CN107886358A - A kind of Agricultural Machinery Equipment service of goods needing forecasting method - Google Patents
A kind of Agricultural Machinery Equipment service of goods needing forecasting method Download PDFInfo
- Publication number
- CN107886358A CN107886358A CN201711088618.8A CN201711088618A CN107886358A CN 107886358 A CN107886358 A CN 107886358A CN 201711088618 A CN201711088618 A CN 201711088618A CN 107886358 A CN107886358 A CN 107886358A
- Authority
- CN
- China
- Prior art keywords
- mrow
- agricultural machinery
- msub
- demand
- service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q10/20—Administration of product repair or maintenance
Abstract
The present invention provides a kind of Agricultural Machinery Equipment service of goods needing forecasting method, realizes the basis that the emergent supply of the quick response of service, Service Source is safeguarded to equipment cluster, has also ensured equipment cluster reliability service.Comprise the following steps：Step 1: Agricultural Machinery Equipment safeguards that Service Source demand structure is analyzed；Step 2: Agricultural Machinery Equipment safeguards Service Source requirement forecasting signature analysis；Step 3: equipment maintenance influencing factors for demand is determined based on grey correlation analysis；Step 4: safeguard that BP neural network model is established in demand for services prediction for Agricultural Machinery Equipment：It is made up of an input layer, two hidden layers and an output layer, it is not connected to between node layer, the input of a node layer under the influence of output only per node layer, BP neural network structure, network training, network verification and prediction are specifically included, safeguards that demand for services is predicted so as to complete Agricultural Machinery Equipment.
Description
Technical field
It is especially a kind of towards Agricultural Machinery Equipment product the present invention relates to a kind of Agricultural Machinery Equipment service of goods needing forecasting method
Cluster safeguards demand for services Forecasting Methodology.
Background technology
Currently, " manufacturing service " is known together extensively among industrial circle, and equipment manufacturing business is using product as core
The competition of the heart has been enter into low margin age, and its major profit has been more that product is after sale visitor not just from production marketing
The value-added service that family provides.The practice of industrial quarters absolutely proves in recent years：The development trend of manufacturing industry serviceization, bring to production
The active demand of product O＆M service ability lifting.
The principal mode that on-site maintenance is equipment Manufacturing service is provided for equipment.Service network is to ensure to service
Provider can provide the network that maintenance service in time, satisfied is formed for customer.In general service network is by equipment manufacturing
The service providers such as enterprise, supplier of spare parts, service provider are formed by connecting by certain membership credentials, that is, Service Source
Acquisition, service ability formation and tangible products and invisible service deliver the network of involved enterprise's composition.Service station conduct
Serving network node, it is the website for receiving customer service request and respective service being provided.For equipment maintenance service, service
The stand attendant that should keep certain, servicer etc. safeguards Service Source, to meet the equipment maintenance demand occurred at any time in time.
In general, set service network can be accomplished preferably to respond to the equipment maintenance service request of fixed position, meet clothes
Business demand.But for the equipment cluster maintenance needs under dynamic and distributed environment, with moving characteristic, due to moving for geographical position etc.
State changes and to safeguarding that response requires the characteristics of high, and the normal needs of its maintenance activity are dependent on accurately requirement forecasting and optimized
Configuration.
Important component of the talents for agri-mechanization as equipment manufacture, it is to improve production efficiency, realizes that resource is effective
Utilize, promote the indispensable instrument of agricultural sustainable development, to ensure national food security, promote agricultural production efficiency,
Change increasing peasant income mode and promote rural development to play very important effect.However, exist during agricultural mechanical operation
Trans-regional, operating environment and job task DYNAMIC DISTRIBUTION, work operations time Relatively centralized, the features such as operation intensity is big, its
Safeguard that the more problems of service facing need to solve.Existing Agricultural Machinery Equipment, which is safeguarded, main relies on existing main of equipment Manufacturing
The service network being made up of service station.It is relatively certain yet with the service ability in the existing service station of enterprise, and network shortage is dynamic
State adaptability, therefore it is explosive in safeguarding to be directed to trans-regional product, DYNAMIC DISTRIBUTION, the Agricultural Machinery Equipment cluster of seasonal concentrative operation
Breakdown Maintenance seem beyond one's ability.
