CN110990663B - Ship process knowledge management method, device and system - Google Patents
Ship process knowledge management method, device and system Download PDFInfo
- Publication number
- CN110990663B CN110990663B CN201911231217.2A CN201911231217A CN110990663B CN 110990663 B CN110990663 B CN 110990663B CN 201911231217 A CN201911231217 A CN 201911231217A CN 110990663 B CN110990663 B CN 110990663B
- Authority
- CN
- China
- Prior art keywords
- ship
- knowledge
- ship process
- process knowledge
- dimension
- 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
- 238000000034 method Methods 0.000 title claims abstract description 570
- 238000007726 management method Methods 0.000 title claims abstract description 29
- 238000007621 cluster analysis Methods 0.000 claims abstract description 30
- 238000004519 manufacturing process Methods 0.000 claims description 49
- 238000012545 processing Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 5
- 239000003016 pheromone Substances 0.000 description 16
- 229910000831 Steel Inorganic materials 0.000 description 12
- 239000010959 steel Substances 0.000 description 12
- 239000006185 dispersion Substances 0.000 description 10
- 238000012360 testing method Methods 0.000 description 10
- 238000013461 design Methods 0.000 description 9
- 230000009286 beneficial effect Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000002708 enhancing effect Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a ship process knowledge management method, a device and a system. The method comprises the following steps: expressing the acquired ship process knowledge by adopting a preset knowledge expression method, classifying the ship process knowledge by adopting a tree classification method, and establishing a ship process knowledge base; the ship process knowledge base comprises a ship process example base and a ship resource database; according to ship process data input by a user, carrying out example reasoning on the ship process example library and outputting a first process knowledge set; and when the first process knowledge set cannot be output, performing cluster analysis on the ship resource database according to the ship process data, performing instance reasoning on the obtained cluster set, and outputting a second process knowledge set. The invention can realize the rapid acquisition and application of the ship process knowledge by establishing the ship process knowledge base.
Description
Technical Field
The invention relates to the technical field of digital manufacturing, in particular to a ship process knowledge management method, device and system.
Background
During the whole ship manufacturing process, such as ship design, steel pretreatment, steel blanking processing, component assembly, segmented manufacturing, slipway folding, launching, wharf mooring test, marine navigation test, ship delivery guarantee and the like, ship process knowledge is always kept through. Because the ship process knowledge is very complicated, the existing ship manufacturing still mainly depends on the management and control of various processes in the manufacturing process by workers according to the professional knowledge and the working experience of the workers, and the uniform and standardized manufacturing is difficult to realize. If the ship process knowledge involved in the whole ship manufacturing process can be managed to form a unified ship process knowledge system, workers can be helped to manage and control various processes in the manufacturing process according to the standard ship process knowledge, the product quality is improved, the manufacturing period and the labor cost are reduced, and therefore the market competitiveness of products is enhanced.
Disclosure of Invention
The invention provides a ship process knowledge management method, a device and a system, which can realize the quick acquisition and application of ship process knowledge by establishing a ship process knowledge base.
In order to solve the above technical problem, an embodiment of the present invention provides a ship process knowledge management method, including:
expressing the acquired ship process knowledge by adopting a preset knowledge expression method, classifying the ship process knowledge by adopting a tree classification method, and establishing a ship process knowledge base; the ship process knowledge base comprises a ship process example base and a ship resource database;
according to ship process data input by a user, carrying out example reasoning on the ship process example library and outputting a first process knowledge set; wherein the first process knowledge set is ship process knowledge in the ship process instance library that matches the ship process data;
when the first process knowledge set cannot be output, performing cluster analysis on the ship resource database according to the ship process data, performing instance reasoning on the obtained cluster set, and outputting a second process knowledge set; wherein the second process knowledge set is ship process knowledge in the ship resource database that matches the ship process data.
Further, the predetermined knowledge representation comprises one or more combinations of an object-oriented knowledge representation method, an instance-based knowledge representation method and a production rule knowledge representation method.
Further, the classifying the ship process knowledge by adopting a tree classification method comprises the following steps:
dividing the ship process knowledge into a professional dimension, a process dimension, a knowledge dimension and a product dimension according to the content attribute of the ship process knowledge;
according to the professional field of the ship process knowledge, dividing the ship process knowledge under the professional dimensionality into a plurality of professional categories;
according to the process flow of the ship process knowledge, dividing the ship process knowledge under the process dimensionality into a plurality of process categories;
dividing the ship process knowledge under the knowledge dimension into a plurality of knowledge categories according to the knowledge category of the ship process knowledge;
and dividing the ship process knowledge under the product dimensionality into a plurality of product categories according to the product types of the ship process knowledge.
Further, the performing cluster analysis on the ship resource database according to the ship process data specifically includes:
and according to the ship process data, carrying out cluster analysis on the ship process knowledge in the ship resource database through an ant colony algorithm to obtain the cluster set.
