压缩机动态检测与故障预测分析
|
摘要
随着工业生产现代化和机器设备的大型化、连续化、高速化和自动化,一方面在提高生产率、降低成本、废品率方面带来很大好处,但另一方面,由于设备故障停工而造成的损失成反比增加,进而维修费用大幅度增加。现代化设备大都技术先进、结构复杂、点检工作量大、检查质量要求高,故障因素很难靠人的感官和经验检查出来。复杂先进的设备不便轻易解体检查,因此必须采用先进的仪器和科学的方法来诊断。
本论文的研究的主要内容是根据检测信号的不同,对齐鲁石化高压聚乙烯车间的压缩机,采用三种针对往复压缩机的故障诊断技术,即参数法、振动法、油液法(又称介质金属法),进行比较分析,得出的结果用于动态检测与故障预测分析,并提早做好预防工作,避免停车造成经济损失。
目前,压缩机动态检测与故障预测分析系统已开发成功,其比较分析出的结果与齐鲁石化塑料厂实际生产过程中遇到的问题基本吻合,它将有效地减少压缩机故障的发生,带来可观的经济效益。
The industrial production is becoming more modernization, machines and equipments is becoming larger, more continually, automatization and rapidly, it benefit from improving the productivity and depressing the cost and waster, but on the other hand, the inverse ratio of loss is increased because of the equipment failure and the charge of maintenance increased more and more. Modern equipments usually have advanced technology and complex structure, they need to do a lot of high quality examination. The hidden trouble of the machine is hard to be found by man's experience and sense. Complex and advanced machine isn't easy to be disassembled to check, so we must use advanced instrument and scientific ways to diagnose.
This thesis is mainly focus on: By the different gathering signs of SINOPEC QILU LTD. PLASTICS COMPEX LDPE high pressure compressor, we use three technology-parameters technique, vibration technique and oil-liquid technique (also be called medium-metal
technique)- to compare and diagnose piston-compressor. And the result is used to dynamic check and failure forecast analysis, so we have time to avoid suddenness shut-down and depress the economic losing.
At present, the system of fault diagnoses and forecast analysis of compressor has been opening out successfully. The result that system get by compare and analysis ways is approximately the same as the LDPE compressor what was happened. It will effectually depress the number of the compressor failure and bring a lot of economic benefit.
本论文的研究的主要内容是根据检测信号的不同,对齐鲁石化高压聚乙烯车间的压缩机,采用三种针对往复压缩机的故障诊断技术,即参数法、振动法、油液法(又称介质金属法),进行比较分析,得出的结果用于动态检测与故障预测分析,并提早做好预防工作,避免停车造成经济损失。
目前,压缩机动态检测与故障预测分析系统已开发成功,其比较分析出的结果与齐鲁石化塑料厂实际生产过程中遇到的问题基本吻合,它将有效地减少压缩机故障的发生,带来可观的经济效益。
The industrial production is becoming more modernization, machines and equipments is becoming larger, more continually, automatization and rapidly, it benefit from improving the productivity and depressing the cost and waster, but on the other hand, the inverse ratio of loss is increased because of the equipment failure and the charge of maintenance increased more and more. Modern equipments usually have advanced technology and complex structure, they need to do a lot of high quality examination. The hidden trouble of the machine is hard to be found by man's experience and sense. Complex and advanced machine isn't easy to be disassembled to check, so we must use advanced instrument and scientific ways to diagnose.
This thesis is mainly focus on: By the different gathering signs of SINOPEC QILU LTD. PLASTICS COMPEX LDPE high pressure compressor, we use three technology-parameters technique, vibration technique and oil-liquid technique (also be called medium-metal
technique)- to compare and diagnose piston-compressor. And the result is used to dynamic check and failure forecast analysis, so we have time to avoid suddenness shut-down and depress the economic losing.
At present, the system of fault diagnoses and forecast analysis of compressor has been opening out successfully. The result that system get by compare and analysis ways is approximately the same as the LDPE compressor what was happened. It will effectually depress the number of the compressor failure and bring a lot of economic benefit.
引文
[1]赵超,张君昌,控制系统故障检测与多模型混合估计方法,系统工程与电子技术,2001.7
[2]齐崇英,贺正洪,陈西宏,基于神经网络的导弹故障智能诊断专家系统,系统工程与电子技术,2001.12
[3]张克辉,黄荣华,欧阳光耀,张萍,分形学在柴油机燃油系统故障诊断中的应用,华中科技大学学报,2002.2
[4]符向前,刘光临,蒋劲,BP神经网络在水轮发电机组状态监测与诊断系统中的应用,武汉大学学报,2002.2
[5]阮学风,韩水生,熊志刚,王四清,杨钟胜,电器故障诊断的系统方法,武汉大学学报,2002.1
[6]卢学军,缪思恩,王一欧,陈仲仪,顾晃,故障诊断专家系统知识处理机知识库管理方法研究,计算机工程与应用,2001.24
[7]陈忠,郑时雄,孙延明,基于WEB的远程检测与故障诊断实现策略,华南理工大学学报,2002.6
[8]张彦铎,蒋兴渭,黄文虎,故障诊断中关联结果与专家知识的融合技术,哈尔滨工业大学学报,2002.2
[9]程耕国,周凤星,一种基于小波分析的故障检测与诊断,控制与决策,2001.11
[10]洪治,李国宏,蔡维由,蔡天富,基于小波包分析的水轮发电机组振动的故障诊断,武汉大学学报,2002.2
[11]王建民,张雅丽,赵海文,师占群,基于小波模型的故障诊断法,河北工业大学学报,2002.2
[12]曹志彤,陈宏平,何国光,异步电动机故障诊断的小波变换等高图方法,仪器仪表学报,2002.8
[13]孙涛,张宏建,周莉,QRS波的多尺度融合检测算法,浙江大学学报,2002.1
[14] 盛昌达. 预防性试验与在线测试. 96’全国电力行业电气绝缘监测技术交流会,1996年10月,海口
[15] 盛昌达. 电气设备故障放电的运行监测——在国内的应用和前景. 96’全国电力行业电气绝缘监测技术交流会,1996年10月,海口
[16] 潘新民,微型计算机控制技术,2001.7
[17](美)R.Dorf 邹逢兴等译,现代控制系统(第八版)(翻译版),2001.7
18] 邹逢兴等,计算机应用系统的故障诊断与可靠性技术基础,
[19]朱德恒,谈克雄,王昌长等. 在线检测变压器局部放电的微机系统. 高电压技术,1992,18(1):45-49
[20]姜磊, 李福祺, 朱德恒, 谈克雄. 新型固定式变压器放电在线监测系统. 清华大学学报(自然科学版), 1999, 39(7):5-8
[21]朱德恒,严璋. 高电压绝缘. 北京. 清华大学出版社,1992
[22] Kawada H .et al. New Apparatus for Detecting Transformer Faults. IEEE Trans. EI. 1986, 21(2):221-229
[23] Wenzel D. et al. Partial Discharge Measurement and Gas Monitoring of a Power Transformer On-site. 7th International Conference on Dielectric Materials , measurements and Applications. Bath, UK, 23-26, September, 1996
[24] Hong-Tzer Yang, et al. On line fault diagnosis of power substation using connection expert system. IEEE Trans. On Power System, 1995, 10(1):323-325
[25] McDonald J. R. Turbine generator plant monitoring towards integrated systems. Proc. of ’96 Intern. Conf. On Intelligent Systems Applications to Power Systems, P. 151
[26] Boehl N. M., et al. Fuzzy art neural network approach for incipient fault detection and isolation in rotating machines. Proc. of 1995 IEEE Intern. Conf. on Neural Networks, P. 538
[27] Zhenyuan Wang, Deheng Zhu, Kexiong Tan, et al. PD monitor system for power generators. IEEE Trans. D&EI, 1998,5(6):850-856
[28]M.S.Ahmed, Neural-Net-Based Direct Adaptive Control for a Class of Nonlinear Plants,IEEE TRANSACTIONS ON AUTOMATIC CONTROL,VOL,45,NO.1,2000.1
[29]Arun T.Vemuri, Sensor Bias Fault Diagnosis in a Class of Nonlinear
Systems, IEEE TRANSACTIONS ON AUTOMATIC CONTROL,VOL.46,NO.46, 2001.6
[30]Zhiqiang Gao, Fuzyy Control—K.Passino and S.Yurkovich(Reading,MA:Addision Wesley Longman,Inc.,1998), IEEE TRANSACTIONS ON AUTOMATIC CONTROL,VOL,45,NO.10,
2000.10
[31]Frederic Hamelin,Dominique Sauter, Robust fault detction ini uncertain dynamic systems,Automatica,2000.36
[32]Walmir M,Caminhas,Ricardo H.C.Takahashi Dep.of Electrical Engineering, Federal University of Minas Gerais Av.Antnio Carlos 6627, Horizontc-MG-Brazil, Dynamic System Failure Detection and Diagnosis Employing Sliding Mode Observers and Fuzzy Neural Networks
[33]NILS. Nilsson. Artificial Intelligence A New Synthesis [M]. China Machine Press, 1999.
[34] Rossi Todd M, Braun James E. Statistical rule-based fault detection and diagnostic method for vapor compression air conditioners. HVAC&R Research,v3 nl,1997
[35]Narayanan, Ajit, Jin Yuanping , Object-oriented representations, causal reasoning and expert systems. Expert Systems, v8 nl,1991.
[36]Leung David, Romagnoli Jose. Dynamic probabilistic model-based expert system for fault diagnosis. Computers and Chemical Engineering, v24 n11,2000.
[37]Grossberg S. Nonlinear Neural Networks: Principles, Machines and Architectures[J].Neural Networks,1998,(1):15-57.
[38]Blum E K, Li L K. Approximation Theory and Feedforward Networks[J]. Neural Networks ,1991,4(4):511-515.
[2]齐崇英,贺正洪,陈西宏,基于神经网络的导弹故障智能诊断专家系统,系统工程与电子技术,2001.12
[3]张克辉,黄荣华,欧阳光耀,张萍,分形学在柴油机燃油系统故障诊断中的应用,华中科技大学学报,2002.2
[4]符向前,刘光临,蒋劲,BP神经网络在水轮发电机组状态监测与诊断系统中的应用,武汉大学学报,2002.2
[5]阮学风,韩水生,熊志刚,王四清,杨钟胜,电器故障诊断的系统方法,武汉大学学报,2002.1
[6]卢学军,缪思恩,王一欧,陈仲仪,顾晃,故障诊断专家系统知识处理机知识库管理方法研究,计算机工程与应用,2001.24
[7]陈忠,郑时雄,孙延明,基于WEB的远程检测与故障诊断实现策略,华南理工大学学报,2002.6
[8]张彦铎,蒋兴渭,黄文虎,故障诊断中关联结果与专家知识的融合技术,哈尔滨工业大学学报,2002.2
[9]程耕国,周凤星,一种基于小波分析的故障检测与诊断,控制与决策,2001.11
[10]洪治,李国宏,蔡维由,蔡天富,基于小波包分析的水轮发电机组振动的故障诊断,武汉大学学报,2002.2
[11]王建民,张雅丽,赵海文,师占群,基于小波模型的故障诊断法,河北工业大学学报,2002.2
[12]曹志彤,陈宏平,何国光,异步电动机故障诊断的小波变换等高图方法,仪器仪表学报,2002.8
[13]孙涛,张宏建,周莉,QRS波的多尺度融合检测算法,浙江大学学报,2002.1
[14] 盛昌达. 预防性试验与在线测试. 96’全国电力行业电气绝缘监测技术交流会,1996年10月,海口
[15] 盛昌达. 电气设备故障放电的运行监测——在国内的应用和前景. 96’全国电力行业电气绝缘监测技术交流会,1996年10月,海口
[16] 潘新民,微型计算机控制技术,2001.7
[17](美)R.Dorf 邹逢兴等译,现代控制系统(第八版)(翻译版),2001.7
18] 邹逢兴等,计算机应用系统的故障诊断与可靠性技术基础,
[19]朱德恒,谈克雄,王昌长等. 在线检测变压器局部放电的微机系统. 高电压技术,1992,18(1):45-49
[20]姜磊, 李福祺, 朱德恒, 谈克雄. 新型固定式变压器放电在线监测系统. 清华大学学报(自然科学版), 1999, 39(7):5-8
[21]朱德恒,严璋. 高电压绝缘. 北京. 清华大学出版社,1992
[22] Kawada H .et al. New Apparatus for Detecting Transformer Faults. IEEE Trans. EI. 1986, 21(2):221-229
[23] Wenzel D. et al. Partial Discharge Measurement and Gas Monitoring of a Power Transformer On-site. 7th International Conference on Dielectric Materials , measurements and Applications. Bath, UK, 23-26, September, 1996
[24] Hong-Tzer Yang, et al. On line fault diagnosis of power substation using connection expert system. IEEE Trans. On Power System, 1995, 10(1):323-325
[25] McDonald J. R. Turbine generator plant monitoring towards integrated systems. Proc. of ’96 Intern. Conf. On Intelligent Systems Applications to Power Systems, P. 151
[26] Boehl N. M., et al. Fuzzy art neural network approach for incipient fault detection and isolation in rotating machines. Proc. of 1995 IEEE Intern. Conf. on Neural Networks, P. 538
[27] Zhenyuan Wang, Deheng Zhu, Kexiong Tan, et al. PD monitor system for power generators. IEEE Trans. D&EI, 1998,5(6):850-856
[28]M.S.Ahmed, Neural-Net-Based Direct Adaptive Control for a Class of Nonlinear Plants,IEEE TRANSACTIONS ON AUTOMATIC CONTROL,VOL,45,NO.1,2000.1
[29]Arun T.Vemuri, Sensor Bias Fault Diagnosis in a Class of Nonlinear
Systems, IEEE TRANSACTIONS ON AUTOMATIC CONTROL,VOL.46,NO.46, 2001.6
[30]Zhiqiang Gao, Fuzyy Control—K.Passino and S.Yurkovich(Reading,MA:Addision Wesley Longman,Inc.,1998), IEEE TRANSACTIONS ON AUTOMATIC CONTROL,VOL,45,NO.10,
2000.10
[31]Frederic Hamelin,Dominique Sauter, Robust fault detction ini uncertain dynamic systems,Automatica,2000.36
[32]Walmir M,Caminhas,Ricardo H.C.Takahashi Dep.of Electrical Engineering, Federal University of Minas Gerais Av.Antnio Carlos 6627, Horizontc-MG-Brazil, Dynamic System Failure Detection and Diagnosis Employing Sliding Mode Observers and Fuzzy Neural Networks
[33]NILS. Nilsson. Artificial Intelligence A New Synthesis [M]. China Machine Press, 1999.
[34] Rossi Todd M, Braun James E. Statistical rule-based fault detection and diagnostic method for vapor compression air conditioners. HVAC&R Research,v3 nl,1997
[35]Narayanan, Ajit, Jin Yuanping , Object-oriented representations, causal reasoning and expert systems. Expert Systems, v8 nl,1991.
[36]Leung David, Romagnoli Jose. Dynamic probabilistic model-based expert system for fault diagnosis. Computers and Chemical Engineering, v24 n11,2000.
[37]Grossberg S. Nonlinear Neural Networks: Principles, Machines and Architectures[J].Neural Networks,1998,(1):15-57.
[38]Blum E K, Li L K. Approximation Theory and Feedforward Networks[J]. Neural Networks ,1991,4(4):511-515.