Therefore, the characteristics of for Agricultural Machinery Equipment cluster maintenance needs with season time, spatial geographical locations dynamic change, need
Want a kind of maintenance needs Forecasting Methodology towards Agricultural Machinery Equipment cluster, maintenance Service Source (such as service network of Support Equipment operation
Point, maintenance tool, attendant and servicer etc.) accommodation, optimised service network design and cloth can be carried out in advance
Office, to meet the equipment maintenance demand of dynamic change in time.
The content of the invention
The present invention in order to adapt to dynamic distributed cluster equipment needs, with the change of operating area, tie up by dynamic mobile, equipment
The demand for services of shield also can therewith dynamic change the characteristics of, there is provided a kind of Agricultural Machinery Equipment service of goods needing forecasting method, realize
The basis of the emergent supply of the quick response of service, Service Source is safeguarded to equipment cluster, has also ensured that equipment cluster is reliably transported
OK.
What the present invention was achieved through the following technical solutions：
A kind of Agricultural Machinery Equipment service of goods needing forecasting method, comprises the following steps：
Step 1: Agricultural Machinery Equipment safeguards that Service Source demand structure is analyzed：According to the service need of corresponding region equipment maintenance
Ask, the decision-making that maximum can meet the benefit of client is made on the premise of limited resources total amount；The level of described demand for services
Feature shows as three kinds of situations, when geographic level characteristics, second, managerial level characteristics, third, service of goods demand
Layer of structure feature；
Step 2: Agricultural Machinery Equipment safeguards Service Source requirement forecasting signature analysis：Predict regional to Service Source
Quantity required, service network is built on this basis, entered on the premise of Service Source is limited using BP neural net methods
Row Agricultural Machinery Equipment maintenance service requirement forecasting；
Step 3: equipment maintenance influencing factors for demand is determined based on grey correlation analysis：Analyze what is obtained by step 2
Agricultural Machinery Equipment maintenance service requirement forecasting result, being associated property of influence factor is analyzed, so as to identify key factor therein,
Input as subsequent prediction model；
Described correlation analysis is closed by the different degree of development trend between gray prediction identification system factor
Connection property analysis, so that it is determined that influenceing the key factor of Agricultural Machinery Equipment maintenance needs；Comprise the following steps that：Step 1.1 Data Collection：
Clearly required field first, and then Data Collection is carried out from different system, and the statistics on basis is completed on this basis
Analysis, data preparation is carried out for subsequent prediction；
Step 1.2 Grey Relational Model is established and solved：Each factor is analyzed to region agriculture using Grey Incidence Analysis
The influence of machine equipment maintenance demand for services amount；The step of grey correlation analysis, is as follows：
Step1：Establish the raw data matrix x of each index of correlation in above tablei
xi=(xi(1), xi(2) ..., xi(k)) ...)
Wherein xi(k) initial data of the i factors in kth year is represented；
Step2：First value matrix x '
Above-mentioned raw data matrix is handled using equalization method, nondimensionalization processing is carried out to matrix, obtained
X '=(xi(1)/xi(1), xi(2)/xi(1) ..., xi(k)/xi(1)) ...)=(xi' (1), xi' (2) ..., xi′
(k) ...)
Step3：Seek difference sequence Δ0i=(k)
Step4：Calculate correlation coefficient ξ0i(k)
Wherein φ is resolution ratio, for improving the significance of difference between incidence coefficient, φ ∈ (0,1),
Further, the φ takes 0.5.
Step5：Calculate grey relational grade γ0i
Grey relational grade is
Step6：Relational degree taxis
A k, which is obtained, by above-mentioned steps ties up degree of association matrix, it is each by being ranked up acquisition to the size of matrix element
Individual factor and the degree of association and its influence power caused by equipment maintenance demand for services.
Step 4: safeguard that BP neural network model is established in demand for services prediction for Agricultural Machinery Equipment：By input layer, two
Individual hidden layer and an output layer are formed, and are not connected to between node layer, a node layer under the influence of the output per node layer only
Input, specifically include BP neural network structure, network training and prediction.
Beneficial effects of the present invention：
The present invention carries out Systematic Analysis for the demand characteristic of Agricultural Machinery Equipment product maintenance service, based on Agricultural Machinery Equipment system
The historical data for making enterprise's different dimensions is precisely predicted equipment maintenance demand, is the dynamic distributed Agricultural Machinery Equipment collection public sentiment
Maintenance service under border provides the decision-making foundation of resource optimization resource distribution, to meet the equipment maintenance need of dynamic change in time
Ask, realize effective delivery of the service of maintenance.
Brief description of the drawings
Fig. 1 is Agricultural Machinery Equipment service of goods needing forecasting method flow chart of the present invention；
Fig. 2 predicts flow chart for BP neural network in the present invention.
Embodiment
The preferred embodiment of the present invention is elaborated below in conjunction with the accompanying drawings,
The present invention specifically includes Agricultural Machinery Equipment and safeguards demand for services structural analysis, predicted characteristics analysis, influence factor association
Spend prediction model construction and demand for services prediction.Specific framework is as shown in Figure 1：
Step 1：Agricultural Machinery Equipment safeguards that Service Source demand structure is analyzed
Safeguard that Service Source configures an inherently decision problem.According to the demand for services of corresponding region equipment maintenance,
Being made on the premise of limited resources total amount maximum can meet the decision-making of the benefit of client.By to service of goods demand layer
Analysis, the structure of resource placement's configuration can be specified.In general the level characteristics of service of goods demand show as three kinds of situations,
When geographic level characteristics, such as some services of goods, its market can be divided into multiple regions or subdivision
Sub- market；Second, managerial level characteristics, such as some service of goods customers can be divided into different classes of client；Three
It is service of goods demand structure level characteristics.
By the specific level that is assigned to of the resource high-efficiency of fixed qty during resource distribution, therefore service of goods is needed
The analysis of level is asked to be advantageous to the unit and granularity of the clear and definite resource distribution of enterprise.Agricultural Machinery Equipment enterprise maintenance service is born using region
Duty system carries out O＆M service, i.e. market is several market departments according to geographical position and administrative division by enterprise, each
Market department includes several service stations again, and the Agricultural Machinery Equipment O＆M that each service station is responsible in area of responsibility provides resource and supported
Kimonos is pragmatic to be applied.Due to the distribution and dynamic of Agricultural Machinery Equipment group operation, enterprise's different zones product is to safeguarding service
Demand dynamic change therewith.Therefore the present invention will safeguard that service needs using market department as object to the Agricultural Machinery Equipment of different market departments
Ask and be predicted.
Step 2：Agricultural Machinery Equipment safeguards Service Source requirement forecasting signature analysis
The main purpose of demand for services prediction is quantity required of the Accurate Prediction regional to Service Source, basic herein
The upper effective service network of structure, maximizes on the premise of Service Source is limited and meets dynamic distributed Agricultural Machinery Equipment
Demand for services is safeguarded, the loss brought by equipment failure is reduced, further increases customer satisfaction degree.
The Maintenance Resource demand in one region is related to factors：Equipped in region recoverable amount, equipment enlistment age in region,
Equip history run situation and repair etc..These information in different forms disperse be present in enterprise different system it
In, such as maintenance service system is present in excel forms, marketing system etc. is present in list record.These data
There is important reference value for regional service resource requirement prediction, prediction mould is established on the basis of to actual data analysis
Type, and verified using the data of continuous renewal and then Optimized model, it can make it that last tentative data is more accurate.
Therefore, the present invention by the historical record to enterprise's equipment maintenance, sales figure etc., analyze by other related datas, summarizes
Agricultural Machinery Equipment cluster safeguards the general character of Service Source demand, refines the best model for summing up its suitable requirement forecasting.
Because Agricultural Machinery Equipment safeguards that demand for services is related to factors, it is main including equipment be in region, residing season,
The region vehicle population, Agricultural Machinery Equipment workload, operating environment, area equipment running status and history repair status etc. because
Element.There is the interaction of complexity between these factors, using conventional method it is difficult to set up one it is accurate and perfect pre-
Survey model.Found by Literature Consult and analysis.BP neural network with to complicated nonlinear system prediction with well retouch
Ability is stated, so the present invention carries out Agricultural Machinery Equipment maintenance service requirement forecasting using BP neural network method.
Step 3：Equipment maintenance influencing factors for demand based on grey correlation analysis determines
Understand that Agricultural Machinery Equipment safeguards that demand for services amount is influenceed by factors by step 2 analysis, specify its influence
The practical function situation of factor has great importance for the prediction of follow-up maintenance demand for services.Generally recognize according to existing subjectivity
For knowing, influence Agricultural Machinery Equipment and safeguard that the principal element of demand for services has：Agricultural Machinery Equipment region, residing season, the region
Equip recoverable amount, Agricultural Machinery Equipment workload, operating environment, area equipment running status and history repair status etc..It will influence
The larger factor of power can make predicted value more accurate as the input of forecast model, but redundancy is excessive in input data
Precision of prediction can be caused to reduce simultaneously.Therefore, it is necessary to being analyzed according to the being associated property of influence factor listed by Subjective,
So as to identify key factor therein, the input as subsequent prediction model.
Gray system is the transition system between white system and Black smoker.If the full detail of a certain system
, it is known that it is then white system；If full detail is unknown, for Black smoker；Partial information is, it is known that partial information is unknown, then
The system is gray system.Agricultural Machinery Equipment involved in the present invention safeguards demand for services system, and it is many to influence factor caused by demand
It is more, but known and X factor simultaneously be present, it is consequently belonging to gray system.The present invention passes through gray prediction identification system factor
Between development trend different degree, that is, being associated property analyze, so that it is determined that influence Agricultural Machinery Equipment maintenance needs it is crucial because
Element.Gray prediction step is as follows：
1) Data Collection
Because above-mentioned related data is distributed in the different system for being stored in enterprise in different forms, grey correlation point is being carried out
At the beginning of analysis, clearly required field, and then Data Collection is carried out from different system first, and basis is completed on this basis
Statistical analysis, for subsequent prediction carry out data preparation.Perfect data form is wherein needed to design as shown in table 1 below：
Table 1：Agricultural Machinery Equipment safeguards demand for services influence factor table
2) Grey Relational Model is established and solved
Demand for services amount is safeguarded to region Agricultural Machinery Equipment using the subjective each factor of Grey Incidence Analysis analysis conventional
Influence.The step of grey correlation analysis, is as follows：
Step1：Establish the raw data matrix x of each index of correlation in above tablei
xi=(xi(1), xi(2) ..., xi(k)) ...)
Wherein xi(k) initial data of the i factors in kth year is represented；
Step2：First value matrix x '
Above-mentioned original matrix is handled using equalization method, nondimensionalization processing is carried out to matrix, obtained
X '=(xi(1)/xi(1), xi(2)/xi(1) ..., xi(k)/xi(1)) ...)=(xi' (1), xi' (2) ..., xi′
(k) ...)
Step3：Seek difference sequence Δ0i=(k)
Step4：Calculate correlation coefficient ξ0i(k)
Wherein φ is resolution ratio, its role is to improve the significance of difference between incidence coefficient, φ ∈ (0,1), is led to
Normal φ takes 0.5, and the present invention takes 0.5.
Step5：Calculate grey relational grade γ0i
Grey relational grade is
Step6：Relational degree taxis
A k is obtained by above-mentioned steps and ties up degree of association matrix, by the way that the size of matrix element is ranked up and can obtained
Take each factor and the degree of association and its influence power caused by equipment maintenance demand for services in table 1.According to mould when subsequent prediction models
Type demand chooses input item of the forward factor as BP neural network that sort.
Step 4：The BP neural network model for safeguarding demand for services prediction for Agricultural Machinery Equipment is established
BP neural network is the multilayer feedforward formula network of error back propagation, and it is hidden by an input layer, one or more
Form containing layer and an output layer, be not connected to between node layer, a node layer is defeated under the influence of the output only per node layer
Enter.Safeguard that demand for services needs to complete BP neural network structure, network training by BP neural network model prediction Agricultural Machinery Equipment
With three partial contents of prediction.Specific BP neural network structure flow is as shown in Figure 2：
Step1：BP neural network mode input
Calculated by preceding step and choose season, region, area equipment recoverable amount, Agricultural Machinery Equipment workload, area equipment
Input data of the larger factor of the workload degree of association as BP neural network, can fully reflect that Agricultural Machinery Equipment safeguards demand for services
Geography, the time, Seasonal Characteristics, to reach more preferable analysis result.Therefore design Agricultural Machinery Equipment safeguards demand for services prediction
BP neural network input data includes season, region, area equipment recoverable amount, Agricultural Machinery Equipment workload, area equipment workload 5
Dimension, uses X successively1,X2,…X5Represent.The specific data input of model be from 2008 to 2015 totally 15 years from January to 12
Month includes the numerical matrix of 5 correlative factors such as season, region, area equipment recoverable amount, predicts some month in 2016
The equipment maintenance demand for services value in individual region.Therefore understand that the output layer of BP neural network is tieed up for 1.
Step2：BP neural network model structure designs
Safeguard that the complexity of demand for services and nonlinear degree are higher in view of Agricultural Machinery Equipment, in order to improve the robust of network
Property and computing accuracy, the present invention is using double hidden layer neural network structures.For the neuron number of two hidden-layer, and BP god
Optimizing is carried out using intelligent optimization algorithm through network weight and threshold value, and then determines to be suitable for agricultural machinery equipment maintenance in present case and takes
The BP neural network optimal parameter of business requirement forecasting.
Step3：BP network model parameter optimizations
Traditional BP neural network is because weights, threshold value are randomized, and node in hidden layer empirically determines, network evolution
When be easily trapped into local optimum, and network robustness is poor.Therefore, the present invention is refreshing to BP using intelligent optimization algorithm genetic algorithm
Parameter through network model optimizes.
If the nodes of hidden layer are respectively m1,m2, the weights of 5 dimension input parameters in Step1 use w successively1,w2,…w5
Represent, the weights of equipment maintenance demand number are represented with a.
The above-mentioned m of genetic algorithm optimization is used on this basis1,m2,w1,w2,…w5, a totally 8 parameters, will using real coding
BP neural network corresponding to individual predicts error as ideal adaptation angle value.Predict that error E rror is specially root-mean-square error
RSME, mean absolute deviation MABE weighted error.The population scale of genetic algorithm is 40, and iterations is 100 times, is used
Matlab Algorithm for Solving, obtain the best of breed of above-mentioned 8 parameters.
The transfer function of BP neural network carries out best practice selection with training function using test method(s).
Step4：BP neural network model training
Choose certain Agricultural Machinery Equipment manufacturing enterprise in January, 2008 in December, 2015 data of totally 8 years, by corresponding sample number
According to training set, checking collection and test set is divided into sequentially in time, wherein in January, 2008 in December, 2013 is training set,
In January, 2014 to December collects for checking, and the data in January, 2015 in December, 2015 are test set.Arrange prepare training set and
The sample of collection is verified, the Optimized model structure and parameter of BP neural network is determined according to method in above-mentioned Step3.
After model structure and parameter determine, input data carries out BP neural network model training, and the error of analysis model refers to
Mark, the deconditioning when neural network forecast error amount is less than a certain numerical value, the BP neural network trained.
Step5：BP neural network is verified
The data in January, 2014 to December are verified to network.Inputted to obtain prediction error, analysis with checking sample
The validity and accuracy of model.
Step6:Agricultural Machinery Equipment safeguards that demand for services is predicted
Neural network prediction some the month Agricultural Machinery Equipment maintenance clothes of some region in 2016 trained using above-mentioned Step5
The requirements of business, safeguard that demand for services is predicted so as to complete Agricultural Machinery Equipment.
Although combining accompanying drawing describes embodiments of the present invention, it will be apparent to those skilled in the art that not
On the premise of departing from the principle of the invention, various modifications and improvements can be made, these also should be regarded as the protection for belonging to the present invention
Scope.
Claims (4)
1. a kind of Agricultural Machinery Equipment service of goods needing forecasting method, it is characterised in that comprise the following steps：
Step 1: Agricultural Machinery Equipment safeguards that Service Source demand structure is analyzed：According to the demand for services of corresponding region equipment maintenance,
Being made on the premise of limited resources total amount maximum can meet the decision-making of the benefit of client；The level characteristics table of described demand for services
It is now three kinds of situations, when geographic level characteristics, second, managerial level characteristics, third, service of goods demand structure layer
Secondary feature；
Step 2: Agricultural Machinery Equipment safeguards Service Source requirement forecasting signature analysis：Predict demand of the regional to Service Source
Quantity, service network is built on this basis, agriculture is carried out using BP neural network method on the premise of Service Source is limited
Machine equipment repair demand for services is predicted；
Step 3: equipment maintenance influencing factors for demand is determined based on grey correlation analysis：The agricultural machinery for analyzing to obtain by step 2
Equipment repair demand for services prediction result, being associated property of influence factor is analyzed, so as to identify key factor therein, as
The input of subsequent prediction model；
Step 4: safeguard that BP neural network model is established in demand for services prediction for Agricultural Machinery Equipment：By an input layer, one or
Multiple hidden layers and an output layer are formed, and are not connected to between node layer, one layer of section under the influence of the output per node layer only
The input of point, specifically include BP neural network structure, network training and prediction.
A kind of 2. Agricultural Machinery Equipment service of goods needing forecasting method as claimed in claim 1, it is characterised in that described influence
Factor includes：Agricultural Machinery Equipment region, residing season, the area equipment recoverable amount, Agricultural Machinery Equipment workload, operating environment,
Area equipment running status and history repair status.
