精密电液伺服阀几何因素与性能指标映射关系研究
|
摘要
鉴于电液伺服系统特有的优点,飞行器的控制系统多采用电液伺服系统实现。作为电液伺服系统中的关键部件,电液伺服阀很大程度上决定了电液伺服系统的性能和航天器飞行任务的成败。航空航天用精密电液伺服阀结构复杂、精密度高,且应用环境恶劣,属于高技术产品。由于受到零、组件加工、装配过程中多种几何因素的影响,精密电液伺服阀的性能指标控制难度较大,直接导致产品合格率低、返修率较高,同时造成极大的资源浪费。精密电液伺服阀的生产能力低已经成为制约我国航空航天事业发展的重要因素之一。因此,如何提高精密电液伺服阀产品合格率及生产效率,避免大量的返修工作,成为相关制造企业面临的一个亟待解决的难题。
以多项高性能指标为制造要求的精密电液伺服阀产品,采用不断提高零、组件加工精度和装配精度,以及精度稳定性的方法,是保证和提高精密电液伺服阀产品合格率的有效途径。但是,鉴于现有生产条件下,加工装备及技术水平的局限性,这种方式将使生产成本以指数倍增加,不切实际。因此,探讨利用现代计算分析方法优化制造要求、提高精密电液伺服阀合格率及生产效率的有效途径,对工业生产具有重要意义。
以航空制导系统中关键部件——精密电液伺服阀为例,首先分析了国内外电液伺服阀相关技术及复杂系统数据关联分析及人工智能建模方法的研究现状,在研究确定精密电液伺服阀多几何因素对性能指标影响的主次关系的基础上,对性能指标预测方法、影响多项性能指标的几何因素区间估计方法进行了深入的研究,最终开发了精密电液伺服阀综合分析系统,研究成果对优化精密电液伺服阀制造要求,提高产品合格率及生产效率具有重要意义。具体研究工作包括以下几点：
(1)研究了精密电液伺服阀多几何因素对各性能指标影响的主次关系。采用灰关联分析方法,对实际测试数据进行灰关联分析以确定影响精密电液伺服阀各性能指标的主要因素和次要因素,结合粗糙决策方法,建立影响精密电液伺服阀各性能指标的多几何因素特征提取模型,实现通过合理控制影响精密电液伺服阀性能指标的几何因素来控制性能指标的目的,同时解决了直接建立精密电液伺服阀性能指标数学模型因输入变量多而不切实际的难题。利用所确定的主要几何因素建立各性能指标预测模型,降低输入空间维数,简化建模过程,提高建模精度。为全文的研究奠定了基础。
(2)合理控制影响精密电液伺服阀性能指标的几何因素,装配后精密电液伺服阀产品不合格的情况仍会发生。鉴于传统系统建模方法对于复杂系统建模的局限性,基于数据挖掘提取的有效信息及精密电液伺服阀多几何因素与性能指标之间的关联模型,采用神经网络、支持向量机及模糊推理技术等人工智能算法探索研究了精密电液伺服阀性能指标预测方法,建立了精密电液伺服阀多几何因素与性能指标之间的数学模型,实现了对精密电液伺服阀性能指标的精确预测。通过进行数值模拟和仿真,进一步改进性能指标预测模型及算法,结合现代数值分析方法对实测结果与预测值进行分析比较,结果验证了所建立算法的有效性。通过分析预测结果,直接确定精密电液伺服阀产品是否合格,实现零、组件选配,剔除不合格组件,避免了反复装卸、检测工作,有效提高生产效率。
(3)对于返修件,研究确定影响精密电液伺服阀性能指标的多几何因素区间范围值,将使零、组件返修具有针对性；另外,对于特定性能指标要求的精密电液伺服阀产品,可以确定零、组件几何因素值的设计范围。研究成果将为产品设计者、制造者提供理论与技术支持。基于数据挖掘提取有效信息,结合逆向工程思想,采用合理的优化设计方法及智能算法,建立了精密电液伺服阀多性能指标与几何因素之间的区间估计模型,实现精密电液伺服阀几何因素的区间估计。利用所建立的区间估计模型,可获得多几何因素合理区间值。
(4)生产精密电液伺服阀产品牵涉企业设计、制造、质检等多个部门,研究开发精密电液伺服阀综合分析系统,从而促进多部门之间的协调能力,实现产品信息的快速交换,是提高精密电液伺服阀产品生产效率的重要途径。基于以上研究成果,采用SQL建立精密电液伺服阀产品信息数据库,利用MATLAB实现数据计算及仿真,通过VC实现可视化操作,研究SQL、MATLAB及VC三者之间的接口技术,开发出精密电液伺服阀综合分析系统平台,为精密电液伺服阀多几何因素对性能指标影响的主次关系、性能指标预测及几何因素区间估计提供可靠的测试手段,为提高精密电液伺服阀产品成品率提供一种新手段,同时对推动现代建模方法在工程技术领域的应用和发展起到重要作用。
本文关于精密电液伺服阀几何因素与性能指标映射关系的研究,包括：影响性能指标的主次因素分析、性能指标预测方法及零、组件几何因素区间估计方法等已经在航空制导系统中构成电液伺服作动器的关键部件——精密电液伺服阀上进行了初步应用。
In view of the advantage of electro-hydraulic servo system, the control system of aircraft often uses the electro-hydraulic servo system. As a key component of electro-hydraulic servo system, the electro-hydraulic servo valve largely determines the performance of electro-hydraulic servo system and the success or failure of aircraft mission. Precise electro-hydraulic servo valve used in aerospace field is a kind of high-tech product, as its complicated structure, high precision and application under worse environment. Influenced by all kinds of geometric factors, such as the machining and assembly precision of the parts and components, the characteristics of precise electro-hydraulic servo valve is rather difficult to be controlled. It results in rather low pass rate and higher rework rate and more costs of the resources as well. The low production ability of precise electro-hydraulic servo valve has been become one of the important factors to restrict the development of aerospace career in our country. Therefore, that how to improve the pass rate and production efficiency of precise electro-hydraulic servo valve and avoid abundance of repair works becomes one of difficult problem that solve urgently in related manufacture enterprises.
Precise electro-hydraulic servo valve product takes multiple characteristics as manufacturing request. The effective way to ensure and improve its pass rate is to improve the machining and assembly precision of the parts and components and the precision stability. However, in view of the limitations of the machining equipment and technology in the existing producing conditions, it is unrealistic to use the above method for it increases the costs on production exponentially. Therefore, it makes lots of sense on industrial production that the effective way is researched by utilizing modern calculation methods to raise the pass rate and production efficiency of precise electro-hydraulic servo valve product.
Precise electro-hydraulic servo valve product, which is the key part in the guidance system in aeronautics industry, is taken for an example. The current situation of research on related technology of electro-hydraulic servo valve, data mining and artificial intelligence method at home and abroad is analyzed at first. Based on the determination of the primary or secondary relationship of each geometric factor for characteristics of precise electro-hydraulic servo valve, deep researches have been done on the method of the prediction of the system characteristics, the interval estimation method of geometric factors which have an influence on the multiple characteristics of the system. Moreover, the synthetic analysis system of precise electro-hydraulic servo valve product has been developed. It is of great significance for research results to optimize the manufacture requirment and increase the rate of finished products and the production efficiency of precise electro-hydraulic servo valve product. The research work in details is as follows:
(1) The primary or secondary relationship of each geometric factor for characteristics of precise electro-hydraulic servo valve product has been studied. Grey correlation analyzing method is adopted to analyze the actual tested data to ascertain the major factors and minor factors of each characteristics of precise electro-hydraulic servo valve product. Rough set strategy method is combined to develop the feature extraction model of multiple geometric factors of precise electro-hydraulic servo valve product in order to control the characteristics by controlling the major geometric factors which have an influence on the characteristics of precise electro-hydraulic servo valve. Meanwhile, the unrealistic problem on dealing with many input variables has been settled when developing the mathematical model of precise electro-hydraulic servo valve product. The characteristics prediction model is developed by using the major geometric factors which have been ascertained to decrease the number of dimensions of the input space, simplify the modeling process and thus improve the modeling precision. It has laid a foundation for the whole research work.
(2) When controlling geometric factors affecting the characteristics of precise electro-hydraulic servo valve reasonablely, the case that precise electro-hydraulic servo valve product after assembly is unqualified occurs occasionally. In view of the limitations of the traditional system modeling method on the modeling of complex systems, and based on the effective information selected by data mining and the correlated model between multiple geometric factors and characteristics of precise electro-hydraulic servo valve product, the characteristics prediction model of precise electro-hydraulic servo valve product is explored and studied by using artificial intelligence algorithm such as neural network, support vector machine and fuzzy inference technology. The mathematical model between multiple geometric factors and characteristics of precise electro-hydraulic servo valve product has been set up so that precise prediction of the characteristics of precise electro-hydraulic servo valve product is realized. The results have proved the effectiveness of the algorithm set up by data modeling and simulation, improving the characteristics prediction model and algorithm of the system, and analyzing and comparing the actual testing results and the predicting figures by utilizing modernized numerical analysis method. Whether the precise electro-hydraulic servo valve product is qualified or not can be directly ascertained by analyzing the prediction results and the unqualified components can also be got rid of so that the repetitive assembly and disassembly, and testing work are prevented and the producing efficiency can been improved.
(3) As for the unqualified components, it has the pertinence on the rework of the parts and components to research that how to determine the range of multiple geometric factors which affect the characteristics of precise electro-hydraulic servo valve product. Moreover, as for the precise electro-hydraulic servo valve products which have specific performance requirements, the design range of geometric factors of the parts and components can be got. Obviously, the research achievement will provide both theoretical and technological support for product designers and manufacturers. It is also a challenge in the product design and production of precise electro-hydraulic servo valve product. The effective information is extracted based on data mining and by the thought of reverse engineering, proper optimized design method and intelligence algorithm are adopted to develop the interval estimation model between the multiple characteristics and geometric factors of the precise electro-hydraulic servo valve product. The interval estimation of geometric factors of precise electro-hydraulic servo valve product is realized. The interval values of multiple geometric factors can be obtained utilizing the interval estimation model which has been set up.
(4) Many departments in enterprises, such as the designing department, manufacturing department and quality inspection department, etc. are involved in the production of precise electro-hydraulic servo valve product. It is a major approach for the improvement of the producing efficiency of precise electro-hydraulic servo valve product to study and develop synthesis analysis system of precise electro-hydraulic servo valve product system so as to increase the coordination capabilities among departments and realize rapid exchanges of products'information. Based on the above research achievements, SQL is adopted to develop the information data base for precise electro-hydraulic servo valve product, MATLAB is utilized to calculate and simulate the data, and VC helps achieve visualization operation. The research of the interface technology among SQL, MATLAB and VC to develop the synthesis analyzing system platform of precise electro-hydraulic servo valve product will provide a reliable test method for the primary or secondary relationship of each geometric factor for characteristics of precise electro-hydraulic servo valve product, characteristics prediction and the reverse interval estimation for geometric factors. It offers a new method to improve the rate of finished products of precise electro-hydraulic servo valve product and meanwhile it plays an important role in promoting the application and development of modernized modeling method in the field of engineering and technology.
The research works in this paper of mapping relationship between geometric parameters and characteristics for precise electro-hydraulic servo valve, include:major factors and minor factors analysis for characteristics, prediction method of the characteristics and the interval estimation method for multiple geometric factors, have been applied preliminary to a precise electro-hydraulic servo valve, which is the key part of the hydraulic actuator in the guidance system in aeronautics industry.
以多项高性能指标为制造要求的精密电液伺服阀产品,采用不断提高零、组件加工精度和装配精度,以及精度稳定性的方法,是保证和提高精密电液伺服阀产品合格率的有效途径。但是,鉴于现有生产条件下,加工装备及技术水平的局限性,这种方式将使生产成本以指数倍增加,不切实际。因此,探讨利用现代计算分析方法优化制造要求、提高精密电液伺服阀合格率及生产效率的有效途径,对工业生产具有重要意义。
以航空制导系统中关键部件——精密电液伺服阀为例,首先分析了国内外电液伺服阀相关技术及复杂系统数据关联分析及人工智能建模方法的研究现状,在研究确定精密电液伺服阀多几何因素对性能指标影响的主次关系的基础上,对性能指标预测方法、影响多项性能指标的几何因素区间估计方法进行了深入的研究,最终开发了精密电液伺服阀综合分析系统,研究成果对优化精密电液伺服阀制造要求,提高产品合格率及生产效率具有重要意义。具体研究工作包括以下几点：
(1)研究了精密电液伺服阀多几何因素对各性能指标影响的主次关系。采用灰关联分析方法,对实际测试数据进行灰关联分析以确定影响精密电液伺服阀各性能指标的主要因素和次要因素,结合粗糙决策方法,建立影响精密电液伺服阀各性能指标的多几何因素特征提取模型,实现通过合理控制影响精密电液伺服阀性能指标的几何因素来控制性能指标的目的,同时解决了直接建立精密电液伺服阀性能指标数学模型因输入变量多而不切实际的难题。利用所确定的主要几何因素建立各性能指标预测模型,降低输入空间维数,简化建模过程,提高建模精度。为全文的研究奠定了基础。
(2)合理控制影响精密电液伺服阀性能指标的几何因素,装配后精密电液伺服阀产品不合格的情况仍会发生。鉴于传统系统建模方法对于复杂系统建模的局限性,基于数据挖掘提取的有效信息及精密电液伺服阀多几何因素与性能指标之间的关联模型,采用神经网络、支持向量机及模糊推理技术等人工智能算法探索研究了精密电液伺服阀性能指标预测方法,建立了精密电液伺服阀多几何因素与性能指标之间的数学模型,实现了对精密电液伺服阀性能指标的精确预测。通过进行数值模拟和仿真,进一步改进性能指标预测模型及算法,结合现代数值分析方法对实测结果与预测值进行分析比较,结果验证了所建立算法的有效性。通过分析预测结果,直接确定精密电液伺服阀产品是否合格,实现零、组件选配,剔除不合格组件,避免了反复装卸、检测工作,有效提高生产效率。
(3)对于返修件,研究确定影响精密电液伺服阀性能指标的多几何因素区间范围值,将使零、组件返修具有针对性；另外,对于特定性能指标要求的精密电液伺服阀产品,可以确定零、组件几何因素值的设计范围。研究成果将为产品设计者、制造者提供理论与技术支持。基于数据挖掘提取有效信息,结合逆向工程思想,采用合理的优化设计方法及智能算法,建立了精密电液伺服阀多性能指标与几何因素之间的区间估计模型,实现精密电液伺服阀几何因素的区间估计。利用所建立的区间估计模型,可获得多几何因素合理区间值。
(4)生产精密电液伺服阀产品牵涉企业设计、制造、质检等多个部门,研究开发精密电液伺服阀综合分析系统,从而促进多部门之间的协调能力,实现产品信息的快速交换,是提高精密电液伺服阀产品生产效率的重要途径。基于以上研究成果,采用SQL建立精密电液伺服阀产品信息数据库,利用MATLAB实现数据计算及仿真,通过VC实现可视化操作,研究SQL、MATLAB及VC三者之间的接口技术,开发出精密电液伺服阀综合分析系统平台,为精密电液伺服阀多几何因素对性能指标影响的主次关系、性能指标预测及几何因素区间估计提供可靠的测试手段,为提高精密电液伺服阀产品成品率提供一种新手段,同时对推动现代建模方法在工程技术领域的应用和发展起到重要作用。
本文关于精密电液伺服阀几何因素与性能指标映射关系的研究,包括：影响性能指标的主次因素分析、性能指标预测方法及零、组件几何因素区间估计方法等已经在航空制导系统中构成电液伺服作动器的关键部件——精密电液伺服阀上进行了初步应用。
In view of the advantage of electro-hydraulic servo system, the control system of aircraft often uses the electro-hydraulic servo system. As a key component of electro-hydraulic servo system, the electro-hydraulic servo valve largely determines the performance of electro-hydraulic servo system and the success or failure of aircraft mission. Precise electro-hydraulic servo valve used in aerospace field is a kind of high-tech product, as its complicated structure, high precision and application under worse environment. Influenced by all kinds of geometric factors, such as the machining and assembly precision of the parts and components, the characteristics of precise electro-hydraulic servo valve is rather difficult to be controlled. It results in rather low pass rate and higher rework rate and more costs of the resources as well. The low production ability of precise electro-hydraulic servo valve has been become one of the important factors to restrict the development of aerospace career in our country. Therefore, that how to improve the pass rate and production efficiency of precise electro-hydraulic servo valve and avoid abundance of repair works becomes one of difficult problem that solve urgently in related manufacture enterprises.
