CN107958327A - A kind of project process Risk Forecast Method based on factorial analysis and SOM networks - Google Patents
A kind of project process Risk Forecast Method based on factorial analysis and SOM networks Download PDFInfo
- Publication number
- CN107958327A CN107958327A CN201711166590.5A CN201711166590A CN107958327A CN 107958327 A CN107958327 A CN 107958327A CN 201711166590 A CN201711166590 A CN 201711166590A CN 107958327 A CN107958327 A CN 107958327A
- Authority
- CN
- China
- Prior art keywords
- msub
- rate
- analysis
- data
- project process
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- 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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computer Hardware Design (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of project process Risk Forecast Method based on factorial analysis and SOM networks, with factorial analysis combination cluster analysis, its result is defeated by SOM, and the indirect data that will observe are assigned to artificial neural network training, equivalent to the burden that neutral net is greatly reduced with statistical instrument, the operation efficiency of SOM is improved, avoids neutral net because magnanimity computing causes the predicament that does not restrain or be absorbed in local minimum；Application mode recognition capability stronger SOM networks carry out sample predictions, and frequency of training is few, classification is accurate, adaptable to the human factor in production reality.Particularly when project is especially more, data volume is especially big, data dimension is higher, which has fully used the big data statistical analysis speciality of MINITAB and the intelligence computation advantage of MATLAB.
Description
Technical field
The present invention relates to a kind of Risk Forecast Method, and in particular to a kind of project based on factorial analysis and SOM networks into
Spend Risk Forecast Method.
Background technology
Progress management and control is the pith of project management, and since engineering is related to multiple links, lagging all occurs in any ring
Whole project process may be delayed.Current project scheduling management, mainly by formulating milestone plan and implementation and supervision, with
And by carrying out the forms such as regular, irregular promotion of item meeting, coordination committee, still lack high effective quantization and judge, is in advance precisely pre-
Alert means, it is difficult to break through " subsequent management " bottleneck, do not reach the effect for prejudging, providing for a rainy day in advance.
There is the method that project process risk profile is carried out using SOM networks, still, SOM networks on the market now
Magnanimity computing is easy to cause the predicament for not restraining or being absorbed in local minimum when the data larger to data volume are handled.
The content of the invention
The technical problems to be solved by the invention are to exist to carry out project process wind using SOM networks on the market now
The method nearly predicted, still, when the SOM networks data larger to data volume are handled magnanimity computing be easy to cause do not restrain or
The predicament of local minimum is absorbed in, and it is an object of the present invention to provide a kind of project process risk profile based on factorial analysis and SOM networks
Method, solves the presence of the method that project process risk profile is carried out using SOM networks, still, SOM networks on the market now
Magnanimity computing is easy to cause asking for the predicament that does not restrain or be absorbed in local minimum when the data larger to data volume are handled
Topic.
The present invention is achieved through the following technical solutions：
A kind of project process Risk Forecast Method based on factorial analysis and SOM networks, including ERP system, further include according to
The following steps of secondary progress：
A, by ERP system acquisition, material requirements carry report rate x1, non-material requirements carry report rate x2, contract signing rate x3, trick
Mark rate of adoption x4, goods and materials receive rate x5, contract agreement fulfillment rate x6, the accumulative analysis data for paying the rate x7 that keeps accounts, and pass through ERP system pair
Above-mentioned data are verified and corrected；
B, x1-x7 is imported into MINITAB softwares and carries out factorial analysis, obtain the latent factor Y1 of influence progress：Applied under line
Work progress, Y2：Purchase of goods and materials progress, Y3：Engineering service procurement progress；
C, cluster analysis is carried out to Y1, Y2, Y3, is organized into project process risk Metrics T；
D, project process risk Metrics T is imported into MATLAB softwares, is programmed in MATLAB softwares and establish SOM networks, it is right
The data of project process risk Metrics T are trained, and the SOM networks stablized after training are verified, analysis test effect；
E, the prediction result of the training result of historical data, SOM networks and current data is encapsulated using ACCESS softwares
Into database, easily project process risk profile inquiry system is formed efficiently.
