλSolving; in practical application, because the dimension of the matrix is high, calculation cannot be performed manually, and a function library can be directly called in python or matlab.
S5.6: constructing a matrix based on the calculated 3 eigenvectors, wherein the column number of the matrix is 3, and the row number of the matrix isn；
S5.7: clustering all row vectors of the matrix into clusters using a k-means clustering algorithm;
the clustering process using the k-means clustering algorithm includes:
step 1: initializing a clustering center: k=3 data points were chosen as the initial cluster center.
Step 2: assigning data points to nearest cluster centers: for each data point, its distance from all cluster centers is calculated and assigned to the cluster center closest thereto.
Step 3: updating a clustering center: for each cluster, the average of all data points in the cluster is calculated and taken as the new cluster center.
Step 4: repeating the step 2 and the step 3, namely repeating the processes of data point distribution and cluster center updating until a stopping condition is reached; the stopping condition is that the cluster center does not change significantly any more.
Step 5: outputting a clustering result: when the stopping condition is met, the algorithm converges and a final clustering result is obtained; each data point is assigned to one cluster, forming k=3 different target clusters.
S5.8: and outputting 3 target clusters.
In this embodiment, the homologous objects are classified into three types, namely, person, machine and object, and are respectively corresponding to person, equipment and material.
Performing ship manufacturing efficiency evaluation based on the cut target cluster, wherein the ship manufacturing efficiency evaluation method comprises the following steps:
step 1: aiming at the cut human target cluster, equipment target cluster and material target cluster, collecting personnel evaluation indexes, equipment evaluation indexes and material evaluation indexes;
personnel evaluation indexes include, but are not limited to, check-in rate, on duty duration, work order completion rate, compliance with production scheduling conditions, violation conditions and civilized operation conditions (1-10).
The equipment evaluation indexes comprise but not limited to equipment utilization rate, alarm rate, failure rate (type 1: mechanical failure, mechanical failure includes but not limited to part wear, part fracture, part seizing, insufficient lubrication, error for the equipment), failure rate (type 2: non-mechanical failure, non-mechanical failure includes but not limited to electrical failure, sensor failure, control system failure, temperature abnormality, material supply problem, operation error), average failure interval time, finished product qualification rate, equipment damage condition (1-10).
The material evaluation index comprises, but is not limited to, material utilization rate, waste material utilization rate, material yield and material in-place condition.
Step 2: normalizing each evaluation index; the calculation formula is as follows:
；
wherein ,a data value representing the normalized evaluation index; />Represent the firstiSample number 1jActual values of the individual evaluation indicators;μ j represent the firstjThe average value of the individual evaluation indexes;s j represent the firstjStandard deviation of each evaluation index;
step 3: calculating a correlation coefficient matrix based on the standardized evaluation index; the calculation formula is as follows:
；
wherein ,mrepresenting the number of samples to be taken,r gh representing the first of the correlation coefficient matricesgLine 1hElements of a column;represent the firstkSample number 1lActual values of the individual evaluation indicators;X kj represent the firstkSample number 1jActual values of the individual evaluation indicators;
step 4: calculating the characteristic value and the characteristic vector in the correlation coefficient matrix, and calculating the contribution degree of the main component to the final evaluation result based on the characteristic value and the characteristic vector in the correlation coefficient matrix; the calculation formula is as follows:
；
wherein ,representing the contribution degree of the main component to the final evaluation result;prepresenting the number of corresponding principal components taken when the cumulative contribution rate reaches 80%;trepresenting the number of evaluation indexes; />Represent the firstvCharacteristic values of the individual principal components; />Represent the firstqCharacteristic values of the evaluation indexes;
step 5: the PCA score is calculated, and the calculation formula is as follows:
；
；
wherein ,Frepresenting PCA scores;prepresenting the number of corresponding principal components taken when the cumulative contribution rate reaches 80%;b v represent the firstvContribution rates of the individual feature values; (PC) v Represent the firstvA computational expression of the individual principal components;represent the firstvFeature vector of each principal componentjElements corresponding to the evaluation indexes; />Represent the firstjData values normalized by the individual evaluation indexes;
step 6: step 2-5 is circulated until all kinds of evaluation indexes are calculated, so as to obtain PCA scores of personnel evaluation indexes, PCA scores of equipment evaluation indexes and PCA scores of material evaluation indexes; calculating a ship manufacturing efficiency comprehensive score based on the three PCA scores, and performing ship manufacturing efficiency evaluation according to the ship manufacturing efficiency comprehensive score; the calculation formula is as follows:
F total = 0.2F 1 + 0.4F 2 + 0.4F 3 ；
wherein ,F total a composite score representing vessel manufacturing efficiency;F 1 PCA scores representing personnel assessment indicators;F 2 PCA scores representing device evaluation metrics;F 3 and (5) representing a PCA score of the material evaluation index.
