CN110147975A - Parts Inventory control method and device - Google Patents

Parts Inventory control method and device Download PDF

Info

Publication number
CN110147975A
CN110147975A CN201910433129.4A CN201910433129A CN110147975A CN 110147975 A CN110147975 A CN 110147975A CN 201910433129 A CN201910433129 A CN 201910433129A CN 110147975 A CN110147975 A CN 110147975A
Authority
CN
China
Prior art keywords
spare part
type
continuous
order
insignificant
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910433129.4A
Other languages
Chinese (zh)
Inventor
齐红梅
王炀
李鹏
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.)
Beijing Runke General Technology Co Ltd
Original Assignee
Beijing Runke General Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Runke General Technology Co Ltd filed Critical Beijing Runke General Technology Co Ltd
Priority to CN201910433129.4A priority Critical patent/CN110147975A/en
Publication of CN110147975A publication Critical patent/CN110147975A/en
Pending legal-status Critical Current

Links

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
    • 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
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present invention provides a kind of Parts Inventory control method and device, the method is applied to the controlling terminal of control Parts Inventory, comprising: determines spare part classification belonging to spare part；Determine Strategy of Inventory Control corresponding with the spare part classification；Judge whether the spare part is out of stock by the Strategy of Inventory Control, is calculated if the spare part shortage of goods by the Strategy of Inventory Control and export size of order.The present invention uses different Strategy of Inventory Control for different spare part classifications, it may be implemented targetedly to determine spare part out of stock, and specific aim calculates size of order to be supplemented, so as to control large-scale spare parts warehouse spare part amount under conditions of meeting requirement in the reasonable scope.

