CN102831269A - Method for determining technological parameters in flow industrial process - Google Patents
Method for determining technological parameters in flow industrial process Download PDFInfo
- Publication number
- CN102831269A CN102831269A CN2012102921647A CN201210292164A CN102831269A CN 102831269 A CN102831269 A CN 102831269A CN 2012102921647 A CN2012102921647 A CN 2012102921647A CN 201210292164 A CN201210292164 A CN 201210292164A CN 102831269 A CN102831269 A CN 102831269A
- Authority
- CN
- China
- Prior art keywords
- quality
- rule
- parameter
- technological parameter
- optimization
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a method for determining technological parameters in a flow industrial process. The method includes the steps of firstly, collecting production data, and using the technological parameters as input and product quality and output to build quality models; secondly, using rule extraction to extract corresponding rules between the input and the output from the production data so as to form a rule library; and thirdly, using optimization to find rules corresponding to given quality indexes according to the given quality indexes, initiating the technological parameters in the range of the rules, using the initiated technological parameters as input of the quality models to predict product quality, calculating errors between the predicted quality and the quality indexes, and correcting to find optimal parameters to enable the errors between the predicted quality and the quality indexes to be minimum. By the method, product yield is improved effectively and production cost is lowered.
Description
Technical field
The present invention relates to a kind of determination method of the process flow industry process technological parameter based on data-driven.
Background technology
Producing Process of Processing Industry generally has the features such as multivariable, non-linear, close coupling, product quality changes and changed with working condition, such as disturbed by material composition, operating condition, a variety of uncertain factors of equipment state, and running often has dynamic characteristic, it is difficult to mechanism model come accurate description.Simultaneously as its production process is extremely complex, there is larger gap in the product quality of domestic process industry production, be mainly shown as unstable product quality, life-span are low, percent defective is high etc. compared with same kind of products at abroad.
Product quality control after all or technological parameter setting problem, i.e., according to the quality index backstepping technological parameter of product.
Currently, in domestic major Producing Process of Processing Industry, the adjustment of technological parameter is mainly by artificial experience, the method gathered using exhaustive examination carries out parameter setting, when working conditions change is frequent, only relies on artificial experience and be difficult to timely and accurately adjusting process parameter, cause product quality effectively to control, waste serious, and waste product easily occur.
It is to solve the key issue place that product quality is rationally controlled using a kind of rational method is come optimization process technological parameter and is set.
Process industry can have accumulated substantial amounts of creation data in long-term production process, at present, the extensive use of substantial amounts of novel meter, networked meters and sensing technology in the industrial production, obtain the real time data in a large amount of actual production process, these data have contained the various rules in production process, data driven technique can be utilized, the quantitative relationship between technological parameter and product quality is obtained from substantial amounts of data, and then realizes the various desired functions such as forecast, monitoring, diagnosis and the optimization of system.
The content of the invention
The technical problem to be solved in the invention is that the defect for overcoming prior art there is provided a kind of determination method of the process flow industry process technological parameter based on data-driven, and it can effectively improve production product yield, reduce production cost.
To solve the above problems, the present invention is adopted the following technical scheme that:
The invention provides a kind of determination method of the process flow industry process technological parameter based on data-driven, methods described comprises the following steps:
1)Quality is modeled:According to the creation data gathered in actual production process, by input of process parameter, product quality be that quality model is set up in output;
2)Rule extraction:According to the creation data gathered in actual production process, the rule of correspondence inputted using the method for rule extraction from extracting data between output, formation rule storehouse;
3)Process parameter optimizing:Using optimization method according to given quality index, find the corresponding rule of given quality index, and in regular scope initialization procedure technological parameter, using the parameter of initialization as quality model input, predict product quality, calculate the error with quality index, according to error, technological parameter is modified using optimization method, constraints is used as using rule during amendment, it is ensured that revised parameter is corrected still in regular scope by optimizing, one group of optimal parameter is found, makes the predicted value of model and the error minimum of quality index.
The quality modeling is using neutral net, SVMs, least square, piece least square, core offset minimum binary or core Ridge Regression Modeling Method.
The rule extraction uses decision tree, RULE EXTRACTION FROM NEURAL NETWORKS or SVMs Rule Extracting Algorithm.
Process parameter optimizing uses particle group optimizing, ant group optimization, fish school optimization, genetic algorithm or immune algorithm.
The advantage of the invention is that:The present invention uses data driven technique, using optimization method, and speed of searching optimization is fast, simple to operate;Make the optimum position of the quality index of product quickly in target range.
