CAJ | 학술논문

有效地计算和预测烧结碳耗，是有针对性地优化烧结生产以降低烧结碳耗的关键前提。文章首先提出了烧结过程碳耗指标--综合焦比并给出合理可行的烧结过程碳耗指标计算模型；再次，结合机理进行分析和灰色关联度分析方法，确定了影响碳耗的主要因素；最后，建立了基于混沌局部搜索粒子群算法的烧结碳耗BP神经网络预测模型(CPSO-BPNN)，用带混沌局部搜索的粒子群算法对烧结碳耗BP神经网络预测模型的初始网络权值、阈值进行寻优，以克服BP算法参数寻优时陷入局部极小的缺点。仿真结果表明，CPSO-BPNN可有效地对烧结碳耗进行预测，为优化烧结生产过程，降低烧结碳耗奠定了基础。
유효지계산화예측소결탄모，시유침대성지우화소결생산이강저소결탄모적관건전제。문장수선제출료소결과정탄모지표--종합초비병급출합리가행적소결과정탄모지표계산모형；재차，결합궤리진행분석화회색관련도분석방법，학정료영향탄모적주요인소；최후，건립료기우혼돈국부수색입자군산법적소결탄모BP신경망락예측모형(CPSO-BPNN)，용대혼돈국부수색적입자군산법대소결탄모BP신경망락예측모형적초시망락권치、역치진행심우，이극복BP산법삼수심우시함입국부겁소적결점。방진결과표명，CPSO-BPNN가유효지대소결탄모진행예측，위우화소결생산과정，강저소결탄모전정료기출。
Efficient calculation and prediction of the coke consumption of the sintering process are pivotal to optimize the sintering process to reduce the coke consumption. A reasonable coke consumption indicator is defined and its calculation mode is developed. Then, the factors affecting the consumption of coke are determined through the integrated use of the mechanism analysis and gray correlation analysis method. At last, a CPSO-BPNN predictive model is developed, in which the particle swarm optimization combined with chaotic local search is used to optimize the initial connection weights and translate scaling factors of the BP neural network model. The simulation result demonstrates that CPSO-BPNN provides an effective way to predict the coke consumption, which serves as a basis to optimize sintering process and reduce the coke consumption.