3. a kind of Agricultural Machinery Equipment service of goods needing forecasting method as claimed in claim 1 or 2, it is characterised in that described
Correlation analysis is analyzed by different the being associated property of degree of development trend between gray prediction identification system factor, so as to really
The fixing key factor for ringing Agricultural Machinery Equipment maintenance needs；Comprise the following steps that：
Step 1.1 Data Collection：Clearly required field first, and then Data Collection is carried out from different system, and herein
On the basis of complete basis statistical analysis, for subsequent prediction carry out data preparation；
Step 1.2 Grey Relational Model is established and solved：Each factor is analyzed using Grey Incidence Analysis to fill region agricultural machinery
The standby influence for safeguarding demand for services amount；The step of grey correlation analysis, is as follows：
Step1：Establish the raw data matrix x of each index of correlation in above tablei
xi=(xi(1),xi(2),…,xi(k)),…)
Wherein xi(k) initial data of the i factors in kth year is represented；
Step2：First value matrix x '
Above-mentioned raw data matrix is handled using equalization method, nondimensionalization processing is carried out to matrix, obtained
X '=(xi(1)/xi(1),xi(2)/xi(1),…,xi(k)/xi), (1) ...)=(xi′(1),xi′(2),…,xi′
(k),…)
Step3:Seek difference sequence Δ0i=(k)
<mrow>
<msub>
<mi>&Delta;</mi>
<mrow>
<mn>0</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>=</mo>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mo>|</mo>
<msubsup>
<mi>x</mi>
<mn>0</mn>
<mi>i</mi>
</msubsup>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msup>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>&prime;</mo>
</msup>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>|</mo>
<mo>,</mo>
<msub>
<mi>&Delta;</mi>
<mrow>
<mn>0</mn>
<mi>i</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>&Delta;</mi>
<mrow>
<mn>0</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
<mo>,</mo>
<msub>
<mi>&Delta;</mi>
<mrow>
<mn>0</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<msub>
<mi>&Delta;</mi>
<mrow>
<mn>0</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
<mo>,</mo>
<mn>...</mn>
<mo>)</mo>
</mrow>
</mrow>
Step4：Calculate correlation coefficient ξ0i(k)
<mrow>
<msub>
<mi>&xi;</mi>
<mrow>
<mn>0</mn>
<mi>i</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<munder>
<mi>min</mi>
<mi>i</mi>
</munder>
<munder>
<mi>min</mi>
<mi>k</mi>
</munder>
<msub>
<mi>&Delta;</mi>
<mrow>
<mn>0</mn>
<mi>i</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>&phi;</mi>
<munder>
<mi>max</mi>
<mi>i</mi>
</munder>
<munder>
<mi>max</mi>
<mi>k</mi>
</munder>
<msub>
<mi>&Delta;</mi>
<mrow>
<mn>0</mn>
<mi>i</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>&Delta;</mi>
<mrow>
<mn>0</mn>
<mi>i</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>&phi;</mi>
<munder>
<mi>max</mi>
<mi>i</mi>
</munder>
<munder>
<mi>max</mi>
<mi>k</mi>
</munder>
<msub>
<mi>&Delta;</mi>
<mrow>
<mn>0</mn>
<mi>i</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
</mrow>
Wherein φ is resolution ratio, for improving the significance of difference between incidence coefficient, φ ∈ (0,1),
Further, the φ takes 0.5.
Step5：Calculate grey relational grade γ0i
Grey relational grade is
Step6：Relational degree taxis
Obtain k by above-mentioned steps and tie up degree of association matrix, by the size of matrix element is ranked up obtain it is each because
Element and the degree of association and its influence power caused by equipment maintenance demand for services.
4. a kind of Agricultural Machinery Equipment service of goods needing forecasting method as claimed in claim 1 or 2, it is characterised in that further
Ground, the forward factor of relational degree taxis is chosen as BP nerve nets according to model requirements when the BP neural network model is established
The input item of network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711088618.8A CN107886358A (en) | 2017-11-08 | 2017-11-08 | A kind of Agricultural Machinery Equipment service of goods needing forecasting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711088618.8A CN107886358A (en) | 2017-11-08 | 2017-11-08 | A kind of Agricultural Machinery Equipment service of goods needing forecasting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107886358A true CN107886358A (en) | 2018-04-06 |
Family
ID=61779280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711088618.8A Pending CN107886358A (en) | 2017-11-08 | 2017-11-08 | A kind of Agricultural Machinery Equipment service of goods needing forecasting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107886358A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898245A (en) * | 2018-06-15 | 2018-11-27 | 上海探能实业有限公司 | A kind of needing forecasting method for Wind turbines components |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2187567A1 (en) * | 2008-11-18 | 2010-05-19 | Alcatel, Lucent | Predictive method and system for optimizing demands of connectivity services |