The method provided by the embodiment has the following beneficial effects:
1. according to the characteristics of the data, the data is automatically layered into time sequence data and state data to realize layered transmission, and the efficiency and reliability of data acquisition and transmission in a ship manufacturing workshop can be improved based on a 5G edge calculation technology.
2. The method for analyzing the main components of the spectral clustering and the PCA is used for carrying out data fusion analysis on the ship manufacturing data at the cloud, so that the problems of 'dimensional disaster' of the ship manufacturing data can be solved, the current situations of rich information and poor knowledge can be relieved, the complexity can be reduced, and the data can be better recognized and understood, thereby obtaining comprehensive evaluation of the ship manufacturing efficiency, and having a certain guiding significance on the ship manufacturing production.
The embodiment also provides a ship manufacturing data cloud fusion system based on 5G edge calculation, which comprises: the system comprises an acquisition module, a layered transmission module, an edge calculation module, a 5G transmission module, a cloud fusion module and an evaluation module;
the acquisition module is used for acquiring data of a ship manufacturing workshop and dividing the data into time sequence data and state data;
the layered transmission module is used for layered transmission of the time sequence type data and the state type data to the edge calculation module;
the edge calculation module is used for constructing an information model subgraph according to the time sequence type data and the state type data;
the 5G transmission module is used for transmitting the constructed information model subgraph to the cloud fusion module through 5G equipment; the 5G devices include, but are not limited to, 5G modules, 5G CPE.
The cloud fusion module is used for fusing the information model subgraphs to construct the ship manufacturing knowledge graph;
the evaluation module is used for cutting the ship manufacturing knowledge graph into target clusters, and further performing ship manufacturing efficiency evaluation based on the target clusters.
The system can perform layered transmission on mass object data in intelligent manufacturing workshop scenes such as ships and the like, performs partial calculation tasks on an edge calculation module, realizes high-reliability and low-delay transmission by using 5G, performs data fusion analysis on a cloud, and efficiently evaluates the manufacturing production efficiency of the ships.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the claims. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. The utility model provides a ship manufacturing data cloud fusion method based on 5G edge calculation, which is characterized by comprising the following steps:
s1: collecting data of a ship manufacturing workshop and dividing the data into time sequence data and state data; the state data comprise equipment operation state data and material state data;
s2: determining the manufacturing process of the equipment according to the equipment operation state data and the material state data, and constructing a first triplet according to the equipment and the manufacturing process of the equipment;
s3: marking the time sequence type data with a homologous object, and determining a first homologous object; constructing a second triplet with the first homologous object and the time sequence data;
marking the homologous object of the state data, and determining a second homologous object; and constructing a third triplet with the second cognate object and the stateful data;
s4: and carrying out entity alignment on the first triplet, the second triplet and the third triplet according to the homologous object to construct a ship manufacturing knowledge graph.
2. The method for cloud fusion of manufacturing data of a ship based on 5G edge calculation according to claim 1, wherein in S1, the time-series data is sensor acquisition data installed on a device; the sensor comprises a temperature sensor, a voltage sensor, a current sensor, a vibration sensor and a rotating speed sensor;
the state data also comprises equipment static parameters and personnel state data;
the equipment running state data comprise equipment starting state, equipment stopping state, alarm, fault type and equipment position;
the material state data comprises a material identification code, a product name, a specification and an execution standard;
the personnel status data comprises sign-in, work number, name, on-duty time length, personnel position and work order information.