The result that each optimizing is obtained can be offline predicted product quality using quality model, it is to avoid manually often adjusting primary parameter all needs online verification, so that causing substantial amounts of waste product;Moreover, in optimization process, being constrained using rule parameter, it is ensured that the parameter that optimizing is obtained meets produce reality.The present invention can weave into visual software with computer language, and quality index only need to be given on software interface, and required process parameter value just can be obtained quickly so that the optimization of process parameter is determined more conveniently and quickly.
The present invention is applied widely, extends in the process industries such as Coal Chemical Industry, petrochemical industry, metallurgy, solves the empirical and trial sex chromosome mosaicism of processing parameter setting in production process, not only energy-saving, and to stabilized product quality, improves production efficiency significant.
Brief description of the drawings
Fig. 1 is the technology of the present invention route map.
Fig. 2 is neutral net quality model predictive simulation result figure.
Fig. 3 is decision tree diagram.
Fig. 4 is BP neural network structure chart.
Fig. 5 is decision tree structure figure.
Fig. 6 is particle shifting principle figure.
Embodiment
The determination method of process flow industry process technological parameter of the embodiment 1 based on data-driven
Technology Roadmap is as shown in figure 1, concretely comprise the following steps:
1st step, sets up quality model extracting method:Existing creation data is normalized first, the influence of different dimensions is eliminated, quality model is set up using the data extracted in production process, and utilize the rule knowledge between the method Extraction technique and quality index of rule extraction, formation rule storehouse;
2nd step, the initial value of setting quality target value, the initial value of algorithm parameter and process parameter:Technological parameter first finds its corresponding rule in initialization according to given quality target value, then initializes technological parameter in the scope of rule, reduces optimizing space, accelerates speed of searching optimization;
3rd step, quality model:Using quality model, product quality is predicted according to the technological parameter after optimization;
4th step, calculates product quality:According to the product quality of prediction, calculate the error with given quality target value, and in this, as the evaluation index of optimization, error is smaller, it was demonstrated that with desired value closer to;
5th step, judges whether product quality meets requirement:Error amount is contrasted with given threshold value, if less than threshold value, meeting and requiring, then stops optimization, its corresponding procedure parameter value is optimal value, obtains process parameter value, obtains product quality measured value, goes to the 8th step;
If more than threshold value, being unsatisfactory for requiring, going to the 6th step;
6th step, using optimization method optimizing:According to optimization method, renewal is optimized to process parameter;Obtain new process parameter value;
Whether the 7th step, judge new process parameter value in regular scopeIf in regular scope, going to 3 steps;
Otherwise, by regular Correction and Control parameter, process parameter is limited in the scope of rule, go to 3 steps;
8th step, calculates measured value and desired value error:It is compared using measured value with desired value, if its error is within given allowable error accuracy rating, meets and require, then declarative procedure technological parameter can use, terminate;If its error is modified beyond given allowable error precision to quality model and rule, the new quality model of acquisition and rule go to 2 steps.
The emulation experiment of embodiment 2
In order to verify the validity of the inventive method, the optimization to the technological parameter in the present invention determines that method carries out emulation experiment.
The emulation experiment is by taking certain iron and steel enterprise's strip hot-dip galvanizing production process as an example, according to given quality index, to optimize determination technological parameter.
Technological parameter includes:Air pressurep, air knife to strip distancedAnd unit speedv, target product quality is zinc layer weightw。
In process of production, regulation is typically passed throughp、d、vThese three technological parameters control the zinc layer weight above stripw。
When producing a zinc layer weight specified, it is necessary to while adjust these three parameters, be operated at present mainly by artificial experience, cause zinc layer weight not controlled quickly and accurately, waste product occur.
The present embodiment chooses 1000 groups of strip hot-dip galvanizing creation datas, data is normalized first, i.e.,:
Neutral net quality model is set up using 800 groups of data, and checking is predicted using remaining 200 groups of data.
Predicted root mean square error reaches 0.065, and precision reaches 94.5%,
Neutral net quality model predictive simulation result figure is as shown in Figure 2.
The decision tree extracting rule of embodiment 3
Equally, using identical data, using decision tree extracting rule, remaining 200 groups of data is verified to model.
Here first have to classify to zinc layer weight data, required according to the difference to zinc layer weight, zinc layer weight is divided into 3 classifications, i.e., 115< w ≤146(1 class)、80 ≤w <115(2 classes)、48 ≤w <80(3 classes), and this 3 classifications and are inputted into attribute as the root node of decision treep、d、vThen as the leaf node of tree.
Fig. 3 is obtained decision tree, and its corresponding rule is:
Regular precision reaches 94.34%.
To plate 60 g/m to belt steel surface2During zinc layer weight, it can be found that the zinc layer weight corresponds to rule 4, that is, technological parameter span is constrained.