Another embodiment of the present invention further provides a ship process knowledge management apparatus, including:
the ship process knowledge base establishing module is used for representing the acquired ship process knowledge by adopting a preset knowledge representation method, classifying the ship process knowledge by adopting a tree classification method and establishing a ship process knowledge base; the ship process knowledge base comprises a ship process example base and a ship resource database;
the first process knowledge set output module is used for carrying out example reasoning on the ship process example base according to ship process data input by a user and outputting a first process knowledge set; wherein the first process knowledge set is ship process knowledge in the ship process instance library that matches the ship process data;
the second process knowledge set output module is used for carrying out cluster analysis on the ship resource database according to the ship process data when the first process knowledge set cannot be output, carrying out instance reasoning on the obtained cluster set and outputting a second process knowledge set; wherein the second process knowledge set is ship process knowledge in the ship resource database that matches the ship process data.
Further, the predetermined knowledge representation comprises one or more combinations of an object-oriented knowledge representation method, an instance-based knowledge representation method and a production rule knowledge representation method.
Further, the classifying the ship process knowledge by adopting a tree classification method comprises the following steps:
dividing the ship process knowledge into a professional dimension, a flow dimension, a knowledge dimension and a product dimension according to the content attribute of the ship process knowledge;
according to the professional field of the ship process knowledge, dividing the ship process knowledge under the professional dimensionality into a plurality of professional categories;
according to the process flow of the ship process knowledge, dividing the ship process knowledge under the process dimension into a plurality of process categories;
dividing the ship process knowledge under the knowledge dimension into a plurality of knowledge categories according to the knowledge category of the ship process knowledge;
and dividing the ship process knowledge under the product dimensionality into a plurality of product categories according to the product types of the ship process knowledge.
Further, the performing cluster analysis on the ship resource database according to the ship process data specifically includes:
and according to the ship process data, carrying out cluster analysis on the ship process knowledge in the ship resource database through an ant colony algorithm to obtain the cluster set.
Another embodiment of the invention provides a ship process knowledge management system, which comprises a data layer, a logic layer and an application layer;
the data layer is used for providing the acquired ship process knowledge to the logic layer;
the logic layer is used for processing the ship process knowledge and providing data obtained by processing to the application layer; the processing mode comprises knowledge representation, knowledge classification, knowledge storage and instance reasoning;
the application layer is used for formulating an application rule facing a user according to the data; the application rules comprise query rules, editing rules and authority management rules.
The embodiment of the invention has the following beneficial effects:
the method comprises the steps of representing the acquired ship process knowledge by a preset knowledge representation method, classifying by a tree classification method, and establishing a ship process knowledge base (comprising a ship process instance base and a ship resource database), so that the ship process instance base can be subjected to instance reasoning according to ship process data input by a user, a first process knowledge set is output, and when the first process knowledge set cannot be output, the ship resource database is subjected to cluster analysis according to the ship process data, so that the obtained cluster set is subjected to instance reasoning, and a second process knowledge set is output. According to the ship process knowledge base and the ship process knowledge method, the obtained ship process knowledge data are sorted and classified, and the ship process knowledge base is established, so that example reasoning can be carried out on the ship process knowledge base according to the ship process data input by a user, a corresponding process knowledge set is output, and the ship process knowledge can be rapidly obtained and applied. The method can provide standard ship process knowledge for users, assists the users in controlling various processes in the ship manufacturing process, is beneficial to improving product quality, and compresses manufacturing period and labor cost, thereby enhancing market competitiveness of products.
Drawings
Fig. 1 is a schematic flow chart of a ship process knowledge management method according to a first embodiment of the present invention;
fig. 2 is a tree structure diagram of a ship process knowledge base according to a preferred embodiment of the present invention;
fig. 3 is a schematic structural diagram of a ship process knowledge management device according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a ship process knowledge management system according to a third embodiment of the present invention.
Detailed Description
The technical solutions in the present invention will be described clearly and completely with reference to the drawings in the present invention, and it should be apparent that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that, the step numbers in the text are only for convenience of explanation of the specific embodiments, and do not serve to limit the execution sequence of the steps. The method provided by the embodiment can be executed by the relevant server, and the server is taken as an example for explanation below.
Please refer to fig. 1-2.
As shown in fig. 1, a first embodiment provides a ship process knowledge management method, including steps S1 to S3:
s1, expressing the acquired ship process knowledge by adopting a preset knowledge expression method, classifying the ship process knowledge by adopting a tree classification method, and establishing a ship process knowledge base; the ship process knowledge base comprises a ship process example base and a ship resource database.
S2, performing instance reasoning on a ship process instance library according to ship process data input by a user, and outputting a first process knowledge set; the first process knowledge set is ship process knowledge matched with ship process data in a ship process example library.
S3, when the first process knowledge set cannot be output, carrying out cluster analysis on a ship resource database according to ship process data, carrying out example reasoning on an obtained cluster set, and outputting a second process knowledge set; and the second process knowledge set is ship process knowledge matched with the ship process data in the ship resource database.
