This work presents the “n<sup>th</sup>-Order Feature Adjoint Sensitivity Analysis Methodology for Nonlinear Systems” (abbreviated as “n<sup>th</sup>-FASAM-N”), which will be shown to be the...This work presents the “n<sup>th</sup>-Order Feature Adjoint Sensitivity Analysis Methodology for Nonlinear Systems” (abbreviated as “n<sup>th</sup>-FASAM-N”), which will be shown to be the most efficient methodology for computing exact expressions of sensitivities, of any order, of model responses with respect to features of model parameters and, subsequently, with respect to the model’s uncertain parameters, boundaries, and internal interfaces. The unparalleled efficiency and accuracy of the n<sup>th</sup>-FASAM-N methodology stems from the maximal reduction of the number of adjoint computations (which are considered to be “large-scale” computations) for computing high-order sensitivities. When applying the n<sup>th</sup>-FASAM-N methodology to compute the second- and higher-order sensitivities, the number of large-scale computations is proportional to the number of “model features” as opposed to being proportional to the number of model parameters (which are considerably more than the number of features).When a model has no “feature” functions of parameters, but only comprises primary parameters, the n<sup>th</sup>-FASAM-N methodology becomes identical to the extant n<sup>th</sup> CASAM-N (“n<sup>th</sup>-Order Comprehensive Adjoint Sensitivity Analysis Methodology for Nonlinear Systems”) methodology. Both the n<sup>th</sup>-FASAM-N and the n<sup>th</sup>-CASAM-N methodologies are formulated in linearly increasing higher-dimensional Hilbert spaces as opposed to exponentially increasing parameter-dimensional spaces thus overcoming the curse of dimensionality in sensitivity analysis of nonlinear systems. Both the n<sup>th</sup>-FASAM-N and the n<sup>th</sup>-CASAM-N are incomparably more efficient and more accurate than any other methods (statistical, finite differences, etc.) for computing exact expressions of response sensitivities of any order with respect to the model’s features and/or primary uncertain parameters, boundaries, and internal interfaces.展开更多
Many countries throughout the world have experienced large earthquakes,which cause building damage or collapse.After such earthquakes,structures must be inspected rapidly to judge whether they are safe to reoccupy.To ...Many countries throughout the world have experienced large earthquakes,which cause building damage or collapse.After such earthquakes,structures must be inspected rapidly to judge whether they are safe to reoccupy.To facilitate the inspection process,the authors previously developed a rapid building safety assessment system using sparse acceleration measurements for steel framed buildings.The proposed system modeled nonlinearity in the measurement data using a calibrated simplified lumped-mass model and convolutional neural networks(CNNs),based on which the buildinglevel damage index was estimated rapidly after earthquakes.The proposed system was validated for a nonlinear 3D numerical model of a five-story steel building,and later for a large-scale specimen of an 18-story building in Japan tested on the E-Defense shaking table.However,the applicability of the safety assessment system for reinforced concrete(RC)structures with complex hysteretic material nonlinearity has yet to be explored;the previous approach based on a simplified lumpedmass model with a Bouc-Wen hysteretic model does not accurately represent the inherent nonlinear behavior and resulting damage states of RC structures.This study extends the rapid building safety assessment system to low-rise RC moment resisting frame structures representing typical residential apartments in Japan.First,a safety classification for RC structures based on a damage index consistent with the current state of practice is defined.Then,a 3D nonlinear numerical model of a two-story moment frame structure is created.A simplified lumped-mass nonlinear model is developed and calibrated using the 3D model,incorporating the Takeda degradation model for the RC material nonlinearity.This model is used to simulate the seismic response and associated damage sensitive features(DSF)for random ground motion.The resulting database of responses is used to train a convolutional neural network(CNN)that performs rapid safety assessment.The developed system is validated using the 3D nonlinear analysis model subjected to historical earthquakes.The results indicate the applicability of the proposed system for RC structures following seismic events.展开更多
A method combining information entropy and radial basis function network is proposed for fault automatic diagnosis of reciprocating compressors.Aiming at the current situation that the accuracy rate of reciprocating c...A method combining information entropy and radial basis function network is proposed for fault automatic diagnosis of reciprocating compressors.Aiming at the current situation that the accuracy rate of reciprocating compressor fault diagnosis which depends on manual work in engineering is very low,we apply information entropy evaluation to select the sensitive features and make clear the corresponding relationship of characteristic parameters and failures.This method could reduce the feature dimension.Then,a complete fault diagnosis architecture has been built combining with radial basis function network which has the fast and efficient characteristics.According to the test results using experimental and engineering data,it is observed that the proposed fault diagnosis method improves the accuracy of fault automatic diagnosis effectively and it could improve the practicability of the monitoring system.展开更多