The present invention provides a kind of project process Risk Forecast Method based on factorial analysis and SOM networks, ERT can be passed through
The project implementation node big data of system monthly, while accurate Schedule schema prediction is carried out to bulk items.At the same time by because
Son analysis analysis, cluster analysis, the Schedule schema classification of automatic decision historical data, is known by artificial neural network into row mode
Not, Schedule schema point concrete reason and pre-control strategy are combed with fault tree, it is established that efficient project progress Risk Forecast System,
It can accurately, quickly predict the progress issue that current project future may face, effectively solve project process " subsequent management "
Bottleneck problem, realize project scheduling management lifted.With factorial analysis combination cluster analysis, its result is defeated by SOM, and it is non-straight
Connect and observation data are assigned to artificial neural network training, the negative of neutral net is greatly reduced equivalent to statistical instrument
Load, improves the operation efficiency of SOM, avoids neutral net because magnanimity computing causes not restrain or be absorbed in the tired of local minimum
Border；Application mode recognition capability stronger SOM networks carry out sample predictions, and frequency of training is few, classification is accurate, to production reality
In human factor it is adaptable.Particularly when project is especially more, data volume is especially big, data dimension is higher, this is pre-
Examining system has fully used the big data statistical analysis speciality of MINITAB and the intelligence computation advantage of MATLAB.
By ERP system acquisition, material requirements carry report rate x1, non-material requirements carry report rate x2, contract label in the step A
Order rate x3, bid and purchase rate x4, goods and materials and receive rate x5, contract agreement fulfillment rate x6, the side of the accumulative analysis data for paying the rate x7 that keeps accounts
Method comprises the following steps：
A1, by ERP system carrying out project over the years, monthly material requirements carry report, non-material requirements put forward report, contract signing, trick
Mark buying, goods and materials are received, contract is honoured an agreement, accumulative expenditure keeps accounts, and data are extracted；
A2, with normalization processing method handled the data extracted in step A1, is obtained material requirements and is put forward report rate
X1, non-material requirements carry report rate x2, contract signing rate x3, bid and purchase rate x4, goods and materials and receive rate x5, contract agreement fulfillment rate x6, tire out
Meter pays the analysis data for the rate x7 that keeps accounts.
Step A3 is further included in the step A：It is real in excel by the Data Integration that A2 is obtained in an excel table
Existing data cleansing, ultimately forms the x1-x7 available for statistical analysis.
The expression formula of factorial analysis is in the step B：
Wherein x1—xmWith the x in step B1—x7It is corresponding, Y1—YnWith Y1—Y3It is corresponding, u1—um、e1—emFor it is special because
Son, a1—amFor Y1—YnCharacteristic value.
In the step C to Y1, Y2, Y3 carry out cluster analysis, be organized into project process risk Metrics T method include with
Lower step：
C1：Y1, Y2, Y3 totally 3 variables, each variable data are divided into hysteresis and not stagnant latter two situation, and symbiosis is into 23I.e. 8
A Schedule schema classification T1-T8；
C2：Assign the characteristic value a of Y1, Y2, Y3 respectively for T1-T81—a3；
C3：The characteristic value that Y1, Y2, Y3 are corresponded to T1-T8 is organized into project process risk Metrics T.
The method being trained in the step D to the data of project process risk Metrics T is：With project process risk square
T is as standard input sample for battle array, each risk sample is learnt, after study, to the nerve with maximum output
Member is marked with the mark of the risk.
The step number of the training walks for 150-250.When train epochs walk for 150-250, when the precision of classification is with training
Between, the degree of balance is higher between calculation amount, it is already possible to realized Accurate classification at 1 second or so.
Further include in the step E and the reason for all kinds of Schedule schemas is combed using fault tree, and formed one by one pre-
Then failure tree analysis (FTA) result and Pre-control measures are also encapsulated into project process risk profile inquiry system by control measure.Last shape
Into query interface is easy to operate, intuitive display, be adapted to all kinds of project managers to use, can intuitively show Pre-control measures.
Compared with prior art, the present invention have the following advantages and advantages：
1st, a kind of project process Risk Forecast Method based on factorial analysis and SOM networks of the present invention, passes through factorial analysis
Play the role of finding core factor and dimensionality reduction to big data so that data results are closer to produce reality；
2nd, a kind of project process Risk Forecast Method based on factorial analysis and SOM networks of the present invention, application mode identification
Ability is strong, the SOM networks with certain fault-tolerance carry out sample predictions, and frequency of training is few, classification is accurate, to produce it is real in
All kinds of interference informations such as human factor it is adaptable, and the bigger precision of prediction of data volume is higher；
3rd, a kind of project process Risk Forecast Method based on factorial analysis and SOM networks of the present invention, with factorial analysis knot
Close cluster, its result be defeated by SOM, and it is indirect observation data are assigned to SOM network trainings, equivalent to statistical instrument
The burden of neutral net is greatly reduced, improves forecasting system operation efficiency.
4th, the Schedule schema forecasting system that the method for the present invention is established, has fully used the big data statistical analysis of MINITAB
The intelligence computation advantage of speciality and MATLAB, makes forecasting system have stronger autgmentability, achievement can extend to various similar
In the analysis project of function.
Brief description of the drawings
Attached drawing described herein is used for providing further understanding the embodiment of the present invention, forms one of the application
Point, do not form the restriction to the embodiment of the present invention.In the accompanying drawings：
Fig. 1 is the method for the present invention analysis process schematic diagram；
Fig. 2 is factorial analysis schematic diagram of the present invention；
Fig. 3 is SOM network structures of the present invention；
Fig. 4 is SOM neural network forecasts training process schematic diagram of the present invention；
Fig. 5 is SOM network trainings result figure of the present invention；
Fig. 6 is the query interface schematic diagram that the present invention establishes.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, with reference to embodiment and attached drawing, to this
Invention is described in further detail, and exemplary embodiment of the invention and its explanation are only used for explaining the present invention, do not make
For limitation of the invention.
Embodiment 1
As shown in Fig. 1 to 5, a kind of project process Risk Forecast Method based on factorial analysis and SOM networks of the present invention, bag
ERP system is included, further includes the following steps carried out successively：
A, by ERP system acquisition, material requirements carry report rate x1, non-material requirements carry report rate x2, contract signing rate x3, trick
Mark rate of adoption x4, goods and materials receive rate x5, contract agreement fulfillment rate x6, the accumulative analysis data for paying the rate x7 that keeps accounts, and pass through ERP system pair
Above-mentioned data are verified and corrected；Material requirements are obtained by ERP system in the step A and put forward report rate x1, non-material requirements
Carry report rate x2, contract signing rate x3, bid and purchase rate x4, goods and materials and receive rate x5, contract agreement fulfillment rate x6, accumulative expenditure and keep accounts rate x7
The methods of analysis data comprise the following steps：
A1, by ERP system carrying out project over the years, monthly material requirements carry report, non-material requirements put forward report, contract signing, trick
Mark buying, goods and materials are received, contract is honoured an agreement, accumulative expenditure keeps accounts, and data are extracted；
A2, with normalization processing method handled the data extracted in step A1, is obtained material requirements and is put forward report rate
X1, non-material requirements carry report rate x2, contract signing rate x3, bid and purchase rate x4, goods and materials and receive rate x5, contract agreement fulfillment rate x6, tire out
Meter pays the analysis data for the rate x7 that keeps accounts.
Step A3 is further included in the step A：It is real in excel by the Data Integration that A2 is obtained in an excel table
Existing data cleansing, ultimately forms the x1-x7 available for statistical analysis.
