CN113610455B - System and method for dialing engineering machinery fittings - Google Patents
System and method for dialing engineering machinery fittings Download PDFInfo
- Publication number
- CN113610455B CN113610455B CN202110760582.3A CN202110760582A CN113610455B CN 113610455 B CN113610455 B CN 113610455B CN 202110760582 A CN202110760582 A CN 202110760582A CN 113610455 B CN113610455 B CN 113610455B
- Authority
- CN
- China
- Prior art keywords
- warehouse
- data
- inventory
- module
- allocation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000013178 mathematical model Methods 0.000 claims abstract description 70
- 239000011159 matrix material Substances 0.000 claims abstract description 65
- 238000007781 pre-processing Methods 0.000 claims abstract description 42
- 238000013500 data storage Methods 0.000 claims abstract description 36
- 238000012546 transfer Methods 0.000 claims abstract description 23
- 238000004891 communication Methods 0.000 claims abstract description 21
- 238000005457 optimization Methods 0.000 claims description 30
- 238000010801 machine learning Methods 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 abstract description 6
- 238000012216 screening Methods 0.000 description 7
- 238000009826 distribution Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000013439 planning Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012384 transportation and delivery Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a system and a method for allocating engineering machinery accessories. The system comprises: the data preprocessing module is configured to acquire inventory data of each warehouse and integrate the inventory data to be converted into a mathematical matrix; the accessory allocation module is in communication connection with the data preprocessing module and is configured to determine allocation schemes among the warehouses according to the mathematical matrix and the constructed mathematical model; the data storage module is in communication connection with the data preprocessing module and the accessory transferring module and is configured to store data information of the data preprocessing module and the accessory transferring module; the accessory transfer billboard module is in communication connection with the data storage module and is configured to display data information of the data preprocessing module and the accessory transfer module. The invention saves the total cost of the allocation of engineering machinery accessories and reduces the dead stock rate; and also improves the maintenance efficiency of warehouse inventory.
Description
Technical Field
The invention relates to the technical field of engineering machinery, in particular to a system and a method for allocating engineering machinery accessories.
Background
The accessory demand of the engineering machinery industry mainly depends on maintenance and repair of a corresponding host machine, and because the host machine greatly influences the construction period of a customer when the host machine is out of plan, and additional economic loss is brought, the accessory demand has the characteristics of urgent time, multiple varieties, small single material demand and the like, most materials cannot form stable logistics, so that stock sites are seriously stagnated, and accessories are not circulated. In the prior art, the dispatching of the engineering machinery accessories is not carried out for mutual dispatching of be stationed or assigned abroad warehouses, and when monthly stock preparation work is carried out, all warehouse requirements are delivered out through a total warehouse, and dispatching orders are generated. This tends to result in a large amount of material becoming overstocked in one portion be stationed or assigned abroad of the warehouse and another portion of the warehouse being out of stock, resulting in higher procurement and shipping costs.
Disclosure of Invention
The invention aims to provide a system and a method for allocating engineering machinery accessories, which are used for solving the problems of higher purchasing cost and transportation cost of scheduling of engineering machinery accessories in the prior art.
To achieve the above object, a first aspect of the present invention provides a system for allocating work machine accessories, the system comprising:
the data preprocessing module is configured to acquire inventory data of each warehouse and integrate the inventory data to be converted into a mathematical matrix;
The accessory allocation module is in communication connection with the data preprocessing module and is configured to determine allocation schemes among the warehouses according to the mathematical matrix and the constructed mathematical model;
the data storage module is in communication connection with the data preprocessing module and the accessory transferring module and is configured to store data information of the data preprocessing module and the accessory transferring module;
the accessory transfer billboard module is in communication connection with the data storage module and is configured to display data information of the data preprocessing module and the accessory transfer module.
In an embodiment of the present invention, the data preprocessing module includes:
A data acquisition sub-module configured to determine inventory data from the safety inventory, the machine learning forecast inventory, and the existing inventory of each warehouse;
The data cleaning sub-module is configured to screen and clean the inventory data to obtain scheduling data of the allocation warehouse;
A matrixing submodule configured to convert the scheduling data into a mathematical matrix.
In an embodiment of the invention, the data cleansing sub-module is configured to:
determining an allocation warehouse and allocation accessories corresponding to the allocation warehouse according to the inventory data of each warehouse;
and screening the transportation distance between the allocation warehouses, the weight of the allocation accessories and the purchase price to obtain an allocation data table.
In an embodiment of the present invention, an accessory deployment module includes:
a mathematical modeling sub-module configured to construct a mathematical model for determining an allocation scheme;
an allocation calculation sub-module configured to determine an allocation scheme from the mathematical matrix and the mathematical model.
In an embodiment of the invention, the mathematical model satisfies the following formula:
argminf＝∑i,j,ks·(xijkzk)dij+∑j,kpkx1jk；
Wherein i represents the ith warehouse, j represents the jth warehouse, and i=1 represent the total warehouse; k represents a fitting; z ijk represents the weight of the fitting k; x ijk represents the number of accessories k (non-negative integers) transferred from warehouse i to warehouse j; d ij denotes the distance from warehouse i to warehouse j; s represents the transport cost per unit weight and distance; q ik represents the redundant inventory of parts k in warehouse i; m jk represents the stock quantity of the parts k out of stock in warehouse j; p k represents the purchase cost of fitting k.
In an embodiment of the invention, the dial computation sub-module is configured to:
inputting the mathematical matrix into a mathematical model to obtain a result matrix;
Converting the result matrix into a corresponding allocation schedule;
The allocation schedule comprises an allocation warehouse, accessory models and allocation quantity.