The particle group optimizing method of embodiment 4
Utilize the method for particle group optimizing, it is first determined the number of population is 50, and iterations is 150, the position of particle is initialized in regular scopeX i = (p,v,d)(That is technological parameter)And speed, assigned error is in ± 0.5g/m2In the range of, zinc layer weight is with 60g/m2As set-point, the corresponding zinc layer weight of each particle is predicted using neutral net quality model, and is contrasted with given progress, if wherein the error of some particle is in ± 0.5g/m2In the range of, then the position of the particle is required technological parameter;If being unsatisfactory for requiring, particle is iterated, the position of more new particle and speed, and using the position of rule constraint particle, defined precision is required or reach until meeting.Optimized by successive ignition, obtained result is:,,, in regular scope, zinc layer weight is 60g/m2, fully meet requirement.
The BP neural network method of embodiment 5
BP neural network structure shows only one of which hidden layer as shown in figure 4, neutral net is generally divided into input layer 1, hidden layer 2, output layer 3, Fig. 1.In order to without loss of generality, it is assumed here that havehIndividual hidden layer,PIndividual training sample, i.e.,PIndividual inputoutput pair, (k=1,2 ...,P).Wherein,ForkIndividual sample input vector:, " 1 " represents first layer,nFor the neuron number in the dimension of input sample, i.e. input layer;ForkThe desired output vector of individual sample:,mFor the neuron number in the dimension of output vector, i.e. output layer.
The activation primitive of output layer and hidden layer is here by taking S type activation primitives as an example.
ForkIndividual sample, thehThe of layer networkiThe output valve of individual neuron can be obtained by the forward-propagating process of working signal:
Wherein,Forh- 1 layerjThe output valve of individual neuron,ForhThe of layeriIndividual neuron andh- 1 layerjThe connection weight of individual neuron,ForhThe of layeriThe threshold value of individual neuron.
Input layer from network can obtain the output valve of each neuron successively to hidden layer, then to output layer with formula (1.1), (1.2).
The derivation of BP algorithm mathematic(al) representation is given below.For convenience of explanation, illustrate below all withkExemplified by individual sample.
Output layerkThe desired output of individual sample and the mean square error of reality output are:
In order to improve the learning ability of neutral net, learning rate is added in network training, i.e.,:
(1.5)
In actual learning process, learning rateInfluence to learning process is very big.It is the step-length by gradient search.
Therefore, modified weight formula is:
Threshold value correction formula is:
(1.7)
Wherein,tFor times of revision.
By formula (1.1), (1.2), (1.3) can obtain:,
Then
(1.9)
By formula (1.1), (1.2), (13) are understood
(1) output layer
According to formula (1.10) and formula (1.11), have
(2) hidden layer
If h<H, then the layer is hidden layer, is at this moment considered as effect of the last layer to it.
By taking three-layer network as an example (i.e. last layer be output layer, and only one layer hidden layer)
Note
The weights of output layer, threshold value correction formula:
The weights of middle hidden layer, threshold value correction formula:
Four formula (1.13) derived above, (1.14), (1.15), (1.16) are four important formulas in BP algorithm implementation process.
The rule extraction uses traditional decision-tree, and other Rule Extracting Algorithms similarly can be with extracting rule, such as RULE EXTRACTION FROM NEURAL NETWORKS, SVMs rule extraction.
The traditional decision-tree of embodiment 6
Decision Tree algorithms are the selection standards by the use of information gain as attribute, and the maximum attribute of selection information gain produces decision-making tree node, to cause when testing each non-leaf node, can obtain the classification information maximum on being tested trial record.Branch is set up by the different values of the attribute, subset recursive call this method to each branch sets up the branch of decision-making tree node again, untill all collection only include same category of data, finally obtain a decision tree, I can be obtained by rule from decision tree, and the form of decision tree is as shown in Figure 5.
If X is the set of training data sample, altogethernIndividual sample,mIndividual classification, the destination of study is exactly willnIndividual training sample is divided intomClass, is designated asIf, theiThe training sample number of class is, a sample belongs toiThe probability of class is, then the sample X classification needed for expectation information be given by:
If attribute A hasvIndividual different value,In the case of belong toiThe example number of class is,, i.e.,Value for testing attribute A isWhen belong toiThe probability of class, noteForWhen example set, then training sample set pair attribute A its expect information be:
The information gain of acquisition is by attribute A top sets:
It is bigger, illustrate that the information for selecting testing attribute A to be provided for classification is bigger, therefore, according toAs testing attribute selection standard split training sample, obtain into decision tree, decision tree finally changed into rule.
The process parameter optimizing uses particle group optimizing (Particle Swarm Optimization, PSO) method, the rule that bond quality model and decision tree obtain realizes the optimization of technological parameter, other optimization methods are equally applicable to this patent, such as ant group algorithm, fish-swarm algorithm, genetic algorithm.
The particle group optimizing method of embodiment 7
In PSO algorithms, the potential solution of each optimization problem is a bird in search space, is referred to as " particle ", i.e., the position of each particle is exactly a potential solution.Particle number is referred to as population scalem, theiIndividual particle existsdThe positional representation of dimension space is, (i=1,2,…,m), speedDetermine the displacement of particle search mikey iterations.Calculate each particle, fitness function typically determines by function optimised in practical problem.According to each particle, update each particleWith.Here whether " optimal " is determined by specific optimization problem:If the problem maximizing, particle fitness is got over greatly optimal;If conversely, the problem is minimized, particle fitness is smaller to be optimal.Particle updates its speed and position by the individual extreme value of dynamic tracking and global most value.Particle updates its speed and position according to below equation:
(3.2)
In formulaiForiIndividual particle, j=1,2 ...,d。c1、c2 be Studying factors, that is, is respectively regulated to the maximum step-length of global preferably particle and individual preferably particle direction flight, if too small, if particle, too big, can cause to fly to target area suddenly, or fly over target area possibly remote from target area.tFor iterations, rand () is the random number being evenly distributed between (0-1).At no point in the update process, particle is in maximal rate of the speed per one-dimensional flight no more than algorithm setting, i.e.,, otherwiseOr=.Set largerThe ability of searching optimum of particle populations can be ensured,The local search ability of smaller then population is strengthened.Meanwhile, particle is also limited in allowed band per one-dimensional coordinate。
The shifting principle of particle is as shown in Figure 6.
Utilize comprising the following steps that for particle group optimizing technological parameter:
1) quality index T and optimization precision E are given, using technological parameter as the position of particle, particle number is initializedm, each particle speedV, positionX、Speed maximum, largest loop iterations;
2) individual extreme value place is initialized, global extremum position, individual extreme value, global extremum;
3) using the position of particle as input, the corresponding quality of each particle is calculated using the quality model above set upY, and and quality indexTContrast, calculates the fitness of particle;
5) position and the speed of each particle are updated;
According to formula (3.1), the speed of formula (3.2) more new particle and position, and consider the speed after updating and position whether in the range of restriction.
OtherwiseIt is constant.
Meanwhile, in order to consider technological parameter in each searching process all in the scope of rule, this patent finds corresponding rule according to given quality index T first, that is, obtains the scope of technological parameter, if the scope of a certain parameter for [,], then constrain as follows:
6) whether number of comparisons reaches maximum iteration or default precision.If meeting default precision, i.e.,, algorithmic statement, last time iteration、It is exactly optimal value position and the optimal value required by us;Otherwise return to step 3), algorithm continues iteration.
Finally it should be noted that:Obviously, above-described embodiment is only intended to clearly illustrate example of the present invention, and the not restriction to embodiment.For those of ordinary skill in the field, it can also make other changes in different forms on the basis of the above description.There is no necessity and possibility to exhaust all the enbodiments.And among the obvious change or variation thus amplified out are still in protection scope of the present invention.
Claims (4)
1. a kind of determination method of process flow industry process technological parameter, it is characterised in that methods described comprises the following steps:
1)Quality is modeled:According to the creation data gathered in actual production process, by input of process parameter, product quality be that quality model is set up in output;
2)Rule extraction:According to the creation data gathered in actual production process, the rule of correspondence inputted using the method for rule extraction from extracting data between output, formation rule storehouse;
3)Process parameter optimizing:Using optimization method according to given quality index, find the corresponding rule of given quality index, and in regular scope initialization procedure technological parameter, using the parameter of initialization as quality model input, predict product quality, calculate the error with quality index, according to error, technological parameter is modified using optimization method, constraints is used as using rule during amendment, it is ensured that revised parameter is corrected still in regular scope by optimizing, one group of optimal parameter is found, makes the predicted value of model and the error minimum of quality index.
2. a kind of determination method of process flow industry process technological parameter as claimed in claim 1, it is characterised in that:The quality modeling is using neutral net, SVMs, least square, piece least square, core offset minimum binary or core Ridge Regression Modeling Method.
3. a kind of determination method of process flow industry process technological parameter as claimed in claim 1, it is characterised in that:The rule extraction uses decision tree, RULE EXTRACTION FROM NEURAL NETWORKS or SVMs Rule Extracting Algorithm.
4. a kind of determination method of process flow industry process technological parameter as claimed in claim 1, it is characterised in that:Process parameter optimizing uses particle group optimizing, ant group optimization, fish school optimization, genetic algorithm or immune algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210292164.7A CN102831269B (en) | 2012-08-16 | 2012-08-16 | Method for determining technological parameters in flow industrial process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210292164.7A CN102831269B (en) | 2012-08-16 | 2012-08-16 | Method for determining technological parameters in flow industrial process |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102831269A true CN102831269A (en) | 2012-12-19 |
CN102831269B CN102831269B (en) | 2015-03-25 |
Family
ID=47334404
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210292164.7A Expired - Fee Related CN102831269B (en) | 2012-08-16 | 2012-08-16 | Method for determining technological parameters in flow industrial process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102831269B (en) |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077288A (en) * | 2013-01-23 | 2013-05-01 | 重庆科技学院 | Small sample test data-oriented method for soft measurement and formula decision of multielement alloy material |
CN103440527A (en) * | 2013-07-29 | 2013-12-11 | 辽宁大学 | Method for improving ant colony algorithm optimization support vector machine parameters |
CN103472783A (en) * | 2013-09-03 | 2013-12-25 | 邵光震 | Monitoring method and system for production in petrochemical industry |
CN103473597A (en) * | 2013-09-05 | 2013-12-25 | 中国寰球工程公司 | Method for optimizing natural gas liquefaction process technological parameters based on genetic algorithm |
CN104049624A (en) * | 2014-07-07 | 2014-09-17 | 蓝星(北京)技术中心有限公司 | Chemical product production mode optimization method and device and continuous type chemical system |
CN104346442A (en) * | 2014-10-14 | 2015-02-11 | 济南大学 | Process object data-oriented rule extracting method |
CN104375478A (en) * | 2014-09-04 | 2015-02-25 | 太极计算机股份有限公司 | Method and device for online predicting and optimizing product quality in steel rolling production process |
CN104463372A (en) * | 2014-12-17 | 2015-03-25 | 中国科学院自动化研究所 | Traffic evacuation destination part random allocation proportion determination method |
CN106096788A (en) * | 2016-06-21 | 2016-11-09 | 重庆科技学院 | Converter steelmaking process cost control method based on PSO_ELM neutral net and system |
CN103955760B (en) * | 2014-04-22 | 2017-01-25 | 江苏祥兆文具有限公司 | Aluminum rod oxidation dyeing technological parameter optimization expert system |
CN106444391A (en) * | 2016-12-07 | 2017-02-22 | 凤城市宝山炭素有限公司 | Forecasting method for pitch volume applied to control on processes of mixing, nipping and cooling materials |
CN106646234A (en) * | 2016-12-28 | 2017-05-10 | 湖南坤宇网络科技有限公司 | Boiler main motor fault early-warning method based on decision tree system |
CN106682778A (en) * | 2016-12-28 | 2017-05-17 | 湖南坤宇网络科技有限公司 | Boiler flue pressure warning method based on decision tree system |
CN106683352A (en) * | 2016-12-28 | 2017-05-17 | 湖南坤宇网络科技有限公司 | Boiler fire tube perforating early-warning method based on decision tree system |
CN106710162A (en) * | 2016-12-28 | 2017-05-24 | 湖南坤宇网络科技有限公司 | Boiler furnace scaling early warning method based on decision tree system |
CN106709605A (en) * | 2016-12-28 | 2017-05-24 | 湖南坤宇网络科技有限公司 | Method for early warning of boiler fire tube corrosion based on decision tree system |
CN106710160A (en) * | 2016-12-28 | 2017-05-24 | 湖南坤宇网络科技有限公司 | Decision-making tree system-based boiler clausilium smoke temperature early-warning method |
CN106781306A (en) * | 2016-12-28 | 2017-05-31 | 湖南坤宇网络科技有限公司 | A kind of boiler air duct based on decision tree system blocks method for early warning |
CN106781307A (en) * | 2016-12-28 | 2017-05-31 | 湖南坤宇网络科技有限公司 | A kind of boiler blow-off stop valve early warning method for failure based on decision tree system |
CN106781308A (en) * | 2016-12-28 | 2017-05-31 | 湖南坤宇网络科技有限公司 | A kind of anti-explosive door for boiler early warning method for failure based on decision tree system |
CN106781342A (en) * | 2016-12-28 | 2017-05-31 | 湖南坤宇网络科技有限公司 | A kind of boiler air preheater fault early warning method based on decision tree system |
CN106991242A (en) * | 2017-04-12 | 2017-07-28 | 柳州市同维达豪科技有限公司 | A kind of control method of plate property optimization |
CN107545105A (en) * | 2017-08-22 | 2018-01-05 | 贵州大学 | A kind of part resilience parameter optimization in forming method based on PSO |
CN109100975A (en) * | 2018-09-03 | 2018-12-28 | 深圳市智物联网络有限公司 | A kind of parameter optimization method and system |
CN109410208A (en) * | 2018-11-14 | 2019-03-01 | 成都极致智造科技有限公司 | The machine learning identification of Wear Mechanism of Abrasive Belt and process parameter optimizing method |
CN110210718A (en) * | 2019-05-09 | 2019-09-06 | 厦门邑通软件科技有限公司 | A method of the promotion product qualification rate based on Multidimensional decision-making woodlot |
CN110609523A (en) * | 2019-07-18 | 2019-12-24 | 浙江工业大学 | Cooperative control method for units in primary tea leaf making process |
CN110827169A (en) * | 2019-10-30 | 2020-02-21 | 云南电网有限责任公司信息中心 | Distributed power grid service monitoring method based on grading indexes |
CN110989522A (en) * | 2019-12-06 | 2020-04-10 | 东北大学 | Multi-steel-coil-oriented optimal setting method for technological parameters in continuous annealing production process |
CN111597729A (en) * | 2020-05-27 | 2020-08-28 | 北京天泽智云科技有限公司 | Method and system for optimizing technological parameters of processing equipment |
CN111723492A (en) * | 2020-06-30 | 2020-09-29 | 哈工大机器人(合肥)国际创新研究院 | Production process parameter determination method based on simulation verification |
CN112465274A (en) * | 2020-12-30 | 2021-03-09 | 镇江龙源铝业有限公司 | Intelligent management system for production workshop |
CN113642160A (en) * | 2021-07-26 | 2021-11-12 | 南京工业大学 | Aluminum alloy engine cylinder body casting process design optimization method based on BP neural network and fish swarm algorithm |
CN113704869A (en) * | 2021-07-20 | 2021-11-26 | 深圳市万泽航空科技有限责任公司 | Optimal design method for casting process of flame stabilizer |
CN113994281A (en) * | 2019-07-03 | 2022-01-28 | 富士胶片株式会社 | Optimization support device, method, and program |
CN113987938A (en) * | 2021-10-27 | 2022-01-28 | 北京百度网讯科技有限公司 | Process parameter optimization method, device, equipment and storage medium |
CN115795983A (en) * | 2023-01-29 | 2023-03-14 | 江苏沙钢集团有限公司 | Wire quality control method, device, equipment and storage medium |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102314527A (en) * | 2010-07-01 | 2012-01-11 | 上海宝信软件股份有限公司 | Metallurgical quality modeling method based on factory modeling |
-
2012
- 2012-08-16 CN CN201210292164.7A patent/CN102831269B/en not_active Expired - Fee Related
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102314527A (en) * | 2010-07-01 | 2012-01-11 | 上海宝信软件股份有限公司 | Metallurgical quality modeling method based on factory modeling |
Non-Patent Citations (1)
Title |
---|
张文兴: "神经网络规则抽取及其在带钢热镀锌质量控制参数设定中的应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (49)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077288A (en) * | 2013-01-23 | 2013-05-01 | 重庆科技学院 | Small sample test data-oriented method for soft measurement and formula decision of multielement alloy material |
CN103077288B (en) * | 2013-01-23 | 2015-08-26 | 重庆科技学院 | Towards hard measurement and the formula decision-making technique thereof of the multicomponent alloy material of small sample test figure |
CN103440527A (en) * | 2013-07-29 | 2013-12-11 | 辽宁大学 | Method for improving ant colony algorithm optimization support vector machine parameters |
CN103472783A (en) * | 2013-09-03 | 2013-12-25 | 邵光震 | Monitoring method and system for production in petrochemical industry |
CN103472783B (en) * | 2013-09-03 | 2015-09-16 | 邵光震 | The method for supervising produced for petrochemical industry and system |
CN103473597A (en) * | 2013-09-05 | 2013-12-25 | 中国寰球工程公司 | Method for optimizing natural gas liquefaction process technological parameters based on genetic algorithm |
CN103955760B (en) * | 2014-04-22 | 2017-01-25 | 江苏祥兆文具有限公司 | Aluminum rod oxidation dyeing technological parameter optimization expert system |
CN104049624A (en) * | 2014-07-07 | 2014-09-17 | 蓝星(北京)技术中心有限公司 | Chemical product production mode optimization method and device and continuous type chemical system |
CN104375478A (en) * | 2014-09-04 | 2015-02-25 | 太极计算机股份有限公司 | Method and device for online predicting and optimizing product quality in steel rolling production process |
CN104375478B (en) * | 2014-09-04 | 2018-09-14 | 太极计算机股份有限公司 | A kind of method and device of Rolling production process product quality on-line prediction and optimization |
CN104346442A (en) * | 2014-10-14 | 2015-02-11 | 济南大学 | Process object data-oriented rule extracting method |
CN104346442B (en) * | 2014-10-14 | 2017-10-20 | 济南大学 | A kind of Rules extraction method of Process-Oriented object data |
CN104463372A (en) * | 2014-12-17 | 2015-03-25 | 中国科学院自动化研究所 | Traffic evacuation destination part random allocation proportion determination method |
CN104463372B (en) * | 2014-12-17 | 2018-05-08 | 中国科学院自动化研究所 | A kind of traffic evacuation destination part is randomly assigned ratio-dependent method |
CN106096788A (en) * | 2016-06-21 | 2016-11-09 | 重庆科技学院 | Converter steelmaking process cost control method based on PSO_ELM neutral net and system |
CN106096788B (en) * | 2016-06-21 | 2021-10-22 | 重庆科技学院 | Converter steelmaking process cost control method and system based on PSO _ ELM neural network |
CN106444391A (en) * | 2016-12-07 | 2017-02-22 | 凤城市宝山炭素有限公司 | Forecasting method for pitch volume applied to control on processes of mixing, nipping and cooling materials |
CN106444391B (en) * | 2016-12-07 | 2019-11-05 | 辽宁丹炭科技集团有限公司 | Applied to the pitch amount prediction technique in the cool material process control of kneading |
CN106710160A (en) * | 2016-12-28 | 2017-05-24 | 湖南坤宇网络科技有限公司 | Decision-making tree system-based boiler clausilium smoke temperature early-warning method |
CN106781306A (en) * | 2016-12-28 | 2017-05-31 | 湖南坤宇网络科技有限公司 | A kind of boiler air duct based on decision tree system blocks method for early warning |
CN106781307A (en) * | 2016-12-28 | 2017-05-31 | 湖南坤宇网络科技有限公司 | A kind of boiler blow-off stop valve early warning method for failure based on decision tree system |
CN106781308A (en) * | 2016-12-28 | 2017-05-31 | 湖南坤宇网络科技有限公司 | A kind of anti-explosive door for boiler early warning method for failure based on decision tree system |
CN106781342A (en) * | 2016-12-28 | 2017-05-31 | 湖南坤宇网络科技有限公司 | A kind of boiler air preheater fault early warning method based on decision tree system |
CN106710162A (en) * | 2016-12-28 | 2017-05-24 | 湖南坤宇网络科技有限公司 | Boiler furnace scaling early warning method based on decision tree system |
CN106646234A (en) * | 2016-12-28 | 2017-05-10 | 湖南坤宇网络科技有限公司 | Boiler main motor fault early-warning method based on decision tree system |
CN106683352A (en) * | 2016-12-28 | 2017-05-17 | 湖南坤宇网络科技有限公司 | Boiler fire tube perforating early-warning method based on decision tree system |
CN106682778A (en) * | 2016-12-28 | 2017-05-17 | 湖南坤宇网络科技有限公司 | Boiler flue pressure warning method based on decision tree system |
CN106709605A (en) * | 2016-12-28 | 2017-05-24 | 湖南坤宇网络科技有限公司 | Method for early warning of boiler fire tube corrosion based on decision tree system |
CN106991242A (en) * | 2017-04-12 | 2017-07-28 | 柳州市同维达豪科技有限公司 | A kind of control method of plate property optimization |
CN107545105A (en) * | 2017-08-22 | 2018-01-05 | 贵州大学 | A kind of part resilience parameter optimization in forming method based on PSO |
CN109100975A (en) * | 2018-09-03 | 2018-12-28 | 深圳市智物联网络有限公司 | A kind of parameter optimization method and system |
CN109410208A (en) * | 2018-11-14 | 2019-03-01 | 成都极致智造科技有限公司 | The machine learning identification of Wear Mechanism of Abrasive Belt and process parameter optimizing method |
CN110210718A (en) * | 2019-05-09 | 2019-09-06 | 厦门邑通软件科技有限公司 | A method of the promotion product qualification rate based on Multidimensional decision-making woodlot |
CN113994281A (en) * | 2019-07-03 | 2022-01-28 | 富士胶片株式会社 | Optimization support device, method, and program |
CN110609523A (en) * | 2019-07-18 | 2019-12-24 | 浙江工业大学 | Cooperative control method for units in primary tea leaf making process |
CN110827169B (en) * | 2019-10-30 | 2022-07-05 | 云南电网有限责任公司信息中心 | Distributed power grid service monitoring method based on grading indexes |
CN110827169A (en) * | 2019-10-30 | 2020-02-21 | 云南电网有限责任公司信息中心 | Distributed power grid service monitoring method based on grading indexes |
CN110989522A (en) * | 2019-12-06 | 2020-04-10 | 东北大学 | Multi-steel-coil-oriented optimal setting method for technological parameters in continuous annealing production process |
CN110989522B (en) * | 2019-12-06 | 2022-09-09 | 东北大学 | Multi-steel-coil-oriented optimal setting method for technological parameters in continuous annealing production process |