B, x1-x7 is imported into MINITAB softwares and carries out factorial analysis, obtain the latent factor Y1 of influence progress：Applied under line
Work progress, Y2：Purchase of goods and materials progress, Y3：Engineering service procurement progress；The expression formula of factorial analysis is in the step B：
Wherein x1—x7With the x in step B1—x7It is corresponding, Y1—Y3With Y1—Y3It is corresponding, u1—u7、e1—e7For it is special because
Son, a1—a3For Y1—Y3Characteristic value.
C, cluster analysis is carried out to Y1, Y2, Y3, is organized into project process risk Metrics T；In the step C to Y1, Y2,
Y3 carries out cluster analysis, and the method for being organized into project process risk Metrics T comprises the following steps：
C1：Y1, Y2, Y3 totally 3 variables, each variable data are divided into hysteresis and not stagnant latter two situation, and symbiosis is into 23I.e. 8
A Schedule schema classification T1-T8；
C2：Assign the characteristic value a of Y1, Y2, Y3 respectively for T1-T81—a3；
C3：The characteristic value that Y1, Y2, Y3 are corresponded to T1-T8 is organized into project process risk Metrics T.
D, project process risk Metrics T is imported into MATLAB softwares, is programmed in MATLAB softwares and establish SOM networks, it is right
The data of project process risk Metrics T are trained, and the SOM networks stablized after training are verified, analysis test effect；Institute
Stating the method being trained in step D to the data of project process risk Metrics T is：Mark is used as using project process risk Metrics T
Quasi- input sample, learns each risk sample, and after study, the wind is marked with to the neuron with maximum output
The mark of danger.
The step number of the training is 200 steps.When train epochs are 200 step, the precision of classification and training time, calculation amount
Between the degree of balance it is higher, it is already possible to realized Accurate classification within 1 second.
E, the prediction result of the training result of historical data, SOM networks and current data is encapsulated using ACCESS softwares
Into database, easily project process risk profile inquiry system is formed efficiently.
Further include in the step E and the reason for all kinds of Schedule schemas is combed using fault tree, and formed one by one pre-
Then failure tree analysis (FTA) result and Pre-control measures are also encapsulated into project process risk profile inquiry system by control measure.Last shape
Into query interface is easy to operate, intuitive display, be adapted to all kinds of project managers to use, can intuitively show Pre-control measures.
Embodiment 2
As shown in fig. 6, the present embodiment is with production technological transformation overhaul item of the achievement using embodiment 1 to certain electric company in recent years
Mesh is predicted as embodiment.Fetched with monthly for frequency, obtain x1-x7Node primary data be 4212, through Data Integration,
Effectively analysis data 4151 are ultimately formed after cleaning, the continuous iteration renewal of data, conceptual data amount surpass in the analysis process
20000.The Y that factorial analysis, cluster are generated afterwards1、Y2、Y3Characteristic value median and its corresponding kind of risk are organized into
Project process risk Metrics T is as shown in table 1.
| Kind of risk | Y1Characteristic value | Y2Characteristic value | Y3Characteristic value |
| T1：Devoid of risk (progress is normal) | -0.5624 | 0.5324 | -0.5585 |
| T2：Purchase of goods and materials lags risk | -0.0469 | -5.0078 | -0.8227 |
| T3：Implement hysteresis risk under non-purchase of goods and materials and line | 2.0076 | 0.9926 | 0.5782 |
| T4：Implement hysteresis risk comprehensively under goods and materials, non-purchase of goods and materials and line | 2.237 | 0.3386 | 2.156 |
| T5：Implement hysteresis risk under purchase of goods and materials and line | 1.247 | -1.2714 | -0.1374 |
| T6：Non- purchase of goods and materials lags risk | -0.6411 | 0.4163 | 2.5159 |
| T7：Goods and materials and non-purchase of goods and materials hysteresis risk | -0.6021 | -0.685 | 0.1925 |
| T8：Implement hysteresis risk under line | 0.7738 | 0.7343 | -0.5919 |
1 project process risk Metrics of table
After SOM network training matrixes T, final pattern-recognition data are formed, and it is simple fast by visualizing means realization
Prompt inquiry operation function.The present invention's puts into practice case with the exploitation design object Schedule schema prediction of ACCESS database software
System, factorial analysis, cluster, the data of SOM pattern-recognitions are all packaged in ACCESS, and are combined per class risk pair
The failure tree analysis (FTA) figure answered, query result is as shown in Figure 6.
