Journal of advanced manufacturing and processing最新文献

{"title":"Stochastic parallel machine scheduling using reinforcement learning","authors":"Juxihong Julaiti,&nbsp;Seog-Chan Oh,&nbsp;Dyutimoy Das,&nbsp;Soundar Kumara","doi":"10.1002/amp2.10119","DOIUrl":"10.1002/amp2.10119","url":null,"abstract":"<p>In a high-mix and low-volume manufacturing facility, heterogeneous jobs introduce frequent reconfiguration of machines which increases the chance of unplanned machine breakdowns. As machines are often nonidentical and their performance degrades over time, it is critical to consider the heterogeneity and non-stationarity of the machines during scheduling. We propose a reinforcement learning-based framework with a novel sampling method to train the agent to schedule heterogeneous jobs on non-stationary unreliable parallel machines to minimize weighted tardiness. The results indicate that the new sampling approach expedites the learning process and the resulting policy significantly outperforms static dispatching rules.</p>","PeriodicalId":87290,"journal":{"name":"Journal of advanced manufacturing and processing","volume":"4 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aiche.onlinelibrary.wiley.com/doi/epdf/10.1002/amp2.10119","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49531942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maximizing margins and optimizing operational conditions for residue fluid catalytic cracking with an artificial intelligence hybrid reaction model","authors":"Eiji Kawai,&nbsp;Hideki Sato,&nbsp;Kazuya Furuichi,&nbsp;Takatsuka Toru,&nbsp;Toshio Yoshioka","doi":"10.1002/amp2.10118","DOIUrl":"10.1002/amp2.10118","url":null,"abstract":"<p>Because of the recent declining demand for gasoline, the key to making refineries competitive is to maximize the yields of propylene and aromatics by converting heavier feedstock into basic petrochemicals through the residue fluid catalytic cracking (RFCC) process. This study presents an artificial intelligence (AI) hybrid reaction model to optimize the catalyst make-up rate and maximize the product yield in a real-time operation by (1) developing a catalyst activity evaluation method, (2) integrating the catalyst to oil (Cat/Oil) ratio to evaluate the reaction performance, and (3) incorporating the yield prediction model into the latest digital technologies. To this end, the catalyst deactivation function, which uses a deep neural network of the basic machine learning method, was added to the past RFCC reaction model. Under actual operational conditions, this study shows that the AI hybrid reaction model using the catalyst deactivation function can minimize catalyst loss and produce an accurate yield prediction as a production planning support tool.</p>","PeriodicalId":87290,"journal":{"name":"Journal of advanced manufacturing and processing","volume":"4 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aiche.onlinelibrary.wiley.com/doi/epdf/10.1002/amp2.10118","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43435528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reaction rate enhancement of three-phase hydrogenation using the Taylor flow reactor","authors":"Takafumi Horie,&nbsp;Kenta Hirai,&nbsp;Norihisa Kumagai,&nbsp;Keita Taniya,&nbsp;Yuichi Ichihashi,&nbsp;Naoto Ohmura,&nbsp;Keigo Matsuda,&nbsp;Hideyuki Matsumoto,&nbsp;Makoto Sakurai,&nbsp;Yoshihide Watabe","doi":"10.1002/amp2.10116","DOIUrl":"10.1002/amp2.10116","url":null,"abstract":"<p>A gas–liquid–solid three-phase reaction was conducted in a Taylor flow reactor to improve the apparent reaction rate by enhancing the mass transfer rate of the gas component to the surface of the solid catalyst through the liquid. Hydrogenation of α-methyl styrene (AMS) was the model reaction. The reactor was an aluminum tube with a length of 300 mm and an inner diameter of 4 mm. A thin alumina layer was formed on the inner wall and palladium was used as the catalyst. Hydrogen and AMS were introduced into a T-joint installed at the upper stream of the reactor to form a gas–liquid Taylor flow. The AMS conversion obtained using the Taylor flow was higher than that obtained without the flow. To examine the effect of the hydrogen absorption promotion by the circulating flow in the AMS slug, the total flow rate of the reactants was varied whereas the length of the gas and liquid slugs was maintained. Although the absorption increased owing to the faster surface renewal, only a slight improvement was observed. Conversely, when the total flow rate was fixed and the ratio of the gas slug length to the liquid slug length was increased, the apparent reaction rate improved significantly. These results indicate that diffusion in the thin liquid film directly toward the solid catalyst on the reactor wall was dominant for enhancing the reaction rate.