CN114723132A - Storage goods space intelligent distribution method based on improved carnivorous plant algorithm - Google Patents

Storage goods space intelligent distribution method based on improved carnivorous plant algorithm Download PDF

Info

Publication number
CN114723132A
CN114723132A CN202210356683.9A CN202210356683A CN114723132A CN 114723132 A CN114723132 A CN 114723132A CN 202210356683 A CN202210356683 A CN 202210356683A CN 114723132 A CN114723132 A CN 114723132A
Authority
CN
China
Prior art keywords
goods
algorithm
rate
improved
index
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210356683.9A
Other languages
Chinese (zh)
Other versions
CN114723132B (en
Inventor
徐跃明
欧阳世波
谢俊明
王磊
周心博
吴颀
安裕强
周安祥
迟文超
李苍云
张清友
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.)
Hongyun Honghe Tobacco Group Co Ltd
Original Assignee
Hongyun Honghe Tobacco Group 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 Hongyun Honghe Tobacco Group Co Ltd filed Critical Hongyun Honghe Tobacco Group Co Ltd
Priority to CN202210356683.9A priority Critical patent/CN114723132B/en
Publication of CN114723132A publication Critical patent/CN114723132A/en
Application granted granted Critical
Publication of CN114723132B publication Critical patent/CN114723132B/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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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
    • G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
    • 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
    • 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
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Abstract

The invention discloses a warehousing goods space intelligent distribution method based on an improved carnivorous plant algorithm, which comprises the following steps: according to the warehouse entry and exit efficiency, the warehouse areas are divided, and the priority degree of each goods is determined by adopting a fuzzy AHP-DEA method based on the ABC warehouse classification of multiple criteria; establishing a multi-target goods space subdivision model based on a first-in first-out principle, a time-interval turnover rate principle and a similar article centralization principle; an improved carnivorous plant algorithm based on self-learning strategies, Cauchi variation strategies and mixed mayflies algorithm solves the multi-objective cargo space subdivision model. According to the intelligent storage goods space allocation method based on the improved carnivorous plant algorithm, a fuzzy AHP-DEA evaluation analysis method and time-interval turnover rates of various goods are introduced into a goods space allocation model, the order sorting distance is reduced, and the storage space utilization rate is improved; the reproduction behavior of the CPA algorithm is reserved to increase the biological diversity of the population, an updating strategy is introduced, the stability of the algorithm is improved, and the global optimum searching capability is improved.

