Fault diagnosis and monitoring are very important for complex chemical process. There are numerous methods that have been studied in this field, in which the effective visualization method is still challenging. In ord...Fault diagnosis and monitoring are very important for complex chemical process. There are numerous methods that have been studied in this field, in which the effective visualization method is still challenging. In order to get a better visualization effect, a novel fault diagnosis method which combines self-organizing map (SOM) with Fisher discriminant analysis (FDA) is proposed. FDA can reduce the dimension of the data in terms of maximizing the separability of the classes. After feature extraction by FDA, SOM can distinguish the different states on the output map clearly and it can also be employed to monitor abnormal states. Tennessee Eastman (TE) process is employed to illustrate the fault diagnosis and monitoring performance of the proposed method. The result shows that the SOM integrated with FDA method is efficient and capable for real-time monitoring and fault diagnosis in complex chemical process.展开更多
A method for incorporation of controlling the heat exchanger networks with or without splits is proposed by integrating mathemati-cal programming and knowledge engineering. The simultaneous optimal mathematical model ...A method for incorporation of controlling the heat exchanger networks with or without splits is proposed by integrating mathemati-cal programming and knowledge engineering. The simultaneous optimal mathematical model is established. This method can be practically used in the integration of large-scale heat exchanger networks, not only to synthesize automatically but also to satisfy the requirement of struc-tural controllability with more objective human intervention.展开更多
In recent decades,materials science has experienced rapid development and posed increasingly high requirements for the characterizations of structures,properties,and performances.Herein,we report on our recent establi...In recent decades,materials science has experienced rapid development and posed increasingly high requirements for the characterizations of structures,properties,and performances.Herein,we report on our recent establishment of a multi-domain(energy,space,time)highresolution platform for integrated spectroscopy and microscopy characterizations,offering an unprecedented way to analyze materials in terms of spectral(energy)and spatial mapping as well as temporal evolution.We present several proof-of-principle results collected on this platform,including in-situ Raman imaging(high-resolution Raman,polarization Raman,low-wavenumber Raman),time-resolved photoluminescence imaging,and photoelectrical performance imaging.It can be envisioned that our newly established platform would be very powerful and effective in the multi-domain high-resolution characterizations of various materials of photoelectrochemical importance in the near future.展开更多
Samples of fog water collected in the area of Guangzhou during February, March and April of 2005 are used in this work to study the chemical composition of fog water in polluting fog there. Three typical episodes of p...Samples of fog water collected in the area of Guangzhou during February, March and April of 2005 are used in this work to study the chemical composition of fog water in polluting fog there. Three typical episodes of polluting fog are analyzed in terms of ionic concentration and their possible sources. It is found that the concentration of various ions in fog water is much higher than those in rainwater. Fog not only blocks visual range but contains liquid particles that result in high degree of pollution and are very harmful to human health. SO4= is the anion with the highest concentration in fog water, followed by NO3-. For the cation, Ca++ and NH4+ are the highest in concentration. It is then known that rainwater is more acidic than fog water, indicating that ionic concentration of fog water is much higher than that of rainwater, but there are much more buffering materials in fog water, like NH4+ and Ca++. There is significant enrichment of Ca++, SO4=, and Mg++ in fog water. In the Guangzhou area, fog water from polluting fog is mainly influenced continental environment and human activity. The episodes of serious fog pollution during the time have immediate relationships with the presence of abundant water vapor and large amount of polluting aerosol particles.展开更多
In machine learning,randomness is a crucial factor in the success of ensemble learning,and it can be injected into tree-based ensembles by rotating the feature space.However,it is a common practice to rotate the featu...In machine learning,randomness is a crucial factor in the success of ensemble learning,and it can be injected into tree-based ensembles by rotating the feature space.However,it is a common practice to rotate the feature space randomly.Thus,a large number of trees are required to ensure the performance of the ensemble model.This random rotation method is theoretically feasible,but it requires massive computing resources,potentially restricting its applications.A multimodal genetic algorithm based rotation forest(MGARF)algorithm is proposed in this paper to solve this problem.It is a tree-based ensemble learning algorithm for classification,taking advantage of the characteristic of trees to inject randomness by feature rotation.However,this algorithm attempts to select a subset of more diverse and accurate base learners using the multimodal optimization method.The classification accuracy of the proposed MGARF algorithm was evaluated by comparing it with the original random forest and random rotation ensemble methods on 23 UCI classification datasets.Experimental results show that the MGARF method outperforms the other methods,and the number of base learners in MGARF models is much fewer.展开更多