</p>","PeriodicalId":87290,"journal":{"name":"Journal of advanced manufacturing and processing","volume":"4 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aiche.onlinelibrary.wiley.com/doi/epdf/10.1002/amp2.10116","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41491383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A techno-economic analysis framework for intensified modular systems","authors":"Vitor Gazzaneo,&nbsp;Madelynn Watson,&nbsp;Carlie B. Ramsayer,&nbsp;Zachary A. Kilwein,&nbsp;Victor Alves,&nbsp;Fernando V. Lima","doi":"10.1002/amp2.10115","DOIUrl":"10.1002/amp2.10115","url":null,"abstract":"<p>In this work, a novel systematic techno-economic analysis framework is proposed for costing intensified modular systems. Conventional costing techniques are extended to allow estimation of capital and operating costs of modular units. Economy of learning concepts are included to consider the effect of experience curves on purchase costs. Profitability measures are scaled with respect to production of a chemical of interest for comparison with plants of traditional scale. In the developed framework, a base case scenario is analyzed to identify the relevance of the economy of learning and cost parameters that are yet to be established for modular projects that will be deployed. Then, a sensitivity analysis step is conducted to define changes in relevant variables that benefit the construction of modular systems. In a final step, scenarios in which the modular technology presents break-even and further reduction in cost are identified. A process model for a modular hydrogen unit is developed and used for demonstration of the proposed framework. In this application, process synthesis is carried out, including operability analysis for selection of feasible operating conditions. A comparison with a benchmark conventional steam methane reforming plant shows that the modular hydrogen unit can benefit from the economy of learning. A synthesized flowsheet for a modular steam methane reforming plant is used to map the decrease in natural gas price that must be needed for the plant to break even when compared to traditional technologies. Scenarios in which the natural gas price is low allow break-even cost for both individual hydrogen units and the assembled modular plant. For such break-even cases, the economy of learning must produce a reduction of 40% or less in capital cost when the natural gas price is under 0.02 US$/Sm³. This result suggests that the synthesized modular hydrogen process has potential to be economically feasible under these conditions. The developed tools can thus be used to accelerate the deployment and manufacturing of standardized modular energy systems.</p>","PeriodicalId":87290,"journal":{"name":"Journal of advanced manufacturing and processing","volume":"4 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aiche.onlinelibrary.wiley.com/doi/epdf/10.1002/amp2.10115","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43294064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"In-situ curing of 3D printed freestanding thermosets","authors":"Chongjie Gao,&nbsp;Jingjing Qiu,&nbsp;Shiren Wang","doi":"10.1002/amp2.10114","DOIUrl":"10.1002/amp2.10114","url":null,"abstract":"<p>Direct-ink-writing (DIW) provides a high-efficiency way for thermoset printing while rapid in-situ curing has a significant role in manufacturing rate, quality, performance, and flexibility. In this review, in-situ curing methods that can be integrated into DIW were discussed, including frontal polymerization, electromagnetic heating, photochemistry, electron beam, and resistance heating curing. The in-situ process monitoring and curing kinetic analysis technologies such as differential scanning calorimetry (DSC), Raman spectroscopy, Fourier transform infrared spectroscopy (FT-IR), broadband dielectric spectroscopy (BDS), ultrasonic dynamic mechanical analysis (UDMA), fluorescence spectroscopy, were briefly presented. The working mechanism and features of these characterization measurements are studied. Furthermore, machine learning and other artificial intelligence tools used for the optimization of printing materials, topology design, printing path, and defect detection sensitivity are reviewed. Finally, some future research directions for the DIW and in-situ curing of thermosets are addressed.</p>","PeriodicalId":87290,"journal":{"name":"Journal of advanced manufacturing and processing","volume":"4 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aiche.onlinelibrary.wiley.com/doi/epdf/10.1002/amp2.10114","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47263359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Benchmark study of reinforcement learning in controlling and optimizing batch processes","authors":"Wenbo Zhu,&nbsp;Ivan Castillo,&nbsp;Zhenyu Wang,&nbsp;Ricardo Rendall,&nbsp;Leo H. Chiang,&nbsp;Philippe Hayot,&nbsp;Jose A. Romagnoli","doi":"10.1002/amp2.10113","DOIUrl":"10.1002/amp2.10113","url":null,"abstract":"<p>In this article, multiple reinforcement learning (RL) methods such as value-based, policy-based, and actor-critic algorithms are investigated for typical control tasks found in the chemical industries. Through a critical assessment of these novel techniques, their main advantages are highlighted, but also the challenges that still need to be resolved are discussed. Two batch control tasks are used as benchmarks, namely, production maximization, and setpoint control. Using these testing environments, a direct comparison of different RL approaches is presented, which could guide the algorithm selection in future RL applications for batch process control. Furthermore, the results obtained with a traditional control method, model predictive control (MPC), are shown to provide a baseline for comparison with RL algorithms. The results show that RL has significant applicability in various control tasks and has comparable control performance to traditional methods but with a lower online computational cost. A batch bioreactor simulation and a simulation of an industrial polyol process are used for illustration purposes.</p>","PeriodicalId":87290,"journal":{"name":"Journal of advanced manufacturing and processing","volume":"4 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aiche.onlinelibrary.wiley.com/doi/epdf/10.1002/amp2.10113","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45104311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Biodiesel purification by novel green solvent based on choline chloride: Deep eutectic solvent","authors":"Matheus Romeiro Manoel dos Santos,&nbsp;Joel Gustavo Teleken,&nbsp;Fernanda Tavares,&nbsp;Edson Antonio da Silva","doi":"10.1002/amp2.10111","DOIUrl":"10.1002/amp2.10111","url":null,"abstract":"<p>In the typical biodiesel production process carried out by the wet method, large volumes of effluents are generated. The objective of this work was to evaluate and compare the use of a novel high efficiency deep eutectic solvent (DES), with the conventional solvent (hot water). The intense ionic interactions established with the formation of hydrogen bonds between DES and impurities, especially with OH<span></span> groups, potentiated the use of DES, reducing the levels of moisture, free and total glycerol, and mono, di- and triglycerides, in accordance with the standards EN 14214 and ASTM D6751, and being more efficient than conventional purification in some cases. The use of triethylene glycol in the DES composition reduced the content of triglyceride, a poorly soluble molecule. Therefore, with a simple and efficient technique, this work presents the potential use of a new alternative green solvent, which can help reduce costs for biodiesel purification.</p>","PeriodicalId":87290,"journal":{"name":"Journal of advanced manufacturing and processing","volume":"4 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aiche.onlinelibrary.wiley.com/doi/epdf/10.1002/amp2.10111","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43902679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Methodology to screen vendors for predictive maintenance in the chemical industry","authors":"Birgit Braun,&nbsp;Michael Dessauer,&nbsp;Kaytlin Henderson,&nbsp;You Peng,&nbsp;Mary Beth Seasholtz","doi":"10.1002/amp2.10109","DOIUrl":"10.1002/amp2.10109","url":null,"abstract":"<p>As an industry leader in digitalization and implementation of value-added data-driven methodologies, Dow is executing a structured evaluation of predictive maintenance (PdM) vendor offerings. PdM offers a tailored alternative to scheduled maintenance or run-to-failure operations, but the identification of suitable solutions offered by third parties is not trivial given the large number of offerings. This paper describes a methodology developed by Dow to deal with the challenge of efficiently screening many vendors with relevant PdM offerings. Prior to the evaluation process, scoring criteria for vendor performance must be identified. For Dow, these included the requirements (1) models can be created and deployed easily, (2) modeled asset health provides information for root causes, (3) the software operates in our preferred IT architecture, (4) confidential data cannot leave the premises, and (5) models have some transparency. The process involves four steps beginning with vendor identification, which explored existing relationships and landscape surveys. Following was the completion of a questionnaire by vendors about the offering. Upon positive completion, a dataset for two reflux pumps was provided for a first demonstration of the tool. The model performance was compared to internal modeling efforts, of which key results are shared in this paper. The last step involved an in-depth evaluation including on-site installation and online deployment of the PdM models, allowing scoring of all categories. What is presented herein is a framework that can be utilized for screening predictive maintenance modeling tools as well as many analytics applications arising in the age of Industry 4.0.</p>","PeriodicalId":87290,"journal":{"name":"Journal of advanced manufacturing and processing","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aiche.onlinelibrary.wiley.com/doi/epdf/10.1002/amp2.10109","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41545521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heat transfer enhancement in fin channels using aeroelastically fluttering reeds","authors":"Sourabh Jha,&nbsp;Ari Glezer,&nbsp;Matthew J. Realff,&nbsp;Miriam E. Blaine,&nbsp;Jiaqi Mai,&nbsp;Arne J. Pearlstein","doi":"10.1002/amp2.10110","DOIUrl":"10.1002/amp2.10110","url":null,"abstract":"<p>Forced convection heat transfer in rectangular channels is enhanced by aeroelastically fluttering thin reeds extending over the channel span. The resulting small-scale vortical motions substantially increase local heat transfer at the channel walls and mixing between the wall thermal boundary layers and the channel's core flow. Mechanisms associated with evolution of these small-scale motions and their thermal effects are experimentally studied in a channel of width <i>W</i>, span , and length . Reed effects on heat transfer are characterized at Reynolds numbers (<i>Re</i>) of 2000, 7000, and 12,000 using embedded thermocouple arrays, and related to small-scale motions by particle image velocimetry and hot-wire anemometry. Reed-induced small-scale motions increase turbulent kinetic energy, increasing the global Nusselt number (by up to 145% at <i>Re</i> = 7000), with enhancement being sustained even when the base flow becomes fully turbulent (<i>Re</i> = 12,000). Enhancement is also demonstrated for fin arrays. Single-reed computations show the effect of reed length on enhancement. Computations with two reeds, one downstream of the trailing edge of the other, predict heat transfer enhancement significantly greater than twice the single-reed result, and point the way to use of a streamwise array of reeds in long channels. A techno-economic analysis for an air-cooled condenser suggests that fluttering reeds can be economically justified for a range of operating conditions.</p>","PeriodicalId":87290,"journal":{"name":"Journal of advanced manufacturing and processing","volume":"4 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aiche.onlinelibrary.wiley.com/doi/epdf/10.1002/amp2.10110","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46154501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Additive manufacturing for adsorption-related applications—A review","authors":"Ana Pereira,&nbsp;Alexandre F. P. Ferreira,&nbsp;Alírio E. Rodrigues,&nbsp;Ana Mafalda Ribeiro,&nbsp;Maria João Regufe","doi":"10.1002/amp2.10108","DOIUrl":"10.1002/amp2.10108","url":null,"abstract":"<p>The effective shaping of adsorbents is essential to guarantee a high-efficiency energetic process in what concerns adsorptive applications. In this way, additive manufacturing is gaining significance in developing structured materials in the field of gas adsorption processes. Additive manufacturing is a promising alternative to the traditional shaping techniques, which possess some drawbacks. This paper aims to review the state-of-art of additive manufacturing technologies in the manufacturing of adsorbent structures. To do so, an overview of the existent shaping techniques is done, followed by a summarized description of the leading existing additive manufacturing technologies. Then, the application of additive manufacturing technologies to the development of adsorbent materials and other materials for chemical engineering-related applications is also reviewed.</p>","PeriodicalId":87290,"journal":{"name":"Journal of advanced manufacturing and processing","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://aiche.onlinelibrary.wiley.com/doi/epdf/10.1002/amp2.10108","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47238571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}