石油与天然气化工
石油與天然氣化工
석유여천연기화공
CHEMICAL ENGINEERING OF OIL AND GAS
2015年
3期
1-5
,共5页
硫沉积%BP神经网络%预测%元素硫%高含硫气体%溶解度
硫沉積%BP神經網絡%預測%元素硫%高含硫氣體%溶解度
류침적%BP신경망락%예측%원소류%고함류기체%용해도
sulfur deposition%BP neural network%prediction%elemental sulfur%high sulfur gas%solubility
元素硫在高含硫气体中溶解度的研究是硫沉积机理研究、硫沉积预测和处理技术研究的前提和基础，也是元素硫沉积室内研究工作的核心课题。为了关联和预测硫在高含硫气体中的溶解度，提出误差逆向传播人工神经网络（BP ANN）模型，并设计了该模型的计算过程，讨论了该模型的参数设置。计算结果表明，该模型可作为模拟和内推硫在高含硫气体中溶解度的一种较好手段，但外推效果较差。与现有其他硫溶解度计算模型相比，该模型计算结果优于Chrastil缔合模型和经验公式，与状态方程法和六参数缔合模型的计算结果相当。
元素硫在高含硫氣體中溶解度的研究是硫沉積機理研究、硫沉積預測和處理技術研究的前提和基礎，也是元素硫沉積室內研究工作的覈心課題。為瞭關聯和預測硫在高含硫氣體中的溶解度，提齣誤差逆嚮傳播人工神經網絡（BP ANN）模型，併設計瞭該模型的計算過程，討論瞭該模型的參數設置。計算結果錶明，該模型可作為模擬和內推硫在高含硫氣體中溶解度的一種較好手段，但外推效果較差。與現有其他硫溶解度計算模型相比，該模型計算結果優于Chrastil締閤模型和經驗公式，與狀態方程法和六參數締閤模型的計算結果相噹。
원소류재고함류기체중용해도적연구시류침적궤리연구、류침적예측화처리기술연구적전제화기출，야시원소류침적실내연구공작적핵심과제。위료관련화예측류재고함류기체중적용해도，제출오차역향전파인공신경망락（BP ANN）모형，병설계료해모형적계산과정，토론료해모형적삼수설치。계산결과표명，해모형가작위모의화내추류재고함류기체중용해도적일충교호수단，단외추효과교차。여현유기타류용해도계산모형상비，해모형계산결과우우Chrastil체합모형화경험공식，여상태방정법화륙삼수체합모형적계산결과상당。
Research on the elemental sulfur solubility in high sulfur gas is the premise and founda‐tion of sulfur deposition mechanism ,sulfur deposition prediction and treatment technology research , as well as the core subject of indoor sulfur deposition research work .To associate and predict the sul‐fur solubility in high sulfur gas ,a Back Propagation Artificial Neural Network (abbreviated as BP ANN) model was proposed .Implementation procedure and parameters setting of this model were in‐troduced in detail .The results showed that the model could simulate and interpolate the solubility of sulfur in high sulfur gas ,while the extrapolative effect was poor .Compared with other existing mod‐el ,the caculation results of BP ANN was model better than that of the Chrastil association model and the empirical formula ,which was in accord with the calculation results of the equation of state method and the six parameters association model .