CN111597729A (en) * | 2020-05-27 | 2020-08-28 | 北京天泽智云科技有限公司 | Method and system for optimizing technological parameters of processing equipment |
CN111597729B (en) * | 2020-05-27 | 2023-07-25 | 北京天泽智云科技有限公司 | Processing equipment technological parameter optimization method and system |
CN111723492A (en) * | 2020-06-30 | 2020-09-29 | 哈工大机器人(合肥)国际创新研究院 | Production process parameter determination method based on simulation verification |
CN111723492B (en) * | 2020-06-30 | 2023-09-05 | 哈工大机器人(合肥)国际创新研究院 | Production process parameter determining method based on simulation verification |
CN112465274A (en) * | 2020-12-30 | 2021-03-09 | 镇江龙源铝业有限公司 | Intelligent management system for production workshop |
CN112465274B (en) * | 2020-12-30 | 2024-03-29 | 镇江龙源铝业有限公司 | Intelligent management system for production workshop |
CN113704869A (en) * | 2021-07-20 | 2021-11-26 | 深圳市万泽航空科技有限责任公司 | Optimal design method for casting process of flame stabilizer |
CN113642160A (en) * | 2021-07-26 | 2021-11-12 | 南京工业大学 | Aluminum alloy engine cylinder body casting process design optimization method based on BP neural network and fish swarm algorithm |
CN113987938A (en) * | 2021-10-27 | 2022-01-28 | 北京百度网讯科技有限公司 | Process parameter optimization method, device, equipment and storage medium |
CN115795983A (en) * | 2023-01-29 | 2023-03-14 | 江苏沙钢集团有限公司 | Wire quality control method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN102831269B (en) | 2015-03-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102831269A (en) | Method for determining technological parameters in flow industrial process | |
CN108764517B (en) | Method, equipment and storage medium for predicting change trend of silicon content in molten iron of blast furnace | |
CN108959728B (en) | Radio frequency device parameter optimization method based on deep learning | |
CN110782658B (en) | Traffic prediction method based on LightGBM algorithm | |
Wu et al. | Operation optimization of natural gas transmission pipelines based on stochastic optimization algorithms: a review | |
CN111310965A (en) | Aircraft track prediction method based on LSTM network | |
CN114969953B (en) | Optimized shield underpass tunnel design method and equipment based on Catboost-NSGA-III | |
CN109472088A (en) | A kind of shale controlled atmosphere production well production Pressure behaviour prediction technique | |
CN111079978B (en) | Coal and gas outburst prediction method based on logistic regression and reinforcement learning | |
CN112749840B (en) | Method for acquiring energy efficiency characteristic index reference value of thermal power generating unit | |
CN113094988A (en) | Data-driven slurry circulating pump operation optimization method and system | |
CN104732067A (en) | Industrial process modeling forecasting method oriented at flow object | |
CN113722997A (en) | New well dynamic yield prediction method based on static oil and gas field data | |
CN110097929A (en) | A kind of blast furnace molten iron silicon content on-line prediction method | |
CN108446771A (en) | A method of preventing Sale Forecasting Model over-fitting | |
CN104483832B (en) | Pneumatic proportional valve fuzzy sliding mode self-adaptation control method based on T S models | |
CN108647483A (en) | A kind of SCR inlet NO based on fuzzy tree modeling methodXThe flexible measurement method of concentration | |
Li et al. | Data cleaning method for the process of acid production with flue gas based on improved random forest | |
CN110221540A (en) | Continuous-stirring reactor system control method based on Hammerstein model | |
CN113515891A (en) | Method for predicting and optimizing quality of emulsion explosive | |
CN117034808A (en) | Natural gas pipe network pressure estimation method based on graph attention network | |
CN111539508A (en) | Generator excitation system parameter identification algorithm based on improved wolf algorithm | |
CN109101683B (en) | Model updating method for pyrolysis kettle of coal quality-based utilization and clean pretreatment system | |
CN114417740B (en) | Deep sea breeding situation sensing method | |
CN107480647B (en) | Method for detecting abnormal behaviors in real time based on inductive consistency abnormality detection |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150325 Termination date: 20210816 |
|
CF01 | Termination of patent right due to non-payment of annual fee |