After tested, the prediction accuracy of forecasting system designed by method reaches more than 90% according to the present invention, present invention tool
There is good project process risk profile effect.Anticipation system interface that ACCESS is established is directly perceived, with simple, compatible and hand over
Mutual property is good, and data storage method is very flexible., can be by factorial analysis and SOM neural network forecasts most in the practice principle stage
Database is updated to during new fructufy, realizes merging for historical data judgement system and current data forecasting system, is had good
Inquiry interactive experience effect.
To sum up, the project process Risk Forecast Method based on factorial analysis and SOM networks, which has, visualizes strong, programming letter
The advantages that single, generally applicable, it can be achieved that the management and control in advance of project process risk, can effectively lift project scheduling management level.
Above-described embodiment, has carried out the purpose of the present invention, technical solution and beneficial effect further
Describe in detail, it should be understood that the foregoing is merely the embodiment of the present invention, be not intended to limit the present invention
Protection domain, within the spirit and principles of the invention, any modification, equivalent substitution, improvement and etc. done, should all include
Within protection scope of the present invention.
Claims (8)
1. a kind of project process Risk Forecast Method based on factorial analysis and SOM networks, including ERP system, it is characterised in that
Further include the following steps carried out successively：
A, by ERP system obtain material requirements carry report rate x1, non-material requirements carry report rate x2, contract signing rate x3, bid adopt
Purchase rate x4, goods and materials receive rate x5, contract agreement fulfillment rate x6, the accumulative analysis data for paying the rate x7 that keeps accounts, by ERP system to above-mentioned
Data are verified and corrected；
B, x1-x7 is imported into MINITAB softwares and carries out factorial analysis, obtain the latent factor Y1 of influence progress：Construct under line into
Degree, Y2：Purchase of goods and materials progress, Y3：Engineering service procurement progress；
C, cluster analysis is carried out to Y1, Y2, Y3, is organized into project process risk Metrics T；
D, project process risk Metrics T is imported into MATLAB softwares, is programmed in MATLAB softwares and establish SOM networks, to project
The data of Schedule schema matrix T are trained, and the SOM networks stablized after training are verified, analysis test effect；
E, the prediction result of the training result of historical data, SOM networks and current data is packaged into number using ACCESS softwares
According to storehouse, easily project process risk profile inquiry system is formed efficiently.
2. a kind of project process Risk Forecast Method based on factorial analysis and SOM networks according to claim 1, it is special
Sign is that material requirements carry report rate x1, non-material requirements propose report rate x2, contract signing by ERP system acquisition in the step A
Rate x3, bid and purchase rate x4, goods and materials receive rate x5, contract agreement fulfillment rate x6, the method for the accumulative analysis data for paying the rate x7 that keeps accounts
Comprise the following steps：
A1, carry out by ERP system project over the years monthly material requirements carry report, non-material requirements carry report, contract signing, bid are adopted
Purchase, goods and materials are received, contract is honoured an agreement, accumulative expenditure keeps accounts, and data are extracted；
A2, with normalization processing method handled the data extracted in step A1, is obtained material requirements and is carried report rate x1, non-
Material requirements carry report rate x2, contract signing rate x3, bid and purchase rate x4, goods and materials and receive rate x5, contract agreement fulfillment rate x6, accumulative expenditure
The analysis data of the rate that keeps accounts x7.
3. a kind of project process Risk Forecast Method based on factorial analysis and SOM networks according to claim 2, it is special
Sign is, step A3 is further included in the step A：It is real in excel by the Data Integration that A2 is obtained in an excel table
Existing data cleansing, ultimately forms the x1-x7 available for statistical analysis.
4. a kind of project process Risk Forecast Method based on factorial analysis and SOM networks according to claim 1, it is special
Sign is that the expression formula of factorial analysis is in the step B：
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<msub>
<mi>u</mi>
<mn>1</mn>
</msub>
<mo>+</mo>
<msub>
<mi>a</mi>
<mn>1</mn>
</msub>
<msub>
<mi>Y</mi>
<mn>1</mn>
</msub>
<mo>+</mo>
<mo>...</mo>
<mo>+</mo>
<msub>
<mi>a</mi>
<mi>n</mi>
</msub>
<msub>
<mi>Y</mi>
<mi>n</mi>
</msub>
<mo>+</mo>
<msub>
<mi>e</mi>
<mn>1</mn>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>......</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
<mo>=</mo>
<msub>
<mi>u</mi>
<mi>m</mi>
</msub>
<mo>+</mo>
<msub>
<mi>a</mi>
<mn>1</mn>
</msub>
<msub>
<mi>Y</mi>
<mn>1</mn>
</msub>
<mo>+</mo>
<mo>...</mo>
<mo>+</mo>
<msub>
<mi>a</mi>
<mi>n</mi>
</msub>
<msub>
<mi>Y</mi>
<mi>n</mi>
</msub>
<mo>+</mo>
<msub>
<mi>e</mi>
<mi>m</mi>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
Wherein x1—xmWith the x in step B1—x7It is corresponding, Y1—YnWith Y1—Y3It is corresponding, u1—um、e1—emFor specific factor,
a1—amFor Y1—YnCharacteristic value.
5. a kind of project process Risk Forecast Method based on factorial analysis and SOM networks according to claim 4, it is special
Sign is, cluster analysis is carried out to Y1, Y2, Y3 in the step C, be organized into the method for project process risk Metrics T include with
Lower step：
C1：Y1, Y2, Y3 totally 3 variables, each variable data are divided into hysteresis and not stagnant latter two situation, and symbiosis is into 23I.e. 8 into
Spend kind of risk T1-T8；
C2：Assign the characteristic value a of Y1, Y2, Y3 respectively for T1-T81—a3；
C3：The characteristic value that Y1, Y2, Y3 are corresponded to T1-T8 is organized into project process risk Metrics T.
6. a kind of project process Risk Forecast Method based on factorial analysis and SOM networks according to claim 1, it is special
Sign is that the method being trained in the step D to the data of project process risk Metrics T is：With project process risk square
T is as standard input sample for battle array, each risk sample is learnt, after study, to the nerve with maximum output
Member is marked with the mark of the risk.
7. a kind of project process Risk Forecast Method based on factorial analysis and SOM networks according to claim 6, it is special
Sign is that the step number of the training walks for 150-250.
8. a kind of project process Risk Forecast Method based on factorial analysis and SOM networks according to claim 1, it is special
Sign is, further includes in the step E and the reason for all kinds of Schedule schemas is combed using fault tree, and form pre-control one by one
Then failure tree analysis (FTA) result and Pre-control measures are also encapsulated into project process risk profile inquiry system by measure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711166590.5A CN107958327B (en) | 2017-11-21 | 2017-11-21 | Project progress risk prediction method based on factor analysis and SOM network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711166590.5A CN107958327B (en) | 2017-11-21 | 2017-11-21 | Project progress risk prediction method based on factor analysis and SOM network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107958327A true CN107958327A (en) | 2018-04-24 |
| CN107958327B CN107958327B (en) | 2021-09-14 |
Family
ID=61965164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711166590.5A Active CN107958327B (en) | 2017-11-21 | 2017-11-21 | Project progress risk prediction method based on factor analysis and SOM network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107958327B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678512A (en) * | 2013-12-26 | 2014-03-26 | 大连民族学院 | Data stream merge sorting method under dynamic data environment |
| CN104200076A (en) * | 2014-08-19 | 2014-12-10 | 钟亚平 | Athlete athletic injury risk early warning method |
| CN105868928A (en) * | 2016-04-29 | 2016-08-17 | 西南石油大学 | High-dimensional evaluating method for oil field operational risk |
| CN106228274A (en) * | 2016-08-03 | 2016-12-14 | 河海大学常州校区 | Photovoltaic power station power generation amount Forecasting Methodology based on SOM Neural Network Data clustering recognition |
| CN106651025A (en) * | 2016-12-20 | 2017-05-10 | 中国人民解放军空军装备研究院雷达与电子对抗研究所 | Traffic situation prediction method and apparatus |
-
2017
- 2017-11-21 CN CN201711166590.5A patent/CN107958327B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678512A (en) * | 2013-12-26 | 2014-03-26 | 大连民族学院 | Data stream merge sorting method under dynamic data environment |
| CN104200076A (en) * | 2014-08-19 | 2014-12-10 | 钟亚平 | Athlete athletic injury risk early warning method |
| CN105868928A (en) * | 2016-04-29 | 2016-08-17 | 西南石油大学 | High-dimensional evaluating method for oil field operational risk |
| CN106228274A (en) * | 2016-08-03 | 2016-12-14 | 河海大学常州校区 | Photovoltaic power station power generation amount Forecasting Methodology based on SOM Neural Network Data clustering recognition |
| CN106651025A (en) * | 2016-12-20 | 2017-05-10 | 中国人民解放军空军装备研究院雷达与电子对抗研究所 | Traffic situation prediction method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107958327B (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jain et al. | Modelling the enablers of industry 4.0 in the Indian manufacturing industry | |
| Zhang et al. | Game theory based real‐time shop floor scheduling strategy and method for cloud manufacturing | |
| Chen et al. | A novel hybrid ICA-FA algorithm for multiperiod uncertain portfolio optimization model based on multiple criteria | |
| Trappey et al. | Genetic algorithm dynamic performance evaluation for RFID reverse logistic management | |
| Yang et al. | Multiple attribute decision-making methods for the dynamic operator allocation problem | |
| Olson et al. | Risk management models for supply chain: a scenario analysis of outsourcing to China | |
| Khalifehzadeh et al. | A four-echelon supply chain network design with shortage: Mathematical modeling and solution methods | |
| Peng et al. | Deep reinforcement learning approach for capacitated supply chain optimization under demand uncertainty | |
| Mahvi et al. | Optimal bidding strategy in a competitive electricity market based on agent-based approach and numerical sensitivity analysis | |
| Moghadam et al. | Inventory lot-sizing with supplier selection using hybrid intelligent algorithm | |
| Tang | An approach to budget allocation for an aerospace company—Fuzzy analytic hierarchy process and artificial neural network | |
| Anbazhagan et al. | A neural network approach to day-ahead deregulated electricity market prices classification | |
| CN108898243A (en) | A kind of Transmission Network of Power System security test system | |
| Krejci et al. | Modeling food supply chains using multi-agent simulation | |
| Mosadegh et al. | A fuzzy multi-objective goal programming model for solving an aggregate production planning problem with uncertainty | |
| Saraeian et al. | Optimal autonomous architecture for uncertain processes management | |
| Min | A rule based expert system for analysis of mobile sales data on fashion market | |
| Ballesteros-Olza et al. | Using reclaimed water to cope with water scarcity: An alternative for agricultural irrigation in Spain | |
| Waeto et al. | Forecasting time series movement direction with hybrid methodology | |
| Gholami et al. | An integrated analytical framework based on fuzzy DEMATEL and fuzzy ANP for competitive market strategy selection | |
| Kaghazchi et al. | Prioritization of agricultural water distribution operating systems based on the sustainable development indicators | |
| CN113610474A (en) | Inventory management method and management system based on event network | |
| CN108053136A (en) | A kind of car dealer's analysis on Achievements expert system based on neutral net | |
| Ebrahimnejad et al. | A model for risk evaluation in construction projects based on fuzzy MADM | |
| Abad et al. | Green closed-loop supply chain network design: A novel bi-objective chance-constraint approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |