CN110009268A - One kind being used for body section logistics link analysis method - Google Patents
One kind being used for body section logistics link analysis method Download PDFInfo
- Publication number
- CN110009268A CN110009268A CN201811286666.2A CN201811286666A CN110009268A CN 110009268 A CN110009268 A CN 110009268A CN 201811286666 A CN201811286666 A CN 201811286666A CN 110009268 A CN110009268 A CN 110009268A
- Authority
- CN
- China
- Prior art keywords
- data
- logistics
- body section
- segmentation
- similarity
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 36
- 230000011218 segmentation Effects 0.000 claims abstract description 105
- 238000005498 polishing Methods 0.000 claims abstract description 18
- 241001269238 Data Species 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 238000013501 data transformation Methods 0.000 claims abstract description 4
- 230000010354 integration Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 18
- 238000006467 substitution reaction Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 230000001939 inductive effect Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 abstract 1
- 239000011248 coating agent Substances 0.000 description 23
- 238000000576 coating method Methods 0.000 description 23
- 239000004576 sand Substances 0.000 description 14
- 238000005406 washing Methods 0.000 description 13
- 238000007592 spray painting technique Methods 0.000 description 12
- 230000007306 turnover Effects 0.000 description 8
- 229910052796 boron Inorganic materials 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 206010017577 Gait disturbance Diseases 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000005422 blasting Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 229910052717 sulfur Inorganic materials 0.000 description 1
Classifications
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses one kind to be used for body section logistics link analysis method, first according to shipyard body section logistical histories data, carry out data entity identification and redundant attributes identification, check logistics data quality, all segmentation logistics datas are pre-processed, polishing is carried out to the exception item of historical data, missing item, redundancy, differences using preprocessing means such as data cleansing, data integration, data transformation, to obtain sample data；Logistics route digitized description is carried out according to sample data, the similarity between logistics route is calculated using similarity calculation method, clustering finally is carried out to all logistics routes, the classification cluster of logistics link is obtained, instructs putting and carrying for shipyard body section logistics.Be conducive to instruct body section putting in stockyard, reduce invalid carrying number, reduce landed cost.
Description
Technical field
The present invention relates to shipbuilding industry body section logistics big data analysis fields, espespecially a kind of to be used for body section logistics
Link analysis method.
Background technique
According to shipbuilding process division of hull principle, the body section that large ship construction is related to is large number of,
Up to 200 to 300, the working space being related to includes that interior outfield manufacture, advance fitting-out, coating and total group job etc. are multiple, together
When in view of the anxiety of working space and adjustment of actual job arrangement etc., a large amount of segmentations need to carry out between operation in stockyard
Turnover, scheduling flat car carry out fragmented transport demand and real work amount it is very huge.Although the Utopian modern times make
Ship model formula is controlled by reasonable and strict plan, and orderly, balanced, continuous and efficient general assembly shipbuilding production is carried out, but
It is that large ship product construction period is long, process control variable is more, inevitably will lead to the unordered and segmentation fortune without planning of flat car
Defeated problem, brought problem of environmental pollution, inefficiency problem, benefit reduction problem are also more to highlight, and become enterprise
Therefore one of main stumbling-block of cost efficiency is carried existing invalid number in face of body section during shipbuilding, is needed
This is solved the problems, such as using a kind of logistics link analysis method, be placement and carrying of the shipyard body section in heap field areas
Path provides decision support.
Summary of the invention
The shortcomings that the technical problem to be solved by the present invention is to overcome the prior arts provides a kind of for body section logistics chain
Road analysis method realizes that carrying out planning to body section stowed location and transport path provides guidance, to solve the above problems.
In order to solve the above-mentioned technical problems, the present invention provides the following technical solutions:
The present invention provides a kind of pre- for body section logistics link analysis method, including body section logistical histories data
It handles S1 and body section logistics link analyzes S2；
S1: according to shipyard body section logistical histories data, data entity identification and redundant attributes identification is carried out, checks object
Flow data quality pre-processes all segmentation logistics datas, utilizes the pre- places such as data cleansing, data integration, data transformation
Reason means carry out polishing to the exception item of historical data, missing item, redundancy, differences, to obtain sample data；
S2: the sample data obtained according to body section logistical histories data prediction carries out logistics route digitlization and retouches
It states, the similarity between logistics route is calculated using similarity calculation method, finally all logistics routes are gathered
Alanysis obtains the classification cluster of logistics link, instructs putting and carrying for shipyard body section logistics.