It should be noted that the ship process knowledge includes process knowledge involved in the whole process of ship manufacturing, namely, various process files, expert experiences and production cases applied in the stages of ship design, steel pretreatment, steel blanking processing, component assembly, segment manufacturing, slipway folding, ship launching, dock mooring test, marine sailing test, ship delivery maintenance and the like. The process files comprise various standardized or relatively fixed files such as process design standards, specifications, process design manuals and the like; the expert experience comprises experience provided by relevant experts; the production cases comprise cases of product ships, sections, parts and the like which are designed by the finished technological procedures. The ship process data comprises process data involved in the actual manufacturing process of the ship, such as selected ship types, characteristics, steel materials, pipes, equipment, manufacturing modes and the like.
In a preferred implementation manner of this embodiment, the ship process knowledge base is established by uploading various process files, expert experiences, and production cases in batch, or by updating uploaded data to obtain ship process knowledge, and then representing the obtained ship process knowledge by using a predetermined knowledge representation method, and classifying the ship process knowledge by using a tree classification method.
The knowledge representation method is a method which can be recognized by a computer and is used for describing a data structure of knowledge, and the acquired ship process knowledge is represented by a preset knowledge representation method, so that the computer can conveniently carry out subsequent example reasoning.
And classifying the ship process knowledge by adopting a tree classification method, and establishing a ship process knowledge base. For example, the expert experience and the production case are divided into a ship process example base, and the process file is divided into a ship process resource database, so that a ship process knowledge base is established.
And carrying out instance reasoning on the ship process instance base according to the ship process data input by the user, outputting a first process knowledge set, and carrying out cluster analysis on the ship resource database according to the ship process data when the first process knowledge set cannot be output so as to carry out instance reasoning on the obtained cluster set and output a second process knowledge set.
The instance reasoning can simply and quickly search the ship process knowledge which is the same as or similar to the ship process data from the ship process instance library/clustering set, and is beneficial to improving the acquisition efficiency of the ship process knowledge.
By preferentially carrying out instance reasoning on the ship process instance library, expert experience and/or production cases matched with ship process data can be quickly acquired, more intuitive ship process knowledge is provided for users, and the users are better assisted in controlling various processes in the ship manufacturing process.
In the embodiment, the ship process knowledge base (comprising the ship process instance base and the ship resource database) is established by representing the acquired ship process knowledge by a preset knowledge representation method and classifying the acquired ship process knowledge by a tree classification method, so that the ship process instance base can be subjected to instance reasoning according to the ship process data input by a user, a first process knowledge set is output, and when the first process knowledge set cannot be output, the ship resource database is subjected to cluster analysis according to the ship process data, so that the acquired cluster set is subjected to instance reasoning, a second process knowledge set is output, namely, the acquired ship process knowledge data is sorted and classified to establish the ship process knowledge base, so that the ship process knowledge base can be subjected to instance reasoning according to the ship process data input by the user, and a corresponding process knowledge set is output, and the ship process knowledge can be rapidly acquired and applied.
The embodiment can provide standard ship process knowledge for users, assists the users to control various processes in the ship manufacturing process, is beneficial to improving product quality, and compresses manufacturing period and labor cost, thereby enhancing market competitiveness of products.
In a preferred embodiment, the predetermined knowledge representation comprises one or more of an object-oriented knowledge representation method, an instance-based knowledge representation method, and a production rule knowledge representation method.
The object-oriented knowledge representation method can be described as follows: object = knowledge + knowledge processing method + problem description framework. An example-based knowledge representation method can be described as: case = { I, O, G }, where I represents an initial state of the problem, O represents a processing scheme of the problem, and G represents a target state of the problem. The generative rule knowledge representation method can be described as: IF A THEN B, i.e. A → B, where A represents the precondition and B represents the conclusion.
In a preferred embodiment of the present implementation, the process file is represented using an example-based knowledge representation.
In a preferred embodiment, the classifying the ship process knowledge by using the tree classification method includes: dividing the ship process knowledge into a professional dimension, a flow dimension, a knowledge dimension and a product dimension according to the content attribute of the ship process knowledge; according to the professional field of the ship process knowledge, dividing the ship process knowledge under the professional dimension into a plurality of professional categories; according to the process flow of the ship process knowledge, dividing the ship process knowledge under the process dimensionality into a plurality of process categories; dividing the ship process knowledge under the knowledge dimension into a plurality of knowledge categories according to the knowledge category of the ship process knowledge; and dividing the ship process knowledge under the product dimension into a plurality of product categories according to the product types of the ship process knowledge.
It should be noted that the ship process knowledge under each category can be continuously classified according to the actual production requirements.
As shown in fig. 2, the ship process knowledge is divided into a professional dimension, a flow dimension, a knowledge dimension and a product dimension according to the content attribute of the ship process knowledge; according to the professional field of ship process knowledge, dividing the ship process knowledge under the professional dimension into a plurality of professional categories, such as ship body, electric, turbine, outfitting and the like; according to the process flow of the ship process knowledge, dividing the ship process knowledge under the process dimension into a plurality of process categories, such as ship design, steel pretreatment, steel blanking processing, component assembly, segmented manufacturing, slipway folding, ship launching, wharf mooring test, sea sailing test, ship-handing maintenance and the like; according to the knowledge category of the ship process knowledge, dividing the ship process knowledge under the knowledge dimension into a plurality of knowledge categories, such as process resources, process examples, process decisions and the like; according to the product types of the ship process knowledge, the ship process knowledge under the product dimensionality is divided into a plurality of product categories, such as the categories of civil ships, military ships, official ships and the like.