Description

Parts Inventory control method and device
Technical field
This application involves automation inventory's technical field more particularly to Parts Inventory control method and device.
Background technique
It can store variety classes article in large-scale spare parts warehouse.In order to rationally manage large-scale spare parts warehouse, it will usually Storage controlling is carried out to spare part.At present for the storage controlling of large-scale spare parts warehouse mainly when finding that spare part storage is insufficient just It is supplemented, and, different spare parts use identical Strategy of Inventory Control.
Since the replacement frequency of different spare parts is different, so different spare parts use same Strategy of Inventory Control, one will cause A little part warehouse storage deficiencies can not provide spare part for product, other Parts Inventories overstock and occupy larger inventory space and cost, Cause stability and the utilization rate of large-scale spare parts warehouse lower.
Summary of the invention
In consideration of it, the application provides Parts Inventory control method and device, can be adapted to based on the setting of spare part generic Strategy of Inventory Control, so as to improve the stability utilization rate of large-scale spare parts warehouse.
This application provides following technical characteristics to achieve the goals above:
A kind of Parts Inventory control method, the controlling terminal applied to control Parts Inventory, which comprises
Determine spare part classification belonging to spare part；
Determine Strategy of Inventory Control corresponding with the spare part classification；
Judge whether the spare part is out of stock by the Strategy of Inventory Control, presses the storage controlling if the spare part shortage of goods Policy calculation simultaneously exports size of order.
Optionally, the spare part classification is that continuous important type, continuous insignificant type, the important type of interval or interval are insignificant Type.
Optionally, described to judge whether the spare part is out of stock by the Strategy of Inventory Control, it is pressed if the spare part shortage of goods The Strategy of Inventory Control calculates and exports size of order, comprising:
If the spare part classification is continuous important type, it is determined that the quantity in stock of the spare part, if the quantity in stock is less than first Numerical value is then calculated by the first formula and exports the first size of order；
If the spare part classification is continuous insignificant type, it is determined that the quantity in stock of the spare part, if the quantity in stock is less than the Two numerical value are then calculated by the second formula and export the second size of order；
If the spare part classification is the important type of interval, it is determined that the forecast consumption amount of the spare part, if the forecast consumption Amount is greater than third value, then calculates by third formula and export third size of order；
If the spare part classification is the insignificant type of interval, temporally variable determines the quantity in stock of the spare part, if the library Storage is then calculated by the 4th formula less than the 4th numerical value and exports the 4th size of order.
Optionally, first numerical value is calculated using following formula: S1=ss+d × L1,Wherein, S1For First numerical value, ss are safety stock needed for the continuous important type spare part, d is using the described of predicting strategy prediction Continuous important type spare part day's expenditure, δ1Deviation, L for the continuous important type spare parts consumption amount1It is standby for the continuous important type Part Ordering Lead Time, μ1For the continuous important type spare part safety coefficient；
The second value is calculated using following formula: S2=(L2+1)D2+μ2×δ2×(L2+1)；Wherein, S2It is described Second value, L2For the continuous insignificant type spare part order time in advance, D2For using the described continuous non-heavy of predicting strategy prediction Want type spare part annual consumption, μ2For the continuous insignificant type spare part safety coefficient, δ2For the continuous insignificant type spare parts consumption The deviation of amount；
The third value S3It is 0；
The time variable is calculated using exponential smoothing, calculation formula is as follows:
Wherein, ti+1Indicate the duration of the time variable in i+1 period, tiIndicate the duration of i cycle time variable, diIt is The actual consumption amount of the insignificant type spare part of interval in i-th period, β is smoothing constant, 0≤β≤1；4th numerical value is adopted It is calculated with following formula:
Wherein, S4For the 4th numerical value,It is ti+L4The consumption of the insignificant type spare part prediction of interval in period The average value of amount, μ4It is the insignificant type spare part safety coefficient of the interval, L4It is that the insignificant type spare parts purchasing of the interval shifts to an earlier date Phase.
Optionally, described that the first size of order is calculated and exported by the first formula, including the use of the first formula It calculates and exports the first size of order Q1；Wherein D1Indicate the annual consumption for the continuous important type spare part that prediction obtains, C1 Indicate the single Order Cost of the continuous important type spare part；H1Indicate the cost of the continuous important type spare part year storage；
It is described to be calculated by the second formula and export the second size of order, comprising: to utilize the second formulaIt calculates And export the second size of order Q2；Wherein D2Indicate the annual consumption for the continuous insignificant type spare part that prediction obtains, C2Table Show the continuous insignificant type spare part single Order Cost；H2Indicate the continuous insignificant type unit spare part year storage at This；
It is described to be calculated by third formula and export third size of order, comprising: will periodically to determine the important type spare part of batch-type Forecast consumption amount as the third size of order, export the third size of order；
It is described to be calculated by the 4th formula and export the 4th size of order, comprising: the 4th numerical value and the interval is non-heavy The difference for wanting the quantity in stock of type spare part is determined as the 4th size of order, exports the 4th size of order.
Optionally, further includes:
The continuous important type spare part annual consumption D is predicted using spare parts consumption amount historical data1；
The continuous insignificant type spare part annual consumption D is predicted using RBF neural method2；
Using the WLS-SVM model optimized based on APSO, the forecast consumption of the important type spare part of interval described in cyclic forecast Amount；
It determines that consumption is distributed by the insignificant type spare parts consumption amount historical data of the interval, and is based on Croston mould Type predicts the forecast consumption amount of the insignificant type spare part of the interval.
Optionally, described to determine that consumption is distributed by the insignificant type spare parts consumption amount historical data of the interval, and base The forecast consumption amount of the insignificant type spare part of interval described in Croston model prediction, comprising: using described in exponential smoothing prediction The intermittently forecast consumption amount of insignificant type spare part；
Wherein, α is smoothing constant, 0≤α≤1；Ri+1It is the insignificant type spare part of interval in i+1 time variable Forecast consumption amount；RiIt is the forecast consumption amount of the insignificant type spare part of interval in i-th of time variable；diIt is to become i-th of time The actual consumption amount of the insignificant type spare part of interval in amount.
A kind of Parts Inventory control device, applied to the controlling terminal of control Parts Inventory, described device includes:
Class location is determined, for determining spare part classification belonging to spare part；
Policy unit is determined, for determining Strategy of Inventory Control corresponding with the spare part classification；
Output unit is calculated, for judging whether the spare part is out of stock by the Strategy of Inventory Control, if the spare part lacks Goods is then calculated by the Strategy of Inventory Control and exports size of order.
Optionally, the spare part classification is that continuous important type, continuous insignificant type, the important type of interval or interval are insignificant Type.
Optionally, the calculating output unit, comprising:
If the spare part classification is continuous important type, it is determined that the quantity in stock of the spare part, if the quantity in stock is less than first Numerical value is then calculated by the first formula and exports the first size of order；
If the spare part classification is continuous insignificant type, it is determined that the quantity in stock of the spare part, if the quantity in stock is less than the Two numerical value are then calculated by the second formula and export the second size of order；
If the spare part classification is the important type of interval, it is determined that the forecast consumption amount of the spare part, if the forecast consumption Amount is greater than third value, then calculates by third formula and export third size of order；
If the spare part classification is the insignificant type of interval, temporally variable determines the quantity in stock of the spare part, if the library Storage is then calculated by the 4th formula less than the 4th numerical value and exports the 4th size of order.
By the above technological means, may be implemented it is following the utility model has the advantages that
The application, which provides, can determine spare part classification belonging to spare part in technical solution, and determine inventory's control of spare part classification System strategy, to make different types of spare part using different Strategy of Inventory Control.Based on different Strategy of Inventory Control come Judge whether spare part is out of stock, and is calculated in situation out of stock by different Strategy of Inventory Control and export size of order.
That is, the application uses different Strategy of Inventory Control for different spare part classifications, it is possible to realize targetedly Determine shortage of goods spare part, and specific aim calculates size of order to be supplemented, so as to control under conditions of meeting requirement Make large-scale spare parts warehouse spare part amount in the reasonable scope.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with It obtains other drawings based on these drawings.
Fig. 1 is a kind of pretreatment operation of Parts Inventory control method disclosed in the embodiment of the present application；
Fig. 2 is a kind of flow diagram of Parts Inventory control method disclosed in the embodiment of the present application；
Fig. 3 is a kind of structural schematic diagram of Parts Inventory control device disclosed in the embodiment of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall in the protection scope of this application.
Before introducing Parts Inventory control method, referring to Fig. 1, some pretreatment operations are provided.
Step S101: the spare part classification of each spare part of large size spare parts warehouse is determined.
By taking large-scale spare parts warehouse is weapon system spare parts warehouse as an example, mutually tied using the classification of fast slow flow with ABC classification Weapon system spare parts warehouse is divided into four spare part classifications: continuous type A class namely continuous important type, company by the classification method of conjunction Continuous property BC class namely continuous insignificant type, batch-type A class namely the important type of interval and batch-type BC class namely the insignificant type of interval.
Process can be realized using following:
S1: the spare part criteria for classifying of fast slow flow is set.
Spare part is divided based on sixteen principle strategies, finds out the criteria for classifying of suitable weapon system spare part, Ye Jinian Consumption threshold value.Depending on determining that the process of annual consumption threshold value can be according to different application scene, details are not described herein.
S2: spare part is divided into continuous type set and batch-type set.
The annual consumption of each spare part is obtained, it is if the annual consumption of a spare part is greater than annual consumption threshold value, this is standby Part is divided into fast moving spare parts set namely continuous type；If the annual consumption of a spare part is less than annual consumption threshold value, will be standby Part is divided into Slow Moving Spare Parts set namely batch-type.
S3: it determines and stores spare part type belonging to each spare part.
To fast moving spare parts set and at a slow speed, spare part flowing set is finely divided using ABC classifying rules respectively, and ABC points Rule-like realizes that process is as follows: spare part being arranged by the value height of its deposit, wherein quantity only accounts for backlog total 20% The spare part for controlling and being worth the total inventory finance volume 70% of Zhan is A class spare part；Quantity accounts for backlog total 80% or so and is worth and accounts for about The spare part of total inventory finance volume 30% is BC class spare part.
Fast moving spare parts set is divided into quick A class (namely continuous important type) and BC class according to ABC classifying rules Spare part subset (namely continuous insignificant type), Slow Moving Spare Parts subset division is for A class at a slow speed (namely the important type of interval) and slowly Fast BC class spare part subset (the insignificant type of interval).
Step S102: generating and stores the corresponding relationship of spare part mark and spare part classification.
After determining each spare part corresponding relationship, the spare part mark of each spare part is determined, and construct spare part mark and spare part The corresponding relationship of type stores corresponding relationship, to be used for subsequent use.
According to the application one embodiment, the application provides a kind of Parts Inventory control method, is applied to large-scale spare part storehouse The inventory control devices in library.Since the spare part in large-scale spare parts warehouse is very more, for ease of description, the present embodiment uses one It is described in detail for spare part.
Referring to fig. 2, Parts Inventory control method the following steps are included:
Step S201: according to the corresponding relationship of spare part mark and spare part classification, spare part classification belonging to spare part is determined.
Shown in Figure 1, spare part classification may include continuous important type, continuous insignificant type, the important type of interval and interval Insignificant type；Spare part mark, and the corresponding relationship according to spare part mark and spare part classification are obtained, determines spare part class belonging to spare part Not.
Step S202: Strategy of Inventory Control corresponding with the spare part classification is determined.
If the spare part classification is continuous important type, Strategy of Inventory Control includes: whether the measurement spare part is out of stock First numerical value, and, calculate the first formula of size of order；
If the spare part classification is continuous insignificant type, Strategy of Inventory Control includes: whether the measurement spare part is out of stock Second value, and, calculate the second formula of size of order；
If the spare part classification is the important type of interval, Strategy of Inventory Control includes: whether the measurement spare part is out of stock Third value, and, calculate the third formula of size of order；
