基于冶炼过程及终点判断技术的烟化炉智能控制系统研究
|
摘要
烟化炉在我国已具有六十多年历史,至今仍应用于铅、锌、锡冶炼过程,以处理其炉渣及低品位氧化精矿。烟化炉的生产过程,多年来依靠操作工积累的经验,即操作工通过观察烟化炉三次风口火焰,凭经验判断烟化炉炉冶炼是否处于结束(即终点)、强挥发、弱挥发,再进行相应的操作。加之生产过程非常复杂、影响因素甚多,现场环境恶劣及检测水平的限制,迄今为止,烟化炉生产尚未实现自动化及标准化操作。
本文对烟化炉的发展现状、研究动态及工艺过程进行了深入的分析研究,并探讨了其热工过程及动力学过程。针对烟化炉燃烧冶炼过程滞后大、非线性、强耦合以及化学反应过程复杂、干扰因素多、难以建立数学模型等特点,提出一种模糊PID控制和专家控制相结合的策略,建立烟化炉燃烧过程的温度控制系统。既保证了较好的控制精度,又达到了快速升温和炉温的稳定,实现烟化炉作业期所需的温度。
然而仅靠炉温控制无法实现烟化炉冶炼过程控制。烟化炉目前仍为间隙式冶炼过程,每一炉的来料,工艺情况差异较大,难以形成固定的控制模式,通过多年来优秀烟化炉操作工丰富经验的总结,形成了对不同的炉况和不同环境条件下的“专家”吹炼经验曲线,将专家吹炼经验、炉温、给煤量、还原情况、吹炼时段相结合,研究设计了基于专家吹炼经验、冶炼过程图像识别、冶炼终点多信息融合判断的智能综合控制系统,实现烟化炉冶炼过程控制及标准化操作,使烟化炉冶炼过程处于较佳工作状态,使锌的挥发、废渣含锌量达到较佳值。
为了实现烟化炉冶炼过程智能综合控制及标准化操作,冶炼过程和冶炼终点的判断极为重要。通过对烟化炉三次风口火焰图象进行RGB处理、YUV处理、灰度直方图处理法、二值化图像处理、灰度共生矩阵处理等研究,发现烟化炉吹炼终点火焰特征与非终点火焰特征具有明显区别,这为烟化炉吹炼终点判断提供了新的方法和技术思路。
通过对烟化炉熟练风口操作工经验收集,以及三次风口冶炼过程火焰图像研究发现：烟化炉吹炼过程的各个阶段,其三次风口处火焰在形态、透明度、颜色上具有不同的特征。因此采用彩色数字摄像机对烟化炉三次风口处火焰图像进行采集,根据所采集的火焰图像的明亮度、颜色、形态,把其分为强挥发火焰、暗弱挥发火焰、亮黄火焰、暗红火焰、弱挥发火焰和亮白火焰六类。通过在RGB颜色空间、HIS彩色系统YUV色彩系统、下提取烟化炉三次风口火焰图像色度、亮度、面积和直方图等特征,采用神经元网络识别技术,分别对上述六类火焰的图像进行识别和分类。建立了烟化炉三次风口火焰图像特征与冶炼过程之间的映射关系。由于烟化炉冶炼过程中三次风口处火焰会出现跳跃和闪烁,因此根据单幅火焰的图像进行分累识别就判定其所处的冶炼过程是不科学的。为此,本文提出了根据烟化炉冶炼过程信息进行其冶炼终点判断,即根据连续拍摄的40秒内20幅三次风口处火焰图像分类结果,来判断当前烟化炉冶炼过程可能所处的冶炼阶段,再与前次判决结果进行综合,最终来判定烟化炉冶炼过程是否已到达“冶炼终点”、或是处于“还原挥发”或“温度偏底,需升温”。并开发了基于图像识别技术的烟化炉冶炼过程状态及终点判断软件系统。
烟化炉冶炼挥发通常分一次挥发,二次挥发或多次挥发,而每次挥发结束时三次风口火焰图像均与冶炼终点火焰图像相似,加之对冶炼终点影响因素多,要实现冶炼终点的准确判断,仅凭火焰图像识别判断冶炼终点必然有些不足。经过大量现场调研及现场大量历史数据分析研究,发现烟化炉的冶炼状态判别与加料量的多少、冶炼时间、给煤量、炉内的温度、三次风口火焰的特征等有直接关系,因此,提出采用多传感器数据融合的方法来实现冶炼终点的判断,将烟化炉在线检测系统采集的炉温、给煤量、冶炼时间、加料量和图像识别系统判断的结果进行融合。在D-S证据理论融合算法基础上,给出了烟化炉冶炼终点判断D-S证据理论融合算法、并将神经网络及参数模板法、图像识别终点判断结果进行综合判决,最终实现冶炼终点判断。提高了烟化炉冶炼终点判别的准确性,并开发了烟化炉冶炼终点判断多传感器信息融合软件系统。
论文所研究开发的基于冶炼过程及冶炼终点判断的烟化炉智能综合控制系统已在云南驰宏锌锗股份有限公司会泽铅厂烟化炉冶炼生产中进行了应用,取得了较大的经济效益和社会效益。
The fuming furnace is an equipment of extracting the metals of lead, zinc, tin and rare metals by deoxidizing-volatilization from the mine slag of smelting process. There are several decades'times of smelting practice using the fuming furnace in our country. And it is also widely used for processing low quality and difficult to beneficiate of tin and zinc oxide concentrate mine in nowadays. However, the current control way is determining by the operator's experience of observation on the flames from the tertiary air orifice of furnace through their naked eye. The judgments are gained, including furnace conditions suiting for deoxidizing-volatilization, volatilization processing, mine volatilization approach to finish, the end point of volatilization, so as to accomplish the smelting process. The process of fuming furnace is complexity, the correlative complication is multitudinous, the condition of smelting fieldwork is rigorous, the detection technology is restricted in thus instance. So far the automatic control system is not realization in the smelting process of fuming furnace.
The paper is proposed on the fuming furnace, research the actuality, the developments, and the last word of this domain. The working procedure and the pyrology principle of fuming furnace are also researched. The thesis aims at the object of lag-time, non-liner, chemism-complicated, interferential-complication, hard to modeling mathematical expression of fuming furnace combustion system, puts forward the control strategy of Fuzzy PID combination Experts System to realize the temperature control of combustion system. It ensures a better control precision and achieves a rapid heating and temperature stability, reaches the temperature requirements of operating period.
But only determining the temperature parameter, the automatic control system of fuming furnace is unable to achieve. The smelting process is discontinuous; the raw material in each period is not the same; the physical parameters conditions are different. It is hard to formed a certain control mode. By collecting the experience of the excellent operators from the fuming furnace fieldwork, the blown smelting curves for mult-conditions as experts are formed. Design the integrated intelligent control system combines with experts blown smelting experience, image recognize of smelting process, information fusion based on mult-sensors of End Point Judgment of smelting process. Realizes the smelting process control of fuming furnace, and make it work in a better state, the parameters of volatilization of Zinc and proportion of Zinc in residue are also in a better state.
To realize the integrated intelligent control of smelting process, it is necessary to realize the judgment of smelting end-point. There are distinct differences of characteristic parameters between the non-end point and end point by disposing the fume images with the RGB method, YUV method, gray histogram, binary bitmap theory and gray level co-occurrence matrix. It provides a new method and technological thought on the judgment of end point of smelting process.
Base on the above research and the collection of the operator's experiment on the fume images of the tertiary air orifice, it is easy to find the commonalities and differences through the colors, transparence luminance and morphology characteristic parameters. The system uses a color digital video camera for flame image collection, according to the different levels of colors, transparence luminance and morphology, the images are divided into volatilization, gloomy eruption, weak volatilization, weak red, bright yellow and white thorn. Then extracting the characteristic parameters of flame picture on area, luminance, chrominance and histogram as the input of the neural network, to realize the classifying and recognizing of the flame pictures. Based on the mapping relationship between flame images of tertiary air orifice and status of the smelting stages, the method of automatically determine of end point is formed, developed a system of automatic judgment of the end point of fuming furnace smelting processing. Taking into account the smelting process of flame flickering and jumping, the method of in accordance with the process information relation to the judgment of end point, general considerations for 20 seconds of 10 images classification results, to determine the current smelting process in which stages, then output with the previous judgments and statistical, finally the results is acquisition for whether in volatilization, calefactive phase or the end point of smelting.