In a preferred implementation manner of this embodiment, the process resource category includes a process file; the process example category comprises expert experience and production cases; the process decision category comprises ship process knowledge which controls the process decision process by an empirical rule, a procedural algorithm and the like.
Through carrying out dimension division, classification and hierarchical management on the ship process knowledge, the ship process knowledge base is favorably established, and the user permission is favorably correspondingly set according to different ship process knowledge, so that the integrity and the safety of the ship process knowledge are ensured.
In a preferred embodiment, the performing cluster analysis on the ship resource database according to the ship process data specifically includes: and according to the ship process data, carrying out cluster analysis on the ship process knowledge in the ship resource database through an ant colony algorithm to obtain a cluster set.
When the input ship process data is complex, cluster analysis is applied, namely, the ship process knowledge in the ship resource database is subjected to cluster analysis through an optimized ant colony algorithm, so that example reasoning is performed on the obtained cluster set, and a second process knowledge set is output.
For example, firstly, a clustering analysis algorithm is adopted to classify ship process knowledge in a ship resource database, so that the maximization of intra-class similarity and the minimization of inter-class similarity are achieved.
Setting ship process knowledge in a ship resource database as X:
X＝{X i i =1,2, …, n }, where X i A p-dimensional vector is represented as,
the cluster set C obtained was:
C＝{C 1 ,C 2 ,…,C n }，
and satisfies the following conditions:
minimize the dispersion sum J:
wherein d (X) i ,Z k ) Representing the distance of the sample to the corresponding cluster center, Z k Representing the center of the k-th cluster.
Because the clustering analysis algorithm is to distribute the pheromones evenly, enough heuristic information is not left for subsequent iteration, and a large amount of invalid retrieval is easily caused in the process knowledge query. To improve the efficiency of the algorithm, the pheromones need to be initialized.
For example, take
As a distribution of the initial pheromone, i.e. < >>
Where τ (r, s) represents the pheromone concentration on the path and d (r, s) (r, s =1,2.
Because the whole algorithm is based on pheromones, the initial cluster set is determined by adopting the distribution concentration of the pheromones, so that the iteration time can be greatly reduced, and the specific steps are as follows: firstly, acquiring the final clustering number; secondly, the concentration of pheromones is reduced; thirdly, calculating the number of initial clusters; and fourthly, if the square of the final clustering number is smaller than the initial clustering number, finishing the operation, otherwise, skipping to execute the second step.
To reduce the dispersion and form a tighter cluster, the pheromone concentration formula is updated as:
wherein p represents the residual concentration after the volatilization of the information concentration,
the updated dispersion sum J is
Wherein S is k As cluster set C k The number of internal elements.
And if the dispersion sum reaches the optimal solution, ending the retrieval, outputting the optimal solution, namely the second process knowledge set, and if the dispersion sum does not reach the optimal solution, performing a new round of updating iteration.
The ship process knowledge in the ship resource database is subjected to cluster analysis through the optimized ant colony algorithm, and the obtained cluster set can be guaranteed to be subjected to instance reasoning and then a second process knowledge set can be output.
Please refer to fig. 3.
As shown in fig. 3, a second embodiment provides a ship process knowledge management apparatus, including: the ship process knowledge base establishing module 21 is used for representing the acquired ship process knowledge by adopting a preset knowledge representation method, classifying the ship process knowledge by adopting a tree classification method and establishing a ship process knowledge base; the ship process knowledge base comprises a ship process example base and a ship resource database; the first process knowledge set output module 22 is used for carrying out example reasoning on the ship process example base according to the ship process data input by the user and outputting a first process knowledge set; the first process knowledge set is ship process knowledge matched with ship process data in a ship process example library; the second process knowledge set output module 23 is configured to, when the first process knowledge set cannot be output, perform cluster analysis on the ship resource database according to the ship process data, perform instance inference on the obtained cluster set, and output a second process knowledge set; and the second process knowledge set is ship process knowledge matched with the ship process data in the ship resource database.
It should be noted that the ship process knowledge includes process knowledge involved in the whole process of ship manufacturing, namely, various process files, expert experiences and production cases applied in the stages of ship design, steel pretreatment, steel blanking processing, component assembly, segment manufacturing, slipway folding, ship launching, dock mooring test, marine sailing test, ship delivery maintenance and the like. The process files comprise various standardized or relatively fixed files such as process design standards, specifications, process design manuals and the like; the expert experience comprises experience provided by relevant experts; the production cases comprise cases of product ships, sections, parts and the like which are designed by the finished technological procedures. The ship process data comprises process data involved in the actual manufacturing process of the ship, such as selected ship types, characteristics, steel materials, pipes, equipment, manufacturing modes and the like.
In a preferred embodiment of this embodiment, the ship process knowledge base establishing module 21 obtains ship process knowledge by uploading various process files, expert experiences, and production cases in batch, or by updating uploaded data, and then represents the obtained ship process knowledge by using a predetermined knowledge representation method, and establishes the ship process knowledge base by classifying the ship process knowledge by using a tree classification method.