The classification of pathological voice from healthy voice was studied based upon 27 acoustic features derived from a single sound signal of vowel /a:/. First, the feature space was transferred to reduce the data dim...The classification of pathological voice from healthy voice was studied based upon 27 acoustic features derived from a single sound signal of vowel /a:/. First, the feature space was transferred to reduce the data dimension by principle component analysis (PCA). Then the voice samples were classified according to the reduced PCA parameters by support vector machine (SVM) using radial basis function (RBF) as a kernel function. Meanwhile, by changing the ratio of opposite class samples, the accuracy under different features combinations was tested. Experimental data were provided by the voice database of Massachusetts Eye and Ear Infirmary (MEEI) in which 216 vowel /a:/ samples were collected from subjects of healthy and pathological cases, and tested with 5 fold cross-validation method. The result shows the positive rate of pathological voices was improved from 92% to 98% through the PCA method. STD, Fatr, Tasm, NHR, SEG, and PER are pathology sensitive features in illness detection. Using these sensitive features the accuracy of detection of pathological voice from healthy voice can reach 97%.展开更多
Fault diagnosis of fuel cells often focuses on single faults,leading to lower accuracy in diagnosing simultaneous faults.This paper researches a data-driven diagnostic method for both single and simultaneous faults,ai...Fault diagnosis of fuel cells often focuses on single faults,leading to lower accuracy in diagnosing simultaneous faults.This paper researches a data-driven diagnostic method for both single and simultaneous faults,aiming to establish an efficient online fault diagnosis approach.Firstly,a theoretical model of a proton exchange membrane fuel cell(PEMFC)system is established.Based on this,a radial basis function(RBF)neural network surrogate model is designed to improve computational efficiency.The average relative error across all features between the surrogate model and the theoretical model is below 1%.Subsequently,Sobol's global sensitivity analysis is used to analyse the relationship between PEMFC system faults and various characteristic parameters during real-time operation.The sensitive feature set related to different faults in the PEMFC system is then identified.Finally,an adaptive diagnostic strategy is proposed,and a sensitivity-based diagnostic algorithm is established.Compared with other common single-label and multi-label diagnostic methods,the sensitivity-based diagnostic algorithm achieves an F1_Score of 99.1%on single-fault data,cutting training time by more than 80%.In scenarios with simultaneous faults and sparse data,the method achieves an accuracy of 92.5%,which is 7.5%higher than that achieved by the best multi-label method.展开更多
Structural health monitoring(SHM)is a vast,interdisciplinary research field whose literature spans several decades with focusing on condition assessment of different types of structures including aerospace,mechanical ...Structural health monitoring(SHM)is a vast,interdisciplinary research field whose literature spans several decades with focusing on condition assessment of different types of structures including aerospace,mechanical and civil structures.The need for quantitative global damage detection methods that can be applied to complex structures has led to vibration-based inspection.Statistical time series methods for SHM form an important and rapidly evolving category within the broader vibration-based methods.In the literature on the structural damage detection,many time series-based methods have been proposed.When a considered time series model approximates the vibration response of a structure and model coefficients or residual error are obtained,any deviations in these coefficients or residual error can be inferred as an indication of a change or damage in the structure.Depending on the technique employed,various damage sensitive features have been proposed to capture the deviations.This paper reviews the application of time series analysis for SHM.The different types of time series analysis are described,and the basic principles are explained in detail.Then,the literature is reviewed based on how a damage sensitive feature is formed.In addition,some investigations that have attempted to modify and/or combine time series analysis with other approaches for better damage identification are presented.展开更多
We present a new method for feature preserving mesh simplification based on feature sensitive （FS） metric. Previous quadric error based approach is extended to a high-dimensional FS space so as to measure the geomet...We present a new method for feature preserving mesh simplification based on feature sensitive （FS） metric. Previous quadric error based approach is extended to a high-dimensional FS space so as to measure the geometric distance together with normal deviation. As the normal direction of a surface point is uniquely determined by the position in Euclidian space, we employ a two-step linear optimization scheme to efficiently derive the constrained optimal target point. We demonstrate that our algorithm can preserve features more precisely under the global geometric properties, and can naturally retain more triangular patches on the feature regions without special feature detection procedure during the simplification process. Taking the advantage of the blow-up phenomenon in FS space, we design an error weight that can produce more suitable results. We also show that Hausdorff distance is markedly reduced during FS simplification.展开更多
文摘This work presents the “n<sup>th</sup>-Order Feature Adjoint Sensitivity Analysis Methodology for Nonlinear Systems” (abbreviated as “n<sup>th</sup>-FASAM-N”), which will be shown to be the most efficient methodology for computing exact expressions of sensitivities, of any order, of model responses with respect to features of model parameters and, subsequently, with respect to the model’s uncertain parameters, boundaries, and internal interfaces. The unparalleled efficiency and accuracy of the n<sup>th</sup>-FASAM-N methodology stems from the maximal reduction of the number of adjoint computations (which are considered to be “large-scale” computations) for computing high-order sensitivities. When applying the n<sup>th</sup>-FASAM-N methodology to compute the second- and higher-order sensitivities, the number of large-scale computations is proportional to the number of “model features” as opposed to being proportional to the number of model parameters (which are considerably more than the number of features).When a model has no “feature” functions of parameters, but only comprises primary parameters, the n<sup>th</sup>-FASAM-N methodology becomes identical to the extant n<sup>th</sup> CASAM-N (“n<sup>th</sup>-Order Comprehensive Adjoint Sensitivity Analysis Methodology for Nonlinear Systems”) methodology. Both the n<sup>th</sup>-FASAM-N and the n<sup>th</sup>-CASAM-N methodologies are formulated in linearly increasing higher-dimensional Hilbert spaces as opposed to exponentially increasing parameter-dimensional spaces thus overcoming the curse of dimensionality in sensitivity analysis of nonlinear systems. Both the n<sup>th</sup>-FASAM-N and the n<sup>th</sup>-CASAM-N are incomparably more efficient and more accurate than any other methods (statistical, finite differences, etc.) for computing exact expressions of response sensitivities of any order with respect to the model’s features and/or primary uncertain parameters, boundaries, and internal interfaces.
基金supported by a fellowship from Design Department of Taisei Corporation。
文摘Many countries throughout the world have experienced large earthquakes,which cause building damage or collapse.After such earthquakes,structures must be inspected rapidly to judge whether they are safe to reoccupy.To facilitate the inspection process,the authors previously developed a rapid building safety assessment system using sparse acceleration measurements for steel framed buildings.The proposed system modeled nonlinearity in the measurement data using a calibrated simplified lumped-mass model and convolutional neural networks(CNNs),based on which the buildinglevel damage index was estimated rapidly after earthquakes.The proposed system was validated for a nonlinear 3D numerical model of a five-story steel building,and later for a large-scale specimen of an 18-story building in Japan tested on the E-Defense shaking table.However,the applicability of the safety assessment system for reinforced concrete(RC)structures with complex hysteretic material nonlinearity has yet to be explored;the previous approach based on a simplified lumpedmass model with a Bouc-Wen hysteretic model does not accurately represent the inherent nonlinear behavior and resulting damage states of RC structures.This study extends the rapid building safety assessment system to low-rise RC moment resisting frame structures representing typical residential apartments in Japan.First,a safety classification for RC structures based on a damage index consistent with the current state of practice is defined.Then,a 3D nonlinear numerical model of a two-story moment frame structure is created.A simplified lumped-mass nonlinear model is developed and calibrated using the 3D model,incorporating the Takeda degradation model for the RC material nonlinearity.This model is used to simulate the seismic response and associated damage sensitive features(DSF)for random ground motion.The resulting database of responses is used to train a convolutional neural network(CNN)that performs rapid safety assessment.The developed system is validated using the 3D nonlinear analysis model subjected to historical earthquakes.The results indicate the applicability of the proposed system for RC structures following seismic events.
基金Supported by the National Basic Research Program of China(973 Program)under Grant(No.2012CB026000)the National High Technology Research and Development Program of China(No.2014AA041806)
文摘A method combining information entropy and radial basis function network is proposed for fault automatic diagnosis of reciprocating compressors.Aiming at the current situation that the accuracy rate of reciprocating compressor fault diagnosis which depends on manual work in engineering is very low,we apply information entropy evaluation to select the sensitive features and make clear the corresponding relationship of characteristic parameters and failures.This method could reduce the feature dimension.Then,a complete fault diagnosis architecture has been built combining with radial basis function network which has the fast and efficient characteristics.According to the test results using experimental and engineering data,it is observed that the proposed fault diagnosis method improves the accuracy of fault automatic diagnosis effectively and it could improve the practicability of the monitoring system.
文摘The classification of pathological voice from healthy voice was studied based upon 27 acoustic features derived from a single sound signal of vowel /a:/. First, the feature space was transferred to reduce the data dimension by principle component analysis (PCA). Then the voice samples were classified according to the reduced PCA parameters by support vector machine (SVM) using radial basis function (RBF) as a kernel function. Meanwhile, by changing the ratio of opposite class samples, the accuracy under different features combinations was tested. Experimental data were provided by the voice database of Massachusetts Eye and Ear Infirmary (MEEI) in which 216 vowel /a:/ samples were collected from subjects of healthy and pathological cases, and tested with 5 fold cross-validation method. The result shows the positive rate of pathological voices was improved from 92% to 98% through the PCA method. STD, Fatr, Tasm, NHR, SEG, and PER are pathology sensitive features in illness detection. Using these sensitive features the accuracy of detection of pathological voice from healthy voice can reach 97%.
基金supported by the National Natural Science Foundation of China(Grant No.51905217)the Carbon Peak and Carbon Neutral Technology Innovation Fund Project of Jiangsu Province(Grant No.BE2023091-1)+1 种基金the International Postdoctoral Exchange Fellowship Program from China Postdoctoral Council(Grant No.PC2021032)the State Scholarship Fund from the China Scholarship Council。
文摘Fault diagnosis of fuel cells often focuses on single faults,leading to lower accuracy in diagnosing simultaneous faults.This paper researches a data-driven diagnostic method for both single and simultaneous faults,aiming to establish an efficient online fault diagnosis approach.Firstly,a theoretical model of a proton exchange membrane fuel cell(PEMFC)system is established.Based on this,a radial basis function(RBF)neural network surrogate model is designed to improve computational efficiency.The average relative error across all features between the surrogate model and the theoretical model is below 1%.Subsequently,Sobol's global sensitivity analysis is used to analyse the relationship between PEMFC system faults and various characteristic parameters during real-time operation.The sensitive feature set related to different faults in the PEMFC system is then identified.Finally,an adaptive diagnostic strategy is proposed,and a sensitivity-based diagnostic algorithm is established.Compared with other common single-label and multi-label diagnostic methods,the sensitivity-based diagnostic algorithm achieves an F1_Score of 99.1%on single-fault data,cutting training time by more than 80%.In scenarios with simultaneous faults and sparse data,the method achieves an accuracy of 92.5%,which is 7.5%higher than that achieved by the best multi-label method.
文摘Structural health monitoring(SHM)is a vast,interdisciplinary research field whose literature spans several decades with focusing on condition assessment of different types of structures including aerospace,mechanical and civil structures.The need for quantitative global damage detection methods that can be applied to complex structures has led to vibration-based inspection.Statistical time series methods for SHM form an important and rapidly evolving category within the broader vibration-based methods.In the literature on the structural damage detection,many time series-based methods have been proposed.When a considered time series model approximates the vibration response of a structure and model coefficients or residual error are obtained,any deviations in these coefficients or residual error can be inferred as an indication of a change or damage in the structure.Depending on the technique employed,various damage sensitive features have been proposed to capture the deviations.This paper reviews the application of time series analysis for SHM.The different types of time series analysis are described,and the basic principles are explained in detail.Then,the literature is reviewed based on how a damage sensitive feature is formed.In addition,some investigations that have attempted to modify and/or combine time series analysis with other approaches for better damage identification are presented.
基金supported by the National Basic Research 973 Program of China (Grant No. 2006CB303106)the National NaturalScience Foundation of China (Grant Nos. 60673004,90718035)the National High Technology Research and Development 863 Program of China (Grant No. 2007AA01Z336)
文摘We present a new method for feature preserving mesh simplification based on feature sensitive （FS） metric. Previous quadric error based approach is extended to a high-dimensional FS space so as to measure the geometric distance together with normal deviation. As the normal direction of a surface point is uniquely determined by the position in Euclidian space, we employ a two-step linear optimization scheme to efficiently derive the constrained optimal target point. We demonstrate that our algorithm can preserve features more precisely under the global geometric properties, and can naturally retain more triangular patches on the feature regions without special feature detection procedure during the simplification process. Taking the advantage of the blow-up phenomenon in FS space, we design an error weight that can produce more suitable results. We also show that Hausdorff distance is markedly reduced during FS simplification.