As a preferred solution of the present invention, in step S1, to data prediction, that steps are as follows is described:
A1: first according to history data set and shipbuilding feature, target ship screening principle is established, determines object ship
Only；
A2: the problem of target ship determined in step A1 is analyzed, target ship segment data is analyzed,
The phenomenon that described problem includes but is not limited to shortage of data, data exception, data redundancy, data redundancy is including but not limited to adjacent
The destination or starting point of two datas record are inconsistent, lack the transportation route data of certain process, data are carried in same segmentation
There is large jump in date；
A3: determining the pretreatment mode of exception segment data, successively as described below:
A31: missing values pretreatment replaces missing values (to be lacked using Decision Tree Inductive method using most likely value
It is worth reasoning), so that the relationship between missing values and other numerical value is kept maximum；
A32: exceptional value pretreatment, deleted using data, in conjunction with overall model comprehensive analysis substitution, be considered as missing values and fill up
Etc. modes pre-processed, minimize the departure degree after outlier processing between other numerical value；
A33: data redundancy pretreatment is divided using relation on attributes of the correlation analysis to segmentation logistics data
Analysis.
A4: it completes to obtain in logistics data sample set storing data warehouse via pretreatment, be analyzed for data.
As a preferred solution of the present invention, when there is data redundancy in target ship segment data, work as number
It is larger (generally take strong correlation value range be [- 1, -0.6] or [0.6,1]) according to the correlation between two attributes, then from this two
An attribute is rejected in a attribute, using 2 big primitive attributes of remaining attribute substitution correlation, reduces data redundancy.
As a preferred solution of the present invention, in step S2 to the following institute of body section logistics link analytical procedure
It states:
B1: the graphical description of body section logistics route:
The image conversion description of any segmentation transport path can include node and two, side element, section by Fig. 2 representation
Point indicates the designated position (total number of positions 7) passed through in transport path, and side then indicates the route between two designated positions.For
Any two are segmented u and v (and u ≠ v) in body section logistics data sample set, and segmentation u and the logistics route for being segmented v are expressed as
The corresponding node of Gu and Gv, u and v, side in two graph structures be in same corresponding position, if the graph structure interior joint of Gu and Gv or
Number of edges mesh differs, then needs to add dummy node and fictitious line operation in short position, Gu and Gv can respectively indicate Gu=(Fu,
Bu), Gv=(Fv, Bv), interior joint collection Fu=<Fu (1), Fu (2) ..., Fu (7)>, Fv=<Fv (1), Fv (2) ..., Fv
(7) >, if segmentation u or v passes through the position i (i=1,2 ..., n), Fu (i)=1 or Fv (i)=1, otherwise Fu (i)=0 or Fv (i)
=0；Side collection Bu=<Bu (1), Bu (2) ..., Bu (21)>(note: number of edges is the maximum value of number of nodes permutation and combination.That is: Bv=<Bv (1), Bv (2) ..., Bv (21)>, if segmentation u logistics by the path j (j=1,2 ...,
21), Bu (j)=1, otherwise Bu (j)=0；
B2: similitude present in body section logistics route is analyzed:
Compare GuWith GvGraph structure, figure interior joint and side are updated operation (see Fig. 2), formed the consistent figure of scale
Structure calculates the similarity of two graph structures using Similarity Algorithm, indicates are as follows:
In formula: α (0≤α≤1) characterizes influence coefficient of the graph structure interior joint to similarity analysis, i.e. body section is carried
Position characterizes influence system of the side to similarity analysis in graph structure to the percentage contribution of transport path similitude, β (0≤β≤1)
Number, the i.e. percentage contribution of the transport path similitude of body section transportation route, alpha+beta=1；N=n1+n2, n indicate that node is total
Number, 0≤n1≤n indicate the number of nodes of ∪ Fv (i)=0 Fu (i)=0, the section of ∩ Fv (i) ≠ 0 0≤n2≤n, Fu (i) ≠ 0
Point quantity.Edis { Fu, Fv } indicates node updates operating distance, and max { Fu, Fv } is the maximum value of Edis { Fu, Fv }, Edis
{ Bu, Bv } indicates node updates operating distance, and max { Bu, Bv } is the maximum value of Edis { Bu, Bv }.
B3: to clustering in body section logistics link:
B31: t initial cluster center is selected from the data of body section logistics route sample；
B32: similarity of each sample data to t cluster centre, Jiang Gelu are calculated separately according to minimum distance criterion
Diameter is assigned among nearest classification；
B33: after the completion of all path allocations, t cluster centre is recalculated；
B34: the cluster centre being calculated by step B33 and the initial cluster center chosen in step B31 are compared
Compared with if cluster centre changes, resumes step B32 is counted again；If cluster centre does not change, stop
Calculate and export cluster as a result, obtaining body section logistics link.