Knowledge representation as a computer-recognizable data structure for describing knowledge, the acquired ship process knowledge is represented by a predetermined knowledge representation, which facilitates example reasoning through the first process knowledge set output module 22 and the second process knowledge set output module 23.
And classifying the ship process knowledge by adopting a tree classification method, and establishing a ship process knowledge base. For example, the expert experience and the production case are divided into a ship process example base, and the process file is divided into a ship process resource database, so that a ship process knowledge base is established.
And when the first process knowledge set cannot be output, the second process knowledge set output module 23 performs clustering analysis on the ship resource database according to the ship process data so as to perform instance reasoning on the obtained cluster set and output a second process knowledge set.
The instance reasoning can simply and quickly search the ship process knowledge which is the same as or similar to the ship process data from the ship process instance library/clustering set, and is beneficial to improving the acquisition efficiency of the ship process knowledge.
By preferentially carrying out instance reasoning on the ship process instance library, expert experience and/or production cases matched with ship process data can be quickly acquired, more intuitive ship process knowledge is provided for users, and the users are better assisted in controlling various processes in the ship manufacturing process.
In the embodiment, the ship process knowledge base establishing module 21 is used for indicating the acquired ship process knowledge by a preset knowledge indicating method and classifying the acquired ship process knowledge by a tree classification method to realize the establishment of the ship process knowledge base (comprising the ship process instance base and the ship resource database), so that the ship process instance base can be subjected to instance reasoning by the first process knowledge base output module 22 according to the ship process data input by a user to output a first process knowledge set, and when the first process knowledge set cannot be output, the ship resource database is subjected to cluster analysis by the second process knowledge set output module 23 according to the ship process data to perform instance reasoning on the acquired cluster set and output a second process knowledge set, namely, the acquired ship process knowledge data is sorted and classified to establish the ship process knowledge base, so that the ship process knowledge base can be subjected to instance reasoning according to the ship process data input by the user to output a corresponding process knowledge set, and the quick acquisition and application of the ship knowledge process are realized.
This embodiment can provide normative boats and ships technology knowledge to the user, and supplementary user management and control each item technology in the boats and ships manufacturing process is favorable to improving product quality, compresses manufacturing cycle and cost of labor to strengthen the market competition of product.
In this embodiment, the predetermined knowledge representation includes one or more combinations of an object-oriented knowledge representation method, an instance-based knowledge representation method, and a production rule knowledge representation method.
The object-oriented knowledge representation method can be described as follows: object = knowledge + knowledge processing method + problem description framework. An example-based knowledge representation method can be described as: case = { I, O, G }, where I represents an initial state of the problem, O represents a processing scheme of the problem, and G represents a target state of the problem. The generative rule knowledge representation method can be described as: IF A THEN B, i.e. A → B, where A represents the precondition and B represents the conclusion.
In a preferred embodiment of the present implementation, the process file is represented using an example-based knowledge representation.
In this embodiment, the classification of ship process knowledge by using a tree classification method includes: dividing the ship process knowledge into a professional dimension, a flow dimension, a knowledge dimension and a product dimension according to the content attribute of the ship process knowledge; according to the professional field of the ship process knowledge, dividing the ship process knowledge under the professional dimension into a plurality of professional categories; according to the process flow of the ship process knowledge, dividing the ship process knowledge under the process dimensionality into a plurality of process categories; dividing the ship process knowledge under the knowledge dimension into a plurality of knowledge categories according to the knowledge category of the ship process knowledge; and dividing the ship process knowledge under the product dimensionality into a plurality of product categories according to the product types of the ship process knowledge.
It should be noted that the ship process knowledge under each category can be continuously classified according to the actual production requirements.
Dividing the ship process knowledge into a professional dimension, a flow dimension, a knowledge dimension and a product dimension according to the content attribute of the ship process knowledge; according to the professional field of ship process knowledge, dividing the ship process knowledge under the professional dimension into a plurality of professional categories, such as ship body, electric, turbine, outfitting and the like; according to the process flow of the ship process knowledge, dividing the ship process knowledge under the process dimensionality into a plurality of process categories, such as ship design, steel pretreatment, steel blanking processing, component assembly, segmented manufacturing, slipway folding, ship launching, wharf mooring test, marine navigation test, ship delivery guarantee and the like; according to the knowledge category of the ship process knowledge, dividing the ship process knowledge under the knowledge dimension into a plurality of knowledge categories, such as process resources, process examples, process decisions and the like; according to the product types of the ship process knowledge, the ship process knowledge under the product dimensionality is divided into a plurality of product categories, such as the categories of civil ships, military ships, official ships and the like.
In a preferred implementation manner of this embodiment, the process resource category includes a process file; the process example category comprises expert experience and production cases; the process decision category comprises ship process knowledge which controls the process decision process by an empirical rule, a procedural algorithm and the like.