Description

Storage goods space intelligent distribution method based on improved carnivorous plant algorithm
Technical Field
The invention relates to the technical field of warehousing goods space distribution, in particular to an intelligent warehousing goods space distribution method based on an improved carnivorous plant algorithm.
Background
With the continuous development of technologies such as internet of things, edge computing, wireless communication technology, etc., smart logistics has become a major development trend in the logistics industry. Storage is one of the key links in the logistics process, and the quality of the storage conditions can directly influence the overall performance of the intelligent logistics.
The intelligent warehousing system adopts a large number of wireless sensing technologies, an internet of things technology, an informatization technology and an intelligent optimization algorithm technology, and changes a large amount of human labor in the traditional warehousing into artificial intelligent automatic processing, so that the cost of warehousing operation is greatly reduced, and the overall efficiency and the response performance of the logistics process are improved.
The allocation of goods space is one of the core decisions in the warehousing process, in the existing goods space allocation system, the allocation of the goods space of the finished cigarette (material) is usually realized by adopting the traditional random allocation, classification allocation and other modes, and the prior art system is difficult to construct an optimal goods space intelligent allocation model in the allocation process.
Therefore, an intelligent storage goods space allocation method based on an improved carnivorous plant algorithm is needed to provide effective technical support for improving the efficiency and quality of storage goods space allocation.
Disclosure of Invention
The invention aims to provide an intelligent storage goods space allocation method based on an improved carnivorous plant algorithm, which is used for solving the problems in the prior art, reducing order sorting distance, improving storage space utilization rate and obtaining a better goods space allocation result.
The invention provides a warehousing goods space intelligent distribution method based on an improved carnivorous plant algorithm, which comprises the following steps:
according to the warehouse entry and exit efficiency, the warehouse areas are divided, and the ABC warehouse classification based on multiple criteria adopts a fuzzy AHP-DEA method to determine the priority degree of each goods so as to classify the goods;
establishing a multi-target goods space subdivision model based on a first-in first-out principle, a time-interval turnover rate principle and a similar article centralization principle so as to subdivide the goods spaces of the three storage areas;
an improved carnivorous plant algorithm based on self-learning strategies, Cauchi variation strategies and hybrid mayflies algorithm solves the multi-target cargo space subdivision model to obtain an optimal cargo space allocation scheme.
The method for intelligently allocating storage goods space based on the improved carnivorous plant algorithm as described above, wherein preferably, the warehouse areas are divided according to the warehouse entry and exit efficiency, and the ABC warehouse classification based on multiple criteria determines the priority of each item by using a fuzzy AHP-DEA method to classify the items, specifically comprising:
dividing the warehouse into three ABC goods storage areas according to the distance from the outlet to the outlet according to the warehouse-in and warehouse-out efficiency;
according to historical order data, a fuzzy AHP-DEA method based on multi-criterion ABC storage classification is introduced to evaluate the priority of goods, and the goods are divided into three categories according to the priority.
The method for intelligently allocating storage goods spaces based on the improved carnivorous plant algorithm preferably introduces a fuzzy AHP-DEA method based on multi-criterion ABC storage classification to evaluate the priority of the goods according to historical order data, and divides the goods into three categories according to the priority, and specifically comprises the following steps:
selecting C key classification indexes for evaluating the priority degree of the goods types according to historical order data;
calculating the weight w of each classification index by adopting an analytic hierarchy processj(j＝1,...,C)；
Calculating the local weight w of each kind of goods i relative to each index j by adopting a data envelope analysis methodij；
According to the weight w of each classification indexjAnd the local weight w of each item i relative to each index jijCalculating total scores S of various goods;
and sorting the goods from high to low in sequence based on the total score so as to classify the goods into ABC three categories according to the priority degree.
The method for intelligently allocating storage goods spaces based on the improved carnivorous plant algorithm is characterized in that the weight w of each classification index is calculated by adopting an analytic hierarchy processj(j ═ 1.., C), including in particular:
constructing a C-order judgment matrix according to pairwise comparison method among various indexes, and solving the maximum characteristic root lambda of the C-order judgment matrixmaxLet a bejiFor j rows and i columns of elements in the matrix, the characteristic value of each index is calculated by the following formula:
Figure BDA0003574733430000031
the maximum feature root is calculated by the following formula:
Figure BDA0003574733430000032
the consistency index CI is calculated by the following formula:
Figure BDA0003574733430000033
wherein C is the number of classification indexes;
the consistency ratio is calculated by the following formula:
Figure BDA0003574733430000034
wherein RI represents a randomness consistency index, and the value thereof can be obtained by table lookup,
if CR is less than 0.1, the matrix passes the consistency test;
respectively adopting three methods of arithmetic mean method, geometric mean method and characteristic value method to obtain weight and taking average value of three weight results to obtain weight w of every classification indexj。
The method for intelligently allocating storage goods spaces based on the improved carnivorous plant algorithm is characterized in that the local weight w of each kind of goods i relative to each index j is preferably obtained by adopting a data envelope analysis methodijThe method specifically comprises the following steps:
defining the grade quantity M for evaluating each kind of goods under each index to obtain a group of grade grades G of each goods relative index jj＝{Pj1,Pj2,…,PjMObtaining the grading result of the fitness of X staff to each goods relative to each index based on the grade to obtain a classification decision matrix, wherein w is the value of the fitness of each staff to each indexijIs defined by the following equation:
Figure BDA0003574733430000035
wherein N is the number of goods, xijmIs to score the goods i under the index j as PijmNumber of staff, w (P)jm) Is a grade PjmThe weight of (c);
solving for the level P by the following DEA modeljmWeight w (P) ofjm)：
Figure BDA0003574733430000041
Figure BDA0003574733430000042
w(Pj1)≥2w(Pj2)≥...≥Mw(PjM)≥0, (6)
Wherein, w (P)j1),...,w(Pjm) Is a decision variable;
by solving the DEA model for each index, the local weight of each item to each index can be obtained by solving the formula (5).
The method for intelligently allocating storage goods spaces based on the improved carnivorous plant algorithm is as described above, wherein preferably, the weights w according to various classification indexes are selectedjAnd the local weight w of each item i relative to each index jijCalculating the total score S of various goods, which specifically comprises the following steps:
the total score S for each item is calculated by the following formula:
Figure BDA0003574733430000043
wherein S isiTotal score for item i, w (P)jm) Is a grade PjmOf (2) is determinedijmIs to score the goods i under the index j as PijmThe number of workers.
The method for intelligently allocating storage cargo space based on the improved carnivorous plant algorithm preferably establishes a multi-target cargo space subdivision model based on a first-in first-out principle, a time-interval turnover rate principle and a similar article centralization principle so as to subdivide the cargo space of three storage areas, and specifically comprises the following steps:
according to the ABC classification result of the goods, a goods space subdivision multi-objective optimization model based on a first-in first-out principle, a time-interval turnover rate principle and a similar goods concentration principle is established so as to subdivide the goods spaces of A, B, C three areas.