The beneficial effects obtained by the present invention are as follows being: the present invention first pre-processes body section logistical histories data,
It carries out the removing of the deficiency of data of body section logistics, the operation such as converts, fills a vacancy, guarantee the analysis of body section logistics data
Accuracy；Then body section logistics data mining analysis is carried out, similitude point is carried out to the boat segmental transportation route of acquisition
Analysis obtains boat segmental logistics link classification, analyzes the distribution trend of boat segmental logistics link.Be conducive to instruct body section
In putting for stockyard, invalid carrying number is reduced, landed cost is reduced.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example to be used to explain the present invention together, not be construed as limiting the invention.
In the accompanying drawings:
Fig. 1 is overall flow block diagram of the invention；
Fig. 2 is body section logistics route Principle of Similarity Analysis of the present invention；
Fig. 3 is body section logistics link clustering flow chart of the present invention；
Fig. 4 is body section logistics link clustering analysis diagram of the present invention；
Fig. 5 is body section logistics chain path link figure of the present invention；
Fig. 6 is body section logistics link analysis result of the present invention；
Fig. 7 is body section logistics link implementation process of the present invention；
Fig. 8 is the path link figure of segmentation BLOCK102 in table 1 of the present invention.
Specific embodiment
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred reality described herein
Apply example only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
Embodiment: as shown in figures 1-8, the present invention provides one kind for body section logistics link analysis method, such as Fig. 1 institute
Show, this method includes two steps: body section logistical histories data prediction S1 and body section logistics link analyze S2.
According to the body section logistical histories data of shipyard ship type, Entity recognition and redundant attributes identification are carried out, is checked
The quality of data pre-processes all segmentation logistics datas, utilizes the pretreatments such as data cleansing, data integration, data transformation
Means carry out polishing to the exception item of historical data, missing item, redundancy, differences；According to the obtained sample data of pretreatment,
Logistics route digitized description is carried out, the similarity between logistics route is calculated using similarity calculation method, finally
To all logistics routes carry out clustering, obtain the classification cluster of logistics link, instruct shipyard body section logistics put and
It carries.
S1 body section logistical histories data prediction is right in body section logistics link analytic process for meeting
The demand of used sample data reliability.
Body section logistical histories data prediction detailed process are as follows:
According to data set and shipbuilding feature, target ship screening principle is established, determines target ship；Analyze object ship
Segment data the problems such as there are shortage of data, data exception, data redundancies, such as the destination of adjacent two data record or rises
Begin transportation route data that are inconsistent, lacking certain process, same segmentation carry Data Date there is large jump etc..It determines and divides
Segment data pretreatment mode: 1, missing values pre-process, using most likely value replace missing values (using Decision Tree Inductive method into
The reasoning of row missing values), so that the relationship between missing values and other numerical value is kept maximum；2, exceptional value pre-processes, and is deleted using data
Remove, in conjunction with overall model comprehensive analysis substitution, be considered as missing values and the modes such as fill up and pre-processed, make after outlier processing with its
Departure degree between his numerical value minimizes；3, data redundancy pre-processes, using correlation analysis to segmentation logistics number
According to relation on attributes analyzed, if segmentation between Segment type, segmentation the data attributes such as position and flat car information between
Correlation it is larger (generally take strong correlation value range be [- 1, -0.6] or [0.6,1]), then reject one from the two attributes
A attribute reduces data redundancy using 2 big primitive attributes of remaining attribute substitution correlation.It is completed via pretreatment
Into logistics data sample set storing data warehouse, analyzed for data.
The analysis of S2 body section logistics link is to carry out phase for completing body section logistics data sample set to pretreatment
Like property clustering, body section logistics link classification cluster is obtained.
