Font Size: a A A

Forecast And Optimal Dispatching Method Of Byproduct Gas In Iron And Steel Industry

Posted on:2021-02-24Degree:MasterType:Thesis
Country:ChinaCandidate:D F YangFull Text:PDF
GTID:2481306743460504Subject:Industrial Engineering
Abstract/Summary:PDF Full Text Request
The byproduct gas is an important secondary energy in iron and steel industry,and the pressure of gas pipe network and flow instability leads to the fluctuation of storage unit and the loss of gas emission in the process of transportation,consumption,and storage of the byproduct gas.Therefore,it is of great significance to achieve the optimal scheduling of the byproduct gas for energy saving and consumption reduction of the iron and steel industry.In view of the problem of the scheduling lag of byproduct gas and the safe operation of storage unit,taking coke oven gas and blast furnace gas as the research objects,a prediction model and optimal scheduling model of byproduct gas are established in this paper by analyzing the whole technological process,in which the byproduct gas unit is subdivided into production unit and consumption unit in the prediction model,and the gas volume of each unit is predicted and analyzed to obtain the prediction results;Meanwhile,based on the above prediction results and with the goal of maximize efficiency,the optimal scheduling model of byproduct gas is established under the condition of fully considering the safety of gas storage tank.The specific research contents are as follows:(1)The LSSVM-ARMA prediction model is established.In view of the influence of noise data in byproduct gas data,wavelet transform analysis is used to process the initial data,and the appropriate prediction method is selected based on the characteristics and properties of one-dimensional time series.The Least Squares Support Vector Machine(LSSVM)and Autoregressive Moving Average(ARMA)prediction model are used to predict the volatility and trend series.In the process of trend series prediction,the appropriate ARMA prediction model is selected for prediction according to the distribution characteristics of data.Compared with the LSSVM and Elman neural network,the proposed method is superior than the two methods,and the predicted values can be used as the input value of the optimal scheduling model.(2)The optimization scheduling model of byproduct gas is established.In this paper,we choose the level of the gas tank in the safe range,taking the maximize efficiency as the objective function,considering the factors that affect the production cost comprehensively,including the gas emission penalty cost,the gas storage tank fluctuation penalty cost and the boiler operation cost,as well as the corresponding constraint conditions to establish the model.By analyzing the characteristics of the model,the genetic algorithm is selected to solve the problem,and the crossover operator is improved to ensure the accuracy and speed of the solution.Finally,the comparison results show that the proposed model can not only effectively ensure the stability of the gasholder,but increase the enterprise benefit by 9.88%.
Keywords/Search Tags:iron and steel industry, byproduct gas, LSSVM-ARMA prediction model, gas tank counter, optimal scheduling, genetic algorithm
PDF Full Text Request
Related items