| CN104008428A (en) * | 2014-05-19 | 2014-08-27 | 上海交通大学 | Product service demand forecasting and resource optimization configuration method |
| CN106980905A (en) * | 2017-03-15 | 2017-07-25 | 南方电网科学研究院有限责任公司 | Distribution network reliability Forecasting Methodology and system |
| CN107194461A (en) * | 2017-05-27 | 2017-09-22 | 国网浙江省电力公司经济技术研究院 | A kind of artificial neural network distribution operation maintenance expense Forecasting Methodology |
-
2017
- 2017-11-08 CN CN201711088618.8A patent/CN107886358A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2187567A1 (en) * | 2008-11-18 | 2010-05-19 | Alcatel, Lucent | Predictive method and system for optimizing demands of connectivity services |
| CN104008428A (en) * | 2014-05-19 | 2014-08-27 | 上海交通大学 | Product service demand forecasting and resource optimization configuration method |
| CN106980905A (en) * | 2017-03-15 | 2017-07-25 | 南方电网科学研究院有限责任公司 | Distribution network reliability Forecasting Methodology and system |
| CN107194461A (en) * | 2017-05-27 | 2017-09-22 | 国网浙江省电力公司经济技术研究院 | A kind of artificial neural network distribution operation maintenance expense Forecasting Methodology |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898245A (en) * | 2018-06-15 | 2018-11-27 | 上海探能实业有限公司 | A kind of needing forecasting method for Wind turbines components |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Padhi et al. | Framework for selecting sustainable supply chain processes and industries using an integrated approach | |
| Kablan | Decision support for energy conservation promotion:: an analytic hierarchy process approach | |
| Aksoy et al. | Supplier selection and performance evaluation in just-in-time production environments | |
| Aragonés-Beltrán et al. | An ANP-based approach for the selection of photovoltaic solar power plant investment projects | |
| Wu et al. | An integrated decision-making model for sustainable photovoltaic module supplier selection based on combined weight and cumulative prospect theory | |
| Xu et al. | Optimisation of partial collaborative transportation scheduling in supply chain management with 3PL using ACO | |
| Yang et al. | A mixed activity-based costing and resource constraint optimal decision model for IoT-oriented intelligent building management system portfolios | |
| Mittal et al. | Ranking of drivers for green manufacturing implementation using fuzzy technique for order of preference by similarity to ideal solution method | |
| CN108932589A (en) | A kind of IT application in enterprises project implementation management system | |
| CN104008428B (en) | Service of goods requirement forecasting and resource preferred disposition method | |
| Hsueh et al. | Constructing a network model to rank the optimal strategy for implementing the sorting process in reverse logistics: case study of photovoltaic industry | |
| Masoumik et al. | A strategic approach to develop green supply chains | |
| CN104573877A (en) | Power distribution network equipment demand prediction and quantitative method and system | |
| CN111401804A (en) | Simulation-based engineering material supply chain network planning method and system | |
| Dadashpour et al. | Evaluation and ranking of sustainable third-party logistics providers using the D-analytic hierarchy process | |
| Flammini et al. | Reducing fossil fuel-based generation: Impact on wholesale electricity market prices in the North-Italy bidding zone | |
| Voskoboynikov | Accounting for growth in the USSR and Russia, 1950–2012 | |
| CN105550813A (en) | Commercial evaluation method for value network-based mechanized equipment cloud service resources | |
| Zandieh et al. | A new framework for dynamic sustainability balanced scorecard in order to strategic decision making in a turbulent environment | |
| Choudhary et al. | Risk investigation in circular economy: a hierarchical decision model approach | |
| Li et al. | A universal enterprise manufacturing services maturity model: a case study in a Chinese company | |
| Memari et al. | Hybrid wind-municipal solid waste biomass power plant location selection considering waste collection problem: a case study | |
| CN107886358A (en) | A kind of Agricultural Machinery Equipment service of goods needing forecasting method | |
| Liu | Internal economic management and performance evaluation method of enterprise based on balanced scorecard | |
| Ramanathan | Successful transfer of environmentally sound technologies for greenhouse gas mitigation: a framework for matching the needs of developing countries |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180406 |