There are once, twice or time after time smelting volatilization of fuming furnace, and every time the end volatilization picture is similar as the end point picture. To achieve the exact end point judgment of smelting processing, relying on single picture sensor information of single judgment is inadequate. Fuming furnace smelting process is complex, the dependents of those various on judgment of end point have non-linear relationship, should not set up precise mathematical relationship. After several times of field research, the fuming furnace's status identification have relationships with the number of cold material, smelting time, the volume of coal, furnace temperature and the characteristics of tertiary air orifice, so using multi-sensor data fusion approach to achieve the end smelting judgments. Using the fusion algorithm disposing the information of temperature, cold material, smelting time, the volume of coal which from the detection system, and the image recognizing system. Based on D-S evidence theory algorithm, integration the judgment of neural network, images recognize and template with parameters, the finally result of end point judgment of smelting process in fuming furnace is formed, also develops the software system of end point judgment of smelting process in fuming furnace.
The integrated intelligent control system of smelting process and the judge of smelting end-point system described in the paper have been applied in HUIZE lead smelting factory of YUNNAN CHIHONG ZINC&GERMANIUM Co., ltd, and have achieved greater economic and social benefits.
本文对烟化炉的发展现状、研究动态及工艺过程进行了深入的分析研究,并探讨了其热工过程及动力学过程。针对烟化炉燃烧冶炼过程滞后大、非线性、强耦合以及化学反应过程复杂、干扰因素多、难以建立数学模型等特点,提出一种模糊PID控制和专家控制相结合的策略,建立烟化炉燃烧过程的温度控制系统。既保证了较好的控制精度,又达到了快速升温和炉温的稳定,实现烟化炉作业期所需的温度。
然而仅靠炉温控制无法实现烟化炉冶炼过程控制。烟化炉目前仍为间隙式冶炼过程,每一炉的来料,工艺情况差异较大,难以形成固定的控制模式,通过多年来优秀烟化炉操作工丰富经验的总结,形成了对不同的炉况和不同环境条件下的“专家”吹炼经验曲线,将专家吹炼经验、炉温、给煤量、还原情况、吹炼时段相结合,研究设计了基于专家吹炼经验、冶炼过程图像识别、冶炼终点多信息融合判断的智能综合控制系统,实现烟化炉冶炼过程控制及标准化操作,使烟化炉冶炼过程处于较佳工作状态,使锌的挥发、废渣含锌量达到较佳值。
为了实现烟化炉冶炼过程智能综合控制及标准化操作,冶炼过程和冶炼终点的判断极为重要。通过对烟化炉三次风口火焰图象进行RGB处理、YUV处理、灰度直方图处理法、二值化图像处理、灰度共生矩阵处理等研究,发现烟化炉吹炼终点火焰特征与非终点火焰特征具有明显区别,这为烟化炉吹炼终点判断提供了新的方法和技术思路。
通过对烟化炉熟练风口操作工经验收集,以及三次风口冶炼过程火焰图像研究发现：烟化炉吹炼过程的各个阶段,其三次风口处火焰在形态、透明度、颜色上具有不同的特征。因此采用彩色数字摄像机对烟化炉三次风口处火焰图像进行采集,根据所采集的火焰图像的明亮度、颜色、形态,把其分为强挥发火焰、暗弱挥发火焰、亮黄火焰、暗红火焰、弱挥发火焰和亮白火焰六类。通过在RGB颜色空间、HIS彩色系统YUV色彩系统、下提取烟化炉三次风口火焰图像色度、亮度、面积和直方图等特征,采用神经元网络识别技术,分别对上述六类火焰的图像进行识别和分类。建立了烟化炉三次风口火焰图像特征与冶炼过程之间的映射关系。由于烟化炉冶炼过程中三次风口处火焰会出现跳跃和闪烁,因此根据单幅火焰的图像进行分累识别就判定其所处的冶炼过程是不科学的。为此,本文提出了根据烟化炉冶炼过程信息进行其冶炼终点判断,即根据连续拍摄的40秒内20幅三次风口处火焰图像分类结果,来判断当前烟化炉冶炼过程可能所处的冶炼阶段,再与前次判决结果进行综合,最终来判定烟化炉冶炼过程是否已到达“冶炼终点”、或是处于“还原挥发”或“温度偏底,需升温”。并开发了基于图像识别技术的烟化炉冶炼过程状态及终点判断软件系统。
烟化炉冶炼挥发通常分一次挥发,二次挥发或多次挥发,而每次挥发结束时三次风口火焰图像均与冶炼终点火焰图像相似,加之对冶炼终点影响因素多,要实现冶炼终点的准确判断,仅凭火焰图像识别判断冶炼终点必然有些不足。经过大量现场调研及现场大量历史数据分析研究,发现烟化炉的冶炼状态判别与加料量的多少、冶炼时间、给煤量、炉内的温度、三次风口火焰的特征等有直接关系,因此,提出采用多传感器数据融合的方法来实现冶炼终点的判断,将烟化炉在线检测系统采集的炉温、给煤量、冶炼时间、加料量和图像识别系统判断的结果进行融合。在D-S证据理论融合算法基础上,给出了烟化炉冶炼终点判断D-S证据理论融合算法、并将神经网络及参数模板法、图像识别终点判断结果进行综合判决,最终实现冶炼终点判断。提高了烟化炉冶炼终点判别的准确性,并开发了烟化炉冶炼终点判断多传感器信息融合软件系统。
论文所研究开发的基于冶炼过程及冶炼终点判断的烟化炉智能综合控制系统已在云南驰宏锌锗股份有限公司会泽铅厂烟化炉冶炼生产中进行了应用,取得了较大的经济效益和社会效益。
The fuming furnace is an equipment of extracting the metals of lead, zinc, tin and rare metals by deoxidizing-volatilization from the mine slag of smelting process. There are several decades'times of smelting practice using the fuming furnace in our country. And it is also widely used for processing low quality and difficult to beneficiate of tin and zinc oxide concentrate mine in nowadays. However, the current control way is determining by the operator's experience of observation on the flames from the tertiary air orifice of furnace through their naked eye. The judgments are gained, including furnace conditions suiting for deoxidizing-volatilization, volatilization processing, mine volatilization approach to finish, the end point of volatilization, so as to accomplish the smelting process. The process of fuming furnace is complexity, the correlative complication is multitudinous, the condition of smelting fieldwork is rigorous, the detection technology is restricted in thus instance. So far the automatic control system is not realization in the smelting process of fuming furnace.
The paper is proposed on the fuming furnace, research the actuality, the developments, and the last word of this domain. The working procedure and the pyrology principle of fuming furnace are also researched. The thesis aims at the object of lag-time, non-liner, chemism-complicated, interferential-complication, hard to modeling mathematical expression of fuming furnace combustion system, puts forward the control strategy of Fuzzy PID combination Experts System to realize the temperature control of combustion system. It ensures a better control precision and achieves a rapid heating and temperature stability, reaches the temperature requirements of operating period.
But only determining the temperature parameter, the automatic control system of fuming furnace is unable to achieve. The smelting process is discontinuous; the raw material in each period is not the same; the physical parameters conditions are different. It is hard to formed a certain control mode. By collecting the experience of the excellent operators from the fuming furnace fieldwork, the blown smelting curves for mult-conditions as experts are formed. Design the integrated intelligent control system combines with experts blown smelting experience, image recognize of smelting process, information fusion based on mult-sensors of End Point Judgment of smelting process. Realizes the smelting process control of fuming furnace, and make it work in a better state, the parameters of volatilization of Zinc and proportion of Zinc in residue are also in a better state.
To realize the integrated intelligent control of smelting process, it is necessary to realize the judgment of smelting end-point. There are distinct differences of characteristic parameters between the non-end point and end point by disposing the fume images with the RGB method, YUV method, gray histogram, binary bitmap theory and gray level co-occurrence matrix. It provides a new method and technological thought on the judgment of end point of smelting process.
Base on the above research and the collection of the operator's experiment on the fume images of the tertiary air orifice, it is easy to find the commonalities and differences through the colors, transparence luminance and morphology characteristic parameters. The system uses a color digital video camera for flame image collection, according to the different levels of colors, transparence luminance and morphology, the images are divided into volatilization, gloomy eruption, weak volatilization, weak red, bright yellow and white thorn. Then extracting the characteristic parameters of flame picture on area, luminance, chrominance and histogram as the input of the neural network, to realize the classifying and recognizing of the flame pictures. Based on the mapping relationship between flame images of tertiary air orifice and status of the smelting stages, the method of automatically determine of end point is formed, developed a system of automatic judgment of the end point of fuming furnace smelting processing. Taking into account the smelting process of flame flickering and jumping, the method of in accordance with the process information relation to the judgment of end point, general considerations for 20 seconds of 10 images classification results, to determine the current smelting process in which stages, then output with the previous judgments and statistical, finally the results is acquisition for whether in volatilization, calefactive phase or the end point of smelting.
There are once, twice or time after time smelting volatilization of fuming furnace, and every time the end volatilization picture is similar as the end point picture. To achieve the exact end point judgment of smelting processing, relying on single picture sensor information of single judgment is inadequate. Fuming furnace smelting process is complex, the dependents of those various on judgment of end point have non-linear relationship, should not set up precise mathematical relationship. After several times of field research, the fuming furnace's status identification have relationships with the number of cold material, smelting time, the volume of coal, furnace temperature and the characteristics of tertiary air orifice, so using multi-sensor data fusion approach to achieve the end smelting judgments. Using the fusion algorithm disposing the information of temperature, cold material, smelting time, the volume of coal which from the detection system, and the image recognizing system. Based on D-S evidence theory algorithm, integration the judgment of neural network, images recognize and template with parameters, the finally result of end point judgment of smelting process in fuming furnace is formed, also develops the software system of end point judgment of smelting process in fuming furnace.
The integrated intelligent control system of smelting process and the judge of smelting end-point system described in the paper have been applied in HUIZE lead smelting factory of YUNNAN CHIHONG ZINC&GERMANIUM Co., ltd, and have achieved greater economic and social benefits.
引文
[1]《铅锌冶金学》编委会.铅锌冶金学.北京：科学出版社,2003
[2]陈维东,国外有色冶金工厂,：铅锌(上下册),株洲冶炼厂等,1988
[3]北京有色冶金设计研究总院等,重有色金属冶炼设计手册,铅锌铋卷,冶金工业出版社,1996
[4]毛月波,祝明星等,富氧在有色冶金中的应用,冶金工业出版社,1988
[5]S.L.Cockcroft等,锌渣烟化过程中的高压喷煤,有色冶金,1990.3
[6]王华等,烟化炉冶炼工艺节能研究,冶金能源,No.6.1991
[7]王克瑞,炼锡烟化炉的技术现状及改进, 云南冶金,1989.1,P23-26
[8]严寿康,烟化炉硫化挥发工艺在锡冶金中的应用与发展。云锡科技,15(2)1988
[9]王华等,烟化护喷吹射流轨迹数学模拟及熔池内气泡特性研究。第三届有色热能与热工学术年会论文集
[20]Beherenet.H.P.Meta,1988(9):876-881
[21]Cockcroft.S.L.Met.Trns,1989.20B(5):227-235
[24]laguitton D, Bilodeauam, Ghibu C, etal. Expert System Adiser for Operators of a Zinc leaching Plant, Preprints of the IFAC Workshop, Buenos Aires, Argentina,1989
[25]李纪归,烟化炉连续作业评述,云南冶金,1991.6,P40-45
[26]沈立俊,李波,雷德君,锌渣烟化炉连续吹炼生产氧化锌研究,云南冶金,2005.10
[27]王洪江,沈立俊,李波,雷德君,锌渣烟化炉连续吹炼的试验研究,中国有色冶金,2005.6
[28]包崇军,吴红林,压密锌渣烟化炉连续吹炼的工业试验,云南冶金,2007.4
[29]李振家,SnO-SiO2系中氧化亚锡挥发性能的研究,《全国第一届冶金过程物理化学学术论文》,1962,12
[30]L. W. Pormmier, The effect of cock in the volatilization of tin, J. Metals, 1979, No.12
[31]刘中华,硕土论文,昆工冶金系,1984
[32]C. Decroly, Gaseous reduction of tin containing condensates obtained by vaccum treatment of oxidized mineral or slag, Frans. Inst. min. metal.77,1968
[33]I. J.bear, Selective reduction of a low-grade cassite concentrates. Frans. Inst. min. metal.85,1976
[34]Refael Padilla and H. Y. Sohn, The reduction of stannic oxide with carbon. Met. Trans. B. Vol-lOB March.1979
[35]R. C. Bell, G. H. Turner and E. Peters, TMS-AIME,1955, Vol 203, P1477-79 [36]H.H. Kellogg, TMS-AIME,1967, Vol 239, P1439-49
[37]R. J. Grant and L. J. Barnett, In South Australia confer 1975. Australas. I. M. M. Melbourne,1975. p247-65
[38]T. A. A. Quarm, amining Magazine,1964, Vol113(2)
[39]0. A. Sundstrom, J. Metals,1969, Vol22(6)p15-21
[40]A. I. Evdokimenko, R. Zh. Khobdabergenov. al. soviet. J. Non-Ferrous Metals. 1977, Vol18(11)
[41]V. A. Ivanor, A. M. Intykbaev. arl, iZv. Vyssh. vehebn, laved. Tsvetn, Metal.1977
[42]E. S. Gnatovskii. al. Soviet J. Non-Ferrous. Metals.1970. Vol.11 (5)
[43]E. N. Mazurchuk. al. soviet. J. Non-Ferrous. Metals.1970. Vol.11 (4)
[44]G. Abrasher, In advances in Extractive Metallurgy and Refining, M. J. Joes, ed, I.M.M.1972
[45]S.L. Cockcroft等,锌渣烟化过程中的高压喷煤,有色冶炼、1990.3
[46]周苓等,锡中矿硫化挥发的动力学研究,昆工硕土论文,1986
[47]G.G.Richards, Kinetics of the Zinc Slag-Fuming Proc MRTALLURGICAL TRANSACTIONS B514-VOLVEM 16B, SEPTEMBER.1985
[48]王华,烟化炉熔渣池内气泡特性研究,昆明工学院学报,1993.6
[49]李灿,唐文武,烟化熔炼中粉煤的燃烧过程及空气系数的确定,冶金能源,2001.3
[50]聂春分,烟化熔炼过程中的燃料燃烧,湖南有色金属2002.8
[51]李存湜,周振刚,烟化炉节能途径研究,云南冶金,1995.1
[52]孙月强,全冷料烟化炉技术特点及参数控制,工程设计与研究总,第116期2004年12月
[53]王华,周振刚,烟化炉冶炼工艺节能研究,冶金能源,1991.11 10卷6期
[55]王华烟化炉计算机自动控制策略,有色金属,第49卷第4期1997.11
[56]华彦平,于向军,吕震中,范小燕单燃烧器火焰数字图像处理与诊断方法研究,热,能动力工程,第17卷,2002.1
[57]孟令军,用计算机数字图像处理技术检测电站锅炉燃烧器火焰,化工自动化及仪表,2001,18：43-45
[58]陈志刚,蒙建波,李良熹,电站锅炉数字图像火焰检测系统设计与实现,重庆大学学报2003年2月,第26卷第2期
[59]徐旭常,燃烧理论与燃烧设备,北京：清华大学出版社,1989
[60]编写组,重有色冶金炉设计手册,北京：冶金工业出版社,1982
[61]韩昭沧,燃料及燃烧,北京：冶金工业出版社,1987
[62]李灿,改善烟化炉燃烧的途径,冶金能源,20卷3期2001.5
[63]张寿明,缪尔康,李伟,欧迪玖,红外测温仪在烟化炉温度测量中的应用,控制工程,Vo1.10.4,2003.7
[64]郑道昌,王颖,冯志敏,胡海刚,火焰图像的数字化探讨,中国航海,2001.2.
[65]谭皓,李立源,陈维南,基于BP网络的锅炉炉膛火焰燃烧状态自动识别,自动化学报Vol.24 No.5 1998
[66]徐伟勇等.数字图象处理在火焰检测上的应用.中国电力,1994,(10)：41—44
[67]王满家.锅炉炉膛安全保护装置应用状况分析.中国电力,1993,(3)：34—38
[68]舒子恺.三菱新型火焰监视装置(OPTIS)简介.热工自动化信息,1993,1：9—11
[69]刘维,郑坚.工业锅炉炉膛火焰图象处理系统.热电技术,1995,2：43—45
[70]焦李成.神经网络系统理论.西安：西安电子科技大学出版社,1990,34—36
[71]姜学东,韦穗,基于彩色CCD的三色法测量炉膛火焰温度场分布,安徽大学学报,Vol.26,No.2,2002.6
[72]李树涛,王耀南,张昌凡,基于燃烧火焰图象特征的回转窑神经网络控制系统,自动化学报,
[72]李树涛,王耀南,基于神经网络的回转窑火焰图象分割,仪器仪表学报,2001,22(1),1016
[73]黄卓鉴,烟化炉系统爆炸成因分析及其预防措施,有色冶炼,第28卷第1期,1999.2
[74]张寿明,缪尔康,李伟,欧迪玖,烟化炉综合控制系统,冶金自动化,2002年第5期
[75]刘明富,黄卓鉴,我厂烟化炉改造和生产中的技术改进株冶科技Vol.23,No.3,1995.8
[76]李燕坤,云锡三冶使用高压离心鼓风机防喘振控制措施,云锡研究设计院,云锡科技.1996,23(4).33-35,47
[77]康文兰,烟化炉结构与烟化过程关系的探讨,有色金属设计.1995,(3).-34-37,28
[78]杨杰,昆冶烟化炉节能措施及其效果,云南能源.1993,(1).23-24,14
[79]刘明富黄卓鉴,我厂烟化炉改造和生产中的技术改进,株冶科技.1995,23(3)
[79]郑明如,云锡一冶3#烟化炉余热利用装置简析,有色金属设计.1991,(1)
[80]刘明富,烟化炉的试生产,株冶科技.1991,19(4).232-235
[81]丁继岱,烟化炉工艺条件的选择与控制,沈冶科技.1990,(3).1-4
[82]金川镍闪速炉计算机在线控制专家组,金川镍闪速炉计算机在线控制技术研究报告,1995
[83]万维汉,万百五,杨金义,闪速炉的神经网络冰镍质量模型与稳态优化控制研究,自动化学报,199,.25(6)728-733
[84]Wu Min, Nakono Micho, She Jin-Hua. A Distributed Expert Control System for a Hydrometallurgical Zinc Press. Control Engineering Practice, 1998(6):1435-1466
[85]Wu Min, Nakono Micho, She Jin-Hua. A Model-based Expert Control System for the Hydrometallurgy. Expert System with Applications.1999,16(1):135-143
[86]Wu Min, Nakono Micho, She Jin-Hua. An Expert Control Strategy Using Neural Networks for the Electrolytic Process in Zinc Hydrometallurgy. Proc. the 1999,2:1044-1049
[87]王耀南,王辉,彭建春扥等,复杂工业过程的综合集成智能控制,信息与控制,1999,28(4)：298-304
[89]钱佰章,1999年先进控制和信息系统策略,炼油化工自动化,1999(6)：1-9
[90]刘文灿,艾萨炉控制系统的优化与思考,中国有色冶金,2005.10(5)
[91]李培智赵奕朱玲云锡DCS控制系统的应用与调试,有色冶炼,2003.4(2)
[92]Kouich matsuda, Naoki Tamura, Masami Konishi et al.Application of Artifical Intelligence to Operation Control of Kobe No.3 Blast Furnace.Proceedings of the Sixth International Iron and Stell Congress,1990, Nagoya, ISIJ:1-7
[93]Kouich Otsuka, Yoshiyuki Matoba, Yoshimasa Kajiwara et al. A Hybrid Expert System Combined with a Mathematical Model for Blast Furnace Operation. Proceedings of the Sixth International Iron and Stell Congress,1990, Nagoya, ISIJ:8-15
[94]Osamu Lida等,人工厂智能技术在高炉操作中的应用。世界钢铁,1996,2：55-59(Tiron and Stell engineer.1995,10:24-28)
[95]William E. Staib, Norman G. Bliss, Robert B.Staib.Developments in Neural Network Applications:The Intelligent Electric Arc Furnace. AISE Year Book 1992:236-239
[96]William E. Staib, Norman G.Bliss, Neural Network Control System for Electric Arc Furnace. MPT,1995,2:58-63
[97]Kayako Omura, Yoshihisa Otsuka, Masami Konishi. Diagnostic Expert System for Mould Level Control Equipwent in Continuous Caster. Proceedings of the Sixth International Iron and Stell Congress,1990, Nagoya, ISIJ:62-68
[98]Takashi Oda, Naoki Satou, Toshiki Yatuba. Adaptive Technology for Thickness Control of Finisher set-up on Hot Strip Mill. ISIJ International,1995,35(1)
[99]King PJ, Mandanni E. H, The Aplication of Fuzzy Control systems to Industrial Process, IFAC world Congress,1980
[100]Makoto Tsukiyama al,An Application Knowledge Based to Control Systems, Proc, conf,on cybernetic and society, Atlanta, USA, October,1981
[101]李重远,循环流化床镊护专家控制系撇计,全国工业沪窑自动控制学术会议论文集(第二届),1990
[102]Astrom K. J,谈自控理论的发展趋势。国外自动化,1986(6)
[103]Astrom K. J, Expert Control. Automatica,1986,22(3)
[104]张云生等,应用信息集成的铜次炼转炉终点控制,冶金自动化,2000,Vol.24,No.3,14-17
[105]盂动松,复次转炉终点控制约实践和理论,鞍钢技术,1995, (8),7—10
[106]原隆康等,转炉终点动态鳞的控制技术开发,世界钢铁,2000,(2),53—59
[107]扬立志,动态控制转炉终点磷的技术开发,大钢译文,2001, (1),6—9
[108]谢书明等,一种转炉炼钢动态终点预报的新方法,自动化学报,2001, (27),(1),136—139
[109]Opitz.,A陈军,氧气顶次转炉动态终点的确定,世界钢铁,2000,(1),43—47
[110]张鉴等,终点控制碳的现状和前景,特殊铜,1995, (16), (4),1-6
[111]张石等,用图象识别法在线判断烧结矿FeO含量等级的研究,钢铁,1998,(33),(5),1-8
[112]牛玉祥,高炉过程控制新技术在瑞典律勒欧工厂的发展和应用,冶金译丛,1996,(3),40—49
[113]张寿明等,烟化炉吹炼终点火焰图象特征研究,《有色金属》冶炼部分,2004,(3),37-40
[114]蔡自新,徐光佑编著。人工智能及应用(第二版).北京：清华大学出版社,1996,5
[115]李士勇.模糊控制·神经控制和智能控制论[M].哈尔滨：哈尔滨工业大学出版社,1996
[116]M. A. Abdel-latif. Fundamentals of zinc recovery from metallurgical wastes in the Enviroplas process. Minerals Engineering. Vol.15, no.11 (supplement),2002
[117]Frank E. Mark & Theo Lehner. "Plastics Recovery from Waste Electrical & Electronic Equipment in Non-Ferrous Metal Processes. " APME Technical Report, www. apme. org
[118]Y. ZHANG, F. HE and T. R. MEADOWCROFT, Metal Recovery From Zinc Fumer Slags, Fifth International Symposium On Waste Processing And Recycling In Mineral And Metallurgical Industries, Hamilton, Canada, August,2004
[119]王华,周振刚,烟化炉冶炼工艺节能研究,冶金能源,1991,10(2)：27-29
[120]尤佳,王绍纯,李希胜,韩艺萍,通过转炉炉口火焰纹理分析判断氧气顶吹转炉吹炼终点,北京科技大学学报,2000,4：524-528
[121]张成海,张铎主编,现代自动识别技术与应用,北京：清华大学出版社,2003
[122]王耀南,李树涛,毛建旭编著,计算机图像处理与识别技术.北京：高等教育出版社,2001.6
[123](美)Kenneth. R. Castleman著,朱志刚,林学阎,石定机译.数字图像处理.北京：电子工业出版社,2002.2
[124]李弼程,彭天强,彭波等编著,智能图像处理技术.北京：电子工业出版社,2004.7
[125]I. T. Yong, J. J. Gerbrands, L. J. van Vliet, Image Processing Fundamentals, http://www.ph.tn.tudelft.nl/Courses/FIP/noframes/fip.html
[126](美) Rafael C.Gonzalez, Richard E. Woods著,阮秋琦,阮宇智等译,数字 图像处理(第二版).北京：电子工业出版社,2003.3
[127](美)Abhijit S. Pandya, Robert B. Marcy著,徐勇,荆涛等译,神经网络模式识别及其实现.北京：电子工业出版社,1999.6
[128](美)Martin T.Hagan, Howard B. Demuth, Mark H. Beale著,戴葵等译,神经网络设计.北京：机械工业出版社,2002.9
[129]王颖,冯志敏,胡海刚等,燃烧火焰特征的数字图像处理系统,燃气轮机技术,2002,vo1.15：13-15
[130]孟令军,用计算机数字图像处理技术检测电站锅炉燃烧器火焰,化工自动化及仪表,2001,28(2)：43-45
[131]陈志刚,蒙建波,李良熹,电站锅炉数字图像火焰检测系统设计与实现,重庆大学学报,2003,26(2)：32-35
[132]邱道尹,张咏梅,王龙辉等,基于图像识别在线推断烧结矿产量的研究,郑州工业大学学报,2002,Vol.21,No.1：46-48
[133]Li Ning, Mao Sixin, Effective Feature Analysis for Color Image Segmentation, Transaction of Nanjing University of Aeronautics & Astronautics, 2001, Vol.18, No.2:206-212
[134]Massimo Chimenti, Carlo Di Natali, et al. "An IR image processing approach for characterizing combustion instability". Pisa:ERCIM Technical Reference Digital Library.2003
[135]Clark F.Olson and Daniel P. Huttenlocher, Automatic Target Recognition by Maching Orient Edge Pixels IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL.6, NO.1, JANUARY 1997:103-113
[136]G. Baldini, P. Campadelli and R. Lanzarotti, Combustion analysis by image processing of premixed flames, Proceedings of the IEEE International Conference on Image Processing (ICIP2000), Vol. II, pp.708-711.
[137]Diagnostics and Control of Natural Gas-Fired Furnaces via Flame Image Analysis Project Report, CELEST Technology Website, http://fusion6.bu.edu/ techlab/modules/techtransfer/
[138]Mari jana Zekic. "Structure Optimization of Neural Networks in Relation to Underlying Data[R]".Abstracts of the 7th International Conference on Operational Research KOI'98, Rovinj, Croatia, Sep.30-Oct.2,1998:31
[139]Magoulas, G. D., V. P. Plagianakos, and M. N. Vrahatis. Globally Convergent Algorithms With Local Learning Rates. IEEE Trans. on Neural Networks, May 02,774-779
[140]张宏林编著,Visual C++数字图像模式识别技术及工程实践.北京：人民邮电出版社,2003.2
[141]刘同明,夏祖勋,解洪成.数据融合技术及其应用.北京：国防工业出版社,1998
[142]杨万海.多传感器数据融合及其应用.西安：西安电子科技大学出版社,2004
[143]许东,吴铮.基于MATLAB6. x的系统分析与设计—神经网络.西安：西安电子科技大学出版社,2002
[144]袁曾任.人工神经元网络及其应用.北京：清华大学出版社,1999
[145]张兆礼,孙圣和.粗神经网络及其在数据融合中的应用.控制与决策,2001,16(1)：76-82
[146]李宏,徐晖,孙仲康等.基于人工神经网络与证据理论相结合的信息融合空间点目标识别方法研究.信息与控制,1997,5(4)：15—19
[147]敬忠良,杨永胜,李建勋等.基于模糊神经网络和DS推理的智能特征信息融合研究.信息与控制,1999,7(4)：123-126
[148]梁建成,李圣怡等.在线估计表面粗糙度的神经网络多传感器融合方法.国防科技大学学报,1999,30(6)：68-72
[149]Waltz E., Linas J. Multisensor Data Fusion. New York:Artech House, INC.1988
[150]Hovanessian SA. Introduction to Sensor System. New York:Artech House, INC.1988
[151]Thomas F. Fultonl, Christopher J. Cassidy. Navigation Sensor Data Fusion for the AUV Remus. Marine Technology,2001,38(1):65-69
[152]Linas. A Survey of Techniques for CIS Data Fusion. Proceedings of the IEEE,1997,85(1):6-23
[153]Hall, David L, Linas, etc. Introduction to Multisensor Data Fusion. Proceedings of the IEEE,2001,89(1):16-33
[154]Varshney, P. K. Multisensor data fusion. Electronics&Communication Engineering Journal,2002,14(6):245-253
[155]Jiantao Liu, Hongbing Chang. Prediction of the flew stress of high-speed steel during hot deformation using a BP artificial neural network. Journal of material processing technology,2000,103(2):200-205
[156]康耀红.数据融合理论与应用.西安：西安电子科技大学出版社,1997
[157]Luo Zhi-Quan, Tsitsiklis John N. Data Fusion with Minimal Communication. IEEE Transactions on Information Theory,1994,40(5):1551-1563
[158]Durrant-Whyte H f. Sensor models and multi-sensor integration. The Intl. Journal of Robitics Research,1988,17(6):97-113
[159]Garvey T D. a Survey of AI approaches to the integration of information. SPIE,782:68-82
[160]Shafer G. A mathematical theory of evidence. Princeton University Press, NJ,1976
[161]Yang Jian-bo, Madah G Singh. An'evidential reasoning approach for multiple-attribute decision madding with uncertainty, IEEE SMC,1994,24(1): 1-17
[162]Dempster A p. Upper and lower probability is induced by a multivalued mapping. Ann. Math. Statistics,1967, (38):325-339
[163]Bogler P L. Shafer-dempster reasoning with applications to multisensor target identification systems. IEEE SMC,1987,17(6):968-977
[164]Pearson J C, Gelfand J J. Sullivan W E et al, Neural network approach to sensory fusion. SPIE,931:103-108
[165]Stelios C A. Thomopoulos, DIGNET:A Self-organizing neural network for automatic pattern recognition, classification and data fusion. SPIE, sensor Fusion Ⅳ,1991,1611
[166]RC Lou. Data fusion and sensor integration:State-of-the art 1990s. Data Fusion in Robotics and Machine Intelligence. Academic Press Inc.1992:127-135
[167]Dasarathy, B. V., Sensor Fusion Potential Exploitation-Innovative Architectures and Illustrative Applications, Proceedings of the IEEE, Vol.85, No.1,1997
[168]何友,王国宏等.多传感器信息融合及应用.北京：电子工业出版社,2000
[169]胡志坤,梅炽等.PS转炉铜锍吹炼过程智能决策与终点预报系统.有色金属,2002,54(1)：40-42
[170]A.Opitz等.陈军译.氧气顶吹转炉动态吹炼终点的确定.世界钢铁,2000(1)：43-47
[171]Shouming Zhang, Yunsheng Zhang. Application of Artificial Neural Network in Judging the End Point of the Zinc Fuming Furnace,第27届中国控制会议论文集,北京航空航天工大学出版社,2008.7
[172]Kurihara N, Nishikawa M. A combustion diagnosis method for pulverized coal boiler using flame imagere cognition technology. IEEE Transaction on Energy Conversion,1986.1 (2):99-103.
[173]Shimoda M, Sugano A, Kimura T, watanabe Y, Ishiyama K. Prediction method of unburnt carbon for coal Fired utility boiler using image processing technique of combustion flame. IEEE Transactions on Enerey Conversion, 1990.5(4):640-645
[174]Collins S. Advanced flame monitors take on. combustion control. Power,1993. (10):75-77
[175]Mitsubishi Heavy Industrisls, Ltd. SPecfication of flame detector.1997
[176]Huang Y, Yan Y. Transient two dimensional temperature measurement of open flames by dual spectral image analysis. Transactions of the Institute of Measurement and Control,2000.22(5):371-384
[177]Huang H, Yan Y, Riley G.Vision-based measuretnent of temperature distribution in a 500kW model furnace using the two-color method. Measurement, 2000.29:175-183
[178]Yan Y, Lu G, Colechin M. Monitoring and characterisation of Pulverized coal flames using digital imaging techniques. Fuel,2002.81:647-656
[179]Bheemul H C, Lu G, Yan Y. Three-dimensional visualization and quantitative characterization of gaseous flames. Measurement Science and Technology,2002.13(10):1643
[180]Correia D P, Ferrao P, Calderira-Pires A. Advanced 3D emission tomography flame temperature sensor. Combust Sci and Tech,2001.163:1-24
[181]吴占松.发光火焰的图像处理及其在燃烧检测中的应用.清华大学博士学位论文.1988
[182]玉补宣,李天锋,吴占松.图像处理用于发光火焰温度分布测量的研究.工程热物理学报,1989.10(4)：446-448
[183]何万青,余岳峰,张银桥,徐伟勇.基于图像处理和数字视频技术的锅炉多路火焰检测系统,热力发电,2000.(3)：45-48
[184]孙江,徐伟勇,余岳峰,吴建繁.据煤粉火焰图像判断燃烧状况的计算机判断算法.热力发电,1997.(1)：14-18
[185]徐伟勇,余岳峰。孙江,吴建繁.数字图像处理技术在火焰检测上的应用.中国电力,1994.(10)：41-44
[186]许柯夫.数字图像处理技术在电厂锅炉燃烧监测中的应用研究。电力系统自动化,1995.19(4)：43～47
[187]薛飞,基于辐射图像场的火焰温度场测量研究.浙江大学博士学位论文.1999
[188]薛飞,李晓东,倪明江,严建华.基于面阵CCD的火焰温度场测量方法研究。中国电机工程学报,1999.19(1)： 39-41
[189]王飞,马增益,严建华,卑可法.利用火焰图像重建三维温度场的模型和实验。燃烧科学与技术,2004.10(2)： 140-145
[190]邹短,吕震中,玉式民.锅炉全炉膛火焰数字图像处理与监测系统开发与研究.热 能动力工程,1998.13(4)：261-263
[191]王式民,赵延军,汪风林,光学分居热成像法重建火焰温度场分布的研究—工程热物理学报.2002.23(S1)：233～236
[192]周怀春,炉内火焰可视化检测原理与技术,北京,科学出版社2006
[193]罗志增,蒋静坪.机器人感觉与多信息融合[M].北京：机械工业出版社,2002
[194]杨万海.多传感器数据融合及其应用[M].西安：西安电子科技大学出版社,2004
[195]张弛,王玮,徐丽杰,王智.基于D-S算法的断路器机械故障诊断技术[J].电气开关,2007(2)：1-4
[196]朱大奇,于盛林.基于D-S证据理论的数据融合算法及其在电路故障诊断中的应用[J].电子学报,2002(2)：153-155
[197]张雨.基于证据理论的内燃机活塞-套缸-活塞环组件磨损状态识别[J].内燃机学报,2004,22(1)：91-95
[198]董敏.基于数据融合的HAGC系统故障多判据诊断研究[D].河北：燕山大学博士论文,2005
[199]原和平,王健.提高烟化炉处理量的途经,有色金属(冶炼部分),2003.6
[2]陈维东,国外有色冶金工厂,：铅锌(上下册),株洲冶炼厂等,1988
[3]北京有色冶金设计研究总院等,重有色金属冶炼设计手册,铅锌铋卷,冶金工业出版社,1996
[4]毛月波,祝明星等,富氧在有色冶金中的应用,冶金工业出版社,1988
[5]S.L.Cockcroft等,锌渣烟化过程中的高压喷煤,有色冶金,1990.3
[6]王华等,烟化炉冶炼工艺节能研究,冶金能源,No.6.1991
[7]王克瑞,炼锡烟化炉的技术现状及改进, 云南冶金,1989.1,P23-26
[8]严寿康,烟化炉硫化挥发工艺在锡冶金中的应用与发展。云锡科技,15(2)1988
[9]王华等,烟化护喷吹射流轨迹数学模拟及熔池内气泡特性研究。第三届有色热能与热工学术年会论文集
[20]Beherenet.H.P.Meta,1988(9):876-881
[21]Cockcroft.S.L.Met.Trns,1989.20B(5):227-235
[24]laguitton D, Bilodeauam, Ghibu C, etal. Expert System Adiser for Operators of a Zinc leaching Plant, Preprints of the IFAC Workshop, Buenos Aires, Argentina,1989
[25]李纪归,烟化炉连续作业评述,云南冶金,1991.6,P40-45
[26]沈立俊,李波,雷德君,锌渣烟化炉连续吹炼生产氧化锌研究,云南冶金,2005.10
[27]王洪江,沈立俊,李波,雷德君,锌渣烟化炉连续吹炼的试验研究,中国有色冶金,2005.6
[28]包崇军,吴红林,压密锌渣烟化炉连续吹炼的工业试验,云南冶金,2007.4
[29]李振家,SnO-SiO2系中氧化亚锡挥发性能的研究,《全国第一届冶金过程物理化学学术论文》,1962,12
[30]L. W. Pormmier, The effect of cock in the volatilization of tin, J. Metals, 1979, No.12
[31]刘中华,硕土论文,昆工冶金系,1984
[32]C. Decroly, Gaseous reduction of tin containing condensates obtained by vaccum treatment of oxidized mineral or slag, Frans. Inst. min. metal.77,1968
[33]I. J.bear, Selective reduction of a low-grade cassite concentrates. Frans. Inst. min. metal.85,1976
[34]Refael Padilla and H. Y. Sohn, The reduction of stannic oxide with carbon. Met. Trans. B. Vol-lOB March.1979
[35]R. C. Bell, G. H. Turner and E. Peters, TMS-AIME,1955, Vol 203, P1477-79 [36]H.H. Kellogg, TMS-AIME,1967, Vol 239, P1439-49
[37]R. J. Grant and L. J. Barnett, In South Australia confer 1975. Australas. I. M. M. Melbourne,1975. p247-65
[38]T. A. A. Quarm, amining Magazine,1964, Vol113(2)
[39]0. A. Sundstrom, J. Metals,1969, Vol22(6)p15-21
[40]A. I. Evdokimenko, R. Zh. Khobdabergenov. al. soviet. J. Non-Ferrous Metals. 1977, Vol18(11)
[41]V. A. Ivanor, A. M. Intykbaev. arl, iZv. Vyssh. vehebn, laved. Tsvetn, Metal.1977
[42]E. S. Gnatovskii. al. Soviet J. Non-Ferrous. Metals.1970. Vol.11 (5)
[43]E. N. Mazurchuk. al. soviet. J. Non-Ferrous. Metals.1970. Vol.11 (4)
[44]G. Abrasher, In advances in Extractive Metallurgy and Refining, M. J. Joes, ed, I.M.M.1972
[45]S.L. Cockcroft等,锌渣烟化过程中的高压喷煤,有色冶炼、1990.3
[46]周苓等,锡中矿硫化挥发的动力学研究,昆工硕土论文,1986
[47]G.G.Richards, Kinetics of the Zinc Slag-Fuming Proc MRTALLURGICAL TRANSACTIONS B514-VOLVEM 16B, SEPTEMBER.1985
[48]王华,烟化炉熔渣池内气泡特性研究,昆明工学院学报,1993.6
[49]李灿,唐文武,烟化熔炼中粉煤的燃烧过程及空气系数的确定,冶金能源,2001.3
[50]聂春分,烟化熔炼过程中的燃料燃烧,湖南有色金属2002.8
[51]李存湜,周振刚,烟化炉节能途径研究,云南冶金,1995.1
[52]孙月强,全冷料烟化炉技术特点及参数控制,工程设计与研究总,第116期2004年12月
[53]王华,周振刚,烟化炉冶炼工艺节能研究,冶金能源,1991.11 10卷6期
[55]王华烟化炉计算机自动控制策略,有色金属,第49卷第4期1997.11
[56]华彦平,于向军,吕震中,范小燕单燃烧器火焰数字图像处理与诊断方法研究,热,能动力工程,第17卷,2002.1
[57]孟令军,用计算机数字图像处理技术检测电站锅炉燃烧器火焰,化工自动化及仪表,2001,18：43-45
[58]陈志刚,蒙建波,李良熹,电站锅炉数字图像火焰检测系统设计与实现,重庆大学学报2003年2月,第26卷第2期
[59]徐旭常,燃烧理论与燃烧设备,北京：清华大学出版社,1989
[60]编写组,重有色冶金炉设计手册,北京：冶金工业出版社,1982
[61]韩昭沧,燃料及燃烧,北京：冶金工业出版社,1987
[62]李灿,改善烟化炉燃烧的途径,冶金能源,20卷3期2001.5
[63]张寿明,缪尔康,李伟,欧迪玖,红外测温仪在烟化炉温度测量中的应用,控制工程,Vo1.10.4,2003.7
[64]郑道昌,王颖,冯志敏,胡海刚,火焰图像的数字化探讨,中国航海,2001.2.
[65]谭皓,李立源,陈维南,基于BP网络的锅炉炉膛火焰燃烧状态自动识别,自动化学报Vol.24 No.5 1998
[66]徐伟勇等.数字图象处理在火焰检测上的应用.中国电力,1994,(10)：41—44
[67]王满家.锅炉炉膛安全保护装置应用状况分析.中国电力,1993,(3)：34—38
[68]舒子恺.三菱新型火焰监视装置(OPTIS)简介.热工自动化信息,1993,1：9—11
[69]刘维,郑坚.工业锅炉炉膛火焰图象处理系统.热电技术,1995,2：43—45
[70]焦李成.神经网络系统理论.西安：西安电子科技大学出版社,1990,34—36
[71]姜学东,韦穗,基于彩色CCD的三色法测量炉膛火焰温度场分布,安徽大学学报,Vol.26,No.2,2002.6
[72]李树涛,王耀南,张昌凡,基于燃烧火焰图象特征的回转窑神经网络控制系统,自动化学报,
[72]李树涛,王耀南,基于神经网络的回转窑火焰图象分割,仪器仪表学报,2001,22(1),1016
[73]黄卓鉴,烟化炉系统爆炸成因分析及其预防措施,有色冶炼,第28卷第1期,1999.2
[74]张寿明,缪尔康,李伟,欧迪玖,烟化炉综合控制系统,冶金自动化,2002年第5期
[75]刘明富,黄卓鉴,我厂烟化炉改造和生产中的技术改进株冶科技Vol.23,No.3,1995.8
[76]李燕坤,云锡三冶使用高压离心鼓风机防喘振控制措施,云锡研究设计院,云锡科技.1996,23(4).33-35,47
[77]康文兰,烟化炉结构与烟化过程关系的探讨,有色金属设计.1995,(3).-34-37,28
[78]杨杰,昆冶烟化炉节能措施及其效果,云南能源.1993,(1).23-24,14
[79]刘明富黄卓鉴,我厂烟化炉改造和生产中的技术改进,株冶科技.1995,23(3)
[79]郑明如,云锡一冶3#烟化炉余热利用装置简析,有色金属设计.1991,(1)
[80]刘明富,烟化炉的试生产,株冶科技.1991,19(4).232-235
[81]丁继岱,烟化炉工艺条件的选择与控制,沈冶科技.1990,(3).1-4
[82]金川镍闪速炉计算机在线控制专家组,金川镍闪速炉计算机在线控制技术研究报告,1995
[83]万维汉,万百五,杨金义,闪速炉的神经网络冰镍质量模型与稳态优化控制研究,自动化学报,199,.25(6)728-733
[84]Wu Min, Nakono Micho, She Jin-Hua. A Distributed Expert Control System for a Hydrometallurgical Zinc Press. Control Engineering Practice, 1998(6):1435-1466
[85]Wu Min, Nakono Micho, She Jin-Hua. A Model-based Expert Control System for the Hydrometallurgy. Expert System with Applications.1999,16(1):135-143
[86]Wu Min, Nakono Micho, She Jin-Hua. An Expert Control Strategy Using Neural Networks for the Electrolytic Process in Zinc Hydrometallurgy. Proc. the 1999,2:1044-1049
[87]王耀南,王辉,彭建春扥等,复杂工业过程的综合集成智能控制,信息与控制,1999,28(4)：298-304
[89]钱佰章,1999年先进控制和信息系统策略,炼油化工自动化,1999(6)：1-9
[90]刘文灿,艾萨炉控制系统的优化与思考,中国有色冶金,2005.10(5)
[91]李培智赵奕朱玲云锡DCS控制系统的应用与调试,有色冶炼,2003.4(2)
[92]Kouich matsuda, Naoki Tamura, Masami Konishi et al.Application of Artifical Intelligence to Operation Control of Kobe No.3 Blast Furnace.Proceedings of the Sixth International Iron and Stell Congress,1990, Nagoya, ISIJ:1-7
[93]Kouich Otsuka, Yoshiyuki Matoba, Yoshimasa Kajiwara et al. A Hybrid Expert System Combined with a Mathematical Model for Blast Furnace Operation. Proceedings of the Sixth International Iron and Stell Congress,1990, Nagoya, ISIJ:8-15
[94]Osamu Lida等,人工厂智能技术在高炉操作中的应用。世界钢铁,1996,2：55-59(Tiron and Stell engineer.1995,10:24-28)
[95]William E. Staib, Norman G. Bliss, Robert B.Staib.Developments in Neural Network Applications:The Intelligent Electric Arc Furnace. AISE Year Book 1992:236-239
[96]William E. Staib, Norman G.Bliss, Neural Network Control System for Electric Arc Furnace. MPT,1995,2:58-63
[97]Kayako Omura, Yoshihisa Otsuka, Masami Konishi. Diagnostic Expert System for Mould Level Control Equipwent in Continuous Caster. Proceedings of the Sixth International Iron and Stell Congress,1990, Nagoya, ISIJ:62-68
[98]Takashi Oda, Naoki Satou, Toshiki Yatuba. Adaptive Technology for Thickness Control of Finisher set-up on Hot Strip Mill. ISIJ International,1995,35(1)
[99]King PJ, Mandanni E. H, The Aplication of Fuzzy Control systems to Industrial Process, IFAC world Congress,1980
[100]Makoto Tsukiyama al,An Application Knowledge Based to Control Systems, Proc, conf,on cybernetic and society, Atlanta, USA, October,1981
[101]李重远,循环流化床镊护专家控制系撇计,全国工业沪窑自动控制学术会议论文集(第二届),1990
[102]Astrom K. J,谈自控理论的发展趋势。国外自动化,1986(6)
[103]Astrom K. J, Expert Control. Automatica,1986,22(3)
[104]张云生等,应用信息集成的铜次炼转炉终点控制,冶金自动化,2000,Vol.24,No.3,14-17
[105]盂动松,复次转炉终点控制约实践和理论,鞍钢技术,1995, (8),7—10
[106]原隆康等,转炉终点动态鳞的控制技术开发,世界钢铁,2000,(2),53—59
[107]扬立志,动态控制转炉终点磷的技术开发,大钢译文,2001, (1),6—9
[108]谢书明等,一种转炉炼钢动态终点预报的新方法,自动化学报,2001, (27),(1),136—139
[109]Opitz.,A陈军,氧气顶次转炉动态终点的确定,世界钢铁,2000,(1),43—47
[110]张鉴等,终点控制碳的现状和前景,特殊铜,1995, (16), (4),1-6
[111]张石等,用图象识别法在线判断烧结矿FeO含量等级的研究,钢铁,1998,(33),(5),1-8
[112]牛玉祥,高炉过程控制新技术在瑞典律勒欧工厂的发展和应用,冶金译丛,1996,(3),40—49
[113]张寿明等,烟化炉吹炼终点火焰图象特征研究,《有色金属》冶炼部分,2004,(3),37-40
[114]蔡自新,徐光佑编著。人工智能及应用(第二版).北京：清华大学出版社,1996,5
[115]李士勇.模糊控制·神经控制和智能控制论[M].哈尔滨：哈尔滨工业大学出版社,1996
[116]M. A. Abdel-latif. Fundamentals of zinc recovery from metallurgical wastes in the Enviroplas process. Minerals Engineering. Vol.15, no.11 (supplement),2002
[117]Frank E. Mark & Theo Lehner. "Plastics Recovery from Waste Electrical & Electronic Equipment in Non-Ferrous Metal Processes. " APME Technical Report, www. apme. org
[118]Y. ZHANG, F. HE and T. R. MEADOWCROFT, Metal Recovery From Zinc Fumer Slags, Fifth International Symposium On Waste Processing And Recycling In Mineral And Metallurgical Industries, Hamilton, Canada, August,2004
[119]王华,周振刚,烟化炉冶炼工艺节能研究,冶金能源,1991,10(2)：27-29
[120]尤佳,王绍纯,李希胜,韩艺萍,通过转炉炉口火焰纹理分析判断氧气顶吹转炉吹炼终点,北京科技大学学报,2000,4：524-528
[121]张成海,张铎主编,现代自动识别技术与应用,北京：清华大学出版社,2003
[122]王耀南,李树涛,毛建旭编著,计算机图像处理与识别技术.北京：高等教育出版社,2001.6
[123](美)Kenneth. R. Castleman著,朱志刚,林学阎,石定机译.数字图像处理.北京：电子工业出版社,2002.2
[124]李弼程,彭天强,彭波等编著,智能图像处理技术.北京：电子工业出版社,2004.7
[125]I. T. Yong, J. J. Gerbrands, L. J. van Vliet, Image Processing Fundamentals, http://www.ph.tn.tudelft.nl/Courses/FIP/noframes/fip.html
[126](美) Rafael C.Gonzalez, Richard E. Woods著,阮秋琦,阮宇智等译,数字 图像处理(第二版).北京：电子工业出版社,2003.3
[127](美)Abhijit S. Pandya, Robert B. Marcy著,徐勇,荆涛等译,神经网络模式识别及其实现.北京：电子工业出版社,1999.6
[128](美)Martin T.Hagan, Howard B. Demuth, Mark H. Beale著,戴葵等译,神经网络设计.北京：机械工业出版社,2002.9
[129]王颖,冯志敏,胡海刚等,燃烧火焰特征的数字图像处理系统,燃气轮机技术,2002,vo1.15：13-15
[130]孟令军,用计算机数字图像处理技术检测电站锅炉燃烧器火焰,化工自动化及仪表,2001,28(2)：43-45
[131]陈志刚,蒙建波,李良熹,电站锅炉数字图像火焰检测系统设计与实现,重庆大学学报,2003,26(2)：32-35
[132]邱道尹,张咏梅,王龙辉等,基于图像识别在线推断烧结矿产量的研究,郑州工业大学学报,2002,Vol.21,No.1：46-48
[133]Li Ning, Mao Sixin, Effective Feature Analysis for Color Image Segmentation, Transaction of Nanjing University of Aeronautics & Astronautics, 2001, Vol.18, No.2:206-212
[134]Massimo Chimenti, Carlo Di Natali, et al. "An IR image processing approach for characterizing combustion instability". Pisa:ERCIM Technical Reference Digital Library.2003
[135]Clark F.Olson and Daniel P. Huttenlocher, Automatic Target Recognition by Maching Orient Edge Pixels IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL.6, NO.1, JANUARY 1997:103-113
[136]G. Baldini, P. Campadelli and R. Lanzarotti, Combustion analysis by image processing of premixed flames, Proceedings of the IEEE International Conference on Image Processing (ICIP2000), Vol. II, pp.708-711.
[137]Diagnostics and Control of Natural Gas-Fired Furnaces via Flame Image Analysis Project Report, CELEST Technology Website, http://fusion6.bu.edu/ techlab/modules/techtransfer/
[138]Mari jana Zekic. "Structure Optimization of Neural Networks in Relation to Underlying Data[R]".Abstracts of the 7th International Conference on Operational Research KOI'98, Rovinj, Croatia, Sep.30-Oct.2,1998:31
[139]Magoulas, G. D., V. P. Plagianakos, and M. N. Vrahatis. Globally Convergent Algorithms With Local Learning Rates. IEEE Trans. on Neural Networks, May 02,774-779
[140]张宏林编著,Visual C++数字图像模式识别技术及工程实践.北京：人民邮电出版社,2003.2
[141]刘同明,夏祖勋,解洪成.数据融合技术及其应用.北京：国防工业出版社,1998
[142]杨万海.多传感器数据融合及其应用.西安：西安电子科技大学出版社,2004
[143]许东,吴铮.基于MATLAB6. x的系统分析与设计—神经网络.西安：西安电子科技大学出版社,2002
[144]袁曾任.人工神经元网络及其应用.北京：清华大学出版社,1999
[145]张兆礼,孙圣和.粗神经网络及其在数据融合中的应用.控制与决策,2001,16(1)：76-82
[146]李宏,徐晖,孙仲康等.基于人工神经网络与证据理论相结合的信息融合空间点目标识别方法研究.信息与控制,1997,5(4)：15—19
[147]敬忠良,杨永胜,李建勋等.基于模糊神经网络和DS推理的智能特征信息融合研究.信息与控制,1999,7(4)：123-126
[148]梁建成,李圣怡等.在线估计表面粗糙度的神经网络多传感器融合方法.国防科技大学学报,1999,30(6)：68-72
[149]Waltz E., Linas J. Multisensor Data Fusion. New York:Artech House, INC.1988
[150]Hovanessian SA. Introduction to Sensor System. New York:Artech House, INC.1988
[151]Thomas F. Fultonl, Christopher J. Cassidy. Navigation Sensor Data Fusion for the AUV Remus. Marine Technology,2001,38(1):65-69
[152]Linas. A Survey of Techniques for CIS Data Fusion. Proceedings of the IEEE,1997,85(1):6-23
[153]Hall, David L, Linas, etc. Introduction to Multisensor Data Fusion. Proceedings of the IEEE,2001,89(1):16-33
[154]Varshney, P. K. Multisensor data fusion. Electronics&Communication Engineering Journal,2002,14(6):245-253
[155]Jiantao Liu, Hongbing Chang. Prediction of the flew stress of high-speed steel during hot deformation using a BP artificial neural network. Journal of material processing technology,2000,103(2):200-205
[156]康耀红.数据融合理论与应用.西安：西安电子科技大学出版社,1997
[157]Luo Zhi-Quan, Tsitsiklis John N. Data Fusion with Minimal Communication. IEEE Transactions on Information Theory,1994,40(5):1551-1563
[158]Durrant-Whyte H f. Sensor models and multi-sensor integration. The Intl. Journal of Robitics Research,1988,17(6):97-113
[159]Garvey T D. a Survey of AI approaches to the integration of information. SPIE,782:68-82
[160]Shafer G. A mathematical theory of evidence. Princeton University Press, NJ,1976
[161]Yang Jian-bo, Madah G Singh. An'evidential reasoning approach for multiple-attribute decision madding with uncertainty, IEEE SMC,1994,24(1): 1-17
[162]Dempster A p. Upper and lower probability is induced by a multivalued mapping. Ann. Math. Statistics,1967, (38):325-339
[163]Bogler P L. Shafer-dempster reasoning with applications to multisensor target identification systems. IEEE SMC,1987,17(6):968-977
[164]Pearson J C, Gelfand J J. Sullivan W E et al, Neural network approach to sensory fusion. SPIE,931:103-108
[165]Stelios C A. Thomopoulos, DIGNET:A Self-organizing neural network for automatic pattern recognition, classification and data fusion. SPIE, sensor Fusion Ⅳ,1991,1611
[166]RC Lou. Data fusion and sensor integration:State-of-the art 1990s. Data Fusion in Robotics and Machine Intelligence. Academic Press Inc.1992:127-135
[167]Dasarathy, B. V., Sensor Fusion Potential Exploitation-Innovative Architectures and Illustrative Applications, Proceedings of the IEEE, Vol.85, No.1,1997
[168]何友,王国宏等.多传感器信息融合及应用.北京：电子工业出版社,2000
[169]胡志坤,梅炽等.PS转炉铜锍吹炼过程智能决策与终点预报系统.有色金属,2002,54(1)：40-42
[170]A.Opitz等.陈军译.氧气顶吹转炉动态吹炼终点的确定.世界钢铁,2000(1)：43-47
[171]Shouming Zhang, Yunsheng Zhang. Application of Artificial Neural Network in Judging the End Point of the Zinc Fuming Furnace,第27届中国控制会议论文集,北京航空航天工大学出版社,2008.7
[172]Kurihara N, Nishikawa M. A combustion diagnosis method for pulverized coal boiler using flame imagere cognition technology. IEEE Transaction on Energy Conversion,1986.1 (2):99-103.
[173]Shimoda M, Sugano A, Kimura T, watanabe Y, Ishiyama K. Prediction method of unburnt carbon for coal Fired utility boiler using image processing technique of combustion flame. IEEE Transactions on Enerey Conversion, 1990.5(4):640-645
[174]Collins S. Advanced flame monitors take on. combustion control. Power,1993. (10):75-77
[175]Mitsubishi Heavy Industrisls, Ltd. SPecfication of flame detector.1997
[176]Huang Y, Yan Y. Transient two dimensional temperature measurement of open flames by dual spectral image analysis. Transactions of the Institute of Measurement and Control,2000.22(5):371-384
[177]Huang H, Yan Y, Riley G.Vision-based measuretnent of temperature distribution in a 500kW model furnace using the two-color method. Measurement, 2000.29:175-183
[178]Yan Y, Lu G, Colechin M. Monitoring and characterisation of Pulverized coal flames using digital imaging techniques. Fuel,2002.81:647-656
[179]Bheemul H C, Lu G, Yan Y. Three-dimensional visualization and quantitative characterization of gaseous flames. Measurement Science and Technology,2002.13(10):1643
[180]Correia D P, Ferrao P, Calderira-Pires A. Advanced 3D emission tomography flame temperature sensor. Combust Sci and Tech,2001.163:1-24
[181]吴占松.发光火焰的图像处理及其在燃烧检测中的应用.清华大学博士学位论文.1988
[182]玉补宣,李天锋,吴占松.图像处理用于发光火焰温度分布测量的研究.工程热物理学报,1989.10(4)：446-448
[183]何万青,余岳峰,张银桥,徐伟勇.基于图像处理和数字视频技术的锅炉多路火焰检测系统,热力发电,2000.(3)：45-48
[184]孙江,徐伟勇,余岳峰,吴建繁.据煤粉火焰图像判断燃烧状况的计算机判断算法.热力发电,1997.(1)：14-18
[185]徐伟勇,余岳峰。孙江,吴建繁.数字图像处理技术在火焰检测上的应用.中国电力,1994.(10)：41-44
[186]许柯夫.数字图像处理技术在电厂锅炉燃烧监测中的应用研究。电力系统自动化,1995.19(4)：43～47
[187]薛飞,基于辐射图像场的火焰温度场测量研究.浙江大学博士学位论文.1999
[188]薛飞,李晓东,倪明江,严建华.基于面阵CCD的火焰温度场测量方法研究。中国电机工程学报,1999.19(1)： 39-41
[189]王飞,马增益,严建华,卑可法.利用火焰图像重建三维温度场的模型和实验。燃烧科学与技术,2004.10(2)： 140-145
[190]邹短,吕震中,玉式民.锅炉全炉膛火焰数字图像处理与监测系统开发与研究.热 能动力工程,1998.13(4)：261-263
[191]王式民,赵延军,汪风林,光学分居热成像法重建火焰温度场分布的研究—工程热物理学报.2002.23(S1)：233～236
[192]周怀春,炉内火焰可视化检测原理与技术,北京,科学出版社2006
[193]罗志增,蒋静坪.机器人感觉与多信息融合[M].北京：机械工业出版社,2002
[194]杨万海.多传感器数据融合及其应用[M].西安：西安电子科技大学出版社,2004
[195]张弛,王玮,徐丽杰,王智.基于D-S算法的断路器机械故障诊断技术[J].电气开关,2007(2)：1-4
[196]朱大奇,于盛林.基于D-S证据理论的数据融合算法及其在电路故障诊断中的应用[J].电子学报,2002(2)：153-155
[197]张雨.基于证据理论的内燃机活塞-套缸-活塞环组件磨损状态识别[J].内燃机学报,2004,22(1)：91-95
[198]董敏.基于数据融合的HAGC系统故障多判据诊断研究[D].河北：燕山大学博士论文,2005
[199]原和平,王健.提高烟化炉处理量的途经,有色金属(冶炼部分),2003.6
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |