价值工程
價值工程
개치공정
Value Engineering
2015年
28期
52-54
,共3页
李万庆%岳丽飞%孟文清%陈盼盼
李萬慶%嶽麗飛%孟文清%陳盼盼
리만경%악려비%맹문청%진반반
气膜%薄壳%串联型灰色神经网络%施工工期%预测
氣膜%薄殼%串聯型灰色神經網絡%施工工期%預測
기막%박각%천련형회색신경망락%시공공기%예측
inflated form%thin-shell%serial grey neural network%project duration%forecasting
根据气膜薄壳钢筋混凝土穹顶储仓的施工特点,详细分析了影响其施工工期的因素及参数获取方式,结合灰色GM(1,1)模型和BP神经网络处理数据的优点,提出了基于串联型灰色神经网络(serial grey neural network,SGNN)的施工工期预测模型并进行预测仿真。结果表明:该方法切实可行,预测精度高于GM(1,1)方法。
根據氣膜薄殼鋼觔混凝土穹頂儲倉的施工特點,詳細分析瞭影響其施工工期的因素及參數穫取方式,結閤灰色GM(1,1)模型和BP神經網絡處理數據的優點,提齣瞭基于串聯型灰色神經網絡(serial grey neural network,SGNN)的施工工期預測模型併進行預測倣真。結果錶明:該方法切實可行,預測精度高于GM(1,1)方法。
근거기막박각강근혼응토궁정저창적시공특점,상세분석료영향기시공공기적인소급삼수획취방식,결합회색GM(1,1)모형화BP신경망락처리수거적우점,제출료기우천련형회색신경망락(serial grey neural network,SGNN)적시공공기예측모형병진행예측방진。결과표명:해방법절실가행,예측정도고우GM(1,1)방법。
According to the construction characteristics of concrete thin-shell domes using inflated forms, this paper analyzes the factors affecting project duration and it presents a new forcasting system of project duration (serial grey neural network), which integrates the data processing advantage of GM (1,1) and BP neural network. The perforamance is demonstrated by using MATLAB software. The results show that the approach is feasible and effective in comparison with single model GM(1,1).