If the spare part classification is the insignificant type of interval, Strategy of Inventory Control includes: whether the measurement spare part is out of stock The 4th numerical value, and, calculate the 4th formula of size of order.
Step S203: judge whether the spare part is out of stock by the Strategy of Inventory Control, press institute if the spare part shortage of goods Strategy of Inventory Control is stated to calculate and export size of order.
Four kinds of spare part classifications are described separately below:
If the spare part classification is continuous important type, it is determined that the quantity in stock of the spare part, if the quantity in stock is less than first Numerical value is then calculated by the first formula and exports the first size of order.
For continuous important type spare part, belong to the key spare parts of key-point management, occupied fund is high and shortage cost is big, disappears Consumption also has certain randomness.In order to reduce the shortage of goods of inventory as far as possible under the premise of meeting production equipment normal demand Probability regulates and controls continuous important type spare part using (S, Q) control strategy, and detailed process is as follows:
The calculation formula of first numerical value is as follows: S1=ss+d × L1,Wherein, S1It is for the first numerical value, ss Safety stock needed for the continuous important type spare part, d are the continuous important type spare part day predicted using predicting strategy Consumption, δ1Deviation, L for the continuous important type spare parts consumption amount1For the continuous important type spare part order time in advance, μ1 For the continuous important type spare part safety coefficient.
Since the consumption of continuity spare part is more quick, it is possible to obtain the quantity in stock of spare part daily, and by inventory Amount is compared with the first numerical value, if the quantity in stock of spare part is greater than the first numerical value, then it represents that the quantity in stock of spare part is also not necessarily to enough Supplement.If quantity in stock is less than the first numerical value, then it represents that the quantity in stock reduction of spare part is supplemented, can be based on the first formula It calculates and exports the first size of order.
The first size of order is calculated and exported by the first formula, including the use of the first formulaFirst is calculated to order Goods amount Q1And export the first size of order Q1；Wherein D1Indicate that prediction obtains the annual consumption of continuous important type spare part, C1Indicate continuous Important type spare part single Order Cost；H1Indicate the cost of continuous important type spare part year storage.
If the spare part classification is continuous insignificant type, it is determined that the quantity in stock of spare part, if quantity in stock is less than second value, It is then calculated by the second formula and exports the second size of order.
For continuous insignificant type spare part, relatively secondary status, importance and service level are belonged in stock control It is high without continuous important type spare part.It is same that continuous insignificant type spare part is regulated and controled using (S, Q) control strategy:
The second value is calculated using following formula: S2=(L2+1)D2+μ2×δ2×(L2+1)；Wherein, S2It is second Numerical value, L2For the continuous insignificant type spare part order time in advance, D2For using the continuous insignificant type of predicting strategy prediction Spare part annual consumption, μ2For the continuous insignificant type spare part safety coefficient, δ2For the continuous insignificant type spare parts consumption amount Deviation.
Since the consumption of continuity spare part is more quick, it is possible to obtain the quantity in stock of spare part daily, and by inventory Amount is compared with second value, if the quantity in stock of spare part is greater than second value, then it represents that the quantity in stock of spare part is also not necessarily to enough Supplement.If quantity in stock is less than second value, then it represents that the quantity in stock reduction of spare part is supplemented, can be based on the second formula It calculates and exports the second size of order.
It is described to be calculated by the second formula and export the second size of order, comprising: to utilize the second formulaIt calculates Second size of order Q2And export the second size of order Q2；Wherein D2Indicate that prediction obtains the annual consumption of continuous insignificant type spare part, C2 Indicate the single Order Cost of continuous insignificant type spare part；H2Indicate the cost of continuous insignificant type spare part year storage.
If the spare part classification is the important type of interval, it is determined that the forecast consumption amount of spare part, if the forecast consumption amount is big In third value, is then calculated by third formula and export third size of order.
Its consumption of type spare part important for interval is less, but price of spare parts and inventory cost are all very high, in Parts Inventory Occupy very big ratio in circulating fund.On the other hand, the important type spare part of interval is also made a difference height, and the order cycle time is long, prediction The features such as difficulty is big, spare part cannot timely be repaired replacement and probably will cause once due to failure of breaking down It shuts down, seriously affects normal operation.
In order to guarantee that the fact that out of stock will not occur, using guarantee (S-1, S) control strategy prediction spare part not out of stock Consumption, once spare part has consumption, i.e. forecast consumption amount is not 0, then needs to propose application of ordering goods, and amount on order is equal to upper one Walk forecast consumption amount.
Therefore, third value S3It is 0.Intermittently important type spare part frequency of use is lower, but occupancy specific gravity is more, so can To determine the forecast consumption amount of spare part using prediction mode, when forecast consumption amount is zero, determines and do not need to increase spare part, when pre- When survey consumption is not zero, just determination needs stock buildup amount.
It is described to be calculated by third formula and export third size of order, comprising: using the forecast consumption amount as the third Size of order exports the third size of order.
If the spare part classification is the insignificant type of interval, temporally variable determines the quantity in stock of spare part, if quantity in stock is small In the 4th numerical value, is then calculated by the 4th formula and export the 4th size of order.
For the insignificant type spare part of interval, the importance of spare part is relatively low and the depletion rate of spare part is slow, consumption compared with Few occupied amount of money is little.In view of ingeniously all not too large and consumption is lower for the insignificant general body of type spare part of interval, more Suitable way is the primary duration ordered larger amt, increase between ordering goods twice, reduces corresponding workload.Therefore it uses (t, S) control strategy based on firm order.
The statistical of temporally variable can be taken in stock control, until finding that the quantity of remaining inventory is lower than inventory Point is guarded against, then issues order application, and once by Inventory Transshipment to highest level, if not reaching inventory's minimum point, no Give processing.
In the case where spare part is the insignificant type of interval, more spare part can be stored in advance, when being then calculated one Between variable t (such as 10 days or one month), the library of the insignificant type spare part of interval is counted when the waiting time reaching time variable t Storage.
The time variable is calculated using exponential smoothing, calculation formula is as follows:
Wherein, ti+1Indicate the duration of the time variable in i+1 period, tiIndicate the duration of i cycle time variable, diIt is The actual consumption amount of the insignificant type spare part of interval described in i-th period, β is smoothing constant, 0≤β≤1；
4th numerical value is calculated using following formula:
Wherein, S4For the 4th numerical value,It is period ti+L4The consumption of the insignificant type spare part prediction of interval in period The average value of amount, μ4It is the insignificant type spare part safety coefficient of the interval, L4It is the interval insignificant type spare parts purchasing time in advance It is the average value of consumption in the t+L period, μ4It is safety coefficient, L4It is purchasing lead time；σRIt is the standard of requirement forecasting value Difference.
Temporally variable obtains the quantity in stock of spare part, and quantity in stock and the 4th numerical value are compared, if the library of spare part Storage is less than the 4th numerical value, then it represents that the quantity in stock reduction of spare part is supplemented, and can be calculated and be exported by the 4th formula 4th size of order.
It is described to be calculated by the 4th formula and export the 4th size of order, comprising: by the difference of the 4th numerical value and the quantity in stock of spare part Value is determined as the 4th size of order, exports the 4th size of order.
It is described in detail separately below for the consumption prediction process of different spare part classifications.
(1) the continuous important type spare part annual consumption D is predicted using spare parts consumption amount historical data1
The frequency of use lower data sample of continuous important type spare part is few, while considering the time response of its consumption, uses Continuous important type spare part prediction model based on the transfer of Markov state carries out consumption prediction, by state Time-varying analysis and Model analyzing obtains relatively accurate premeasuring.Concrete methods of realizing is as follows:
It is assumed that continuous important type spare parts consumption rate is d (t), turnover rate is μ (t).Pn(t) indicate that continuous important type spare part disappears Consumption is the probability of n, P 'nIt (t) is Pn(t) derivative about time t, state transition equation are as follows:
P′n(t)=- [d (t)+n μ (t)] Pn(t)+d(t)Pn-1+
(n+1)μ(t)Pn+1(t)
N=1,2,3 ... ... formula (1)
P′0(t)=- d (t) P0(t)+μ(t)P1(t) ... ... formula (2)
It enables E [N (t)] to indicate the continuous important type spare parts consumption amount of t moment, is denoted as E (t).E ' (t) be E [N (t)] about The derivative of time t.According to state transition equation, can obtain:
As can be seen from the above equation, E ' (t) is that continuously important type spare parts consumption rate and composite are (continuous important for t moment The product of type spare parts consumption amount E (t) and turn-around speed μ) difference, indicate the change rate of continuous important type spare parts consumption amount pair.
It can similarly obtain:
It enables D [N (t)] to indicate the variance of continuous important type spare parts consumption amount of t moment, is denoted as D (t), D ' (t) indicates that it is led Number, then have:
According to above formula, the mean value and variance of the continuous important type spare parts consumption amount of any time can be calculated.
It calculates E (t) and D (t) is required to calculate Pn, any t moment Pn(t) calculation method are as follows:
1. if D (t)/E (t) > 1, can be approximately considered Pn(t) negative binomial distribution, distribution form are obeyed are as follows:
Mean value is r (1-p)/p, and variance is r (1-p)/p2, P0It can indicate are as follows:
2. if D (t)/E (t) ≈ 1, can be approximately considered Pn(t) Poisson distribution, distribution form are obeyed are as follows:
The mean value and variance of Poisson distribution are λ, P0It can indicate are as follows:
P0=e-λ, λ=D (t)=E (t) ... formula (9)
3. if D (t)/E (t) < 1, can be approximately considered Pn(t) bi-distribution, distribution form are obeyed are as follows:
The mean value of bi-distribution is np, and variance is np (1-p).P0 can be indicated are as follows:
According to the distribution function of continuous important type spare parts consumption amount, it can use formula (3) and formula (5) calculate t moment spare part The mean value E (t) and variance D (t) of consumption.Steps are as follows for calculating:
(a) distribution function is determined using spare parts consumption amount historical data, and calculate Pn[E(t),D(t)]
(b) E ' (t) and D ' (t) is calculated according to formula (3) and (5)；
(c) Δ > 0 is given, δ is the change step of d (t) and μ (t), enables Δ t=min (Δ, δ)
(d) max [0, E (t)+Δ tE ' (t)] approximation E (t+ Δ t), max [0, D (t)+Δ tD ' (t)] approximation D (t+ Δ is used t)
(e) t=t+ Δ t, return step (b).
(f) the mean value E (t) of t moment spare parts consumption amount will temporally be integrated, obtains the continuous important type spare part Annual consumption D1。
(2) the continuous insignificant type spare part annual consumption D is predicted using RBF neural method2
Carry out in a deep going way and constantly improve with weaponry comprehensive support engineering, use, the reality of maintenance and maintenance In the process, many guarantee data for influencing continuous insignificant type spare parts consumption amount including annual consumption be will record, these It is all the important information for predicting continuous insignificant type spare parts consumption amount, it can to carry out that prediction provides using RBF neural method The data source leaned on.Therefore the forecasting problem of continuous insignificant type spare parts consumption amount is solved using RBF network.Concrete methods of realizing It is as follows:
1) propose multiple data quantity continuous insignificant type spare part forecasting problem, by the natural wastage amount of ballistic weapon system, Weather conditions, conduction time, war preparedness watch time, disassembly number, on-hook flight time are continuous non-in weaponry as influencing The influence factor of important type spare part.
2) influence factor index mentioned above is quantified by range transformation method, continuous insignificant type spare part The related data of consumption is quantized into the numerical value in [0,1] section.
3) be based on above-mentioned influence factor index and quantization method, determine input and output vector, with the natural wastage amount of quantization, Weather conditions, conduction time, war preparedness watch time, disassembly number, on-hook flight time are standby with continuous insignificant type as input The annual consumption of part is collected sample data and is normalized as output.
4) RBF Network Prediction Model is designed, realizes that the input and output of neuron are closed using gaussian radial basis function transmission function System, network structure use 2 layers of preceding paragraph type neural network, comprising 1 hidden layer with Radial Basis Function neural member and 1 with line The output layer of nerve member.Input signal is transmitted to hidden layer, and hidden layer is transmitted to output layer again, and hidden node function is Gaussian function Number, output layer node function is linear function.
5) based on the RBF network structure of above-mentioned design, network is trained and is tested using the sample data of collection, really Determine network parameter, and comparative analysis training error and prediction error, determines optimal RBF network structure.
6) it is predicted using trained RBF neural prediction model, obtains disappearing in year for continuous insignificant type spare part Consumption.
(3) the WLS-SVM model optimized based on APSO, the prediction of the important type spare part of batch-type described in cyclic forecast are utilized Consumption.
1) the consumption characteristic parameter for choosing the important type spare part of batch-type, when natural wastage amount, weather conditions may be selected, being powered Between, the war preparedness watch time, disassembly number, the quantizations such as on-hook flight time influence factor.
2) trained and test sample data set is collected, initializes WLS-SVM parameter to carry out sample training.
3) set APSO population scale m, aceleration pulse c1 and c2, aberration rate pm, exchange rate pc, minimum average B configuration grain away from Current evolutionary generation is set to t=1 away from Dmax, maximum evolutionary generation Tmax by Dmin, the average grain of maximum；
4) speed and the position of particle are initialized in solution space；
5) adaptive value of each particle is calculated, fitness function is defined as yiRespectively SVM instruction Practice output valve and desired output.I-th of particle current point adaptive value is set as optimal location pi, the maximum is set as planting in pi value Group's optimal location pg；
6) average grain is calculated away from D (t), if D (t) > Dmax, goes to step 7)；If D (t) < Dmin is made a variation and is exchanged Step 8) is gone to after operation；
7) inertia weight wi is updated by (8) formula, by the speed and position of (5) formula and (6) formula more new particle, generates new population Xt；
8) population Xt is evaluated.The optimal location pi's that i-th of particle current point adaptive value and the particle are found so far is suitable It should be worth and be compared, if more excellent, update pi, otherwise keep pi constant, then the optimal location pg's that finds so far with population is suitable It should be worth and be compared, if more excellent, update pg；Otherwise keep pg constant；
9) it checks whether and meets optimizing termination condition, terminate optimizing if meeting, find out optimal solution；Otherwise, t=t+1 is set, Go to step 6)；Termination condition is that optimizing reaches maximum evolutionary generation Tmax；
10) by the optimal result of optimization, i.e. optimized parameter vector is assigned to WLS-SVM.
11) training sample and test sample are chosen using ten folding cross-validation methods, realizes the important type spare part prediction of batch-type As a result output.In order to examine the validity of prediction model, a variety of methods such as APSO-WLS-SVM predict that batch-type is important respectively The annual consumption of type spare part.
(4) it determines that consumption is distributed by the insignificant type spare parts consumption amount historical data of the interval, and is based on Croston The forecast consumption amount of the insignificant type spare part of interval described in model prediction.
The amount of the insignificant type spare parts demand of weapon system interval is larger, is easy the means counted by historical data acquisition and disappears Consumption distribution and Annual distribution, Croston model carry out time variable and consumption to separate prediction.Implementation method is as follows:
Using exponential smoothing, according to the actual consumption amount of the insignificant type spare part of interval in i-th of time variable and The forecast consumption amount of the insignificant type of interval in i-th of time variable predicts that the interval in i+1 time variable is insignificant The predicted required amount of type spare part:
Wherein, α is smoothing constant, 0≤α≤1；Ri+1It is the pre- of the insignificant type spare part of interval in i+1 time variable Survey consumption；RiIt is the forecast consumption amount of the insignificant type spare part of interval in the i-th time variable；diIt is interval in i time variable The actual consumption amount of insignificant type spare part is the spare part forecast consumption amount in t+1 period；It is the spare part forecast consumption amount in t period； dtIt is the spare part actual consumption amount in t period.
Wherein, ti+1Indicate the duration of the time variable in i+1 period, tiIndicate the duration of i cycle time variable, diIt is The actual consumption amount of the insignificant type spare part of interval described in i-th period, β is smoothing constant, 0≤β≤1.
Croston is by time variable ti+1With forecast consumption amount Ri+1It separates, time change is calculated separately using exponential smoothing Amount and forecast consumption amount；If actual consumption amount non-zero, renewal time variable and forecast consumption amount.
In traditional Croston model, forecast consumption amount is independent from each other with the period, therefore application tradition When the insignificant type spare parts consumption amount of Croston model progress batch-type is predicted, haves the defects that Biased estimator.
In the present solution, Croston model is improved appropriately, by the forecast consumption amount of the insignificant spare part of batch-type Be split as two segmentations: a segmentation is the sequence of actual consumption amount non-zero, the other is the sequence that actual consumption amount is zero.It is right It is predicted respectively with exponential smoothing in two sequences, is improved by this, the prediction of the insignificant spare part of batch-type may be implemented The unbiased esti-mator of consumption.
By the above technological means, may be implemented it is following the utility model has the advantages that
The application, which provides, can determine spare part classification belonging to spare part in technical solution, and determine inventory's control of spare part classification System strategy, to make different types of spare part using different Strategy of Inventory Control.Based on different Strategy of Inventory Control come Judge whether spare part is out of stock, and is calculated in situation out of stock by different Strategy of Inventory Control and export size of order.
That is, the application uses different Strategy of Inventory Control for different spare part classifications, it is possible to realize targetedly Determine shortage of goods spare part, and specific aim calculates size of order to be supplemented, so as to control under conditions of meeting requirement Make large-scale spare parts warehouse spare part amount in the reasonable scope.
Referring to Fig. 3, this application provides a kind of Parts Inventory control device, the control applied to control Parts Inventory is whole End, described device include:
Class location 31 is determined, for according to spare part classification belonging to determining spare part；Policy unit 32 is determined, for determining Strategy of Inventory Control corresponding with the spare part classification；
Output unit 33 is calculated, for judging whether the spare part is out of stock by the Strategy of Inventory Control, if the spare part It is out of stock then calculated by the Strategy of Inventory Control and export size of order.
Scheme about Parts Inventory control device is detailed in Fig. 1 and embodiment shown in Fig. 2, and details are not described herein.
If function described in the present embodiment method is realized in the form of SFU software functional unit and as independent product pin It sells or in use, can store in a storage medium readable by a compute device.Based on this understanding, the embodiment of the present application The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, this is soft Part product is stored in a storage medium, including some instructions are used so that calculating equipment (it can be personal computer, Server, mobile computing device or network equipment etc.) execute all or part of step of each embodiment the method for the application Suddenly.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), deposits at random The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic or disk.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with it is other The difference of embodiment, same or similar part may refer to each other between each embodiment.
The foregoing description of the disclosed embodiments makes professional and technical personnel in the field can be realized or use the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein General Principle can be realized in other embodiments without departing from the spirit or scope of the application.Therefore, the application It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one The widest scope of cause.

Claims (10)

1. a kind of Parts Inventory control method, which is characterized in that applied to the controlling terminal of control Parts Inventory, the method packet It includes:
Determine spare part classification belonging to spare part；
Determine Strategy of Inventory Control corresponding with the spare part classification；
Judge whether the spare part is out of stock by the Strategy of Inventory Control, presses the Strategy of Inventory Control if the spare part shortage of goods It calculates and exports size of order.
2. the method as described in claim 1, which is characterized in that the spare part classification be continuous important type, continuous insignificant type, Intermittently important type or the insignificant type of interval.
3. method according to claim 2, which is characterized in that described whether to judge the spare part by the Strategy of Inventory Control Shortage of goods is calculated by the Strategy of Inventory Control if the spare part shortage of goods and exports size of order, comprising:
If the spare part classification is continuous important type, it is determined that the quantity in stock of the spare part, if the quantity in stock less than the first numerical value, It is then calculated by the first formula and exports the first size of order；
If the spare part classification is continuous insignificant type, it is determined that the quantity in stock of the spare part, if the quantity in stock is less than the second number Value, then calculated by the second formula and export the second size of order；
If the spare part classification is the important type of interval, it is determined that the forecast consumption amount of the spare part, if the forecast consumption amount is big In third value, is then calculated by third formula and export third size of order；
If the spare part classification is the insignificant type of interval, temporally variable determines the quantity in stock of the spare part, if the quantity in stock Less than the 4th numerical value, is then calculated by the 4th formula and export the 4th size of order.
4. method as claimed in claim 3, which is characterized in that
First numerical value is calculated using following formula: S1=ss+d × L1,Wherein, S1For first number Value, ss are safety stock needed for the continuous important type spare part, d is the continuous important type predicted using predicting strategy Spare part day's expenditure, δ1Deviation, L for the continuous important type spare parts consumption amount1Shift to an earlier date for the continuous important type spare part order Phase, μ1For the continuous important type spare part safety coefficient；
The second value is calculated using following formula: S2=(L2+1)D2+μ2×δ2×(L2+1)；Wherein, S2For second number Value, L2For the continuous insignificant type spare part order time in advance, D2It is standby using the continuous insignificant type of predicting strategy prediction Part annual consumption, μ2For the continuous insignificant type spare part safety coefficient, δ2For the inclined of the continuous insignificant type spare parts consumption amount Difference；
The third value S3It is 0；
The time variable is calculated using exponential smoothing, calculation formula is as follows:
Wherein, ti+1Indicate the duration of the time variable in i+1 period, tiIndicate the duration of i cycle time variable, diIt is i-th The actual consumption amount of the insignificant type spare part of interval in period, β is smoothing constant, 0≤β≤1；
4th numerical value is calculated using following formula:
Wherein, S4For the 4th numerical value,It is ti+L4The insignificant type spare part forecast consumption amount of interval is averaged in period Value, μ4It is the insignificant type spare part safety coefficient of the interval, L4It is the interval insignificant type spare parts purchasing time in advance.
5. method as claimed in claim 3, which is characterized in that
It is described that the first size of order is calculated and exported by the first formula, including the use of the first formulaIt calculates and exports The first size of order Q1；Wherein D1Indicate the annual consumption for the continuous important type spare part that prediction obtains, C1Indicate the company Continue the single Order Cost of important type spare part；H1Indicate the cost of the continuous important type spare part year storage；
It is described to be calculated by the second formula and export the second size of order, comprising: to utilize the second formulaIt calculates and defeated The second size of order Q out2；Wherein D2Indicate the annual consumption for the continuous insignificant type spare part that prediction obtains, C2Indicate institute State continuous insignificant type spare part single Order Cost；H2Indicate the cost of the continuous insignificant type unit spare part year storage；
It is described to be calculated by third formula and export third size of order, comprising: will periodically to determine the important type spare part of interval Forecast consumption amount exports the third size of order as the third size of order；
It is described to be calculated by the 4th formula and export the 4th size of order, comprising: by the 4th numerical value and the insignificant type of the interval The difference of the quantity in stock of spare part is determined as the 4th size of order, exports the 4th size of order.
6. method as claimed in claim 5, which is characterized in that further include:
The continuous important type spare part annual consumption D is predicted using spare parts consumption amount historical data1；
The continuous insignificant type spare part annual consumption D is predicted using RBF neural method2；
Using the WLS-SVM model optimized based on APSO, the forecast consumption amount of the important type spare part of interval described in cyclic forecast；
Determine that consumption is distributed by the insignificant type spare parts consumption amount historical data of the interval, and pre- based on Croston model Survey the forecast consumption amount of the insignificant type spare part of the interval.
7. method as claimed in claim 6, which is characterized in that described to pass through the insignificant type spare parts consumption amount history of the interval Data determine that consumption is distributed, and the forecast consumption amount based on the insignificant type spare part of interval described in Croston model prediction, packet It includes: predicting the forecast consumption amount of the insignificant type spare part of the interval using exponential smoothing；
Wherein, α is smoothing constant, 0≤α≤1；Ri+1It is the prediction of the insignificant type spare part of interval in i+1 time variable Consumption；RiIt is the forecast consumption amount of the insignificant type spare part of interval in i-th of time variable；diIt is in i-th of time variable The intermittently actual consumption amount of insignificant type spare part.
8. a kind of Parts Inventory control device, which is characterized in that applied to the controlling terminal of control Parts Inventory, described device packet It includes:
Class location is determined, for determining spare part classification belonging to spare part；
Policy unit is determined, for determining Strategy of Inventory Control corresponding with the spare part classification；
Output unit is calculated, for judging whether the spare part is out of stock by the Strategy of Inventory Control, if the spare part shortage of goods It is calculated by the Strategy of Inventory Control and exports size of order.
9. device as claimed in claim 7, which is characterized in that the spare part classification be continuous important type, continuous insignificant type, Intermittently important type or the insignificant type of interval.
10. device as claimed in claim 9, which is characterized in that the calculating output unit, comprising:
If the spare part classification is continuous important type, it is determined that the quantity in stock of the spare part, if the quantity in stock less than the first numerical value, It is then calculated by the first formula and exports the first size of order；
If the spare part classification is continuous insignificant type, it is determined that the quantity in stock of the spare part, if the quantity in stock is less than the second number Value, then calculated by the second formula and export the second size of order；
If the spare part classification is the important type of interval, it is determined that the forecast consumption amount of the spare part, if the forecast consumption amount is big In third value, is then calculated by third formula and export third size of order；
If the spare part classification is the insignificant type of interval, temporally variable determines the quantity in stock of the spare part, if the quantity in stock Less than the 4th numerical value, is then calculated by the 4th formula and export the 4th size of order.
CN201910433129.4A 2019-05-23 2019-05-23 Parts Inventory control method and device Pending CN110147975A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910433129.4A CN110147975A (en) 2019-05-23 2019-05-23 Parts Inventory control method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910433129.4A CN110147975A (en) 2019-05-23 2019-05-23 Parts Inventory control method and device

Publications (1)

Publication Number Publication Date
CN110147975A true CN110147975A (en) 2019-08-20

Family

ID=67592749

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910433129.4A Pending CN110147975A (en) 2019-05-23 2019-05-23 Parts Inventory control method and device

Country Status (1)

Country Link
CN (1) CN110147975A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110705777A (en) * 2019-09-26 2020-01-17 联想(北京)有限公司 Method, device and system for predicting spare part reserve
CN111325920A (en) * 2020-02-10 2020-06-23 上海探能实业有限公司 Cabinet and system are got to spare part intelligence
CN112561411A (en) * 2019-09-10 2021-03-26 上海杰之能软件科技有限公司 Computing method of spare part safety inventory number, storage device and terminal

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003052649A1 (en) * 2001-11-22 2003-06-26 Metso Paper, Inc. Delivery system for consumption and/or spare parts
CN104732287A (en) * 2013-12-19 2015-06-24 广州市地下铁道总公司 Stock control method based on optimum replenishment period of spare part
CN108846608A (en) * 2018-06-15 2018-11-20 上海探能实业有限公司 A kind of large-scale wind electricity unit standby redundancy inventory management and Optimization Scheduling
CN109754118A (en) * 2018-12-26 2019-05-14 复旦大学 A kind of prediction technique of system self-adaption

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003052649A1 (en) * 2001-11-22 2003-06-26 Metso Paper, Inc. Delivery system for consumption and/or spare parts
CN104732287A (en) * 2013-12-19 2015-06-24 广州市地下铁道总公司 Stock control method based on optimum replenishment period of spare part
CN108846608A (en) * 2018-06-15 2018-11-20 上海探能实业有限公司 A kind of large-scale wind electricity unit standby redundancy inventory management and Optimization Scheduling
CN109754118A (en) * 2018-12-26 2019-05-14 复旦大学 A kind of prediction technique of system self-adaption

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王路: "复杂装备备件库存预测与控制方法及其应用研究", 《中国优秀硕士学位论文全文数据库（信息科技Ⅱ辑）》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112561411A (en) * 2019-09-10 2021-03-26 上海杰之能软件科技有限公司 Computing method of spare part safety inventory number, storage device and terminal
CN112561411B (en) * 2019-09-10 2023-11-21 上海杰之能软件科技有限公司 Method for calculating spare part safety stock number, storage equipment and terminal
CN110705777A (en) * 2019-09-26 2020-01-17 联想(北京)有限公司 Method, device and system for predicting spare part reserve
CN110705777B (en) * 2019-09-26 2022-07-26 联想(北京)有限公司 Method, device and system for predicting spare part reserve
CN111325920A (en) * 2020-02-10 2020-06-23 上海探能实业有限公司 Cabinet and system are got to spare part intelligence

Similar Documents

Publication Publication Date Title
Leng et al. A loosely-coupled deep reinforcement learning approach for order acceptance decision of mass-individualized printed circuit board manufacturing in industry 4.0
CN110147975A (en) Parts Inventory control method and device
Sheu A novel dynamic resource allocation model for demand-responsive city logistics distribution operations
Hadavandi et al. An improved sales forecasting approach by the integration of genetic fuzzy systems and data clustering: Case study of printed circuit board
Han et al. A two-stage method for predicting and scheduling energy in an oxygen/nitrogen system of the steel industry
CN113052533B (en) Inventory transaction early warning and allocation scheme updating method and system for probability products
CN117539726B (en) Energy efficiency optimization method and system for green intelligent computing center
Deng Research on evaluation of intelligent manufacturing capability and layout superiority of supply chains by big data analysis
CN110689217A (en) Intelligent manufacturing system for computer production
Sabbaghnia et al. Reducing the Bullwhip effect in a supply chain network by application of optimal control theory
CN108510101A (en) A kind of Parts Inventory quota model prediction method based on weighting Markov
Seo et al. Rebalancing docked bicycle sharing system with approximate dynamic programming and reinforcement learning
Işık et al. Deep learning based electricity demand forecasting to minimize the cost of energy imbalance: A real case application with some fortune 500 companies in Türkiye
Wang et al. A data-driven load forecasting method for incentive demand response
CN111353794B (en) Data processing method, supply chain scheduling method and device
CN112990584B (en) Automatic production decision system and method based on deep reinforcement learning
Zhou et al. [Retracted] Research on Intelligent Solution of Service Industry Supply Chain Network Optimization Based on Genetic Algorithm
Xu et al. Resource allocation optimization model of collaborative logistics network based on bilevel programming
Qiu et al. High‐Order Fuzzy Time Series Model Based on Generalized Fuzzy Logical Relationship
CN109993271A (en) Grey neural network forecasting based on theory of games
CN102542432B (en) Inventory management system and method
Ge et al. Proactive Two‐Level Dynamic Distribution Routing Optimization Based on Historical Data
Gao [Retracted] Intelligent Prediction Algorithm of Cross‐Border E‐Commerce Logistics Cost Based on Cloud Computing
Khonakdar‐Tarsi et al. Reliability incentive regulation based on reward‐penalty mechanism using distribution feeders clustering
Bansal et al. Brief application description. neural networks based forecasting techniques for inventory control applications

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190820