In an embodiment of the invention, a data storage module includes:
A source data storage sub-module configured to store inventory data for each warehouse;
a result data storage sub-module configured to store the reconciliation data for each warehouse;
a model optimization sub-module configured to store parameter data of the mathematical model.
In an embodiment of the present invention, an inventory transfer sign module includes:
The inventory state board watching sub-module is configured to display the data information of the data preprocessing sub-module;
the transfer state board viewing sub-module is configured to display data information of the accessory transfer module.
A second aspect of the present invention provides a method for deploying an engineering machine tool accessory, the method comprising:
Determining inventory data based on the safety inventory, machine learning forecast inventory, and on-hand inventory of each warehouse;
Screening and cleaning the inventory data to obtain scheduling data of the allocation warehouse;
Converting the scheduling data into a mathematical matrix;
and determining an allocation scheme among all warehouses according to the mathematical matrix and the constructed mathematical model.
In an embodiment of the present invention, determining an allocation scheme between warehouses according to a mathematical matrix and a constructed mathematical model includes:
Constructing a mathematical model for determining an allocation scheme;
inputting the mathematical matrix into a mathematical model to obtain a result matrix;
Converting the result matrix into a corresponding allocation schedule;
The allocation schedule comprises an allocation warehouse, accessory models and allocation quantity.
According to the technical scheme, the data preprocessing module and the accessory transferring module are combined with the machine learning predicted value to calculate the accessory inventory, so that the accuracy is improved, the mathematical model is introduced to perform global optimization, the stock shortage inventory is filled through the redundant inventory, the purchasing cost of the accessories is reduced, the total cost is saved, the inventory states of different warehouses and the accessories are balanced by using an automatic method, the stability of warehouse allocation is improved, and the slow inventory rate is reduced; and the data storage module and the accessory transfer board module can timely track the accessory inventory and transfer state information, so that the maintenance efficiency of the warehouse inventory is improved.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate the invention and together with the description serve to explain, without limitation, the invention. In the drawings:
FIG. 1 is a schematic diagram of a system for deploying an engineering machine tool accessory according to one embodiment of the present invention;
FIG. 2 is a schematic diagram of a system for dialing engineering machinery accessories provided in accordance with another embodiment of the present invention;
FIG. 3 is a flow chart of a method for dialing engineering machinery parts provided by an embodiment of the present invention;
fig. 4 is a flow chart of a method for dialing engineering machinery parts according to another embodiment of the present invention.
Detailed Description
The following describes specific embodiments of the present invention in detail with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
It should be noted that, if directional indications (such as up, down, left, right, front, and rear … …) are included in the embodiments of the present invention, the directional indications are merely used to explain the relative positional relationship, movement conditions, etc. between the components in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indications are correspondingly changed.
In addition, if there is a description of "first", "second", etc. in the embodiments of the present application, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present application.
According to the embodiment of the invention, a mathematical model for transferring engineering machinery accessories is combined with machine learning prediction and mixed integer optimization, and an accessory transferring optimization scheme among all warehouses is obtained according to multi-dimensional data such as redundant inventory, stock shortage, distribution distance of all the warehouses and quality, purchase price, sales price and the like of all the types of accessories, so that all the warehouse inventory is updated, accessory inventory gaps are made up, and accessory inventory stagnation is reduced.
Fig. 1 is a schematic diagram of a system for allocating work machine accessories according to an embodiment of the present invention. As shown in fig. 1, the present invention provides a system for dialing engineering machinery accessories, which may include:
A data preprocessing module 1 configured to acquire inventory data of each warehouse and integrate the inventory data to be converted into a mathematical matrix;
the accessory allocation module 2 is in communication connection with the data preprocessing module and is configured to determine allocation schemes among the warehouses according to the mathematical matrix and the constructed mathematical model;
A data storage module 3, which is in communication connection with the data preprocessing module and the accessory transferring module, and is configured to store data information of the data preprocessing module and the accessory transferring module;
The accessory transfer signboard module 4 is in communication connection with the data storage module and is configured to display data information of the data preprocessing module and the accessory transfer module.
In an embodiment of the present invention, a system for transferring a construction machine includes a data preprocessing module 1, an accessory transferring module 2, a data storage module 3, and an accessory transferring signboard module 4. The data preprocessing module 1 is in communication connection with the accessory transferring module 2, the data storage module 3 is in communication connection with the data preprocessing module 1 and the accessory transferring module 2 respectively, and the accessory transferring signboard module 4 is in communication connection with the data storage module 3. The embodiment of the invention can be combined with the machine learning model to predict the inventory data, and compared with the traditional inventory management, the machine learning model can obtain more accurate data, and can utilize the inventory data of products, the sales condition and the distribution condition of a certain node to realize high-precision prediction of the inventory optimization. In one example, inventory data for each accessory of each warehouse of the embodiments of the present invention may be obtained from safety inventory, machine learning forecast inventory, and on-hand inventory. For example, the stock condition of the warehouse is calculated in units of months, and stock data of each accessory=safety stock+machine learning prediction stock-on-hand stock. Among them, a safety stock (also called an insurance stock) is a buffer stock prepared for preventing uncertainty factors of supply or demand of future goods, such as a large number of sudden orders, unexpected interruption or sudden delay of delivery, etc., and its size depends on uncertainty of supply and demand, customer service level (or order satisfaction rate), and stock out cost and stock holding cost. If the customer service level is higher, the safety stock quantity is increased, and the stock-out cost is lower, and the stock holding cost is higher; conversely, if customer service levels are lower, the secure inventory is reduced and results in higher stock out costs and lower inventory holding costs. The existing inventory refers to the available inventory of the material actually deposited by the enterprise in the warehouse, e.g., the existing inventory for a period is equal to the existing inventory for the previous period plus the contemporaneous planned received amount, plus the contemporaneous planned order received amount, and minus the gross demand. After the inventory data of each warehouse is obtained through the calculation formula, whether the inventory data of each warehouse is larger than zero or not is judged. And when the inventory data of the warehouse is smaller than zero, judging the inventory data of the current warehouse as an out-of-stock inventory. After determining the inventory data for each warehouse, the data preprocessing module 1 may also integrate and convert the inventory data into a mathematical matrix to facilitate the input of a mathematical model to determine the deployment scenario. The warehouse which is judged to be the stock with the shortage is a warehouse which needs to allocate accessories from the outside, the warehouse which is judged to be the redundant stock can allocate the accessories to the stock with the shortage, the warehouse and the accessories which participate in allocation can be determined according to the stock data of each accessory in each warehouse, the distance between each warehouse, the weight of the accessory and other data are matched and screened to obtain an allocation data table, and the allocation data table is converted into a mathematical matrix form. The mathematical matrix of the embodiment of the invention can be that the allocation data of the allocation data table is matrixed by representing accessories and warehouses by rows and columns respectively. For example, the first row represents an A fitting, the second row represents a B fitting …, the first column represents warehouse number 1, the second column represents warehouse number 2 …, and so on. In this way, inventory data about the accessories and warehouse are presented in a matrixed form for input to the mathematical model.
In the embodiment of the invention, the mathematical model refers to an operation optimization mathematical model, mathematical modeling is carried out on an accessory allocation plan, the accessory allocation plan is converted into a mixed integer planning problem, and the accessory allocation mathematical model is constructed by using an allocation cost minimization optimization target. Combining the mathematical matrix and the mathematical model obtained by the data preprocessing module 1, the fitting allocation scheme between each warehouse can be obtained. The mixed integer programming algorithm integrates solving algorithms such as an accurate algorithm (a cut plane method, a branch-and-bound method), an approximation algorithm, a heuristic algorithm and the like. And inputting warehouse and accessory data into a mathematical model in the form of a mathematical matrix for operation so as to obtain an optimization result. The result obtained by the mathematical model is also a matrix model, so that the matrix result also needs to be converted, and the result solved by the mixed integer programming algorithm is converted into an accessory allocation schedule containing information data such as an allocation warehouse, accessory models, allocation quantity and the like. According to the embodiment of the invention, the machine learning predicted value is combined to calculate the accessory inventory, so that the accuracy is improved, the mathematical model is introduced to perform global optimization, the stock shortage is filled through the redundant inventory, the purchasing cost of the accessories is reduced, the total cost is saved, the automatic method is used for balancing the inventory states of different warehouses and accessories, the stock allocation stability of the warehouses is improved, and the dead stock rate is reduced.
In an embodiment of the present invention, the data storage module 3 is communicatively connected to the data preprocessing module 1 and the accessory deployment module 2, and may store data of the data preprocessing module 1 and the accessory deployment module 2, such as source data, result data, and model optimization data. The source data is data such as safety stock of each warehouse, machine learning pre-stored stock, actual stock, distribution distance between each warehouse, weight of accessories, purchase price and the like; the result data is accessory data participated in the allocation of each warehouse; the model optimization data is data such as model paths, model index data, model reference data and the like. The accessory transfer signboard module 4 is also in communication connection with the data storage module 3, and can view the data stored in the data storage module 3, for example, the accessory inventory data is subjected to visual processing, and the inventory condition is displayed by taking a warehouse as a unit; and displaying the execution conditions such as the completion progress of the accessory allocation scheme, allocation cost and the like. According to the embodiment of the invention, the data storage module 3 and the accessory transfer billboard module 4 can timely track the accessory inventory and transfer state information, so that the maintenance efficiency of the warehouse inventory is improved.
Fig. 2 is a schematic structural diagram of a system for dialing engineering machinery parts according to another embodiment of the present invention. As shown in fig. 2, the data preprocessing module 1 may include:
a data acquisition sub-module 11 configured to determine inventory data from the safety inventory, machine learning forecast inventory, and on-hand inventory of each warehouse;
a data cleansing sub-module 12 configured to screen and cleanse inventory data to obtain dispatch data for the reconciliation warehouse;
A matrixing sub-module 13 configured to convert the scheduling data into a mathematical matrix.
In an embodiment of the present invention, inventory data for each accessory of each warehouse may be obtained through safety inventory, machine learning forecast inventory, and on-hand inventory. For example, the stock condition of the warehouse is calculated in units of months, and stock data of each accessory=safety stock+machine learning prediction stock-on-hand stock. Among them, a safety stock (also called an insurance stock) is a buffer stock prepared for preventing uncertainty factors of supply or demand of future goods, such as a large number of sudden orders, unexpected interruption or sudden delay of delivery, etc., and its size depends on uncertainty of supply and demand, customer service level (or order satisfaction rate), and stock out cost and stock holding cost. If the customer service level is higher, the safety stock quantity is increased, and the stock-out cost is lower, and the stock holding cost is higher; conversely, if customer service levels are lower, the secure inventory is reduced and results in higher stock out costs and lower inventory holding costs. The existing inventory refers to the available inventory of the material actually deposited by the enterprise in the warehouse, e.g., the existing inventory for a period is equal to the existing inventory for the previous period plus the contemporaneous planned received amount, plus the contemporaneous planned order received amount, and minus the gross demand. After the inventory data of each warehouse is obtained through the calculation formula, whether the inventory data of each warehouse is larger than zero or not is judged. And when the inventory data of the warehouse is smaller than zero, judging the inventory data of the current warehouse as an out-of-stock inventory.
In embodiments of the present invention, the planned inventory data may deviate from the actual inventory data acquired, and thus the data cleansing sub-module 12 may cleansing and sift through the inventory data. For example, warehouse No. 1, part a is out of stock, but part a is not required for this month, so part B inventory data required for this month can be screened and washed out.
In one example, the data cleansing sub-module 12 may be configured to:
determining an allocation warehouse and allocation accessories corresponding to the allocation warehouse according to the inventory data of each warehouse;
and screening the transportation distance between the allocation warehouses, the weight of the allocation accessories and the purchase price to obtain an allocation data table.
Specifically, the warehouse determined as the stock shortage is a warehouse which needs to allocate accessories from the outside, the warehouse determined as the redundant stock can allocate accessories to the stock shortage, the warehouse and the accessories participating in allocation can be determined according to the stock data of each accessory in each warehouse, the data such as the distance between each warehouse and the weight of the accessory are matched and screened to obtain an allocation data table, and the allocation data table is converted into a mathematical matrix form. All warehouse and accessory data which can participate in allocation can be determined according to the stock shortage and the redundant stock, data such as the transportation distance between allocation warehouses and the weight of allocation accessories are screened out, and finally the matrixing submodule 3 matrices allocation data of the allocation data table by representing the accessories and warehouses by rows and columns respectively. For example, the first row represents an A fitting, the second row represents a B fitting …, the first column represents warehouse number 1, the second column represents warehouse number 2 …, and so on. In this way, inventory data about the accessories and warehouse are presented in a matrixed form for input to the mathematical model. In this way, inventory data about the accessories and warehouse are presented in a matrixed form for input to the mathematical model.
As shown in fig. 2, in an embodiment of the present invention, the accessory deployment module 2 may include:
a mathematical modeling sub-module 21 configured to construct a mathematical model for determining an allocation scheme;
the allocation calculation sub-module 22 is configured to determine an allocation scheme from the mathematical matrix and the mathematical model.
In the embodiment of the invention, the mathematical model refers to an operation optimization mathematical model, mathematical modeling is carried out on an accessory allocation plan, the accessory allocation plan is converted into a mixed integer planning problem, and the accessory allocation mathematical model is constructed by using an allocation cost minimization optimization target. Combining the mathematical matrix and the mathematical model obtained by the data preprocessing module 1, the fitting allocation scheme between each warehouse can be obtained. The mixed integer programming algorithm integrates solving algorithms such as an accurate algorithm (a cut plane method, a branch-and-bound method), an approximation algorithm, a heuristic algorithm and the like. And inputting warehouse and accessory data into a mathematical model in the form of a mathematical matrix for operation so as to obtain an optimization result. The result obtained by the mathematical model is also a matrix model, so that the matrix result also needs to be converted, and the result solved by the mixed integer programming algorithm is converted into an accessory allocation schedule containing information data such as an allocation warehouse, accessory models, allocation quantity and the like. According to the embodiment of the invention, the machine learning predicted value is combined to calculate the accessory inventory, so that the accuracy is improved, the mathematical model is introduced to perform global optimization, the stock shortage is filled through the redundant inventory, the purchasing cost of the accessories is reduced, the total cost is saved, the automatic method is used for balancing the inventory states of different warehouses and accessories, the stock allocation stability of the warehouses is improved, and the dead stock rate is reduced.
In an embodiment of the present invention, the mathematical model may satisfy the following formula:
argminf＝∑i,j,ks.(xijkzk)dij+∑j,kpkx1jk；
Wherein i represents the ith warehouse, j represents the jth warehouse, and i=1 represent the total warehouse; k represents a fitting; z ijk represents the weight of the fitting k; x ijk represents the number of accessories k (non-negative integers) transferred from warehouse i to warehouse j; d ij denotes the distance from warehouse i to warehouse j; s represents the transport cost per unit weight and distance; q ik represents the redundant inventory of parts k in warehouse i; m jk represents the stock quantity of the parts k out of stock in warehouse j; p k represents the purchase cost of fitting k.
It should be noted that the mathematical model of the embodiment of the present invention is not limited to the above formula, but may be other mathematical models capable of performing operation optimization.
In an embodiment of the present invention, the dial computation sub-module 22 may be configured to:
inputting the mathematical matrix into a mathematical model to obtain a result matrix;
Converting the result matrix into a corresponding allocation schedule;
The allocation schedule comprises an allocation warehouse, accessory models and allocation quantity.
Specifically, warehouse and fitting data are input into a mathematical model in the form of a mathematical matrix to be operated so as to obtain an optimization result. The result obtained by the mathematical model is also a matrix model, so that the matrix result also needs to be converted, and the result solved by the mixed integer programming algorithm is converted into an accessory allocation schedule containing information data such as an allocation warehouse, accessory models, allocation quantity and the like.
As shown in fig. 2, in an embodiment of the present invention, the data storage module 3 may include:
a source data storage sub-module 31 configured to store inventory data for each warehouse;
a result data storage sub-module 32 configured to store the reconciliation data for each warehouse;
the model optimization sub-module 33 is configured to store parameter data of the mathematical model.
In an embodiment of the present invention, the data storage module 3 is communicatively connected to the data preprocessing module 1 and the accessory deployment module 2, and may store data of the data preprocessing module 1 and the accessory deployment module 2, such as source data, result data, and model optimization data. The source data is data such as safety stock of each warehouse, machine learning pre-stored stock, actual stock, distribution distance between each warehouse, weight of accessories, purchase price and the like; the result data is accessory data participated in the allocation of each warehouse; the model optimization data is data such as model paths, model index data, model reference data and the like.
As shown in fig. 2, in an embodiment of the present invention, the inventory transfer bulletin module 4 may include:
an inventory status viewing sub-module 41 configured to display data information of the data preprocessing sub-module;
The dial-up status viewing sub-module 42 is configured to display data information of the accessory dial-up module.
In the embodiment of the invention, the accessory transfer board module 4 is also in communication connection with the data storage module 3, and can view the data stored in the data storage module 3, for example, the accessory inventory data is subjected to visual processing, and the inventory condition is displayed by taking a warehouse as a unit; and displaying the execution conditions such as the completion progress of the accessory allocation scheme, allocation cost and the like. According to the embodiment of the invention, the data storage module 3 and the accessory transfer billboard module 4 can timely track the accessory inventory and transfer state information, so that the maintenance efficiency of the warehouse inventory is improved.
Fig. 3 is a flow chart of a method for allocating an engineering machine tool accessory according to an embodiment of the present invention. As shown in fig. 3, the present invention provides a method for deploying an engineering machine tool accessory, which may include:
Step S31, determining stock data according to the safety stock, the machine learning forecast stock and the existing stock of each warehouse;
Step S32, screening and cleaning the inventory data to obtain scheduling data of a dispatching warehouse;
step S33, converting the scheduling data into a mathematical matrix;
And step S34, determining an allocation scheme among all warehouses according to the mathematical matrix and the constructed mathematical model.
The method for allocating engineering machine fittings in the embodiment of the invention is applied to the system for allocating engineering machine fittings, and the system comprises a data preprocessing module, a fitting allocation module, a data storage module and a fitting allocation billboard module. The data preprocessing module is in communication connection with the accessory transferring module, the data storage module is in communication connection with the data preprocessing module and the accessory transferring module respectively, and the accessory transferring board module is in communication connection with the data storage module. The embodiment of the invention can be combined with the machine learning model to predict the inventory data, and compared with the traditional inventory management, the machine learning model can obtain more accurate data, and can utilize the inventory data of products, the sales condition and the distribution condition of a certain node to realize high-precision prediction of the inventory optimization. In one example, inventory data for each accessory of each warehouse of the embodiments of the present invention may be obtained from safety inventory, machine learning forecast inventory, and on-hand inventory. For example, the stock condition of the warehouse is calculated in units of months, and stock data of each accessory=safety stock+machine learning prediction stock-on-hand stock. Among them, a safety stock (also called an insurance stock) is a buffer stock prepared for preventing uncertainty factors of supply or demand of future goods, such as a large number of sudden orders, unexpected interruption or sudden delay of delivery, etc., and its size depends on uncertainty of supply and demand, customer service level (or order satisfaction rate), and stock out cost and stock holding cost. If the customer service level is higher, the safety stock quantity is increased, and the stock-out cost is lower, and the stock holding cost is higher; conversely, if customer service levels are lower, the secure inventory is reduced and results in higher stock out costs and lower inventory holding costs. The existing inventory refers to the available inventory of the material actually deposited by the enterprise in the warehouse, e.g., the existing inventory for a period is equal to the existing inventory for the previous period plus the contemporaneous planned received amount, plus the contemporaneous planned order received amount, and minus the gross demand. After the inventory data of each warehouse is obtained through the calculation formula, whether the inventory data of each warehouse is larger than zero or not is judged. And when the inventory data of the warehouse is smaller than zero, judging the inventory data of the current warehouse as an out-of-stock inventory.
In embodiments of the present invention, the planned inventory data may deviate from the actual inventory data obtained, and thus the inventory data may also be cleaned and screened. For example, warehouse No. 1, part a is out of stock, but part a is not required for this month, so part B inventory data required for this month can be screened and washed out. In one example, screening and cleaning inventory data to obtain dispatch data for an inventory warehouse may include: determining an allocation warehouse and allocation accessories corresponding to the allocation warehouse according to the inventory data of each warehouse; and screening the transportation distance between the allocation warehouses, the weight of the allocation accessories and the purchase price to obtain an allocation data table.
After the stock data of each warehouse is determined through data cleaning and screening, the stock data can be integrated and converted into a mathematical matrix so as to be convenient for inputting a mathematical model to determine an allocation scheme. The warehouse which is judged to be the stock with the shortage is a warehouse which needs to allocate accessories from the outside, the warehouse which is judged to be the redundant stock can allocate the accessories to the stock with the shortage, the warehouse and the accessories which participate in allocation can be determined according to the stock data of each accessory in each warehouse, the distance between each warehouse, the weight of the accessory and other data are matched and screened to obtain an allocation data table, and the allocation data table is converted into a mathematical matrix form. The mathematical matrix of the embodiment of the invention can be that the allocation data of the allocation data table is matrixed by representing accessories and warehouses by rows and columns respectively. For example, the first row represents an A fitting, the second row represents a B fitting …, the first column represents warehouse number 1, the second column represents warehouse number 2 …, and so on. In this way, inventory data about the accessories and warehouse are presented in a matrixed form for input to the mathematical model.
In the embodiment of the invention, the mathematical model refers to an operation optimization mathematical model, mathematical modeling is carried out on an accessory allocation plan, the accessory allocation plan is converted into a mixed integer planning problem, and the accessory allocation mathematical model is constructed by using an allocation cost minimization optimization target. Combining the mathematical matrix and the mathematical model, an accessory allocation scheme between each warehouse can be obtained. The mixed integer programming algorithm integrates solving algorithms such as an accurate algorithm (a cut plane method, a branch-and-bound method), an approximation algorithm, a heuristic algorithm and the like. And inputting warehouse and accessory data into a mathematical model in the form of a mathematical matrix for operation so as to obtain an optimization result. The result obtained by the mathematical model is also a matrix model, so that the matrix result also needs to be converted, and the result solved by the mixed integer programming algorithm is converted into an accessory allocation schedule containing information data such as an allocation warehouse, accessory models, allocation quantity and the like. According to the embodiment of the invention, the machine learning predicted value is combined to calculate the accessory inventory, so that the accuracy is improved, the mathematical model is introduced to perform global optimization, the stock shortage is filled through the redundant inventory, the purchasing cost of the accessories is reduced, the total cost is saved, the automatic method is used for balancing the inventory states of different warehouses and accessories, the stock allocation stability of the warehouses is improved, and the dead stock rate is reduced.
Fig. 4 is a flow chart of a method for dialing engineering machinery parts according to another embodiment of the present invention. As shown in fig. 4, step S34, determining an allocation scheme between warehouses according to the mathematical matrix and the constructed mathematical model includes:
step S41, constructing a mathematical model for determining an allocation scheme;
Step S42, inputting the mathematical matrix into a mathematical model to obtain a result matrix;
Step S43, converting the result matrix into a corresponding allocation schedule;
The allocation schedule comprises an allocation warehouse, accessory models and allocation quantity.
In an embodiment of the present invention, the mathematical model may satisfy the following formula:
argminf＝∑i,j,ks·(xijkzk)dij+∑j,kpkx1jk；
Wherein i represents the ith warehouse, j represents the jth warehouse, and i=1 represent the total warehouse; k represents a fitting; z ijk represents the weight of the fitting k; x ijk represents the number of accessories k (non-negative integers) transferred from warehouse i to warehouse j; d ij denotes the distance from warehouse i to warehouse j; s represents the transport cost per unit weight and distance; q ik represents the redundant inventory of parts k in warehouse i; m jk represents the stock quantity of the parts k out of stock in warehouse j; p k represents the purchase cost of fitting k.
It should be noted that the mathematical model of the embodiment of the present invention is not limited to the above formula, but may be other mathematical models capable of performing operation optimization.
In the embodiment of the invention, warehouse and accessory data are input into a mathematical model in the form of a mathematical matrix for operation so as to obtain an optimized result. The result obtained by the mathematical model is also a matrix model, so that the matrix result also needs to be converted, and the result solved by the mixed integer programming algorithm is converted into an accessory allocation schedule containing information data such as an allocation warehouse, accessory models, allocation quantity and the like. In summary, the embodiment of the invention calculates the inventory of the accessories by combining the machine learning predicted value, improves the accuracy, introduces a mathematical model to perform global optimization, fills the stock lacking through the redundant inventory, reduces the purchase cost of the accessories, saves the total cost, balances the inventory states of different warehouses and accessories by using an automatic method, improves the stability of warehouse allocation and reduces the dead stock rate.
In an embodiment of the present invention, the data storage module is communicatively coupled to the data preprocessing module and the accessory deployment module, and may store data of the data preprocessing module and the accessory deployment module, such as source data, result data, and model optimization data. The source data is data such as safety stock of each warehouse, machine learning pre-stored stock, actual stock, distribution distance between each warehouse, weight of accessories, purchase price and the like; the result data is accessory data participated in the allocation of each warehouse; the model optimization data is data such as model paths, model index data, model reference data and the like.
In the embodiment of the invention, the accessory transfer board module is also in communication connection with the data storage module, and can view the data stored by the data storage module, for example, the accessory inventory data is subjected to visual processing, and the inventory condition is displayed by taking a warehouse as a unit; and displaying the execution conditions such as the completion progress of the accessory allocation scheme, allocation cost and the like. According to the embodiment of the invention, the data storage module and the accessory transfer board module can timely track the accessory inventory and transfer state information, so that the maintenance efficiency of the warehouse inventory is improved.
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the specific details of the above embodiments, and various simple modifications can be made to the technical solution of the present invention within the scope of the technical concept of the present invention, and all the simple modifications belong to the protection scope of the present invention.
In addition, the specific features described in the above embodiments may be combined in any suitable manner without contradiction. The various possible combinations of the invention are not described in detail in order to avoid unnecessary repetition.
Moreover, any combination of the various embodiments of the invention can be made without departing from the spirit of the invention, which should also be considered as disclosed herein.
Claims (8)
1. A system for deploying a work machine accessory, the system comprising:
A data preprocessing module, the data preprocessing module comprising: a data acquisition sub-module configured to determine inventory data from the safety inventory, the machine learning forecast inventory, and the on-hand inventory of each warehouse, the inventory data = safety inventory + machine learning forecast inventory-on-hand inventory; the data cleaning sub-module is configured to screen and clean the inventory data to obtain scheduling data of the allocation warehouse; a matrixing submodule configured to convert the scheduling data into a mathematical matrix;
The accessory allocation module is in communication connection with the data preprocessing module and is configured to determine allocation schemes among all warehouses according to the mathematical matrix and the constructed mathematical model;
a data storage module, in communication with the data preprocessing module and the accessory deployment module, configured to store data information of the data preprocessing module and the accessory deployment module;
the accessory transfer billboard module is in communication connection with the data storage module and is configured to display data information of the data preprocessing module and the accessory transfer module;
Wherein the data cleansing sub-module is configured to: determining an allocation warehouse and allocation accessories corresponding to the allocation warehouse according to the inventory data of each warehouse; judging whether the inventory data of each warehouse is greater than zero; when the inventory data of the warehouse is smaller than zero, the inventory data of the current warehouse is judged to be an out-of-stock inventory; the warehouse determined as the stock shortage is a warehouse which needs to allocate accessories from the outside, the warehouse determined as the redundant stock can allocate accessories to the stock shortage, and the warehouse and the accessories which participate in allocation are determined according to the stock data of each accessory in each warehouse, and the distance between each warehouse and the accessory weight data are matched and screened to obtain scheduling data.
2. The system of claim 1, wherein the accessory deployment module comprises:
a mathematical modeling sub-module configured to construct a mathematical model for determining an allocation scheme;
An allocation calculation sub-module configured to determine an allocation scheme from the mathematical matrix and the mathematical model.
3. The system of claim 2, wherein the mathematical model satisfies the following formula:
；
，/>；
，/>；
Wherein i represents the ith warehouse, j represents the jth warehouse, and i=1 represent the total warehouse; k represents a fitting; z k represents the weight of the fitting k; x ijk represents the number of accessories k transferred from warehouse i to warehouse j, x ijk is a non-negative integer; d ij denotes the distance from warehouse i to warehouse j; s represents the transport cost per unit weight and distance; q ik represents the redundant inventory of parts k in warehouse i; m jk represents the stock quantity of the parts k out of stock in warehouse j; p k represents the purchase cost of fitting k; Representing the number of accessories k transferred from the total warehouse to warehouse j,/> Is a non-negative integer; /(I)Representing constraints.
4. The system of claim 3, wherein the dial computation sub-module is configured to:
inputting the mathematical matrix to the mathematical model to obtain a result matrix;
Converting the result matrix into a corresponding allocation schedule;
the allocation schedule comprises an allocation warehouse, accessory models and allocation quantity.
5. The system of claim 1, wherein the data storage module comprises:
A source data storage sub-module configured to store inventory data for each warehouse;
a result data storage sub-module configured to store the reconciliation data for each warehouse;
a model optimization sub-module configured to store parameter data of the mathematical model.
6. The system of claim 1, wherein the accessory dial-up sign module comprises:
The inventory state board watching sub-module is configured to display the data information of the data preprocessing sub-module;
and the dialing state board watching sub-module is configured to display the data information of the accessory dialing module.
7. A method for deploying an engineering machine tool accessory, the method comprising:
Determining inventory data according to the safety inventory, the machine learning prediction inventory and the existing inventory of each warehouse, wherein the inventory data is formed by the steps of safety inventory and machine learning prediction inventory; determining an allocation warehouse and allocation accessories corresponding to the allocation warehouse according to the inventory data of each warehouse; judging whether the inventory data of each warehouse is greater than zero; when the inventory data of the warehouse is smaller than zero, the inventory data of the current warehouse is judged to be an out-of-stock inventory; the warehouse which is judged to be the stock with the shortage is a warehouse which needs to allocate accessories from the outside, the warehouse which is judged to be the redundant stock can allocate the accessories to the stock with the shortage, the warehouse and the accessories which participate in allocation are determined according to the stock data of each accessory in each warehouse, and the distance between the warehouse and each warehouse and the accessory weight data are matched and screened to obtain scheduling data; converting the scheduling data into a mathematical matrix;
And determining an allocation scheme among all warehouses according to the mathematical matrix and the constructed mathematical model.
8. The method of claim 7, wherein determining an allocation scheme between warehouses based on the mathematical matrix and the constructed mathematical model comprises:
Constructing a mathematical model for determining an allocation scheme;
inputting the mathematical matrix to the mathematical model to obtain a result matrix;
Converting the result matrix into a corresponding allocation schedule;
the allocation schedule comprises an allocation warehouse, accessory models and allocation quantity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110760582.3A CN113610455B (en) | 2021-07-06 | 2021-07-06 | System and method for dialing engineering machinery fittings |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110760582.3A CN113610455B (en) | 2021-07-06 | 2021-07-06 | System and method for dialing engineering machinery fittings |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113610455A CN113610455A (en) | 2021-11-05 |
| CN113610455B true CN113610455B (en) | 2024-05-07 |
Family
ID=78304071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110760582.3A Active CN113610455B (en) | 2021-07-06 | 2021-07-06 | System and method for dialing engineering machinery fittings |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610455B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5450317A (en) * | 1993-11-24 | 1995-09-12 | U S West Advanced Technologies, Inc. | Method and system for optimized logistics planning |
| KR20010084924A (en) * | 2001-04-24 | 2001-09-07 | 김영삼 | An inventory management system and the inventory managing method on the distribution rate |
| EP1215606A1 (en) * | 2000-12-13 | 2002-06-19 | Itt Manufacturing Enterprises, Inc. | Supply management system |
| CN103870943A (en) * | 2012-12-18 | 2014-06-18 | 郝敬方 | Stock management system |
| CN105825354A (en) * | 2016-03-11 | 2016-08-03 | 北京小米移动软件有限公司 | Storage scheduling method and apparatus |
| CN106503869A (en) * | 2016-11-14 | 2017-03-15 | 东南大学 | A kind of public bicycles dynamic dispatching method that is predicted based on website short-term needs |
| JP6186537B1 (en) * | 2017-05-31 | 2017-08-23 | ベンダーサービス株式会社 | Stock management ordering apparatus, stock management ordering method, and program |
| CN107153880A (en) * | 2016-03-02 | 2017-09-12 | 阿里巴巴集团控股有限公司 | One kind allots procurement practice, device and equipment |
| CN107993033A (en) * | 2017-11-14 | 2018-05-04 | 广东电网有限责任公司物流服务中心 | A kind of Power Material Forecasting Methodology |
| CN108985691A (en) * | 2018-07-11 | 2018-12-11 | 北京实派科技有限公司 | A kind of automatic replenishing method and system based on dynamic stock control |
| CN109993484A (en) * | 2019-03-28 | 2019-07-09 | 杭州网易再顾科技有限公司 | Data processing method and system, medium and calculating equipment |
| CN110046755A (en) * | 2019-04-03 | 2019-07-23 | 中国联合网络通信集团有限公司 | Allot the determination method and apparatus in warehouse |
| EP3561749A1 (en) * | 2018-04-26 | 2019-10-30 | Hitachi Transport System, Ltd. | Inventory management apparatus, inventory management method, and storage medium |
| CN111582788A (en) * | 2020-04-29 | 2020-08-25 | 北京小米松果电子有限公司 | Article scheduling method and device and computer readable storage medium |
| KR102210339B1 (en) * | 2020-09-18 | 2021-02-01 | 주식회사 티비오헬스케어 | Hospital integrated logistics management system using ai technology and hospital integrated logistics management method using the same |
| CN112884404A (en) * | 2021-02-08 | 2021-06-01 | 中国科学技术大学 | Intelligent supply chain inventory transfer optimization and transaction early warning system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140278713A1 (en) * | 2013-03-15 | 2014-09-18 | Oracle International Corporation | Asset forecasting in asset intensive enterprises |
-
2021
- 2021-07-06 CN CN202110760582.3A patent/CN113610455B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5450317A (en) * | 1993-11-24 | 1995-09-12 | U S West Advanced Technologies, Inc. | Method and system for optimized logistics planning |
| EP1215606A1 (en) * | 2000-12-13 | 2002-06-19 | Itt Manufacturing Enterprises, Inc. | Supply management system |
| KR20010084924A (en) * | 2001-04-24 | 2001-09-07 | 김영삼 | An inventory management system and the inventory managing method on the distribution rate |
| CN103870943A (en) * | 2012-12-18 | 2014-06-18 | 郝敬方 | Stock management system |
| CN107153880A (en) * | 2016-03-02 | 2017-09-12 | 阿里巴巴集团控股有限公司 | One kind allots procurement practice, device and equipment |
| CN105825354A (en) * | 2016-03-11 | 2016-08-03 | 北京小米移动软件有限公司 | Storage scheduling method and apparatus |
| CN106503869A (en) * | 2016-11-14 | 2017-03-15 | 东南大学 | A kind of public bicycles dynamic dispatching method that is predicted based on website short-term needs |
| JP6186537B1 (en) * | 2017-05-31 | 2017-08-23 | ベンダーサービス株式会社 | Stock management ordering apparatus, stock management ordering method, and program |
| CN107993033A (en) * | 2017-11-14 | 2018-05-04 | 广东电网有限责任公司物流服务中心 | A kind of Power Material Forecasting Methodology |
| EP3561749A1 (en) * | 2018-04-26 | 2019-10-30 | Hitachi Transport System, Ltd. | Inventory management apparatus, inventory management method, and storage medium |
| CN108985691A (en) * | 2018-07-11 | 2018-12-11 | 北京实派科技有限公司 | A kind of automatic replenishing method and system based on dynamic stock control |
| CN109993484A (en) * | 2019-03-28 | 2019-07-09 | 杭州网易再顾科技有限公司 | Data processing method and system, medium and calculating equipment |
| CN110046755A (en) * | 2019-04-03 | 2019-07-23 | 中国联合网络通信集团有限公司 | Allot the determination method and apparatus in warehouse |
| CN111582788A (en) * | 2020-04-29 | 2020-08-25 | 北京小米松果电子有限公司 | Article scheduling method and device and computer readable storage medium |
| KR102210339B1 (en) * | 2020-09-18 | 2021-02-01 | 주식회사 티비오헬스케어 | Hospital integrated logistics management system using ai technology and hospital integrated logistics management method using the same |
| CN112884404A (en) * | 2021-02-08 | 2021-06-01 | 中国科学技术大学 | Intelligent supply chain inventory transfer optimization and transaction early warning system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113610455A (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Marchwinski et al. | Lean lexicon: a graphical glossary for lean thinkers | |
| US20150109287A1 (en) | Method and system for supply chain network sensitivity analysis and presentation | |
| Ramaa et al. | Impact of warehouse management system in a supply chain | |
| US5450317A (en) | Method and system for optimized logistics planning | |
| US20130018696A1 (en) | Supply Chain Analysis | |
| Shook et al. | Lean Lexicon: a graphical glossary for Lean Thinkers | |
| CN103460229A (en) | System and method for closed loop purchase order compliance management | |
| US20160300169A1 (en) | Supply chain network sensitivity analysis using adjusted network parameters | |
| Porter | Operations management | |
| Flanagan et al. | A Bridge to the Future: Profitable Construction for Tomorrow's Industry and it [ie It's] Customers | |
| Jiraruttrakul | Applying an EQQ model to reduce inventory cost | |
| CN113610455B (en) | System and method for dialing engineering machinery fittings | |
| Tapping et al. | The Lean Pocket Guide: Tools for the Elimination of Waste!. | |
| CN117910615A (en) | Method and system for processing raw material inventory prediction data of steel processing distribution center | |
| US20160300173A1 (en) | Oscillation detection and reduction in supply chain | |
| Goyal et al. | Impact of warehouse management system in a supply chain | |
| Raafat et al. | Warehouse and distribution operations improvements: a case study | |
| US20090083166A1 (en) | Supporting Chargeable Subcontracting When Outsourcing Manufacturing Of An Assembled Unit While Supplying Components | |
| Pannekoek | Provide insights and improve the Poland material flow | |
| Groenteman et al. | Inventory management and facility layout design for AXEL Americas | |
| Kennedy et al. | Lean synchronous manufacturing ‘Hard-wiring’production to demand | |
| Naraharisetti et al. | Capacity management in the chemical supply chain | |
| Reimers | GEARBOX (China) Ltd.: will the company's ERP system support its ambitious growth strategy? | |
| JP2005352993A (en) | Production planning support system and production planning support method | |
| Cimorelli et al. | Control of production and materials |
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 |