CN114117637A - Ship segmented coating process design method based on improved DBSCAN and decision tree - Google Patents
Ship segmented coating process design method based on improved DBSCAN and decision tree Download PDFInfo
- Publication number
- CN114117637A CN114117637A CN202111425119.XA CN202111425119A CN114117637A CN 114117637 A CN114117637 A CN 114117637A CN 202111425119 A CN202111425119 A CN 202111425119A CN 114117637 A CN114117637 A CN 114117637A
- Authority
- CN
- China
- Prior art keywords
- coating
- segmented
- coating process
- evaluation
- decision tree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000576 coating method Methods 0.000 title claims abstract description 169
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003066 decision tree Methods 0.000 title claims abstract description 27
- 238000013461 design Methods 0.000 title claims abstract description 26
- 239000011248 coating agent Substances 0.000 claims abstract description 105
- 238000011156 evaluation Methods 0.000 claims abstract description 56
- 241000282461 Canis lupus Species 0.000 claims abstract description 28
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 18
- 230000011218 segmentation Effects 0.000 claims abstract description 14
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000013145 classification model Methods 0.000 claims abstract description 4
- 238000007621 cluster analysis Methods 0.000 claims abstract description 4
- 230000009467 reduction Effects 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 22
- 239000003973 paint Substances 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000008439 repair process Effects 0.000 claims description 6
- 239000007787 solid Substances 0.000 claims description 4
- 230000003746 surface roughness Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- -1 plate type Substances 0.000 claims description 3
- 238000012797 qualification Methods 0.000 claims description 3
- BTCSSZJGUNDROE-UHFFFAOYSA-N gamma-aminobutyric acid Chemical compound NCCCC(O)=O BTCSSZJGUNDROE-UHFFFAOYSA-N 0.000 claims description 2
- 238000010276 construction Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Manufacturing & Machinery (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- Algebra (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Application Of Or Painting With Fluid Materials (AREA)
Abstract
The invention discloses a ship segmented coating process design method based on improved DBSCAN and decision trees, which comprises the following steps: performing feature extraction on the features of the segmented coating part by using a Laplace fraction method to realize feature dimension reduction of the coating part; performing cluster analysis on the existing segmented coating part by using a DBSCAN algorithm improved by a wolf algorithm to form the category of the segmented coating part; constructing a training set and a testing set based on the clustering result, training a decision tree algorithm to obtain a segmentation coating part classification model, and classifying segmentation parts to be coated based on the training result of the decision tree algorithm to obtain a similar segmentation coating part set and a corresponding similar segmentation coating process set; and analyzing factors influencing the coating process evaluation, constructing a coating process fuzzy comprehensive evaluation index system, and evaluating each process in the similar segmented coating process set based on a fuzzy comprehensive evaluation method. The invention provides a powerful means for reasonably formulating the sectional coating process.
Description
Technical Field
The invention relates to the technical field of ship coating, in particular to a ship segmented coating process design method based on improved DBSCAN and decision trees.
Background
The coating is one of three large process pillars of the modern shipbuilding and runs through the shipbuilding process all the time. As a huge steel structure crop which moves in the sea, all parts of the ship body are in different corrosive environments. Therefore, the coatings used at different positions need to have different corrosion resistance requirements. The diversity of marine paints determines the differences in construction conditions, construction processes and coating equipment. Therefore, a series of process routes and process methods need to be established, and coating operation is performed at different process stages.
The sectional coating is an important link in the coating stage of the ship, and except for special parts of the special ship, each part of the ship body needs to be coated with partial or all coatings in the sectional stage. The segment coating data is huge and redundant. At present, transformation and upgrading in the intelligent manufacturing and driving ship industry are in a starting stage, but the degree of intellectualization of a domestic shipyard in a sectional coating design stage is not high, and the design is carried out by depending on the experience of process personnel during process design, so that the sectional coating process has long design time and low efficiency. The requirement of ship sectional coating design under intelligent development cannot be met.
Disclosure of Invention
The purpose of the invention is as follows: in order to overcome the defects of the background art, the invention discloses a ship segmented coating process design method based on improved DBSCAN and decision trees, which effectively realizes the classification of parts to be coated and the scientific evaluation of a segmented coating process and realizes the rapid design of the segmented coating process.
The technical scheme is as follows: the invention discloses a ship segmented coating process design method based on improved DBSCAN and decision tree, which comprises the following steps:
s1, extracting the characteristics of the segmented coating part by using a Laplace score method to realize the characteristic dimension reduction of the coating part;
s2, performing cluster analysis on the existing segmented coating parts by using a DBSCAN algorithm improved by a wolf algorithm to form the classes of the segmented coating parts;
s3, constructing a training set and a test set based on the clustering result, training a decision tree algorithm to obtain a segmentation coating part classification model, and classifying segmentation parts to be coated based on the training result of the decision tree algorithm to obtain a similar segmentation coating part set and a similar segmentation coating process set corresponding to the similar segmentation coating part set;
and S4, analyzing factors influencing the coating process evaluation, constructing a coating process fuzzy comprehensive evaluation index system, evaluating each process in the similar segmented coating process set based on a fuzzy comprehensive evaluation method, and taking the process with the highest score as a process design result.
In S1, the characteristics of the segment coating portion include material, plate type, coating area, surface roughness, coating area, rust removal grade, coating type, paint color, solid content, dry film thickness, minimum coating interval, and maximum coating interval.
Further, S1 is specifically divided into the following steps:
s11, constructing a segmented coating part nearest neighbor graph containing 12 nodes;
s12, constructing a weight matrix;
s13, generating a Laplace matrix;
s14, calculating the Laplace score of the segmented coating part;
s15, 5 features with the lowest score are selected as the result of the feature extraction of the segment coating portion.
Further, S2 includes the steps of:
s21, setting the wolf cluster number n and the maximum iteration number ItermaxTaking neighborhood parameters epsilon and MinPts of the DBSCAN as two-dimensional coordinates of the individual positions of the wolf group, randomly initializing the epsilon and the MinPts, and generating a clustering result of the segmented coating parts;
s22, dividing the wolf colony grades (alpha, beta, delta and omega) according to the fitness value, wherein the fitness calculation formula is as follows:
in the formula: avg (C) is the average distance between samples within a cluster,dist (·,) is used to calculate the distance between two samples, dcen (C)i,Cj)=dist(μi,μj) And μ represents the center point of the cluster C,
s23, updating the position of the wolf group, calculating the fitness value of the updated individual, and recording the optimal fitness value Fit of the current algebrabestIf Fitbest>FitαThen, the fitness value of the alpha wolf is updated to FitbestAnd recording the corresponding position if Fitβ<Fitbest<FitαThen will FitbestAssigning a value to the beta wolf, and updating the corresponding position to the beta wolf if Fitδ<Fitbest<FitβThen will FitbestAnd corresponding location updates to the delta wolf;
and S24, obtaining the optimal epsilon and MinPts when the maximum iteration times or the global optimization is reached, and obtaining the final clustering result of the ship segmented coating part by taking the optimal epsilon and MinPts as the parameters of the DBSCAN.
Further, in S3, the samples are divided into 2: 1, proportionally dividing the paint into a training set and a testing set, training a decision tree, and classifying the segmented coating parts to be coated according to the decision tree to obtain a similar segmented coating part set and a similar segmented coating process set corresponding to the similar segmented coating part set.
Further, S4 includes the steps of:
s41, constructing fuzzy comprehensive evaluation indexes of the segmented coating process to obtain a segmented coating process evaluation index set U, wherein U is { U ═ U }1,u2,...,umSubdividing the evaluation indexes of the segmented coating process into a main index layer and a sub-index layer;
s42, comparing every two index elements to form a judgment matrix A ═ Aij)n×nAs shown in the following formula:
in the formula: a. theij>0,Aij=1/Aji(i≠j),Aii=1(i,j=1,2,...,n)。AijRepresenting the factor i and the factor j relative to the target important value, wherein n is the number of indexes of each layer;
s43, carrying out consistency check on the judgment matrix;
s44, calculating the characteristic value of the judgment matrix to obtain the index weight;
s45, constructing an evaluation set V, and determining the value and the standard value of the evaluation set V, wherein V is { V ═ V }1,v2,...,vx};
S46, performing single index evaluation on each evaluation index in the evaluation set U to obtain a single factor evaluation set r of the ith indexi=(ri1,ri2,...,rin) Based on the single-factor evaluation set, obtaining a total scoring matrix R as shown in the following formula:
s47, carrying out fuzzy transformation on the scoring matrix R and the comprehensive weight vector to obtain a fuzzy comprehensive evaluation vector B, which is shown as the following formula:
and S48, according to the fuzzy comprehensive evaluation result of the similar sectional coating process set, taking the sectional coating process with the highest score as the process design result.
Further, in S41, the ship section coating process evaluation index, the main index layer includes: film thickness quality, coating dosage and operation time; the sub-index layer includes: film thickness qualification rate, film thickness uniformity, sectional coating paint usage, repair coating paint usage, sectional coating operation time, coating auxiliary operation time, repair coating operation time.
Has the advantages that: compared with the prior art, the invention has the advantages that:
the method adopts the Laplace fraction method to extract the characteristics of the segmented coating part, thereby reducing the dimensionality of the characteristics, avoiding the occurrence of dimension disaster and improving the operation efficiency of a classification algorithm; the DBSCAN algorithm is improved, self-adaptive determination of clustering parameters of the DBSCAN algorithm is achieved, and clustering quality is improved; when the sectional coating parts are classified, the differences among the sectional coating parts can be effectively distinguished, and the accurate classification of the sectional coating parts to be coated is realized; the construction condition of the sectional coating process is fully considered, each process in the similar sectional coating process set is evaluated based on a fuzzy comprehensive evaluation method, and objective comprehensive evaluation of the sectional coating process is realized;
the invention provides a powerful means for reasonably formulating the sectional coating process.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a diagram of a fuzzy comprehensive evaluation index system of the ship section coating process.
Detailed Description
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
The ship segmented coating process design method based on the improved DBSCAN and the decision tree as shown in FIG. 1 comprises the following steps:
s1, extracting the characteristics of the segmented coating part by using a Laplace score method to realize the characteristic dimension reduction of the coating part;
wherein in step S1, the characteristics of the segment coating portion include material, plate type, coating area, surface roughness, coating area, rust removal grade, coating type, paint color, solid content, dry film thickness, minimum coating interval, and maximum coating interval. As shown in table 1 below.
TABLE 1 characteristics of the coating sites by stages
In this example, step S1 is specifically divided into the following steps:
s11, constructing a segmented coating part nearest neighbor graph containing 12 nodes;
s12, constructing a weight matrix;
s13, generating a Laplace matrix;
s14, calculating the Laplace score of the segmented coating part;
s15, 5 features with the lowest score are selected as the result of the feature extraction of the segment coating portion.
In this example, 1200 pieces of segment coating history data in 2010 to 2020 of a certain shipyard are selected, feature extraction is performed according to step S1, and laplacian scores thereof are ranked as follows.
LS(F10)<LS(F5)<LS(F9)<LS(F3)<LS(F4)<LS(F6)<LS(F7)<LS(F12)<LS(F11)<LS(F2)<LS(F1)<LS(F8)
In this example, the characteristics of the segment coating portion after feature extraction are as follows: dry film thickness, coating area, solid content, coating area, surface roughness.
S2, performing cluster analysis on the existing segmented coating parts by using a DBSCAN algorithm improved by a wolf algorithm to form the classes of the segmented coating parts;
wherein, step S2 is specifically divided into the following steps:
s21, setting the wolf cluster number n and the maximum iteration number Itermax. Taking neighborhood parameters epsilon and MinPts of the DBSCAN as two-dimensional coordinates of the individual positions of the wolf group, randomly initializing epsilon and MinPts, and generating a clustering result of the segmented coating parts;
s22, dividing the wolf pack classes (α, β, δ, and ω) according to the fitness value. The fitness calculation formula is as follows:
in the formula: avg (C) is the average distance between samples within a cluster,dist (·,) is used to calculate the distance between two samples, dcen (C)i,Cj)=dist(μi,μj) And μ represents the center point of the cluster C,
s23, updating the position of the wolf group, calculating the fitness value of the updated individual, and recording the optimal fitness value Fit of the current algebrabest. If Fitbest>FitαThen, the fitness value of the alpha wolf is updated to FitbestAnd the corresponding position is recorded. If Fitβ<Fitbest<FitαThen will FitbestThe value is assigned to the beta wolf, and the corresponding position is updated to the beta wolf. If Fitδ<Fitbest<FitβThen will FitbestAnd corresponding location updates to the delta wolf;
and S24, obtaining the optimal epsilon and MinPts when the maximum iteration times or the global optimization is reached, and obtaining the clustering result of the ship segmented coating part by taking the optimal epsilon and MinPts as the parameters of the DBSCAN.
And S3, constructing a training set and a testing set based on the clustering result, and training the decision tree algorithm to obtain a segmented coating part classification model. Classifying the to-be-coated segmented parts based on the training result of the decision tree algorithm to obtain a similar segmented coating part set and a similar segmented coating process set corresponding to the similar segmented coating part set.
In step S3, the samples are divided into 2: 1, dividing the ratio into a training set and a testing set to train the decision tree. I.e., 800 training sets and 400 testing sets.
In this example, the water-line outer plate is used as the object to be coated, and the classification results are shown in table 2 below.
TABLE 2 similar sectional coating position set of the upper and lower outer plates of waterline
Further, a similar sectional coating process set of the part to be coated was obtained, and the results are shown in table 3.
TABLE 3 similar segmented coating process set (part) for waterline upper and outer plates
And S4, analyzing factors influencing the coating process evaluation, constructing a coating process fuzzy comprehensive evaluation index system, evaluating each process in the similar segmented coating process set based on a fuzzy comprehensive evaluation method, and taking the process with the highest score as a process design result.
Wherein, step S4 is specifically divided into the following steps:
s41, constructing fuzzy comprehensive evaluation indexes of the segmented coating process to obtain a segmented coating process evaluation index set U, wherein U is { U ═ U }1,u2,...,umAnd subdividing the evaluation indexes of the segmented coating process into a main index layer and a sub-index layer.
As shown in fig. 2, the main index layers of the evaluation indexes of the ship sectional coating process in the present example include: the film thickness quality, the coating dosage and the operation time, and the sub-index layer comprises: film thickness qualification rate, film thickness uniformity, sectional coating paint usage, repair coating paint usage, sectional coating operation time, coating auxiliary operation time, repair coating operation time.
S42, comparing every two index elements to form a judgment matrix A ═ Aij)n×nThe following formula is shown below.
In the formula: a. theij>0,Aij=1/Aji(i≠j),Aii=1(i,j=1,2,...,n)。AijAnd n is the number of indexes of each layer.
S43, carrying out consistency check on the judgment matrix;
s44, calculating the characteristic value of the judgment matrix to obtain the index weight;
the main index layer weight calculation results in this example are shown in table 4.
TABLE 4 Primary index layer weight calculation results
The results of the film thickness mass weight calculation in this example are shown in Table 5.
TABLE 5 film thickness quality weight calculation results
The results of the coating weight calculations in this example are shown in Table 6.
TABLE 6 coating weight calculation results
The results of the calculation of the operation time weight in this example are shown in table 7.
TABLE 7 Job time weight calculation results
S45, constructing an evaluation set V, and determining the value and the standard value of the evaluation set V through a ship field expert, wherein V is { V ═ V { (V) }1,v2,...,vx}。
S46, performing single index evaluation on each evaluation index in the evaluation set U to obtain a single factor evaluation set r of the ith indexi=(ri1,ri2,...,rin). Based on the single-factor evaluation set, a total score matrix R is obtained as shown in the following formula.
The determination of the total score matrix in this example is specifically shown below.
And S47, carrying out fuzzy transformation on the scoring matrix R and the comprehensive weight vector to obtain a fuzzy comprehensive evaluation vector B as shown in the following formula.
The fuzzy comprehensive evaluation result of the sectional coating process in the example is shown in the following formula.
B=[0.7976 0.8233 0.7937 0.7997 0.8737 0.8465 ...]
And S48, according to the fuzzy comprehensive evaluation result of the similar segmented coating process set, taking the process with the highest score as the result of the process design of the on-line outer plate, wherein the specific process parameters in the example are shown in Table 8.
TABLE 8 coating process parameters of the upper and lower plates of the waterline
Claims (7)
1. A ship segmented coating process design method based on improved DBSCAN and decision tree is characterized in that: the method comprises the following steps:
s1, extracting the characteristics of the segmented coating part by using a Laplace score method to realize the characteristic dimension reduction of the coating part;
s2, performing cluster analysis on the existing segmented coating parts by using a DBSCAN algorithm improved by a wolf algorithm to form the classes of the segmented coating parts;
s3, constructing a training set and a test set based on the clustering result, training a decision tree algorithm to obtain a segmentation coating part classification model, and classifying segmentation parts to be coated based on the training result of the decision tree algorithm to obtain a similar segmentation coating part set and a similar segmentation coating process set corresponding to the similar segmentation coating part set;
and S4, analyzing factors influencing the coating process evaluation, constructing a coating process fuzzy comprehensive evaluation index system, evaluating each process in the similar segmented coating process set based on a fuzzy comprehensive evaluation method, and taking the process with the highest score as a process design result.
2. The design method of ship segmented coating process based on improved DBSCAN and decision tree as claimed in claim 1, wherein: in S1, the characteristics of the segment coating portion include material, plate type, coating area, surface roughness, coating area, rust removal grade, coating type, paint color, solid content, dry film thickness, minimum coating interval, and maximum coating interval.
3. The design method of the ship segmented coating process based on the improved DBSCAN and the decision tree as claimed in claim 1, wherein S1 is specifically divided into the following steps:
s11, constructing a segmented coating part nearest neighbor graph containing 12 nodes;
s12, constructing a weight matrix;
s13, generating a Laplace matrix;
s14, calculating the Laplace score of the segmented coating part;
s15, 5 features with the lowest score are selected as the result of the feature extraction of the segment coating portion.
4. The design method of the ship segmented coating process based on the improved DBSCAN and the decision tree as claimed in claim 1, wherein S2 comprises the following steps:
s21, setting the wolf cluster number n and the maximum iteration number ItermaxTaking neighborhood parameters epsilon and MinPts of the DBSCAN as two-dimensional coordinates of the individual positions of the wolf group, randomly initializing the epsilon and the MinPts, and generating a clustering result of the segmented coating parts;
s22, dividing the wolf colony grades (alpha, beta, delta and omega) according to the fitness value, wherein the fitness calculation formula is as follows:
in the formula: avg (C) is the average distance between samples within a cluster,dist (·,) is used to calculate the distance between two samples, dcen (C)i,Cj)=dist(μi,μj) And μ represents the center point of the cluster C,
s23, updating the position of the wolf group, calculating the fitness value of the updated individual, and recording the current fitness valueOptimal fitness value Fit of algebrabestIf Fitbest>FitαThen, the fitness value of the alpha wolf is updated to FitbestAnd recording the corresponding position if Fitβ<Fitbest<FitαThen will FitbestAssigning a value to the beta wolf, and updating the corresponding position to the beta wolf if Fitδ<Fitbest<FitβThen will FitbestAnd corresponding location updates to the delta wolf;
and S24, obtaining the optimal epsilon and MinPts when the maximum iteration times or the global optimization is reached, and obtaining the final clustering result of the ship segmented coating part by taking the optimal epsilon and MinPts as the parameters of the DBSCAN.
5. The design method of ship segmented coating process based on improved DBSCAN and decision tree as claimed in claim 1, wherein: in S3, the samples are divided into 2: 1, proportionally dividing the paint into a training set and a testing set, training a decision tree, and classifying the segmented coating parts to be coated according to the decision tree to obtain a similar segmented coating part set and a similar segmented coating process set corresponding to the similar segmented coating part set.
6. The design method of the ship segmented coating process based on the improved DBSCAN and the decision tree as claimed in claim 1, wherein S4 comprises the following steps:
s41, constructing fuzzy comprehensive evaluation indexes of the segmented coating process to obtain a segmented coating process evaluation index set U, wherein U is { U ═ U }1,u2,...,umSubdividing the evaluation indexes of the segmented coating process into a main index layer and a sub-index layer;
s42, comparing every two index elements to form a judgment matrix A ═ Aij)n×nAs shown in the following formula:
in the formula: a. theij>0,Aij=1/Aji(i≠j),Aii=1(i,j=1,2,...,n)。AijRepresenting the factor i and the factor j relative to the target important value, wherein n is the number of indexes of each layer;
s43, carrying out consistency check on the judgment matrix;
s44, calculating the characteristic value of the judgment matrix to obtain the index weight;
s45, constructing an evaluation set V, and determining the value and the standard value of the evaluation set V, wherein V is { V ═ V }1,v2,...,vx};
S46, performing single index evaluation on each evaluation index in the evaluation set U to obtain a single factor evaluation set r of the ith indexi=(ri1,ri2,...,rin) Based on the single-factor evaluation set, obtaining a total scoring matrix R as shown in the following formula:
s47, carrying out fuzzy transformation on the scoring matrix R and the comprehensive weight vector to obtain a fuzzy comprehensive evaluation vector B, which is shown as the following formula:
and S48, according to the fuzzy comprehensive evaluation result of the similar sectional coating process set, taking the sectional coating process with the highest score as the process design result.
7. The design method of ship segmented coating process based on improved DBSCAN and decision tree as claimed in claim 6, wherein: in S41, the ship section coating process evaluation index, the main index layer includes: film thickness quality, coating dosage and operation time; the sub-index layer includes: film thickness qualification rate, film thickness uniformity, sectional coating paint usage, repair coating paint usage, sectional coating operation time, coating auxiliary operation time, repair coating operation time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111425119.XA CN114117637A (en) | 2021-11-26 | 2021-11-26 | Ship segmented coating process design method based on improved DBSCAN and decision tree |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111425119.XA CN114117637A (en) | 2021-11-26 | 2021-11-26 | Ship segmented coating process design method based on improved DBSCAN and decision tree |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114117637A true CN114117637A (en) | 2022-03-01 |
Family
ID=80370642
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111425119.XA Pending CN114117637A (en) | 2021-11-26 | 2021-11-26 | Ship segmented coating process design method based on improved DBSCAN and decision tree |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114117637A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114548610A (en) * | 2022-04-27 | 2022-05-27 | 季华实验室 | Automatic arrangement method and device for engine cover outer plate stamping process |
-
2021
- 2021-11-26 CN CN202111425119.XA patent/CN114117637A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114548610A (en) * | 2022-04-27 | 2022-05-27 | 季华实验室 | Automatic arrangement method and device for engine cover outer plate stamping process |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104375478B (en) | A kind of method and device of Rolling production process product quality on-line prediction and optimization | |
CN106201897B (en) | Software defect based on principal component distribution function predicts unbalanced data processing method | |
CN111160750A (en) | Distribution network analysis and investment decision method based on association rule mining | |
CN110321658B (en) | Method and device for predicting plate performance | |
CN114117637A (en) | Ship segmented coating process design method based on improved DBSCAN and decision tree | |
CN110909802A (en) | Improved PSO (particle swarm optimization) based fault classification method for optimizing PNN (portable network) smoothing factor | |
CN107220498B (en) | Mechanical material evaluation method and system | |
JP2008077403A (en) | Evaluation device, method and program | |
CN112991271A (en) | Aluminum profile surface defect visual detection method based on improved yolov3 | |
CN111651929A (en) | Multi-objective optimization method based on fusion of Dynaform and intelligent algorithm | |
CN112101649B (en) | Processing parameter optimization method based on fuzzy entropy weight comprehensive evaluation method-gray correlation analysis method and surface quality evaluation system | |
CN102663422A (en) | Floor layer classification method based on color characteristic | |
CN110378433A (en) | The classifying identification method of bridge cable surface defect based on PSO-SVM | |
CN110458111B (en) | LightGBM-based rapid extraction method for vehicle-mounted laser point cloud power line | |
CN116882774A (en) | AIS-based fishing boat navigation and operation influence assessment method | |
CN111584010A (en) | Key protein identification method based on capsule neural network and ensemble learning | |
CN116341276A (en) | Scoring method for coating process | |
CN109767430B (en) | Quality detection method and quality detection system for valuable bills | |
CN114118292B (en) | Fault classification method based on linear discriminant neighborhood preserving embedding | |
CN114936661A (en) | Improved A-algorithm based on analytic hierarchy process optimization and used for planning paths of ship cabin personnel in fire environment | |
CN115374858A (en) | Intelligent diagnosis method for process industrial production quality based on hybrid integration model | |
CN113448840A (en) | Software quality evaluation method based on predicted defect rate and fuzzy comprehensive evaluation model | |
Feng et al. | A method for surface detect classification of hot rolled strip steel based on Xception | |
CN113376015A (en) | Method for rapidly characterizing and analyzing microstructure evolution of nickel-based single crystal superalloy | |
CN113837293A (en) | mRNA subcellular localization model training method, mRNA subcellular localization model localization method and readable storage medium |
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 |