石煤提钒行业工艺先进性评价研究
|
摘要
石煤是我国一种重要的优势含钒资源,在我国储量丰富,从石煤中提取钒是获得v205的重要途径。随着石煤提钒行业的发展,先进提钒工艺技术越来越受到高度重视。但是由于缺乏提钒行业评估准则及系统的评估体系,难以对各种提钒工艺及污染防治技术进行最优筛选,无法实现对提钒行业切实可行的监督管理。造成目前国内提钒行业面临资源利用率低,工艺及设备配置参差不齐,以及提钒技术落后、环境污染等问题。因此,为促进石煤提钒行业的有序发展,提升提钒企业的技术管理水平,亟须制定和实施一套科学、合理、有效的生产工艺先进性的评价体系、标准和方法,对石煤提钒行业的整体生产工艺技术进行综合评估,对于促进我国钒资源开发利用的良性发展,有重要的理论和现实意义。
本研究利用数据挖掘技术,对基于小样本的石煤提钒行业工艺先进性评价问题进行研究。通过对石煤提钒行业先进工艺及污染治理现有技术的调研分析,构建了提钒行业生产工艺评价路线,制定了生产评价指标体系及标准,并采用数据挖掘技术中的模糊数学法对指标体系及标准的合理性进行了验证。此外,本研究还借助遗传算法对支持向量机模型参数进行了优化,充分利用支持向量机良好的学习性能和潜在的应用价值,并将其成功应用于石煤提钒工艺先进性评价体系。上述研究在我国石煤提钒行业领域尚属首次,为推动建立完整的石煤提钒行业工艺先进性评价体系提供了相关理论支持。
论文的主要成果如下：
1.对石煤提钒行业生产工艺及污染防治现状进行了系统的分析与总结。在调研基础上系统总结出当前国内石煤提钒行业工艺技术现状、排污节点、特征污染物、污染防治现状,以及工艺技术和污染防治中存在的问题,为先进工艺的评价奠定了基础。
2.首次在我国建立了石煤提钒工艺先进性评价指标体系及标准值。基于生命周期系统评价方法,以易操作性、特殊性和兼容性为原则构建了石煤提钒行业先进生产评价指标体系及各项指标标准值;利用模糊数学综合评判法、集成赋权法,验证了所构建的石煤提钒行业先进工艺评价指标体系及其标准值的合理性。
3.将数据挖掘技术中的支持向量机、遗传算法引入石煤提钒工艺先进性评价研究领域。根据石煤提钒工艺特点,利用遗传算法(GA)对支持向量机方法(SVM)在核函数及参数选择问题上进行了改进。通过训练样本及测试样本的评价,证明了改进后的支持向量机方法(GA-SVM)可实际应用于石煤提钒行业工艺先进性的评价过程,是一种具有较高实用价值的小样本评价方法。
4.制定出石煤提钒行业先进工艺及污染防治技术政策建议。通过AHP/Entroy集成赋权法,分析指标参数对工艺水平影响的重要程度,制定出石煤提钒行业先进工艺及污染防治技术政策建议,为政府、环保部门制定政策及准入条件提供了借鉴。
Stone coal is a kind of important and abundant vanadium resources in China, and vanadium extraction from stone coal is a important way of acquiring V2O5.With the development of the vanadium extraction industry, the advanced technology has been attached more and more importance to. But due to the lack of evaluation criteria and systematic evaluation system of vanadium extraction industry, the optimal selection from various vanadium extraction technology and pollution control technology is hard, and it is unable to realize the feasible supervision and management of vanadium extraction industry, all these make the current domestic industry face low resource utilization, uneven process and equipment configuration, backward extraction technology, and environmental pollution problems. Therefore, in order to promote the development of the industry orderly and improve the enterprise management level, it is desiderate to formulate and implement a set of scientific, reasonable and effective evaluation system, standards and method of technological advancement, and comprehensively evaluate the whole production process of v vanadium industry technology, which have important theoretical and realistic significance to promote the benign development of vanadium resources development and utilization in our country.
Using data mining technology, this study conducts a research on stone coal vanadium extraction technology advancement evaluation based on small samples. Through analyzing the advanced process in vanadium industry and the existing pollution control technology, this study constructs the route of technological advancement evaluation in vanadium extraction industry, establishes evaluation index system and standard production and verifies the rationality of the index system and standard by using data mining technology in the fuzzy mathematics method. In addition, this study also optimizes the support vector machine (SVM) model parameters with the help of genetic algorithm, makes full use of support vector machine (SVM) good study performance and potential application value, and applies it successfully to stone coal vanadium extraction technology advancement evaluation system. The aforementioned research in the field of vanadium industry in China is doing for the first time and provides relevant theoretical support to promote a complete advancement evaluation system of stone coal vanadium industry technology.
The main results of paper are as follows:
1. It analysis and summarize the production status of vanadium extraction industry and the situation of pollution prevention. On the basis of research system it sums up the current status of domestic vanadium extraction industry technology, sewage node, characteristics of pollutants, the situation of pollution prevention, control of the status quo of the technology and problems in pollution prevention, which laid a foundation for the evaluation of advanced technology.
2. It sets up the evaluation indicator system and standard values of technological advancement of vanadium extraction from stone coal on this basis of using life cycle assessment method with the principles of ease, particularity and compatibility; by the method of comprehensive evaluation in the fuzzy mathematics, the integration weighting method, it verifies the rationality of advanced evaluation indicator system and standard in vanadium extraction industry.
3. The data mining technology of support vector machine (SVM) and genetic algorithm is introduced into the research of vanadium extraction from stone coal technology advancement evaluation. According to the characteristics of the established evaluation index system, by using the genetic algorithm (GA) the method of support vector machine (SVM) is improved on the kernel function and parameters selection, and the specific modeling process were determined. Through the evaluation of training samples and testing samples, it proved that the improved support vector machine method (GA-SVM) can be practical applied to the evaluation process of vanadium extraction industry technological advancement, and it is a kind of evaluation method with high practical value of small sample.
4. It makes some policy recommendations on advanced technology and pollution control technology in vanadium extraction industry. By AHP/Entroy, it analyzes indicator parameter values to the importance of the importance on the technological level. It gives some policy advice on advanced technology and pollution control technology for government and provides the reference for environmental protection department1s policy making and access requirements.
本研究利用数据挖掘技术,对基于小样本的石煤提钒行业工艺先进性评价问题进行研究。通过对石煤提钒行业先进工艺及污染治理现有技术的调研分析,构建了提钒行业生产工艺评价路线,制定了生产评价指标体系及标准,并采用数据挖掘技术中的模糊数学法对指标体系及标准的合理性进行了验证。此外,本研究还借助遗传算法对支持向量机模型参数进行了优化,充分利用支持向量机良好的学习性能和潜在的应用价值,并将其成功应用于石煤提钒工艺先进性评价体系。上述研究在我国石煤提钒行业领域尚属首次,为推动建立完整的石煤提钒行业工艺先进性评价体系提供了相关理论支持。
论文的主要成果如下：
1.对石煤提钒行业生产工艺及污染防治现状进行了系统的分析与总结。在调研基础上系统总结出当前国内石煤提钒行业工艺技术现状、排污节点、特征污染物、污染防治现状,以及工艺技术和污染防治中存在的问题,为先进工艺的评价奠定了基础。
2.首次在我国建立了石煤提钒工艺先进性评价指标体系及标准值。基于生命周期系统评价方法,以易操作性、特殊性和兼容性为原则构建了石煤提钒行业先进生产评价指标体系及各项指标标准值;利用模糊数学综合评判法、集成赋权法,验证了所构建的石煤提钒行业先进工艺评价指标体系及其标准值的合理性。
3.将数据挖掘技术中的支持向量机、遗传算法引入石煤提钒工艺先进性评价研究领域。根据石煤提钒工艺特点,利用遗传算法(GA)对支持向量机方法(SVM)在核函数及参数选择问题上进行了改进。通过训练样本及测试样本的评价,证明了改进后的支持向量机方法(GA-SVM)可实际应用于石煤提钒行业工艺先进性的评价过程,是一种具有较高实用价值的小样本评价方法。
4.制定出石煤提钒行业先进工艺及污染防治技术政策建议。通过AHP/Entroy集成赋权法,分析指标参数对工艺水平影响的重要程度,制定出石煤提钒行业先进工艺及污染防治技术政策建议,为政府、环保部门制定政策及准入条件提供了借鉴。
Stone coal is a kind of important and abundant vanadium resources in China, and vanadium extraction from stone coal is a important way of acquiring V2O5.With the development of the vanadium extraction industry, the advanced technology has been attached more and more importance to. But due to the lack of evaluation criteria and systematic evaluation system of vanadium extraction industry, the optimal selection from various vanadium extraction technology and pollution control technology is hard, and it is unable to realize the feasible supervision and management of vanadium extraction industry, all these make the current domestic industry face low resource utilization, uneven process and equipment configuration, backward extraction technology, and environmental pollution problems. Therefore, in order to promote the development of the industry orderly and improve the enterprise management level, it is desiderate to formulate and implement a set of scientific, reasonable and effective evaluation system, standards and method of technological advancement, and comprehensively evaluate the whole production process of v vanadium industry technology, which have important theoretical and realistic significance to promote the benign development of vanadium resources development and utilization in our country.
Using data mining technology, this study conducts a research on stone coal vanadium extraction technology advancement evaluation based on small samples. Through analyzing the advanced process in vanadium industry and the existing pollution control technology, this study constructs the route of technological advancement evaluation in vanadium extraction industry, establishes evaluation index system and standard production and verifies the rationality of the index system and standard by using data mining technology in the fuzzy mathematics method. In addition, this study also optimizes the support vector machine (SVM) model parameters with the help of genetic algorithm, makes full use of support vector machine (SVM) good study performance and potential application value, and applies it successfully to stone coal vanadium extraction technology advancement evaluation system. The aforementioned research in the field of vanadium industry in China is doing for the first time and provides relevant theoretical support to promote a complete advancement evaluation system of stone coal vanadium industry technology.
The main results of paper are as follows:
1. It analysis and summarize the production status of vanadium extraction industry and the situation of pollution prevention. On the basis of research system it sums up the current status of domestic vanadium extraction industry technology, sewage node, characteristics of pollutants, the situation of pollution prevention, control of the status quo of the technology and problems in pollution prevention, which laid a foundation for the evaluation of advanced technology.
2. It sets up the evaluation indicator system and standard values of technological advancement of vanadium extraction from stone coal on this basis of using life cycle assessment method with the principles of ease, particularity and compatibility; by the method of comprehensive evaluation in the fuzzy mathematics, the integration weighting method, it verifies the rationality of advanced evaluation indicator system and standard in vanadium extraction industry.
3. The data mining technology of support vector machine (SVM) and genetic algorithm is introduced into the research of vanadium extraction from stone coal technology advancement evaluation. According to the characteristics of the established evaluation index system, by using the genetic algorithm (GA) the method of support vector machine (SVM) is improved on the kernel function and parameters selection, and the specific modeling process were determined. Through the evaluation of training samples and testing samples, it proved that the improved support vector machine method (GA-SVM) can be practical applied to the evaluation process of vanadium extraction industry technological advancement, and it is a kind of evaluation method with high practical value of small sample.
4. It makes some policy recommendations on advanced technology and pollution control technology in vanadium extraction industry. By AHP/Entroy, it analyzes indicator parameter values to the importance of the importance on the technological level. It gives some policy advice on advanced technology and pollution control technology for government and provides the reference for environmental protection department1s policy making and access requirements.
引文
[1]Zhang Y M, Bao S X. The technology of extracting Vanadium from stone coal in China: history, current status and future prospects[J]. Hydrometallurgy,2011,109:116-124.
[2]Bao S X, Zhang Y M, Liu T, et al. The production, conSVMption and market analysis of Vanadium in the world[J]. China Mining Magazine,2009,18(7):12-15.
[3]宾智勇.石煤提钒研究进展与五氧化二钒的市场状况[J].湖南有色金属,2006,22(1)：16-20.
[4]段炼,田庆华,郭学益.我国钒资源的生产及应用研究进展[J].湖南有色金属,2006,22(6)：17-19.
[5]蔡晋强.石煤提钒工艺及设备进展[J].稀有金属与硬质合金,2010,38(2)：67-71.
[6]Mi X X, Lan W F. Processes of Vanadium extraction pentoxide from stone coal [J]. Hydrometallurgy of China,2008,27(4):208-211.
[7]荣华.日本开发大容量钒二次电池[J].有色与稀有金属国外动态,1995(11)：14-16.
[8]漆明鉴.从石煤中提钒现状及前景[J].湿法冶金,1999,4(12)：1-10.
[9]段炼,田庆华,郭学益.我国钒资源的生产及应用研究进展[J].湖南有色金属,2006,22(6)：17-22.
[10]王忠,王军.国内外五氧化二钒市场状况与分析[J].矿冶工程,2007,16(2)：47-51.
[11]Moskalyk R R, Alfantazi A M. Review processing of Vanadium[J]. Minerals Engineering, 2003,16:793-805.
[12]刘景槐,牛磊.湖南怀化会同地区含钒石煤提钒与资源综合利用[J].有色金属工程,2012(4)：31-35.
[13]齐小鸣.钒消费前景看好-国内外钒资源、生产和市场预测[J].世界有色金属,2008(5)：38-41.
[14]许国镇,夏华,戈西锷.江西皈大石煤中钒的价态初步研究[J].矿产资源利用,1983(4)：39-44.
[15]许国镇,司徒安力,陈农,等.湖北杨家堡石煤中的钒的价态研究[J].地球化学,1984(4)：379-389.
[16]包申旭,张一敏,胡杨甲,等.石煤焙烧过程中矿相与钒价态的变化及对钒浸出的影[J].矿冶工程,2007,16(2)：47-51.
[17]陈庆根.石煤钒矿提钒工艺技术的研究进展[J].矿产综合利用.2009(2)：30-33.
[18]刘景槐,谭爱华.我国石煤钒矿提钒现状综述[J].湖南有色金属.2010,26(5)：11-14.
[19]舒型武.石煤提钒工艺及废物治理综述[J].钢铁技术,2007(1)：47-50.
[20]何东升.石煤型钒矿焙烧—浸出过程的理论研究[D].中南大学,2009.
[21]Huang J, Zhang Y M, Liu T, et al. Extraction of Vanadium from low-grode Vanadium shale using Bi-circulation and high-efficiency oxidization roast technology[C]. Proceeding of the 48th conference of metallurgists,2009,73-80.
[22]Nadi E Y A, Awwad N S, Nayl A A. A comparative study of Vanadium extraction by aliquat-336 from acidic alkaline media with application to spent catalyst[J]. International Joumal of Mineral Processing,2009,92:115-120.
[23]Liu Y, Yang C, Li P, et al. A new process of extracting Vanadium from stone coal[J]. International Journal of Minerals, Metallurgy, and Materials.2010,17(4),381-382.
[24]Bie S, Wang Z, Li Q, et al. Review of Vanadium extraction from stone coal by roasting technique with sodium chloride and calcium oxide[J]. Chinese Journal of Rare Metals,2010,34(2):291-297.
[25]邹骁勇,彭清静,欧阳玉祝,等.高硅低钙钒矿的钙化焙烧过程[J].过程工程学报,2001(2)：189-192.
[26]Xu Y, Hou Y, Yang H. Experimental study on the overall recovering silver and Vanadium from the black shale-hosted silver and Vanadium deposits[J]. Mining and Metallurgical Engineering,2008,28(1):67-70.
[27]He D, Feng Q, Zhang G, et al. An environmentally-friendly technology of Vanadium extraction from stone coal[J]. Minerals Engineering,2007,20:11184-11186.
[28]黄晶,张一敏,刘涛,等.石煤提钒碳酸盐复合添加剂的研制及焙烧工艺研究[J].矿冶工程,2012,32(z1)：93-96.
[29]黄晶.碳质含钒页岩高效提取技术及机理研究[D].武汉理工大学,2010.
[30]包申旭,张一敏,刘涛,等.电渗析处理石煤提钒废水[J].中国有色金属学报,2010,20(7)：1440-1445.
[31]刘涛,张一敏,李佳.石煤提钒行业污染防治技术现状及进展[J].环境保护.2013,41(15)：75-79.
[32]郑桂花.石煤提钒工艺清洁生产评价的研究[D].武汉理工大学,2009.
[33]Saaty T L. The analytic hierarchy process:planning priority setting, resource allocation[M]. New York,1980.
[34]Barbiroli G, Raggi A. A method for evaluating the overall technical and economic performance of environmental innovations in production cycles[J]. Journal of Cleaner Production, 2003,11:365-374.
[35]杜栋,庞庆华.现代综合评价方法与案例精选[M].北京：清华大学出版社,2008.
[36]白兵.煤炭开采清洁生产水平评价方法研究[D].河北理工大学,2009.
[37]Fayyad U, Uthursamy R. Evolving data mining into solutions for insights[J].Communications of The ACM,2002,45(8):28-31.
[38]Han J W, Kamber M, Mining D. Concepts and techniques[M], Morgan Kaufmann Publishers, 2000.
[39]Fayyad U, Shapiro G P, Smyth P. Knowledge discovery and data mining, towards a unifying framework[C]. Proceedings of 2nd International Conference on knowledge Discovery and Data Mining,1996:82-88.
[40]Brachman R J, Arand T. The process of knowledge discovery in databases; A human-centered approach[C]. Advance In knowledge Discovery And Data Mining,1996:37-58.
[41]关菁华.基于贝叶斯网数据挖掘若干问题研究[D].吉林大学,2009.
[42]Safavian S R, Landgrebe D. A survey of decision tree classifier methodology[M]. School of Electrical Engineering Purdue University,2002.
[43]申文明,王文杰,罗海江,等.基于决策树分类技术的遥感影像分类方法研究[J].遥感技术与应用,2001,22(3)：333-337.
[44]余晶,蒋平安,高敏华.基于决策树的土地应用方法研究[J].新疆农业科学,2009,46(2)：214-218.
[45]李锡钦.结构方程模型[M].北京：高等教育出版社,2011.
[46]Andrade A R, Teixeira P F. A bayesian model to assess rail track geometry degradation through its life-cycle[J]. Research in Transportation Economics,2011,137(3):193-200.
[47]Goulding R, Jayasuriya N, Horan E. A bayesian network model to assess the public health risk associated with wet weather sewer overflows discharging into waterways[J]. Water Research, 2012,46(16),4933-4940.
[48]王晨婉.基于贝叶斯理论的供水管道风险评价研究[D].天津大学,2010.
[49]赵晓慎.基于熵权法赋权的贝叶斯水质评价模型[J].水电能源科学,2011,29(6)：33-35.
[50]张泽旭.神经网络控制与MATLAB仿真[M].哈尔滨：哈尔滨工业大学出版社,2011.
[51]Li M S, Chen W C. Application of BP neural network algorithm in sustainable development of highway construction projects[J]. Changsha University of Science& Technology, 2012(25):1212-1217.
[52]Singh K P, Basant A, Malik A, et al. Artificial neural network modeling of the rier water quality-A case study[J]. India Institute of Taxicology Research,2009,220:888-895.
[53]杜刚.改进的BP神经网络在地下水质评价中的应用[D].上海师范大学,2007.
[54]张旭.基于BP神经网络的清洁生产评价模型研究[D].重庆大学,2009.
[55]李敏强,寇纪淞,林丹,等.遗传算法的基本理论与应用[M].北京：科学出版社,2002.
[56]Niu Y, He W B, Zhang J. Using genetic algorithm to improve fuzzy k-NN[J]. Suzhou, 2008,8:475-479.
[57]Fu X J, Wang L P. Rule extraction by genetic algorithms based on a simplified RBF neural network [J]. Congress on Evolutionary Computation,2001(2):753-758.
[58]穆阿华,周绍磊,刘青志,等.利用遗传算法改进BP学习算法[J].计算机仿真,2005,22(2)：150-152.
[59]马祥陆.遗传算法的贝叶斯网络学习算法[D].吉林大学,2007.
[60]Week M, Klocke F, Schell H, et al. Evaluating alternative production cycles using the extended fuzzy AHP method[J]. European Journal of Operational Research,1997,100(2):351-366.
[61]Zheng G Z, Zhu N, Tian Z, et al. Application of a trapezoidal fuzzy AHPmethod for work safety evaluation and early warning rating of hot and humid environments[J]. Safety Science, 2012,50:228-239.
[62]Laarhoven V, Pedrycz P J M. A fuzzy extension of saaty's priority theory[J]. Fuzzy Set System,1983,11(3):229-241.
[63]Cengiz K, Ufuk C, Ziya U. Multi-criteria supplier selection using fuzzy AHP[J]. Logistics Information Management,2003,16(6):382-394.
[64]Tseng ML, Lin YH, Chiu A S F. Fuzzy AHP-based study of cleaner production implementation in Taiwan PWB manufacture[J]. Journal of Cleaner Production, 2009,17:1249-1256.
[65]Wang Y K, Wang D, Ma H Q, et al. Risk assessment for flood control engineering using fuzzy theory:A case study in China[C]. Nanjing University,2011.
[66]李远贵.提高支持向量机的学习效率和分类速度的研究和应用[D].上海交通大学,2006.
[67]许建华,张学工,李衍达.支持向量机的新发展[J].控制与决策,2004,19(5)：481-484.
[68]Vapnik V. Statistical learning theory[M]. New York:Springer,1998.
[69]朱明.数据挖掘[M].中国科学技术大学出版社,2008.
[70]杨力.基于小样本数据的矿井瓦斯突出风险评价[D].中国科学技术大学,2011.
[71]Reyna R A, Hernandez N, Esteve D, et al. Segmenting images with support vector machines[J]. Vancouver,2000,1:820-823.
[72]Keren D, Osadchy M, Gostman C. Antifaces:A novel, fast method for image detection[J]. IEEE transactions on pattern analysis and machine intelligence,2001,23(7):747-761.
[73]Dong G G, Jain A K, Ying M W, et al. Learning similarity measure for natural image retrieval with relevance feedback[J]. IEEE Transactions on Neural Networks,2002,13(4):811-820.
[74]Brown M, Lewis H G, Gunn S R. Linear spectral mixture models and support vector machines for remote sensing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000,38(5):2346-2360.
[75]Pontil M, Verri A. Support vector machines for 3D object recognition[J]. IEEE Transactions on pattern Analysis and Machine Intelligence,1998,20(6):637-646.
[76]Xin D, Wu Z. Speaker recognition using continuous density support vector machines[J]. Electronics Letters,2001,37:1009-1101.
[77]Osuna E, Freund R, Girosi F. Training support machines:An application to face detection[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Puerto, 1997:130-136.
[78]赵晖.支持向量机分类方法及其在文本分类中的应用研究[D].大连理工大学,2005.
[79]Valentini G. Gene expression data analysis of human lymphoma using support vector machines and output coding ensembles[J]. Artificial Intelligence in Machines, 2002,26(3):281-304.
[80]Cai Y, Liu X, Xu X, et al. Prediction of protein structural classes by support vector machines[J]. Computers and Chemistry,2002,26(3):293-296.
[81]Bbanu P K, Ramakrishnan A G, Suresh S, et al. Fetal lung maturity analysis using ultrasound image features[J]. IEEE Transactions on Information Technology in Biomedicine, 2002,6(1):38-45.
[82]Bradley P, Mangasarian O L. Feature selection via concave minimization and support vector machines[C]. Machine Learning Proceedings of the Fifteenth International Conference. San Francisco,1998,82-90.
[83]Fung G. The disputed federalist papers:SVM feature selection via concave minimization[C]. Journal of the ACM,2003,42-46.
[84]Sun W, Yang C G. Credit risk assessment in commercial banks based on muti-layer SVM classifier[J]. Computational Intelligence,2006,4114:778-785.
[85]Bui D T, Pradhan B, Lofman O, et al. Landslide susceptibility assessment in vietnam using support vector machines,decision tree,and na□ve bayes models[J]. Problems in Engineering, 2012(2012):26.
[86]王冉,杨道军.基于支持向量机的巢湖富营养化程度评价研究[J].环境科学与管理,2005,5：180-184.
[87]张磊,郑丕谔,王中权,等.基于支持向量机的中国石油安全分析[J].工业工程,2010,13(4)：40-47.
[88]Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letters,1999,9:293-300.
[89]Scholkopf B, Smola A, Williamson P C, et al. New support vector algorithms[J].Neural Computation,2000,12:1207-1245.
[90]Tsang E C C, Yeung D S, Chan P P K. Fuz2y support vector machines for solving two-class problems[J]. Proceedings of the Second International Conference on Machine Learning and Cybernetics,2003,1:1080-1083.
[91]Daisuke T, Shigeo A. Fuzzy least squares support vector machines for multiclass problems[J]. Neural Networks,2003,16:785-792.
[92]Hsu C, Lin C J. A simple decomposition method for support vector machines[J]. Machine Learning,2002,46:291-314.
[93]David M J T, Robert P W D. Data domain description using support vector[A]. Proceedings of the Unropean Symposium on Artificial Neural Network, bruges(Belgium), 1999(20):1191-1199.
[94]David M J T, Robert P W D. Support vector domain description[J]. Pattern Recognition Letters,1999,20:1191-1199.
[95]丁胜峰.基于模糊推理的多源图像融合研究[D].南京理工大学,2004.
[96]王喜宾,张小平,王翰虎.基于粒子群优化模式搜索的支持向量机参数优化应用[J].计算机应用,2011,31(12)：3302-3305.
[97]李露璐.基于改进的SVM算法的耕地地力评价模型研究[J].沈阳农业大学学报,2012,43(1)：126-128.
[98]陈海洋,滕彦国,王金生.基于GA参数寻优的决策树支持向量机生态环境质量评价方法[J].生态与农村环境学报,2010,26(6)：600-604.
[99]李佳,张一敏,刘涛.石煤提钒行业清洁生产评价指标体系建立[J],环境科学与技术,2013,36(7)：191-194.
[100]Thomas F. Produce life cycle assessment principles and methodology [M].Nordic Council of Ministers,1992.
[101]GB/T2010-2006工业清洁生产评价指标体系编制通则[S].北京：中国国家标准化管理委员会,2006.
[102]Jia Li, Yimin Zhang, Tao Liu. Research on pollution prevention and control technologies in the industry of Vanadium extraction from stone coal[J]. Int. J. Environmental Technology and Management 2013.
[103]Ezatollah K. Appropriateness of farmers'adoption of irrigation methods:the application of the AHP model[J]. Agricultural systems,2006,87:101-119.
[104]Mergias I, Moustakas K, Papadopoulos A, et al. Multi-criteria decision aid approach for the selection of the best compromise management scheme for ELVs:the case of Cyprus[J]. Journal of Hazardous Materials,2007,147(3):706-717.
[105]司春棣.引水工程安全保障体系研究[D].天津大学,2007.
[106]Yun C Q, Hua Q W. Think of aggregation on group decision making,systems science and systems engineering[J]. Relation Entropy and Transferable Entropy,2002,11(1):11-18.
[107]余建星,李彦苍,吴海欣,等.基于熵的海洋平台安全评价专家评定模型[J].海洋工程,2006,24(4)：90-94.
[108]Salty T L. The analytic hierarchy process[M]. New York:McGraw-Hill,1980.
[109]汪应洛.系统工程[M].北京：机械工业出版社,1999.
[110]邱菀华.管理决策与应用熵学[M].北京：机械工业出版社,2002.
[111]Fulvio A, Marco B, Maurizio C. A fuzzy software for the energy and environmental balances of products[J]. Ecological Modelling,2004,176(3-4):359-379.
[112]Zheng G Z, Zhu N, Tian Z, et al. Application of a trapezoidal fuzzy AHP method for work safety evaluation and early warning rating of hot and humid environments[J]. Safety Science, 2012,50:228-239.
[113]Li S C. Fuzzy hierarchical weight analysis for criteria of the Taiwan national quality award[J]. Kaoyuan Journal,2005,11(7):259-279.
[114]Hsu Y G, Tzeng G H, Shyu J Z. Fuzzy multiple criteria selection of government-sponsored frontier technology R&D projects[J]. R&D Management,2003,33(5):539-551.
[115]Mergias I, Moustakas K, Papadopoulos A, et al. Multi-criteria decision aid approach for the selection of the best compromise management scheme for ELVs:the case of Cyprus[J]. Journal of Hazardous Materials,2007,147(3):706-717.
[116]Muller K R, Mika S, Ratsch G, et al. An introduction to kernel-based learning algorithms[J]. IEEE Transactions on Neural Networks,2001,12(2):181-202.
[117]Lin K M.A study on reduced support vector machines[J]. IEEE Trans, Menural Network, 2003,14(6):1449-1459.
[118]Edmundo B H, Beatrice D,Jin-Kao Hao. A hybrid GA/SVM approach forgene selection and classification of microarray data[J]. Application of Evolutionary Computing,2006,3907:34-44.
[119]戴晓晖,李敏强,寇纪淞.遗传算法理论研究综述[J].控制与决策,2000,15(3)：263-268.
[120]吕蕾,刘弘.基于支持向量机的小区规划方案评价方法[J].计算机技术与发展,2009,19(1)：193-196.
[121]许建强,李高平.基于遗传算法的支持向量机的特征选取[J],计算机工程,2004,12(24)：1-2.
[122]Nandi S. Process modeling and optimization strategies integrating neural networks/support vector regression and genetic algorithms:study of Benzene isopropylation on Hbeta eatalyst[J]. Chemieal Engineering Journal,2004,23(97):115-129.
[123]杨旭,纪玉波,田雪.基于遗传算法的SVM参数选取[J].辽宁石油化工大学学报,2004,22(1)：54-58.
[124]Pai P F, Hong W C. Forecasting regional electrieity load based on recurrent support vector machines with genetic algorithms[J]. Electric Power Systems Research,2005,45(74):417-425.
[125]Samanta B. Gear fault detection using artificial neural networks and support vector machines with genetic algorithms[J]. Mechanical Systems and Signal Proeessing, 2004(18):625-644.
[126]Muhlenthen H, Voosen D S. Predictive models for the breeder genetic algorithm: continuous parameter optimization[J]. Evolutionary Computation,2003,11(1):25-29.
[127]黄解军.贝叶斯网络结构学习及其在数据挖掘中的应用研究[D].武汉大学,2005.
[128]Hou G X, Li H B, Recknagel F, et al. Modeling phytoplankton dynamics in the River Darling (Australia) using the radial basis function neural network[J]. Journal of Freshwater Ecology,2006,21(4):639-647.
[129]Hou G X, Li HB, Recknagel F, et al. Using the moving window incorporated neural network to forecast the population behavior of Nostocales spp. in the River Darling[J]. Australia: Fresenius Environmental Bulletin,2007,16(3):304-309.
[2]Bao S X, Zhang Y M, Liu T, et al. The production, conSVMption and market analysis of Vanadium in the world[J]. China Mining Magazine,2009,18(7):12-15.
[3]宾智勇.石煤提钒研究进展与五氧化二钒的市场状况[J].湖南有色金属,2006,22(1)：16-20.
[4]段炼,田庆华,郭学益.我国钒资源的生产及应用研究进展[J].湖南有色金属,2006,22(6)：17-19.
[5]蔡晋强.石煤提钒工艺及设备进展[J].稀有金属与硬质合金,2010,38(2)：67-71.
[6]Mi X X, Lan W F. Processes of Vanadium extraction pentoxide from stone coal [J]. Hydrometallurgy of China,2008,27(4):208-211.
[7]荣华.日本开发大容量钒二次电池[J].有色与稀有金属国外动态,1995(11)：14-16.
[8]漆明鉴.从石煤中提钒现状及前景[J].湿法冶金,1999,4(12)：1-10.
[9]段炼,田庆华,郭学益.我国钒资源的生产及应用研究进展[J].湖南有色金属,2006,22(6)：17-22.
[10]王忠,王军.国内外五氧化二钒市场状况与分析[J].矿冶工程,2007,16(2)：47-51.
[11]Moskalyk R R, Alfantazi A M. Review processing of Vanadium[J]. Minerals Engineering, 2003,16:793-805.
[12]刘景槐,牛磊.湖南怀化会同地区含钒石煤提钒与资源综合利用[J].有色金属工程,2012(4)：31-35.
[13]齐小鸣.钒消费前景看好-国内外钒资源、生产和市场预测[J].世界有色金属,2008(5)：38-41.
[14]许国镇,夏华,戈西锷.江西皈大石煤中钒的价态初步研究[J].矿产资源利用,1983(4)：39-44.
[15]许国镇,司徒安力,陈农,等.湖北杨家堡石煤中的钒的价态研究[J].地球化学,1984(4)：379-389.
[16]包申旭,张一敏,胡杨甲,等.石煤焙烧过程中矿相与钒价态的变化及对钒浸出的影[J].矿冶工程,2007,16(2)：47-51.
[17]陈庆根.石煤钒矿提钒工艺技术的研究进展[J].矿产综合利用.2009(2)：30-33.
[18]刘景槐,谭爱华.我国石煤钒矿提钒现状综述[J].湖南有色金属.2010,26(5)：11-14.
[19]舒型武.石煤提钒工艺及废物治理综述[J].钢铁技术,2007(1)：47-50.
[20]何东升.石煤型钒矿焙烧—浸出过程的理论研究[D].中南大学,2009.
[21]Huang J, Zhang Y M, Liu T, et al. Extraction of Vanadium from low-grode Vanadium shale using Bi-circulation and high-efficiency oxidization roast technology[C]. Proceeding of the 48th conference of metallurgists,2009,73-80.
[22]Nadi E Y A, Awwad N S, Nayl A A. A comparative study of Vanadium extraction by aliquat-336 from acidic alkaline media with application to spent catalyst[J]. International Joumal of Mineral Processing,2009,92:115-120.
[23]Liu Y, Yang C, Li P, et al. A new process of extracting Vanadium from stone coal[J]. International Journal of Minerals, Metallurgy, and Materials.2010,17(4),381-382.
[24]Bie S, Wang Z, Li Q, et al. Review of Vanadium extraction from stone coal by roasting technique with sodium chloride and calcium oxide[J]. Chinese Journal of Rare Metals,2010,34(2):291-297.
[25]邹骁勇,彭清静,欧阳玉祝,等.高硅低钙钒矿的钙化焙烧过程[J].过程工程学报,2001(2)：189-192.
[26]Xu Y, Hou Y, Yang H. Experimental study on the overall recovering silver and Vanadium from the black shale-hosted silver and Vanadium deposits[J]. Mining and Metallurgical Engineering,2008,28(1):67-70.
[27]He D, Feng Q, Zhang G, et al. An environmentally-friendly technology of Vanadium extraction from stone coal[J]. Minerals Engineering,2007,20:11184-11186.
[28]黄晶,张一敏,刘涛,等.石煤提钒碳酸盐复合添加剂的研制及焙烧工艺研究[J].矿冶工程,2012,32(z1)：93-96.
[29]黄晶.碳质含钒页岩高效提取技术及机理研究[D].武汉理工大学,2010.
[30]包申旭,张一敏,刘涛,等.电渗析处理石煤提钒废水[J].中国有色金属学报,2010,20(7)：1440-1445.
[31]刘涛,张一敏,李佳.石煤提钒行业污染防治技术现状及进展[J].环境保护.2013,41(15)：75-79.
[32]郑桂花.石煤提钒工艺清洁生产评价的研究[D].武汉理工大学,2009.
[33]Saaty T L. The analytic hierarchy process:planning priority setting, resource allocation[M]. New York,1980.
[34]Barbiroli G, Raggi A. A method for evaluating the overall technical and economic performance of environmental innovations in production cycles[J]. Journal of Cleaner Production, 2003,11:365-374.
[35]杜栋,庞庆华.现代综合评价方法与案例精选[M].北京：清华大学出版社,2008.
[36]白兵.煤炭开采清洁生产水平评价方法研究[D].河北理工大学,2009.
[37]Fayyad U, Uthursamy R. Evolving data mining into solutions for insights[J].Communications of The ACM,2002,45(8):28-31.
[38]Han J W, Kamber M, Mining D. Concepts and techniques[M], Morgan Kaufmann Publishers, 2000.
[39]Fayyad U, Shapiro G P, Smyth P. Knowledge discovery and data mining, towards a unifying framework[C]. Proceedings of 2nd International Conference on knowledge Discovery and Data Mining,1996:82-88.
[40]Brachman R J, Arand T. The process of knowledge discovery in databases; A human-centered approach[C]. Advance In knowledge Discovery And Data Mining,1996:37-58.
[41]关菁华.基于贝叶斯网数据挖掘若干问题研究[D].吉林大学,2009.
[42]Safavian S R, Landgrebe D. A survey of decision tree classifier methodology[M]. School of Electrical Engineering Purdue University,2002.
[43]申文明,王文杰,罗海江,等.基于决策树分类技术的遥感影像分类方法研究[J].遥感技术与应用,2001,22(3)：333-337.
[44]余晶,蒋平安,高敏华.基于决策树的土地应用方法研究[J].新疆农业科学,2009,46(2)：214-218.
[45]李锡钦.结构方程模型[M].北京：高等教育出版社,2011.
[46]Andrade A R, Teixeira P F. A bayesian model to assess rail track geometry degradation through its life-cycle[J]. Research in Transportation Economics,2011,137(3):193-200.
[47]Goulding R, Jayasuriya N, Horan E. A bayesian network model to assess the public health risk associated with wet weather sewer overflows discharging into waterways[J]. Water Research, 2012,46(16),4933-4940.
[48]王晨婉.基于贝叶斯理论的供水管道风险评价研究[D].天津大学,2010.
[49]赵晓慎.基于熵权法赋权的贝叶斯水质评价模型[J].水电能源科学,2011,29(6)：33-35.
[50]张泽旭.神经网络控制与MATLAB仿真[M].哈尔滨：哈尔滨工业大学出版社,2011.
[51]Li M S, Chen W C. Application of BP neural network algorithm in sustainable development of highway construction projects[J]. Changsha University of Science& Technology, 2012(25):1212-1217.
[52]Singh K P, Basant A, Malik A, et al. Artificial neural network modeling of the rier water quality-A case study[J]. India Institute of Taxicology Research,2009,220:888-895.
[53]杜刚.改进的BP神经网络在地下水质评价中的应用[D].上海师范大学,2007.
[54]张旭.基于BP神经网络的清洁生产评价模型研究[D].重庆大学,2009.
[55]李敏强,寇纪淞,林丹,等.遗传算法的基本理论与应用[M].北京：科学出版社,2002.
[56]Niu Y, He W B, Zhang J. Using genetic algorithm to improve fuzzy k-NN[J]. Suzhou, 2008,8:475-479.
[57]Fu X J, Wang L P. Rule extraction by genetic algorithms based on a simplified RBF neural network [J]. Congress on Evolutionary Computation,2001(2):753-758.
[58]穆阿华,周绍磊,刘青志,等.利用遗传算法改进BP学习算法[J].计算机仿真,2005,22(2)：150-152.
[59]马祥陆.遗传算法的贝叶斯网络学习算法[D].吉林大学,2007.
[60]Week M, Klocke F, Schell H, et al. Evaluating alternative production cycles using the extended fuzzy AHP method[J]. European Journal of Operational Research,1997,100(2):351-366.
[61]Zheng G Z, Zhu N, Tian Z, et al. Application of a trapezoidal fuzzy AHPmethod for work safety evaluation and early warning rating of hot and humid environments[J]. Safety Science, 2012,50:228-239.
[62]Laarhoven V, Pedrycz P J M. A fuzzy extension of saaty's priority theory[J]. Fuzzy Set System,1983,11(3):229-241.
[63]Cengiz K, Ufuk C, Ziya U. Multi-criteria supplier selection using fuzzy AHP[J]. Logistics Information Management,2003,16(6):382-394.
[64]Tseng ML, Lin YH, Chiu A S F. Fuzzy AHP-based study of cleaner production implementation in Taiwan PWB manufacture[J]. Journal of Cleaner Production, 2009,17:1249-1256.
[65]Wang Y K, Wang D, Ma H Q, et al. Risk assessment for flood control engineering using fuzzy theory:A case study in China[C]. Nanjing University,2011.
[66]李远贵.提高支持向量机的学习效率和分类速度的研究和应用[D].上海交通大学,2006.
[67]许建华,张学工,李衍达.支持向量机的新发展[J].控制与决策,2004,19(5)：481-484.
[68]Vapnik V. Statistical learning theory[M]. New York:Springer,1998.
[69]朱明.数据挖掘[M].中国科学技术大学出版社,2008.
[70]杨力.基于小样本数据的矿井瓦斯突出风险评价[D].中国科学技术大学,2011.
[71]Reyna R A, Hernandez N, Esteve D, et al. Segmenting images with support vector machines[J]. Vancouver,2000,1:820-823.
[72]Keren D, Osadchy M, Gostman C. Antifaces:A novel, fast method for image detection[J]. IEEE transactions on pattern analysis and machine intelligence,2001,23(7):747-761.
[73]Dong G G, Jain A K, Ying M W, et al. Learning similarity measure for natural image retrieval with relevance feedback[J]. IEEE Transactions on Neural Networks,2002,13(4):811-820.
[74]Brown M, Lewis H G, Gunn S R. Linear spectral mixture models and support vector machines for remote sensing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000,38(5):2346-2360.
[75]Pontil M, Verri A. Support vector machines for 3D object recognition[J]. IEEE Transactions on pattern Analysis and Machine Intelligence,1998,20(6):637-646.
[76]Xin D, Wu Z. Speaker recognition using continuous density support vector machines[J]. Electronics Letters,2001,37:1009-1101.
[77]Osuna E, Freund R, Girosi F. Training support machines:An application to face detection[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Puerto, 1997:130-136.
[78]赵晖.支持向量机分类方法及其在文本分类中的应用研究[D].大连理工大学,2005.
[79]Valentini G. Gene expression data analysis of human lymphoma using support vector machines and output coding ensembles[J]. Artificial Intelligence in Machines, 2002,26(3):281-304.
[80]Cai Y, Liu X, Xu X, et al. Prediction of protein structural classes by support vector machines[J]. Computers and Chemistry,2002,26(3):293-296.
[81]Bbanu P K, Ramakrishnan A G, Suresh S, et al. Fetal lung maturity analysis using ultrasound image features[J]. IEEE Transactions on Information Technology in Biomedicine, 2002,6(1):38-45.
[82]Bradley P, Mangasarian O L. Feature selection via concave minimization and support vector machines[C]. Machine Learning Proceedings of the Fifteenth International Conference. San Francisco,1998,82-90.
[83]Fung G. The disputed federalist papers:SVM feature selection via concave minimization[C]. Journal of the ACM,2003,42-46.
[84]Sun W, Yang C G. Credit risk assessment in commercial banks based on muti-layer SVM classifier[J]. Computational Intelligence,2006,4114:778-785.
[85]Bui D T, Pradhan B, Lofman O, et al. Landslide susceptibility assessment in vietnam using support vector machines,decision tree,and na□ve bayes models[J]. Problems in Engineering, 2012(2012):26.
[86]王冉,杨道军.基于支持向量机的巢湖富营养化程度评价研究[J].环境科学与管理,2005,5：180-184.
[87]张磊,郑丕谔,王中权,等.基于支持向量机的中国石油安全分析[J].工业工程,2010,13(4)：40-47.
[88]Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letters,1999,9:293-300.
[89]Scholkopf B, Smola A, Williamson P C, et al. New support vector algorithms[J].Neural Computation,2000,12:1207-1245.
[90]Tsang E C C, Yeung D S, Chan P P K. Fuz2y support vector machines for solving two-class problems[J]. Proceedings of the Second International Conference on Machine Learning and Cybernetics,2003,1:1080-1083.
[91]Daisuke T, Shigeo A. Fuzzy least squares support vector machines for multiclass problems[J]. Neural Networks,2003,16:785-792.
[92]Hsu C, Lin C J. A simple decomposition method for support vector machines[J]. Machine Learning,2002,46:291-314.
[93]David M J T, Robert P W D. Data domain description using support vector[A]. Proceedings of the Unropean Symposium on Artificial Neural Network, bruges(Belgium), 1999(20):1191-1199.
[94]David M J T, Robert P W D. Support vector domain description[J]. Pattern Recognition Letters,1999,20:1191-1199.
[95]丁胜峰.基于模糊推理的多源图像融合研究[D].南京理工大学,2004.
[96]王喜宾,张小平,王翰虎.基于粒子群优化模式搜索的支持向量机参数优化应用[J].计算机应用,2011,31(12)：3302-3305.
[97]李露璐.基于改进的SVM算法的耕地地力评价模型研究[J].沈阳农业大学学报,2012,43(1)：126-128.
[98]陈海洋,滕彦国,王金生.基于GA参数寻优的决策树支持向量机生态环境质量评价方法[J].生态与农村环境学报,2010,26(6)：600-604.
[99]李佳,张一敏,刘涛.石煤提钒行业清洁生产评价指标体系建立[J],环境科学与技术,2013,36(7)：191-194.
[100]Thomas F. Produce life cycle assessment principles and methodology [M].Nordic Council of Ministers,1992.
[101]GB/T2010-2006工业清洁生产评价指标体系编制通则[S].北京：中国国家标准化管理委员会,2006.
[102]Jia Li, Yimin Zhang, Tao Liu. Research on pollution prevention and control technologies in the industry of Vanadium extraction from stone coal[J]. Int. J. Environmental Technology and Management 2013.
[103]Ezatollah K. Appropriateness of farmers'adoption of irrigation methods:the application of the AHP model[J]. Agricultural systems,2006,87:101-119.
[104]Mergias I, Moustakas K, Papadopoulos A, et al. Multi-criteria decision aid approach for the selection of the best compromise management scheme for ELVs:the case of Cyprus[J]. Journal of Hazardous Materials,2007,147(3):706-717.
[105]司春棣.引水工程安全保障体系研究[D].天津大学,2007.
[106]Yun C Q, Hua Q W. Think of aggregation on group decision making,systems science and systems engineering[J]. Relation Entropy and Transferable Entropy,2002,11(1):11-18.
[107]余建星,李彦苍,吴海欣,等.基于熵的海洋平台安全评价专家评定模型[J].海洋工程,2006,24(4)：90-94.
[108]Salty T L. The analytic hierarchy process[M]. New York:McGraw-Hill,1980.
[109]汪应洛.系统工程[M].北京：机械工业出版社,1999.
[110]邱菀华.管理决策与应用熵学[M].北京：机械工业出版社,2002.
[111]Fulvio A, Marco B, Maurizio C. A fuzzy software for the energy and environmental balances of products[J]. Ecological Modelling,2004,176(3-4):359-379.
[112]Zheng G Z, Zhu N, Tian Z, et al. Application of a trapezoidal fuzzy AHP method for work safety evaluation and early warning rating of hot and humid environments[J]. Safety Science, 2012,50:228-239.
[113]Li S C. Fuzzy hierarchical weight analysis for criteria of the Taiwan national quality award[J]. Kaoyuan Journal,2005,11(7):259-279.
[114]Hsu Y G, Tzeng G H, Shyu J Z. Fuzzy multiple criteria selection of government-sponsored frontier technology R&D projects[J]. R&D Management,2003,33(5):539-551.
[115]Mergias I, Moustakas K, Papadopoulos A, et al. Multi-criteria decision aid approach for the selection of the best compromise management scheme for ELVs:the case of Cyprus[J]. Journal of Hazardous Materials,2007,147(3):706-717.
[116]Muller K R, Mika S, Ratsch G, et al. An introduction to kernel-based learning algorithms[J]. IEEE Transactions on Neural Networks,2001,12(2):181-202.
[117]Lin K M.A study on reduced support vector machines[J]. IEEE Trans, Menural Network, 2003,14(6):1449-1459.
[118]Edmundo B H, Beatrice D,Jin-Kao Hao. A hybrid GA/SVM approach forgene selection and classification of microarray data[J]. Application of Evolutionary Computing,2006,3907:34-44.
[119]戴晓晖,李敏强,寇纪淞.遗传算法理论研究综述[J].控制与决策,2000,15(3)：263-268.
[120]吕蕾,刘弘.基于支持向量机的小区规划方案评价方法[J].计算机技术与发展,2009,19(1)：193-196.
[121]许建强,李高平.基于遗传算法的支持向量机的特征选取[J],计算机工程,2004,12(24)：1-2.
[122]Nandi S. Process modeling and optimization strategies integrating neural networks/support vector regression and genetic algorithms:study of Benzene isopropylation on Hbeta eatalyst[J]. Chemieal Engineering Journal,2004,23(97):115-129.
[123]杨旭,纪玉波,田雪.基于遗传算法的SVM参数选取[J].辽宁石油化工大学学报,2004,22(1)：54-58.
[124]Pai P F, Hong W C. Forecasting regional electrieity load based on recurrent support vector machines with genetic algorithms[J]. Electric Power Systems Research,2005,45(74):417-425.
[125]Samanta B. Gear fault detection using artificial neural networks and support vector machines with genetic algorithms[J]. Mechanical Systems and Signal Proeessing, 2004(18):625-644.
[126]Muhlenthen H, Voosen D S. Predictive models for the breeder genetic algorithm: continuous parameter optimization[J]. Evolutionary Computation,2003,11(1):25-29.
[127]黄解军.贝叶斯网络结构学习及其在数据挖掘中的应用研究[D].武汉大学,2005.
[128]Hou G X, Li H B, Recknagel F, et al. Modeling phytoplankton dynamics in the River Darling (Australia) using the radial basis function neural network[J]. Journal of Freshwater Ecology,2006,21(4):639-647.
[129]Hou G X, Li HB, Recknagel F, et al. Using the moving window incorporated neural network to forecast the population behavior of Nostocales spp. in the River Darling[J]. Australia: Fresenius Environmental Bulletin,2007,16(3):304-309.