CN115392842B - Tray identification and analysis method based on artificial intelligence - Google Patents

Tray identification and analysis method based on artificial intelligence Download PDF

Info

Publication number
CN115392842B
CN115392842B CN202211340995.7A CN202211340995A CN115392842B CN 115392842 B CN115392842 B CN 115392842B CN 202211340995 A CN202211340995 A CN 202211340995A CN 115392842 B CN115392842 B CN 115392842B
Authority
CN
China
Prior art keywords
bearing
simulation
tray
placing
transported
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
Application number
CN202211340995.7A
Other languages
Chinese (zh)
Other versions
CN115392842A (en
Inventor
方俊
丁伯双
李长好
陶慧
胡薇薇
张家星
张睿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hefei Huanzhi Technology Co ltd
Original Assignee
Hefei Huanzhi Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hefei Huanzhi Technology Co ltd filed Critical Hefei Huanzhi Technology Co ltd
Priority to CN202211340995.7A priority Critical patent/CN115392842B/en
Publication of CN115392842A publication Critical patent/CN115392842A/en
Application granted granted Critical
Publication of CN115392842B publication Critical patent/CN115392842B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • 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
    • 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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of tray identification, and particularly discloses a tray identification and analysis method based on artificial intelligence. This tray identification analysis method based on artificial intelligence specifically through acquireing the transportation information that waits transportation goods basic information and the article of waiting to transport correspond the associated transportation tray, carry out demand tray figure prediction, bearing simulation is carried out through the mode of constructing the model simultaneously, confirm actual demand tray figure and article from this and put the rule, the effectual problem that has solved current technology and lacks based on article loading aspect tray identification analysis has on the one hand broken the limitation that current technology exists, the accuracy and the rationality of tray loading have been improved, and still provide clear direction for the follow-up operation plan deployment of fork truck, thereby the follow-up operation process of fork truck has been promoted. Meanwhile, the pertinence and flexibility of loading of the tray are improved, and the reasonability, reliability and standardability of placing articles in the tray are guaranteed.

