Article
Engineering, Environmental
Junwei Ma, Yankun Wang, Xiaoxu Niu, Sheng Jiang, Zhiyang Liu
Summary: This study proposes an input variable selection method based on mutual information and incorporates it into an optimized support vector regression model for predicting the displacement of seepage-driven landslides. The experimental results show that the optimized model based on mutual information can significantly improve prediction accuracy and stability.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Article
Engineering, Multidisciplinary
Thomas Y. Wu, Asaad Kenbar
Summary: New methods have been proposed to reduce the measurement uncertainty of LNG mass flow using Coriolis mass flowmeters (CMF). By deriving the Young's modulus at LNG temperature and calculating the Poisson's ratio from torsional and bending frequency measurements, more accurate LNG mass flow measurement can be achieved. The expanded uncertainty of these calculations is significantly lower than the measured values, leading to a reduction in measurement uncertainty.
Article
Engineering, Multidisciplinary
Thomas Y. Wu, Asaad Kenbar, Aart Pruysen
Summary: The study investigated the uncertainty of CMF for LNG mass flowrate measurement, evaluating the Young's modulus of stainless steel 316 and finding a corrected value with smaller uncertainty at cryogenic temperature. The expanded uncertainty of a CMF for LNG flowrate measurement is estimated to be 0.50%, with the dominating component being the uncertainty of the corrected Young's modulus at cryogenic temperature.
Article
Engineering, Multidisciplinary
Hao Zhu, Alfred Rieder, Paul Ceglia, Hai-Thuy Ngo
Summary: Coriolis mass flowmeters are widely accepted for their high performance measurement of density and mass flow rate. A new measuring concept based on the Coriolis principle utilizing two parallel meters has advantages in reducing measurement uncertainty, increasing reliability, and gaining greater process insights.
Article
Construction & Building Technology
Jihong Ling, Na Dai, Jincheng Xing, Hui Tong
Summary: This paper aims to improve the prediction accuracy of the data-driven model of load prediction through optimizing the input variable selection based on hourly correlation analysis. The results show that hourly correlation analysis can reduce the RMSE of the prediction results and increase the R-2 while keeping the calculation time unchanged, thus improving the prediction accuracy of the model.
JOURNAL OF BUILDING ENGINEERING
(2021)
Article
Energy & Fuels
Ting'ao Shen, Siyu Huang, Peng Chen, Liwei Chen, Yi Zhou
Summary: A new phase difference measurement method for Coriolis mass flowmeter is proposed based on correlation theories, aiming to solve the poor precision problem in phase difference measurements in engineering practice. The method estimates the signal frequency using an adaptive notch filter, conducts Hilbert transformation on the extended signals, and computes the correlation functions. Compared to traditional methods, the proposed method is suitable for both integer period and non-integer period sampling signals, and demonstrates superior accuracy, real-time performance, and dynamic performance.
Article
Automation & Control Systems
Pedro H. P. da Cunha, Ellisson H. de Paulo, Gabriely Silveira Folli, Marcia H. C. Nascimento, Mariana K. Moro, Paulo R. Filgueiras
Summary: This study demonstrates the potential of variable selection methods, SPA and NISPA, in overcoming the limitations of support vector regression (SVR) as a black box machine-learning method. The application of these methods in FTIR data of crude oil samples resulted in more accurate and parsimonious models, revealing the most important variables for building the SVR models.
JOURNAL OF CHEMOMETRICS
(2022)
Article
Engineering, Civil
Kun Ren, Xue Wang, Xiaoyu Shi, Jihong Qu, Wei Fang
Summary: The study highlights the importance of selecting appropriate input variable selection methods in practice, as some examined wrappers were found to be inferior to benchmark models. The BMWIVS model combining different methods yielded the best performance across the three cases studied. Additionally, the correlations between global climate indices and streamflow were lower than those between local weather information and streamflow, indicating that both types of information are important for forecasting monthly streamflow.
JOURNAL OF HYDROLOGY
(2021)
Article
Engineering, Environmental
Xinhong Li, Luyao Zhang, Faisal Khan, Ziyue Han
Summary: Corrosion prediction is crucial for subsea process system in the industry 4.0 environment. A hybrid data-driven model integrating PCA, ABC, and SVR was proposed for corrosion degradation modeling. The PCA-ABC-SVR model demonstrated superior prediction accuracy and robustness.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Optics
Peng Li, Junchao Ma, Nan Zhong
Summary: This study demonstrates that Raman spectroscopy combined with the CARS-SPA-SVR model can accurately predict the storage time of salmon fillets, providing a fast and non-destructive approach.
Article
Engineering, Mechanical
Olga L. Ibryaeva, Denis K. Lebedev, Manus P. Henry
Summary: Using a support vector machine (SVM) approach, this study analyzed a dataset of Coriolis meter errors and found that a linear SVM model outperformed non-linear SVM and neural network models. This improved performance may be attributed to over-fitting by the latter two on the relatively small dataset.
FLOW MEASUREMENT AND INSTRUMENTATION
(2021)
Article
Engineering, Mechanical
Yajun Liu, Liya Wang, Qi Luo, Yanjin Zhang
Summary: This study proposes two improved correlation analysis methods to enhance the accuracy of phase difference extraction. Simulation and experiments were conducted to investigate the impact of sequence length, signal-to-noise ratio, and Kalman filtering on extraction accuracy, as well as to compare different algorithms under different phase differences. The experimental results demonstrate that the improved algorithms have higher accuracy and stability, verifying the feasibility of the proposed methods.
FLOW MEASUREMENT AND INSTRUMENTATION
(2021)
Article
Engineering, Multidisciplinary
Mehdi Fadaei, Forough Ameli, Seyed Hassan Hashemabadi
Summary: Various methods for multiphase flow metering were introduced in this study, including using Coriolis flow meter to measure gas-liquid average density and determining gas volume fraction by discharge coefficient of an orifice plate. The application of Orifice plate and Coriolis flow meters for gas-liquid flow metering was investigated, along with predicting gas volume fraction using a soft sensor. Among various computational intelligence methods, the 3-layer neural network performed the best with a mean square error of 0.91% and mean absolute percent error of 3%.
Article
Mathematics
Antonis Christou, Andreas Artemiou
Summary: In this study, we propose a sparse version of Support Vector Regression (SVR) that achieves sparsity in function estimation through regularization. We introduce an adaptive L-0 penalty with a ridge structure, which does not increase computational complexity. Additionally, we adopt an alternative approach based on a similar proposal in the Support Vector Machine (SVM) literature. Numerical studies confirm the effectiveness of our novel approach, which focuses on variable selection rather than support vector selection.
Article
Automation & Control Systems
Amit Mathur, Pradeep Kumar, S. P. Harsha
Summary: This article presents a data-driven fault diagnosis method for rolling element bearing under different operating conditions. Filter-type feature selection algorithms are incorporated to rank the time-domain statistical features extracted from vibration data of various bearing defect conditions. The results show that the neighborhood component analysis algorithm achieves the highest accuracies for bearing fault detection with both the support vector machine and artificial neural network. The effective feature ranking before fault classification can lead to efficient and reliable bearing fault diagnosis.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Yong Yan, Jiali Wu, Yonghui Hu
Summary: This paper presents a study on using electrostatic probes to measure charge density in flames. Experimental results show that the charge density in a methane diffusion flame increases with fuel flowrate, while in a methane-air premixed flame, it varies with equivalence ratio. The developed electrostatic probe and index can effectively indicate charge density in different flames.
IEEE SENSORS JOURNAL
(2021)
Article
Automation & Control Systems
Ling Qin, Wei-jie Huo, Jing Hu, Jian Wang, Wan-sheng Zhao, Ya-ou Zhang
Summary: Spark discharge plasma in electrical discharge machining is difficult to measure, but a parallel PIC-MCC simulation architecture based on GPU can effectively analyze the machining process. The simulation results show that the micro-peak geometry limits the plasma size and the energy absorbed by the anode is higher than that of the cathode.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Yongyue Wang, Xiangchen Qian, Lijuan Wang, Yong Yan
Summary: A novel approach using sensors and Gaussian process regression (GPR) is presented for measuring the cross-sectional particle velocity distribution in a square-shaped pipe. Experimental tests show that the electrostatic sensor in conjunction with the GPR model is a feasible approach to obtain the cross-sectional velocity distribution of pneumatically conveyed particles in a square-shaped pipe.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Yonghui Hu, Junkai Wang, Yi Li, Yong Yan
Summary: This article presents a method for locating charged objects using an electrostatic sensor array. Numerical simulations show that the linear sensor array can accurately locate the charged object in areas far from the electrodes and the grounded surface.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Ge Guo, Yong Yan, Wenbiao Zhang, Yonghui Hu, Guimei Fu
Summary: The distribution of moisture in stored biomass fuels plays a crucial role in their self-heating and spontaneous combustion. This study proposes the use of electrical capacitance tomography (ECT) as a noninvasive imaging technique to measure the moisture distribution in stored wood pellets. Experimental results demonstrate the capability of ECT in accurately measuring the wet area, centroid position, and moisture content of the biomass fuels.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Weicheng Xu, Yong Yan, Gang Lu, Xiaojing Bai
Summary: This article introduces a method for quantifying flame stability through digital imaging and image processing, resulting in a flame stability index. The proposed method is more sensitive and requires a shorter data length compared to other methods, and it can effectively evaluate flame stability regardless of combustion conditions.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Yonghui Hu, Yong Yan, Yuanqing Yang
Summary: This article presents a comprehensive comparative study of four types of preamplifiers used in electrostatic sensors and establishes an equivalent circuit model to quantify the interaction between charged objects and electrodes. The analysis reveals similarities in signal waveforms among different amplifiers under pulse excitation. The current sense and potential amplifiers are significantly affected by parasitic capacitances, requiring measures to reduce their effects.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Computer Science, Information Systems
Qing Zhang, Yong Yan, Yong Lin, Yan Li
Summary: This study proposes an image retrieval method based on deep learning, which achieves secure retrieval of ciphertext images through a deep artificial neural network model and an image encryption algorithm. Experimental results show significant improvements in retrieval efficiency and performance indicators, highlighting the importance of research on image information security retrieval.
Article
Engineering, Electrical & Electronic
Faisal Abbas, Yong Yan, Lijuan Wang
Summary: This article introduces a technique for mass flow rate measurement of pneumatically conveyed solids based on multimodal sensing and data-driven modeling. Experimental results show that the ANN, SVM, and CNN models can predict the mass flow rate of solids with a relative error within +/-18%, +/-14%, and +/-8% respectively under all test conditions. Predicted mass flow rate measurements with the models are repeatable with a normalized standard deviation within 14%, 8%, and 5% respectively under all test conditions.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Electrical & Electronic
Jingqiong Zhang, Yong Yan, Jinyu Liu, Edward Jukes
Summary: Coriolis flowmeters are widely used in industrial applications, but may face erosion when measuring abrasive fluids. A stiffness diagnosis technique can identify potential wear on the measuring tube through frequency response analysis. Experimental results show that the technique can successfully detect slight tube erosion with a relative change in SRDP of -1%.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Electrical & Electronic
Yonghui Hu, Yong Yan, Christos Efstratiou, David Vela-Orte
Summary: The article introduces a method for measuring the cross-sectional shape of a rubber dam using an array of inertial measurement units and an adaptive complementary filter. Experimental evaluation shows good agreement between measured and reference shapes under static conditions, with considerable improvement achieved under dynamic conditions compared with an accelerometer-only approach. Additionally, the measurement system exhibits a high level of fault tolerance, as the elimination of faulty nodes has negligible influence on the results.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Electrical & Electronic
Ge Zheng, Yong Yan, Yonghui Hu, Wenbiao Zhang, Long Yang, Lanqi Li
Summary: A novel method for online measurement of the mass flow rate of pulverized fuel through acoustic emission detection and electrostatic sensing is proposed. By changing the installation orientation of the sensing head, the relative error can be reduced. The system shows promising performance under experimental conditions.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Electrical & Electronic
Bojian Qi, Yong Yan, Wenbiao Zhang, Xinyan Li
Summary: The article introduces a method for measuring bubble characteristics in a two-dimensional fluidized bed using a two-dimensional electrostatic sensor array. The study shows that this method can accurately measure the size, shape, rising velocity, and generation frequency of bubbles, with good agreement with results from an optical imaging system.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Electrical & Electronic
Jiali Wu, Yong Yan, Yonghui Hu, Shan Li, Weicheng Xu
Summary: This article presents a study on measuring the flame boundary using an electrostatic sensor array, which shows reliable results for predicting flame properties. The methodology provides important information for the design and operation of combustion systems. The system is capable of providing accurate measurements and determining the overall polarity of charges in a flame.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Electrical & Electronic
Yonghui Hu, Yong Yan
Summary: This article introduces a novel wearable electrostatic sensor that can detect limb and torso movements. The sensor measures the potential difference for motion sensing and converts the induced charge into a voltage signal using a charge amplifier. Experimental assessment validates the sensor's capability to capture movements from any location, with signal depending on mounting location, activity type, and various factors.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)