Precise electro-hydraulic servo valve product takes multiple characteristics as manufacturing request. The effective way to ensure and improve its pass rate is to improve the machining and assembly precision of the parts and components and the precision stability. However, in view of the limitations of the machining equipment and technology in the existing producing conditions, it is unrealistic to use the above method for it increases the costs on production exponentially. Therefore, it makes lots of sense on industrial production that the effective way is researched by utilizing modern calculation methods to raise the pass rate and production efficiency of precise electro-hydraulic servo valve product.
Precise electro-hydraulic servo valve product, which is the key part in the guidance system in aeronautics industry, is taken for an example. The current situation of research on related technology of electro-hydraulic servo valve, data mining and artificial intelligence method at home and abroad is analyzed at first. Based on the determination of the primary or secondary relationship of each geometric factor for characteristics of precise electro-hydraulic servo valve, deep researches have been done on the method of the prediction of the system characteristics, the interval estimation method of geometric factors which have an influence on the multiple characteristics of the system. Moreover, the synthetic analysis system of precise electro-hydraulic servo valve product has been developed. It is of great significance for research results to optimize the manufacture requirment and increase the rate of finished products and the production efficiency of precise electro-hydraulic servo valve product. The research work in details is as follows:
(1) The primary or secondary relationship of each geometric factor for characteristics of precise electro-hydraulic servo valve product has been studied. Grey correlation analyzing method is adopted to analyze the actual tested data to ascertain the major factors and minor factors of each characteristics of precise electro-hydraulic servo valve product. Rough set strategy method is combined to develop the feature extraction model of multiple geometric factors of precise electro-hydraulic servo valve product in order to control the characteristics by controlling the major geometric factors which have an influence on the characteristics of precise electro-hydraulic servo valve. Meanwhile, the unrealistic problem on dealing with many input variables has been settled when developing the mathematical model of precise electro-hydraulic servo valve product. The characteristics prediction model is developed by using the major geometric factors which have been ascertained to decrease the number of dimensions of the input space, simplify the modeling process and thus improve the modeling precision. It has laid a foundation for the whole research work.
(2) When controlling geometric factors affecting the characteristics of precise electro-hydraulic servo valve reasonablely, the case that precise electro-hydraulic servo valve product after assembly is unqualified occurs occasionally. In view of the limitations of the traditional system modeling method on the modeling of complex systems, and based on the effective information selected by data mining and the correlated model between multiple geometric factors and characteristics of precise electro-hydraulic servo valve product, the characteristics prediction model of precise electro-hydraulic servo valve product is explored and studied by using artificial intelligence algorithm such as neural network, support vector machine and fuzzy inference technology. The mathematical model between multiple geometric factors and characteristics of precise electro-hydraulic servo valve product has been set up so that precise prediction of the characteristics of precise electro-hydraulic servo valve product is realized. The results have proved the effectiveness of the algorithm set up by data modeling and simulation, improving the characteristics prediction model and algorithm of the system, and analyzing and comparing the actual testing results and the predicting figures by utilizing modernized numerical analysis method. Whether the precise electro-hydraulic servo valve product is qualified or not can be directly ascertained by analyzing the prediction results and the unqualified components can also be got rid of so that the repetitive assembly and disassembly, and testing work are prevented and the producing efficiency can been improved.
(3) As for the unqualified components, it has the pertinence on the rework of the parts and components to research that how to determine the range of multiple geometric factors which affect the characteristics of precise electro-hydraulic servo valve product. Moreover, as for the precise electro-hydraulic servo valve products which have specific performance requirements, the design range of geometric factors of the parts and components can be got. Obviously, the research achievement will provide both theoretical and technological support for product designers and manufacturers. It is also a challenge in the product design and production of precise electro-hydraulic servo valve product. The effective information is extracted based on data mining and by the thought of reverse engineering, proper optimized design method and intelligence algorithm are adopted to develop the interval estimation model between the multiple characteristics and geometric factors of the precise electro-hydraulic servo valve product. The interval estimation of geometric factors of precise electro-hydraulic servo valve product is realized. The interval values of multiple geometric factors can be obtained utilizing the interval estimation model which has been set up.
(4) Many departments in enterprises, such as the designing department, manufacturing department and quality inspection department, etc. are involved in the production of precise electro-hydraulic servo valve product. It is a major approach for the improvement of the producing efficiency of precise electro-hydraulic servo valve product to study and develop synthesis analysis system of precise electro-hydraulic servo valve product system so as to increase the coordination capabilities among departments and realize rapid exchanges of products'information. Based on the above research achievements, SQL is adopted to develop the information data base for precise electro-hydraulic servo valve product, MATLAB is utilized to calculate and simulate the data, and VC helps achieve visualization operation. The research of the interface technology among SQL, MATLAB and VC to develop the synthesis analyzing system platform of precise electro-hydraulic servo valve product will provide a reliable test method for the primary or secondary relationship of each geometric factor for characteristics of precise electro-hydraulic servo valve product, characteristics prediction and the reverse interval estimation for geometric factors. It offers a new method to improve the rate of finished products of precise electro-hydraulic servo valve product and meanwhile it plays an important role in promoting the application and development of modernized modeling method in the field of engineering and technology.
The research works in this paper of mapping relationship between geometric parameters and characteristics for precise electro-hydraulic servo valve, include:major factors and minor factors analysis for characteristics, prediction method of the characteristics and the interval estimation method for multiple geometric factors, have been applied preliminary to a precise electro-hydraulic servo valve, which is the key part of the hydraulic actuator in the guidance system in aeronautics industry.
引文
[1]章宏甲,黄谊.液压传动[M].北京：机械工业出版社,2005.
[2]王春行.液压控制系统[M].北京：机械工业出版社,1999.
[3]肖凯鸣,虞勤俭,王渝,等.MK电液伺服阀结构原理及性能[J].液压气动与密封,1998,4：33-36.
[4]ICHIRYU K, WATANABE H, Yamaguchi T. Direct-acting servo valve. US Patent:US4544129, 1985.
[5]MARCO D A. Linear-force motors enhance proportional valves [J]. Hydraulics & Pneumatics,1998, 4:14-16.
[6]朱盘生MOOG(穆格)DDV伺服阀[J].液压与气动.1996,5：20-21.
[7]HOCKADAY B D. Direct optical actuation for hydraulic systems [J]. Lasers and Electro-Optics Society Annual Meeting,1993,1:143-144.
[8]王新华,孙树文,李剑锋,等.水压伺服控制技术发展的现状及应用前景[J].机床与液压,2008,36(5)：177-180.
[9]阮健,李胜,杨继隆.液压及气动阀直接数字控制的新途径[J].中国机械工程,2000,11(3)：317-320.
[10]张光琼.单级转轴式旋转电液伺服阀[J].机床与液压,1991,2：34-38.
[11]卢菊仙,李树立,焦宗夏.一种有限角度旋转式电液伺服阀[J].液压气动与密封,2005,4：155-157.