The chemical composition of rainwater has been studied in a karst rural area from September 2012 to August 2013 in Guizhou Province,Southwest China.The results indicated that the VWM value of p H was 5.4,varied from 4...The chemical composition of rainwater has been studied in a karst rural area from September 2012 to August 2013 in Guizhou Province,Southwest China.The results indicated that the VWM value of p H was 5.4,varied from 4.6 to 6.9.Ca^(2+)and NH_4^+were the major cations,and SO_4^(2-)was the dominant anion.Neutralization factors show that the acid was mainly neutralized by Ca^(2+),NH_4^+and Mg^(2+).Investigations of correlation coefficients and enrichment factors revealed that Ca^(2+)and Mg^(2+)were mainly crust origins,and NH_4^+was from agriculture and livestock manure.SO_4^(2-)and NO_3^-were mainly from anthropogenic sources.展开更多
Fault diagnosis plays an important role in complicated industrial process.It is a challenging task to detect,identify and locate faults quickly and accurately for large-scale process system.To solve the problem,a nove...Fault diagnosis plays an important role in complicated industrial process.It is a challenging task to detect,identify and locate faults quickly and accurately for large-scale process system.To solve the problem,a novel Multi Boost-based integrated ENN(extension neural network) fault diagnosis method is proposed.Fault data of complicated chemical process have some difficult-to-handle characteristics,such as high-dimension,non-linear and non-Gaussian distribution,so we use margin discriminant projection(MDP) algorithm to reduce dimensions and extract main features.Then,the affinity propagation(AP) clustering method is used to select core data and boundary data as training samples to reduce memory consumption and shorten learning time.Afterwards,an integrated ENN classifier based on Multi Boost strategy is constructed to identify fault types.The artificial data sets are tested to verify the effectiveness of the proposed method and make a detailed sensitivity analysis for the key parameters.Finally,a real industrial system—Tennessee Eastman(TE) process is employed to evaluate the performance of the proposed method.And the results show that the proposed method is efficient and capable to diagnose various types of faults in complicated chemical process.展开更多
Thirty sediment subsamples were recovered from the Iheya North hydrothermal field （with an average of 38 m away from the hydrothermal vent） in the middle Okinawa Trough. Samples were obtained by the ROV （Remote Ope...Thirty sediment subsamples were recovered from the Iheya North hydrothermal field （with an average of 38 m away from the hydrothermal vent） in the middle Okinawa Trough. Samples were obtained by the ROV （Remote Operated Vehicle） Faxian during the virgin cruise of the R/V Kexue in 2014 with the application of push cores. The chemical compositions of the sediments show that the hydrothermal sediments near the hydrothermal vent are mainly composed of SO3, ZnO and Fe203. Moreover, the hydrothermal sediments are also highly enriched in Pb, As, Sb, Hg, Se, Ag, Ba, Mo and Cd comparing with previous analysis results. On the other hand, the concentrations of St, Hg andAg in studied sediments are strongly and positively correlated, these elements can be used as an hydrothermal indicator. In addition, a factor analysis of the sediments suggested that the sediments were mainly influenced by hydrothermal origin, and terrestrial and biogenic input are limited in studied area. It is also suggested that different stages of crystallization were involved in the formation of hydrothermal chimney from factor analysis.展开更多
Monolithic integration of resonant tunneling diodes (RTDs) and high electron mobility transistors (HEMTs) is an important development direction of ultra-high speed integrated circuit. A kind of top-RTD and bottom-HEMT...Monolithic integration of resonant tunneling diodes (RTDs) and high electron mobility transistors (HEMTs) is an important development direction of ultra-high speed integrated circuit. A kind of top-RTD and bottom-HEMT material structure is epitaxied on InP substrate through molecular beam epitaxy. Based on wet chemical etching, metal lift-off and air bridge interconnection technology, RTD and HEMT are fabricated simultaneously. The peak-to-valley current ratio of RTD is 7.7 and the peak voltage is 0.33 V at room temperature. The pinch-off voltage is -0.5 V and the current gain cut-frequency is 30 GHz for a 1.0 μm gate length depletion mode HEMT. The two devices are conformable in current magnitude, which is suitable for the construction of various RTD/HEMT monolithic integration logic circuits.展开更多
基金Supported by the National Basic Research Program of China （2013CB733600）, the National Natural Science Foundation of China （21176073）, the Doctoral Fund of Ministry of Education of China （20090074110005）, the Program for New Century Excellent Talents in University （NCET-09-0346）, Shu Guang Project （09SG29） and the Fundamental Research Funds for the Central Universities.
文摘Fault diagnosis and monitoring are very important for complex chemical process. There are numerous methods that have been studied in this field, in which the effective visualization method is still challenging. In order to get a better visualization effect, a novel fault diagnosis method which combines self-organizing map (SOM) with Fisher discriminant analysis (FDA) is proposed. FDA can reduce the dimension of the data in terms of maximizing the separability of the classes. After feature extraction by FDA, SOM can distinguish the different states on the output map clearly and it can also be employed to monitor abnormal states. Tennessee Eastman (TE) process is employed to illustrate the fault diagnosis and monitoring performance of the proposed method. The result shows that the SOM integrated with FDA method is efficient and capable for real-time monitoring and fault diagnosis in complex chemical process.
基金Supported by the Natural Science Foundation of Guangdong Province (No. 990630) and the State Major Basic Research Development Program (No. G20000263).
文摘A method for incorporation of controlling the heat exchanger networks with or without splits is proposed by integrating mathemati-cal programming and knowledge engineering. The simultaneous optimal mathematical model is established. This method can be practically used in the integration of large-scale heat exchanger networks, not only to synthesize automatically but also to satisfy the requirement of struc-tural controllability with more objective human intervention.
基金supported by the National Key Research and Development Program of China(No.2016YFA0200602,No.2017YFA0303500,and No.2018YFA0208702)the National Natural Science Foundation of China(No.21573211,No.21633007,No.21803067,and No.91950207)+1 种基金the Anhui Initiative in Quantum Information Technologies(AHY090200)the USTC-NSRL Joint Funds(UN2018LHJJ).
文摘In recent decades,materials science has experienced rapid development and posed increasingly high requirements for the characterizations of structures,properties,and performances.Herein,we report on our recent establishment of a multi-domain(energy,space,time)highresolution platform for integrated spectroscopy and microscopy characterizations,offering an unprecedented way to analyze materials in terms of spectral(energy)and spatial mapping as well as temporal evolution.We present several proof-of-principle results collected on this platform,including in-situ Raman imaging(high-resolution Raman,polarization Raman,low-wavenumber Raman),time-resolved photoluminescence imaging,and photoelectrical performance imaging.It can be envisioned that our newly established platform would be very powerful and effective in the multi-domain high-resolution characterizations of various materials of photoelectrochemical importance in the near future.
基金Natural Science Foundation of China (40375002, 40418008, 40775011, U0733004)Project 863 (2006AA06A306, 2006AA06A308)+3 种基金National Basic Research Program of China (973 Program):2005CB422207Natural Science Foundation of Guangdong Province (033029)Project of Key Scientific Research of Guangdong Province (2004A30401002, 2005B32601011)Project of Applied Fundamental Research of Guangzhou (2004J1-0021)
文摘Samples of fog water collected in the area of Guangzhou during February, March and April of 2005 are used in this work to study the chemical composition of fog water in polluting fog there. Three typical episodes of polluting fog are analyzed in terms of ionic concentration and their possible sources. It is found that the concentration of various ions in fog water is much higher than those in rainwater. Fog not only blocks visual range but contains liquid particles that result in high degree of pollution and are very harmful to human health. SO4= is the anion with the highest concentration in fog water, followed by NO3-. For the cation, Ca++ and NH4+ are the highest in concentration. It is then known that rainwater is more acidic than fog water, indicating that ionic concentration of fog water is much higher than that of rainwater, but there are much more buffering materials in fog water, like NH4+ and Ca++. There is significant enrichment of Ca++, SO4=, and Mg++ in fog water. In the Guangzhou area, fog water from polluting fog is mainly influenced continental environment and human activity. The episodes of serious fog pollution during the time have immediate relationships with the presence of abundant water vapor and large amount of polluting aerosol particles.
基金Project(61603274)supported by the National Natural Science Foundation of ChinaProject(2017KJ249)supported by the Research Project of Tianjin Municipal Education Commission,China。
文摘In machine learning,randomness is a crucial factor in the success of ensemble learning,and it can be injected into tree-based ensembles by rotating the feature space.However,it is a common practice to rotate the feature space randomly.Thus,a large number of trees are required to ensure the performance of the ensemble model.This random rotation method is theoretically feasible,but it requires massive computing resources,potentially restricting its applications.A multimodal genetic algorithm based rotation forest(MGARF)algorithm is proposed in this paper to solve this problem.It is a tree-based ensemble learning algorithm for classification,taking advantage of the characteristic of trees to inject randomness by feature rotation.However,this algorithm attempts to select a subset of more diverse and accurate base learners using the multimodal optimization method.The classification accuracy of the proposed MGARF algorithm was evaluated by comparing it with the original random forest and random rotation ensemble methods on 23 UCI classification datasets.Experimental results show that the MGARF method outperforms the other methods,and the number of base learners in MGARF models is much fewer.
基金supported by the National Natural Science Foundation of China(Grant Nos.4132501041661144029)National Key Basic Research Program of China(Grant No.2013CB956703)
文摘The chemical composition of rainwater has been studied in a karst rural area from September 2012 to August 2013 in Guizhou Province,Southwest China.The results indicated that the VWM value of p H was 5.4,varied from 4.6 to 6.9.Ca^(2+)and NH_4^+were the major cations,and SO_4^(2-)was the dominant anion.Neutralization factors show that the acid was mainly neutralized by Ca^(2+),NH_4^+and Mg^(2+).Investigations of correlation coefficients and enrichment factors revealed that Ca^(2+)and Mg^(2+)were mainly crust origins,and NH_4^+was from agriculture and livestock manure.SO_4^(2-)and NO_3^-were mainly from anthropogenic sources.
基金Project (61203021) supported by the National Natural Science Foundation of ChinaProject (2011216011) supported by the Key Science and Technology Program of Liaoning Province,China+1 种基金Project (2013020024) supported by the Natural Science Foundation of Liaoning Province,ChinaProject (LJQ2015061) supported by the Program for Liaoning Excellent Talents in Universities,China
文摘Fault diagnosis plays an important role in complicated industrial process.It is a challenging task to detect,identify and locate faults quickly and accurately for large-scale process system.To solve the problem,a novel Multi Boost-based integrated ENN(extension neural network) fault diagnosis method is proposed.Fault data of complicated chemical process have some difficult-to-handle characteristics,such as high-dimension,non-linear and non-Gaussian distribution,so we use margin discriminant projection(MDP) algorithm to reduce dimensions and extract main features.Then,the affinity propagation(AP) clustering method is used to select core data and boundary data as training samples to reduce memory consumption and shorten learning time.Afterwards,an integrated ENN classifier based on Multi Boost strategy is constructed to identify fault types.The artificial data sets are tested to verify the effectiveness of the proposed method and make a detailed sensitivity analysis for the key parameters.Finally,a real industrial system—Tennessee Eastman(TE) process is employed to evaluate the performance of the proposed method.And the results show that the proposed method is efficient and capable to diagnose various types of faults in complicated chemical process.
基金Supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(Nos.XDA11030301,XDA11040301)
文摘Thirty sediment subsamples were recovered from the Iheya North hydrothermal field （with an average of 38 m away from the hydrothermal vent） in the middle Okinawa Trough. Samples were obtained by the ROV （Remote Operated Vehicle） Faxian during the virgin cruise of the R/V Kexue in 2014 with the application of push cores. The chemical compositions of the sediments show that the hydrothermal sediments near the hydrothermal vent are mainly composed of SO3, ZnO and Fe203. Moreover, the hydrothermal sediments are also highly enriched in Pb, As, Sb, Hg, Se, Ag, Ba, Mo and Cd comparing with previous analysis results. On the other hand, the concentrations of St, Hg andAg in studied sediments are strongly and positively correlated, these elements can be used as an hydrothermal indicator. In addition, a factor analysis of the sediments suggested that the sediments were mainly influenced by hydrothermal origin, and terrestrial and biogenic input are limited in studied area. It is also suggested that different stages of crystallization were involved in the formation of hydrothermal chimney from factor analysis.
基金Supported by National Natural Science Foundation of China (No. 60876009)Tianjin Research Program of Application Foundation and Advanced Technology (No. 09JCZDJC16600)
文摘Monolithic integration of resonant tunneling diodes (RTDs) and high electron mobility transistors (HEMTs) is an important development direction of ultra-high speed integrated circuit. A kind of top-RTD and bottom-HEMT material structure is epitaxied on InP substrate through molecular beam epitaxy. Based on wet chemical etching, metal lift-off and air bridge interconnection technology, RTD and HEMT are fabricated simultaneously. The peak-to-valley current ratio of RTD is 7.7 and the peak voltage is 0.33 V at room temperature. The pinch-off voltage is -0.5 V and the current gain cut-frequency is 30 GHz for a 1.0 μm gate length depletion mode HEMT. The two devices are conformable in current magnitude, which is suitable for the construction of various RTD/HEMT monolithic integration logic circuits.
