The curse of dimensionality refers to the problem o increased sparsity and computational complexity when dealing with high-dimensional data.In recent years,the types and vari ables of industrial data have increased si...The curse of dimensionality refers to the problem o increased sparsity and computational complexity when dealing with high-dimensional data.In recent years,the types and vari ables of industrial data have increased significantly,making data driven models more challenging to develop.To address this prob lem,data augmentation technology has been introduced as an effective tool to solve the sparsity problem of high-dimensiona industrial data.This paper systematically explores and discusses the necessity,feasibility,and effectiveness of augmented indus trial data-driven modeling in the context of the curse of dimen sionality and virtual big data.Then,the process of data augmen tation modeling is analyzed,and the concept of data boosting augmentation is proposed.The data boosting augmentation involves designing the reliability weight and actual-virtual weigh functions,and developing a double weighted partial least squares model to optimize the three stages of data generation,data fusion and modeling.This approach significantly improves the inter pretability,effectiveness,and practicality of data augmentation in the industrial modeling.Finally,the proposed method is verified using practical examples of fault diagnosis systems and virtua measurement systems in the industry.The results demonstrate the effectiveness of the proposed approach in improving the accu racy and robustness of data-driven models,making them more suitable for real-world industrial applications.展开更多
Recently developed fault classification methods for industrial processes are mainly data-driven.Notably,models based on deep neural networks have significantly improved fault classification accuracy owing to the inclu...Recently developed fault classification methods for industrial processes are mainly data-driven.Notably,models based on deep neural networks have significantly improved fault classification accuracy owing to the inclusion of a large number of data patterns.However,these data-driven models are vulnerable to adversarial attacks;thus,small perturbations on the samples can cause the models to provide incorrect fault predictions.Several recent studies have demonstrated the vulnerability of machine learning methods and the existence of adversarial samples.This paper proposes a black-box attack method with an extreme constraint for a safe-critical industrial fault classification system:Only one variable can be perturbed to craft adversarial samples.Moreover,to hide the adversarial samples in the visualization space,a Jacobian matrix is used to guide the perturbed variable selection,making the adversarial samples in the dimensional reduction space invisible to the human eye.Using the one-variable attack(OVA)method,we explore the vulnerability of industrial variables and fault types,which can help understand the geometric characteristics of fault classification systems.Based on the attack method,a corresponding adversarial training defense method is also proposed,which efficiently defends against an OVA and improves the prediction accuracy of the classifiers.In experiments,the proposed method was tested on two datasets from the Tennessee–Eastman process(TEP)and steel plates(SP).We explore the vulnerability and correlation within variables and faults and verify the effectiveness of OVAs and defenses for various classifiers and datasets.For industrial fault classification systems,the attack success rate of our method is close to(on TEP)or even higher than(on SP)the current most effective first-order white-box attack method,which requires perturbation of all variables.展开更多
Generally,Doppler fuze can only estimate actuation delay-time with a limited precision. As an improvement,imaging fuze can estimate actuation delay-time more precisely with the available two-dimensional image of the t...Generally,Doppler fuze can only estimate actuation delay-time with a limited precision. As an improvement,imaging fuze can estimate actuation delay-time more precisely with the available two-dimensional image of the target. In this paper,imprecision of actuation delay-time estimation with Doppler fuze is first analyzed theoretically in brief. Secondly,feasibility analysis and theoretical model of imaging fuze are described,in which a criterion is established for the actuation delay-time based on the image,and then an image based gray-value weighted least square( GWLS) algorithm is presented to calculate actuation delay-time of the imaging fuze. Finally,a simulation model of missiletarget near-field encounter is established. Simulation results indicate that actuation delay-time of the imaging fuze is estimated more precisely than by the Doppler fuze.展开更多
We investigate frequency-comb generation in normal dispersion silicon microresonators from the near-infrared to mid-infrared wavelength range in the presence of multiphoton absorption and free-carrier effects. It is f...We investigate frequency-comb generation in normal dispersion silicon microresonators from the near-infrared to mid-infrared wavelength range in the presence of multiphoton absorption and free-carrier effects. It is found that parametric oscillation is inhibited in the telecom wavelength range resulting from strong two-photon absorption.On the contrary, beyond the wavelength of 2200 nm, where three-and four-photon absorption are less detrimental,a comb can be generated with moderate pump power, or free-carriers are swept out by a positive-intrinsic-negative structure. In the temporal domain, the generated combs correspond to flat-top pulses, and the pulse duration can be easily controlled by varying the laser detuning. The reported comb generation process shows a high conversion efficiency compared with anomalous dispersion regime, which can guide and promote comb formation in materials with normal dispersion. As the comb spectra cover the mid-infrared wavelength range, they can find applications in comb-based radiofrequency photonic filters and mid-infrared spectroscopy.展开更多
In this paper, a new nonlinear fault detection technique based on locally linear embedding (LLE) is developed. LLE can efficiently compute the low-dimensional embedding of the data with the local neighborhood struct...In this paper, a new nonlinear fault detection technique based on locally linear embedding (LLE) is developed. LLE can efficiently compute the low-dimensional embedding of the data with the local neighborhood structure information preserved. In this method, a data-dependent kernel matrix which can reflect the nonlinear data structure is defined. Based on the kernel matrix, the Nystrrm formula makes the mapping extended to the testing data possible. With the kernel view of the LLE, two monitoring statistics are constructed. Together with the out of sample extensions, LLE is used for nonlinear fault detection. Simulation cases were studied to demonstrate the performance of the proposed method.展开更多
基金supported in part by the National Natural Science Foundation of China(NSFC)(92167106,61833014)Key Research and Development Program of Zhejiang Province(2022C01206)。
文摘The curse of dimensionality refers to the problem o increased sparsity and computational complexity when dealing with high-dimensional data.In recent years,the types and vari ables of industrial data have increased significantly,making data driven models more challenging to develop.To address this prob lem,data augmentation technology has been introduced as an effective tool to solve the sparsity problem of high-dimensiona industrial data.This paper systematically explores and discusses the necessity,feasibility,and effectiveness of augmented indus trial data-driven modeling in the context of the curse of dimen sionality and virtual big data.Then,the process of data augmen tation modeling is analyzed,and the concept of data boosting augmentation is proposed.The data boosting augmentation involves designing the reliability weight and actual-virtual weigh functions,and developing a double weighted partial least squares model to optimize the three stages of data generation,data fusion and modeling.This approach significantly improves the inter pretability,effectiveness,and practicality of data augmentation in the industrial modeling.Finally,the proposed method is verified using practical examples of fault diagnosis systems and virtua measurement systems in the industry.The results demonstrate the effectiveness of the proposed approach in improving the accu racy and robustness of data-driven models,making them more suitable for real-world industrial applications.
基金This work was supported in part by the National Natural Science Foundation of China(NSFC)(92167106,62103362,and 61833014)the Natural Science Foundation of Zhejiang Province(LR18F030001).
文摘Recently developed fault classification methods for industrial processes are mainly data-driven.Notably,models based on deep neural networks have significantly improved fault classification accuracy owing to the inclusion of a large number of data patterns.However,these data-driven models are vulnerable to adversarial attacks;thus,small perturbations on the samples can cause the models to provide incorrect fault predictions.Several recent studies have demonstrated the vulnerability of machine learning methods and the existence of adversarial samples.This paper proposes a black-box attack method with an extreme constraint for a safe-critical industrial fault classification system:Only one variable can be perturbed to craft adversarial samples.Moreover,to hide the adversarial samples in the visualization space,a Jacobian matrix is used to guide the perturbed variable selection,making the adversarial samples in the dimensional reduction space invisible to the human eye.Using the one-variable attack(OVA)method,we explore the vulnerability of industrial variables and fault types,which can help understand the geometric characteristics of fault classification systems.Based on the attack method,a corresponding adversarial training defense method is also proposed,which efficiently defends against an OVA and improves the prediction accuracy of the classifiers.In experiments,the proposed method was tested on two datasets from the Tennessee–Eastman process(TEP)and steel plates(SP).We explore the vulnerability and correlation within variables and faults and verify the effectiveness of OVAs and defenses for various classifiers and datasets.For industrial fault classification systems,the attack success rate of our method is close to(on TEP)or even higher than(on SP)the current most effective first-order white-box attack method,which requires perturbation of all variables.
基金Supported by the Ministerial Level Advanced Research Foundation of China(9140A05030213HT25012)
文摘Generally,Doppler fuze can only estimate actuation delay-time with a limited precision. As an improvement,imaging fuze can estimate actuation delay-time more precisely with the available two-dimensional image of the target. In this paper,imprecision of actuation delay-time estimation with Doppler fuze is first analyzed theoretically in brief. Secondly,feasibility analysis and theoretical model of imaging fuze are described,in which a criterion is established for the actuation delay-time based on the image,and then an image based gray-value weighted least square( GWLS) algorithm is presented to calculate actuation delay-time of the imaging fuze. Finally,a simulation model of missiletarget near-field encounter is established. Simulation results indicate that actuation delay-time of the imaging fuze is estimated more precisely than by the Doppler fuze.
基金National Natural Science Foundation of China(NSFC)(61635013,61675231,61475188,61705257)Strategic Priority Research Program of the Chinese Academy of Sciences(CAS)(XDB24030600)
文摘We investigate frequency-comb generation in normal dispersion silicon microresonators from the near-infrared to mid-infrared wavelength range in the presence of multiphoton absorption and free-carrier effects. It is found that parametric oscillation is inhibited in the telecom wavelength range resulting from strong two-photon absorption.On the contrary, beyond the wavelength of 2200 nm, where three-and four-photon absorption are less detrimental,a comb can be generated with moderate pump power, or free-carriers are swept out by a positive-intrinsic-negative structure. In the temporal domain, the generated combs correspond to flat-top pulses, and the pulse duration can be easily controlled by varying the laser detuning. The reported comb generation process shows a high conversion efficiency compared with anomalous dispersion regime, which can guide and promote comb formation in materials with normal dispersion. As the comb spectra cover the mid-infrared wavelength range, they can find applications in comb-based radiofrequency photonic filters and mid-infrared spectroscopy.
基金supported in part by the National Basic Research Program of China(973 Program)(No.2012CB720505)the National Natural Science Foundation of China(No.61273167)
文摘In this paper, a new nonlinear fault detection technique based on locally linear embedding (LLE) is developed. LLE can efficiently compute the low-dimensional embedding of the data with the local neighborhood structure information preserved. In this method, a data-dependent kernel matrix which can reflect the nonlinear data structure is defined. Based on the kernel matrix, the Nystrrm formula makes the mapping extended to the testing data possible. With the kernel view of the LLE, two monitoring statistics are constructed. Together with the out of sample extensions, LLE is used for nonlinear fault detection. Simulation cases were studied to demonstrate the performance of the proposed method.