[12]付永领,裴忠才,王占林.伺服作动系统的余度控制[J].北京航空航天大学学报,1999,25(5)：531-534.
[13]陈鹏.智能化全自动电液伺服阀配磨系统[J].仪表技术与传感器,1996,2：45-47.
[14]浙人,编译.加工精密伺服阀的自动化“流量磨削”系统[J].世界制造技术与装备市场,1994,4：70.
[15]孙谦.矩形节流窗口的电液伺服阀阀套及其加工[J].1982,2：29-32.
[16]王传礼.基于GMM转换器喷嘴挡板伺服阀的研究[D].硕士学位论文,杭州：浙江大学,2005.
[17]沈传亮,程光明,曾平,等.压电驱动式高频电液伺服阀实验研究[J].哈尔滨工业大学学报,2008,40(9)：1443-1446.
[18]米智楠,钱晋武,龚振邦,李旻,智计龙.形状记忆合金微型阀的研制[J].机床与液压,2001,1：20-21.
[19]盛晓伟.添加磁流体的射流管伺服阀动态性能研究[D].硕士学位论文,哈尔滨：哈尔滨工业大学,2006.
[20]覃爱明.电流变伺服阀的特性研究[J].湘潭大学学报,1998,12：88-90.
[21]佟文王.电液流量伺服阀的发展方向[J].液压与气动,1996,6：3-6.
[22]张坤发.电液伺服阀动静态性能计算机辅助测试系统的研究[D].硕士学位论文,哈尔滨：哈尔滨工业大学,2006.
[23]袁宏杰,李传日,姚金勇.通用电液伺服阀自动测试系统研制[J].机床与液压,2009,37(1)：105-106.
[24]王宣银,孙赫,李潇潇,李福尚.电液伺服阀动静特性一体化自动测试系统研制[J].机床与液压,2010,38(20)：37-38.
[25]许益民.电液伺服阀频率特性测试系统误差分析[J].武汉科技大学学报,2005,28(4)：346-348.
[26]易建钢,湛从昌,吴琼进.电液伺服阀动态特性测试中复合数字滤波算法研究[J].液压与气动,2004,2：15-17.
[27]魏鹏,王占林,裘丽华.基于液压伺服阀动态特性测试的改进型逆重复伪随机算法[J].机床与液压,2005,2：99-101.
[28]刘建.电液伺服阀静动态综合特性计算机辅助测试系统的研发[D].硕士学位论文,秦皇岛：燕山大学,2004.
[29]师占群,王建民,岳宏,刘庆和.基于小波故障提取的电液伺服阀故障诊断[J].机械科学与技术,2000,19：111-112.
[30]陈新元,黄富,陈灿军,吴海峰,曾良才.基于BP神经网络电液伺服阀多参数故障模式识别研究[J].机床与液压,2004,6：179-181.
[31]胡生清,幸国全.未来的仪器仪表一虚拟仪器[J].自动化与仪表,1999,14(6)：15-17.
[32]王益群,王燕山,姜万录.基于虚拟仪器的电液伺服阀静动态特性测试[J].液压气动与密封,2001,1：13-15.
[33]宋涛.基于虚拟一起的电液伺服阀性能测试实验台系统研究[D].硕士学位论文,沈阳：东北大学,2006.
[34]龚树强.基于CAN总线的电液伺服阀静态性能测试系统的研究[D].硕士学位论文,哈尔滨：哈尔滨工业大学,2007.
[35]黄伟.基于虚拟仪器的电液伺服阀静态特性测试[D].硕士学位论文,武汉：武汉科技大学,2008.
[36]张正甫.基于虚拟仪器的电液伺服阀测试系统研究[D].硕士学位论文,广州：广东工业大学,2004.
[37]DENG J L. Introduction to Grey System Theory [J]. The Journal of Grey System,1989,1(1):1-24.
[38]邓聚龙.灰理论基础[M].武汉：华中科技大学出版社,2002.
[39]李永祥,童恒超,杨建国.灰色系统理论在机床热误差测点优化中的应用[J].机械设计与研究,2006,22(3)：78-81.
[40]满维伟,夏新涛,陈龙,等.圆锥滚子轴承套圈参数与振动速度的灰关联分析[J].哈尔滨轴承,2006,27(2)：6-9.
[41]罗佑新.灰色关联分析法在机器设计方案选择中的应用[J].重型机械,1984,2：40-43.
[42]许洁,胡寿松.灰关联分析在歼击机操纵面故障识别中的应用[J].南京师范大学学报,2006,6(3)：5-9.
[43]张东方,陈东林.灰关联分析在人机系统可靠性评价中的应用[J].火力与指挥控制,2005,30：149-151.
[44]宋斌,于萍,罗运柏,等.基于灰关联熵的充油变压器故障诊断方法[J].电力系统自动化,2005,29(18)：76-79.
[45]刘长新,张运田.基于灰色GM(1,1)模型和灰关联的数据挖掘方法[J].长沙航空职业技术学院学报,2005,5(3)：60-62.
[46]李勇,邵诚,候晓星.一种新的灰关联分析算法——一致关联度[J].信息与控制,2006,35(4)：462-466.
[47]孙小军.试验数据间的关联度分析[J].红外技术,1994,16(3)：39-40.
[48]施法鹏,杜秀琦.灰色关联度分析及其在传染病上应用[J].工科数学,1994,10(4)：121-123.
[49]刘金英.灰色预测理论与评价方法在水环境中的应用研究[D],博士学位论文,长春：吉林大学,2004.
[50]井水淼.电火花微小孔加工控制方法及参数优化的研究[D].硕士学位论文,大连：大连理工大学,2008.
[51]PAWLAK Z. Theorize with Data using Rough Sets [A]. Proc of the 26th Annual International Computer Software and Applications Conference [C]. IEEE,2002,137-156.
[52]PAWLAK Z. Rough classification [J]. International Journal of Human-Computer Studies,1999,51: 369-383.
[53]PAWLAK Z, GRZYMALA-BUSSE J, SLAWINSKI R. Rough Sets [M]. Communication of the ACM,1995,38(11):89-95.
[54]张文修,吴伟志.粗糙集理论介绍和研究综述[J].模糊系统与数学,2000,14(4)：1-12.
[55]GENG Z Q, ZHU Q X. Rough set-based heuristic hybrid recognizer and its application in fault diagnosis [J]. Expert System with Application,2009,36:2711-2788.
[56]QUESTIER F, ROLLIER I A, WALCZAK B, et al. Application of rough set theory to feature selection for unsupervised clustering [J]. Chemometrics and Intelligent Laboratory Systems,2002, 63(2):155-167.
[57]SWINIARSKI R W, SKOWRON A. Rough set methods in feature selection and recognition [J]. Pattern Recognition Letters,2003,24(6):833-849.
[58]THANGAVER K, PETHALAKSHMI A. Performance analysis of accelerated quickreduct algorithm [J]. Proceedings of International Conference on Computational Intelligence and Multimedia Applications,2007,2:318-322.
[59]杨帆.粗糙集约简算法及其应用的研究[D].硕士学位论文,武汉：武汉科技大学,2005.
[60]杜晓,刘维亭,杜茜,等.基于粗糙集理论与灰色理论的属性约简算法[J].计算机技术与发展,2008,18(1)：154-156.
[61]尹宗成.运用粗糙集理论对我国粮食产量的预测[J].决策参考,2008,6：46-48.
[62]张雪峰,石凡,郝丽娜,张庆灵.粗糙集数据分析系统的程序实现[J].辽宁石油化工大学学报,2004,24(3)：66-69.
[63]张雪峰,张庆灵.粗糙集数据分析系统MATLAB仿真工具箱设计[J].东北大学学报,2007,28(1)：40-43.
[64]张冬玲.基于粗糙集理论的属性约简算法的实现[J].计算机应用,2006,26：78-79.
[65]代广珍.基于粗糙集理论的属性约简算法研究和设计[D].硕士学位论文,合肥：安徽大学,2007.
[66]HOPFIELD J J. Neural network and physical systems with emergent collective computational abilities [J]. Proc. Natl. Acad. Sci. USA,1982,79(8):2554-2558.
[67]RUMELHART D E, MCCIELLAND. Parallel Distributed Processing [M]. Cambridge:MIT Press, 1986.
[68]LUO X B, YIN G F, CHEN K, et al. Fuzzy neural network for machine parts recognition system [J]. Chinese Journal of Mechanical Engineering,2003,16(3):334-336.
[69]ZHANG D L, CHEN Y P, AI W, et al. Force ripple suppression technology for linear motors based on back propagation neural network [J]. Chinese Journal of Mechanical Engineering,2008,21(2): 13-16.
[70]李方方,赵英凯,张兴华.自适应递阶遗传算法优化BP网络的程序设计[J].计算机仿真,2007,24(8)：159-162.
[71]鹿文鹏,刘巍,孟祥增.利用Matlab神经网络工具箱在VC++中进行形状识别[J].计算机时代,2004.4：43-44.
[72]李永强,刘杰,侯祥林,等.人工神经网络的混合算法及其工程应用[J].机械工程学报,2004,40(1)：127-130.
[73]MIZE C D, ZIEGERT J C. Neural network thermal error compensation of a machining center [J]. Precision Engineering,2000,24(4),338-346.
[74]HAKEEM M A, KAMIL M, ARMAN I. Prediction of temperature profiles using artificial neural networks in a vertical thermosiphon reboiler [J]. Applied Thermal Engineering.2008,28: 1572-1579.
[75]SRINIVASAN D, SHARMA V, TOH K A. Reduced multivariate polynomial-based neural network for automated traffic incident detection [J]. Neural Networks,2008,21:484-492.
[76]冯冬青,李玮.基于灰关联理论和神经网络的价值预测方法[J].计算机工程与应用,2006,28：221-224.
[77]严修红,许伦辉.基于神经网络实现的改进灰色组合预测及应用[J].交通与计算机,2006,133(24)：9-12.
[78]毕小龙,袁勇.基于BP神经网络的人口预测方法研究[J].武汉理工大学学报,2007,31(3)：556-558.
[79]薛隆泉,徐国宁,刘荣昌,等.基于神经网络的曲轴残余应力预测[J].铸造技术,2007,28(5)：686-689.
[80]刘国良,张宏涛,曹洪涛,等.神经网络理论在数控机床热误差建模中的应用[J].现代制造工程,2005,8：20-23.
[81]陈水利,李敬功,王向公.模糊集理论及其应用[M].北京：科学出版社,2005.
[82]BATENI S M, JENG D S. Estimation of pile group scour using adaptive neuro-fuzzy approach [J]. Ocean Engineering,2007,34(8-9):1344-1354.
[83]BATENI S M, BORGHEI S M, JENG D S. Neural network and neuro-fuzzy assessments for scour depth around bridge piers [J]. Engineering Applications of Artificial Intelligence,2007,20(3): 401-414.
[84]HUANG M J, TSOUT Y L, LEE S C. Integrating fuzzy data mining and fuzzy artificial neural networks for discovering implicit knowledge [J]. Knowledge-Based Systems,2006,19(6):396-403.
[85]HUANG M L, CHEN H Y, HUANG J J. Glaucoma detection using adaptive neuro-fuzzy inference system [J]. Expert Systems with Applications,2007,32(2):458-468.
[86]POLAT K, GUNES S. A hybrid medical decision making system based on principles component analysis, k-NN based weighted preprocessing and adaptive neuro-fuzzy inference system [J]. Digital Signal Processing,2006,16(6):913-921.
[87]POLAT K, GUNES S. An expert system approach based on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease [J]. Digital Signal Processing, 2007,17(4):702-710.
[88]TUNG W L, QUEK C. A generic self-organizing fuzzy neural network [J]. IEEE Transactions on Neural Network,2002,13(5):1075-1086.
[89]MAGUIRE L P, ROCHE B, MCGINNITY T M, et al. Predicting a chaotic time series using a fuzzy neural network [J]. Information Sciences,1998(1),112:125-136.
[90]HAN M, SUN Y N, FAN Y N. An improved fuzzy neural network based on T-S mode [J]. Expert Systems with Applications,2008,34(4):2905-2920.
[91]YING L C, PAN M C. Using adaptive network based fuzzy inference system to forecast regional electricity loads [J]. Energy Conversion and Management,2008,49(2):205-211.
[92]AY ATA T, CAM E, YILDIZ O. Adaptive neuro-fuzzy inference systems (ANFIS) application to investigate potential use of natural ventilation in new building designs in Turkey [J]. Energy Conversion and Management,2007,48:1472-1479.
[93]WANG W. An adaptive predictor for dynamic system forecasting [J]. Mechanical Systems and Signal Processing,2007,21:809-823.
[94]LEE W K, HYUN C H, LEE H, et al. Model reference adaptive synchronization of T-S fuzzy discrete chaotic systems using output tracking control [J]. Chaos, Solitons and Fractals,2007,34: 1590-1598.
[95]KORBICZ J, KOWAL M. Neuro-fuzzy networks and their application to fault detection of dynamical systems [J]. Engineering Applications of Artificial Intelligence,2007,20:609-617.
[96]OZGER M, SEN Z. Prediction of wave parameters by using fuzzy logic approach [J]. Ocean Engineering,2007,34:460-469.
[97]FIRAT M, GUNGOR M. River flow estimation using adaptive neuro fuzzy inference system [J]. Mathematics and Computers in Simulation,2007,75:87-96.
[98]VAPNIK, V N. The nature of statistical learning theory [M]. New York:Springer-Verlag,2005.
[99]STANISLAW O, KONRAD G. Forecasting of the daily meteorological pollution using wavelets and support vector machine [J]. Engineering Applications of Artificial Intelligence,2007,20: 745-755.
[100]MULLER K R, SMOLA A J, RATSCH G, et al. Predicting time series with support vector machines [J]. In:Proceedings of the 7th International Conference on Artificial Neural Networks (ICANN), Lausanne, Switzerland,1997, vol.1327 of Lecture Notes in Computer Science. pp: 999-1004.
[101]安金龙.支持向量机若干问题的研究[D].博士学位论文,天津：天津大学,2004.
[102]卢虎,李彦,肖颖.支持向量机理论及其应用[J].空军工程大学学报,2003,4(4)：89-91.
[103]马云潜,张学工.支持向量机函数拟合在分形插值中的应用[J].清华大学学报,2000,40(3)：76-78.
[104]孙德山.支持向量机分类与回归方法研究[D].博士学位论文,长沙：中南大学,2004.
[105]田英杰.支持向量回归机及其应用研究[D].博士学位论文,北京：中国农业大学,2005.
[106]孟媛媛.模糊支持向量机的研究与应用[D].硕士学位论文,济南：山东师范大学,2006.
[107]往国碰.基于支持向量机的系统建模方法研究[D].硕士学位论文,保定：华北电力大学,2004.
[108]杨明,张凤鸣,张宣.粗糙集理论的支持向量机建模研究及应用[J].火力与指挥控制,2008,33：50-51.
[109]姜德民,王磊,徐义田,袁冬梅.基于粗糙集理论与支持向量回归的预测模型[J].理论新探,2008,10：32-33.
[110]HESHMATY B, KANDEL A. Fuzzy linear regression and its applications to forecasting in uncertain environment [J]. Fuzzy Sets and Systems,1985,15:159-191.
[111]KANEYOSHI M, TANAKA H, KAMEI M, et al. New system identification technique using fuzzy regression analysis [J]. In:International Symposium on Uncertainty Modeling and Analysis, College Park, MD, USA,1990, pp.528-533.
[112]KWON K, ISHIBUCHI H, TANAKA H. Neural networks with interval weights for nonlinear mapping of interval vector [J]. IEICE Transactions on Information Systems,1994,77:409-417.
[113]JENG J T, CHUANG C C, SU S F. Support vector interval regression networks for interval regression analysis [J]. Fuzzy Sets and Systems,2003,138:283-300.
[114]CHUANG C C. Extended support vector interval regression networks for interval input-output data [J]. Information Sciences,2008,178:871-891.
[115]姜波.灰色系统与神经网络分析方法及其应用研究[D].博士学位论文,武汉：华中科技大学,2004.
[116]PAWLAK Z. Rough sets[J]. International Journal of Computer and Information Science,1982, 11(5):341-356.
[117]PAWLAK Z. Rough sets-theoretical aspects of reasoning about data [M]. Norwell:Kluwer Academic Publisher,1991:1-5.
[118]武志峰,陈冬霞.基于粗糙集方法的知识发现[J].河北省科学院学报,2006,23(4)：56-60.
[119]李蔚,盛德仁,陈坚红,等.双重BP神经网络组合模型在实时数据预测中的应用[J].中国电机工程学报,2007,27(17)：94-97.
[120]张志明,程惠涛,徐鸿.神经网络组合预报模型及其在汽轮发电机组状态检修中的应用[J].中国电机工程学报,2003,23(9)：204-206.
[121]CHERKASSKY V, MULIER F. Learning from Data:Concepts, Theory and Methods [J]. NY: JohnViley&Sons,1997.
[122]谭东宁,谭东汉.小样本机器学习理论：统计学习理论[J].南京理工大学学报,2001,25(1)：108-112.
[123]张学工.关于统计学习理论与支持向量机[J].北京：自动化学报,2000,26(1)：32-42.
[124]张学工译.统计学习理论的本质[M].北京：清华大学出版社,2000.
[125]乔弘,周黎辉,潘卫华,等.基于参数自适应SVR的火电厂热工参数软测量[J].华北电力大学学报,2008,35(2)：94-97.
[126]王凡.基于支持向量机的交通流预测方法研究[D].博士学位论文,大连：大连理工大学,2010.
[127]DURIC, P M. Model selection by cross-validation [J]. In Proceedings of the 1990 IEEE International Symposium on Circuits and Systems,1990, pp:2760-2763.
[128]张志涌MATLAB6.5[M]北京：北京航空航天大学出版社,2002.
[129]陈杰MATLAB宝典[M].北京：电子工业出版社,2007.
[130]David J. Kraglinski. Visual C++技术内幕[M].北京：清华大学出版社,2000.
[131]许雪开.VC++与MATLAB混合编程[J].机电工程,2007,24(2)：26-27.
[132]翟军红,王红宣.基于VC与MATLAB混合编程的研究[J].微计算机信息,2007,23(11)：226-227.
[133]彭博栋,魏福利.VC6.0与MATLAB7.X混合编程方法研究[J].计算机与数字工程,2008,36(9)：174-178.
[134]卢晓红,贾振元,麻硕士,装喜春.虚拟数字信号处理仪的研究与开发[J].计算机仿真,2007,24(3)：240-245.
[135]孙昆峰MATLAB和数据库的连接[J].电脑开发与应用,2001,4：10.
[136]侯春生MATLAB/VB/SQL Server组合编程[J].计算机时代,2002,1：31-33.
[137]李明旭,曹家兴,李仲麟MATLAB/VC/SQL SERVER编程在模糊综合评价中的应用[J].广西工学院学报,2007,18(2)：95-99.
[2]王春行.液压控制系统[M].北京：机械工业出版社,1999.
[3]肖凯鸣,虞勤俭,王渝,等.MK电液伺服阀结构原理及性能[J].液压气动与密封,1998,4：33-36.
[4]ICHIRYU K, WATANABE H, Yamaguchi T. Direct-acting servo valve. US Patent:US4544129, 1985.
[5]MARCO D A. Linear-force motors enhance proportional valves [J]. Hydraulics & Pneumatics,1998, 4:14-16.
[6]朱盘生MOOG(穆格)DDV伺服阀[J].液压与气动.1996,5：20-21.
[7]HOCKADAY B D. Direct optical actuation for hydraulic systems [J]. Lasers and Electro-Optics Society Annual Meeting,1993,1:143-144.
[8]王新华,孙树文,李剑锋,等.水压伺服控制技术发展的现状及应用前景[J].机床与液压,2008,36(5)：177-180.
[9]阮健,李胜,杨继隆.液压及气动阀直接数字控制的新途径[J].中国机械工程,2000,11(3)：317-320.
[10]张光琼.单级转轴式旋转电液伺服阀[J].机床与液压,1991,2：34-38.
[11]卢菊仙,李树立,焦宗夏.一种有限角度旋转式电液伺服阀[J].液压气动与密封,2005,4：155-157.
[12]付永领,裴忠才,王占林.伺服作动系统的余度控制[J].北京航空航天大学学报,1999,25(5)：531-534.
[13]陈鹏.智能化全自动电液伺服阀配磨系统[J].仪表技术与传感器,1996,2：45-47.
[14]浙人,编译.加工精密伺服阀的自动化“流量磨削”系统[J].世界制造技术与装备市场,1994,4：70.
[15]孙谦.矩形节流窗口的电液伺服阀阀套及其加工[J].1982,2：29-32.
[16]王传礼.基于GMM转换器喷嘴挡板伺服阀的研究[D].硕士学位论文,杭州：浙江大学,2005.
[17]沈传亮,程光明,曾平,等.压电驱动式高频电液伺服阀实验研究[J].哈尔滨工业大学学报,2008,40(9)：1443-1446.
[18]米智楠,钱晋武,龚振邦,李旻,智计龙.形状记忆合金微型阀的研制[J].机床与液压,2001,1：20-21.
[19]盛晓伟.添加磁流体的射流管伺服阀动态性能研究[D].硕士学位论文,哈尔滨：哈尔滨工业大学,2006.
[20]覃爱明.电流变伺服阀的特性研究[J].湘潭大学学报,1998,12：88-90.
[21]佟文王.电液流量伺服阀的发展方向[J].液压与气动,1996,6：3-6.
[22]张坤发.电液伺服阀动静态性能计算机辅助测试系统的研究[D].硕士学位论文,哈尔滨：哈尔滨工业大学,2006.
[23]袁宏杰,李传日,姚金勇.通用电液伺服阀自动测试系统研制[J].机床与液压,2009,37(1)：105-106.
[24]王宣银,孙赫,李潇潇,李福尚.电液伺服阀动静特性一体化自动测试系统研制[J].机床与液压,2010,38(20)：37-38.
[25]许益民.电液伺服阀频率特性测试系统误差分析[J].武汉科技大学学报,2005,28(4)：346-348.
[26]易建钢,湛从昌,吴琼进.电液伺服阀动态特性测试中复合数字滤波算法研究[J].液压与气动,2004,2：15-17.
[27]魏鹏,王占林,裘丽华.基于液压伺服阀动态特性测试的改进型逆重复伪随机算法[J].机床与液压,2005,2：99-101.
[28]刘建.电液伺服阀静动态综合特性计算机辅助测试系统的研发[D].硕士学位论文,秦皇岛：燕山大学,2004.
[29]师占群,王建民,岳宏,刘庆和.基于小波故障提取的电液伺服阀故障诊断[J].机械科学与技术,2000,19：111-112.
[30]陈新元,黄富,陈灿军,吴海峰,曾良才.基于BP神经网络电液伺服阀多参数故障模式识别研究[J].机床与液压,2004,6：179-181.
[31]胡生清,幸国全.未来的仪器仪表一虚拟仪器[J].自动化与仪表,1999,14(6)：15-17.
[32]王益群,王燕山,姜万录.基于虚拟仪器的电液伺服阀静动态特性测试[J].液压气动与密封,2001,1：13-15.
[33]宋涛.基于虚拟一起的电液伺服阀性能测试实验台系统研究[D].硕士学位论文,沈阳：东北大学,2006.
[34]龚树强.基于CAN总线的电液伺服阀静态性能测试系统的研究[D].硕士学位论文,哈尔滨：哈尔滨工业大学,2007.
[35]黄伟.基于虚拟仪器的电液伺服阀静态特性测试[D].硕士学位论文,武汉：武汉科技大学,2008.
[36]张正甫.基于虚拟仪器的电液伺服阀测试系统研究[D].硕士学位论文,广州：广东工业大学,2004.
[37]DENG J L. Introduction to Grey System Theory [J]. The Journal of Grey System,1989,1(1):1-24.
[38]邓聚龙.灰理论基础[M].武汉：华中科技大学出版社,2002.
[39]李永祥,童恒超,杨建国.灰色系统理论在机床热误差测点优化中的应用[J].机械设计与研究,2006,22(3)：78-81.
[40]满维伟,夏新涛,陈龙,等.圆锥滚子轴承套圈参数与振动速度的灰关联分析[J].哈尔滨轴承,2006,27(2)：6-9.
[41]罗佑新.灰色关联分析法在机器设计方案选择中的应用[J].重型机械,1984,2：40-43.
[42]许洁,胡寿松.灰关联分析在歼击机操纵面故障识别中的应用[J].南京师范大学学报,2006,6(3)：5-9.
[43]张东方,陈东林.灰关联分析在人机系统可靠性评价中的应用[J].火力与指挥控制,2005,30：149-151.
[44]宋斌,于萍,罗运柏,等.基于灰关联熵的充油变压器故障诊断方法[J].电力系统自动化,2005,29(18)：76-79.
[45]刘长新,张运田.基于灰色GM(1,1)模型和灰关联的数据挖掘方法[J].长沙航空职业技术学院学报,2005,5(3)：60-62.
[46]李勇,邵诚,候晓星.一种新的灰关联分析算法——一致关联度[J].信息与控制,2006,35(4)：462-466.
[47]孙小军.试验数据间的关联度分析[J].红外技术,1994,16(3)：39-40.
[48]施法鹏,杜秀琦.灰色关联度分析及其在传染病上应用[J].工科数学,1994,10(4)：121-123.
[49]刘金英.灰色预测理论与评价方法在水环境中的应用研究[D],博士学位论文,长春：吉林大学,2004.
[50]井水淼.电火花微小孔加工控制方法及参数优化的研究[D].硕士学位论文,大连：大连理工大学,2008.
[51]PAWLAK Z. Theorize with Data using Rough Sets [A]. Proc of the 26th Annual International Computer Software and Applications Conference [C]. IEEE,2002,137-156.
[52]PAWLAK Z. Rough classification [J]. International Journal of Human-Computer Studies,1999,51: 369-383.
[53]PAWLAK Z, GRZYMALA-BUSSE J, SLAWINSKI R. Rough Sets [M]. Communication of the ACM,1995,38(11):89-95.
[54]张文修,吴伟志.粗糙集理论介绍和研究综述[J].模糊系统与数学,2000,14(4)：1-12.
[55]GENG Z Q, ZHU Q X. Rough set-based heuristic hybrid recognizer and its application in fault diagnosis [J]. Expert System with Application,2009,36:2711-2788.
[56]QUESTIER F, ROLLIER I A, WALCZAK B, et al. Application of rough set theory to feature selection for unsupervised clustering [J]. Chemometrics and Intelligent Laboratory Systems,2002, 63(2):155-167.
[57]SWINIARSKI R W, SKOWRON A. Rough set methods in feature selection and recognition [J]. Pattern Recognition Letters,2003,24(6):833-849.
[58]THANGAVER K, PETHALAKSHMI A. Performance analysis of accelerated quickreduct algorithm [J]. Proceedings of International Conference on Computational Intelligence and Multimedia Applications,2007,2:318-322.
[59]杨帆.粗糙集约简算法及其应用的研究[D].硕士学位论文,武汉：武汉科技大学,2005.
[60]杜晓,刘维亭,杜茜,等.基于粗糙集理论与灰色理论的属性约简算法[J].计算机技术与发展,2008,18(1)：154-156.
[61]尹宗成.运用粗糙集理论对我国粮食产量的预测[J].决策参考,2008,6：46-48.
[62]张雪峰,石凡,郝丽娜,张庆灵.粗糙集数据分析系统的程序实现[J].辽宁石油化工大学学报,2004,24(3)：66-69.
[63]张雪峰,张庆灵.粗糙集数据分析系统MATLAB仿真工具箱设计[J].东北大学学报,2007,28(1)：40-43.
[64]张冬玲.基于粗糙集理论的属性约简算法的实现[J].计算机应用,2006,26：78-79.
[65]代广珍.基于粗糙集理论的属性约简算法研究和设计[D].硕士学位论文,合肥：安徽大学,2007.
[66]HOPFIELD J J. Neural network and physical systems with emergent collective computational abilities [J]. Proc. Natl. Acad. Sci. USA,1982,79(8):2554-2558.
[67]RUMELHART D E, MCCIELLAND. Parallel Distributed Processing [M]. Cambridge:MIT Press, 1986.
[68]LUO X B, YIN G F, CHEN K, et al. Fuzzy neural network for machine parts recognition system [J]. Chinese Journal of Mechanical Engineering,2003,16(3):334-336.
[69]ZHANG D L, CHEN Y P, AI W, et al. Force ripple suppression technology for linear motors based on back propagation neural network [J]. Chinese Journal of Mechanical Engineering,2008,21(2): 13-16.
[70]李方方,赵英凯,张兴华.自适应递阶遗传算法优化BP网络的程序设计[J].计算机仿真,2007,24(8)：159-162.
[71]鹿文鹏,刘巍,孟祥增.利用Matlab神经网络工具箱在VC++中进行形状识别[J].计算机时代,2004.4：43-44.
[72]李永强,刘杰,侯祥林,等.人工神经网络的混合算法及其工程应用[J].机械工程学报,2004,40(1)：127-130.
[73]MIZE C D, ZIEGERT J C. Neural network thermal error compensation of a machining center [J]. Precision Engineering,2000,24(4),338-346.
[74]HAKEEM M A, KAMIL M, ARMAN I. Prediction of temperature profiles using artificial neural networks in a vertical thermosiphon reboiler [J]. Applied Thermal Engineering.2008,28: 1572-1579.
[75]SRINIVASAN D, SHARMA V, TOH K A. Reduced multivariate polynomial-based neural network for automated traffic incident detection [J]. Neural Networks,2008,21:484-492.
[76]冯冬青,李玮.基于灰关联理论和神经网络的价值预测方法[J].计算机工程与应用,2006,28：221-224.
[77]严修红,许伦辉.基于神经网络实现的改进灰色组合预测及应用[J].交通与计算机,2006,133(24)：9-12.
[78]毕小龙,袁勇.基于BP神经网络的人口预测方法研究[J].武汉理工大学学报,2007,31(3)：556-558.
[79]薛隆泉,徐国宁,刘荣昌,等.基于神经网络的曲轴残余应力预测[J].铸造技术,2007,28(5)：686-689.
[80]刘国良,张宏涛,曹洪涛,等.神经网络理论在数控机床热误差建模中的应用[J].现代制造工程,2005,8：20-23.
[81]陈水利,李敬功,王向公.模糊集理论及其应用[M].北京：科学出版社,2005.
[82]BATENI S M, JENG D S. Estimation of pile group scour using adaptive neuro-fuzzy approach [J]. Ocean Engineering,2007,34(8-9):1344-1354.
[83]BATENI S M, BORGHEI S M, JENG D S. Neural network and neuro-fuzzy assessments for scour depth around bridge piers [J]. Engineering Applications of Artificial Intelligence,2007,20(3): 401-414.
[84]HUANG M J, TSOUT Y L, LEE S C. Integrating fuzzy data mining and fuzzy artificial neural networks for discovering implicit knowledge [J]. Knowledge-Based Systems,2006,19(6):396-403.
[85]HUANG M L, CHEN H Y, HUANG J J. Glaucoma detection using adaptive neuro-fuzzy inference system [J]. Expert Systems with Applications,2007,32(2):458-468.