3. The method of cloud fusion of manufacturing data of a ship based on 5G edge calculation according to claim 2, wherein in S2, determining a manufacturing process of a device according to the device operation state data and the material state data comprises:
step 1: determining an enabled device according to the device start state and the device stop state; scanning the material identification code to obtain material information, and determining the type of the material according to the material information;
step 2: constructing a state character pair according to the enabled equipment and the types of the materials;
step 3: acquiring expert priori knowledge character pairs from an expert priori knowledge base, and calculating editing distances between the state character pairs and the expert priori knowledge character pairs;
step 4: calculating the similarity between the state character pair and the expert a priori knowledge character pair based on the editing distance;
step 5: when the similarity reaches a set threshold, determining a manufacturing process being performed by the device, i.e. determining the manufacturing process of the device.
4. The ship manufacturing data cloud fusion method based on 5G edge calculation of claim 3, wherein the similarity calculation formula is:
；
wherein ,representing the similarity between the pair of status characters and the pair of expert a priori knowledge characters; (E',M') represents a pair of status characters; (E,M ) Representing expert a priori knowledge character pairs;E' means an enabled device;M' indicates the kind of material;Erepresenting enabled devices in the expert a priori knowledge base;Mrepresenting the types of materials in the expert priori knowledge base;n 1 +n 2 representing edit distance between the state character pair and the expert a priori knowledge character pair;n 1 representing the minimum number of edits required to convert the name of the enabled device to the name of the enabled device in the expert a priori knowledge base;n 2 the minimum number of edits required to convert the name representing the category of the material into the name of the category of the material in the expert a priori knowledge base;σthe formula sensitivity control parameters are expressed.
5. The method of cloud fusion of vessel fabrication data based on 5G edge computation of claim 2, wherein in S2, constructing a first triplet according to the equipment and the fabrication process of the equipment comprises:
constructing the first triplet by taking the equipment as a head entity and a process as a relation, and taking the manufacturing process of the equipment as a specific process, wherein the first triplet is expressed as: { header entity, process, specific process }.
6. The method of 5G edge computing based marine manufacturing data cloud fusion of claim 5, wherein constructing a second triplet of the first homogeneous object and the time-sequential data in S3 comprises:
taking the first homologous object as a head entity, taking a sensor type as an attribute, taking time sequence data corresponding to the sensor type as an attribute value, and constructing the second triplet, wherein the second triplet is expressed as: { header entity, attribute value };
constructing a third triplet with the second cognate object and the stateful data comprises:
and constructing the third triplet by taking the second homologous object as a head entity, the category of the state data as a relation, and the data corresponding to the category of the state data as a tail entity, wherein the third triplet is expressed as: { head entity, relationship, tail entity }.
7. The method for cloud fusion of manufacturing data of a ship based on 5G edge calculation of claim 6, wherein in S4, the process of constructing a ship manufacturing knowledge graph includes:
s4.1: aligning the first triples, the second triples and the third triples with the same head entity to obtain an information model subgraph; the information model subgraph comprises a plurality of information model subgraphs;
s4.2: and carrying out entity alignment on the information model subgraphs by taking the homologous objects as entities, and constructing the ship manufacturing knowledge graph.
8. The 5G edge computation based marine manufacturing data cloud fusion method of claim 1, further comprising:
s5: carrying out graph cutting on the ship manufacturing knowledge graph by adopting a spectral clustering algorithm, and cutting out a target cluster; the target cluster comprises a human target cluster, an equipment target cluster and a material target cluster, and the process of cutting out the target cluster comprises the following steps:
s5.1: setting the number of target clusters to be 3, and taking each information model subgraph as a sample point; including a plurality of specific process or attribute values or tail entities in the sample points, and the plurality of specific process or attribute values or tail entities forming a vector; the dimension of the vector corresponding to each sample point is different;
s5.2: searching the highest dimension of the vector, and supplementing the vector with the low dimension by adding 0 with the highest dimension as the upper limit; after the dimensions are aligned, calculating the similarity between every two sample points; constructing a similarity matrix according to the similarity between every two sample points; the similarity between every two sample points is used as the weight between every two sample points;
the calculation formula is as follows:
；
wherein ,represent the firstiSample points and the firstjSimilarity between individual sample points;nrepresenting the number of sample points;represent the firstiSample points and the firstjL2 norms between sample points;σexpressing a formula sensitivity control parameter; the size of the similarity matrix isn×n；
S5.3: calculating a similarity matrix of the similarity matrix according to the similarity matrix; the calculation formula is as follows:
；
wherein ,d i a representation;W ab representing the first in the similarity matrixaLine 1bSimilarity of columns; the similarity matrix isd i A diagonal array of the size ofn×n；
S5.4: calculating a Laplace matrix according to the similarity matrix and the degree matrix; the calculation formula is as follows:
L=D-W；
wherein ,Lrepresenting a laplace matrix;Da degree matrix representing a similarity matrix;Wrepresenting a similarity matrix;
s5.5: calculating first eigenvalues in the Laplace matrix, sorting the first eigenvalues from small to large, and selecting the first 3 eigenvalues; calculating the feature vectors of the first 3 selected first feature values;
s5.6: constructing a matrix based on the calculated 3 eigenvectors, wherein the column number of the matrix is 3, and the row number of the matrix isn；
S5.7: clustering all row vectors of the matrix into clusters using a k-means clustering algorithm;
s5.8: and outputting 3 target clusters.
9. The 5G edge calculation based marine vessel manufacturing data cloud fusion method of claim 8, further comprising performing a marine vessel manufacturing efficacy assessment based on the cut-out target cluster, the process comprising:
step 1: aiming at the cut human target cluster, equipment target cluster and material target cluster, collecting personnel evaluation indexes, equipment evaluation indexes and material evaluation indexes;
step 2: normalizing each evaluation index; the calculation formula is as follows:
；
wherein ,a data value representing the normalized evaluation index; />Represent the firstiSample number 1jActual values of the individual evaluation indicators;μ j represent the firstjThe average value of the individual evaluation indexes;s j represent the firstjStandard deviation of each evaluation index;
step 3: calculating a correlation coefficient matrix based on the standardized evaluation index; the calculation formula is as follows:
；
wherein ,mrepresenting the number of samples to be taken,r gh representing the first of the correlation coefficient matricesgLine 1hElements of a column;represent the firstkSample number 1lActual values of the individual evaluation indicators;X kj represent the firstkSample number 1jActual values of the individual evaluation indicators;
step 4: calculating the characteristic value and the characteristic vector in the correlation coefficient matrix, and calculating the contribution degree of the main component to the final evaluation result based on the characteristic value and the characteristic vector in the correlation coefficient matrix; the calculation formula is as follows:
；
wherein ,representing the contribution degree of the main component to the final evaluation result;prepresenting the number of corresponding principal components taken when the cumulative contribution rate reaches 80%;trepresenting the number of evaluation indexes; />Representation ofpMiddle (f)vFeature vectors of the individual principal components; />Represent the firstqCharacteristic values of the evaluation indexes;
step 5: the PCA score is calculated, and the calculation formula is as follows:
；
；
wherein ,Frepresenting PCA scores;pindicating that the cumulative contribution rate reaches 80%The number of the obtained corresponding main components;b v represent the firstvThe contribution rate of the feature vectors of the individual principal components; (PC) v Represent the firstvA computational expression of the individual principal components;represent the firstvFeature vector of each principal componentjElements corresponding to the evaluation indexes; />Represent the firstjData values normalized by the individual evaluation indexes;
step 6: step 2-5 is circulated until all kinds of evaluation indexes are calculated, so as to obtain PCA scores of personnel evaluation indexes, PCA scores of equipment evaluation indexes and PCA scores of material evaluation indexes; calculating a ship manufacturing efficiency comprehensive score based on the three PCA scores, and performing ship manufacturing efficiency evaluation according to the ship manufacturing efficiency comprehensive score; the calculation formula is as follows:
F total = 0.2F 1 + 0.4F 2 + 0.4F 3 ；
wherein ,F total a composite score representing vessel manufacturing efficiency;F 1 PCA scores representing personnel assessment indicators;F 2 PCA scores representing device evaluation metrics;F 3 and (5) representing a PCA score of the material evaluation index.
10. A 5G edge computation based shipbuilding data cloud fusion system, comprising: the system comprises an acquisition module, a layered transmission module, an edge calculation module, a 5G transmission module, a cloud fusion module and an evaluation module;
the acquisition module is used for acquiring data of a ship manufacturing workshop and dividing the data into time sequence data and state data;
the layered transmission module is used for layered transmission of the time sequence type data and the state type data to the edge calculation module;
the edge calculation module is used for constructing an information model subgraph according to the time sequence type data and the state type data;
the 5G transmission module is used for transmitting the constructed information model subgraph to the cloud fusion module through 5G equipment;
the cloud fusion module is used for fusing the information model subgraphs to construct the ship manufacturing knowledge graph;
the evaluation module is used for cutting the ship manufacturing knowledge graph into target clusters, and further performing ship manufacturing efficiency evaluation based on the target clusters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310784277.7A CN116521904B (en) | 2023-06-29 | 2023-06-29 | Ship manufacturing data cloud fusion method and system based on 5G edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310784277.7A CN116521904B (en) | 2023-06-29 | 2023-06-29 | Ship manufacturing data cloud fusion method and system based on 5G edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116521904A true CN116521904A (en) | 2023-08-01 |
| CN116521904B CN116521904B (en) | 2023-09-22 |
Family
ID=87397953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310784277.7A Active CN116521904B (en) | 2023-06-29 | 2023-06-29 | Ship manufacturing data cloud fusion method and system based on 5G edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116521904B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117235559A (en) * | 2023-11-14 | 2023-12-15 | 四川万物纵横科技股份有限公司 | Internet of things data acquisition method and system based on edge calculation |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012000648A1 (en) * | 2010-06-28 | 2012-01-05 | Precitec Kg | Method for closed-loop controlling a laser processing operation and laser material processing head using the same |
| US20210103256A1 (en) * | 2019-09-06 | 2021-04-08 | Intelligent Fusion Technology, Inc. | Decision support method and apparatus for machinery control |
| WO2021258758A1 (en) * | 2020-06-22 | 2021-12-30 | 大连海洋大学 | Coastline change identification method based on multiple factors |
| CN114003734A (en) * | 2021-11-22 | 2022-02-01 | 四川大学华西医院 | Breast cancer risk factor knowledge system model, knowledge map system and construction method |
| WO2022072785A1 (en) * | 2020-10-01 | 2022-04-07 | University Of Massachusetts | A neural graph model for automated clinical assessment generation |
| CN115905574A (en) * | 2022-12-22 | 2023-04-04 | 杭州电子科技大学 | Knowledge graph construction method and device for ship power system design task |
| CN115905563A (en) * | 2022-11-15 | 2023-04-04 | 中华人民共和国盐城海事局 | Method and device for constructing ship field supervision knowledge graph and electronic equipment |
| CN115965085A (en) * | 2022-11-25 | 2023-04-14 | 集美大学 | Ship static attribute reasoning method and system based on knowledge graph technology |
| CN116340534A (en) * | 2023-02-27 | 2023-06-27 | 中能融合智慧科技有限公司 | Knowledge graph construction method and system for identifying new energy abnormal data |
-
2023
- 2023-06-29 CN CN202310784277.7A patent/CN116521904B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012000648A1 (en) * | 2010-06-28 | 2012-01-05 | Precitec Kg | Method for closed-loop controlling a laser processing operation and laser material processing head using the same |
| US20210103256A1 (en) * | 2019-09-06 | 2021-04-08 | Intelligent Fusion Technology, Inc. | Decision support method and apparatus for machinery control |
| WO2021258758A1 (en) * | 2020-06-22 | 2021-12-30 | 大连海洋大学 | Coastline change identification method based on multiple factors |