Description

Tray identification and analysis method based on artificial intelligence
Technical Field
The invention belongs to the technical field of tray identification, and relates to a tray identification and analysis method based on artificial intelligence.
Background
With the rapid development of warehouse logistics, the number of articles managed by the warehouse is increasing, the times of warehouse entry and exit are more frequent, and the warehouse management operation tends to be complicated and diversified gradually. In this context, since the transportation with pallets is rapidly spread, pallet recognition is required to ensure the operational stability of the warehouse logistics.
The target carries out tray discernment analysis and mainly carries out discernment in coordination based on the fork truck operation, carries out discernment analysis to the aspect such as type, tray jack, the transport mode of fork truck operation demand tray promptly, but the core function of tray is bearing article, and current discernment mode emphasizes on the transport aspect of fork truck, lacks the tray discernment analysis based on article loading aspect, still has certain limitation, and its concrete embodiment is in following aspect: first, fork truck is when carrying out the tray discernment, and the tray state is for loading the article state, and the front end that belongs to the fork truck tray discernment is selected to article bearing tray, only discerns the tray type that fork truck corresponds etc. at present, does not carry out tray figure discernment according to transportation article information, can't improve accurate nature and the rationality that the tray loaded, also can't provide clear and definite direction for fork truck operation plan deployment simultaneously.
Secondly, the article in the current tray is the fixed formula of putting, does not put the analysis according to the basic information of article and the transportation information of article, has very big limitation, and it specifically includes: 1. the fixed pertinence of putting the formula is relatively poor, and the flexibility is not enough, leads to being suitable for the scene and comparatively limits to the fixed standardization and the stability of putting the formula and can't improving article and putting, and then can't reduce the hidden danger that drops of article in the tray at the state of placing and transport state, still can't reduce the damage risk of tray simultaneously, make the life of tray can't obtain the powerful guarantee, increased storehouse material cost of transportation.
2. The tray is generally used with the fork truck cooperation, must involve the transportation route aspect, does not carry out article based on article transportation route at present and puts the mode analysis, can't improve the subsequent transportation operation's of fork truck smoothness, also can't improve the adaptation degree that the tray article were put and the transportation route.
3. The stability of the article is the primary consideration factor of the operation of the forklift, certain differences exist in the stability corresponding to different placing modes, the current tray identification mode cannot ensure the stability of the article placement, the complexity of the analysis of the subsequent forklift operation mode cannot be reduced, the analysis flow of the subsequent forklift operation cannot be simplified, and therefore the operation efficiency of the subsequent forklift cannot be improved.
Disclosure of Invention
In view of this, in order to solve the problems in the background art, a tray identification and analysis method based on artificial intelligence is proposed.
The purpose of the invention can be realized by the following technical scheme: the invention provides a tray identification and analysis method based on artificial intelligence, which comprises the following steps: s1, acquiring basic information of goods to be transported: counting the number of the current to-be-transported articles in the target warehouse, and extracting transportation path information, associated transportation tray models and basic attribute information corresponding to the current to-be-transported articles.
S2, acquiring the transportation information of the pallets to be transported: and recording the related transport tray corresponding to the current article to be transported as a target tray, and positioning the transport information corresponding to the target tray from the information base based on the model corresponding to the target tray.
Step S3, forecasting and analyzing the number of the required trays: and carrying out forecasting analysis on the number of the required trays to obtain the number of the required trays corresponding to the current to-be-transported goods, and recording the number as K.
S4, model construction and bearing simulation: and constructing each tray simulation model and each article to be transported simulation model, and carrying out bearing simulation to obtain bearing simulation information.
S5, analyzing tray transportation simulation information: and analyzing the bearing simulation information to obtain the number of the trays and the article placing rule which are actually required.
S6, pallet simulation analysis information feedback: and feeding back the actual required tray number and the article placing rule to the current transportation management personnel of the target storage.
In a preferred embodiment of the present invention, the performing of the demand pallet number prediction analysis specifically includes: and S3-1, positioning the rated bearing height, the rated dynamic load and the rated bearing area from the transportation information corresponding to the target pallet.
And S3-2, positioning the weight, the height and the area corresponding to the reference placing surface from the basic attribute information corresponding to the current article to be transported.
S3-3, based on the height corresponding to the current object to be transported and the rated bearing height corresponding to the target tray, analyzing the height through an analysis formula
Figure 74922DEST_PATH_IMAGE001
Calculating to obtain the expected bearing layer number corresponding to the target tray,
Figure 718393DEST_PATH_IMAGE002
indicating a rounded-down symbol.
S3-4, based on the area corresponding to the current standard placing surface of the object to be transported and the rated bearing area corresponding to the target tray, analyzing the area through an analysis formula
Figure 164811DEST_PATH_IMAGE003
And analyzing to obtain the expected single-layer supporting article number of the target tray, and calculating to obtain the expected maximum supporting article number corresponding to the size layer of the target tray according to the expected supporting layer number corresponding to the target tray and the expected single-layer supporting article number.
S3-5, based on the weight corresponding to the current object to be transported and the rated dynamic load corresponding to the target pallet, analyzing the formula
Figure 221628DEST_PATH_IMAGE004
And calculating to obtain the maximum number of the supported articles corresponding to the loading layer of the target pallet.
And S3-6, confirming that the target tray is allowed to bear the number of the articles to be transported based on the maximum number of the articles to be supported corresponding to the size level of the target tray and the maximum number of the articles to be supported corresponding to the load level of the target tray.
Step S3-7, based on calculation formula
Figure 175809DEST_PATH_IMAGE005
ComputingObtaining the number of the trays corresponding to the current goods to be transported, wherein,
Figure 516530DEST_PATH_IMAGE006
indicating a rounded up symbol.
In a preferred embodiment of the present invention, the confirmation of the number of the objects to be transported permitted by the target pallet includes the following steps: the method comprises the following steps of firstly, calculating the rated bearing space volume corresponding to a target tray, and extracting the corresponding volume of the current object to be transported.
Secondly, recording the weight corresponding to the current object to be transported, the maximum number of the supported objects corresponding to the size layer of the target tray and the rated dynamic load corresponding to the target tray as the weight of the object to be transported, the maximum number of the supported objects corresponding to the size layer of the target tray and the rated dynamic load respectively
Figure 819335DEST_PATH_IMAGE007
And
Figure 645340DEST_PATH_IMAGE008
according to analytical formulae
Figure 576780DEST_PATH_IMAGE009
Analyzing to obtain a target pallet size layer corresponding load conformity assessment index
Figure 257160DEST_PATH_IMAGE010
，
Figure 747178DEST_PATH_IMAGE011
The load deviation is referred to for a set pallet,
Figure 450692DEST_PATH_IMAGE012
a correction factor is evaluated for the set pallet load.
And thirdly, according to the corresponding volume of the current object to be transported, the rated bearing space volume corresponding to the target tray and the maximum number of the bearing objects corresponding to the load bearing level of the target tray, analyzing in the same way to obtain the corresponding volume of the load bearing level of the target tray, wherein the corresponding volume of the load bearing level of the target tray meets the evaluation index.
And fourthly, comparing the load conformity assessment index corresponding to the target tray size layer with the volume conformity assessment index corresponding to the target tray load layer, if the load conformity assessment index corresponding to the target tray size layer is larger than or equal to the volume conformity assessment index corresponding to the target tray load layer, taking the maximum number of the bearing articles corresponding to the target tray size layer as the target tray permission to bear the number of the articles to be transported, otherwise, taking the maximum number of the bearing articles corresponding to the target tray load layer as the target tray permission to bear the number of the articles to be transported.
In a preferred embodiment of the present invention, the bearer simulation information includes static bearer simulation information and dynamic bearer simulation information, where a specific obtaining process of the static bearer simulation information is as follows: and based on the model corresponding to the target tray, positioning each set placing mode of the model corresponding to the target tray from the information base, taking each set placing mode as each placing simulation scene, and positioning a placing rule corresponding to each set placing mode from the information base.
And sequentially placing the simulation models of the objects to be transported on the tray simulation model according to the placing rules corresponding to the placing simulation scenes to form static bearing simulation models, and counting the number of the corresponding static bearing simulation models in each placing simulation scene.
