A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively ...A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively used and still have considerable potential. In recent years, methods based on deep neural networks have made significant breakthroughs, and fault diagnosis methods for industrial processes based on deep learning have attracted considerable research attention. Therefore, we propose a fusion deeplearning algorithm based on a fully convolutional neural network(FCN) to extract features and build models to correctly diagnose all types of faults. We use long short-term memory(LSTM) units to expand our proposed FCN so that our proposed deep learning model can better extract the time-domain features of chemical process data. We also introduce the attention mechanism into the model, aimed at highlighting the importance of features, which is significant for the fault diagnosis of chemical processes with many features. When applied to the benchmark Tennessee Eastman process, our proposed model exhibits impressive performance, demonstrating the effectiveness of the attention-based LSTM FCN in chemical process fault diagnosis.展开更多
A hybrid method for synthesizing antenna＇s three dimensional （3D） pattern is proposed to obtain the low sidelobe feature of truncated cone conformal phased arrays. In this method, the elements of truncated cone con...A hybrid method for synthesizing antenna＇s three dimensional （3D） pattern is proposed to obtain the low sidelobe feature of truncated cone conformal phased arrays. In this method, the elements of truncated cone conformal phased arrays are projected to the tangent plane in one generatrix of the truncated cone. Then two dimensional （2D） Chebyshev amplitude distribution optimization is respectively used in two mutual vertical directions of the tangent plane. According to the location of the elements, the excitation current amplitude distribution of each element on the conformal structure is derived reversely, then the excitation current amplitude is further optimized by using the genetic algorithm （GA）. A truncated cone problem with 8x8 elements on it, and a 3D pattern desired side lobe level （SLL） up to 35 dB, is studied. By using the hybrid method, the optimal goal is accomplished with acceptable CPU time, which indicates that this hybrid method for the low sidelobe synthesis is feasible.展开更多
传统的Pareto支配关系在高维目标空间存在固有缺陷,而一些改进的支配方法在平衡高维目标解群的收敛性与多样性上尚有提升空间.基于此,提出一种参考向量关联区域(小生境)自动缩减的支配关系A2R(dominance relation based on the Automati...传统的Pareto支配关系在高维目标空间存在固有缺陷,而一些改进的支配方法在平衡高维目标解群的收敛性与多样性上尚有提升空间.基于此,提出一种参考向量关联区域(小生境)自动缩减的支配关系A2R(dominance relation based on the Automatically reduced region Associated with the Reference vector).该支配方法在进化全过程中逐代缩减小生境规模,从而实现收敛性与多样性自动平衡,而且不引入额外参数.另外,提出利用基于Lp-范式(p=1/M,M为目标数)的拥挤距离度量高维目标解群的多样性.将上述两种策略嵌入到经典的NSGA-II(Nondominated Sorting Genetic Algorithm II)框架,设计一种基于A2R支配关系的高维多目标进化算法MaOEA/A2R(Many-Objective Evolutionary Algorithm base on A2R).该算法与其他5种代表性的高维多目标进化算法一同在5-、10-、15-和20-目标的DTLZ(benchmark MOP proposed by Deb,Thiele,Lau-manns,and Zitzler)和WFG(benchmark MOP pro-posed by Walking Fish Group)基准测试问题上进行IGD(Inverted Generational Distance)和HV(Hyper Volume)性能测试.结果表明,MaOEA/A2R算法总体上具有较好的收敛性和多样性.由此表明,MaOEA/A2R是一种颇具前景的高维多目标进化算法.展开更多
Cocurrent gas-solid downer reactors have many applications in industry because they possess the tech- nological advantages of a lower pressure drop, shorter residence time, and less solid backmixing when compared with...Cocurrent gas-solid downer reactors have many applications in industry because they possess the tech- nological advantages of a lower pressure drop, shorter residence time, and less solid backmixing when compared with traditional circulating fluidized bed risers. By introducing the concept of particle clusters explicitly, a one-dimensional model with consideration of the interphase interactions between the fluid and particles at both microscale and mesoscale is formulated for concurrent downward gas-solid flow according to energy-minimization multi-scale （EMMS） theory. A unified stability condition is proposed for the differently developed sections of gas-solid flow according to the principle of the compromise in competition between dominant mechanisms. By optimizing the number density of particle clusters with respect to the stability condition, the formulated model can be numerically solved without introducing cluster-specific empirical correlations. The EMMS-based model predicts well the axial hydrodynamics of cocurrent gas-solid downers and is expected to have a wider range of applications than the existing cluster-based models.展开更多
文摘A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively used and still have considerable potential. In recent years, methods based on deep neural networks have made significant breakthroughs, and fault diagnosis methods for industrial processes based on deep learning have attracted considerable research attention. Therefore, we propose a fusion deeplearning algorithm based on a fully convolutional neural network(FCN) to extract features and build models to correctly diagnose all types of faults. We use long short-term memory(LSTM) units to expand our proposed FCN so that our proposed deep learning model can better extract the time-domain features of chemical process data. We also introduce the attention mechanism into the model, aimed at highlighting the importance of features, which is significant for the fault diagnosis of chemical processes with many features. When applied to the benchmark Tennessee Eastman process, our proposed model exhibits impressive performance, demonstrating the effectiveness of the attention-based LSTM FCN in chemical process fault diagnosis.
基金supported by the Fundamental Research Funds for the Central Universities(YWF-13D2-XX-13)the National High-tech Research and Development Program(863 Program)(2008AA121802)
文摘A hybrid method for synthesizing antenna＇s three dimensional （3D） pattern is proposed to obtain the low sidelobe feature of truncated cone conformal phased arrays. In this method, the elements of truncated cone conformal phased arrays are projected to the tangent plane in one generatrix of the truncated cone. Then two dimensional （2D） Chebyshev amplitude distribution optimization is respectively used in two mutual vertical directions of the tangent plane. According to the location of the elements, the excitation current amplitude distribution of each element on the conformal structure is derived reversely, then the excitation current amplitude is further optimized by using the genetic algorithm （GA）. A truncated cone problem with 8x8 elements on it, and a 3D pattern desired side lobe level （SLL） up to 35 dB, is studied. By using the hybrid method, the optimal goal is accomplished with acceptable CPU time, which indicates that this hybrid method for the low sidelobe synthesis is feasible.
文摘传统的Pareto支配关系在高维目标空间存在固有缺陷,而一些改进的支配方法在平衡高维目标解群的收敛性与多样性上尚有提升空间.基于此,提出一种参考向量关联区域(小生境)自动缩减的支配关系A2R(dominance relation based on the Automatically reduced region Associated with the Reference vector).该支配方法在进化全过程中逐代缩减小生境规模,从而实现收敛性与多样性自动平衡,而且不引入额外参数.另外,提出利用基于Lp-范式(p=1/M,M为目标数)的拥挤距离度量高维目标解群的多样性.将上述两种策略嵌入到经典的NSGA-II(Nondominated Sorting Genetic Algorithm II)框架,设计一种基于A2R支配关系的高维多目标进化算法MaOEA/A2R(Many-Objective Evolutionary Algorithm base on A2R).该算法与其他5种代表性的高维多目标进化算法一同在5-、10-、15-和20-目标的DTLZ(benchmark MOP proposed by Deb,Thiele,Lau-manns,and Zitzler)和WFG(benchmark MOP pro-posed by Walking Fish Group)基准测试问题上进行IGD(Inverted Generational Distance)和HV(Hyper Volume)性能测试.结果表明,MaOEA/A2R算法总体上具有较好的收敛性和多样性.由此表明,MaOEA/A2R是一种颇具前景的高维多目标进化算法.
基金We appreciate financial support from the Strategic Prior- ity Research Program of the Chinese Academy of Sciences （No. XDA07080400） and the Natural Science Foundation of China （Nos. 21376244 and 91334107）.
文摘Cocurrent gas-solid downer reactors have many applications in industry because they possess the tech- nological advantages of a lower pressure drop, shorter residence time, and less solid backmixing when compared with traditional circulating fluidized bed risers. By introducing the concept of particle clusters explicitly, a one-dimensional model with consideration of the interphase interactions between the fluid and particles at both microscale and mesoscale is formulated for concurrent downward gas-solid flow according to energy-minimization multi-scale （EMMS） theory. A unified stability condition is proposed for the differently developed sections of gas-solid flow according to the principle of the compromise in competition between dominant mechanisms. By optimizing the number density of particle clusters with respect to the stability condition, the formulated model can be numerically solved without introducing cluster-specific empirical correlations. The EMMS-based model predicts well the axial hydrodynamics of cocurrent gas-solid downers and is expected to have a wider range of applications than the existing cluster-based models.
