建筑经济
建築經濟
건축경제
Construction Economy
2015年
9期
72-75
,共4页
张召冉%陈华义%矫伟刚%郭义先
張召冉%陳華義%矯偉剛%郭義先
장소염%진화의%교위강%곽의선
煤矿建设%神经网络%造价估算%井筒工程
煤礦建設%神經網絡%造價估算%井筒工程
매광건설%신경망락%조개고산%정통공정
mine construction%neural network%investment estimation%shaft engineering
矿建工程投资数额大、周期长,井筒工程造价所占比重大,投资估算准确性对决策至关重要.在分析井筒工程施工特点的基础上,甄选7个工程特征指标,利用Matlab提供的神经网络函数构建7个输入指标、1个输出指标的BPNN模型来预测井筒工程造价估算值.结果表明,利用BPNN模型预测,只要井筒工程特征选取合理,BPNN模型的参数设置准确,BPNN神经网络能较快地达到设定的目标,预测精度在±10%以内,能够为煤矿建设的决策提供可靠依据.
礦建工程投資數額大、週期長,井筒工程造價所佔比重大,投資估算準確性對決策至關重要.在分析井筒工程施工特點的基礎上,甄選7箇工程特徵指標,利用Matlab提供的神經網絡函數構建7箇輸入指標、1箇輸齣指標的BPNN模型來預測井筒工程造價估算值.結果錶明,利用BPNN模型預測,隻要井筒工程特徵選取閤理,BPNN模型的參數設置準確,BPNN神經網絡能較快地達到設定的目標,預測精度在±10%以內,能夠為煤礦建設的決策提供可靠依據.
광건공정투자수액대、주기장,정통공정조개소점비중대,투자고산준학성대결책지관중요.재분석정통공정시공특점적기출상,견선7개공정특정지표,이용Matlab제공적신경망락함수구건7개수입지표、1개수출지표적BPNN모형래예측정통공정조개고산치.결과표명,이용BPNN모형예측,지요정통공정특정선취합리,BPNN모형적삼수설치준학,BPNN신경망락능교쾌지체도설정적목표,예측정도재±10%이내,능구위매광건설적결책제공가고의거.
Mine construction has the characteristics of huge investment,long cycle,the accuracy of the investment estimate for investment decisions is essential. Base on analyzing shaft construction,selects 7 index of engineering characteristics,uses Matlab to build BPNN model including 7 input and 1 output index for predicting the shaft project investment. The results show that,as long as the selecting of project characteristics and BPNN model parameter settings are appropriate and accurate,the neural network method can quickly achieve the target,the prediction accuracy could reach± 10% or less,provides reliable basis for making decision of mine construction.