Extracting the maximum exceeding volume of the simulation model for bearing the articles to be transported, the number of the simulation models for bearing the articles to be transported in each bearing layer, the distance between the simulation models for bearing the articles to be transported in each bearing layer and the position of the center point corresponding to the simulation models for bearing the articles to be transported in each bearing layer from the corresponding static bearing simulation models in each placing simulation scene, and using the extracted numbers of the corresponding static bearing simulation models in each placing simulation scene and the corresponding basic simulation information of each static bearing simulation model as the static bearing simulation information.
In a preferred embodiment of the present invention, the specific process of acquiring the dynamic bearing simulation information includes: and setting a reference dynamic bearing model based on the number of the simulation models for bearing the object to be transported in each bearing layer in each static bearing simulation model in each placing simulation scene.
And extracting the path type from the transportation path information corresponding to the current article to be transported, and constructing an article transportation simulation scene.
And extracting the position corresponding to each corner from the transportation path information corresponding to the current object to be transported, selecting dynamic bearing monitoring points at each corner, and marking each corner and each dynamic bearing monitoring point in each corner in the object transportation simulation scene.
And carrying out dynamic bearing simulation on the corresponding reference bearing model in each placing simulation scene in the article transportation simulation scene, further extracting the central point position corresponding to each dynamic bearing monitoring point of each bearing to-be-transported article simulation model in each bearing layer in each bearing model in each placing simulation scene in the article transportation simulation scene, and taking the central point position as dynamic bearing simulation information.
In a preferred embodiment of the present invention, the analyzing the bearer simulation information is used for analyzing the static bearer simulation information, and the specific analyzing process includes the following steps: the number of the corresponding static bearing simulation models under each placing simulation scene is positioned from the static bearing simulation information and recorded as
Figure 199205DEST_PATH_IMAGE013
And d represents a number of the placement simulation scene,
Figure 983359DEST_PATH_IMAGE014
。
positioning the number of the simulation models of the objects to be transported for bearing corresponding to each static bearing simulation model under each placing simulation scene from the static bearing simulation information, analyzing to obtain the uniformity of the number of the corresponding objects to be transported under each placing simulation scene, and recording the uniformity as
Figure 159126DEST_PATH_IMAGE015
。
Positioning the objects to be transported in each bearing layer in each static bearing simulation model under each placing simulation scene from the static bearing simulation informationCalculating the distance between the simulation models to obtain the corresponding supporting object gap conformity under each placing simulation scene, and recording the conformity as
Figure 100668DEST_PATH_IMAGE016
。
Positioning the maximum exceeding volume of the simulation model of the object to be transported in each static bearing simulation model under each placing simulation scene from the static bearing simulation information, and recording the maximum exceeding volume as
Figure 387293DEST_PATH_IMAGE017
。
Positioning the gravity center point position corresponding to each supporting layer bearing article to be transported simulation model in each static supporting simulation model in each placing simulation scene from the static supporting simulation information, analyzing to obtain the stability of the corresponding supporting article in each placing simulation scene, and recording as
Figure 813902DEST_PATH_IMAGE018
。
By analytical formulae
Figure 363832DEST_PATH_IMAGE019
Analyzing to obtain corresponding static bearing coincidence indexes under each placing simulation scene
Figure 323829DEST_PATH_IMAGE020
，
Figure 414145DEST_PATH_IMAGE021
Respectively expressed as the number of the set trays, the number uniformity of the supporting objects, the gap conformity of the supporting objects, the exceeding volume of the supporting objects, the stability of the supporting objects corresponding to the static supporting conformity evaluation proportion weight factor,
Figure 172891DEST_PATH_IMAGE022
the reference supporting object number uniformity, the reference supporting object gap conformity, the reference object excess volume and the reference object stability are respectively set.
In a preferred embodiment of the present invention, the specific analysis process of the stability of the corresponding supporting object under each placing simulation scene is as follows: and mapping the gravity center point position corresponding to each supporting object simulation model to the static supporting simulation model to obtain the corresponding gravity center mapping point number and each gravity center mapping point position in each static supporting simulation model under each placing simulation scene.
Extracting the gravity center point position corresponding to the target tray from the transportation information corresponding to the target tray, and marking the position in the static bearing simulation model, thereby obtaining the distance between the gravity center point position of each static bearing simulation model and each gravity center mapping point position thereof under each placing simulation scene, and marking the distance as the position
Figure 893722DEST_PATH_IMAGE023
R represents the number of each static bearing simulation model,
Figure 855862DEST_PATH_IMAGE024
p is the p-th static bearing simulation model, i is the center of gravity mapping point number,
Figure 235022DEST_PATH_IMAGE025
and n is the nth barycentric mapping point.
The number of simulation models for supporting the object to be transported in each bearing layer in each static bearing simulation model under each placing simulation scene is positioned from the static bearing simulation information and is recorded as
Figure 333428DEST_PATH_IMAGE026
T represents the number of the supporting layer,
Figure 274096DEST_PATH_IMAGE027
and z is expressed as the z-th supporting layer.
Recording the number of corresponding gravity mapping points in each static bearing simulation model under each placing simulation scene
Figure 457952DEST_PATH_IMAGE028
Based on analytical formulae
Figure 906382DEST_PATH_IMAGE029
Analyzing to obtain the stability of the corresponding supporting object under each placing simulation scene
Figure 124874DEST_PATH_IMAGE030
，
Figure 233513DEST_PATH_IMAGE031
For a set reference centre-of-gravity spacing,
Figure 107928DEST_PATH_IMAGE032
respectively expressed as the weight of the center of gravity concentration of the goods in the tray, the number of the center of gravity mapping points of the goods in the tray to the stable estimation of the placement,
Figure 828891DEST_PATH_IMAGE033
and evaluating a correction factor corresponding to the set number of the article gravity center mapping points in the tray.
In a preferred embodiment of the present invention, the analyzing the bearer simulation information is further configured to analyze the dynamic bearer simulation information, and the specific analyzing process includes the following steps: positioning the central point position corresponding to each dynamic bearing monitoring point at each corner of each bearing layer article simulation model in each bearing layer in the reference bearing model in each placing simulation scene in the article transportation simulation scene from the dynamic bearing simulation information, analyzing to obtain the central offset value corresponding to each dynamic bearing monitoring point at each corner of each bearing layer article simulation model in each bearing layer in the reference bearing model in each placing simulation scene in the article transportation simulation scene, and recording the central offset value as the central offset value
Figure 901889DEST_PATH_IMAGE034
G represents the number of the simulation model for bearing the goods to be transported,
Figure 449938DEST_PATH_IMAGE035
and v is expressed as the v-th simulation model for supporting the article to be transported,
Figure 811650DEST_PATH_IMAGE036
to representThe number of the turning part is numbered,
Figure 585571DEST_PATH_IMAGE037
and c is denoted as the c-th turn,
Figure 794966DEST_PATH_IMAGE038
the number of the dynamic bearing monitoring point is shown,
Figure 199403DEST_PATH_IMAGE039
。
extracting the corresponding length and angle of each corner from the transportation path information corresponding to the current object to be transported, and recording the lengths and angles as the lengths and angles
Figure 828836DEST_PATH_IMAGE040
And
Figure 406448DEST_PATH_IMAGE041
from this, the weight of the influence of the offset of the supporting article corresponding to each corner is set and is expressed as
Figure 204771DEST_PATH_IMAGE042
。
By analysis of formulas
Figure 842425DEST_PATH_IMAGE043
Analyzing to obtain corresponding dynamic bearing coincidence indexes under each placing simulation scene
Figure 962085DEST_PATH_IMAGE044
U denotes the number of dynamic bearing monitor points,
Figure 77808DEST_PATH_IMAGE045
in order for the set dynamic bearing to conform to the estimated correction factor,
Figure 183167DEST_PATH_IMAGE046
for a set reference offset corresponding to the jth turn,
Figure 476877DEST_PATH_IMAGE047
is the set allowable offset difference.
In a preferred embodiment of the present invention, the specific expression formula for setting the offset impact weight of the supporting object corresponding to each corner is
Figure 362793DEST_PATH_IMAGE048
Wherein, in the process,
Figure 265896DEST_PATH_IMAGE049
respectively set reference turning length and reference turning angle,
Figure 491341DEST_PATH_IMAGE050
for the set reference corner angle difference,
Figure 955951DEST_PATH_IMAGE051
and respectively expressing the deviation influence evaluation occupation weight factors corresponding to the set turning length and the set turning angle, wherein e is a natural constant.
In a preferred embodiment of the present invention, the obtaining of the actual required number of trays and the article placement rule specifically comprises: corresponding static bearing under each placing simulation scene is in accordance with the index
Figure 798005DEST_PATH_IMAGE052
Corresponding dynamic bearing coincidence index under each placing simulation scene
Figure 785027DEST_PATH_IMAGE053
Importing a calculation formula
Figure 661716DEST_PATH_IMAGE054
In the method, a comprehensive recommendation index corresponding to each placing simulation scene is obtained
Figure 749758DEST_PATH_IMAGE055
，
Figure 95419DEST_PATH_IMAGE056
Corresponding to static and dynamic bearers, respectively, indicated as setAnd recommending and evaluating the proportion weight.
The comprehensive recommendation index corresponding to each placement simulation scene
Figure 91057DEST_PATH_IMAGE057
And sequencing according to a mode from large to small, and marking the placing simulation scene with the first ranking as a target simulation scene.
And extracting the number of corresponding static bearing simulation models in the target simulation scene as the number of actual demand trays corresponding to the current object to be transported, and extracting the placing rules corresponding to the target simulation scene as the object placing rules.
Compared with the prior art, the invention has the following beneficial effects: according to the artificial intelligence-based pallet recognition and analysis method, the basic information of goods to be transported and the transportation information of the goods to be transported corresponding to the associated transportation pallet are obtained, the number of the required pallets is predicted, and meanwhile, the bearing simulation is carried out in a model building mode, so that the actual number of the required pallets and the goods placing rules are confirmed, on one hand, the problem that the pallet recognition and analysis based on the goods loading layer is lacked in the prior art is effectively solved, the limitation of the prior art is broken, the pallet loading accuracy and the rationality are improved, and a clear direction is provided for the subsequent operation plan deployment of the forklift, so that the subsequent operation process of the forklift is promoted; on the other hand has improved the pertinence and the flexibility that the tray loaded to through putting of flexibility, not only richened the suitable scene of follow-up tray transportation, still improved rationality, reliability and the standardization that article were put in the tray, reduced the hidden danger that drops and the damage risk of tray of article when the state of placing and transport state in the tray simultaneously effectively, maintained the life of tray, and then reduced storage goods cost of transportation.
The method and the device predict the number of the required trays from two dimensions of a size aspect and a load aspect, belong to multi-dimensional prediction, not only ensure the reference of a prediction result, but also provide a decision-making reference suggestion for the formulation of a subsequent transportation plan of the current to-be-transported articles, also provide data support for the analysis of the placement rule of the current to-be-transported articles, and simultaneously avoid the occurrence of tray overload and over-height phenomena.
According to the invention, through carrying out static bearing simulation and dynamic bearing simulation and carrying out actual demand tray number and article placement rule analysis based on static bearing simulation information and dynamic bearing simulation information, the analysis of two levels of tray fixed storage and dynamic transportation is realized, the sequence of subsequent forklift operation is greatly ensured, the adaptation degree of the tray article placement to the transportation route of the tray article is effectively improved, and from the other level, the use amount of the tray is reduced under the condition of ensuring that the current articles to be transported are completely placed, and the uniformity and stability of the articles placed in the tray are also ensured. And the complexity of the analysis of the subsequent forklift operation mode is effectively reduced, and the analysis flow of the subsequent forklift operation is simplified, so that the operation efficiency and the operation safety of the subsequent forklift operation are ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating the steps of the method of the present invention.
Detailed Description
While the foregoing is directed to embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.
Referring to fig. 1, the present invention provides a tray identification and analysis method based on artificial intelligence, which includes the following steps: s1, acquiring basic information of goods to be transported: counting the number of the current to-be-transported articles in the target warehouse, and extracting transportation path information, associated transportation tray models and basic attribute information corresponding to the current to-be-transported articles.
In a specific embodiment, the transportation path information corresponding to the current article to be transported includes, but is not limited to, a route type, the number of corners, a length corresponding to each corner, and an angle corresponding to each corner, and the basic attribute information corresponding to the current article to be transported includes, but is not limited to, a three-dimensional profile, a volume, a reference placement surface area, a weight, and a height.
S2, acquiring the transportation information of the pallets to be transported: and recording the related transport tray corresponding to the current article to be transported as a target tray, and positioning the transport information corresponding to the target tray from the information base based on the model corresponding to the target tray.
In one particular example, the transportation information associated with the target pallet includes, but is not limited to, a center of gravity position, a nominal support height, a nominal dynamic load, and a nominal support area.
S3, forecasting and analyzing the number of the required trays: and carrying out the forecast analysis on the number of the required trays to obtain the number of the required trays corresponding to the current to-be-transported goods, and recording the number as K.
Specifically, the number of the demand trays is predicted and analyzed, and the specific analysis process is as follows: and S3-1, positioning the rated bearing height, the rated dynamic load and the rated bearing area from the transportation information corresponding to the target pallet.
And S3-2, positioning the weight, the height and the area corresponding to the reference placing surface from the basic attribute information corresponding to the current article to be transported.
S3-3, based on the height corresponding to the current object to be transported and the rated bearing height corresponding to the target tray, analyzing the height through an analysis formula
Figure 337100DEST_PATH_IMAGE058
Calculating to obtain the expected bearing layer number corresponding to the target tray,
Figure 392780DEST_PATH_IMAGE059
indicating a rounded-down symbol.
S3-4, based on the area corresponding to the reference placing surface of the current object to be transported and the rated bearing area corresponding to the target tray, analyzing the area through an analysis formula
Figure 163421DEST_PATH_IMAGE060
And analyzing to obtain the expected single-layer supporting article number of the target tray, and calculating to obtain the expected maximum supporting article number corresponding to the size layer of the target tray according to the expected supporting layer number corresponding to the target tray and the expected single-layer supporting article number.
It should be noted that the specific calculation formula of the expected maximum number of supported objects corresponding to the size of the target pallet is
Figure 228329DEST_PATH_IMAGE061
Wherein, in the step (A),
Figure 331808DEST_PATH_IMAGE062
expressed as the expected maximum number of supported articles for the target pallet size level,
Figure 558390DEST_PATH_IMAGE063
expressed as the number of expected single-layer support articles for the target pallet,
Figure 65595DEST_PATH_IMAGE064
expressed as the expected number of bearing layers for the target pallet,
Figure 684926DEST_PATH_IMAGE065
supporting the number of articles for a set revision.
S3-5, based on the weight corresponding to the current object to be transported and the rated dynamic load corresponding to the target pallet, analyzing the formula
Figure 125135DEST_PATH_IMAGE066
And calculating to obtain the maximum number of the supported articles corresponding to the loading layer of the target pallet.
And S3-6, confirming that the target tray is allowed to bear the number of the articles to be transported based on the maximum number of the articles to be supported corresponding to the size level of the target tray and the maximum number of the articles to be supported corresponding to the load level of the target tray.
Illustratively, confirming that the target pallet is allowed to hold the number of articles to be transported includes the following steps: the method comprises the following steps of firstly, calculating the rated bearing space volume corresponding to a target tray, and extracting the corresponding volume of the current object to be transported.
Understandably, the rated bearing space volume corresponding to the target tray is the product of the rated bearing height of the target tray and the rated bearing area of the target tray.
Secondly, recording the weight corresponding to the current object to be transported, the maximum number of the supported objects corresponding to the size layer of the target tray and the rated dynamic load corresponding to the target tray as the weight of the object to be transported, the maximum number of the supported objects corresponding to the size layer of the target tray and the rated dynamic load respectively
Figure 37465DEST_PATH_IMAGE067
And
Figure 563124DEST_PATH_IMAGE068
according to analytical formulae
Figure 923829DEST_PATH_IMAGE069
Analyzing to obtain a target pallet size layer corresponding load conformity assessment index
Figure 218544DEST_PATH_IMAGE070
，
Figure 304706DEST_PATH_IMAGE071
The load deviation is referred to for a set pallet,
Figure 317661DEST_PATH_IMAGE072
the correction factor is evaluated for the set pallet load.
Thirdly, recording the volume corresponding to the current object to be transported, the rated bearing space volume corresponding to the target pallet and the maximum number of the bearing objects corresponding to the loading level of the target pallet as
Figure 13216DEST_PATH_IMAGE073
、
Figure 693596DEST_PATH_IMAGE074
And
Figure 682149DEST_PATH_IMAGE075
according to analytical formulae
Figure 979138DEST_PATH_IMAGE076
Analyzing to obtain the corresponding volume conformity evaluation index of the loading layer of the target pallet
Figure 212805DEST_PATH_IMAGE077
，
Figure 265468DEST_PATH_IMAGE078
The volume deviation is referenced for a set tray,
Figure 237972DEST_PATH_IMAGE079
the correction factor is evaluated for the set tray volume.
And fourthly, comparing the corresponding load conformity assessment index of the target tray size level with the corresponding volume conformity assessment index of the target tray load level, if the corresponding load conformity assessment index of the target tray size level is greater than or equal to the corresponding volume conformity assessment index of the target tray load level, taking the maximum bearing article number corresponding to the target tray size level as the target tray permission to bear the number of the articles to be transported, otherwise, taking the maximum bearing article number corresponding to the target tray load level as the target tray permission to bear the number of the articles to be transported.
Step S3-7, based on calculation formula
Figure 976252DEST_PATH_IMAGE080
Calculating to obtain the number of the trays required by the current goods to be transported, wherein,
Figure 997297DEST_PATH_IMAGE081
indicating a rounded up symbol.
The embodiment of the invention carries out the demand pallet number prediction from two dimensions of a size aspect and a load aspect, belongs to multi-dimensional prediction, not only ensures the reference of the prediction result, but also provides a decision-making reference suggestion for the formulation of the subsequent transportation plan of the current to-be-transported goods, and also provides data support for the analysis of the placement rule of the current to-be-transported goods, and simultaneously avoids the occurrence of the phenomena of overload and superelevation of pallets.
S4, model construction and bearing simulation: and constructing each tray simulation model and each article to be transported simulation model, and carrying out bearing simulation to obtain bearing simulation information.
It should be noted that the tray simulation model is constructed according to the model of the target tray, and the article to be transported simulation model is constructed according to the three-dimensional profile of the current article to be transported.
Exemplarily, the bearer simulation information includes static bearer simulation information and dynamic bearer simulation information, wherein a specific acquisition process of the static bearer simulation information is: a1, based on the model corresponding to the target tray, positioning each set placing mode of the model corresponding to the target tray from the information base, taking each set placing mode as each placing simulation scene, and positioning a placing rule corresponding to each set placing mode from the information base.
In one embodiment, the placing modes include, but are not limited to, a tiling and stacking mode, a cross placing simulation mode, and a seam pressing placing mode, and the placing rules include, but are not limited to, the number of placing layers, the number of placing articles in each placing layer, and the distance between placing articles in each placing layer.
And A2, sequentially placing the to-be-transported object simulation models on the tray simulation models according to the placing rules corresponding to the placing simulation scenes to form static bearing simulation models, and counting the number of the corresponding static bearing simulation models in the placing simulation scenes.
And A3, extracting the maximum excess volume of the simulation model for bearing the articles to be transported, the number of simulation models for bearing the articles to be transported in each bearing layer, the distance between the simulation models for bearing the articles to be transported in each bearing layer and the position of the center point corresponding to the simulation model for bearing the articles to be transported in each bearing layer from the corresponding static bearing simulation models in each placing simulation scene, and using the extracted numbers of the static bearing simulation models corresponding to the placing simulation scenes and the basic simulation information corresponding to the static bearing simulation models as the static bearing simulation information.
Further, the specific acquisition process of the dynamic bearing simulation information is as follows: and B1, setting a reference dynamic bearing model based on the number of the simulation models for bearing the object to be transported in each bearing layer in each static bearing simulation model in each placing simulation scene.
It should be added that the specific setting mode for setting the reference dynamic bearing model is as follows: and accumulating the number of the simulation models for supporting the to-be-transported object in each bearing layer in each static bearing simulation model in each placing simulation scene to obtain the number of the simulation models for comprehensively supporting the to-be-transported object corresponding to each static bearing simulation model, and taking the static bearing simulation model with the largest number of the simulation models for comprehensively supporting the to-be-transported object as the reference dynamic bearing model corresponding to each placing simulation scene.
And B2, extracting the path type from the transportation path information corresponding to the current article to be transported, and constructing an article transportation simulation scene.
And B3, extracting the position corresponding to each corner from the transportation path information corresponding to the current object to be transported, selecting dynamic bearing monitoring points at each corner, and marking each corner and each dynamic bearing monitoring point in each corner in the object transportation simulation scene.
And B4, carrying out dynamic bearing simulation on the corresponding reference bearing model in each placing simulation scene in the article transportation simulation scene, further extracting the central point position corresponding to each dynamic bearing monitoring point of each bearing layer to-be-transported article simulation model in each bearing layer in the reference bearing model in each placing simulation scene in the article transportation simulation scene, and taking the central point position as dynamic bearing simulation information.
S5, analyzing tray transportation simulation information: and analyzing the bearing simulation information to obtain the actual required tray number and the article placing rule.
In the above, analyzing the bearing simulation information is used for analyzing the static bearing simulation information, and the specific analysis process includes the following steps: c1, positioning the number of corresponding static bearing simulation models in each placing simulation scene from the static bearing simulation information, and recording the number as
Figure 901537DEST_PATH_IMAGE082
And d represents a number of the placement simulation scene,
Figure 982626DEST_PATH_IMAGE083
。
c2, positioning the number of the simulation models for supporting the object to be transported corresponding to each static bearing simulation model under each placing simulation scene from the static bearing simulation information, analyzing to obtain the uniformity of the number of the corresponding supporting objects under each placing simulation scene, and recording the uniformity as
Figure 208202DEST_PATH_IMAGE084
。
It should be noted that the specific analysis process of the number uniformity of the corresponding supporting objects in each placing simulation scene is as follows: positioning the highest number of the simulation models for bearing the articles to be transported and the lowest number of the simulation models for bearing the articles to be transported corresponding to the static simulation models in each placing simulation scene from the number of the simulation models for bearing the articles to be transported corresponding to the static simulation models in each placing simulation scene, and respectively recording the numbers as the highest number of the simulation models for bearing the articles to be transported and the lowest number of the simulation models for bearing the articles to be transported in each placing simulation scene
Figure 501780DEST_PATH_IMAGE085
And
Figure 986158DEST_PATH_IMAGE086
meanwhile, carrying out mean value calculation on the number of the simulation models for supporting the articles to be transported corresponding to the static bearing simulation models in each placing simulation scene to obtain the number of the simulation models for supporting the articles to be transported corresponding to the static bearing simulation models in each placing simulation scene, and marking the number as the number
Figure 769306DEST_PATH_IMAGE087
。
By analytical formulae
Figure 669129DEST_PATH_IMAGE088
Analyzing to obtain the number uniformity of corresponding supported articles under each placing simulation scene
Figure 313868DEST_PATH_IMAGE089
。
C3, positioning the distance between the simulation models of the objects to be transported of each bearing layer in each static bearing simulation model under each placing simulation scene from the static bearing simulation information, calculating the gap conformity of the corresponding bearing objects under each placing simulation scene, and recording the gap conformity as
Figure 881116DEST_PATH_IMAGE090
。
It should be noted that the specific calculation process of the gap conformity of the corresponding supporting object under each placing simulation scene is as follows: carrying out mean value calculation on the distances between the simulation models for supporting the object to be transported in the bearing layers in the static bearing simulation models in the placing simulation scenes to obtain the average distance between the simulation models for supporting the object to be transported corresponding to the bearing layers in the static bearing simulation models in the placing simulation scenes, and marking as the average distance
Figure 818853DEST_PATH_IMAGE091
And r represents the number of the static bearing simulation model,
Figure 471552DEST_PATH_IMAGE092
p is the p-th static bearing simulation model, t is the bearing layer number,
Figure 903670DEST_PATH_IMAGE093
and z is expressed as the z-th supporting layer.
By calculation of formula
Figure 138473DEST_PATH_IMAGE094
Calculating to obtain the correspondence under each placing simulation sceneSupporting article gap conformity
Figure 732266DEST_PATH_IMAGE095
，
Figure 921195DEST_PATH_IMAGE096
Respectively expressed as the gap coincidence evaluation proportion weight factor corresponding to the article spacing in the set supporting layers and the article spacing between the set supporting layers,
Figure 891425DEST_PATH_IMAGE097
for the reference distance corresponding to the supported object in the t bearing layer in the set static bearing simulation model,
Figure 918418DEST_PATH_IMAGE098
expressed as the reference interval corresponding to the bearing article in the t +1 th bearing layer in the set static bearing simulation model,
Figure 214270DEST_PATH_IMAGE099
for the reference spacing of the articles between the bearing layers in the set static bearing simulation model,
Figure 356407DEST_PATH_IMAGE100
the correction factor is evaluated for the set gap.
C4, positioning the maximum exceeding volume of the simulation model of the object to be transported in each static bearing simulation model under each placing simulation scene from the static bearing simulation information, and recording the maximum exceeding volume as
Figure 130328DEST_PATH_IMAGE101
。
C5, positioning the gravity center point position corresponding to each supporting object to be transported simulation model in each static supporting simulation model in each placing simulation scene from the static supporting simulation information, analyzing to obtain the stability of the corresponding supporting object in each placing simulation scene, and recording the stability as the stability of the corresponding supporting object in each placing simulation scene
Figure 808566DEST_PATH_IMAGE102
。
Understandably, the specific analysis process of the stability of the corresponding bearing article under each placing simulation scene is as follows: and mapping the gravity center point position corresponding to each supporting object simulation model to the static supporting simulation model to obtain the corresponding gravity center mapping point number and each gravity center mapping point position in each static supporting simulation model under each placing simulation scene.
Extracting the gravity center point position corresponding to the target tray from the transportation information corresponding to the target tray, and marking the position in the static bearing simulation model, thereby obtaining the distance between the gravity center point position of each static bearing simulation model and each gravity center mapping point position thereof under each placing simulation scene, and marking the distance as the position
Figure 275319DEST_PATH_IMAGE103
I represents the gravity center mapping point number,
Figure 124326DEST_PATH_IMAGE104
and n is represented as an nth gravity center mapping point.
The number of simulation models for supporting the object to be transported in each bearing layer in each static bearing simulation model under each placing simulation scene is positioned from the static bearing simulation information and is recorded as
Figure 954135DEST_PATH_IMAGE105
。
Recording the number of corresponding gravity mapping points in each static bearing simulation model under each placing simulation scene
Figure 1726DEST_PATH_IMAGE106
Based on analytical formulae
Figure 124534DEST_PATH_IMAGE107
Analyzing to obtain the stability of the corresponding supporting object under each placing simulation scene
Figure 460837DEST_PATH_IMAGE108
，
Figure 91408DEST_PATH_IMAGE109
For reference of settingThe distance between the centers of gravity is increased,
Figure 196767DEST_PATH_IMAGE110
respectively expressed as the weight of the center of gravity concentration of the goods in the tray and the weight of the mapping points of the center of gravity of the goods in the tray to the stable estimation of the placement,
Figure 739744DEST_PATH_IMAGE111
and evaluating a correction factor corresponding to the set number of the article gravity center mapping points in the tray.
C6, passing analysis formula
Figure 376392DEST_PATH_IMAGE112
Analyzing to obtain corresponding static bearing coincidence indexes under each placing simulation scene
Figure 233490DEST_PATH_IMAGE113
，
Figure 242291DEST_PATH_IMAGE114
Respectively expressed as the estimated proportion weight factor corresponding to the set number of trays used, the number uniformity of the supported objects, the gap conformity of the supported objects, the excess volume of the supported objects and the stability of the supported objects,
Figure 487327DEST_PATH_IMAGE115
the reference supporting object number uniformity, the reference supporting object gap conformity, the reference object excess volume and the reference object stability are respectively set.
Further, carrying out the analysis to the bearing simulation information is also used for carrying out the analysis to the dynamic bearing simulation information, and the specific analysis process comprises the following steps: g1, positioning central point positions corresponding to the dynamic bearing monitoring points at the corners of the simulation models for supporting the articles to be transported in the bearing layers in the reference bearing models in the simulation scenes for transporting the articles in the simulation scenes for placing the articles in the simulation scenes from the dynamic bearing simulation information, and analyzing to obtain the positions of the central points corresponding to the dynamic bearing monitoring points at the corners of the simulation models for supporting the articles to be transported in the bearing layers in the reference bearing models in the simulation scenes for placing the articles in the simulation scenes for transporting the articles in the simulation scenes for placing the articles in the simulation scenesThe central offset value corresponding to each dynamic bearing monitoring point at the bend is recorded as
Figure 532644DEST_PATH_IMAGE116
G represents the number of the simulation model for bearing the goods to be transported,
Figure 740902DEST_PATH_IMAGE117
and v is expressed as the v-th simulation model for supporting the article to be transported,
Figure 883171DEST_PATH_IMAGE118
the number of the corner is shown,
Figure 17218DEST_PATH_IMAGE119
and c is denoted as the c-th turn,
Figure 549830DEST_PATH_IMAGE120
the number of the dynamic bearing monitoring point is shown,
Figure 561779DEST_PATH_IMAGE121
。
it should be explained that, in each placement simulation scenario, the specific analysis process of the central offset value corresponding to each dynamic bearing monitoring point at each corner in the article transportation simulation scenario of each bearing layer-to-be-transported article simulation model in each bearing layer in the reference bearing model is as follows: leading the central point position of each bearing to-be-transported article simulation model in each bearing layer in the reference bearing model in each placing simulation scene, which corresponds to each dynamic bearing monitoring point in the article transportation simulation scene, into a set three-dimensional reference coordinate system to obtain the three-dimensional central coordinates of each bearing to-be-transported article simulation model in each bearing layer in the reference bearing model in each placing simulation scene, which corresponds to each dynamic bearing monitoring point in the article transportation simulation scene, and recording the three-dimensional central coordinates as the three-dimensional central coordinates
Figure 558554DEST_PATH_IMAGE122
。
Simulation model for simulating objects to be transported in each bearing layer in reference bearing model under each placing simulation sceneThe position of the central point corresponding to the model is led into a set three-dimensional reference coordinate system, and three-dimensional central coordinates corresponding to simulation models of objects to be transported in each bearing layer in reference bearing model in each placing simulation scene are obtained and recorded as
Figure 817497DEST_PATH_IMAGE123
。
Based on formula of passing analysis
Figure 898060DEST_PATH_IMAGE124
Analyzing to obtain the central offset value of each dynamic bearing monitoring point corresponding to each turning section in the object transportation simulation scene of each bearing layer simulation model for supporting the object to be transported in each bearing layer in the reference bearing model under each placing simulation scene
Figure 962968DEST_PATH_IMAGE125
。
G2, extracting the corresponding length and angle of each corner from the transportation path information corresponding to the current object to be transported, and recording the lengths and angles as the lengths and angles
Figure 299402DEST_PATH_IMAGE126
And
Figure 994826DEST_PATH_IMAGE127
setting the bearing article offset impact weight for each turn, and noting
Figure 813615DEST_PATH_IMAGE128
Wherein, in the step (A),
Figure 354318DEST_PATH_IMAGE129
，
Figure 60106DEST_PATH_IMAGE130
respectively set reference turning length and reference turning angle,
Figure 473900DEST_PATH_IMAGE131
for the set reference corner angle difference,
Figure 468401DEST_PATH_IMAGE132
and respectively expressing the deviation influence evaluation occupation weight factors corresponding to the set turning length and the set turning angle, wherein e is a natural constant.
G3, passing analysis formula
Figure 861730DEST_PATH_IMAGE133
Analyzing to obtain corresponding dynamic bearing coincidence indexes under each placing simulation scene
Figure 687603DEST_PATH_IMAGE134
And u is expressed as the number of dynamic bearing monitoring points,
Figure 724830DEST_PATH_IMAGE135
in order for the set dynamic bearing to conform to the estimated correction factor,
Figure 754097DEST_PATH_IMAGE136
for a set reference offset corresponding to the jth turn,
Figure 698919DEST_PATH_IMAGE137
is the set allowable offset difference.
Further, the actual number of the required trays and the article placing rule are obtained, and the specific obtaining process is as follows: corresponding static bearing under each placing simulation scene is in accordance with the index
Figure 566250DEST_PATH_IMAGE138
Corresponding dynamic bearing coincidence index under each placing simulation scene
Figure 571115DEST_PATH_IMAGE139
Importing a calculation formula
Figure 87678DEST_PATH_IMAGE140
In the method, a comprehensive recommendation index corresponding to each placing simulation scene is obtained
Figure 773874DEST_PATH_IMAGE141
，
Figure 308761DEST_PATH_IMAGE142
And respectively representing the recommended evaluation proportion weight corresponding to the set static support and the set dynamic support.
The comprehensive recommendation index corresponding to each placement simulation scene
Figure 2303DEST_PATH_IMAGE143
And sequencing according to a mode from big to small, and marking the placing simulation scene with the first ranking as a target simulation scene.
And extracting the number of corresponding static bearing simulation models in the target simulation scene as the number of actual demand trays corresponding to the current object to be transported, and simultaneously extracting the placing rules corresponding to the target simulation scene as the object placing rules.
According to the embodiment of the invention, by performing static bearing simulation and dynamic bearing simulation and analyzing the number of the trays and the article placing rule according to the actual demand based on the static bearing simulation information and the dynamic bearing simulation information, the analysis of two levels of tray fixed storage and dynamic transportation is realized, the sequence of subsequent forklift operation is greatly ensured, the adaptability of the tray article placement to the transportation route of the tray article placement is effectively improved, the use amount of the trays is reduced under the condition of ensuring that the current articles to be transported are completely placed from the other level, and the uniformity and stability of the articles placed in the trays are also ensured. And the complexity of the analysis of the subsequent forklift operation mode is effectively reduced, and the analysis flow of the subsequent forklift operation is simplified, so that the operation efficiency and the operation safety of the subsequent forklift operation are ensured.
S6, pallet simulation analysis information feedback: and feeding back the actual required tray number and the article placing rule to the current transportation management personnel of the target storage.
According to the embodiment of the invention, the basic information of the goods to be transported and the transportation information of the goods to be transported corresponding to the associated transportation tray are obtained, the number of the demand trays is predicted, and the bearing simulation is carried out in a mode of constructing a model, so that the actual number of the demand trays and the goods placing rules are confirmed, on one hand, the problem that the prior art is lack of the tray identification analysis based on the goods loading layer is effectively solved, the limitation of the prior art is broken, the accuracy and the reasonability of the loading of the trays are improved, and a definite direction is provided for the subsequent operation plan deployment of the forklift, so that the subsequent operation process of the forklift is promoted; on the other hand has improved the pertinence and the flexibility that the tray loaded to through putting of flexibility, not only richened the suitable scene of follow-up tray transportation, still improved rationality, reliability and the standardization that article were put in the tray, reduced effectively in the tray that article are when the state of placing and transport state drop hidden danger and the damage risk of tray, maintained the life of tray, and then reduced storage goods cost of transportation.
The foregoing is merely exemplary and illustrative of the principles of the present invention and various modifications, additions and substitutions of the specific embodiments described herein may be made by those skilled in the art without departing from the principles of the present invention or exceeding the scope of the claims set forth herein.

Claims (8)

1. A tray identification and analysis method based on artificial intelligence is characterized by comprising the following steps: the method comprises the following steps:
s1, acquiring basic information of goods to be transported: counting the number of the current to-be-transported articles in the target storage, and extracting transportation path information, associated transportation tray models and basic attribute information corresponding to the current to-be-transported articles;
s2, acquiring the transportation information of the pallets to be transported: recording a related transport tray corresponding to the current article to be transported as a target tray, and positioning transport information corresponding to the target tray from an information base based on the model corresponding to the target tray;
s3, forecasting and analyzing the number of the required trays: carrying out forecasting analysis on the number of the required trays to obtain the number of the required trays corresponding to the current to-be-transported goods, and recording the number of the required trays as K;
s4, model construction and bearing simulation: constructing each tray simulation model and each simulation model of the articles to be transported, and carrying out bearing simulation to obtain bearing simulation information;
s5, analyzing the tray transportation simulation information: analyzing the bearing simulation information to obtain the number of trays and article placement rules which are actually required;
s6, pallet simulation analysis information feedback: feeding back the actual required tray number and the article placing rule to a target storage current transportation manager;
the method for predicting and analyzing the number of the demand trays comprises the following specific analysis processes:
s3-1, positioning a rated bearing height, a rated dynamic load and a rated bearing area from transportation information corresponding to a target tray;
s3-2, positioning the weight, the height and the area corresponding to the reference placing surface from the basic attribute information corresponding to the current article to be transported;
s3-3, based on the height corresponding to the current object to be transported and the rated bearing height corresponding to the target tray, analyzing the height through an analysis formula
Figure 202212060959127355
Calculating to obtain the expected number of bearing layers corresponding to the target tray,
Figure 202212060959147623
represents a rounded-down symbol;
s3-4, based on the area corresponding to the reference placing surface of the current object to be transported and the rated bearing area corresponding to the target tray, analyzing the area through an analysis formula
Figure 202212060959151242
Analyzing to obtain the expected single-layer bearing article number of the target tray, and calculating to obtain the expected maximum bearing article number corresponding to the size layer of the target tray according to the expected bearing layer number corresponding to the target tray and the expected single-layer bearing article number;
s3-5, based on the corresponding weight of the current object to be transported and the target pallet pairRated dynamic load by analytical formula
Figure 202212060959153696
Calculating to obtain the maximum number of the supported articles corresponding to the loading layer of the target pallet;
s3-6, confirming that the target tray is allowed to bear the number of the articles to be transported based on the maximum number of the articles to be supported corresponding to the size level of the target tray and the maximum number of the articles to be supported corresponding to the load level of the target tray;
step S3-7, based on calculation formula
Figure 202212060959161130
Calculating to obtain the number of the trays required by the current goods to be transported, wherein,
Figure 202212060959168314
represents a rounded up symbol;
the confirmation target tray is allowed to bear the number of the articles to be transported, and the specific confirmation process comprises the following steps:
firstly, calculating the volume of a rated bearing space corresponding to a target tray, and extracting the corresponding volume of the current object to be transported;
secondly, recording the weight corresponding to the current object to be transported, the maximum number of the supported objects corresponding to the size layer of the target tray and the rated dynamic load corresponding to the target tray as the weight of the object to be transported, the maximum number of the supported objects corresponding to the size layer of the target tray and the rated dynamic load respectively
Figure 202212060959168587
And
Figure 202212060959169751
according to analytical formulae
Figure 202212060959170123
Analyzing to obtain a target pallet size layer corresponding load conformity assessment index
Figure 202212060959172617
，
Figure 202212060959172891
The load deviation is referred to for a set pallet,
Figure 202212060959173645
evaluating a correction factor for the set pallet load;
thirdly, according to the corresponding volume of the current object to be transported, the rated bearing space volume corresponding to the target pallet and the maximum number of the bearing objects corresponding to the load bearing level of the target pallet, analyzing in the same way to obtain the corresponding volume of the load bearing level of the target pallet, which meets the evaluation index;
and fourthly, comparing the corresponding load conformity assessment index of the target tray size level with the corresponding volume conformity assessment index of the target tray load level, if the corresponding load conformity assessment index of the target tray size level is greater than or equal to the corresponding volume conformity assessment index of the target tray load level, taking the maximum bearing article number corresponding to the target tray size level as the target tray permission to bear the number of the articles to be transported, otherwise, taking the maximum bearing article number corresponding to the target tray load level as the target tray permission to bear the number of the articles to be transported.
2. The artificial intelligence based tray identification and analysis method of claim 1, wherein: bearing analog information includes static bearing analog information and developments bearing analog information, and wherein, the concrete acquisition process of static bearing analog information does:
based on the model corresponding to the target tray, positioning each set placing mode of the model corresponding to the target tray from the information base, taking each set placing mode as each placing simulation scene, and positioning a placing rule corresponding to each set placing mode from the information base;
sequentially placing the simulation models of the objects to be transported on the tray simulation model according to the placing rules corresponding to the placing simulation scenes to form static bearing simulation models, and counting the number of the corresponding static bearing simulation models in each placing simulation scene;
the method comprises the steps of extracting the maximum excess volume of a simulation model for bearing the articles to be transported, the number of simulation models for bearing the articles to be transported in each bearing layer, the distance between the simulation models for bearing the articles to be transported in each bearing layer and the position of a center point and the position of the center point corresponding to the simulation model for bearing the articles to be transported in each bearing layer from the corresponding static bearing simulation models in each placing simulation scene, and using the extracted numbers of the corresponding static bearing simulation models in each placing simulation scene and the corresponding basic simulation information of the corresponding static bearing simulation models in each bearing layer as the static bearing simulation information.
3. The artificial intelligence based tray identification and analysis method of claim 2, wherein: the specific acquisition process of the dynamic bearing simulation information is as follows:
setting a reference dynamic bearing model based on the number of simulation models for bearing the object to be transported in each bearing layer in each static bearing simulation model in each placing simulation scene;
extracting a path type from transportation path information corresponding to the current article to be transported, and constructing an article transportation simulation scene;
extracting the position corresponding to each corner from the transportation path information corresponding to the current object to be transported, selecting dynamic bearing monitoring points at each corner, and marking each corner and each dynamic bearing monitoring point at each corner in an object transportation simulation scene;
and carrying out dynamic bearing simulation on the corresponding reference bearing model in the goods transportation simulation scene under each placing simulation scene, further extracting the central point position corresponding to each dynamic bearing monitoring point of each turning position of each bearing simulation model in each bearing layer in each bearing model in each placing simulation scene in the goods transportation simulation scene, and taking the central point position as dynamic bearing simulation information.
4. The artificial intelligence based tray identification and analysis method of claim 3, wherein: analyze bearing analog information and be used for analyzing static bearing analog information, its concrete analytic process includes following step:
positioning the number of the corresponding static bearing simulation models in each placement simulation scene from the static bearing simulation information, and recording the number as
Figure 202212060959174035
And d represents a number of the placing simulation scene,
Figure 202212060959174309
；
positioning the number of the simulation models of the objects to be transported for bearing corresponding to each static bearing simulation model under each placing simulation scene from the static bearing simulation information, analyzing to obtain the uniformity of the number of the corresponding objects to be transported under each placing simulation scene, and recording the uniformity as
Figure 202212060959174660
；
Positioning the distance between the simulation models of the objects to be transported in each bearing layer in each static bearing simulation model under each placing simulation scene from the static bearing simulation information, calculating the gap conformity of the corresponding bearing objects under each placing simulation scene, and recording the gap conformity as
Figure 202212060959175375
；
Positioning the maximum exceeding volume of the simulation model of the object to be transported in each static bearing simulation model under each placing simulation scene from the static bearing simulation information, and recording the maximum exceeding volume as
Figure 202212060959175746
；
Positioning the gravity center point position corresponding to each supporting layer supporting object simulation model in each static supporting simulation model in each placing simulation scene from the static supporting simulation information, analyzing and obtaining the stability of the corresponding supporting object in each placing simulation scene,and is marked as
Figure 202212060959175981
；
By analytical formulae
Figure 202212060959176254
Analyzing to obtain corresponding static bearing coincidence indexes under each placing simulation scene
Figure 202212060959177016
，
Figure 202212060959177340
Respectively expressed as the number of the set trays, the number uniformity of the supporting objects, the gap conformity of the supporting objects, the exceeding volume of the supporting objects, the stability of the supporting objects corresponding to the static supporting conformity evaluation proportion weight factor,
Figure 202212060959177594
the reference supporting object number uniformity, the reference supporting object gap conformity, the reference object excess volume and the reference object stability are respectively set.
5. The artificial intelligence based tray identification and analysis method of claim 4, wherein: the specific analysis process of the stability of the corresponding bearing article under each placing simulation scene is as follows:
mapping the gravity center point position corresponding to each simulation model for supporting the object to be transported into the static bearing simulation model to obtain the number of corresponding gravity center mapping points and the position of each gravity center mapping point in each static bearing simulation model under each placing simulation scene;
extracting the gravity center point position corresponding to the target tray from the transportation information corresponding to the target tray, and marking the position in the static bearing simulation model, thereby obtaining the distance between the gravity center point position of each static bearing simulation model and each gravity center mapping point position thereof under each placing simulation scene, and marking the distance as the position
Figure 202212060959178668
R represents the number of each static bearing simulation model,
Figure 202212060959179364
p is the p-th static bearing simulation model, i is the center of gravity mapping point number,
Figure 202212060959180098
n is the nth barycentric mapping point;
the number of simulation models for supporting the object to be transported in each bearing layer in each static bearing simulation model under each placing simulation scene is positioned from the static bearing simulation information and is recorded as
Figure 202212060959180743
T represents the number of the supporting layer,
Figure 202212060959181047
and z is expressed as the z-th supporting layer;
recording the number of corresponding gravity mapping points in each static bearing simulation model under each placing simulation scene
Figure 202212060959181301
Based on analytical formulae
Figure 202212060959120742
Analyzing to obtain the stability of the corresponding supporting object under each placing simulation scene
Figure 202212060959182102
，
Figure 202212060959182356
For a set reference centre-of-gravity spacing,
Figure 202212060959182629
respectively shown as items in a trayThe weight of the center of gravity concentration, the number of the center of gravity mapping points of the articles in the tray to the stable evaluation of the placement,
Figure 202212060959183676
and evaluating a correction factor corresponding to the set number of the article gravity center mapping points in the tray.
6. The artificial intelligence based tray identification and analysis method of claim 5, wherein: the analysis of the bearing simulation information is also used for analyzing the dynamic bearing simulation information, and the specific analysis process comprises the following steps:
positioning a central point position corresponding to each dynamic bearing monitoring point at each corner of each bearing layer article simulation model in each bearing layer to be transported in the reference bearing model in each placing simulation scene in the article transportation simulation scene from the dynamic bearing simulation information, analyzing to obtain a central offset value corresponding to each dynamic bearing monitoring point at each corner of each bearing layer article simulation model in each bearing layer in each placing simulation scene in the reference bearing model in the article transportation simulation scene, and recording the central offset value as the corresponding central offset value
Figure 202212060959183950
G represents the number of the simulation model for bearing the goods to be transported,
Figure 202212060959184223
and v is expressed as the v-th simulation model for bearing the goods to be transported,
Figure 202212060959184477
the number of the corner is shown,
Figure 202212060959184731
and c is denoted as the c-th turn,
Figure 202212060959185447
the number of the dynamic bearing monitoring point is shown,
Figure 202212060959185720
；
extracting the corresponding length and angle of each corner from the transportation path information corresponding to the current object to be transported, and recording the lengths and angles as the lengths and angles
Figure 202212060959186052
And
Figure 202212060959186306
setting the bearing article offset impact weight for each turn, and noting
Figure 202212060959186814
；
By analysis of formulas
Figure 202212060959187158
Analyzing to obtain corresponding dynamic bearing coincidence indexes under each placing simulation scene
Figure 202212060959190724
And u is expressed as the number of dynamic bearing monitoring points,
Figure 202212060959190997
in order for the set dynamic bearing to conform to the estimated correction factor,
Figure 202212060959191282
for a set reference offset corresponding to the jth turn,
Figure 202212060959192073
is the set allowable offset difference.
7. The artificial intelligence based tray identification and analysis method of claim 6, wherein: the concrete expression formula for setting the offset influence weight of the bearing article corresponding to each corner is as follows
Figure 202212060959192405
Wherein, in the step (A),
Figure 202212060959194783
respectively a reference turning length and a reference turning angle which are set,
Figure 202212060959195050
for the set reference corner angle difference,
Figure 202212060959195851
and respectively expressing the deviation influence evaluation occupation weight factors corresponding to the set turning length and the set turning angle, wherein e is a natural constant.
8. The artificial intelligence based tray identification and analysis method of claim 7, wherein: obtaining the actual demand tray number and the article placing rule, wherein the specific obtaining process comprises the following steps:
corresponding static bearing under each placing simulation scene is in accordance with the index
Figure 202212060959197679
Corresponding dynamic bearing coincidence index under each placing simulation scene
Figure 202212060959197972
Importing a calculation formula
Figure 202212060959198265
In the method, a comprehensive recommendation index corresponding to each placing simulation scene is obtained
Figure 202212060959199528
，
Figure 202212060959199782
Recommendation scores corresponding to static and dynamic bearers respectively expressed as settingsEstimating the proportion weight;
the comprehensive recommendation index corresponding to each placement simulation scene
Figure 202212060959200095
Sequencing according to a mode from big to small, and marking the placing simulation scene with the first rank as a target simulation scene;
and extracting the number of corresponding static bearing simulation models in the target simulation scene as the number of actual demand trays corresponding to the current object to be transported, and simultaneously extracting the placing rules corresponding to the target simulation scene as the object placing rules.
CN202211340995.7A 2022-10-30 2022-10-30 Tray identification and analysis method based on artificial intelligence Active CN115392842B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211340995.7A CN115392842B (en) 2022-10-30 2022-10-30 Tray identification and analysis method based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211340995.7A CN115392842B (en) 2022-10-30 2022-10-30 Tray identification and analysis method based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN115392842A CN115392842A (en) 2022-11-25
CN115392842B true CN115392842B (en) 2023-01-31

Family

ID=84114971

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211340995.7A Active CN115392842B (en) 2022-10-30 2022-10-30 Tray identification and analysis method based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN115392842B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109665328A (en) * 2018-11-29 2019-04-23 湖南视比特机器人有限公司 A kind of dynamic optimization chest palletizing method, information data processing terminal
CN110861925A (en) * 2019-10-10 2020-03-06 广州秉优信息科技有限公司 Stacking method and system for same goods
CN112085385A (en) * 2020-09-09 2020-12-15 广东力生智能有限公司 Generation system and method of stable mixed box stack type box supply sequence based on order
CN113183156A (en) * 2021-05-17 2021-07-30 广东工业大学 Intelligent stacking method based on digital twinning technology
CN114862063A (en) * 2022-07-04 2022-08-05 杭州灵西机器人智能科技有限公司 Online hybrid stacking method and system, electronic device and storage medium

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6505094B2 (en) * 2001-03-05 2003-01-07 Dell Products L.P. System and method for shipping items from a distribution facility
KR101813887B1 (en) * 2015-08-03 2018-01-04 삼성에스디에스 주식회사 Method and apparatus for providing guide for pallet loading
IT201700101543A1 (en) * 2017-09-11 2019-03-11 Bema Srl SOCKET AND HANDLING DEVICE FOR PALLETS AND PULPES IN PALLETIZED LOADS AND RELATED METHODS
WO2019055625A1 (en) * 2017-09-14 2019-03-21 Walmart Apollo, Llc System and method for pallet optimization

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109665328A (en) * 2018-11-29 2019-04-23 湖南视比特机器人有限公司 A kind of dynamic optimization chest palletizing method, information data processing terminal
CN110861925A (en) * 2019-10-10 2020-03-06 广州秉优信息科技有限公司 Stacking method and system for same goods
CN112085385A (en) * 2020-09-09 2020-12-15 广东力生智能有限公司 Generation system and method of stable mixed box stack type box supply sequence based on order
CN113183156A (en) * 2021-05-17 2021-07-30 广东工业大学 Intelligent stacking method based on digital twinning technology
CN114862063A (en) * 2022-07-04 2022-08-05 杭州灵西机器人智能科技有限公司 Online hybrid stacking method and system, electronic device and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
智能化立体仓库入库货位分配的综合优化算法;张仰森等;《计算机科学》;20101231(第12期);全文 *
铁路同类适盘货物装载方案优化研究;秦鉴;《山东科学》;20161015(第05期);全文 *

Also Published As

Publication number Publication date
CN115392842A (en) 2022-11-25

Similar Documents

Publication Publication Date Title
Wu et al. An integrated programming model for storage management and vehicle scheduling at container terminals
Li et al. Joint optimisation of order batching and picker routing in the online retailer’s warehouse in China
US8234004B2 (en) Systems and methods for efficiently determining item slot assignments
EP1864924A1 (en) Stowage information creating device, stowage information creating method using same, method of lading cargo in transport container, distribution management system, computer-readable storage medium used for them, and program
Momani et al. Material handling equipment selection using hybrid Monte Carlo simulation and analytic hierarchy process
Kutzelnigg Optimal allocation of goods in a warehouse: Minimizing the order picking costs under real-life constraints
KR20170049204A (en) Method for risk scoring in logistics system
CN115063090B (en) Digital goods position management method for bulk goods storage
CN115392842B (en) Tray identification and analysis method based on artificial intelligence
CN113822637B (en) Container logistics cloud management system based on internet
Karakaya et al. Relocations in container depots for different handling equipment types: Markov models
CN113650997B (en) Article warehouse-out positioning method and device
Chen et al. Performance evaluation of compact automated parking systems with mobile application and customer service priority
CN117634926A (en) Comprehensive port operation prediction method and system based on big data analysis
Clements et al. Evaluation of warehouse bulk storage lane depth and ABC space allocation using simulation
CN111056210A (en) Material box position adjusting method and device, storage system, medium and electronic equipment
CN115796732A (en) Regional logistics delivery and home distribution management method based on E-commerce platform commodities
CN113592395A (en) Intelligent management method and equipment for industrial material warehousing and computer storage medium
JP4268408B2 (en) Product shipment amount prediction apparatus, method, and computer-readable storage medium
RU2338254C1 (en) Method for determining storage facility adequacy for processing freight flows
JP5434204B2 (en) Product transfer work amount prediction apparatus, product transfer work amount prediction method, and computer program
Sarudin et al. Mixed integer goal programming model for ABC classification based warehouse storage volume and travel distance optimization
KR101398157B1 (en) System for multi piling management of steel plate using rfid and loadcell
Mazur et al. Designing a Physical Packing Sequence Algorithm with Static Stability for Pallet Loading Problems in Air Cargo
CN117689142A (en) Queuing algorithm-based quick assessment method for number of latent transfer robots

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