CN100445901C - Dynamic cost control method for industrial process of procedure based on AR(p)model - Google Patents
Dynamic cost control method for industrial process of procedure based on AR(p)model Download PDFInfo
- Publication number
- CN100445901C CN100445901C CNB2007100367862A CN200710036786A CN100445901C CN 100445901 C CN100445901 C CN 100445901C CN B2007100367862 A CNB2007100367862 A CN B2007100367862A CN 200710036786 A CN200710036786 A CN 200710036786A CN 100445901 C CN100445901 C CN 100445901C
- Authority
- CN
- China
- Prior art keywords
- cost
- model
- value
- forecasting
- prediction
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A dynamic cost-control method of process industrial production course based on AR (p) model includes forming hardware control unit by production execution control including switch board, server, user terminal and enterprise network; and process control; using cost module as core of system flow to integrate basic information from real time databank with ERP enterprise resource planning data and data of related databank for carrying out dynamic cost-control based on data of cost-accounting.
Description
Technical field
The present invention relates to a kind of method of industrial control process, specifically is a kind of industrial process of procedure Dynamic Cost Control method based on AR (p) model.
Background technology
The market competition of process industrial globalization is fierce day by day, mainly show cost competition, product quality competition, sale service competition, wherein the competition of cost is basis and crucial, and reducing cost becomes important means and the approach that process industrial is enhanced competitiveness.The principal character of Dynamic Cost Control is: the production run Dynamic Cost Control under infotecies such as network, database are supported, each process cost data message in the real-time follow-up production run, be carried out to this analysis, prediction, monitor the every index variation tendency of cost, shorten the cost accounting cycle, thereby effectively improve the productivity effect of enterprise.The evolution of Dynamic Cost Control has embodied the trend of control system to networking, synthesization, distribution and intelligent development.In the production cost control of enterprise, forecasting of cost is a link primary and important in the cost control process.By forecasting of cost, can make enterprise that the cost level and the variation tendency thereof in future are accomplished correct assurance, thereby for the decision-making of the cost of enterprise provides the foundation of science, to reduce subjectivity and the blindness in the cost decision process.
As the important component part of cost control system, forecasting of cost provides foundation for formulating cost planning on the one hand, on the other hand for monitoring that the every index variation tendency of cost, the dynamic online mid-event control of cost provide information.Therefore, to the dynamic tracking of cost and accurately prediction, become the key link of Cost Control.At present the method for forecasting of cost is a lot, and more common have linear regression, non-linear regression, exponential smoothing, weighted mean, gray prediction, a neural network prediction etc.Yet above these traditional must be determined some parameters artificially based on the experience Forecasting Methodology, because it is many and complicated influence the factor of production cost, even artificially definite parameters, institute's data predicted is very not objective yet.The method based on AR (p) model prediction that development in recent years is got up is a kind of numerical method, because made full use of the dynamic characteristic information of system, is subjected to paying attention to widely.
Through literature search to prior art, find that Chinese patent application number is: 03111592, patent name is: " based on the metallurgical production process Dynamic Cost Control method of neural network ", this patent proposes a kind of metallurgical production process Dynamic Cost Control method based on neural network, it is characterized in that this method is to utilize Dynamic Cost Control method in a kind of metallurgical production process under the support of infotecies such as network, database.By intelligent control technologies such as neural networks, realize the method for metallurgical production process Dynamic Cost Control.Weak point, the deficiency below neural network exists: lack statistics mechanism, Variables Selection is very difficult, can't provide relevant conspicuousness statistical criteria, also is difficult to provide suitable Variables Selection criterion; Arithmetic speed is slow; The macro-forecast difficulty.
Summary of the invention
The objective of the invention is at the deficiencies in the prior art, utilize control technology and computer realization performance prediction cost, a kind of industrial process of procedure Dynamic Cost Control method based on AR (p) model is proposed, make its result according to cost accounting in relational database and the real-time data base, can real-time online carry out dynamic forecasting of cost, according to the automatic adjustment model parameter of least square method, just get predicted value near actual value, reach better control effect.
