Complex processes often work with multiple operation regions, it is critical to develop effective monitoring approaches to ensure the safety of chemical processes. In this work, a discriminant local consistency Gaussi...Complex processes often work with multiple operation regions, it is critical to develop effective monitoring approaches to ensure the safety of chemical processes. In this work, a discriminant local consistency Gaussian mixture model(DLCGMM) for multimode process monitoring is proposed for multimode process monitoring by integrating LCGMM with modified local Fisher discriminant analysis(MLFDA). Different from Fisher discriminant analysis(FDA) that aims to discover the global optimal discriminant directions, MLFDA is capable of uncovering multimodality and local structure of the data by exploiting the posterior probabilities of observations within clusters calculated from the results of LCGMM. This may enable MLFDA to capture more meaningful discriminant information hidden in the high-dimensional multimode observations comparing to FDA. Contrary to most existing multimode process monitoring approaches, DLCGMM performs LCGMM and MFLDA iteratively, and the optimal subspaces with multi-Gaussianity and the optimal discriminant projection vectors are simultaneously achieved in the framework of supervised and unsupervised learning. Furthermore, monitoring statistics are established on each cluster that represents a specific operation condition and two global Bayesian inference-based fault monitoring indexes are established by combining with all the monitoring results of all clusters. The efficiency and effectiveness of the proposed method are evaluated through UCI datasets, a simulated multimode model and the Tennessee Eastman benchmark process.展开更多
The China Seismo-Electromagnetic Satellite(CSES)deploys three payloads to detect the electromagnetic environment in the ionosphere.The tri-axial fluxgate magnetometers(FGM),as part of the high precision magnetometer(H...The China Seismo-Electromagnetic Satellite(CSES)deploys three payloads to detect the electromagnetic environment in the ionosphere.The tri-axial fluxgate magnetometers(FGM),as part of the high precision magnetometer(HPM),measures the Earth magnetic vector field in a frequency range from direct current(DC)to 15 Hz.The tri-axial search coil magnetometer(SCM)detects the alternating current(AC)related magnetic field in a frequency range from several Hz to 20 k Hz,and the electric field detector(EFD)measures the spatial electric field in a broad frequency band from DC to 3.5 MHz.This work mainly crosscalibrates the consistency of these three payloads in their overlapped detection frequency range and firstly evaluates CSES’s timing system and the sampling time differences between EFD and SCM.A sampling time synchronization method for EFD and SCM waveform data is put forward.The consistency between FGM and SCM in the ultra-low-frequency(ULF)range is validated by using the magnetic torque(MT)signal as a reference.A natural quasiperiodic electromagnetic wave event verifies SCM and EFD’s consistency in extremely low-frequency and very low-frequency(ELF/VLF)bands.This cross-calibration work is helpful to upgrade the data quality of CSES and brings valuable insights to similar electromagnetic detection solutions by low earth orbit satellites.展开更多
基金Supported by the National Natural Science Foundation of China(61273167)
文摘Complex processes often work with multiple operation regions, it is critical to develop effective monitoring approaches to ensure the safety of chemical processes. In this work, a discriminant local consistency Gaussian mixture model(DLCGMM) for multimode process monitoring is proposed for multimode process monitoring by integrating LCGMM with modified local Fisher discriminant analysis(MLFDA). Different from Fisher discriminant analysis(FDA) that aims to discover the global optimal discriminant directions, MLFDA is capable of uncovering multimodality and local structure of the data by exploiting the posterior probabilities of observations within clusters calculated from the results of LCGMM. This may enable MLFDA to capture more meaningful discriminant information hidden in the high-dimensional multimode observations comparing to FDA. Contrary to most existing multimode process monitoring approaches, DLCGMM performs LCGMM and MFLDA iteratively, and the optimal subspaces with multi-Gaussianity and the optimal discriminant projection vectors are simultaneously achieved in the framework of supervised and unsupervised learning. Furthermore, monitoring statistics are established on each cluster that represents a specific operation condition and two global Bayesian inference-based fault monitoring indexes are established by combining with all the monitoring results of all clusters. The efficiency and effectiveness of the proposed method are evaluated through UCI datasets, a simulated multimode model and the Tennessee Eastman benchmark process.
基金supported by the National Natural Science Foundation of China(Grant Nos.41874174 and 41574139)the National Key R&D Program of China(Grant No.2018YFC1503501)+1 种基金the APSCO Earthquake Research Project PhaseⅡand ISSI-BJ projectSouthern Yunnan Observatory for Cross-block Dynamic Process,Yuxi Yunnan,China。
文摘The China Seismo-Electromagnetic Satellite(CSES)deploys three payloads to detect the electromagnetic environment in the ionosphere.The tri-axial fluxgate magnetometers(FGM),as part of the high precision magnetometer(HPM),measures the Earth magnetic vector field in a frequency range from direct current(DC)to 15 Hz.The tri-axial search coil magnetometer(SCM)detects the alternating current(AC)related magnetic field in a frequency range from several Hz to 20 k Hz,and the electric field detector(EFD)measures the spatial electric field in a broad frequency band from DC to 3.5 MHz.This work mainly crosscalibrates the consistency of these three payloads in their overlapped detection frequency range and firstly evaluates CSES’s timing system and the sampling time differences between EFD and SCM.A sampling time synchronization method for EFD and SCM waveform data is put forward.The consistency between FGM and SCM in the ultra-low-frequency(ULF)range is validated by using the magnetic torque(MT)signal as a reference.A natural quasiperiodic electromagnetic wave event verifies SCM and EFD’s consistency in extremely low-frequency and very low-frequency(ELF/VLF)bands.This cross-calibration work is helpful to upgrade the data quality of CSES and brings valuable insights to similar electromagnetic detection solutions by low earth orbit satellites.