| WO2022072785A1 (en) * | 2020-10-01 | 2022-04-07 | University Of Massachusetts | A neural graph model for automated clinical assessment generation |
| CN114003734A (en) * | 2021-11-22 | 2022-02-01 | 四川大学华西医院 | Breast cancer risk factor knowledge system model, knowledge map system and construction method |
| CN115905563A (en) * | 2022-11-15 | 2023-04-04 | 中华人民共和国盐城海事局 | Method and device for constructing ship field supervision knowledge graph and electronic equipment |
| CN115965085A (en) * | 2022-11-25 | 2023-04-14 | 集美大学 | Ship static attribute reasoning method and system based on knowledge graph technology |
| CN115905574A (en) * | 2022-12-22 | 2023-04-04 | 杭州电子科技大学 | Knowledge graph construction method and device for ship power system design task |
| CN116340534A (en) * | 2023-02-27 | 2023-06-27 | 中能融合智慧科技有限公司 | Knowledge graph construction method and system for identifying new energy abnormal data |
Non-Patent Citations (1)
| Title |
|---|
| 张晔;贾雨葶;傅洛伊;王新兵;: "AceMap学术地图与AceKG学术知识图谱――学术数据可视化", 上海交通大学学报, no. 10 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117235559A (en) * | 2023-11-14 | 2023-12-15 | 四川万物纵横科技股份有限公司 | Internet of things data acquisition method and system based on edge calculation |
| CN117235559B (en) * | 2023-11-14 | 2024-02-06 | 四川万物纵横科技股份有限公司 | Internet of things data acquisition method and system based on edge calculation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116521904B (en) | 2023-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10831163B2 (en) | Syntax translation from first syntax to second syntax based on string analysis | |
| CN111158977A (en) | Abnormal event root cause positioning method and device | |
| CN116521904B (en) | Ship manufacturing data cloud fusion method and system based on 5G edge calculation | |
| CN114386538B (en) | Method for marking wave band characteristics of KPI (Key performance indicator) curve of monitoring index | |
| US11210555B2 (en) | High-dimensional image feature matching method and device | |
| CN111367777B (en) | Alarm processing method, device, equipment and computer readable storage medium | |
| CN108197647B (en) | Rapid clustering method for automobile starter endurance test data | |
| CN113626607B (en) | Abnormal work order identification method and device, electronic equipment and readable storage medium | |
| CN110515931B (en) | Capacitive type equipment defect prediction method based on random forest algorithm | |
| CN110297207A (en) | Method for diagnosing faults, system and the electronic device of intelligent electric meter | |
| CN112446399A (en) | Label determination method, device and system | |
| CN112699945A (en) | Data labeling method and device, storage medium and electronic device | |
| CN113435703A (en) | Wind turbine generator system fault analysis system based on SCADA data modeling | |
| CN115632966A (en) | Automatic operation and maintenance method of Internet of things equipment based on cloud computing | |
| CN115015683A (en) | Cable production performance test method, device, equipment and storage medium | |
| CN117319452B (en) | Safety inspection method and system applied to barium sulfate preparation | |
| CN115810419B (en) | Operation management method, device, equipment and storage medium for intelligent operating room | |
| CN112434049A (en) | Table data storage method and device, storage medium and electronic device | |
| CN114386535B (en) | Method for setting width of sliding window for scanning KPI curve | |
| CN108460119A (en) | A kind of system for supporting efficiency using machine learning lift technique | |
| CN104462139A (en) | User behavior clustering method and system | |
| Xia et al. | Automated manufacturability analysis in smart manufacturing systems: a signature mapping method for product-centered digital twins | |
| CN113033090A (en) | Push model training method, data push device and storage medium | |
| CN112070140A (en) | Density clustering mark-like pattern recognition method based on dimension decomposition | |
| CN117631599B (en) | Industrial control computer data transmission method and system based on data analysis |
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 |