Through carrying out dimension division, classification and hierarchical management on the ship process knowledge, the ship process knowledge base is favorably established, and the user permission is favorably correspondingly set according to different ship process knowledge, so that the integrity and the safety of the ship process knowledge are ensured.
In this embodiment, the performing cluster analysis on the ship resource database according to the ship process data specifically includes: and according to the ship process data, carrying out cluster analysis on the ship process knowledge in the ship resource database through an ant colony algorithm to obtain a cluster set.
When the input ship process data is complex, cluster analysis is applied, namely, the ship process knowledge in the ship resource database is subjected to cluster analysis through an optimized ant colony algorithm, so that example reasoning is performed on the obtained cluster set, and a second process knowledge set is output.
For example, firstly, a clustering analysis algorithm is adopted to classify ship process knowledge in a ship resource database, so that the maximization of intra-class similarity and the minimization of inter-class similarity are achieved.
Setting ship process knowledge in a ship resource database as X:
X＝{X i i =1,2, …, n }, where X i A p-dimensional vector is represented as,
the cluster set C obtained was:
C＝{C 1 ,C 2 ,…,C n }，
and satisfies the following conditions:
minimize the dispersion sum J:
wherein d (X) i ,Z k ) Representing the distance of the sample to the corresponding cluster center, Z k Representing the center of the kth cluster.
Because the clustering analysis algorithm is to distribute the pheromones evenly, enough heuristic information is not left for subsequent iteration, and a large amount of invalid retrieval is easily caused in the process knowledge query. To improve the efficiency of the algorithm, pheromones need to be initialized.
For example, take
As a distribution of the initial pheromone, i.e. < >>
Wherein τ (r, s) represents pheromone concentration on the pathway, d (r, s) ((r, s))r, s =1,2,.., n) represents the path length.
Because the whole algorithm is based on pheromones, the initial cluster set is determined by adopting the distribution concentration of the pheromones, so that the iteration time can be greatly reduced, and the method comprises the following specific steps: firstly, acquiring the final clustering number; secondly, the concentration of pheromone is reduced; thirdly, calculating the number of initial clusters; and fourthly, if the square of the final clustering number is smaller than the initial clustering number, ending the operation, otherwise, skipping to execute the second step.
To reduce the dispersion and form a tighter cluster, the pheromone concentration formula is updated as:
wherein p represents the residual concentration after the volatilization of the information concentration,
the updated dispersion sum J is
Wherein S is k As cluster set C k The number of internal elements.
And if the dispersion sum reaches the optimal solution, ending the retrieval, outputting the optimal solution, namely the second process knowledge set, and if the dispersion sum does not reach the optimal solution, performing a new round of updating iteration.
The ship process knowledge in the ship resource database is subjected to cluster analysis through the optimized ant colony algorithm, and the obtained cluster set can be guaranteed to be subjected to instance reasoning and then a second process knowledge set can be output.
Please refer to fig. 4.
As shown in fig. 4, a third embodiment provides a ship process knowledge management system, which includes a data layer, a logic layer and an application layer; the data layer is used for providing the acquired ship process knowledge to the logic layer;
the logic layer is used for processing ship process knowledge and providing data obtained by processing to the application layer; the processing mode comprises knowledge representation, knowledge classification, knowledge storage and instance reasoning; the application layer is used for formulating an application rule facing a user according to the processed data; the application rules comprise query rules, editing rules and authority management rules.
In summary, the present embodiment has the following beneficial effects:
the method comprises the steps of representing the acquired ship process knowledge by a preset knowledge representation method, classifying by a tree classification method, and establishing a ship process knowledge base (comprising a ship process instance base and a ship resource database), so that the ship process instance base can be subjected to instance reasoning according to ship process data input by a user, a first process knowledge set is output, and when the first process knowledge set cannot be output, the ship resource database is subjected to cluster analysis according to the ship process data, so that the obtained cluster set is subjected to instance reasoning, and a second process knowledge set is output. According to the ship process knowledge base and the ship process knowledge method, the obtained ship process knowledge data are sorted and classified, and the ship process knowledge base is established, so that example reasoning can be carried out on the ship process knowledge base according to the ship process data input by a user, a corresponding process knowledge set is output, and the ship process knowledge can be rapidly obtained and applied. The method can provide standard ship process knowledge for users, assists the users in controlling various processes in the ship manufacturing process, is beneficial to improving product quality, and compresses manufacturing period and labor cost, thereby enhancing market competitiveness of products.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
It will be understood by those skilled in the art that all or part of the processes of the above embodiments may be implemented by hardware related to instructions of a computer program, and the computer program may be stored in a computer readable storage medium, and when executed, may include the processes of the above embodiments. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Claims (7)
1. A ship process knowledge management method is characterized by comprising the following steps:
expressing the acquired ship process knowledge by adopting a preset knowledge expression method, classifying the ship process knowledge by adopting a tree classification method, and establishing a ship process knowledge base; the ship process knowledge base comprises a ship process example base and a ship resource database;
the method for classifying the ship process knowledge by adopting the tree classification method comprises the following steps:
dividing the ship process knowledge into a professional dimension, a flow dimension, a knowledge dimension and a product dimension according to the content attribute of the ship process knowledge;
according to the professional field of the ship process knowledge, dividing the ship process knowledge under the professional dimensionality into a plurality of professional categories;
according to the process flow of the ship process knowledge, dividing the ship process knowledge under the process dimension into a plurality of process categories;
dividing the ship process knowledge under the knowledge dimension into a plurality of knowledge categories according to the knowledge category of the ship process knowledge;
dividing the ship process knowledge under the product dimension into a plurality of product categories according to the product types of the ship process knowledge;
carrying out instance reasoning on the ship process instance library according to ship process data input by a user, and outputting a first process knowledge set; wherein the first process knowledge set is ship process knowledge in the ship process instance library that matches the ship process data;
when the first process knowledge set cannot be output, performing cluster analysis on the ship resource database according to the ship process data, performing instance reasoning on the obtained cluster set, and outputting a second process knowledge set; wherein the second process knowledge set is ship process knowledge in the ship resource database that matches the ship process data.