The method for intelligently allocating storage cargo spaces based on the improved carnivorous plant algorithm preferably establishes a cargo space subdivision multi-objective optimization model based on a first-in first-out principle, a time-sharing turnover rate principle and a similar article concentration principle according to the ABC classification result of the goods so as to subdivide the cargo spaces of A, B, C three areas, and specifically comprises the following steps:
distributing the A-type goods in the area A, and if the area A has idle goods positions after all the A-type goods are distributed, establishing a proper model to determine the goods to be placed, which specifically comprises the following steps:
assuming the remaining I cargo spaces in the area A, the coordinate of the ith cargo space is (x)i,yi,zi) Warehouse exit coordinates (x)0,y0,z0) Then, the distance between the ith cargo space and the exit is calculated by the following formula:
Figure BDA0003574733430000051
according to the first-in first-out principle, the goods with longer warehousing time should be taken out of the warehouse preferentially, namely the goods are allocated to the goods position closer to the outlet, if J goods to be allocated remain, the warehousing time of each goods J is tjIntroduction of a variable u of 0 to 1ijIf item j is assigned to slot i, then uij1, otherwise uijIf 0, the first optimization objective is:
Figure BDA0003574733430000052
according to the principle of the turnover rate of different periods, the turnover rates of different goods in different periods are different, the goods with high turnover rate in the period should be placed at a goods position closer to an outlet, and the turnover rate of the goods j in the period is set as pjThen the second optimization objective is:
Figure BDA0003574733430000053
according to the same-class article centralization principle, assuming that K shelves are provided in the warehouse, each class of articles should be centrally distributed on the same shelf as much as possible, namely, the types of the articles on each shelf are as few as possible, and the number of the articles on the K shelves is nkThen, the third optimization objective is:
Figure BDA0003574733430000054
weights w introducing three optimization objectives1,w2,w3Converting the three objective functions into a single objective function:
maxY＝w1Y1+w2Y2-w3Y3(12)。
the method for intelligently allocating storage cargo space based on the improved carnivorous plant algorithm as described above, wherein preferably, the improved carnivorous plant algorithm based on the self-learning strategy, the cauchy variation strategy and the hybrid mayfly algorithm solves the multi-target cargo space subdivision model to obtain an optimal cargo space allocation scheme, and specifically comprises the following steps:
a non-linear adjustment parameter omega is introduced into a traditional CPA algorithm to adjust the attraction rate and the reproduction rate in the population iteration process, so that the global search capability of the algorithm is improved, and the variation of omega along with the iteration times is calculated through the following formula:
Figure BDA0003574733430000055
wherein N isiterFor the current number of iterations, MaxiterIs the maximum number of iterations;
due to the growth rate GrateThe higher the search range, the greater the likelihood of missing a globally optimal solution, and therefore GrateWith the decreasing trend of iteration times, the attraction rate ArateThe higher the possibility that the carnivorous plant will digest and absorb the prey, therefore ArateThe trend is presented as the number of iterations increases, the formula of change is as follows:
Figure BDA0003574733430000061
wherein G is1Denotes a predetermined growth rate, A1Representing a preset attraction rate;
the positions of offspring are updated by using the disturbance capability of the Cauchy variation strategy to increase the population biodiversity and simultaneously improve the stability of the algorithm, and the individual position strategy is updated by introducing the mayflies algorithm to increase the biodiversity of each iteration.
The method for intelligently allocating warehouse goods places based on the improved carnivorous plant algorithm as described above, wherein preferably, the disturbance capability of the cauchy variation strategy is utilized to update the positions of offspring so as to increase the population biodiversity and simultaneously promote the stability of the algorithm, and the individual position strategy is simultaneously updated in the mayfly algorithm so as to increase the biodiversity of each iteration, and the method specifically comprises the following steps:
initializing a population, setting algorithm parameters, and generating an initial feasible solution by using an MA algorithm;
calculating the fitness value of each individual in the population, recording the global optimal value and the global optimal solution, selecting N individuals before ranking as carnivorous plants, using the remaining N individuals as preys, and grouping the carnivorous plants and the preys;
each population randomly selects a prey, and when the attraction rate is higher than the randomly generated number, the carnivorous plant captures the prey according to the formula (15) and digests to grow, otherwise, the prey escapes from the trap and continues to grow; the carnivorous plant updates the individual location according to equation (16):
Xnew＝CPi,j×Grate+(1-Grate)×Preyv,j，rand<Rrate (15)
Xnew＝Preyu,j×Grate+(1-Grate)×Preyv,j，rand>＝Rrate (16)
wherein, Preyv,jAnd Preu,jDenotes randomly selected prey, CPi,jIndicating the carnivorous plant at the ith ranking;
the carnivorous plant ranked first, according to the cauchy variation strategy, multiplies the offspring with random individuals in the population according to equation (18) to produce an optimal solution:
the Cauchy variation is derived from a Cauchy distribution, and the one-dimensional Cauchy distribution probability density is as follows:
Figure BDA0003574733430000062
when a is 1, called the standard cauchy distribution, let cauchy (0,1), the formulas of the CPA and MA algorithms update the offspring are as follows:
Xnew＝Xpg+Rrate×+cauchy(0,1)×|Xi-Xv| (18)
wherein, XnewGeneration of offspring for CPA algorithm breeding process, and, at the same time, XiRepresenting the iteration individual, XvRepresents a random individual;
and (3) simulating the cross variation behavior in the MA algorithm to update individuals, updating according to a formula (19), and respectively recording new individuals generated by the CPA algorithm and the MA algorithm:
Figure BDA0003574733430000071
wherein the offset is1And offset printing2Representing MA Algorithm reproductive behavior to produce offspring, XmaleAnd XfemaleRespectively representing male individuals and female individuals in the MA algorithm reproduction behavior when r is1When the number is smaller than the random number, adopting the reproduction behavior in the CPA algorithm to update the individual, or adopting the MA algorithm to reproduce the behavior to update the individual;
combining the newly generated carnivorous plant and prey in the previous population to obtain a new population with a new dimension, and calculating a fitness value of the new population;
evaluating the fitness value of the new population, taking the n individuals before ranking as a new candidate solution to ensure that the population size is unchanged, and simultaneously recording the optimal individual of the iteration;
checking whether the iteration times reach a preset maximum iteration time, and if the iteration times are smaller than the maximum iteration times, returning to the step of randomly selecting a prey in the population;
and outputting the global optimal solution and the iteration curve.
The invention provides a storage goods space intelligent distribution method based on an improved carnivorous plant algorithm, which introduces a fuzzy AHP-DEA evaluation analysis method, time-interval turnover rates of various goods and the like into a goods space distribution model, comprehensively considers the time-interval turnover rates of the goods in a storage, order demands of different time intervals and the storage-in and storage-out efficiency of different goods spaces, and reduces order sorting distance and improves the utilization rate of storage space; an improved carnivorous plant algorithm based on a self-learning strategy, a Cauchy variation strategy and a mixed mayflies algorithm is introduced, the algorithm keeps the reproductive behavior of a CPA algorithm to increase the biological diversity of population, and simultaneously, the self-learning strategy, the disturbance capability of Cauchy variation and the updating strategy of an MA algorithm are introduced, so that the problem that the traditional CPA algorithm is easy to fall into local optimum is solved, the stability of the algorithm is improved, the global optimum searching capability is improved, a more optimal goods allocation result is obtained, and effective technical support is provided for dynamic utilization of storage goods and intelligentization of warehouse order sorting.
Drawings
To make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart of an embodiment of a warehousing goods space intelligent allocation method based on an improved carnivorous plant algorithm provided by the invention;
fig. 2 is a schematic diagram of sorting and sorting of goods in the embodiment of the intelligent allocation method of storage goods space based on the improved carnivorous plant algorithm provided by the invention;
fig. 3 is a logic diagram of an embodiment of the intelligent allocation method of warehousing goods space based on the improved carnivorous plant algorithm provided by the invention.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and is in no way intended to limit the disclosure, its application, or uses. The present disclosure may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that: the relative arrangement of parts and steps, the composition of materials, numerical expressions and numerical values set forth in these embodiments are to be construed as merely illustrative, and not as limitative, unless specifically stated otherwise.
As used in this disclosure, "first", "second": and the like, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element preceding the word covers the element listed after the word, and does not exclude the possibility that other elements are also covered. "upper", "lower", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
In the present disclosure, when a specific component is described as being located between a first component and a second component, there may or may not be intervening components between the specific component and the first component or the second component. When it is described that a specific component is connected to other components, the specific component may be directly connected to the other components without having an intervening component, or may be directly connected to the other components without having an intervening component.
All terms (including technical or scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs unless specifically defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
The goods position distribution is one of the core decisions in the warehousing process, in the existing goods position distribution system, the goods position distribution of finished cigarettes (materials) is usually realized by adopting the traditional modes of random distribution, classified distribution and the like, but in the existing distribution technology, the problems of empty goods positions, overlong carrying distance of workers, first-in first-out of goods, time-sharing difference of goods turnover rate and the like are not fully considered, the defects of no relevance of goods on adjacent goods positions, low efficiency, high time consumption and the like in the order picking process exist, and the existing technology system is difficult to construct an optimal goods position intelligent distribution model in the distribution process.
Only a few studies at present involve a cargo space intelligent allocation model in consideration of the optimization of the personnel carrying path, but none of the studies involve evaluating the goods priority by the fuzzy AHP-DEA method.
As shown in fig. 1 and fig. 3, in an actual implementation process, the method for intelligently allocating storage goods spaces based on an improved carnivorous plant algorithm specifically includes the following steps:
and step S1, according to the warehouse-in and warehouse-out efficiency, dividing warehouse areas, and determining the priority of each goods by adopting a fuzzy AHP-DEA method based on the ABC warehouse classification of multiple criteria so as to classify the goods.
In an embodiment of the method for intelligently allocating storage cargo space based on the improved carnivorous plant algorithm according to the present invention, the step S1 may specifically include:
and step S11, dividing the warehouse into three ABC goods storage areas according to the distance from the exit according to the warehouse-in and warehouse-out efficiency.
And step S12, according to historical order data, introducing a fuzzy AHP-DEA method based on multi-criterion ABC storage classification to evaluate the priority of the goods, and dividing the goods into three categories according to the priority.
In an embodiment of the method for intelligently allocating storage cargo space based on the improved carnivorous plant algorithm according to the present invention, the step S12 may specifically include:
step S121, as shown in fig. 2, selects C key classification indexes for evaluating the priority degree of the item type from the historical order data.
Step S122, calculating the weight w of each classification index by adopting an Analytic Hierarchy Process (AHP)j(j＝1,...,C)。
In an embodiment of the method for intelligently allocating storage cargo space based on the improved carnivorous plant algorithm of the present invention, the step S122 may specifically include:
step S1221, constructing a C-order judgment matrix according to pairwise comparison method among indexes, and solving the maximum characteristic root lambda of the C-order judgment matrixmaxLet a bejiFor j rows and i columns of elements in the matrix, the characteristic value of each index is calculated by the following formula:
Figure BDA0003574733430000101
step S1222, calculating a maximum feature root by the following formula:
Figure BDA0003574733430000102
step S1223, the consistency index CI is calculated by the following formula:
Figure BDA0003574733430000103
wherein C is the number of classification indexes.
Step S1224, calculate the consistency ratio by the following formula:
Figure BDA0003574733430000104
wherein RI represents a randomness consistency index, and the value thereof can be obtained by table lookup,
if CR < 0.1, the matrix passes the consistency test.
Step S1225, calculating weights by arithmetic mean method, geometric mean method and characteristic value methodTaking the average value of the three weight results to obtain the weight w of each classification indexj。
Step S123, calculating the local weight w of each kind of goods i relative to each index j by adopting a data envelope analysis methodij。
In an embodiment of the method for intelligently allocating storage cargo space based on the improved carnivorous plant algorithm of the present invention, the step S123 may specifically include:
step S1231, defining the grade number M of each goods under each index to obtain a group of grading grades G of each goods relative index jj＝{Pj1,Pj2,…,PjMObtaining the grading result of the fitness of X staff to each goods relative to each index based on the grade to obtain a classification decision matrix, wherein w is the value of the fitness of each staff to each indexijIs defined by the following equation:
Figure BDA0003574733430000111
wherein N is the number of goods, xijmIs to score the goods i under the index j as PijmNumber of staff, w (P)jm) Is a grade PjmThe weight of (c).
Step S1232, solving for the rank P by the following DEA modeljmWeight w (P) ofjm)：
Figure BDA0003574733430000112
Figure BDA0003574733430000113
w(Pj1)≥2w(Pj2)≥…≥Mw(PjM)≥0, (6)
Wherein, w (P)j1),...,w(Pjm) Is a decision variable;
by solving the DEA model for each index separately, the local weight of each item to each index can be solved by equation (5).
Step S124, according to the weight w of each classification indexjAnd the local weight w of each item i relative to each index jijThe total score S for each item is calculated.
Specifically, the total score S of each good is calculated by the following formula:
Figure BDA0003574733430000115
wherein S isiTotal score for item i, w (P)jm) Is a grade PjmOf (2) is determinedijmIs to score the goods i under the index j as PijmThe number of workers.
And step S125, sequencing the goods from high to low in sequence based on the total scores so as to classify the goods into ABC three types according to the priority degree.
And step S2, establishing a multi-target goods space subdivision model based on a first-in first-out principle, a time-interval turnover rate principle and a similar goods centralization principle so as to subdivide the goods spaces of the three storage areas.
According to the ABC classification result of the goods, a goods space subdivision multi-objective optimization model based on a first-in first-out principle, a time-interval turnover rate principle and a similar goods centralization principle is established to subdivide the goods spaces of A, B, C three areas. Specifically, the category a goods are allocated to the area a, and if there is a free goods location in the area a after all the category a goods are allocated, an appropriate model needs to be established to determine the goods that should be placed into the area a, in an embodiment of the method for intelligently allocating storage goods locations based on the improved carnivorous plant algorithm of the present invention, the step S2 may specifically include:
step S21, assuming the remaining I cargo spaces in the area A, the coordinate of the ith cargo space is (x)i,yi,zi) Warehouse exit coordinates (x)0,y0,z0) Then, the distance between the ith cargo space and the exit is calculated by the following formula:
Figure BDA0003574733430000121
step S22, according to the first-in first-out principle, the goods with longer warehousing time should be taken out of the warehouse preferentially, namely the goods with longer warehousing time should be distributed to the goods position closer to the outlet, if J goods to be distributed remain, the warehousing time of each goods J is tjIntroduction of a variable u of 0 to 1ijIf item j is assigned to slot i, then u ij1, otherwise uijWhen 0, the first optimization objective is:
Figure BDA0003574733430000122
step S23, according to the principle of time-interval turnover rate, the turnover rates of different goods in different periods are different, the goods with high turnover rate in the period should be preferentially placed at the goods position closer to the export, and the turnover rate of the goods j in the period is set as pjThen the second optimization objective is:
Figure BDA0003574733430000123
step S24, according to the principle of centralization of similar articles, assuming that K shelves are provided in the warehouse, each type of goods should be centrally distributed on the same shelf as much as possible, i.e. the types of goods on each shelf are as few as possible, and the number of the goods on the K shelves is set to be nkThen, the third optimization objective is:
Figure BDA0003574733430000124
step S25, introducing weights w of three optimization targets1,w2,w3Converting the three objective functions into a single objective function:
maxY＝w1Y1+w2Y2-w3Y3 (12)
step S3, solving the multi-target cargo space subdivision model through an improved carnivorous plant algorithm based on the self-learning strategy, the Cauchi variation strategy and the hybrid mayflies algorithm to obtain an optimal cargo space allocation scheme.
A nonlinear adjustment parameter omega is introduced into a traditional CPA algorithm and used for adjusting the attraction rate and the reproduction rate in the population iteration process, so that the global search capability of the algorithm is improved. In an embodiment of the method for intelligently allocating storage cargo space based on the improved carnivorous plant algorithm according to the present invention, the step S3 may specifically include:
step S31, introducing a nonlinear adjustment parameter omega into the traditional CPA algorithm to adjust the attraction rate and the reproduction rate in the population iteration process, thereby improving the global search capability of the algorithm, and calculating the variation of omega along with the iteration times through the following formula:
Figure BDA0003574733430000131
wherein N isiterFor the current number of iterations, MaxiterIs the maximum number of iterations.
Step S32, growth rate GrateThe higher the search range, the greater the likelihood of missing a globally optimal solution, and therefore GrateWith the decreasing trend of iteration times, the attraction rate ArateThe higher the possibility that the carnivorous plant will digest and absorb the prey, therefore ArateThe trend is presented as the number of iterations increases, the formula of change is as follows:
Figure BDA0003574733430000132
wherein G is1Indicates a predetermined growth rate, A1Indicating a preset attraction rate.
Step S33, updating the positions of offspring seeds by using the disturbance capability of the Cauchy variation strategy to increase the population biodiversity and simultaneously improve the stability of the algorithm, and simultaneously introducing the strategy of updating the positions of individuals in the mayfly algorithm to increase the biodiversity of each iteration.
According to the method, an improved carnivorous plant algorithm is adopted, the positions of the offspring are updated by using the disturbance capability of the Cauchy variation strategy, the population biological diversity is increased, and the stability of the algorithm is improved; and simultaneously, an individual position updating strategy is introduced into the mayfly algorithm, the biodiversity of each iteration is increased, the disturbance capability of the algorithm is improved at one time, and the global optimization performance of the algorithm is further improved. In an embodiment of the method for intelligently allocating storage spaces based on the improved carnivorous plant algorithm according to the present invention, the step S33 may specifically include:
step S331, initializing a population, setting algorithm parameters, and generating an initial feasible solution by using an MA algorithm;
s332, calculating the fitness value of each individual in the population, recording the global optimal value and the global optimal solution, selecting N individuals before ranking as carnivorous plants, using the remaining N individuals as prey, and grouping the carnivorous plants and the prey;
step S333, randomly selecting a prey for each population, and when the attraction rate is higher than the randomly generated number, capturing the prey by the carnivorous plant according to a formula (15) and digesting the prey to grow, otherwise, escaping the trap and continuing to grow; the carnivorous plant updates the individual location according to equation (16):
Xnew＝CPi,j×Grate+(1-Grate)×Preyv,j，rand<Rrate (15)
Xnew＝Preyu,j×Grate+(1-Grate)×Preyv,j，rand>＝Rrate (16)
wherein, Prev,jAnd Preu,jDenotes randomly selected prey, CPi,jIndicating the carnivorous plant at the ith ranking;
step S334, the carnivorous plant with the first ranking produces the optimal solution according to the Cauchy variation strategy and the random individuals in the population according to the formula (18):
the Cauchy variation is derived from a Cauchy distribution, and the one-dimensional Cauchy distribution probability density is as follows:
Figure BDA0003574733430000141
when a is 1, called the standard cauchy distribution, let cauchy (0,1), the formulas of the CPA and MA algorithms update the offspring are as follows:
Xnew＝Xpg+Rrate×+cauchy(0,1)×|Xi-Xv| (18)
wherein, XnewGeneration of offspring for CPA algorithm breeding process, and, at the same time, XiRepresenting the iteration individual, XvRepresents a random individual;
and (3) simulating the cross variation behavior in the MA algorithm to update individuals, updating according to a formula (19), and respectively recording new individuals generated by the CPA algorithm and the MA algorithm:
Figure BDA0003574733430000142
wherein the offset is1And offset2Representing MA Algorithm reproductive behavior to produce offspring, XmaleAnd XfemaleRespectively representing male individuals and female individuals in the MA algorithm reproduction behavior when r is1When the number is smaller than the random number, adopting a reproduction behavior in the CPA algorithm to update the individual, or adopting an MA algorithm to reproduce the behavior to update the individual;
step S335, combining the newly generated carnivorous plant and prey in the previous population to obtain a new population with a new dimension, and then calculating a fitness value of the new population;
step S336, evaluating the fitness value of the new population, taking the individuals n before ranking as new candidate solutions to ensure that the population size is unchanged, and simultaneously recording the optimal individuals of the iteration;
step S337, checking whether the iteration times reaches a preset maximum iteration time, and if the iteration times is less than the maximum iteration time, returning to the step of randomly selecting a prey in the population (step S333);
and step S338, outputting the global optimal solution and the iteration curve.
According to the intelligent storage goods space allocation method based on the improved carnivorous plant algorithm, a fuzzy AHP-DEA evaluation analysis method, the time-interval turnover rate of each goods and the like are introduced into a goods space allocation model, the time-interval turnover rate of the goods in a warehouse, the order demands in different time intervals and the warehouse-in and warehouse-out efficiency of different goods spaces are comprehensively considered, so that the order sorting distance is reduced, and the storage space utilization rate is improved; an improved carnivorous plant algorithm based on a self-learning strategy, a Cauchy variation strategy and a mixed mayflies algorithm is introduced, the algorithm keeps the reproductive behavior of a CPA algorithm to increase the biological diversity of population, and simultaneously, the self-learning strategy, the disturbance capability of Cauchy variation and the updating strategy of an MA algorithm are introduced, so that the problem that the traditional CPA algorithm is easy to fall into local optimum is solved, the stability of the algorithm is improved, the global optimum searching capability is improved, a more optimal goods allocation result is obtained, and effective technical support is provided for dynamic utilization of storage goods and intelligentization of warehouse order sorting.
Thus, various embodiments of the present disclosure have been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the foregoing examples are for purposes of illustration only and are not intended to limit the scope of the present disclosure. It will be understood by those skilled in the art that various changes may be made in the above embodiments or equivalents may be substituted for elements thereof without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims (10)

1. A warehousing goods space intelligent distribution method based on an improved carnivorous plant algorithm is characterized by comprising the following steps:
according to the warehouse entry and exit efficiency, dividing warehouse areas, and determining the priority of each goods by adopting a fuzzy AHP-DEA method based on the ABC warehouse classification of multiple criteria so as to classify the goods;
establishing a multi-target goods space subdivision model based on a first-in first-out principle, a time-interval turnover rate principle and a similar article centralization principle so as to subdivide the goods spaces of the three storage areas;
an improved carnivorous plant algorithm based on self-learning strategies, Cauchi variation strategies and hybrid mayflies algorithm solves the multi-target cargo space subdivision model to obtain an optimal cargo space allocation scheme.
2. The method for intelligently allocating storage goods spaces based on the improved carnivorous plant algorithm according to the claim 1, wherein the warehouse areas are divided according to the warehouse-in and warehouse-out efficiency, the ABC storage classification based on multiple criteria adopts a fuzzy AHP-DEA method to determine the priority of each goods so as to classify the goods, and the method specifically comprises the following steps:
dividing the warehouse into three ABC goods storage areas according to the distance from the outlet to the outlet according to the warehouse-in and warehouse-out efficiency;
according to historical order data, a fuzzy AHP-DEA method based on multi-criterion ABC storage classification is introduced to evaluate the priority of goods, and the goods are classified into three categories according to the priority.
3. The intelligent storage goods space allocation method based on the improved carnivorous plant algorithm as claimed in claim 2, wherein according to historical order data, a fuzzy AHP-DEA method based on multi-criterion ABC storage classification is introduced to evaluate the priority of goods, and the goods are classified into three categories according to the priority, specifically comprising the following steps:
selecting C key classification indexes for evaluating the priority degree of the goods types according to historical order data;
calculating the weight w of each classification index by adopting an analytic hierarchy processj(j＝1,...,C)；
Calculating the local weight w of each kind of goods i relative to each index j by adopting a data envelope analysis methodij；
According to the weight w of each classification indexjAnd the local weight w of each item i relative to each index jijCalculating total scores S of various goods;
and sorting the goods from high to low in sequence based on the total score so as to classify the goods into ABC three categories according to the priority degree.
4. The method as claimed in claim 3, wherein the method for intelligently allocating storage goods spaces based on the improved carnivorous plant algorithm is characterized in that the weight w of each classification index is calculated by adopting an analytic hierarchy processj(j ═ 1.., C), including in particular:
constructing a C-order judgment matrix according to pairwise comparison method among various indexes, and solving the maximum characteristic root lambda of the C-order judgment matrixmaxAssume ajiFor j rows and i columns of elements in the matrix, the characteristic value of each index is calculated by the following formula:
Figure FDA0003574733420000021
the maximum feature root is calculated by the following formula:
Figure FDA0003574733420000022
the consistency index CI is calculated by the following formula:
Figure FDA0003574733420000023
wherein C is the number of classification indexes;
the consistency ratio is calculated by the following formula:
Figure FDA0003574733420000024
wherein RI represents a randomness consistency index, and the value thereof can be obtained by table lookup,
if CR is less than 0.1, the matrix passes the consistency test;
respectively adopting an arithmetic mean method, a geometric mean method and a characteristic value methodThe method calculates the weight and averages the three weight results to obtain the weight w of each classification indexj。
5. The intelligent storage goods space allocation method based on the improved carnivorous plant algorithm as claimed in claim 3, wherein the local weight w of each kind of goods i relative to each index j is obtained by adopting a data envelope analysis methodijThe method specifically comprises the following steps:
defining the grade quantity M for evaluating each kind of goods under each index to obtain a group of grade grades G of each goods relative index jj＝{Pj1,Pj2,…,PjMObtaining the grading result of the fitness of X staff to each goods relative to each index based on the grade to obtain a classification decision matrix, wherein w is the value of the fitness of each staff to each indexijIs defined by the following equation:
Figure FDA0003574733420000025
wherein N is the number of goods, xijmIs to score the goods i under the index j as PijmNumber of staff members, w (P)jm) Is a grade PjmThe weight of (c);
solving for the level P by the following DEA modeljmWeight w (P) ofjm)：
Figure FDA0003574733420000031
Figure FDA0003574733420000032
w(Pj1)≥2w(Pj2)≥...≥Mw(PjM)≥0, (6)
Wherein, w (P)j1),...,w(Pjm) Is a decision variable;
by solving the DEA model for each index, the local weight of each item to each index can be obtained by solving the formula (5).
6. The intelligent warehousing goods space allocation method based on improved carnivorous plant algorithm as claimed in claim 3, wherein the weight w according to each classification indexjAnd a local weight w of each item i relative to each index jijCalculating the total score S of various goods, which specifically comprises the following steps:
the total score S for each good is calculated by the following formula:
Figure FDA0003574733420000033
wherein S isiTotal score for item i, w (P)jm) Is a grade PjmOf (2) is determinedijmIs to score the goods i under the index j as PijmThe number of workers.
7. The intelligent warehousing goods space allocation method based on the improved carnivorous plant algorithm as claimed in claim 1, wherein the multi-target goods space subdivision model is established based on a first-in first-out principle, a time-interval turnover rate principle and a similar article centralization principle so as to subdivide the goods spaces of three storage areas, and the method specifically comprises the following steps:
according to the ABC classification result of the goods, a goods space subdivision multi-objective optimization model based on a first-in first-out principle, a time-interval turnover rate principle and a similar goods concentration principle is established so as to subdivide the goods spaces of A, B, C three areas.
8. The intelligent distribution method for the warehouse goods space based on the improved carnivorous plant algorithm according to the claim 7, characterized in that a goods space subdivision multi-objective optimization model based on a first-in first-out principle, a time-sharing turnover rate principle and a similar article centralization principle is established according to the ABC classification result of goods so as to subdivide the goods space of A, B, C three areas, and the method specifically comprises the following steps:
distributing the A-type goods in the area A, and if the area A has idle goods positions after all the A-type goods are distributed, establishing a proper model to determine the goods to be placed, which specifically comprises the following steps:
assuming the remaining I cargo spaces in the area A, the coordinate of the ith cargo space is (x)i,yi,zi) Warehouse exit coordinates (x)0,y0,z0) Then, the distance between the ith cargo space and the exit is calculated by the following formula:
Figure FDA0003574733420000041
according to the first-in first-out principle, the goods with longer warehousing time should be taken out of the warehouse preferentially, namely the goods are allocated to the goods position closer to the outlet, if J goods to be allocated remain, the warehousing time of each goods J is tjIntroduction of a variable u of 0 to 1ijIf item j is assigned to slot i, then uij1, otherwise uijWhen 0, the first optimization objective is:
Figure FDA0003574733420000042
according to the principle of the turnover rate of different periods, the turnover rates of different goods in different periods are different, the goods with high turnover rate in the period should be placed at a goods position closer to an outlet, and the turnover rate of the goods j in the period is set as pjThen the second optimization objective is:
Figure FDA0003574733420000043
according to the same-class article centralization principle, assuming that K shelves are provided in the warehouse, each class of articles should be centrally distributed on the same shelf as much as possible, namely, the types of the articles on each shelf are as few as possible, and the number of the articles on the K shelves is nkThen, the third optimization objective is:
Figure FDA0003574733420000044
weights w introducing three optimization objectives1,w2,w3Converting the three objective functions into a single objective function:
maxY＝w1Y1+w2Y2-w3Y3 (12)
9. the intelligent warehousing cargo space allocation method based on the improved carnivorous plant algorithm as claimed in claim 1, wherein the improved carnivorous plant algorithm based on the self-learning strategy, the cauchy variation strategy and the hybrid mayflies algorithm solves the multi-target cargo space subdivision model to obtain an optimal cargo space allocation scheme, which specifically comprises:
a non-linear adjustment parameter omega is introduced into a traditional CPA algorithm to adjust the attraction rate and the reproduction rate in the population iteration process, so that the global search capability of the algorithm is improved, and the variation of omega along with the iteration times is calculated through the following formula:
Figure FDA0003574733420000051
wherein N isiterFor the current number of iterations, MaxiterIs the maximum iteration number;
due to the growth rate GrateThe higher the search range, the greater the likelihood of missing a globally optimal solution, and therefore GrateWith the decreasing trend of iteration times, the attraction rate ArateThe higher the possibility that the carnivorous plant will digest and absorb the prey, therefore ArateThe trend is presented as the number of iterations increases, the formula of change is as follows:
Figure FDA0003574733420000052
wherein G is1The growth rate is shown as a preset growth rate,A1representing a preset attraction rate;
the positions of offspring are updated by using the disturbance capability of the Cauchy variation strategy to increase the population biodiversity and simultaneously improve the stability of the algorithm, and the individual position strategy is updated by introducing the mayflies algorithm to increase the biodiversity of each iteration.
10. The method for intelligently allocating warehouse goods locations based on the improved carnivorous plant algorithm according to claim 9, wherein the disturbance ability of the cauchy variation strategy is utilized to update the positions of offspring seeds so as to increase the population biodiversity and simultaneously promote the stability of the algorithm, and the individual position strategy is simultaneously updated in the mayfly algorithm so as to increase the biodiversity of each iteration, which comprises the following steps:
initializing a population, setting algorithm parameters, and generating an initial feasible solution by using an MA algorithm;
calculating the fitness value of each individual in the population, recording the global optimal value and the global optimal solution, selecting N individuals before ranking as carnivorous plants, using the remaining N individuals as preys, and grouping the carnivorous plants and the preys;
each population randomly selects a prey, and when the attraction rate is higher than the randomly generated number, the carnivorous plant captures the prey according to the formula (15) and digests to grow, otherwise, the prey escapes from the trap and continues to grow; the carnivorous plant updates the individual location according to equation (16):
Xnew＝CPi,j×Grate+(1-Grate)×Preyv,j，rand<Rrate (15)
Xnew＝Preyu,j×Grate+(1-Grate)×Preyv,j，rand>＝Rrate (16)
wherein, Prev,jAnd Preyu,jDenotes randomly selected prey, CPi,jIndicating the carnivorous plant at the ith ranking;
the carnivorous plant ranked first, according to the cauchy variation strategy, multiplies the offspring with random individuals in the population according to equation (18) to produce an optimal solution:
the Cauchy variation is derived from a Cauchy distribution, and the one-dimensional Cauchy distribution probability density is as follows:
Figure FDA0003574733420000061
when a is 1, called the standard cauchy distribution, cauchy (0,1), the CPA and MA algorithms update the offspring by the following formula:
Xnew＝Xpg+Rrate×+cauchy(0,1)×|Xi-Xv| (18)
wherein XnewGeneration of offspring for CPA algorithm breeding process, and, at the same time, XiRepresenting the individual of this iteration, XvRepresents a random individual;
and (3) simulating the cross variation behavior in the MA algorithm to update individuals, updating according to a formula (19), and respectively recording new individuals generated by the CPA algorithm and the MA algorithm:
Figure FDA0003574733420000062
wherein the offset is1And offset2Representing MA Algorithm reproductive behavior to produce offspring, XmaleAnd XfemaleRespectively representing male individuals and female individuals in the MA algorithm reproduction behavior when r is1When the number is smaller than the random number, adopting a reproduction behavior in the CPA algorithm to update the individual, or adopting an MA algorithm to reproduce the behavior to update the individual;
combining the newly generated carnivorous plant and prey in the previous population to obtain a new population with a new dimension, and calculating a fitness value of the new population;
evaluating the fitness value of the new population, taking the n individuals before ranking as a new candidate solution to ensure that the population size is unchanged, and simultaneously recording the optimal individual of the iteration;
checking whether the iteration times reach a preset maximum iteration time, and if the iteration times are smaller than the maximum iteration times, returning to the step of randomly selecting a prey in the population;
and outputting the global optimal solution and the iteration curve.
CN202210356683.9A 2022-03-31 2022-03-31 Storage goods space intelligent distribution method based on improved carnivorous plant algorithm Active CN114723132B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210356683.9A CN114723132B (en) 2022-03-31 2022-03-31 Storage goods space intelligent distribution method based on improved carnivorous plant algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210356683.9A CN114723132B (en) 2022-03-31 2022-03-31 Storage goods space intelligent distribution method based on improved carnivorous plant algorithm

Publications (2)

Publication Number Publication Date
CN114723132A true CN114723132A (en) 2022-07-08
CN114723132B CN114723132B (en) 2023-04-07

Family

ID=82241953

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210356683.9A Active CN114723132B (en) 2022-03-31 2022-03-31 Storage goods space intelligent distribution method based on improved carnivorous plant algorithm

Country Status (1)

Country Link
CN (1) CN114723132B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117854064A (en) * 2024-03-04 2024-04-09 江苏源坤电子科技有限公司 Refrigerator goods identification system and method based on artificial intelligence
CN117875189A (en) * 2024-03-06 2024-04-12 安徽建筑大学 Three-dimensional warehouse space layout method based on GA optimization GRO
CN117875189B (en) * 2024-03-06 2024-05-14 安徽建筑大学 Three-dimensional warehouse space layout method based on GA optimization GRO

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103473616A (en) * 2013-09-17 2013-12-25 四川航天系统工程研究所 Dynamic goods allocation planning method and system for processing multi-variety goods and material storage
CN113222410A (en) * 2021-05-12 2021-08-06 西安建筑科技大学 Method for establishing goods allocation model in bidirectional layout mode

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103473616A (en) * 2013-09-17 2013-12-25 四川航天系统工程研究所 Dynamic goods allocation planning method and system for processing multi-variety goods and material storage
CN113222410A (en) * 2021-05-12 2021-08-06 西安建筑科技大学 Method for establishing goods allocation model in bidirectional layout mode

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
A. HADI-VENCHEH 等: "A fuzzy AHP DEA approach for multiple criteria ABC inventory classification", 《EXPERT SYSTEMS WITH APPLICATIONS》 *
杨琳: "考虑货位共享效应的非传统仓储布局优化研究", 《中国优秀硕士学位论文全文数据库》 *
松间沙路HBA: "智能优化算法（源码）-食肉植物算法", 《CSDN》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117854064A (en) * 2024-03-04 2024-04-09 江苏源坤电子科技有限公司 Refrigerator goods identification system and method based on artificial intelligence
CN117875189A (en) * 2024-03-06 2024-04-12 安徽建筑大学 Three-dimensional warehouse space layout method based on GA optimization GRO
CN117875189B (en) * 2024-03-06 2024-05-14 安徽建筑大学 Three-dimensional warehouse space layout method based on GA optimization GRO

Also Published As

Publication number Publication date
CN114723132B (en) 2023-04-07

Similar Documents

Publication Publication Date Title
Kuo et al. Integration of particle swarm optimization and genetic algorithm for dynamic clustering
CN103914506B (en) Data searcher, date storage method and data retrieval method
CN109214449A (en) A kind of electric grid investment needing forecasting method
CN102238686A (en) Wireless sensor network routing method for modeling quantum genetic algorithm
CN105929690B (en) A kind of Flexible Workshop Robust Scheduling method based on decomposition multi-objective Evolutionary Algorithm
CN106408132A (en) Method and device of crop yield prediction based on plantation device
Feldmann et al. Multi-dimensional machine learning approaches for fruit shape phenotyping in strawberry
Alimoradi et al. Trees Social Relations Optimization Algorithm: A new Swarm-Based metaheuristic technique to solve continuous and discrete optimization problems
CN108564592A (en) Based on a variety of image partition methods for being clustered to differential evolution algorithm of dynamic
CN112862380B (en) Project type product assembly workshop personnel scheduling method and device based on hybrid algorithm and storage medium
CN107067164A (en) A kind of index Method of fast estimating and system
Guedes et al. Performance analysis of metaheuristic optimization algorithms in estimating the parameters of several wind speed distributions
CN114723132B (en) Storage goods space intelligent distribution method based on improved carnivorous plant algorithm
CN110991518B (en) Two-stage feature selection method and system based on evolutionary multitasking
CN110020712A (en) A kind of optimization population BP neural network forecast method and system based on cluster
Che et al. Stand basal area modelling for Chinese fir plantations using an artificial neural network model
Zhou et al. A decomposition-based multiobjective evolutionary algorithm with weight vector adaptation
Xiao et al. A novel sub-models selection algorithm based on max-relevance and min-redundancy neighborhood mutual information
CN108764749A (en) A kind of 3I strategy process for preferably depositing evaluation suitable for grain storage
CN115374106A (en) Intelligent data grading method based on knowledge graph technology
CN109934681A (en) The recommended method of user&#39;s commodity interested
Kumar et al. A Novel Cluster Analysis-Based Crop Dataset Recommendation Method in Precision Farming.
CN109034462A (en) Maize population cropping pattern optimization method and device
Bijanzadeh et al. Determining the most important features contributing to wheat grain yield using supervised feature selection model
Vanarase et al. Crop Prediction Using Data Mining and Machine Learning Techniques

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