CN107958327B - Project progress risk prediction method based on factor analysis and SOM network - Google Patents

Project progress risk prediction method based on factor analysis and SOM network Download PDF

Info

Publication number
CN107958327B
CN107958327B CN201711166590.5A CN201711166590A CN107958327B CN 107958327 B CN107958327 B CN 107958327B CN 201711166590 A CN201711166590 A CN 201711166590A CN 107958327 B CN107958327 B CN 107958327B
Authority
CN
China
Prior art keywords
rate
data
analysis
project progress
progress risk
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201711166590.5A
Other languages
Chinese (zh)
Other versions
CN107958327A (en
Inventor
沈润夏
罗飞
李晓东
余秦军
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.)
State Grid Sichuan Electric Power Co Ltd
Original Assignee
State Grid Sichuan Electric Power 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 State Grid Sichuan Electric Power Co Ltd filed Critical State Grid Sichuan Electric Power Co Ltd
Priority to CN201711166590.5A priority Critical patent/CN107958327B/en
Publication of CN107958327A publication Critical patent/CN107958327A/en
Application granted granted Critical
Publication of CN107958327B publication Critical patent/CN107958327B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—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 project progress risk prediction method based on factor analysis and an SOM network, which is characterized in that the factor analysis is combined with cluster analysis, the result is input to the SOM, observation data is not directly assigned to artificial neural network training, the load of the neural network is greatly reduced by using a statistical tool, the operation efficiency of the SOM is improved, and the dilemma that the neural network is not converged or falls into a local minimum value due to massive operation is avoided; the SOM network with strong pattern recognition capability is used for sample prediction, the training times are few, the classification is accurate, and the adaptability to artificial factors in the production reality is strong. Particularly, when the number of projects is large, the data size is large, and the data dimension is high, the prediction system fully utilizes the characteristics of the large data statistical analysis of MINITAB and the intelligent computing advantages of MATLAB.

Description

Project progress risk prediction method based on factor analysis and SOM network
Technical Field
The invention relates to a risk prediction method, in particular to a project progress risk prediction method based on factor analysis and a SOM network.
Background
Progress control is an important part of project management, and due to the fact that engineering involves multiple links, the whole project progress can be delayed when any loop lags. At present, project schedule management is mainly implemented by establishing a milestone plan and supervising, and by developing regular and irregular project conferences, concerts and other forms, a means of efficient quantitative judgment and accurate early warning in advance is still lacked, the bottleneck of 'post management' is difficult to break through, and the effect of pre-judging in advance and no rain and silk is achieved.
At present, a method for predicting project progress risks by using an SOM network exists in the market, but when the SOM network processes data with large data volume, massive computation is easy to cause the difficulty that the data is not converged or falls into a local minimum value.
Disclosure of Invention
The technical problem to be solved by the invention is that a method for project progress risk prediction by utilizing an SOM (sequence-oriented modeling) network exists in the market, but mass computation is easy to cause the difficulty of non-convergence or falling into a local minimum value when the SOM network processes data with large data quantity.
The invention is realized by the following technical scheme:
a project progress risk prediction method based on factor analysis and SOM network comprises an ERP system and further comprises the following steps which are carried out in sequence:
A. the method comprises the steps that analysis data of a material demand reporting rate x1, a non-material demand reporting rate x2, a contract signing rate x3, a bid inviting purchase rate x4, a material utilization rate x5, a contract performance rate x6 and an accumulated expenditure posting rate x7 are obtained through an ERP system, and the data are verified and corrected through the ERP system;
B. and (3) introducing x1-x7 into MINITAB software for factor analysis to obtain a potential factor Y1 for influencing progress: offline construction progress, Y2: material purchase progress, Y3: engineering service purchase progress;
C. performing cluster analysis on Y1, Y2 and Y3, and sorting into a project progress risk matrix T;
D. importing the project progress risk matrix T into MATLAB software, programming and establishing an SOM network in the MATLAB software, training data of the project progress risk matrix T, verifying the trained stable SOM network, and analyzing a test effect;
E. and packaging the training result of the historical data, the SOM network and the prediction result of the current data into a database by using ACCESS software to form an efficient and convenient project progress risk prediction query system.
The invention provides a project progress risk prediction method based on factor analysis and a SOM network, which can implement node big data through monthly projects of an ERT system and can accurately predict progress risks of a large number of projects. Meanwhile, by means of factor analysis and cluster analysis, the progress risk category of historical data is automatically judged, mode identification is carried out through an artificial neural network, specific reasons and a pre-control strategy of progress risk points are combed through a fault tree, an efficient engineering progress risk prediction system is established, the progress problem which can face in the future of the current project can be accurately and quickly predicted, the bottleneck problem of 'post-management' of project progress is effectively solved, and project progress management promotion is achieved. The SOM is input with the result by combining factor analysis and cluster analysis, and observation data are not directly assigned to artificial neural network training, so that the load of the neural network is greatly reduced by using a statistical tool, the operation efficiency of the SOM is improved, and the dilemma that the neural network is not converged or falls into a local minimum value due to mass operation is avoided; the SOM network with strong pattern recognition capability is used for sample prediction, the training times are few, the classification is accurate, and the adaptability to artificial factors in the production reality is strong. Particularly, when the number of projects is large, the data size is large, and the data dimension is high, the prediction system fully utilizes the characteristics of the large data statistical analysis of MINITAB and the intelligent computing advantages of MATLAB.
The method for acquiring the analysis data of the material demand reporting rate x1, the non-material demand reporting rate x2, the contract signing rate x3, the bid procurement rate x4, the material lead rate x5, the contract performance rate x6 and the accumulated expenditure posting rate x7 through the ERP system in the step A comprises the following steps:
a1, carrying out monthly material demand reporting, non-material demand reporting, contract signing, bid inviting and purchasing, material receiving, contract performing and accumulated expense posting data extraction on the past year project through an ERP system;
a2, processing the data extracted in the step A1 by using a normalization processing method to obtain analysis data of material demand reporting rate x1, non-material demand reporting rate x2, contract signing rate x3, bid procurement rate x4, material utilization rate x5, contract performance rate x6 and accumulated expenditure posting rate x 7.
The step A also comprises a step A3: integrating the data obtained from A2 into an excel table, and realizing data cleaning in excel to finally form x1-x7 which can be used for statistical analysis.
The expression of the factor analysis in the step B is as follows:
Figure BDA0001476411490000021
wherein x1—xmAnd x in step B1—x7Corresponds to, Y1—YnAnd Y1—Y3Corresponds to u1—um、e1—emIs a special factor, a1—amIs Y1—YnThe characteristic value of (2).
The method for performing cluster analysis on Y1, Y2 and Y3 in the step C and sorting the cluster analysis into the project progress risk matrix T comprises the following steps:
c1: y1, Y2 and Y3 have 3 variables, and data of each variable are divided into two cases of lag and no lag, so that 2 is generated3Namely 8 progress risk categories T1-T8;
c2: the characteristic values a of Y1, Y2 and Y3 are respectively assigned to T1-T81—a3；
C3: and (3) sorting the eigenvalues of T1-T8 corresponding to Y1, Y2 and Y3 into a project progress risk matrix T.
The method for training the data of the project progress risk matrix T in the step D comprises the following steps: and (4) learning each risk sample by taking the project progress risk matrix T as a standard input sample, and marking the neuron with the maximum output with the mark of the risk after learning is finished.
The number of training steps is 150 and 250. When the training steps are 150 steps and 250 steps, the balance degree between the classification precision and the training time and the calculated amount is high, and accurate classification can be realized within about 1 second.
And E, combing the reasons of various progress risks by using the fault tree, forming precontrol measures one by one, and packaging the analysis result of the fault tree and the precontrol measures into the project progress risk prediction query system. The finally formed query interface is simple to operate and visual in display, is suitable for various project managers to use, and can visually display precontrol measures.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. according to the project progress risk prediction method based on the factor analysis and the SOM network, the factor analysis plays roles of searching a core factor and reducing dimensions on big data, so that a data analysis result is closer to the actual production;
2. the invention relates to a project progress risk prediction method based on factor analysis and an SOM (sequence of events) network, which is used for predicting samples by using the SOM network with strong pattern recognition capability and certain fault tolerance, has less training times and accurate classification, has strong adaptability to various interference information such as human factors in production reality, and has higher prediction precision when the data volume is larger;
3. the invention relates to a project progress risk prediction method based on factor analysis and an SOM network, which is characterized in that the factor analysis is combined with clustering, the result is input to the SOM, observation data is not directly assigned to the SOM network for training, and the method is equivalent to greatly reducing the burden of a neural network by using a statistical tool and improving the operation efficiency of a prediction system.
4. The progress risk prediction system established by the method fully utilizes the characteristics of big data statistical analysis of MINITAB and the intelligent computing advantage of MATLAB, so that the prediction system has strong expansibility, and achievements can be popularized to various analysis projects with similar functions.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a schematic analysis flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of the factor analysis of the present invention;
FIG. 3 is a diagram of a SOM network architecture according to the present invention;
FIG. 4 is a schematic diagram of a SOM network prediction training process according to the present invention;
FIG. 5 is a diagram of the SOM network training results of the present invention;
FIG. 6 is a schematic diagram of a query interface established by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Example 1
As shown in fig. 1 to 5, the project progress risk prediction method based on factor analysis and SOM network of the present invention includes an ERP system, and further includes the following steps performed in sequence:
A. the method comprises the steps that analysis data of a material demand reporting rate x1, a non-material demand reporting rate x2, a contract signing rate x3, a bid inviting purchase rate x4, a material utilization rate x5, a contract performance rate x6 and an accumulated expenditure posting rate x7 are obtained through an ERP system, and the data are verified and corrected through the ERP system; the method for acquiring the analysis data of the material demand reporting rate x1, the non-material demand reporting rate x2, the contract signing rate x3, the bid procurement rate x4, the material lead rate x5, the contract performance rate x6 and the accumulated expenditure posting rate x7 through the ERP system in the step A comprises the following steps:
a1, carrying out monthly material demand reporting, non-material demand reporting, contract signing, bid inviting and purchasing, material receiving, contract performing and accumulated expense posting data extraction on the past year project through an ERP system;
a2, processing the data extracted in the step A1 by using a normalization processing method to obtain analysis data of material demand reporting rate x1, non-material demand reporting rate x2, contract signing rate x3, bid procurement rate x4, material utilization rate x5, contract performance rate x6 and accumulated expenditure posting rate x 7.
The step A also comprises a step A3: integrating the data obtained from A2 into an excel table, and realizing data cleaning in excel to finally form x1-x7 which can be used for statistical analysis.
B. And (3) introducing x1-x7 into MINITAB software for factor analysis to obtain a potential factor Y1 for influencing progress: offline construction progress, Y2: material purchase progress, Y3: engineering service purchase progress; the expression of the factor analysis in the step B is as follows:
Figure BDA0001476411490000041
wherein x1—x7And x in step B1—x7Corresponds to, Y1—Y3And Y1—Y3Corresponds to u1—u7、e1—e7Is a special factor, a1—a3Is Y1—Y3The characteristic value of (2).
C. Performing cluster analysis on Y1, Y2 and Y3, and sorting into a project progress risk matrix T; the method for performing cluster analysis on Y1, Y2 and Y3 in the step C and sorting the cluster analysis into the project progress risk matrix T comprises the following steps:
c1: y1, Y2 and Y3 have 3 variables, and data of each variable are divided into two cases of lag and no lag, so that 2 is generated3Namely 8 progress risk categories T1-T8;
c2: the characteristic values a of Y1, Y2 and Y3 are respectively assigned to T1-T81—a3；
C3: and (3) sorting the eigenvalues of T1-T8 corresponding to Y1, Y2 and Y3 into a project progress risk matrix T.
D. Importing the project progress risk matrix T into MATLAB software, programming and establishing an SOM network in the MATLAB software, training data of the project progress risk matrix T, verifying the trained stable SOM network, and analyzing a test effect; the method for training the data of the project progress risk matrix T in the step D comprises the following steps: and (4) learning each risk sample by taking the project progress risk matrix T as a standard input sample, and marking the neuron with the maximum output with the mark of the risk after learning is finished.
The number of training steps is 200 steps. When the training step number is 200 steps, the precision of classification and the balance between training time and calculated amount are high, and accurate classification can be realized within 1 second.
E. And packaging the training result of the historical data, the SOM network and the prediction result of the current data into a database by using ACCESS software to form an efficient and convenient project progress risk prediction query system.
And E, combing the reasons of various progress risks by using the fault tree, forming precontrol measures one by one, and packaging the analysis result of the fault tree and the precontrol measures into the project progress risk prediction query system. The finally formed query interface is simple to operate and visual in display, is suitable for various project managers to use, and can visually display precontrol measures.
Example 2
As shown in fig. 6, the present embodiment is an embodiment of predicting recent production engineering major repair projects of a certain power supply company using the results of embodiment 1. Taking the number of months as the frequency to obtain x1-x74212 pieces of initial data of the nodes are obtained, 4151 pieces of effective analysis data are finally formed after data integration and cleaning, data are continuously updated in an iteration mode in the analysis process, and the total data volume exceeds 20000 pieces. Analyzing and clustering the factors to generate Y1、Y2、Y3The median of the characteristic values and the risk categories corresponding to the median are arranged into a project progress risk matrix T as shown in Table 1.
Risk classes Y1Characteristic value Y2Characteristic value Y3Characteristic value
T1: without risk (normal progress) -0.5624 0.5324 -0.5585
T2: delayed risk of material procurement -0.0469 -5.0078 -0.8227
T3: non-material procurement and offline implementation lag risk 2.0076 0.9926 0.5782
T4: full delay risk of material and non-material purchase and offline implementation 2.237 0.3386 2.156
T5: risk of delayed material procurement and offline implementation 1.247 -1.2714 -0.1374
T6: delayed risk of non-material procurement -0.6411 0.4163 2.5159
T7: delayed risk of material and non-material procurement -0.6021 -0.685 0.1925
T8: risk of offline implementation hysteresis 0.7738 0.7343 -0.5919
TABLE 1 project progress Risk matrix
After the SOM network trains the matrix T, final pattern recognition data is formed, and a simple and quick query operation function is realized through a visualization means. The practice case of the invention utilizes ACCESS database software to develop a project progress risk prediction system, the data of factor analysis, clustering and SOM mode identification are all encapsulated in ACCESS, and the query result is shown as the attached figure 6 by combining a fault tree analysis chart corresponding to each type of risk.
Tests show that the prediction accuracy of the prediction system designed according to the method provided by the invention reaches more than 90%, and the method provided by the invention has a good project progress risk prediction effect. The pre-judgment system interface established by the ACCESS is visual, simple to operate, good in compatibility and interactivity, and very flexible in data storage mode. In the practical application stage, the latest results of the factor analysis and the SOM network prediction can be updated to the database in real time, the combination of the historical data discrimination system and the current data prediction system is realized, and the query interactive experience effect is good.
In conclusion, the project progress risk prediction method based on the factor analysis and the SOM network has the advantages of strong visualization, simple programming, wide application and the like, can realize the prior management and control of project progress risks, and can effectively improve the project progress management level.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (6)

1. A project progress risk prediction method based on factor analysis and SOM network comprises an ERP system and is characterized by further comprising the following steps of:
A. the method comprises the steps that analysis data of a material demand reporting rate x1, a non-material demand reporting rate x2, a contract signing rate x3, a bid inviting purchase rate x4, a material utilization rate x5, a contract performance rate x6 and an accumulated expenditure posting rate x7 are obtained through an ERP system, and the data are verified and corrected through the ERP system;
B. and (3) introducing x1-x7 into MINITAB software for factor analysis to obtain a potential factor Y1 for influencing progress: offline construction progress, Y2: material purchase progress, Y3: engineering service purchase progress;
C. performing cluster analysis on Y1, Y2 and Y3, and sorting into a project progress risk matrix T;
D. importing the project progress risk matrix T into MATLAB software, programming and establishing an SOM network in the MATLAB software, training data of the project progress risk matrix T, verifying the trained stable SOM network, and analyzing a test effect;
E. packaging a training result of historical data, an SOM network and a prediction result of current data into a database by using ACCESS software to form an efficient and convenient project progress risk prediction query system;
the expression of the factor analysis in the step B is as follows:
Figure FDA0003130586960000011
wherein x1—xmAnd x in step B1—x7Corresponds to, Y1—YnAnd Y1—Y3Corresponds to u1—um、e1—emIs a special factor, a1—amIs Y1—YnA characteristic value of (d);
the method for performing cluster analysis on Y1, Y2 and Y3 in the step C and sorting the cluster analysis into the project progress risk matrix T comprises the following steps:
c1: y1, Y2 and Y3 have 3 variables, and data of each variable are divided into two cases of lag and no lag, so that 2 is generated3Namely 8 progress risk categories T1-T8;
c2: the characteristic values a of Y1, Y2 and Y3 are respectively assigned to T1-T81—a3；
C3: and (3) sorting the eigenvalues of T1-T8 corresponding to Y1, Y2 and Y3 into a project progress risk matrix T.
2. The project progress risk prediction method based on factor analysis and SOM network as claimed in claim 1, wherein the method for obtaining analysis data of material demand reporting rate x1, non-material demand reporting rate x2, contract signing rate x3, bid procurement rate x4, material lead rate x5, contract performance rate x6 and accumulated expenditure posting rate x7 by ERP system in step A comprises the following steps:
a1, carrying out monthly material demand reporting, non-material demand reporting, contract signing, bid inviting and purchasing, material receiving, contract performing and accumulated expense posting data extraction on the past year project through an ERP system;
a2, processing the data extracted in the step A1 by using a normalization processing method to obtain analysis data of material demand reporting rate x1, non-material demand reporting rate x2, contract signing rate x3, bid procurement rate x4, material utilization rate x5, contract performance rate x6 and accumulated expenditure posting rate x 7.
3. The project progress risk prediction method based on factor analysis and SOM network as claimed in claim 2, wherein the step A further comprises the step A3: integrating the data obtained from A2 into an excel table, and realizing data cleaning in excel to finally form x1-x7 which can be used for statistical analysis.
4. The project progress risk prediction method based on factor analysis and SOM network as claimed in claim 1, wherein the method for training the data of the project progress risk matrix T in the step D is: and (4) learning each risk sample by taking the project progress risk matrix T as a standard input sample, and marking the neuron with the maximum output with the mark of the risk after learning is finished.
5. The project progress risk prediction method based on factor analysis and SOM network as claimed in claim 4, wherein the training steps are 150-250 steps.
6. The project progress risk prediction method based on factor analysis and SOM network as claimed in claim 1, wherein the step E further comprises using a fault tree to comb the causes of various progress risks and form precontrol measures one by one, and then packaging the fault tree analysis result and the precontrol measures into the project progress risk prediction query system.
CN201711166590.5A 2017-11-21 2017-11-21 Project progress risk prediction method based on factor analysis and SOM network Active CN107958327B (en)

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 CN107958327A (en) 2018-04-24
CN107958327B true 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)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
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
CN104200076B (en) * 2014-08-19 2015-09-02 钟亚平 A kind of Athletes damage risk method for early warning
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
CN106651025B (en) * 2016-12-20 2020-09-08 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 condition prediction method and device

Also Published As

Publication number Publication date
CN107958327A (en) 2018-04-24

Similar Documents

Publication Publication Date Title
CN108764663B (en) Method and system for generating and managing power customer portrait
CN106570778B (en) A kind of method that data integration based on big data is calculated with line loss analyzing
CN106909933B (en) A kind of stealing classification Forecasting Methodology of three stages various visual angles Fusion Features
Ribas et al. Multi-criteria risk assessment: Case study of a large hydroelectric project
CN104572449A (en) Automatic test method based on case library
CN107644279A (en) The modeling method and device of evaluation model
CN107590565A (en) A kind of method and device for building building energy consumption forecast model
CN108345670B (en) Service hotspot discovery method for 95598 power work order
CN111832861A (en) Resident load variable-scale portrait method and system based on big data platform
CN107918639A (en) Based on electric power big data main transformer peak load forecasting method and data warehouse
CN110147389A (en) Account number treating method and apparatus, storage medium and electronic device
CN109754122A (en) A kind of Numerical Predicting Method of the BP neural network based on random forest feature extraction
CN110321960A (en) A kind of prediction technique and system of plant produced element
CN111177128B (en) Metering big data batch processing method and system based on improved outlier detection algorithm
Sun et al. Using improved RFM model to classify consumer in big data environment
Sood Land market frictions in developing countries: Evidence from manufacturing firms in India
CN107958327B (en) Project progress risk prediction method based on factor analysis and SOM network
CN114676931B (en) Electric quantity prediction system based on data center technology
Zhang et al. A deep reinforcement learning algorithm for order acceptance decision of individualized product assembling
CN113435494A (en) Low-voltage resident user abnormal electricity utilization identification method and simulation system
CN109754186A (en) Method for calculating probability and device
CN111178763A (en) Enterprise energy efficiency data management method and device
CN105468871B (en) A kind of momenttum wheel success Envelope Analysis and application process
CN116258574B (en) Mixed effect logistic regression-based default rate prediction method and system
CN107798124A (en) Search system and method based on prediction modeling technique

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