☆ 4.8 Article

A Spatially Progressive Neural Network for Locally/Globally Prioritized TDLAS Tomography

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

CSTNet: A Dual-Branch Convolutional Neural Network for Imaging of Reactive Flows Using Chemical Species Tomography

Yunfan Jiang et al.

Summary: Chemical species tomography (CST) is used for in situ imaging of critical parameters in reactive flows. This study presents a novel convolutional neural network, CSTNet, for high-fidelity and rapid imaging of species concentration and temperature. CSTNet incorporates the CST measurements and sensor layout into the learning network and introduces a dual-branch decoder for image reconstructions. Experimental validation shows superior performance in terms of reconstruction accuracy and robustness to measurement noise.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

Add to Collection

Article Automation & Control Systems

Cost-Effective Quasi-Parallel Sensing Instrumentation for Industrial Chemical Species Tomography

Godwin Enemali et al.

Summary: This article presents a novel quasi-parallel sensing technique and electronic circuits for industrial chemical species tomography (CST). The proposed technique achieves cost-effective implementation of industrial CST with low complexity and reduced data transfer load by multiplexing the digitization and demodulation of multiple beam signals within a wavelength scan.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

A Quality-Hierarchical Temperature Imaging Network for TDLAS Tomography

Jingjing Si et al.

Summary: A novel quality-hierarchical temperature imaging network based on stacked LSTM is developed for TDLAS tomography, which can output two reconstructed temperature images of different qualities to meet various requirements. Both numerical stimulation and lab-scale experiment validated the accuracy-efficiency tradeoff achieved by this network.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2022)

Add to Collection

Article Engineering, Multidisciplinary

Flow field tomography with uncertainty quantification using a Bayesian physics-informed neural network

Joseph P. Molnar et al.

Summary: We introduce a new approach to flow field tomography using the Navier-Stokes and advection-diffusion equations for regularization. Through the use of physics-informed neural networks (PINNs), we are able to leverage the governing physics to improve the accuracy of flow field reconstructions from sparse line-of-sight integrated measurements. Our results demonstrate that PINNs outperform state-of-the-art algorithms in terms of accuracy, even when used for post-processing. However, high levels of noise can lead to semi-convergence, which we address with a Bayesian PINN that allows for uncertainty quantification and reveals the source of semi-convergence.

MEASUREMENT SCIENCE AND TECHNOLOGY (2022)

Add to Collection

Article Automation & Control Systems

Multidirection and Multiscale Pyramid in Transformer for Video-Based Pedestrian Retrieval

Xianghao Zang et al.

Summary: This article proposes a PiT model, which is a multidirection and multiscale Pyramid in Transformer, to address the issue of fine-grained and part-informed information in pedestrian retrieval. By splitting and dividing the images into different patches and parts, and fusing the multiscale feature representation using a pyramid structure, the proposed PiT achieves state-of-the-art performance.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Add to Collection

Article Optics

Temperature field reconstruction method for aero engine exhaust using the colored background oriented Schlieren technology

Song Fengcheng et al.

Summary: The article proposes a colored background oriented Schlieren (CBOS) method to detect the temperature field of an aircraft engine tail jet. By collecting Schlieren images and obtaining the refractive index field, a three-dimensional temperature field can be reconstructed, and the effectiveness and feasibility of the proposed method are demonstrated through simulations and experiments.

OPTOELECTRONICS LETTERS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Spatially Driven Chemical Species Tomography With Size-Adaptive Hybrid Meshing Scheme

Rui Zhang et al.

Summary: The paper introduces a novel size-adaptive hybrid meshing scheme for Chemical Species Tomography (CST) to detail the target flow field and consider physical phenomena in industrial combustion processes.

IEEE SENSORS JOURNAL (2022)

Add to Collection

Article Optics

Tomographic imaging of carbon dioxide in the exhaust plume of large commercial aero-engines

Abhishek Upadhyay et al.

Summary: This article reports the first attempt to implement chemically specific imaging in the exhaust plume of a gas turbine typical of those used for propulsion in commercial aircraft. The method used is chemical species tomography (CST), and the target species is CO2, which absorbs in the near-infrared at 1999.4 nm. The CO2 absorption spectrum is measured using tunable diode laser spectroscopy with wavelength modulation. The results of the study provide valuable insights for turbine combustion research, turbine engine development, and aviation fuel research and development.

APPLIED OPTICS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

TDLAS Tomography System for Online Imaging and Dynamic Process Playback of Temperature and Gas Mole Fraction

Mingxiang Li et al.

Summary: Tunable diode laser absorption spectroscopy (TDLAS) tomography enables online diagnosis of dynamic flames by imaging temperature variations and exhaust gases. The system requires large amounts of absorption spectrum data and high-speed data acquisition rate for high temporal resolution. Designed based on FPGA and PC, it provides real-time reconstruction and offline playback capabilities for temperature and gas distribution measurement.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2022)

Add to Collection

Article Engineering, Multidisciplinary

Quantifying the spatial resolution of the maximum a posteriori estimate in linear, rank-deficient, Bayesian hard field tomography

Johannes Emmert et al.

Summary: This study proposes a statistical spatial resolution measure based on the covariance of the reconstruction, taking into account the statistical prior information for rank-deficient tomography in chemical species imaging. The method can serve as a reference for designing tomographic systems considering the spatial inhomogeneity of spatial resolution.

MEASUREMENT SCIENCE AND TECHNOLOGY (2021)

Add to Collection

Article Automation & Control Systems

Efficient Multitask Structure-Aware Sparse Bayesian Learning for Frequency-Difference Electrical Impedance Tomography

Shengheng Liu et al.

Summary: This article introduces an efficient and high-spatial-resolution algorithm for reconstructing multiple frames of fdEIT, addressing issues related to anomaly detection and reconstruction algorithm. The proposed algorithm's recovery performance is verified through real-data experiments.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

Add to Collection

Article Automation & Control Systems

Parallel Deep Learning Algorithms With Hybrid Attention Mechanism for Image Segmentation of Lung Tumors

Hexuan Hu et al.

Summary: Medical images are crucial in clinical treatment, with lung images providing important references for diagnosis. This article introduces a deep learning algorithm with a hybrid attention mechanism for lung tumor image segmentation, achieving better performance by modifying the convolution quantity in DenseNet.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Relative Entropy Regularized TDLAS Tomography for Robust Temperature Imaging

Yong Bao et al.

Summary: TDLAS tomography is widely used for combustion diagnostics, but noise effects from ill-posed data inversion can generate artifacts in retrieved temperature images. The Relative Entropy Tomographic RecOnstruction (RETRO) algorithm improves the quality and robustness of temperature images by introducing relative entropy regularization.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Hierarchical Temperature Imaging Using Pseudoinversed Convolutional Neural Network Aided TDLAS Tomography

Jingjing Si et al.

Summary: TDLAS tomography is commonly used for temperature imaging in reactive flows, but CNN has been proven to be more robust and accurate for image reconstruction. The newly proposed PI-CNN algorithm efficiently performs temperature imaging with high accuracy and computational efficiency, prioritizing temperature imaging in the Region of Interest (RoI).

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2021)

Add to Collection

Article Engineering, Electrical & Electronic

An FPGA-Based On-Chip Neural Network for TDLAS Tomography in Dynamic Flames

Ang Huang et al.

Summary: A back propagation neural network is implemented on a field programmable gate array chip for tunable diode laser absorption spectroscopy tomography, achieving fast response and high signal-to-noise ratio in temperature and water concentration imaging. The method effectively reduces noise distortions in normalized second harmonics and average temperature in real experiments, showcasing more details in dynamic flame monitoring compared to typical quadrature demodulators. This approach demonstrates improved performance on the FPGA chip and enhances the accuracy of temperature and water vapor molar concentration distribution reconstruction.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2021)

Add to Collection

Article Thermodynamics

Influence of surrounding gas temperature on thermocouple measurement

Budong Liu et al.

CASE STUDIES IN THERMAL ENGINEERING (2020)

Add to Collection

Review Instruments & Instrumentation

Laser absorption spectroscopy for combustion diagnosis in reactive flows: A review

Chang Liu et al.

APPLIED SPECTROSCOPY REVIEWS (2019)

Add to Collection

Article Automation & Control Systems

Big Data-Driven Contextual Processing Methods for Electrical Capacitance Tomography

Andrzej Romanowski

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2019)

Add to Collection

Article Engineering, Electrical & Electronic

Toward Customized Spatial Resolution in TDLAS Tomography

Chang Liu et al.

IEEE SENSORS JOURNAL (2019)

Add to Collection

Article Engineering, Multidisciplinary

Multiparameter gas sensing with linear hyperspectral absorption tomography

Samuel J. Grauer et al.

MEASUREMENT SCIENCE AND TECHNOLOGY (2019)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Compressing convolutional neural networks using POD for the reconstruction of nonlinear tomographic absorption spectroscopy

Jianqing Huang et al.

COMPUTER PHYSICS COMMUNICATIONS (2019)

Add to Collection

Article Automation & Control Systems

Accelerated Structure-Aware Sparse Bayesian Learning for Three-Dimensional Electrical Impedance Tomography

Shengheng Liu et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2019)

Add to Collection

Article Engineering, Electrical & Electronic

Online Cross-Sectional Monitoring of a Swirling Flame Using TDLAS Tomography

Chang Liu et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2018)

Add to Collection

Article Optics

Reconstruction for limited-data nonlinear tomographic absorption spectroscopy via deep learning

Jianqing Huang et al.

JOURNAL OF QUANTITATIVE SPECTROSCOPY & RADIATIVE TRANSFER (2018)

Add to Collection

Article Optics

Measurement-based meshing, basis selection, and prior assignment in chemical species tomography

Samuel J. Grauer et al.

OPTICS EXPRESS (2017)

Add to Collection

Review Thermodynamics

Tomographic absorption spectroscopy for the study of gas dynamics and reactive flows

Weiwei Cai et al.

PROGRESS IN ENERGY AND COMBUSTION SCIENCE (2017)

Add to Collection

Article Optics

Chemical species tomography of turbulent flows: Discrete ill-posed and rank deficient problems and the use of prior information

Kyle J. Daun et al.

JOURNAL OF QUANTITATIVE SPECTROSCOPY & RADIATIVE TRANSFER (2016)

Add to Collection

Article Instruments & Instrumentation

Tunable diode laser absorption spectroscopy-based tomography system for on-line monitoring of two-dimensional distributions of temperature and H2O mole fraction

Lijun Xu et al.

REVIEW OF SCIENTIFIC INSTRUMENTS (2016)

Add to Collection

Article Automation & Control Systems

w Advanced Features and Industrial Applications of FPGAs-A Review

Juan J. Rodriguez-Andina et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2015)

Add to Collection

Article Engineering, Electrical & Electronic

Reconstruction of Axisymmetric Temperature and Gas Concentration Distributions by Combining Fan-Beam TDLAS With Onion-Peeling Deconvolution

Chang Liu et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2014)

Add to Collection

Article Optics

Simulation-based comparison of noise effects in wavelength modulation spectroscopy and direct absorption TDLAS

B. Lins et al.

APPLIED PHYSICS B-LASERS AND OPTICS (2010)

Add to Collection

© Peeref 2019-2024. All rights reserved.