2. The ship process knowledge management method of claim 1, wherein the predetermined knowledge representation comprises one or more of a combination of an object-oriented knowledge representation method, an instance-based knowledge representation method and a production rule knowledge representation method.
3. The ship process knowledge management method according to claim 1, wherein the cluster analysis is performed on the ship resource database according to the ship process data, specifically:
and according to the ship process data, carrying out cluster analysis on the ship process knowledge in the ship resource database through an ant colony algorithm to obtain the cluster set.
4. A ship process knowledge management device, comprising:
the ship process knowledge base establishing module is used for representing the acquired ship process knowledge by adopting a preset knowledge representation method, classifying the ship process knowledge by adopting a tree classification method and establishing a ship process knowledge base; the ship process knowledge base comprises a ship process example base and a ship resource database;
the method for classifying the ship process knowledge by adopting the tree classification method comprises the following steps:
dividing the ship process knowledge into a professional dimension, a process dimension, a knowledge dimension and a product dimension according to the content attribute of the ship process knowledge;
according to the professional field of the ship process knowledge, dividing the ship process knowledge under the professional dimensionality into a plurality of professional categories;
according to the process flow of the ship process knowledge, dividing the ship process knowledge under the process dimensionality into a plurality of process categories;
dividing the ship process knowledge under the knowledge dimension into a plurality of knowledge categories according to the knowledge category of the ship process knowledge;
according to the product type of the ship process knowledge, dividing the ship process knowledge under the product dimension into a plurality of product categories;
the first process knowledge set output module is used for carrying out example reasoning on the ship process example base according to ship process data input by a user and outputting a first process knowledge set; wherein the first process knowledge set is ship process knowledge in the ship process instance library that matches the ship process data;
the second process knowledge set output module is used for carrying out cluster analysis on the ship resource database according to the ship process data and carrying out example reasoning on the obtained cluster set when the first process knowledge set cannot be output, and outputting a second process knowledge set; wherein the second process knowledge set is ship process knowledge in the ship resource database that matches the ship process data.
5. The ship process knowledge management apparatus of claim 4, wherein the predetermined knowledge representation comprises one or more of a combination of an object-oriented knowledge representation method, an instance-based knowledge representation method, and a production rule knowledge representation method.
6. The ship process knowledge management device according to claim 4, wherein the cluster analysis is performed on the ship resource database according to the ship process data, specifically:
and according to the ship process data, carrying out cluster analysis on the ship process knowledge in the ship resource database through an ant colony algorithm to obtain the cluster set.
7. A ship process knowledge management system is characterized by comprising a data layer, a logic layer and an application layer;
the data layer is used for providing the acquired ship process knowledge to the logic layer;
the logic layer is used for processing the ship process knowledge according to the ship process knowledge management method of any one of claims 1 to 3, and providing data obtained by processing to the application layer; the processing mode comprises knowledge representation, knowledge classification, knowledge storage and instance reasoning;
the application layer is used for formulating an application rule facing a user according to the data; the application rules comprise query rules, editing rules and authority management rules.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911231217.2A CN110990663B (en) | 2019-12-04 | 2019-12-04 | Ship process knowledge management method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911231217.2A CN110990663B (en) | 2019-12-04 | 2019-12-04 | Ship process knowledge management method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110990663A CN110990663A (en) | 2020-04-10 |
| CN110990663B true CN110990663B (en) | 2023-03-24 |
Family
ID=70090178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911231217.2A Active CN110990663B (en) | 2019-12-04 | 2019-12-04 | Ship process knowledge management method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110990663B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932074B (en) * | 2020-07-09 | 2023-10-27 | 江苏科技大学 | Knowledge-based intelligent ship coating process recommendation method |
| CN112036760B (en) * | 2020-09-04 | 2024-02-20 | 江南造船(集团)有限责任公司 | Ship outfitting process sequence automatic planning method, device, terminal and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030008011A (en) * | 2001-07-12 | 2003-01-24 | (주)토탈소프트뱅크 | 3D VR Port Simulator |