[86]POLAT K, GUNES S. A hybrid medical decision making system based on principles component analysis, k-NN based weighted preprocessing and adaptive neuro-fuzzy inference system [J]. Digital Signal Processing,2006,16(6):913-921.
[87]POLAT K, GUNES S. An expert system approach based on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease [J]. Digital Signal Processing, 2007,17(4):702-710.
[88]TUNG W L, QUEK C. A generic self-organizing fuzzy neural network [J]. IEEE Transactions on Neural Network,2002,13(5):1075-1086.
[89]MAGUIRE L P, ROCHE B, MCGINNITY T M, et al. Predicting a chaotic time series using a fuzzy neural network [J]. Information Sciences,1998(1),112:125-136.
[90]HAN M, SUN Y N, FAN Y N. An improved fuzzy neural network based on T-S mode [J]. Expert Systems with Applications,2008,34(4):2905-2920.
[91]YING L C, PAN M C. Using adaptive network based fuzzy inference system to forecast regional electricity loads [J]. Energy Conversion and Management,2008,49(2):205-211.
[92]AY ATA T, CAM E, YILDIZ O. Adaptive neuro-fuzzy inference systems (ANFIS) application to investigate potential use of natural ventilation in new building designs in Turkey [J]. Energy Conversion and Management,2007,48:1472-1479.
[93]WANG W. An adaptive predictor for dynamic system forecasting [J]. Mechanical Systems and Signal Processing,2007,21:809-823.
[94]LEE W K, HYUN C H, LEE H, et al. Model reference adaptive synchronization of T-S fuzzy discrete chaotic systems using output tracking control [J]. Chaos, Solitons and Fractals,2007,34: 1590-1598.
[95]KORBICZ J, KOWAL M. Neuro-fuzzy networks and their application to fault detection of dynamical systems [J]. Engineering Applications of Artificial Intelligence,2007,20:609-617.
[96]OZGER M, SEN Z. Prediction of wave parameters by using fuzzy logic approach [J]. Ocean Engineering,2007,34:460-469.
[97]FIRAT M, GUNGOR M. River flow estimation using adaptive neuro fuzzy inference system [J]. Mathematics and Computers in Simulation,2007,75:87-96.
[98]VAPNIK, V N. The nature of statistical learning theory [M]. New York:Springer-Verlag,2005.
[99]STANISLAW O, KONRAD G. Forecasting of the daily meteorological pollution using wavelets and support vector machine [J]. Engineering Applications of Artificial Intelligence,2007,20: 745-755.
[100]MULLER K R, SMOLA A J, RATSCH G, et al. Predicting time series with support vector machines [J]. In:Proceedings of the 7th International Conference on Artificial Neural Networks (ICANN), Lausanne, Switzerland,1997, vol.1327 of Lecture Notes in Computer Science. pp: 999-1004.
[101]安金龙.支持向量机若干问题的研究[D].博士学位论文,天津：天津大学,2004.
[102]卢虎,李彦,肖颖.支持向量机理论及其应用[J].空军工程大学学报,2003,4(4)：89-91.
[103]马云潜,张学工.支持向量机函数拟合在分形插值中的应用[J].清华大学学报,2000,40(3)：76-78.
[104]孙德山.支持向量机分类与回归方法研究[D].博士学位论文,长沙：中南大学,2004.
[105]田英杰.支持向量回归机及其应用研究[D].博士学位论文,北京：中国农业大学,2005.
[106]孟媛媛.模糊支持向量机的研究与应用[D].硕士学位论文,济南：山东师范大学,2006.
[107]往国碰.基于支持向量机的系统建模方法研究[D].硕士学位论文,保定：华北电力大学,2004.
[108]杨明,张凤鸣,张宣.粗糙集理论的支持向量机建模研究及应用[J].火力与指挥控制,2008,33：50-51.
[109]姜德民,王磊,徐义田,袁冬梅.基于粗糙集理论与支持向量回归的预测模型[J].理论新探,2008,10：32-33.
[110]HESHMATY B, KANDEL A. Fuzzy linear regression and its applications to forecasting in uncertain environment [J]. Fuzzy Sets and Systems,1985,15:159-191.
[111]KANEYOSHI M, TANAKA H, KAMEI M, et al. New system identification technique using fuzzy regression analysis [J]. In:International Symposium on Uncertainty Modeling and Analysis, College Park, MD, USA,1990, pp.528-533.
[112]KWON K, ISHIBUCHI H, TANAKA H. Neural networks with interval weights for nonlinear mapping of interval vector [J]. IEICE Transactions on Information Systems,1994,77:409-417.
[113]JENG J T, CHUANG C C, SU S F. Support vector interval regression networks for interval regression analysis [J]. Fuzzy Sets and Systems,2003,138:283-300.
[114]CHUANG C C. Extended support vector interval regression networks for interval input-output data [J]. Information Sciences,2008,178:871-891.
[115]姜波.灰色系统与神经网络分析方法及其应用研究[D].博士学位论文,武汉：华中科技大学,2004.
[116]PAWLAK Z. Rough sets[J]. International Journal of Computer and Information Science,1982, 11(5):341-356.
[117]PAWLAK Z. Rough sets-theoretical aspects of reasoning about data [M]. Norwell:Kluwer Academic Publisher,1991:1-5.
[118]武志峰,陈冬霞.基于粗糙集方法的知识发现[J].河北省科学院学报,2006,23(4)：56-60.
[119]李蔚,盛德仁,陈坚红,等.双重BP神经网络组合模型在实时数据预测中的应用[J].中国电机工程学报,2007,27(17)：94-97.
[120]张志明,程惠涛,徐鸿.神经网络组合预报模型及其在汽轮发电机组状态检修中的应用[J].中国电机工程学报,2003,23(9)：204-206.
[121]CHERKASSKY V, MULIER F. Learning from Data:Concepts, Theory and Methods [J]. NY: JohnViley&Sons,1997.
[122]谭东宁,谭东汉.小样本机器学习理论：统计学习理论[J].南京理工大学学报,2001,25(1)：108-112.
[123]张学工.关于统计学习理论与支持向量机[J].北京：自动化学报,2000,26(1)：32-42.
[124]张学工译.统计学习理论的本质[M].北京：清华大学出版社,2000.
[125]乔弘,周黎辉,潘卫华,等.基于参数自适应SVR的火电厂热工参数软测量[J].华北电力大学学报,2008,35(2)：94-97.
[126]王凡.基于支持向量机的交通流预测方法研究[D].博士学位论文,大连：大连理工大学,2010.
[127]DURIC, P M. Model selection by cross-validation [J]. In Proceedings of the 1990 IEEE International Symposium on Circuits and Systems,1990, pp:2760-2763.
[128]张志涌MATLAB6.5[M]北京：北京航空航天大学出版社,2002.
[129]陈杰MATLAB宝典[M].北京：电子工业出版社,2007.
[130]David J. Kraglinski. Visual C++技术内幕[M].北京：清华大学出版社,2000.
[131]许雪开.VC++与MATLAB混合编程[J].机电工程,2007,24(2)：26-27.
[132]翟军红,王红宣.基于VC与MATLAB混合编程的研究[J].微计算机信息,2007,23(11)：226-227.
[133]彭博栋,魏福利.VC6.0与MATLAB7.X混合编程方法研究[J].计算机与数字工程,2008,36(9)：174-178.
[134]卢晓红,贾振元,麻硕士,装喜春.虚拟数字信号处理仪的研究与开发[J].计算机仿真,2007,24(3)：240-245.
[135]孙昆峰MATLAB和数据库的连接[J].电脑开发与应用,2001,4：10.
[136]侯春生MATLAB/VB/SQL Server组合编程[J].计算机时代,2002,1：31-33.
[137]李明旭,曹家兴,李仲麟MATLAB/VC/SQL SERVER编程在模糊综合评价中的应用[J].广西工学院学报,2007,18(2)：95-99.