Body section logistics link analyzes detailed process are as follows:
B1: the graphical description of body section logistics route:
The image conversion description of any segmentation transport path can include node and two, side element, section by Fig. 2 representation
Point indicates the designated position (in the present embodiment by taking the total number of positions is 7 as an example) passed through in transport path, and side then indicates two fingers
Position the route between setting.For in body section logistics data sample set any two be segmented u and v (and u ≠ v), segmentation u and
The logistics route of segmentation v is expressed as Gu and Gv, and u and the corresponding node of v, side are in same corresponding position in two graph structures, if
The graph structure interior joint or number of edges mesh of Gu and Gv differs, then needs to add dummy node and fictitious line operation, Gu in short position
It can be respectively indicated Gu=(Fu, Bu) with Gv, Gv=(Fv, Bv), interior joint collection Fu=<Fu (1), Fu (2) ..., Fu (7)>, Fv
=<Fv (1), Fv (2) ..., Fv (7)>, if segmentation u or v passes through the position i (i=1,2 ..., n), Fu (i)=1 or Fv (i)=1,
Otherwise Fu (i)=0 or Fv (i)=0；Side collection Bu=<Bu (1), Bu (2) ..., Bu (21)>(note: number of edges is number of nodes arrangement group
The maximum value of conjunction.That is:Bv=<Bv (1), Bv (2) ..., Bv (21)>, if the road j is passed through in segmentation u logistics
Diameter (j=1,2 ..., 21), Bu (j)=1, otherwise Bu (j)=0；
It is analyzed by above content and in conjunction with table 1
Table 1:
From the above: the table is that initial data passes through step S1 acquisition preprocessed data；Each row of data table in the table
The path for showing a segmentation, that is, alphabetical u, v, which is mentioned above, indicates segmentation, what Gu, Gv expression were made of (A, S, O, B, P, R, E)
Segmented paths are assembled into A (Assembly) in table, and advance fitting-out is O (PreOutfitting), and sand washing polishing is B
(Blasting), it paints for P (Painting), pre- total group is E (PreErection), and stockyard is S (Stockyard), and coating is wide
Field is that R S-S indicates that stockyard internal shift, O-O indicate that advance fitting-out internal shift, R-R indicate coating square internal shift, and E-E expression is pre- total
Group internal shift.
In addition first row indicates segmentation and fragment sequence number in table, each to be segmented corresponding segmented paths, by algorithm above
" if segmentation u or v passes through the position i (i=1,2 ..., n), Fu (i)=1 or Fv (i)=1, otherwise Fu (i)=0 or Fv (i)=0 ",
Therefore the path that Block102 passes through are as follows: S-B-P-R-E；Specific path link figure is as shown in Figure 8；
(2) body section logistics route similarity analysis:
The graph structure for comparing Gu and Gv, is updated operation (see Fig. 2) figure interior joint and side, forms the consistent figure of scale
Structure calculates the similarity of two graph structures using Similarity Algorithm, indicates are as follows:
In formula: α (0≤α≤1) characterizes influence coefficient of the graph structure interior joint to similarity analysis, i.e. body section is carried
Position characterizes influence system of the side to similarity analysis in graph structure to the percentage contribution of transport path similitude, β (0≤β≤1)
Number, the i.e. percentage contribution of the transport path similitude of body section transportation route, alpha+beta=1；N=n1+n2, n expression node total number,
0≤n1≤n indicates Fu(i)=0 the number of nodes of ∪ Fv (i)=0,0≤n2≤ n, Fu(i)≠0∩Fv(i) ≠ 0 number of nodes
Amount.Edis{Fu,FvIndicate node updates operating distance, max { Fu, Fv } and it is Edis { Fu, FvMaximum value, Edis { Bu,Bv}
Indicate node updates operating distance, max { Bu,BvIt is Edis { Bu,BvMaximum value.
(3) body section logistics link clustering detailed process is as shown in Figure 3:
1. selecting t initial cluster center from body section logistics route sample data；2. according to minimum distance criterion
Calculate separately each sample data to t cluster centre cluster, by each path allocation among nearest classification；3. being
After the completion of all path allocations, the center of t cluster is recalculated；4. being and preceding t cluster centre being once calculated
Compare, if cluster centre changes, switchs to second step；5. be that cluster centre does not change, stopping calculating is simultaneously defeated
Cluster result out obtains body section logistics link；
Pass through the reason of body section logistics route similarity analysis and body section logistics link clustering detailed process
By support, there are up to a hundred segmentations in our actual cases, can pass through the public affairs in segmentation logistics route similarity analysis
Formula are as follows:It calculates between any two segmentation
Similarity obtains similarity distance matrix, according to similarity distance matrix, is ranked up to each segmentation position, obtains clustering tree most bottom
One layer, line is carried out according to the size of similar distance, obtains each layer structure, clustering tree generating principle is shown in Fig. 4, and concrete analysis is such as
Shown in lower: since the bottom:
(1) first layer, since any two object all has similarity distance, we sort to similarity distance, between B, C most
Small, so selecting B, C for first layer, other values are put aside.
(2) there was only the similarity distance between D, E to the value for being greater than B, C similarity distance, therefore connecting D, E is the second layer.
(3) ibid, determine that A, F are third layer according to similarity distance.
(4) also according to similarity distance calculated result: B and A, B and F, C and A, C are identical as F similarity distance, obtain the 4th
Layer, in addition, the similar value of G and D, G and E are identical as the 4th layer of value, therefore obtains the 4th layer of two clusters.
(5) the 5th layer is finally similarly obtained.
Cluster the division of classification: divide value takes according to similarity distance, in the range of (0,1), if value is small, i.e., close to 0
When, indicate that similarity distance is small, their similarity degree is high, otherwise takes 1, and similarity degree is low.If taking small, classification is too many, processing
Difficulty is big, does not embody the meaning of classification, if taking greatly, classification accuracy is low, is likely to be obtained result mistake, usually takes median,
The division that 0.5 carry out classification is taken in this example, obtains 6 class links, as shown in figure 5, link 1, link 2, link 3 ... chain in figure
The grouping that 6 groups of typical cases are segmented logistics link paths is expressed on road 6, is each group by the flow chart that the letter of expression processing step forms
The process model figure of representative link；The fragment number that every kind of classification is included is exported, shipyard fragmented transport is instructed；It realizes clustering tree
Figure it is as shown in Figure 6；
Wherein 6 groups of typical cases are segmented logistics link paths, respectively indicate are as follows:
(1) A---S in link 1 is indicated after assembling operation, and the segmentation in the path will enter stockyard and have enough to meet the need, etc.
To other job instructions；S---B indicates that the segmentation waited in stockyard will be transported to and carries out sand washing polishing operation；B-P refers to
Segmentation is moved to spray painting operation from sand washing polishing operation；Segmentation is transported to the progress of coating square after the completion of P-R refers to spray painting operation
Turnover；R-S refers to that segmentation enters stockyard turnover from coating square and stacks；R-E refers to that segmentation removes coating square and enters pre- total group of work
Industry；S-E refers to that segmentation enters pre- total group job from stockyard；Wherein S-S refers to field internal shift, steps down to give other to be segmented；R-
R refers to segmentation in coating square internal shift；E-E refers to segmentation in pre- total group of station internal shift；
(2) A---S is indicated after assembling operation in link 2, and the segmentation in the path will enter stockyard and have enough to meet the need, and is waited
Other job instructions；S-E refers to that segmentation enters pre- total group job from stockyard；S---B indicates that the segmentation waited in stockyard will be by
Transport extremely carries out sand washing polishing operation；B-P refers to that segmentation is moved to spray painting operation from sand washing polishing operation；P-R refers to spray painting operation
Segmentation is transported to coating square and is had enough to meet the need after the completion；R-E refers to that segmentation removes coating square and enters pre- total group job；R—S
Refer to that segmentation enters stockyard turnover from coating square and stacks；Wherein the self-loopa arrow in S operation refers to field internal shift, in order to give
Other segmentations are stepped down；The upper self-loopa arrow of A refers to segmentation in assembling station internal shift；
(3) A---S indicates that segmentation is moved to stockyard from assembling operation and is had enough to meet the need in link 3, waits other job instructions；
S-E refers to that segmentation enters pre- total group job from stockyard；S---B indicates that the segmentation waited in stockyard will be transported to and rushes
Sand polishing operation；B-P refers to that segmentation is moved to spray painting operation from sand washing polishing operation；P-R refer to segmentation from spray painting operation transport to
It stacks on coating square；R-S refers to that segmentation enters stockyard turnover from coating square and stacks；R-E refers to that segmentation removes coating square and enters
Pre- total group job；Wherein S-S refers to field internal shift, may step down for other segmentations；E-E refers to segmentation in pre- total group of station
Displacement；
(4) A---S indicates that segmentation is moved to stockyard from assembling operation and is had enough to meet the need in link 4, waits other job instructions；
Arrow indicates that segmentation is had enough to meet the need back and forth between advance fitting-out and stockyard between S-O, in order to which other segmentations are stepped down；S---B is indicated in heap
The segmentation waited in, which will be transported to, carries out sand washing polishing operation；B-P refers to that segmentation is moved to spray painting from sand washing polishing operation and makees
Industry；P-R refers to that segmentation is transported from spray painting operation to coating square and stacks；R-S refers to that segmentation enters stockyard turnover heap from coating square
It puts；R-E refers to that segmentation removes coating square and enters pre- total group job；S-E refers to that segmentation enters pre- total group job from stockyard；Wherein S-
S refers to segmentation to field internal shift；
(5) A---S indicates that segmentation is moved to stockyard from assembling operation and is had enough to meet the need in link 5, waits other job instructions；
Arrow indicates that segmentation is had enough to meet the need back and forth between advance fitting-out and stockyard between S-O, in order to which other segmentations are stepped down；S---B is indicated in heap
The segmentation waited in, which will be transported to, carries out sand washing polishing operation；B-P refers to that segmentation is moved to spray painting from sand washing polishing operation and makees
Industry；P-R refers to that segmentation is transported from spray painting operation to coating square and stacks；R-S refers to that segmentation enters stockyard turnover heap from coating square
It puts；R-E refers to that segmentation removes coating square and enters pre- total group job；S-E refers to that segmentation enters pre- total group job from stockyard；P-S refers to
Segmentation is waited from spray station transport stockyard today；Wherein S-S refers to segmentation to field internal shift；E-E refers to segmentation in pre- total group of work
Position internal shift；R-R refers to segmentation in coating square internal shift；O-O refers to that segmentation in advance fitting-out station internal shift, allows for other segmentations
Position；
(6) A---S in link 6 is indicated after assembling operation, and the segmentation in the path will enter stockyard and have enough to meet the need, etc.
To other job instructions；Arrow indicates that segmentation is had enough to meet the need back and forth between advance fitting-out and stockyard between S-O, in order to which other segmentations are stepped down；
O-B, which refers to share from advance fitting-out operation, moves into sand washing polishing operation；S---B indicates that the segmentation waited in stockyard will be by
Transport extremely carries out sand washing polishing operation；B-P refers to that segmentation is moved to spray painting operation from sand washing polishing operation；P-R refers to segmentation from spray painting
Operation, which is transported to coating square, stacks；R-S refers to that segmentation enters stockyard turnover from coating square and stacks；R-E refers to that segmentation removes coating
Square enters pre- total group job；S-E refers to that segmentation enters pre- total group job from stockyard；It is modern that P-S refers to that segmentation is transported from spray station
Day stockyard waiting；Wherein S-S refers to segmentation to field internal shift；E-E refers to segmentation in pre- total group of station internal shift；O-O refers to that segmentation exists
Advance fitting-out station internal shift is stepped down for other segmentations.
The implementation process of above-mentioned 6 groups of typical cases segmentation logistics link paths is as shown in Figure 7 simultaneously.
Finally, it should be noted that these are only the preferred embodiment of the present invention, it is not intended to restrict the invention, although
Present invention has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, still can be right
Technical solution documented by foregoing embodiments is modified or equivalent replacement of some of the technical features.It is all
Within the spirit and principles in the present invention, any modification, equivalent replacement, improvement and so on should be included in protection of the invention
Within the scope of.
Claims (4)
1. one kind is used for body section logistics link analysis method, which is characterized in that pre- including body section logistical histories data
It handles S1 and body section logistics link analyzes S2；
S1: according to shipyard body section logistical histories data, data entity identification and redundant attributes identification is carried out, checks logistics number
According to quality, all segmentation logistics datas are pre-processed, utilize the pretreatment hands such as data cleansing, data integration, data transformation
Section carries out polishing to the exception item of historical data, missing item, redundancy, differences, to obtain sample data；
S2: the sample data obtained according to body section logistical histories data prediction carries out logistics route digitized description, adopts
The similarity between logistics route is calculated with similarity calculation method, cluster point finally is carried out to all logistics routes
Analysis, obtains the classification cluster of logistics link, instructs putting and carrying for shipyard body section logistics.
2. according to claim 1 a kind of for body section logistics link analysis method, which is characterized in that be directed to step
To data prediction, that steps are as follows is described in S1:
A1: first according to history data set and shipbuilding feature, target ship screening principle is established, determines target ship；
A2: the problem of target ship determined in step A1 is analyzed, target ship segment data is analyzed, it is described
The phenomenon that problem includes but is not limited to shortage of data, data exception, data redundancy, data redundancy is two including but not limited to adjacent
Data Date is carried in the destination or starting point of data record are inconsistent, lack certain process transportation route data, same segmentation
There is large jump；
A3: determining the pretreatment mode of exception segment data, successively as described below:
A31: missing values pretreatment replaces missing values (to carry out missing values using Decision Tree Inductive method to push away using most likely value
Reason), so that the relationship between missing values and other numerical value is kept maximum；
A32: exceptional value pretreatment, deleted using data, in conjunction with overall model comprehensive analysis substitution, be considered as missing values and the side such as fill up
Formula is pre-processed, and the departure degree after outlier processing between other numerical value is minimized；
A33: data redundancy pretreatment is analyzed using relation on attributes of the correlation analysis to segmentation logistics data.
A4: it completes to obtain in logistics data sample set storing data warehouse via pretreatment, be analyzed for data.