| DE102013016965A1 (en) * | 2013-10-09 | 2015-04-09 | Thyssenkrupp Marine Systems Gmbh | Method for integrating isolation data into a ship model |
| CN105095995A (en) * | 2015-07-28 | 2015-11-25 | 上海外高桥造船有限公司 | Precision compensation system for large-scale ship and maritime work construction |
| CN105528411A (en) * | 2015-12-03 | 2016-04-27 | 中国人民解放军海军工程大学 | Full-text retrieval device and method for interactive electronic technical manual of shipping equipment |
| CN107330585A (en) * | 2017-06-15 | 2017-11-07 | 江苏科技大学 | A kind of method that shipbuilding data integrated system and auxiliary build ship |
| CN108256021A (en) * | 2018-01-10 | 2018-07-06 | 圣泓工业设计创意有限公司 | A kind of shipbuilding accuracy data knowledge base system |
| CN108256027A (en) * | 2018-01-10 | 2018-07-06 | 圣泓工业设计创意有限公司 | A kind of ship technique manufactures micro-system |
-
2019
- 2019-12-04 CN CN201911231217.2A patent/CN110990663B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030008011A (en) * | 2001-07-12 | 2003-01-24 | (주)토탈소프트뱅크 | 3D VR Port Simulator |
| DE102013016965A1 (en) * | 2013-10-09 | 2015-04-09 | Thyssenkrupp Marine Systems Gmbh | Method for integrating isolation data into a ship model |
| CN105095995A (en) * | 2015-07-28 | 2015-11-25 | 上海外高桥造船有限公司 | Precision compensation system for large-scale ship and maritime work construction |
| CN105528411A (en) * | 2015-12-03 | 2016-04-27 | 中国人民解放军海军工程大学 | Full-text retrieval device and method for interactive electronic technical manual of shipping equipment |
| CN107330585A (en) * | 2017-06-15 | 2017-11-07 | 江苏科技大学 | A kind of method that shipbuilding data integrated system and auxiliary build ship |
| CN108256021A (en) * | 2018-01-10 | 2018-07-06 | 圣泓工业设计创意有限公司 | A kind of shipbuilding accuracy data knowledge base system |
| CN108256027A (en) * | 2018-01-10 | 2018-07-06 | 圣泓工业设计创意有限公司 | A kind of ship technique manufactures micro-system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110990663A (en) | 2020-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112101190B (en) | Remote sensing image classification method, storage medium and computing device | |
| CN108491765B (en) | Vegetable image classification and identification method and system | |
| US10719780B2 (en) | Efficient machine learning method | |
| CN109919685B (en) | Customer churn prediction method, apparatus, device and computer readable storage medium | |
| CN110858269B (en) | Fact description text prediction method and device | |
| CN110990663B (en) | Ship process knowledge management method, device and system | |
| CN107103362A (en) | The renewal of machine learning system | |
| CN112052951A (en) | Pruning neural network method, system, equipment and readable storage medium | |
| Gauci et al. | Machine learning for galaxy morphology classification | |
| CN112613536A (en) | Near infrared spectrum diesel grade identification method based on SMOTE and deep learning | |
| CN110705283A (en) | Deep learning method and system based on matching of text laws and regulations and judicial interpretations | |
| Han et al. | Speech emotion recognition based on Gaussian kernel nonlinear proximal support vector machine | |
| CN113254655A (en) | Text classification method, electronic device and computer storage medium | |
| CN111709225A (en) | Event cause and effect relationship judging method and device and computer readable storage medium | |
| CN114896392A (en) | Work order data clustering method and device, electronic equipment and storage medium | |
| CN109543571B (en) | Intelligent identification and retrieval method for special-shaped processing characteristics of complex products | |
| CN117251777A (en) | Data processing method, device, computer equipment and storage medium | |
| Sosnowski | Framework of compound object comparators | |
| Sufikarimi et al. | Speed up biological inspired object recognition, HMAX | |
| CN111291169A (en) | Template editing reply method, device, equipment and storage medium | |
| Henri et al. | A deep transfer learning model for the identification of bird songs: A case study for Mauritius | |
| CN115357720A (en) | Multi-task news classification method and device based on BERT | |
| Koromyslova et al. | Feature selection for natural language call routing based on self-adaptive genetic algorithm | |
| CN108287817A (en) | A kind of information processing method and equipment | |
| CN104200225B (en) | A kind of image classification method based on local space constraint-graph model |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230508 Address after: 510000 Changzhou street, Huangpu District, Guangzhou City, Guangdong Province Patentee after: CSSC HUANGPU WENCHONG SHIPBUILDING Co.,Ltd. Patentee after: China Shipping Industry Internet Co.,Ltd. Address before: 510700 Changzhou street, Huangpu District, Guangzhou City, Guangdong Province Patentee before: CSSC HUANGPU WENCHONG SHIPBUILDING Co.,Ltd. |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20200410 Assignee: Zhanjiang Nanhai Shipbuilding High tech Service Co.,Ltd. Assignor: CSSC HUANGPU WENCHONG SHIPBUILDING Co.,Ltd. Contract record no.: X2023980048830 Denomination of invention: A Ship Process Knowledge Management Method, Device, and System Granted publication date: 20230324 License type: Common License Record date: 20231130 |