Machine vision in Process Systems Engineering

J. Jay Liu,Hyun-woo Cho 제어로봇시스템학회 2011 제어로봇시스템학회 국제학술대회 논문집 Vol.2011 No.10

Machine vision has been introduced to solve numerous problems in Process Systems Engineering (PSE) as well as in other discipline. In the field of PSE however, machine vision’s potentials have never been explored to the full extent yet. This is not only because the techniques involved in machine vision are still poorly-known to researchers and practitioners in PSE, but also because the characteristics of the scenes that the images acquired in process industries are often difficult to analyze due to their stochastic nature. On the other hand, data analysis has been known in PSE for several decades and extensively employed in process industries producing innumerous applications. The purpose of this article is to give an overview of methods and possible applications of machine vision from a data analysis perspective, which is more familiar to PSE community.

Design and analysis of a diesel processing unit for a molten carbonate fuel cell for auxiliary power unit applications

J. Jay Liu,Agnesia Permatasari,Peyman Fasahati,Jun-Hyung Ryu 한국화학공학회 2016 Korean Journal of Chemical Engineering Vol.33 No.12

Fuel cell-based auxiliary power units (APUs) are a promising technology for meeting global energy needs in an environmentally friendly way. This study uses diesel containing sulfur components such as dibenzothiophene (DBT) as a feed. The sulfur tolerance of molten carbonate fuel cell (MCFC) modules is not more than 0.5 ppm, as sulfur can poison the fuel cell and degrade the performance of the fuel cell module. The raw diesel feed in this study contains 10 ppm DBT, and its sulfur concentration should be reduced to 0.1 ppm. After desulfurization, the feed goes through several unit operations, including steam reforming, water-gas shift, and gas purification. Finally, hydrogen is fed to the fuel cell module, where it generates 500 kW of electrical energy. The entire process, with 52% and 89% fuel cell and overall system efficiencies, respectively, is rigorously simulated using Aspen HYSYS, and the results are input into a techno-economic analysis to calculate the minimum electricity selling price (MESP). The electricity cost for this MCFC-based APU was calculated as 1.57$/kWh. According to predictions, the cost reductions for fuel cell stacks will afford electricity selling prices of 1.51$/kWh in 2020 and 1.495$/kWh in 2030. Based on a sensitivity analysis, the diesel price and capital cost were found to have the strongest impact on the MESP.

화상분석을 이용한 소프트 센서의 설계와 산업응용사례 1. 외관 품질의 수치적 추정과 모니터링

유준 ( J. Jay Liu ) 한국화학공학회 2010 Korean Chemical Engineering Research(HWAHAK KONGHA Vol.48 No.4

Deep Learning-based Prediction of Oversupply of Solar Energy

Saeideh Khakzadkelarijani,J. Jay Liu 한국에너지학회 2023 한국에너지공학회 학술발표회 Vol.2023 No.10

Quality Determination of Steel Surfaces Based on Best Feature Selection

Kim, Daeyoun,Liu, J. Jay,Han, Chonghun The Society of Chemical Engineers, Japan 2011 Journal of chemical engineering of Japan Vol.44 No.7

<P>We propose a quality classification methodology based on optimal textural feature selection. This method employs the wavelet packet transform to decompose the original image into multiple-resolution images. Wavelet texture analysis is applied to extract quality-related features from subimages. Optimal textural feature selection is employed to select the discriminative texture in accordance with class information. The previously used best basis approach is incapable of optimal texture classification when combined with wavelet texture analysis. The proposed texture classification method unifies the best basis approach with wavelet texture analysis. Further, we improve the previous best basis to obtain an optimal basis using a simple rule to select discriminative signatures. The proposed methodology is applied and validated for classifying the surface quality of rolled steel sheets. Experimental results show that features extracted using the proposed method are more discriminative than those obtained using the best basis in terms of classification performance and Fisher's index.</P>

거대조류 바이오가스를 연료로 하는 고체산화물 연료전지를 이용한 삼중발전

Ivannie Effendi,유준(J. Jay Liu) 한국청정기술학회 2020 청정기술 Vol.26 No.2

이 논문에서는 3세대 바이오매스 중 거대조류, 즉 해조류 바이오매스로부터 유래된 바이오가스를 연료로 사용하여 열, 전력 및 수소를 생산하는 삼중발전의 타당성 평가를 수행하였다. 이를 위해 3 MW급 고체산화물 연료전지와 가스터빈, 그리고 유기 랭킨 사이클로 이루어진 상용 규모의 열, 전력 및 수소 생산공정을 공정모사기를 사용하여 설계, 모사하였고, 공정모사로부터 얻은 열 및 물질 수지를 통해 각 단위조작 장치의 가격을 추정하고 경제성을 분석하였다. 수소를 생산하기 위해 고체산화물 연료전지의 설계를 수정하였는데, 연료전지 내 애프터-버너를 제거하고 수성-가스 전환 반응기를 추가하였다. 공정모사 결과 설계된 삼중발전 공정은 시간당 3.47톤의 건조 갈조류 원료로부터 생산된 2톤의 바이오가스를 이용하여 2.3 MW의 전력과 50kg hr<SUP>-1</SUP>의 수소를 37%의 효율로 생산한다. 이 결과를 토대로 가장 현실적인 시나리오에 대해 경제적으로 평가하고 BESP (breakeven electricity selling price)를 계산하였는데, ¢10.45 kWh<SUP>-1</SUP>로 기존의 고정 발전 대비 동등 이상의 수준으로 나타났다. In this paper, the commercial feasibility of trigeneration, producing heat, power, and hydrogen (CHHP) and using biogas derived from macroalgae (i.e., seaweed biomass feedstock), are investigated. For this purpose, a commercial scale trigeneration process, consisting of three MW solid oxide fuel cells (SOFCs), gas turbine, and organic Rankine cycle, is designed conceptually and simulated using Aspen plus, a commercial process simulator. To produce hydrogen, a solid oxide fuel cell system is re-designed by the removal of after-burner and the addition of a water-gas shift reactor. The cost of each unit operation equipment in the process is estimated through the calculated heat and mass balances from simulation, with the techno-economic analysis following through. The designed CHHP process produces 2.3 MW of net power and 50kg hr<SUP>-1</SUP> of hydrogen with an efficiency of 37% using 2 ton hr<SUP>-1</SUP> of biogas from 3.47 ton hr<SUP>-1</SUP> (dry basis) of brown algae as feedstock. Based on these results, a realistic scenario is evaluated economically and the breakeven electricity selling price (BESP) is calculated. The calculated BESP is ¢10.45 kWh<SUP>-1</SUP>, which is comparable to or better than the conventional power generation. This means that the CHHP process based on SOFC can be a viable alternative when the technical targets on SOFC are reached.

Molecular Descriptor Subset Selection in Theoretical Peptide Quantitative Structure–Retention Relationship Model Development Using Nature-Inspired Optimization Algorithms

Ž,uvela, Petar,Liu, J. Jay,Macur, Katarzyna,Bą,czek, Tomasz American Chemical Society 2015 ANALYTICAL CHEMISTRY - Vol.87 No.19

<P>In this work, performance of five nature-inspired optimization algorithms, genetic algorithm (GA), particle swarm optimization (PSO), artificial bee colony (ABC), firefly algorithm (FA), and flower pollination algorithm (EPA), was compared in molecular descriptor selection for development of quantitative structure retention relationship (QSRR) models for 83 peptides that originate from eight model proteins. The matrix with 423 descriptors was used as input, and QSRR models based on selected descriptors were built using partial least squares (PLS), whereas root mean square error of prediction (RMSEP) was used as a fitness function for their selection. Three performance criteria, prediction accuracy, computational cost, and the number of selected descriptors, were used to evaluate the developed QSRR models. The results show that all five variable selection methods outperform interval PLS (iPLS), sparse PLS (sPLS), and the full PLS model, whereas GA is superior because of its lowest computational cost and higher accuracy (RMSEP of 5.534%) with a smaller number of variables (nine descriptors). The GA-QSRR model was validated initially through Y-randomization. In addition, it was successfully validated with an external testing set out of 102 peptides originating from Bacillus subtilis proteomes (RMSEP of 22.030%). Its applicability domain was defined, from which it was evident that the developed GA-QSRR exhibited strong robustness. All the sources of the model's error were identified, thus allowing for further application of the developed methodology in proteomics.</P>

Comparative Study of NIR-based Prediction Methods for Biomass Weight Loss Profiles

Cho, Hyun-Woo,Liu, J. Jay The Korean Society of Clean Technology 2012 청정기술 Vol.18 No.1

바이오매스가 가진 재생 가능성과 환경적인 장점으로 인해 바이오매스는 바이오에너지와 다른 제품의 주요 원료가 되었다. 바이오매스의 중요 성질을 예측하기 위해 분광학 데이터를 이용하는 연구를 포함한 많은 연구가 수행되었는데 근적외선 분광학은 빠르고 신뢰성 있는 결과를 저비용으로 제공하는 비파괴 방법이기 때문에 널리 사용되었다. 이 연구에서는 서로 다른 여섯가지의 목질계 바이오매스의 근적외선 스펙트럼 데이터를 기반으로 질량 손실 프로파일을 예측하는 다변량 통계기법을 개발하였으며, 상관없는 잡음을 제거하고 근적외선 데이터를 잘 설명하는 파장대역을 선택하기 위해 웨이블릿 분석이 사용되었다. 실제 근적외선 데이터를 가지고 개발된 방법을 예시하였는데 이 때 여러가지 예측모델이 예측 성능을 기준으로 평가되었고 적절한 근적외선 스펙트럼 전처리법의 장점 또한 설명되었다. 웨이블릿으로 압축된 근적외선 스펙트럼을 이용한 부분최소자승법 예측모델이 가장 좋은 성능을 보였으며 개발된 방법은 바이오매스의 빠른 분석에 쉽게 적용될 수 있음 또한 증명되었다. Biomass has become a major feedstock for bioenergy and other bio-based products because of its renewability and environmental benefits. Various researches have been done in the prediction of crucial characteristics of biomass, including the active utilization of spectroscopy data. Near infrared (NIR) spectroscopy has been widely used because of its attractive features: it's non-destructive and cost-effective producing fast and reliable analysis results. This work developed the multivariate statistical scheme for predicting weight loss profiles based on the utilization of NIR spectra data measured for six lignocellulosic biomass types. Wavelet analysis was used as a compression tool to suppress irrelevant noise and to select features or wavelengths that better explain NIR data. The developed scheme was demonstrated using real NIR data sets, in which different prediction models were evaluated in terms of prediction performance. In addition, the benefits of using right pretreatment of NIR spectra were also given. In our case, it turned out that compression of high-dimensional NIR spectra by wavelet and then PLS modeling yielded more reliable prediction results without handling full set of noisy data. This work showed that the developed scheme can be easily applied for rapid analysis of biomass.

Comprehensive feasibility assessment of a poly-generation process integrating fast pyrolysis of <i>S. japonica</i> and the Rankine cycle

Brigljević,, Boris,Liu, Jay J.,Lim, Hankwon Elsevier 2019 APPLIED ENERGY Vol.254 No.-

<P><B>Abstract</B></P> <P>Marine macroalgae or seaweeds are increasingly becoming strong candidates for sustainable biofuel feedstocks of the future. This study features a large-scale process design and comprehensive analysis of an industrial-scale (400,000 tons dry feedstock per year) poly-generation pyrolysis process that utilizes 3rd generation biofuel feedstock, <I>Saccharina japonica</I> brown seaweed, and produces diesel-range hydrocarbon fuel, heat, and power. Process design relied predominately on published experimental data regarding fast pyrolysis of <I>S. japonica</I> in a fixed-bed reactor system, followed by dewatering and catalytic upgrading of the produced biocrude. The design featured acid wash pretreatment for the reduction of mineral content, and subsequently a Rankine power cycle utilizing biochar. The design also considered two distinct cases of on-site hydrogen production and hydrogen purchase. Based on the experimental data, a rigorous steady-state flowsheet model was constructed using Aspen Plus for each design case. The results of comprehensive techno-economic assessment, sensitivity, and Monte Carlo analyses provided insight into capital cost for the process, minimum product selling price, and selling price ranges. Finally, the process is compared with traditional crude oil extraction and processing in terms of significant reductions in CO<SUB>2</SUB> emissions, hence providing strong evidence of its environmental sustainability.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Experiment based, process design of fast pyrolysis of <I>S. japonica</I> brown seaweed. </LI> <LI> Poly-generation process producing diesel-grade fuel, heat, and power. </LI> <LI> Process simulation using with Aspen Plus and specialized biocrude modeling method. </LI> <LI> Features acid wash mineral removal, fixed-bed reactor system, and Rankine power cycle. </LI> <LI> 7–45 times less CO<SUB>2</SUB> emissions compared to conventional crude oil processes. </LI> </UL> </P> <P><B>Graphical abstract</B></P> <P>[DISPLAY OMISSION]</P>

Target-based drug discovery through inversion of quantitative structure-drug-property relationships and molecular simulation: CA IX-sulphonamide complexes

Ž,uvela, Petar,Liu, J. Jay,Yi, Myunggi,Pomastowski, Paweł P.,Sagandykova, Gulyaim,Belka, Mariusz,David, Jonathan,Bą,czek, Tomasz,Szafrań,ski, Krzysztof,Ż,ołnowska, Beata,Sławi TaylorFrancis 2018 Journal of enzyme inhibition and medicinal chemist Vol.33 No.1

<P><B>Abstract</B></P><P>In this work, a target-based drug screening method is proposed exploiting the synergy effect of ligand-based and structure-based computer-assisted drug design. The new method provides great flexibility in drug design and drug candidates with considerably lower risk in an efficient manner. As a model system, 45 sulphonamides (33 training, 12 testing ligands) in complex with carbonic anhydrase IX were used for development of quantitative structure-activity-lipophilicity (property)-relationships (QSPRs). For each ligand, nearly 5,000 molecular descriptors were calculated, while lipophilicity (log<I>k</I><SUB>w</SUB>) and inhibitory activity (log<I>K</I><SUB>i</SUB>) were used as drug properties. Genetic algorithm-partial least squares (GA-PLS) provided a QSPR model with high prediction capability employing only seven molecular descriptors. As a proof-of-concept, optimal drug structure was obtained by inverting the model with respect to reference drug properties. 3509 ligands were ranked accordingly. Top 10 ligands were further validated through molecular docking. Large-scale MD simulations were performed to test the stability of structures of selected ligands obtained through docking complemented with biophysical experiments.</P>