The present invention is achieved in that by the following technical programs
The present invention utilizes Dynamic Cost Control method in a kind of industrial process of procedure under the support of infotecies such as network, database, and this method is to realize by following software and hardware control setting.The hardware controls setting comprises settings such as switch, server, user terminal, control net, intranet.And the hardware controls setting is formed by producing execution control and process control two parts, wherein produce to carry out to control and be made up of switch, server, user terminal, intranet, its connection is to realize that by switch server is connected with the user terminal operation area.System flow is the center with the cost module, the dcs DCS of cost module (Distributed Control System) collection in worksite is that Back ground Information, ERP (Enterprise Resource Planning) Enterprise Resources Plan data are summarised in relational database with the real-time data base after the adjustment of data, in the data basis enterprising action attitude cost control of cost accounting.
Among the present invention, the dynamic forecasting of cost of the AR of employing (p) model is based on cost of products component relationship matrix, sets up the cost composition model; According to the mutual relationship between each cost factor, set up the cost forecast model; To predict that input anticipates and utilize AR (p) forecast model to predict, and draw at last and predict the outcome.
The control method concrete steps that the present invention proposes are as follows:
The first step, " forecasting of cost " function key is set on the operation interface of production run cost control, and set the model error value of (± 2%) by AR (p) forecast model, these data are delivered to that to form matrix with cost of products be to store in the relational database that constitutes of basis by industrial computer.When actual material consumption cost and cost of labor change (being that the object model error changes), perhaps the user wishes the error amount that obtains to require, also can online adjusting model order numerical value, make that predicted value is not have partially to estimate.
The forecasting of cost module realizes material consumption index prediction and Method of Product Cost Prediction, foundation is at the key-course (DCS of factory, PLC etc.) output data, and and enterprise management level between the real-time data base formed of the real time data set up, the formula and the time interval according to setting, can automatically provide the arbitrary period cost of products of (day, ten days, the moon etc.).
Second step, carried out the dynamic forecasting of cost program of AR (p) model that weaves in advance by the forecasting of cost module: elder generation proofreaies and correct the data of the DCS device collection of manufacturing enterprise, adopt the data after proofreading and correct to carry out the material consumption pricing, every cost accounting result is imported relational database.Because order that in advance can't judgment models, under the support of infotecies such as network, database, order that should first given model in modeling process is predicted cost and computation model error amount in view of the above by AR (p) model;
The AR model of setting up p rank is:
Wherein
P is respectively the model parameter of model AR (p) and the exponent number of model.a
tBe that average is zero, variance is σ
2White noise sequence.According to the cost data of certain production run, the parameter in the estimate equation is set up the cost model of this production run.Order
A=[a
P+1a
P+2L a
N]
T, y=[x
P+1x
P+2L x
N]
T,
Wherein N is the number of data, according to multiple regression theory, parameter matrix
Least-squares estimation be:
Concrete rule is: if mean value error on the occasion of the time, then should reduce the exponent number of AR (p) model; When if mean value error is negative value, then should increase the exponent number of AR (p) model.
The 3rd step, judge then between the predicted value of cost and the actual value with error whether in allowed band (± 2%), if error amount exceeds allowed band, program stops; If error amount is in allowed band, prediction of output result.
Core of the present invention is by AR (p) forecast model, sets up the mathematical relation between the day part cost data, forward predict l step best predictor according to history value by model in the t time, and the error between assurance predicted value and the actual value is in allowed band.By forecasting of cost, can make enterprise that the cost level and the variation tendency thereof in future are accomplished correct assurance, thereby for the decision-making of the cost of enterprise provides the foundation of science, to reduce subjectivity and the blindness in the cost decision process.
The 4th step, adopt information theory AIC criterion (Akaike Information Criterion is called for short AIC), the optimum order of judgment models, AIC criterion:
Calculate the exponent number p of model, wherein,
δ
a 2Be error variance.AIC criterion claims information criterion again, is a criterion utilizing maximum likelihood method to derive out.Get the best order of the minimum order of C (p) value at last, also determined AR (p) model parameter simultaneously as model.
The 5th step is according to the AR that calculates (p) model parameter
And exponent number p, predict l step best predictor forward in the t time
And calculating reliability forecasting between predicted value and the actual value according to predicting the outcome, i.e. correlation coefficient r is with its index as precision of prediction, prediction of output result then.Dynamic forecasting of cost value
With its actual value x
t(l) correlation coefficient r between has reflected this dependence indirectly, and is not easy to occur ill-conditioning problem, so related coefficient is high more, accuracy of predicting is also high more, can be it as one of index of estimating precision of prediction.
AR (p) the model prediction method that in the process industrial Dynamic Cost Control, adopts the present invention to propose, but maximum characteristics are exactly the forecasting of cost that carries out of real-time online, realized the dynamic tracking of cost and accurately prediction, thereby reduced cost, improved enterprise competitiveness and become possibility.So-called dynamic tracking generally, is exactly that predicted data can adopt cost accounting result in the real-time data base, can carry out forecasting of cost in real time by computer network.The formula and the time interval according to setting, can automatically provide the arbitrary period cost of products of (day, ten days, the moon etc.).When using the inventive method, the work that the technician will do is exactly: according to the actual requirements input time section, other work are finished automatically by relational database and real-time data base.The Dynamic Cost Control system can calculate the forecasting of cost value automatically, realizes the accurate estimation to cost.The user operates easier to be directly perceived, and method is simple, cost control is described by quantitative static state risen to the qualitative dynamic analysis and Control.Take the Dynamic Cost Control system of AR of the present invention (p) model prediction method can be widely used in the energy, metallurgy, petrochemical industry, etc. the cost control of process industrial.
Description of drawings
Fig. 1 realizes Dynamic Cost Control method system module pie graph in industrial process of procedure.
Fig. 2 realizes the forecasting of cost workflow diagram of Dynamic Cost Control method based on AR (p) model in industrial process of procedure.
Fig. 3 is the forecasting of cost value and the actual value curve map of certain production material in the embodiment of the invention.
Embodiment
Below in conjunction with accompanying drawing certain example of the present invention is elaborated: present embodiment is being to implement under the prerequisite with the technical solution of the present invention, provided detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
The dynamic forecasting of cost of thick methyl alcohol, refined methanol, CO, hydrogen that the forecasting of cost method of the present invention's proposition is used for certain process industrial enterprise, its objective is real time dynamic tracing reflection production run cost information stream, onlinely carry out dynamic cost forecast analysis, implement the production run cost control.The hardware controls setting of adopting comprises switch, server, uses and produce terminal, control net, intranet etc.According to realizing that Dynamic Cost Control method system module constitutes shown in Figure 1, intelligence instrument according to technological process, under the bus environment, data to dcs (DCS) are carried out the adjustment of data, to proofread and correct the result and import the MES system, carry out device operating load and material consumption cost analysis again, carry out the analysis of product direct cost according to Enterprise Resources Plan and device operating load, thereby can calculate product material expenses of labour and manufacturing cost.The formula and the time interval according to setting, can automatically provide the various products (CO, methyl alcohol, oxygen, hydrogen etc.) of arbitrary period (class, day, ten days, the moon etc.) or the dynamic cost of intermediate product (conversion gas, waste hot gas, purified gas, non-change purified gas etc.).
On cost prediction work process flow diagram 2 operations before entering forecasting of cost, earlier according to the data in the real-time data base, are adjusted the cost of various products, prepare for forecasting of cost provides data.The totally 30 light unit product consuming cost data of for example getting certain refined methanol wherein on May 8th, 2006 to June 16 are (unit: 100,000 yuan): 1.938,2.203,2.153,2.087,2.012,1.965,2.067,2.085,1.916,2.025,1.956,1.986,2.108,2.021,1.780,2.133,2.068,2.096,2.126,1.956,2.006,2.090,2.012,1.976,2.102,1.896,1.968,2.098,2.036,2.162, according to this time series forecasting June 19 to July 4.Delivery type exponent number p=3, this AR (p) model is:
Wherein: t=1, K, N, N=30.On this basis, enter AR (p) model prediction process.Present embodiment is a foundation with the statistics of these factors, constructs day consumption cost actual value and predicted value that an AR (3) model is analyzed four kinds of compositions such as thick methyl alcohol, refined methanol, CO, hydrogen, and the data result in a certain period sees Table 1.Concrete implementation step has following a few step:
The first step, " forecasting of cost " function key is set on the operation interface of production run cost control, and set the model error value of (± 2%) by AR (p) forecast model, these data are delivered to that to form matrix with cost of products be to store in the relational database that constitutes of basis by industrial computer.With the input data is the totally 30 light unit product consuming cost data composition real-time data base on May 8th, 2006 to June 16;
Second step, carry out AR (p) the model prediction program that weaves in advance by the forecasting of cost module, just set the order p=3 of AR (p) model, by AR (p) model cost is predicted;
The 3rd step, judge then between the predicted value of cost and the actual value with error whether in allowed band (± 2%), if error amount exceeds allowed band, program stops; If error amount in allowed band, calculates the parameter of AR (p) model according to least square method
The 4th step, adopt information theory AIC criterion (Akaike Information Criterion is called for short AIC), judge the optimum order p of AR (p) model;
The 5th step is according to the AR that calculates (p) model parameter
And exponent number p, predict l step best predictor forward in the t time
Prediction of output result then.
The actual value and the predicted value of the daily consumption of table 1 production run material in a certain period.
According to this time series forecasting refined methanol cost curve on June 19 to June 30 as shown in Figure 3.
The actual value and the predicted value of certain production run material daily consumption of table 1
Claims (3)
1, a kind of industrial process of procedure Dynamic Cost Control method based on AR (p) model is characterized in that, may further comprise the steps:
The first step, " forecasting of cost " function key is set on the operation interface of production run cost control, and set ± 2% model error value by AR (p) forecast model, these data are delivered to that to form matrix with cost of products be to store in the relational database that constitutes of basis by industrial computer;
In second step, the AR model of setting up p rank is:
Wherein
P is respectively the model parameter of model AR (p) and the exponent number of model, a
tBe that average is zero, variance is σ
2White noise sequence, carried out AR (p) the model prediction program that weaves in advance by the forecasting of cost module: elder generation proofreaies and correct the data of the DCS device collection of manufacturing enterprise, adopt the data after proofreading and correct to carry out the material consumption pricing, every cost accounting result is imported relational database; Because order that in advance can't judgment models, under the support of network, database information technology, order that should first given model in modeling process is predicted cost and computation model error amount in view of the above by AR (p) model;
The 3rd step, according to the order p of the given model of elder generation in modeling process, and the parameter that calculates AR (p) model according to least square method
AR model by the p rank
Can obtain t forecasting of cost value constantly
Judge the predicted value of cost then
With actual value x
tBetween error whether in allowed band ± 2%, that is:
If error amount exceeds allowed band, program stops; If error amount is in allowed band, prediction of output value
The 4th step, adopt the information theory AIC criterion, the optimum order of judgment models, AIC criterion:
Calculate the exponent number p of model, wherein,
δ
a 2Be error variance, get the best order of the minimum order of C (p) value at last, also determined AR (p) model parameter simultaneously as model;
The 5th step is according to the AR that calculates (p) model parameter
And exponent number p, predict l step best predictor forward in the t time
And calculating reliability forecasting between predicted value and the actual value according to predicting the outcome, i.e. correlation coefficient r is with its index as precision of prediction, prediction of output value then
And this predicted value
Be finally predicting the outcome of this program; Dynamic forecasting of cost value
With its actual value x
t(l) correlation coefficient r between has reflected this dependence indirectly, and is not easy to occur ill-conditioning problem, so related coefficient is high more, accuracy of predicting is also high more.
2, the industrial process of procedure Dynamic Cost Control method based on AR (p) model according to claim 1, it is characterized in that, in the first step, when actual material consumption cost and cost of labor change are that the object model error is when changing, perhaps the user wishes the error amount that obtains to require, online adjusting model order numerical value makes that predicted value is not have partially to estimate.
3, the industrial process of procedure Dynamic Cost Control method based on AR (p) forecast model according to claim 1, it is characterized in that, described forecasting of cost module realizes material consumption index prediction and Method of Product Cost Prediction, according to the output data of factory's key-course, and and enterprise management level between the real-time data base formed of the real time data set up, according to the formula and the time interval set, automatically provide the cost of products of arbitrary period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007100367862A CN100445901C (en) | 2007-01-25 | 2007-01-25 | Dynamic cost control method for industrial process of procedure based on AR(p)model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007100367862A CN100445901C (en) | 2007-01-25 | 2007-01-25 | Dynamic cost control method for industrial process of procedure based on AR(p)model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101004593A CN101004593A (en) | 2007-07-25 |
| CN100445901C true CN100445901C (en) | 2008-12-24 |
Family
ID=38703799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2007100367862A Expired - Fee Related CN100445901C (en) | 2007-01-25 | 2007-01-25 | Dynamic cost control method for industrial process of procedure based on AR(p)model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100445901C (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101510281B (en) * | 2009-03-23 | 2012-07-25 | 金蝶软件（中国）有限公司 | System and method for determining cost calculation step |
| WO2011085203A1 (en) * | 2010-01-08 | 2011-07-14 | Fluor Technologies Corporation | Systems for estimating new industrial plant operational readiness costs |
| CN104076686A (en) * | 2013-03-29 | 2014-10-01 | 沈阳铝镁设计研究院有限公司 | Method for controlling aluminum oxide production process dynamic cost |
| CN103984280B (en) * | 2014-05-15 | 2016-08-17 | 山西太钢不锈钢股份有限公司 | A kind of metallurgy that adapts to directly fills the interface method that heat is sent |
| US20160292325A1 (en) * | 2015-03-30 | 2016-10-06 | Uop Llc | Advanced data cleansing system and method |
| CN106019940B (en) * | 2016-06-21 | 2019-02-12 | 重庆科技学院 | Converter steelmaking process cost control method and system based on UKF neural network |
| CN106325242B (en) * | 2016-08-16 | 2019-09-24 | 苏州朋泰智能科技有限公司 | A kind of MES system based on modular control unit |
| CN106292584B (en) * | 2016-08-16 | 2019-07-23 | 苏州朋泰智能科技有限公司 | A kind of flexible manufacturing system based on modular control unit |
| CN106599487B (en) * | 2016-12-16 | 2019-10-25 | 天津大学 | The dynamic variance Realtime Alerts method regulated and controled based on ARIMA model and user |
| CN113505946A (en) * | 2021-08-09 | 2021-10-15 | 中车青岛四方机车车辆股份有限公司 | Production cost control method, system, storage medium and equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000032667A (en) * | 1998-07-08 | 2000-01-28 | Central Res Inst Of Electric Power Ind | Out-of-step prediction system the power system |
| US20020065790A1 (en) * | 2000-11-20 | 2002-05-30 | Toshihiro Oouchi | Cost estimation method, cost estimation apparatus, product manufacturing estimation method and product manufacturing estimation apparatus |
| JP2003050829A (en) * | 2001-08-07 | 2003-02-21 | Ricoh Co Ltd | Component cost estimation system, component cost estimation method and program |
| JP2003085342A (en) * | 2001-09-11 | 2003-03-20 | Ricoh Co Ltd | Model factory system, and system and method for cost estimation |
| US20040015458A1 (en) * | 2002-07-17 | 2004-01-22 | Nec Corporation | Autoregressive model learning device for time-series data and a device to detect outlier and change point using the same |
| JP2004118355A (en) * | 2002-09-24 | 2004-04-15 | Japan Research Institute Ltd | Power spectral density estimating method, power spectral density estimating device, computer program, and recording medium |
| CN1542658A (en) * | 2003-04-30 | 2004-11-03 | 东北大学 | Metallurgy production process dynamic cost control method based on neural network |
| US6859768B1 (en) * | 2000-03-03 | 2005-02-22 | The Beck Technology | Computer-implemented automated building design and modeling and project cost estimation and scheduling system |
-
2007
- 2007-01-25 CN CNB2007100367862A patent/CN100445901C/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000032667A (en) * | 1998-07-08 | 2000-01-28 | Central Res Inst Of Electric Power Ind | Out-of-step prediction system the power system |
| US6859768B1 (en) * | 2000-03-03 | 2005-02-22 | The Beck Technology | Computer-implemented automated building design and modeling and project cost estimation and scheduling system |
| US20020065790A1 (en) * | 2000-11-20 | 2002-05-30 | Toshihiro Oouchi | Cost estimation method, cost estimation apparatus, product manufacturing estimation method and product manufacturing estimation apparatus |
| JP2003050829A (en) * | 2001-08-07 | 2003-02-21 | Ricoh Co Ltd | Component cost estimation system, component cost estimation method and program |
| JP2003085342A (en) * | 2001-09-11 | 2003-03-20 | Ricoh Co Ltd | Model factory system, and system and method for cost estimation |
| US20040015458A1 (en) * | 2002-07-17 | 2004-01-22 | Nec Corporation | Autoregressive model learning device for time-series data and a device to detect outlier and change point using the same |
| JP2004118355A (en) * | 2002-09-24 | 2004-04-15 | Japan Research Institute Ltd | Power spectral density estimating method, power spectral density estimating device, computer program, and recording medium |
| CN1542658A (en) * | 2003-04-30 | 2004-11-03 | 东北大学 | Metallurgy production process dynamic cost control method based on neural network |
Non-Patent Citations (10)
| Title |
|---|
| AR模型在质量控制中的应用. 俞青峰等.计算机应用与软件，第22卷第2期. 2005 |
| AR模型在质量控制中的应用. 俞青峰等. 计算机应用与软件，第22卷第2期. 2005 * |
| 冶金工业过程动态成本控制系统及应用研究. 王冠等.信息与控制，第33卷第3期. 2004 |
| 冶金工业过程动态成本控制系统及应用研究. 王冠等. 信息与控制，第33卷第3期. 2004 * |
| 基于MES的动态成本控制系统设计及其应用. 刘威等.东北大学学报（自然科学版），第24卷第8期. 2003 |
| 基于MES的动态成本控制系统设计及其应用. 刘威等. 东北大学学报(自然科学版)，第24卷第8期. 2003 * |
| 工程项目成本控制流程的改进与模型构建. 卢娜等.陕西理工学院学报，第22卷第1期. 2006 |
| 工程项目成本控制流程的改进与模型构建. 卢娜等. 陕西理工学院学报，第22卷第1期. 2006 * |
| 谈AR(P)模型及其应用. 程葆伦.重庆职业技术学院学报（综合版），第12卷第3期. 2003 |
| 谈AR(P)模型及其应用. 程葆伦. 重庆职业技术学院学报(综合版)，第12卷第3期. 2003 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101004593A (en) | 2007-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100445901C (en) | Dynamic cost control method for industrial process of procedure based on AR(p)model | |
| CN101619850B (en) | Dispatching method and dispatching system based on load online forecasting of thermoelectric power system | |
| Wang et al. | Secondary forecasting based on deviation analysis for short-term load forecasting | |
| CN101408769B (en) | On-line energy forecasting system and method based on product ARIMA model | |
| CN108876132B (en) | Industrial enterprise energy efficiency service recommendation method and system based on cloud | |
| CN108198093B (en) | CPS-based intelligent building system | |
| CN112365029A (en) | Missing value processing method for air conditioner load prediction and air conditioner load prediction system | |
| CN112926770A (en) | Unified data metering and collecting system based on digital twins | |
| Solding et al. | Using simulation for more sustainable production systems–methodologies and case studies | |
| CN112332404B (en) | Intelligent management system and method for heating service | |
| CN109325880A (en) | A kind of Mid-long term load forecasting method based on Verhulst-SVM | |
| CN109118012A (en) | A kind of industrial dynamics various dimensions energy consumption cost prediction technique, system, storage medium and terminal | |
| CN110197296B (en) | Unit load prediction method based on time series similarity | |
| CN110895774A (en) | Thermal power plant cost fine management method | |
| CN106022542A (en) | Enterprise gateway load prediction method based on operation load characteristics | |
| Liu et al. | Application of fuzzy ordered weighted geometric averaging (FOWGA) operator for project delivery system decision-making | |
| Sancho et al. | Design and implementation of a decision support system for competitive electricity markets | |
| CN116826976A (en) | Distribution network operation automatic supervision control system | |
| CN112764400A (en) | Online automatic control quality evaluation and optimization system and method | |
| Xin et al. | Analysis of chaotic dynamics for aircraft assembly lines | |
| CN118100175B (en) | Energy management method of energy system based on distributed optimization | |
| Yakovenko et al. | STUDY OF DIGITAL TWINS AS THE DRIVING FORCE OF DIGITAL TRANSFORMATION AND ACHIEVING THE GOALS OF SUSTAINABLE DEVELOPMENT. | |
| Li | Optimization strategy of property energy management based on artificial intelligence | |
| CN103777569A (en) | Bending machine numerical control system with high bending accuracy | |
| Mu et al. | A fuzzy multi-objective model of QFD product planning integrating Kano model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20081224 Termination date: 20120125 |