3. according to claim 2 a kind of for body section logistics link analysis method, which is characterized in that using related
Property analysis method the relation on attributes of segmentation logistics data is analyzed, the correlation between data attribute is larger, and data are related
Property related value range be [- 1, -0.6] or [0.6,1]), an attribute is rejected in two data attributes, utilization is remaining
Data attribute substitutes the big primitive attribute of correlation, reduces data redundancy.
4. according to claim 1 a kind of for body section logistics link analysis method, which is characterized in that be directed to step
It is as described below to body section logistics link analytical procedure in S2:
B1: the graphical description of body section logistics route:
The image conversion description of any segmentation transport path includes node and two, side element, is passed through in node expression transport path
Designated position, the total number of positions are a, and side then indicates the route between two designated positions.For body section logistics data sample
Any two are concentrated to be segmented u and v, and u ≠ v, the logistics route for being segmented u and segmentation v is expressed as Gu and Gv, u section corresponding with v
Point, side are needed in same corresponding position if the graph structure interior joint or number of edges mesh of Gu and Gv differ in two graph structures
Short position addition dummy node and fictitious line operation, Gu and Gv can be respectively indicated Gu=(Fu, Bu), Gv=(Fv, Bv), wherein
Node collection Fu=<Fu (1), Fu (2) ..., Fu (a)>, Fv=<Fv (1), Fv (2) ..., Fv (a)>, if segmentation u or v passes through i
It sets (i=1,2 ..., n), Fu (i)=1 or Fv (i)=1, otherwise Fu (i)=0 or Fv (i)=0；Side collection Bu=< Bu (1), Bu
(2) ..., Bu (b) >, number of edges be number of nodes permutation and combination maximum value, i.e.,Bv=< Bv (1), Bv (2) ..., Bv (b)
>, if the path j (j=1,2 ..., b) is passed through in segmentation u logistics, Bu (j)=1, otherwise Bu (j)=0；
B2: similitude present in body section logistics route is analyzed:
Compare GuWith GvGraph structure, it is full to figure interior joint and the connection when the scale that is formed is consistent, any two node all exists
And graph structure, the similarity of two graph structures is calculated using Similarity Algorithm, is indicated are as follows:
In formula: the value range of α is 0≤α≤1, and α characterizes influence coefficient of the graph structure interior joint to similarity analysis, i.e. hull
Segmentation carries position to the percentage contribution of transport path similitude, and the value range of β is 0≤β≤1, and β characterizes side pair in graph structure
The influence coefficient of similarity analysis, the i.e. percentage contribution of the transport path similitude of body section transportation route, alpha+beta=1；N=
n1+n2, n expression node total number, 0≤n1≤ n indicates Fu(i)=0 ∪ Fv(i)=0 number of nodes,
0≤n2≤ n, Fu(i)≠0∩Fv(i) ≠ 0 number of nodes；
Edis{Fu,FvIndicate node updates operating distance, max { Fu,FvIt is Edis { Fu,FvMaximum value, Edis { Bu,Bv}
Indicate node updates operating distance, max { Bu,BvIt is Edis { Bu,BvMaximum value.
B3: to clustering in body section logistics link:
B31: t initial cluster center is selected from the data of body section logistics route sample；
B32: each sample data is calculated separately to the similarity of t cluster centre according to minimum distance criterion, each path is divided
It is fitted among nearest classification；
B33: after the completion of all path allocations, t cluster centre is recalculated；
B34: the cluster centre being calculated by step B33 and the initial cluster center chosen in step B31 are compared, such as
Fruit cluster centre changes, then resumes step B32, counts again；If cluster centre does not change, stop calculating simultaneously
Output cluster as a result, obtaining body section logistics link.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811286666.2A CN110009268A (en) | 2018-10-31 | 2018-10-31 | One kind being used for body section logistics link analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811286666.2A CN110009268A (en) | 2018-10-31 | 2018-10-31 | One kind being used for body section logistics link analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110009268A true CN110009268A (en) | 2019-07-12 |
Family
ID=67164903
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811286666.2A Pending CN110009268A (en) | 2018-10-31 | 2018-10-31 | One kind being used for body section logistics link analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110009268A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111818404A (en) * | 2020-06-13 | 2020-10-23 | 东南大学 | Method for judging discretization link state of passive optical network user side reflected signal |
| CN117094641A (en) * | 2023-10-19 | 2023-11-21 | 湖南省交通科学研究院有限公司 | Traffic logistics public information service system and method based on block chain |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103257615A (en) * | 2013-04-11 | 2013-08-21 | 西安交通大学 | Form quality dynamic identification and modification control method in machining process |
| CN104951912A (en) * | 2015-05-13 | 2015-09-30 | 武汉理工大学 | Internet of Things technology based ship part sectional logistics monitoring system and method |
| CN105956723A (en) * | 2016-07-19 | 2016-09-21 | 成都镜杰科技有限责任公司 | Logistics information management method based on data mining |
| CN106503944A (en) * | 2016-10-26 | 2017-03-15 | 上海海事大学 | Rule-based body section Logistic Scheduling method |
| CN108428067A (en) * | 2018-04-09 | 2018-08-21 | 东华大学 | A kind of printing quality analysis of Influential Factors method based on historical data |
-
2018
- 2018-10-31 CN CN201811286666.2A patent/CN110009268A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103257615A (en) * | 2013-04-11 | 2013-08-21 | 西安交通大学 | Form quality dynamic identification and modification control method in machining process |
| CN104951912A (en) * | 2015-05-13 | 2015-09-30 | 武汉理工大学 | Internet of Things technology based ship part sectional logistics monitoring system and method |
| CN105956723A (en) * | 2016-07-19 | 2016-09-21 | 成都镜杰科技有限责任公司 | Logistics information management method based on data mining |
| CN106503944A (en) * | 2016-10-26 | 2017-03-15 | 上海海事大学 | Rule-based body section Logistic Scheduling method |
| CN108428067A (en) * | 2018-04-09 | 2018-08-21 | 东华大学 | A kind of printing quality analysis of Influential Factors method based on historical data |
Non-Patent Citations (1)
| Title |
|---|
| SEUNG-KYUNG LEE: "Mining transportation logs for understanding the after-assembly block manufacturing process in the shipbuilding industry" * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111818404A (en) * | 2020-06-13 | 2020-10-23 | 东南大学 | Method for judging discretization link state of passive optical network user side reflected signal |
| CN111818404B (en) * | 2020-06-13 | 2022-03-08 | 东南大学 | Method for judging discretization link state of passive optical network user side reflected signal |
| CN117094641A (en) * | 2023-10-19 | 2023-11-21 | 湖南省交通科学研究院有限公司 | Traffic logistics public information service system and method based on block chain |
| CN117094641B (en) * | 2023-10-19 | 2024-01-02 | 湖南省交通科学研究院有限公司 | Traffic logistics public information service system and method based on block chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101585453B (en) | Distribution Method for export container yard of container wharf | |
| CN102004922B (en) | High-resolution remote sensing image plane extraction method based on skeleton characteristic | |
| Ikli et al. | The aircraft runway scheduling problem: A survey | |
| CN110110403A (en) | A kind of scheduling gear method being applicable in unidirectional continuous lockage ship | |
| Linn et al. | A heuristic for dynamic yard crane deployment in a container terminal | |
| CN110009268A (en) | One kind being used for body section logistics link analysis method | |
| CN101844681A (en) | Buffer area facing coating or assemble production line | |
| CN109726917B (en) | Freight flight scheduling method and device based on four-dimensional track | |
| CN102004852A (en) | Airport ground aircraft slide route automatic calculating method | |
| CN110502509A (en) | A kind of traffic big data cleaning method and relevant apparatus based on Hadoop Yu Spark frame | |
| CN112164247A (en) | Ship route prediction method based on ship track clustering | |
| CN101986313A (en) | Knowledge-based container quay berth and shore bridge dispatching method | |
| CN110751309B (en) | Abnormal flight recovery method, electronic equipment and storage medium | |
| CN108564136A (en) | A kind of airspace operation Situation Assessment sorting technique based on fuzzy reasoning | |
| Mokhtarimousavi et al. | Multi-objective mathematical modeling of aircraft landing problem on a runway in static mode, scheduling and sequence determination using NSGA-II | |
| CN103714396A (en) | Rapid intelligent optimization method and system for motor train unit application and maintenance scheme | |
| CN114446094A (en) | Space-time conversion method of flight sequencing information | |
| CN115439766A (en) | Unmanned aerial vehicle target detection method based on improved yolov5 | |
| CN113743666B (en) | Flight outgoing mission planning method, device, equipment and medium | |
| CN113438620B (en) | Optimal selection method for central nodes of unmanned aerial vehicle clusters | |
| CN112083734A (en) | Collective flight path planning method using probabilistic weather forecast | |
| CN108665091A (en) | A kind of goods and materials intelligent dispatching method based on machine learning | |
| CN108168558A (en) | Unmanned aerial vehicle flight path planning algorithm applied to river target search task | |
| CN108734346A (en) | The method for allocating tasks of multi-robot system is balanced based on K- mean clusters | |
| Viglioni et al. | Methodology for railway demand forecasting using data mining |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190712 |
|
| RJ01 | Rejection of invention patent application after publication |