Abstract：Loss on ignition is an important index for the marine geological study. The determination of loss on ignition by conventional method is time-consuming. Moreover, the requirements for analysis environment are relatively high. Based on the correlation between loss on ignition and the contents of SiO2, Al2O3, Fe2O3, CaO, K2O and TiO2, BP neural network model was introduced to predict the loss on ignition using its nonlinear fitting ability. The loss on ignition and the contents of SiO2, Al2O3, Fe2O3, CaO, K2O and TiO2 in many ocean sediment samples were used as training pattern. The initial weights and biases of BP neural network were optimized by genetic algorithm. The experiments showed that the prediction model of loss on ignition for ocean sediments could be successfully established based on genetic algorithm (GA)-BP neural network. The loss on ignition of ocean sediments was predicted by GA-BP neural network on the basis of analysis data using X-ray fluorescence spectrometry (XRF). The relative standard deviation (RSD) was 1.3%. The relative deviation absolute value of prediction values and reference values was in range of 0.1%-6.2% for standard samples and actual samples of ocean sediment. The proposed study provided a new and effective route for the determination of loss on ignition.
李强, 张学华. 基于遗传算法的BP神经网络模型在预测海洋沉积物烧失量中的应用[J]. 冶金分析, 2019, 39(4): 25-30.
LI Qiang, ZHANG Xue-hua. Application of BP neural network to the prediction of loss on ignition in marine sediments based on genetic algorithm. , 2019, 39(4): 25-30.
刘子亭,余俊清,张保华,等.黄旗海岩芯烧失量分析与冰后期环境演变[J].盐湖研究,2008,16(4):1-5.LIU Zi-ting,YU Jun-qing,ZHANG Bao-hua,et al.Investigation on loss-on-ignition of lake Huangqihai core and post-glacial environmental evolution[J].Journal of Salt Lake Research,2008,16(4):1-5.
[2]
杨冰洁,余凤玲,郑卓,等.南澳岛青澳湾沉积物粒度与烧失量指示的全新世沉积环境变化[J].海洋地质与第四纪地质,2015,35(6):41-51.YANG Bing-jie,YU Feng-ling,ZHENG Zhuo,et al.Changes in holocene depositional environment of Qin′ao embayment on Nan′ao island inferred from sediment grain-size and loss-on-ignition[J].Marine Geology & Quaternary Geology,2015,35(6):41-51.
[3]
胡彩莉,马玉贞,郭超,等.烧失量法测定土壤有机质含量的实验条件探究[J].地球与环境,2016,44(1):110-118.HU Cai-li,MA Yu-zhen,GUO Chao,et al.Optimization of the experiment conditions for estimating organic matter content with loss-on-ignition method[J].Earth and Environment,2016,44(1):110-118.
[4]
陈钢花,胡琮,曾亚丽,等.基于BP神经网络的碳酸盐岩储层缝洞充填物测井识别方法[J].石油物探,2015,54(1):99-104.CHEN Gang-hua,HU Zong,ZENG Ya-li,et al.Logging identification method of fillings in fractures and cavers in carbonate reservoir based BP neural network[J].Geophysical Prospecting for Petroleum,2015,54(1):99-104.
[5]
徐星,孙光中,田坤云.GA-BP神经网络在煤矿突水水源判别中的应用[J].煤炭技术,2018,37(10):172-174.XU Xing,SUN Guang-zhong,TIAN Kun-yun.Application of GA-BP neural network in discrimination of water inrush source in coal mine[J].Coal Technology,2018,37(10):172-174.
[6]
聂敏,刘志辉,刘洋,等.基于PCA和BP神经网络的径流预测[J].中国沙漠,2016,36(4):1144-1152.NIE Min,LIU Zhi-hui,LIU Yang,et al.Runoff forecast based on principal component analysis and BP neural network[J].Journal of Desert Research,2016,36(4):1144-1152.
[7]
张青,王学雷,张婷,等.基于BP神经网络的洪湖水质指标预测研究[J].湿地科学,2016,14(2):212-218.ZHANG Qing,WANG Xue-lei,ZHANG Ting,et al.Prediction of water quality index of Honghu lake based on back propagation neural network model[J].Wetland Science,2016,14(2):212-218.
[8]
李强,刘坚,李小穗,等.基于遗传算法的BP 神经网络模型在岩心扫描仪测定海洋沉积物多种组分中的应用研究[J].岩矿测试,2016,35(5):488-495.LI Qiang,LIU Jian,LI Xiao-sui,et al.Determination of multi-components in marine sediments by core scanner based on BP neural network of genetic algorithm[J].Rock and Mineral Analysis,2016,35(5):488-495.
[9]
李家文,赖华,冯丽辉.基于神经网络与LabVIEW平台建立焊锡真空炉粗锡含铅量的软测量模型与在线监测研究[J].冶金分析,2017,37(2):1-6.LI Jia-wen,LAI Hua,FENG Li-hui.Research on soft measurement model and on-line monitoring of lead content in crude tin in solder vacuum furnace based on neural network and LabVIEW[J].Metallurgical Analysis,2017,37(2):1-6.
[10]
邹孝恒,郝中骐,易荣兴,等.基于遗传算法和偏最小二乘法的土壤激光诱导击穿光谱定量分析研究[J].分析化学,2015,43(2):181-186.ZOU Xiao-heng,HAO Zhong-qi,YI Rong-xing,et al.Quantitative analysis of soil by laser-induced breakdown spectroscopy using genetic algorithm-partial least squares[J].Chinese Journal of Analytical Chemistry,2015,43(2):181-186.
[11]
林志贵,杜军兰,冯林强,等.长江口流域亚硝酸盐预测模型与分析[J].海洋技术学报,2017,36(1):80-85.LIN Zhi-gui,DU Jun-lan,FENG Lin-qiang,et al.Analysis on the prediction model of nitrite in the Yangtze river estuary[J].Journal of Ocean Technology,2017,36(1):80-85.
[12]
李颖娜,徐志彬,刘双龙.遗传神经网络-X射线荧光光谱法测定铁矿石中铅砷[J].冶金分析,2017,37(10):22-26.LI Ying-na,XU Zhi-bin,LIU Shuang-long.Determination of lead and arsenic in iron ore by X-ray fluorescence spectrometry based on genetic neural network[J].Metallurgical Analysis,2017,37(10):22-26.
[13]
范晓东,邱波,刘园园,等.一种基于遗传优化的BP神经网络的测光红移估计算法[J].光谱学与光谱分析,2018,38(8):2374-2378.FAN Xiao-dong,QIU Bo,LIU Yuan-yuan,et al.A photometric redshift estimation algorithm based on the BP neural network optimized by genetic algorithm[J].Spectroscopy and Spectral Analysis,2018,38(8):2374-2378.
